Article

Differential evolution and underwater glider path planning applied to the short-term opportunistic sampling of dynamic mesoscale ocean structures

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

This paper presents an approach where differential evolution is applied to underwater glider path planning. The objective of a glider is to reach a target location and gather research data along its path by propelling itself underwater and returning periodically to the surface. The main hypothesis of this work is that gliders operational capabilities will benefit from improved path planning, especially when dealing with opportunistic short-term missions focused on the sampling of dynamic structures. To model a glider trajectory, we evolve a global underwater glider path based on the local kinematic simulation of an underwater glider, considering the daily and hourly sea currents predictions. The global path is represented by control points where the glider is expected to resurface for communication with a satellite and to receive further navigation instructions. Some well known differential evolution instance algorithms are then assessed and compared on 12 test scenarios using the proposed approach. Finally, a real case glider vessel mission was commanded using this approach.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Another popular evolutionary approach, Differential Evolution (DE) has also been implemented as global path planning due to its features like easy calibration, stochastic nature and randomization along with fast convergence [12]. The DE based trajectory optimization for underwater glider has been achieved by Zamuda and Sosa [13] based on predicted knowledge on sea currents as well as local kinematic model of underwater glider. Such evolutionary algorithms possess advantageous aspects like robustness, adaptability and less computational time while finding out near optimal solution but they may face lack of exploration ability or slow convergence speed due to increase in dimension of given search space [14]. ...
... So, probability of using difference between best and worst fitted vectors (given in Eq. 15) as perturbation factor will be high to enhance diversity in population for avoiding premature convergence. As iteration progresses, P AR e will decrease linearly and probability of choosing perturbation schemes given in Eq. (13) or (14) will be high. In the middle phase of evolution (e < e max ), activation probability of Eq. (14) will be high. ...
... An extensive trial and error analysis has been performed in "Appendix" to find out minimum value of BW e which is required to provide safe three-dimensional navigation. Newly generated solution vector directly depends on the value and sign of BW e as shown in Eq. (13) and (14). So, Apart from value, sign of BW e may affect the direction of search process. ...
Article
Full-text available
The current research work has employed an evolutionary based novel navigational strategy to trace the collision free near optimal path for underwater robot in a three-dimensional scenario. The population based harmony search algorithm has been dynamically adapted and used to search next global best pose for underwater robot while obstacle is identified near about robot’s current pose. Each pose is evaluated based on their respective value for objective function which incorporates features of path length minimization as well as obstacle avoidance. Dynamic adaptation of control parameters and new perturbation schemes for solution vectors of harmony search has been proposed to strengthen both exploitation and randomization ability of present search process in a balanced manner. Such adaptive tuning process has found to be more effective for avoiding early convergence during underwater motion in comparison with performances of other popular variants of Harmony Search. The proposed path planning method has also shown better navigational performance in comparison with improved version of ant colony optimization and heuristic potential field method for avoiding static obstacles of different shape and sizes during underwater motion. Simulation studies and corresponding experimental verification for three-dimensional navigation are performed to check the accuracy, robustness and efficiency of proposed dynamically adaptive harmony search algorithm.
... We average the horizontal flow locally, between successive control adjustment positions. This assumption is reasonable for relatively small changes in depth, since ocean current velocity is dominated by its horizontal components by several orders of magnitude [7,8]. Change in depth is typically limited to a few hundred metres, either by physical constraints of the glider itself or by applications that require surveying within a given depth range. ...
... A large portion of existing work considers a 2D oceanic flow either using surface currents [24,27] or implicitly using a depth-average current [21,28,29]. The few that do plan in 3D workspace either model the glider with simple kinematics and a directly controllable turning rate [7], or do not account for flow fields [30,31]. ...
... We express the flow velocity v c (x) in state space with the non-velocity dimensions set to zero. We consider the vertical flow w c to be zero, in line with common practice [7,24]. The glider gains forward velocity by shifting its centre of mass and pumping water in or out from a ballast tank to change its buoyancy. ...
Preprint
Full-text available
Autonomous underwater gliders use buoyancy control to achieve forward propulsion via a sawtooth-like, rise-and-fall trajectory. Because gliders are slow-moving relative to ocean currents, glider control must consider the effect of oceanic flows. In previous work, we proposed a method to control underwater vehicles in the (horizontal) plane by describing such oceanic flows in terms of streamlines, which are the level sets of stream functions. However, the general analytical form of streamlines in 3D is unknown. In this paper, we show how streamline control can be used in 3D environments by assuming a 2.5D model of ocean currents. We provide an efficient algorithm that acts as a steering function for a single rise or dive component of the glider's sawtooth trajectory, integrate this algorithm within a sampling-based motion planning framework to support long-distance path planning, and provide several examples in simulation in comparison with a baseline method. The key to our method's computational efficiency is an elegant dimensionality reduction to a 1D control region. Streamline-based control can be integrated within various sampling-based frameworks and allows for online planning for gliders in complicated oceanic flows.
... [13] Such a mission is also influenced to a large extent by the remote sensing for forecasting weather models' outcomes used to predict spatial currents in deep sea, further limiting the available time for accurate run-time decisions by the pilot, who needs to re-test several possible mission scenarios in a short time, usually a few minutes. [12,14,15]. ...
... An algorithm for path optimization considering the ocean currents' model predictions, vessel dynamics, and limited communication, yields potential way-points for the vessel based on the most probable scenario; this is specially useful for short term opportunistic missions where no reactive control is possible, and producing a new expert system joining optimization and UGPP. [12][13][14][15] In the perspective of optimization algorithms, the set of papers [12][13][14][15] introduce also novel ways of benchmarking evolutionary algorithms by assessing operational appropriateness of the optimization algorithms compared in terms of fitness budget planning, convergence quality, and obtained solutions. Furthermore, improvements of some algorithms are also proposed along, in order to more widely include the benchmarking over well known terminologies of heuristic stochastic optimizers. ...
... An algorithm for path optimization considering the ocean currents' model predictions, vessel dynamics, and limited communication, yields potential way-points for the vessel based on the most probable scenario; this is specially useful for short term opportunistic missions where no reactive control is possible, and producing a new expert system joining optimization and UGPP. [12][13][14][15] In the perspective of optimization algorithms, the set of papers [12][13][14][15] introduce also novel ways of benchmarking evolutionary algorithms by assessing operational appropriateness of the optimization algorithms compared in terms of fitness budget planning, convergence quality, and obtained solutions. Furthermore, improvements of some algorithms are also proposed along, in order to more widely include the benchmarking over well known terminologies of heuristic stochastic optimizers. ...
Conference Paper
The real-world implementation of Underwater Glider Path Planning (UGPP) over the dynamic and changing environment in deep ocean waters requires complex mission planning under very high uncertainties. Such a mission is also influenced to a large extent by remote sensing for forecasting weather models outcomes used to predict spatial currents in deep sea, further limiting the available time for accurate run-time decisions by the pilot, who needs to re-test several possible mission scenarios in a short time, usually a few minutes. Hence, this paper presents the recently proposed UGPP mission scenarios' optimization with a recently well performing algorithm for continuous numerical optimization, Success-History Based Adaptive Differential Evolution Algorithm (SHADE) including Linear population size reduction (L-SHADE). An algorithm for path optimization considering the ocean currents' model predictions, vessel dynamics, and limited communication, yields potential way-points for the vessel based on the most probable scenario; this is especially useful for short-term opportunistic missions where no reactive control is possible. The newly obtained results with L-SHADE outperformed existing literature results for the UGPP benchmark scenarios. Thereby, this new application of Evolutionary Algorithms to UGPP contributes significantly to the capacity of the decision-makers when they use the improved UGPP expert system yielding better trajectories.
... Zhang et al. [88] defined the path of AUVs as a series of points in the problem domain. The problem domain has been divided into parallel sub-domains. ...
... Individual component [88] predictable underwater work space as a "multi-objective optimization problem". He proposed a "real-time" PP algorithm by integrating PSO with "waypoint guidance". ...
... •Intelligent system that achieves collision avoidance •Deals with inaccuracy and uncertainty with low computational cost •Somehow depends on type of AUVs involved Unpredictable Evolutionary algorithms [80][81][82][83][84][85][86][87][88][89] [114][115][116] Time optimal Achieved Low ...
Article
Full-text available
The underwater path planning problem deals with finding an optimal or sub-optimal route between an origin point and a termination point in marine environments. The underwater environment is still considered as a great challenge for the path planning of autonomous underwater vehicles (AUVs) because of its hostile and dynamic nature. The major constraints for path planning are limited data transmission capability, power and sensing technology available for underwater operations. The sea environment is subjected to a large set of challenging factors classified as atmospheric, coastal and gravitational. Based on whether the impact of these factors can be approximated or not, the underwater environment can be characterized as predictable and unpredictable respectively. The classical path planning algorithms based on artificial intelligence assume that environmental conditions are known apriori to the path planner. But the current path planning algorithms involve continual interaction with the environment considering the environment as dynamic and its effect cannot be predicted. Path planning is necessary for many applications involving AUVs. These are based upon planning safety routes with minimum energy cost and computation overheads. This review is intended to summarize various path planning strategies for AUVs on the basis of characterization of underwater environments as predictable and unpredictable. The algorithms employed in path planning of single AUV and multiple AUVs are reviewed in the light of predictable and unpredictable environments.
... We average the horizontal flow locally, between successive control adjustment positions. This assumption is reasonable for relatively small changes in depth, since ocean current velocity is dominated by its horizontal components by several orders of magnitude [7,8]. Change in depth is typically limited to a few hundred metres, either by physical constraints of the glider itself or by applications that require surveying within a given depth range. ...
... A large portion of existing work considers a 2D oceanic flow either using surface currents [24,27] or implicitly using a depth-average current [21,28,29]. The few that do plan in 3D workspace either model the glider with simple kinematics and a directly controllable turning rate [7], or do not account for flow fields [30,31]. ...
... We express the flow velocity v c (x) in state space with the non-velocity dimensions set to zero. We consider the vertical flow w c to be zero, in line with common practice [7,24]. The glider gains forward velocity by shifting its centre of mass and pumping water in or out from a ballast tank to change its buoyancy. ...
... Most recently, Zhang and Duan 17 have combined DE with improved version of level comparison technique for planning of UAV's global path in 3D environment. DE-based trajectory optimization for underwater glider has been achieved by Zamuda and Sosa 18 based on the predicted knowledge on sea currents as well as local kinematic model of underwater glider. ...
... As such, there is no systematic way of determining value of control parameters (F i and CR i ) and their optimal values are also typically problem-specific. After completion of each iteration, acceptance rate of trial vectors will be estimated in equation (18). If it is lower than threshold, F max and CR min will be employed for next iteration to provide enough exploration (equation (21)). ...
This article focuses on the navigational control of underwater mobile robot. Differential evolution approach has been used to navigate the underwater robot from source to destination while avoiding various types of obstacles. Differential evolution algorithm has been employed to find out the robot’s global best pose among a set of possible solutions based on the fitness value with respect to the current sensory data about obstacles and target. Such evolutionary computation scheme can provide desirable convergence, diversity and also robustness depending on proper selection and adaptive tuning of parameters. Self-learning ability of the parameters in the path planning algorithm is crucial to deal with nonlinearities and ambiguities of hydrodynamics as created by high-frequency oscillations during underwater motion. A sequence of intermediate positions chosen by proposed dynamic differential evolution algorithm between start and goal points can be defined as a near-optimum path for underwater robot. During navigation of the robot, the path smoothness and clearance from obstacles and computational time are also considered for performance evaluation of implemented algorithm. The feasibility of the proposed underwater motion planning approach has been authenticated through the simulation and experimental results.
... Path planning for rendezvous concept should be optimized in order to satisfy the objectives of the operation. One objective of the rendezvous idea is to accelerate accessing of data collected by the underwater gliders, it may be desirable to plan trajectories for underwater glider such that it can complete rendezvous as fast as possible [10,11]. Recognizing the energy limitations of underwater gliders, another main objective is instead to perform each rendezvous using the minimal possible energy [12,13]. ...
... The GA-based path planner is applied to generate the trajectory with minimal energy consumption in the motion process. In this case, the initial size of population is S p = [10,20,50,100,200]. Figure 3 presents the monitoring of energy consumption and standard deviation of best individual in each iteration. ...
Article
Full-text available
In this paper, a path planning system is proposed for optimal rendezvous of multiple underwater gliders in three-dimensional (3D) space. Inspired by the Dubins Paths consisting of straight lines and circular arcs, this paper presents the first attempt to extend the 3D Dubins curve to accommodate the characteristic glider motions include upwards and downwards straight glides in a sawtooth pattern and gliding in a vertical spiral. This modified 3D Dubins scheme is combined with genetic algorithm (GA), together with a rendezvous position selection scheme to find rendezvous trajectories for multiple gliders with minimal energy consumption over all participating vehicles. The properties and capabilities of the proposed path planning methodology are illustrated for several rendezvous mission scenarios. First, a simple application was performed for a single glider to rendezvous with a fix dock. Simulation results show the proposed planner is able to obtain more optimized trajectories when compared with the typical Dubins trajectory with nominal velocity. Additional representative simulations were run to analyse the performance of this path planner for multiple gliders rendezvous. The results demonstrate that the proposed path planner identifies the optimal rendezvous location and generates the corresponding rendezvous trajectories for multiple gliders that ensures they reach their destination with optimized energy consumption.
... DE has also been used for learning and intelligence accumulation approaches optimization, like [16], [17]. DE has also been applied in the robotics and autonomous systems class of applied soft computing [18]. Joshi et al. [19] used DE to fuse multi-sensor data in building intelligent robotic systems. ...
... The UGPP was already addressed for mesoscale eddy sampling in [18], where several computational intelligence algorithms for optimization were compared and showing, that 1) DE was suitable for UGPP optimization and 2) suggesting especially well performing DE for UGPP. In that approach, some interesting trajectories nearby islands were presented, and the land area had already created some sort of constraints for adhering, i.e. the approach allowed for certain land constraints. ...
... DE is relatively simple to implement and was demonstrated to be very effective on a large number of cases. In the past few decades, DE has been successfully used in many real-world applications, such as space trajectory design [8][9][10], hydrothermal optimization [11], underwater glider path planning [12], and vehicle routing problem [13]. ...
... if NFES < 0.2 × Max_NFEs then (12) Using DE/rand/1/bin to generate (13) else (14) Using DE/rand/1/exp to generate (15) end if (16) Evaluate the trial vector . NFEs = NFEs + 1 (17) if is better than then ...
Article
Full-text available
Memetic algorithms with an appropriate trade-off between the exploration and exploitation can obtain very good results in continuous optimization. In this paper, we present an improved memetic differential evolution algorithm for solving global optimization problems. The proposed approach, called memetic DE (MDE), hybridizes differential evolution (DE) with a local search (LS) operator and periodic reinitialization to balance the exploration and exploitation. A new contraction criterion, which is based on the improved maximum distance in objective space, is proposed to decide when the local search starts. The proposed algorithm is compared with six well-known evolutionary algorithms on twenty-one benchmark functions, and the experimental results are analyzed with two kinds of nonparametric statistical tests. Moreover, sensitivity analyses for parameters in MDE are also made. Experimental results have demonstrated the competitive performance of the proposed method with respect to the six compared algorithms.
... It was first proposed by Storn and Price [20] to solve global numerical optimization problems over continuous search spaces. It is a simple yet powerful evolutionary algorithm and exhibits excellent capability in solving a variety of numerical and real-world optimization problems, such as space trajectory design [21][22][23][24][25], hydrothermal optimization [26], underwater glider path planning [27], vehicle routing problem [28,29], short-term optimal hydrothermal scheduling [30], satellite scheduling [31,32], and satellite image enhancement [33]. 2 Computational Intelligence and Neuroscience ...
... (2) e investigations in [21][22][23][24][25][26][27][28][29][30][31][32][33] indicate that DE has been successfully used in a variety of domains. However, the use of DE for the weight parameters determination of ILAIS has not been reported. ...
Article
Full-text available
Information literacy assessment is extremely important for the evaluation of the information literacy skills of college students. Intelligent optimization technique is an effective strategy to optimize the weight parameters of the information literacy assessment index system (ILAIS). In this paper, a new version of differential evolution algorithm (DE), named hybrid differential evolution with model-based reinitialization (HDEMR), is proposed to accurately fit the weight parameters of ILAIS. The main contributions of this paper are as follows: firstly, an improved contraction criterion which is based on the population entropy in objective space and the maximum distance in decision space is employed to decide when the local search starts. Secondly, a modified model-based population reinitialization strategy is designed to enhance the global search ability of HDEMR to handle complex problems. Two types of experiments are designed to assess the performance of HDEMR. In the first type of experiments, HDEMR is tested and compared with seven well-known DE variants on CEC2005 and CEC2014 benchmark functions. In the second type of experiments, HDEMR is compared with the well-known and widely used deterministic algorithm DIRECT on GKLS test classes. The experimental results demonstrate the effectiveness of HDEMR for global numerical optimization and show better performance. Furthermore, HDEMR is applied to optimize the weight parameters of ILAIS at China University of Geosciences (CUG), and satisfactory results are obtained.
... They also concluded that vehicles that can change their displacement speeds can reach the programmable locations by using favourable currents, saving energy for crossing areas with unfavourable conditions. UGPP challenge has also been tackled using evolutionary techniques, like in Zamuda et al. works [13,14], including eddy sampling applications [15]. ...
... This simulator has been adapted from a Matlab version that was used in previous works [13][14][15]. It has been redesigned to be able to respond to the much higher computational demands the present work requires; however, exhaustive testing has been performed in order to guarantee that both simulators produce the same results under the same input conditions. ...
Conference Paper
The Macaronesia is a vast area playing a key role in the East boundary of the Central North-Atlantic Ocean- circulation system. Despite a significant research activity in ocean monitoring for decades using a wide range of observing systems and methodologies, the area is still under-sampled, mainly due access and coverage constrains, as well as the observation sustainability. Ocean gliders offer a new approach in terms of capacity and sustainability, allowing undertake ocean- monitoring in spatiotemporal scales hitherto unavailable. The present work shows preliminary results from the latest mission with buoyancy-driven and surface ocean gliders in the area, whose main goal focuses on to improve and expand ocean observation capabilities strengthening glider endurance lines between archipelagos, as part of the global ocean-observation strategy conducted by the Marine & Maritime Network (R3M), as contributing party aligned with the European and international efforts in the North Atlantic basin.
... They also concluded that vehicles that can change their displacement speeds can reach the programmable locations by using favourable currents, saving energy for crossing areas with unfavourable conditions. UGPP challenge has also been tackled using evolutionary techniques, like in Zamuda et al. works [13,14], including eddy sampling applications [15]. ...
... This simulator has been adapted from a Matlab version that was used in previous works [13][14][15]. It has been redesigned to be able to respond to the much higher computational demands the present work requires; however, exhaustive testing has been performed in order to guarantee that both simulators produce the same results under the same input conditions. ...
Article
Underwater gliders are energy-efficient vehicles that rely on changes in buoyancy in order to convert up and down movement into forward displacement. These vehicles are conceived as multi-sensor platforms, and can be used to collect ocean data for long periods in wide range areas. This endurance is achieved at the cost of low speed, which requires extensive planning to ensure vehicle safety and mission success, particularly when dealing with strong ocean currents. As gliders are often involved on missions that pursue multiple objectives (track events, reach a target point, avoid obstacles, sample specified areas, save energy), path planning requires a way to deal with several constraints at the same time; this makes glider path planning a multi-objective (MO) optimization problem. In this work, we analyse the usage of the non-dominated sorting genetic algorithm II (NSGA-II) to tackle a MO glider path planning application on a complex environment integrating 3D and time varying ocean currents. Multiple experiments using a glider kinematic simulator coupled with NSGA-II, combining different control parameters were carried out, to find the best parameter configuration that provided suitable paths for the desired mission. Ultimately, the system described in this work was able to optimize multi-objective trajectories, providing non dominated solutions. Such a planning tool could be of great interest in real mission planning, to assist glider pilots in selecting the most convenient paths for the vehicle, taking into account ocean forecasts and particular characteristics of the deployment location.
... Todas estas interrelaciones dificultan la comprensión y la predicción de la respuesta dinámica de tales sistemas. Los modelos numéricos y físicos existentes están diseñados para estudiar fases particulares de las operaciones, pero ninguno cubre todo el proceso ni incluye la interacción humana [1][2] [3]. Los cambios en la distribución de la carga, el control del lastrado, las restricciones de las amarras o del entorno físico están relacionados con las decisiones tomadas por el operador humano. ...
... El objetivo principal de la simulación es definir y ampliar los umbrales operativos para permitir una explotación segura y mejorada de la infraestructura. La recogida de datos de campo y criterios de operación segura, se realizaron varias campañas de medición, desde febrero de 2011, para poder diseñar la configuración experimental de la simulación [3]. Para caracterizar la dinámica del cajón, se emplearon acelerómetros, giróscopos y sistemas de monitorización de movimiento por video imagen. ...
Article
Floating structures are widely used in Marine Civil Engineering constructions, offshore and port operations. Safe operation of those structures requires sensing, monitoring and control systems able to deal not only with the physical parameters that affect to the system behaviour, but also with others parameters related to human interaction, since they are frequently manually operated. Any failure in these operations has a very high economic impact, so detailed previous studies and simulations are needed. In this paper, it has been developed a new methodology and an instrumental system for floating structures response analysis, scalable for field and laboratory. This new approach conjugates control, monitoring and wireless communication systems in a real time basis, offering the possibility to register and simulate all the parameters involved in operations with floating structures, including human interaction. The system developed is modular. An actual implementation of the system and positive results of the tests conducted are shown.
... The impact of ocean currents is perceived as highly relevant for slow-speed vehicles, such as Autonomous Underwater Vehicles (AUVs) or Underwater Gliders (UG). Zamuda and Sosa (2014) employ Differential Evolution (DE), an evolutionary 15 algorithm, for UG path planning in the area of Gran Canaria island. They demonstrate the superior performance of DE with respect to state-of-the-art genetic algorithms and compare the fitness of several variants of DE. ...
... At the present level of approximation, such adjustment is instantaneous (as no second derivatives of 30 x appear in Eq. 1) and independent of vessel displacement (no vehicle mass in Eq. 1). Also Bijlsma (2010) and Techy (2011) in their optimal control methods and Zamuda and Sosa (2014), as a kinematic basis of an evolutionary approach for describing gliders' motion, make the assumption of linear superposition of speeds. Fossen (2012, Eq.26), in a context of vessel motion control, defines STW or relative speed through linear composition of SOG and current velocity. ...
Article
Full-text available
VISIR-I.b, the latest development of the ship routing model published in Mannarini et al. (2016a), is here presented. The new model version targets large ocean-going vessels by accounting for both waves and ocean currents. In order to effectively use currents in a graph-search method, new equations are derived and validated versus analytical benchmarks. A case study is computed in the Atlantic Ocean, on a route from the Chesapeake Bay to the Mediterranean Sea and vice versa. Ocean analysis fields from data-assimilative models (for both ocean state and hydrodynamics) are employed. The impact of waves and ocean currents on transatlantic crossings is assessed through mapping of the spatial variability of the routes, analysis of their kinematics, distribution of the optimal voyage duration vs. its length, and impact on the Energy Efficiency Operational Indicator of the International Maritime Organization. It is distinguished between sailing with or against the main ocean current. The seasonal dependence of the savings is evaluated, indicating, for the featured case study, larger savings during the summer crossings and larger intra-monthly variability in winter. The monthly-mean savings sum up to values between 3 and 12 %, while the contribution of ocean currents is between 1 and 4 %. Also, several other ocean routes are considered, providing a pan-Atlantic scenario assessment of the potential gains in energy efficiency from optimal tracks and linking them to regional meteo-oceanographic features.
... Most path planning algorithms aim to design optimal path minimizing certain cost, for example, those associated with engineering or flight characteristics (battery life, travel time) or scientific value (e.g., distance relative to other assets or spacing of relevant processes). Algorithms that have been applied to AUV optimal path planning include: 1) graph-based methods such as the A* method (Rhoads et al., 2012;Pereira et al., 2013;Kularatne et al., 2017Kularatne et al., , 2018 and the Sliding Wavefront Expansion (SWE) (Soulignac, 2011); 2) sampling-based methods like the Rapidly exploring Random Trees (RRTs) (Kuffner and LaValle, 2000;Cui et al., 2015), RRT* (Karaman and Frazzoli, 2011) and informed RRT* (Gammell et al., 2018); 3) methods that approximate the solution of HJ (Hamilton-Jacobi) equations, such as the Level Set Method (LSM) (Subramani and Lermusiaux, 2016;Lolla et al., 2014), and 4) the evolutionary algorithms, including the particle swarm optimization methods (Roberge et al., 2012;Zeng et al., 2014), and the differential evolution methods (Zamuda and Sosa, 2014;Zamuda et al., 2016). See (Zamuda and Sosa, 2019;Zeng et al., 2015;Panda et al., 2020) for a comprehensive review on the existing AUV path planning methods. ...
... Assumption 2.3: We assume the flow field is time-invariant throughout the deployment. Remark 2.3: Even though there are existing work that considers the time-variant flow field in solving the AUV planning problem, such as (Eichhorn, 2013;Lolla et al., 2014;Zamuda and Sosa, 2014), we make this assumption due to the patterns of the flow field in this domain. In the domain of interest considered in this paper, which is near Cape Hatteras, NC, the current field is driven by a combination and interaction of Gulf Stream, wind, and buoyancy forcing (Savidge et al., 2013a, Savidge et al., 2013b. ...
Article
Full-text available
A bounded cost path planning method is developed for underwater vehicles assisted by a data-driven flow modeling method. The modeled flow field is partitioned as a set of cells of piece-wise constant flow speed. A flow partition algorithm and a parameter estimation algorithm are proposed to learn the flow field structure and parameters with justified convergence. A bounded cost path planning algorithm is developed taking advantage of the partitioned flow model. An extended potential search method is proposed to determine the sequence of partitions that the optimal path crosses. The optimal path within each partition is then determined by solving a constrained optimization problem. Theoretical justification is provided for the proposed extended potential search method generating the optimal solution. The path planned has the highest probability to satisfy the bounded cost constraint. The performance of the algorithms is demonstrated with experimental and simulation results, which show that the proposed method is more computationally efficient than some of the existing methods.
... This task is quite tedious if performed manually; furthermore, a manually generated path may not stay close to a straight line relative to the eddy center (Martin, Lee, Eriksen, Ladd, & Kachel, 2009). For convenience, some field experiments for sampling eddies with underwater gliders have been executed based on a predefined, fixed sampling path by assuming that the eddy region is still or moving slowly (Bouffard et al., 2012;Shu, Xiu, Xue, Yao, & Yu, 2016;Zamuda, Hernández Sosa, & Adler, 2016;Zamuda & Sosa, 2014). Prediction of the movement of eddy center has been achieved using the constant velocity (CV) motion model and the Kalman filter (Yi, Du, Liang, & Zhou, 2017;Zhao, Zhou, Yu, Zhang & Huang, 2016), but the model parameters are not identified from historical data in these works. ...
... The Still model treats eddy center as static in one day before new satellite data is available. This model was used for eddy tracking by many researchers (Bouffard et al., 2012;Shu et al., 2016;Zamuda et al., 2016;Zamuda & Sosa, 2014). This model in not very accurate, but due to its popularity, it is compared with the models used in this paper. ...
Article
A heading angle control method is proposed for controlling underwater gliders to follow a straight line sampling path relative to the center of a dynamically moving mesoscale eddy. The constant velocity and constant acceleration kinematic models are employed as motion models of eddy center movements. The model parameters are identified from historical data of eddy tracks. A Kalman filter is developed based on the models and real-time satellite imaging data to estimate and predict the movement of eddy centers. Performance of the two modeling approaches are compared based on historical data, results show that the constant velocity model is preferred for eddy movement prediction when used for glider heading control. Both simulation and field experiments confirm that underwater gliders under the heading control, when used with the Kalman filter, are able to follow the sampling path autonomously with acceptable level of tracking error.
... When underwater glider is used for observing the ocean phenomenon of a fixed point, we hope the position that the glider resurfaces is accurate enough. For the path planning problem mentioned by Zamuda et al. 35,36 and Lucas et al., 37 it is also significant to ensure the position accuracy that the glider resurfaces. In view of this, the position accuracy that the glider resurfaces and the energy utilization rate are two important performance metrics for underwater glider. ...
... When underwater glider is used for observing the ocean phenomenon of a fixed point, we hope the position that the glider resurfaces is accurate enough. For the path planning problem mentioned by Zamuda et al. 35,36 and Lucas et al., 37 it is also significant to ensure the position accuracy that the glider resurfaces. Therefore, the position accuracy that the glider resurfaces and the energy utilization rate are two important performance metrics for underwater glider. ...
Article
In actual application, the energy utilization rate of underwater glider directly affects the total voyage range. When underwater glider is used for executing exploration mission for a fixed point, the position that the glider resurfaces should be accurate enough. In this paper, we employ a multi-objective optimization method to determine the control parameters values that can maximize the position accuracy that the glider resurfaces and the energy utilization rate simultaneously. Especially, the optimization of this paper considers the effect of uncertain input errors. The control parameters include the net buoyancy adjustment amount and the movable mass block translation amount. The input errors include the control parameters errors, the motion depth error and the current. Based on the dynamic model of an underwater glider, we propose the calculation model and evaluation flow that are used for analyzing the glider position accuracy and energy utilization rate, considering the effect of uncertain input errors. Besides, a combinatorial experimental design method is proposed to calculate the performance evaluation parameters under different control parameters values. Then the radial basis function neural network is employed to establish the surrogate models of performance evaluation parameters to participate in the optimization calculation, which can improve the optimization efficiency. After optimization calculation based on the non-dominated sorting genetic algorithm II, we obtain a Pareto optimal set consisting of 257 sets of non-dominated solutions. Finally, the selection rule of optimal control parameters values is given, and the optimization results are validated under 3 sets of solutions. This research may be valuable for the improvement of the glider work quality.
... These studies include testing different multiobjective optimization algorithms, as well as studying the impact of key parameters. Such systematic studies have recently illuminated the performance of evolutionary algorithms in underwater path planning [45,46], and we consider them an important step in further studies of inspection path planning. ...
Article
Full-text available
An important open problem in robotic planning is the autonomous generation of 3D inspection paths – that is, planning the best path to move a robot along in order to inspect a target structure. We recently suggested a new method for planning paths allowing the inspection of complex 3D structures, given a triangular mesh model of the structure. The method differs from previous approaches in its emphasis on generating and considering also plans that result in imperfect coverage of the inspection target. In many practical tasks, one would accept imperfections in coverage if this results in a substantially more energy efficient inspection path. The key idea is using a multiobjective evolutionary algorithm to optimize the energy usage and coverage of inspection plans simultaneously – and the result is a set of plans exploring the different ways to balance the two objectives. We here test our method on a set of inspection targets with large variation in size and complexity, and compare its performance with two state-of-the-art methods for complete coverage path planning. The results strengthen our confidence in the ability of our method to generate good inspection plans for different types of targets. The method's advantage is most clearly seen for real-world inspection targets, since traditional complete coverage methods have no good way of generating plans for structures with hidden parts. Multiobjective evolution, by optimizing energy usage and coverage together ensures a good balance between the two – both when 100% coverage is feasible, and when large parts of the object are hidden.
... Further comparison of PSO and GA can be found in [96]. Zamuda et al., [97] also applied a Differential Evolution (DE) based path planner for underwater glider for opportunistic sampling of dynamic mesoscale ocean structures considering dynamic ocean structure. ...
Article
Full-text available
An Autonomous Underwater Vehicle (AUV) should carry out complex tasks in a limited time interval. Since existing AUVs have limited battery capacity and restricted endurance, they should autonomously manage mission time and the resources to perform effective persistent deployment in longer missions. Task assignment requires making decisions subject to resource constraints, while tasks are assigned with costs and/or values that are budgeted in advance. Tasks are distributed in a particular operation zone and mapped by a waypoint covered network. Thus, design an efficient routing-task priority assign framework considering vehicle's availabilities and properties is essential for increasing mission productivity and on-time mission completion. This depends strongly on the order and priority of the tasks that are located between node-like waypoints in an operation network. On the other hand, autonomous operation of AUVs in an unfamiliar dynamic underwater and performing quick response to sudden environmental changes is a complicated process. Water current instabilities can deflect the vehicle to an undesired direction and perturb AUVs safety. The vehicle's robustness to strong environmental variations is extremely crucial for its safe and optimum operations in an uncertain and dynamic environment. To this end, the AUV needs to have a general overview of the environment in top level to perform an autonomous action selection (task selection) and a lower level local motion planner to operate successfully in dealing with continuously changing situations. This research deals with developing a novel reactive control architecture to provide a higher level of decision autonomy for the AUV operation that enables a single vehicle to accomplish multiple tasks in a single mission in the face of periodic disturbances in a turbulent and highly uncertain environment.
... It directly operates on the structure object. There is no limitation for the derivation and function continuity and it has inherent implicit parallelism and excellent global optimization ability (Aleš and José et al, 2014). After repeated iterations, DE preserves the individuals which have been adapted to the environment. ...
Article
Evolutionary computation is now increasingly applied in many fields of scientific research and engineering practices, and more and more people begin to pay close attention to. In this context, based on the theory and application of differential evolution algorithm (DE) and artificial immune algorithm (AIA), this paper makes some related explorations and researches. By summing up the principle and characteristics of DE and AIA, this paper improves the original differential algorithm and the proposed algorithm introduces will be introduced the immune thought of the biological immune system into DE, thus employing previous knowledge to structure immune operator, and not only retaining the best individuals in the colony but also ensuring the diversity of individuals through vaccination and immune selection, so as to avoid the premature convergence of the evolutionary search and improve the convergence speed of the algorithm accordingly. Experimental results show that the designed algorithm in this paper has faster convergence speed and strong global search ability, and can effectively overcome and avoid the premature convergence and data redundancy phenomenon of differential evolution algorithm, and meanwhile, with good scalability and stability, which can be successfully applied to multimodal function optimization problems.
... A typical example of this is when the performance measure values are received from computer simulation (see, e.g., Dębski, 2014a). In such an instance, most classic optimization methods cannot be used (at least not directly) and the optimization process is often based on soft-computing/AI methods (Vasile and Locatelli, 2009;Ceriotti and Vasile, 2010;Pošík et al., 2012;Szłapczyński and Szłapczyńska, 2012;Zamuda and Sosa, 2014;Sun and Wu, 2011;Ćurković et al., 2009;Li and Lü, 2014;Bai et al., 2012;Kojic et al., 2013;Zhou et al., 2011). ...
Article
Full-text available
A new dynamic programming based parallel algorithm adapted to on-board heterogeneous computers for simulation based trajectory optimization is studied in the context of "high-performance sailing". The algorithm uses a new discrete space of continuously differentiable functions called the multi-splines as its search space representation. A basic version of the algorithm is presented in detail (pseudo-code, time and space complexity, search space auto-adaptation properties). Possible extensions of the basic algorithm are also described. The presented experimental results show that contemporary heterogeneous on-board computers can be effectively used for solving simulation based trajectory optimization problems. These computers can be considered micro high performance computing (HPC) platforms—they offer high performance while remaining energy and cost efficient. The simulation based approach can potentially give highly accurate results since the mathematical model that the simulator is built upon may be as complex as required. The approach described is applicable to many trajectory optimization problems due to its black-box represented performance measure and use of OpenCL. The article available at: https://www.amcs.uz.zgora.pl/?action=download&pdf=AMCS_2016_26_2_8.pdf
... A real-time Differential Evolution (DE) based motion planner is designed by MahmoudZadeh et al. [11] to provide a time/battery efficient operation for a single AUV in a dynamic ocean environment. Zamuda et al. [41] also applied a DE-based path planner for an underwater glider used in sampling of dynamic mesoscale ocean structures, where the dynamic ocean structure is also taken into consideration. Later on, another elaborated evolution-based online path planner/re-planner is proposed for AUV path planning and rendezvous problem in an uncertain underwater terrain to ensure AUV's safe deployment and secure docking [2]. ...
Chapter
Full-text available
Autonomous mission management is closely related to the accuracy of the navigation system. Path planning is an essential component in the UV’s development, which determines the vehicle’s level of autonomy in dealing with environmental changes and it is considered as a premise of mission reliability and success Statheros et al. (J Navig 61:129–142, 2008 [1]). One primary concern for autonomy is the advancement of the navigation system, including trajectory/path planning, to be robust to the extreme environmental variability.
... The DE algorithm (Price and Storn 1997) is improved version of GA and uses similar operators of selection, crossover and mutation that is very suitable for synthetic natured problems like path planning (Zamuda and Sosa 2014;M.Zadeh et al. 2016c). The DE produces better solutions and faster process due to use of real coding of floating point numbers in presenting problem parameters. ...
Article
Full-text available
Providing a higher level of decision autonomy is a true challenge in development of today AUVs and promotes a single vehicle to accomplish multiple tasks in a single mission as well as accompanying prompt changes of a turbulent and highly uncertain environment, which has not been completely attained yet. The proceeding approach builds on recent researches toward constructing a comprehensive structure for AUV mission planning, routing, task-time managing and synchronic online motion planning adaptive to sudden changes of the time variant environment. Respectively, an "Autonomous Reactive Mission Scheduling and Path Planning" (ARMSP) architecture is constructed in this paper and a bunch of evolutionary algorithms are employed by different layers of the proposed control architecture to investigate the efficiency of the structure toward handling addressed objectives and prove stability of its performance in real-time mission task-time-threat management regardless of the applied metaheuristic algorithm. Static current map data, uncertain dynamic-static obstacles, vehicles Kino-dynamic constraints are taken into account and online path re-planning strategy is adopted to consider local variations of the environment so that a small computational load is devoted for re-planning procedure since the upper layer, which is responsible for mission scheduling, renders an overview of the operation area that AUV should fly thru. Numerical simulations for analysis of different situations of the real-world environment is accomplished separately for each layer and also for the entire ARMSP model at the end. Performance and stability of the model is investigated thorough employing metaheuristic algorithms toward furnishing the stated mission goals.
... Two points need to be clarified here. First, both ocean and atmospheric models only provide data on flow and wind velocities in the horizontal direction and combined with studies in the existing literature, the velocity components of the wind and flow fields in the vertical direction are very small compared to the velocity components in the horizontal direction _ and are very small in the order of magnitude and therefore negligible [49]. Second, the forecast-based air-sea models are mainly for studies of large sea This work has been submitted to the IEEE for possible publication. ...
Preprint
This paper presents a novel Rapidly-exploring Adaptive Sampling Tree (RAST) algorithm for the adaptive sampling mission of a hybrid aerial underwater vehicle (HAUV) in an air-sea 3D environment. This algorithm innovatively combines the tournament-based point selection sampling strategy, the information heuristic search process and the framework of Rapidly-exploring Random Tree (RRT) algorithm. Hence can guide the vehicle to the region of interest to scientists for sampling and generate a collision-free path for maximizing information collection by the HAUV under the constraints of environmental effects of currents or wind and limited budget. The simulation results show that the fast search adaptive sampling tree algorithm has higher optimization performance, faster solution speed and better stability than the Rapidly-exploring Information Gathering Tree (RIGT) algorithm and the particle swarm optimization (PSO) algorithm.
... To apply DE most efficiently on a new challenge for parameter estimation like the discussed simulation in this chapter, one of effective DE variants should be taken and adapted for the domain challenge at hand, following recent experiences on DE applications in e.g. image processing [143], energy scheduling [145], and autonomous vehicle navigation [147,148]. ...
Chapter
Full-text available
The faithful reproduction and accurate prediction of the phenotypes and emergent behaviors of complex cellular systems are among the most challenging goals in Systems Biology. Although mathematical models that describe the interactions among all biochemical processes in a cell are theoretically feasible, their simulation is generally hard because of a variety of reasons. For instance, many quantitative data (e.g., kinetic rates) are usually not available, a problem that hinders the execution of simulation algorithms as long as some parameter estimation methods are used. Though, even with a candidate parameterization, the simulation of mechanistic models could be challenging due to the extreme computational effort required. In this context, model reduction techniques and High-Performance Computing infrastructures could be leveraged to mitigate these issues. In addition, as cellular processes are characterized by multiple scales of temporal and spatial organization, novel hybrid simula-tors able to harmonize different modeling approaches (e.g., logic-based, constraint-based, continuous deterministic, discrete stochastic, spatial) should be designed. This chapter describes a putative unified approach to tackle these challenging tasks, hopefully paving the way to the definition of large-scale comprehensive models that aim at the comprehension of the cell behavior by means of computational tools.
... The impact of ocean currents significantly affects slowspeed vehicles, such as autonomous underwater vehicles (AUVs) or underwater gliders. Zamuda and Sosa (2014) use differential evolution (DE), an evolutionary algorithm, for glider path planning in the area of the Canary Islands. They demonstrate the superior performance of DE with respect to state-of-the-art genetic algorithms and compare the fitness of several variants of DE. ...
Article
Full-text available
The latest development of the ship-routing model published in Mannarini et al. (2016a) is VISIR-1.b, which is presented here. The new version of the model targets large ocean-going vessels by considering both ocean surface gravity waves and currents. To effectively analyse currents in a graph-search method, new equations are derived and validated against an analytical benchmark. A case study in the Atlantic Ocean is presented, focussing on a route from the Chesapeake Bay to the Mediterranean Sea and vice versa. Ocean analysis fields from data-assimilative models (for both ocean state and hydrodynamics) are used. The impact of waves and currents on transatlantic crossings is assessed through mapping of the spatial variability in the tracks, an analysis of their kinematics, and their impact on the Energy Efficiency Operational Indicator (EEOI) of the International Maritime Organization. Sailing with or against the main ocean current is distinguished. The seasonal dependence of the EEOI savings is evaluated, and greater savings with a higher intra-monthly variability during winter crossings are indicated in the case study. The total monthly mean savings are between 2 % and 12 %, while the contribution of ocean currents is between 1 % and 4 %. Several other ocean routes are also considered, providing a pan-Atlantic scenario assessment of the potential gains in energy efficiency from optimal tracks, linking them to regional meteo-oceanographic features.
... For instance, in [6] a GA combined with space partitioning methods is used to find the most optimal path to cover a desired area. The Differential Evolution (DE) algorithm is utilized in [7] to optimize a shortterm sea trajectory for an underwater glide. Another work that proposes an improved constrained DE algorithm is [8], where an optimal feasible route for UAVs is generated. ...
Article
Full-text available
This research presents a novel approach for missions of Coverage Path Planning (CPP) carried out by a UAVs in a 3D environment. These missions are focused on path planning to cover a certain area in an environment in order to carry out tracking, search or rescue tasks. The methodology followed uses an optimization process based on the Differential Evolution (DE) algorithm in combination with the Fast Marching Square (FM2) planner. The DE algorithm evaluates a cost function to determine what the zigzag path with the minimum cost is, according to the steering angle of the zigzag bands. This optimization process allows achieving the most optimal zigzag path in terms of distance traveled by the UAV to cover the whole area. Then, the FM2 method is applied to generate the final path according to the steering angle of the zigzag bands resulting from the DE algorithm. The approach generates a feasible path free from obstacles, keeping a fixed altitude flight over the ground. The flight level, smoothness and safety of the path can be modified by two adjustment parameters included in our approach. Simulated experiments carried out in this work demonstrate that the proposed approach generates the most optimal zigzag path in terms of distance, safety and smoothness to cover a certain whole area, keeping a determined flight level with successful results.
... In [21], genetic algorithm (GA) is utilized to determine an energy efficient path for on an AUV encountering strong time/space varying ocean current field [21] and in [22], an energy efficient path considering time-varying ocean currents is generated by means of particle swarm optimization (PSO) algorithm. Differential evolution (DE) based path planner is applied on an underwater glider to opportunistic sampling of dynamic ocean structures [23,24] and off-line path planning based on quantum-based PSO (QPSO) is offered for path planning of unmanned aerial vehicle [25]. The online version of QPSO-based path planner for dealing with dynamic environment is proposed in [26,27]. ...
Article
Full-text available
In this study, a single autonomous underwater vehicle (AUV) aims to rendezvous with a submerged leader recovery vehicle through a cluttered and variable operating field. The rendezvous problem is transformed into a nonlinear optimal control problem (NOCP) and then numerical solutions are provided. A penalty function method is utilized to combine the boundary conditions, vehicular and environmental constraints with the performance index that is final rendezvous time.Four evolutionary based path planning methods namely particle swarm optimization (PSO), biogeography-based optimization (BBO), differential evolution (DE) and Firefly algorithm (FA) are employed to establish a reactive planner module and provide a numerical solution for the proposed NOCP. The objective is to synthesize and analysis the performance and capability of the mentioned methods for guiding an AUV from loitering point toward the rendezvous place through a comprehensive simulation study.The proposed planner module entails a heuristic for refining the path considering situational awareness of underlying environment, encompassing static and dynamic obstacles overwhelmed in spatiotemporal current vectors.This leads to accommodate the unforeseen changes in the operating field like emergence of unpredicted obstacles or variability of current vector filed and turbulent regions. The simulation results demonstrate the inherent robustness and significant efficiency of the proposed planner in enhancement of the vehicle's autonomy in terms of using current force, coping undesired current disturbance for the desired rendezvous purpose. Advantages and shortcoming of all utilized methods are also presented based on the obtained results.
... Yu et al. [22] and Song et al. [23] derived the energy consumption equations of underwater gliders and optimized the glider motion parameters to minimize energy consumption. Zamuda et al. [24][25][26] proposed the glider path planning method based on the differential evolution algorithm. Liu et al. [27] discovered that the turning direction of the glider spiral motion was related to the wings location. ...
Article
Control parameters errors and current can weaken the motion accuracy of underwater gliders, which will obstruct the achievement of high accuracy exploration missions. To improve the glider motion accuracy more pertinently, it is necessary to identify the key factors that affect the glider motion accuracy. To resolve the above problem, we employ Sobol’ method to analyze the sensitivity of control parameters errors and current parameters to the glider motion accuracy. The control parameters errors include the net buoyancy adjustment amount error, the movable mass block translation amount error and the movable mass block rotation amount error. The current parameters include the current intensity, action depth and direction. First, the dynamic model of an underwater glider is established, and this model considers the effects of hull deformation, water density variation and current simultaneously. Then the dynamic model is validated by experimental data. After the evaluation parameter of motion accuracy is given, the glide motion accuracy is preliminarily analyzed, and then the sensitivity analysis is carried out. In this paper, we calculate the sensitivity coefficients by Monte Carlo method. To reconcile calculation efficiency with calculation accuracy, a convergence rule is proposed to reduce the number of sample points that are used for calculating sensitivity coefficients as much as possible. Besides, based on simulation results of dynamic model, the surrogate models are established to participate in the calculation of sensitivity coefficients, which can improve analysis efficiency further. For two typical motion modes, analysis results identify the key factors affecting the glider motion accuracy and illustrate the form of their effect on the glider motion accuracy. This research may be valuable for the achievement of the glider precision operation.
... Regarding motion optimization of the glider with separate navigational objectives, a lot of excellent research has been carried out: Zamud et al. introduce their work on utilizing the Differential Evolution (DE) algorithm to optimize a series of departure points bearing angles to counteract the effects of ocean currents and make the glider reach the predetermined waypoint accurately [6]. Song et al. construct a precise energy consumption model and gliding range model of the underwater glider; based on the established model, the optimal gliding range of underwater gliders increases 11.97% with an average diving depth of 1000 m [7]. ...
Article
Full-text available
Underwater gliders are prevailing in oceanic observation nowadays for their flexible deployment and low cost. However, the limited onboard energy constrains their application, hence the motion pattern optimization and energy analysis are the key to maximizing the range of the glider while maintaining the acceptable navigation preciseness of the glider. In this work, a Multi-Objective Artificial Bee Colony (MOABC) algorithm is used to solve the constrained hybrid non-convex multi-objective optimization problem about range and accuracy of gliders in combination with specific glider dynamics models. The motion parameters Pareto front that balances the navigational index referring to range and preciseness are obtained, relevant gliding profile motion results are simulated simultaneously, and the results are compared with the conventional gliding patterns to examine the quality of the solution. Comparison shows that, with the utilization of the algorithm, glider voyage performance with respect to endurance and preciseness can be effectively improved.
... At present, the glider path planning problem involves the motion accuracy evaluation of the glider in currents. According to references [43][44][45][46][47] , the path planning problem deals with finding an optimal or sub-optimal route between an origin point and a termination point in marine environments. Therefore, for the path planning problem, the motion accuracy is generally described by the deviation between the actual termination point and the ideal one, and the specific underwater motion trajectory of a single profile has never been paid highly attention to. ...
Article
Energy consumption and motion accuracy are both important performance metrics for underwater gliders, which are closely related to the glider control parameters values. For the above two performance metrics, we study a multi-objective optimization method to determine the control parameters values that make the glider have the better performance. Here the control parameters include the net buoyancy adjustment amount and the movable internal mass block translation amount. The basis of the optimization method is the dynamic model of the glider. Based on the dynamic model established by us, the evaluation parameter of energy utilization rate is deduced, and it reflects the ideal voyage range produced by 1 kJ energy. Besides, the evaluation parameter of motion accuracy is defined by the mean and standard deviation of the glider motion error in uncertain current. Next, the flow, which is used for calculating the above two evaluation parameters under the same set of control parameters values, is proposed. Based on the above flow and the radial basis function neural network, we fit surrogate models to participate in the optimization calculation to improve the efficiency. Here the optimization objectives are to maximize the energy utilization rate and minimize the glider motion error simultaneously. Then, we obtain the Pareto optimal set containing many sets of control parameters values by using the non-dominated sorting genetic algorithm II. Finally, the selection rule of control parameters values is shown by an example. This research can be used for determining the appropriate control parameters values of underwater gliders in actual application.
... In [41] evolution of trees among DE and CMA-ES mechanisms is compared and suspected on the suggestions by Das and Suganthan, that CMA-ES is competitive up to 100 variables, but it is difficult to extend it to higher dimensional problems due mainly to the cost of computing and updating the covariance matrix [13]; Fonlupt et al. [41] conclude that for both regression and artificial ants, CMA-based algorithm performs poorly, compared with a DE-based algorithm, with the same representation of solutions; they attribute the better DE performance to its fundamental differences in behavior and robustness, and CMA-ES lacking elitism. DE variants, CMA-ES, and other similar evolutionary algorithms were recently also compared on a real application problem domain of underwater robotics, where a jDE-like variant outperformed other algorithms [11]. These DE performances give clear implications to consider DE as an optimizer in this paper. ...
Article
The paper concerns parallel methods for Extremal Optimization (EO) applied in processor load balancing in execution of distributed programs. In these methods EO algorithms detect an optimized strategy of tasks migration leading to reduction of program execution time. We use an improved EO algorithm with guided state changes (EO–GS) that provides parallel search for next solution state during solution improvement based on some knowledge of the problem. The search is based on two-step stochastic selection using two fitness functions which account for computation and communication assessment of migration targets. Based on the improved EO–GS approach we propose and evaluate several versions of the parallelization methods of EO algorithms in the context of processor load balancing. Some of them use the crossover operation known in genetic algorithms. The quality of the proposed algorithms is evaluated by experiments with simulated load balancing in execution of distributed programs represented as macro data flow graphs. Load balancing based on so parallelized improved EO provides better convergence of the algorithm, smaller number of task migrations to be done and reduced execution time of applications.
Article
Ocean environmental surveys typically involve multi-area coverage path planning tasks. The most important problem is improving the coverage efficiency of the task. A new path planning method based on Successful History-Based Adaptive Differential Evolution variants with Linear population size reduction(L-SHADE) is presented to solve this problem. The method comprises two parts: the part of sub area coverage path planning and the part of finding the optimized sequence of sub area start points. The key idea is establishing the relationship between the starting point of each sub area and the optimized multi-area path. We implement the method through numbering the possible starting point of sub area path and proposing a computing formula. In addition, the results of L-SHADE mutation process are optimized which make L-SHADE possible to apply in multi-area coverage path planning. This method avoids area discretization and exponential growth of computational quantities, and it is suitable for complex areas as well as multi-area. The simulation results with MATLAB showed the improvement of coverage path planning task execution efficiency. Compared with the method thinking of the sub area as the center of it, our method reduced the multi-area coverage path length by 4%–7%. From the simulations and analysis, we concluded that the method is able to improve the efficiency and stability of multi-area coverage path planning.
Article
This paper presents a differential evolution algorithm that is adapted for the protein folding optimization on a three-dimensional AB off-lattice model. The proposed algorithm is based on a self-adaptive differential evolution that improves the algorithm efficiency and reduces the number of control parameters. A mutation strategy for the fast convergence is used inside the algorithm. A temporal locality is used in order to speed up the algorithm convergence additionally and to find amino-acid conformations with the lowest free energy values. Within this mechanism a new vector is calculated when the trial vector is better than the corresponding vector from the population. This new vector is likely better than the trial vector and this accelerates convergence speed. Because of the fast convergence the algorithm has some chance to be trapped into the local optima. To mitigate this problem the algorithm includes reinitialization. The proposed algorithm was tested on amino-acid sequences that are used frequently in literature. The obtained results show that the proposed algorithm is superior to the algorithms from the literature and the obtained amino-acid sequences have significantly lower free energy values.
Article
Cervical cancer is one of the vital and most frequent cancers, but can be cured effectively if diagnosed in the early stage. This is a novel effort towards effective characterization of cervix lesions from contrast enhanced CT-Scan images to provide a reliable and objective discrimination between benign and malignant lesions. Performance of such classification models mostly depends on features used to represent samples in a training dataset. Selection of optimal feature subset here is NP-hard; where, randomized algorithms do better. In this paper, Grey Wolf Optimizer (GWO), which is a population based meta-heuristic inspired by the leadership hierarchy and hunting mechanism of grey wolves has been utilized for feature selection. The traditional GWO is applicable for continuous single objective optimization problems. Since, feature selection is inherently multi-objective; this paper proposes two different approaches for multi-objective binary GWO algorithms. One is a scalarized approach to multi-objective GWO (MOGWO) and the other is a Non-dominated Sorting based GWO (NSGWO). These are used for wrapper based feature selection that selects optimal textural feature subset for improved classification of cervix lesions. For experiments, contrast enhanced CT-Scan (CECT) images of 62 patients have been used, where all lesions had been recommended for surgical biopsy by specialist. Gray-level co-occurrence matrix based texture features are extracted from two-level decomposition of wavelet coefficients of cervix regions extracted from CECT images. The results of proposed approaches are compared with mostly used meta-heuristics such as genetic algorithm (GA) and firefly algorithm (FA) for multi-objective optimization. With better diversification and intensification, GWO obtains Pareto solutions, which dominate the solutions obtained by GA and FA when assessed on the utilized cervix lesion cases. Cervix lesions are up to 91% accurately classified as benign and malignant with only five features selected by NSGWO. A two-tailed t-test was conducted by hypothesizing the mean F-score obtained by the proposed NSGWO method at significance level = 0.05. This confirms that NSGWO performs significantly better than other methods for the real cervix lesion dataset in hand. Further experiments were conducted on high dimensional microarray gene expression datasets collected online. The results demonstrate that the proposed method performs significantly better than other methods selecting relevant genes for high-dimensional, multi-category cancer diagnosis with an average of 12.82% improvement in F-score value.
Article
This paper explores the execution of planned autonomous underwater vehicle (AUV) missions where opportunities to achieve additional utility can arise during execution. The missions are represented as temporal planning problems, with hard goals and time constraints. Opportunities are soft goals with high utility. The probability distributions for the occurrences of these opportunities are not known, but it is known that they are unlikely, so it is not worth trying to anticipate their occurrence prior to plan execution. However, as they are high utility, it is worth trying to address them dynamically when they are encountered, as long as this can be done without sacrificing the achievement of the hard goals of the problem. We formally characterize the opportunistic planning problem, introduce a novel approach to opportunistic planning, and compare it with an on-board replanning approach in the domain of AUVs performing pillar expection and chain-following tasks.
Conference Paper
The ocean, as vast as it is complex, has a plethora of phenomena that are of legitimate scientific interest, e.g., ocean fronts and Lagrangian Coherent Structures. These coherent ocean features occur from tidal mixing and ocean circulation, and are generally characterized with narrow bands of locally intensive physical gradients with enhanced circulation, biological productivity, and optimal transport phenomena. Spatial extents of these phenomena can be on the order of 10's of km2, and episodic events can last from hours to weeks. These ocean features are 3-dimensional, where to date, most research has focused on examining only their 2-dimensional expression. These coherent features cannot be thoroughly studied through traditional sampling involving random and/or discrete sampling approaches, moreover it is not cost-effective to validate new sampling methodologies in the field. Additionally, operating a single robotic platform in the ocean is hard, and coordinating a team of robots presents challenges in communication on top of dealing with navigation and complex ocean dynamics. To this end, in this paper we present the development and validation of a micro Autonomous Underwater Vehicle for deployment in a laboratory testing tank able to accurately simulate large-scale ocean dynamics. The goal is to provide a laboratory-scale, underwater vehicle for validating and testing algorithms and strategies to sample the 3-dimensional structure that exists in coherent ocean features, e.g., ocean fronts, eddys and Lagrangian Coherent Structures, for the purpose of developing better physical and biological models to aid autonomous ocean research. We provide a detailed description of the vehicle and present multiple results from lab experiments.
Article
Autonomous underwater vehicles (AUVs) operate in the three-dimensional and time-dependent marine environment with strong and dynamic currents. Our goal is to predict the time history of the optimal three-dimensional headings of these vehicles such that they reach the given destination location in the least amount of time, starting from a known initial position. We employ the exact differential equations for time-optimal path planning and develop theory and numerical schemes to accurately predict three-dimensional optimal paths for several classes of marine vehicles, respecting their specific propulsion constraints. We further show that the three-dimensional path planning problem can be reduced to a two-dimensional one if the motion of the vehicle is partially known, e.g. if the vertical component of the motion is forced. This reduces the computational cost. We then apply the developed theory in three-dimensional analytically known flow fields to verify the schemes, benchmark the accuracy, and demonstrate capabilities. Finally, we showcase time-optimal path planning in realistic data-assimilative ocean simulations for the Middle Atlantic Bight region, integrating the primitive-equation of the Multidisciplinary Simulation Estimation and Assimilation System (MSEAS) with the three-dimensional path planning equations for three common marine vehicles, namely propelled AUVs (with unrestricted motion), floats (that only propel vertically), and gliders (that often perform sinusoidal yo-yo motions in vertical planes). These results highlight the effects of dynamic three-dimensional multiscale ocean currents on the optimal paths, including the Gulf Stream, shelfbreak front jet, upper-layer jets, eddies, and wind-driven and tidal currents. They also showcase the need to utilize data-assimilative ocean forecasts for planning efficient autonomous missions, from optimal deployment and pick-up, to monitoring and adaptive data collection.
Article
Astrophysics and Cosmology are entering in a new epoch in which an extremely large volume of data is accessible by the researchers. Consequently, the researchers have to modify their procedures for data analysis to adapt them to this new scenario. This requires the incorporation of new scientific computing resources able to maintain, at least, the present scientific production performance. As part of this increment in the data volume, it should be underlined the number of high-quality galaxy spectra produced by the new instruments. Galaxy spectra are important in Astrophysics because of they encode essential information, such as age and metallicity, of the constituent stellar populations, and, therefore the evolutionary history of the corresponding galaxy. In this work, these galaxy spectra are modeled by using Simple Stellar Populations. This mechanism to model the galaxy spectra allows an in-depth understanding of the present state of the galaxy, but also it allows understanding its past evolution. However, this modeling requires to adequately combine more than one Simple Stellar Population to reproduce the galaxy spectral energy distribution. To find high-quality solutions, metaheuristic algorithms are suitable. In this work, a wide portfolio of metaheuristics are evaluated to reproduce the Low-Resolution Spectra Energy Distribution of galaxies: M110, M32, and NGC3190. The final aim of this work is to advance in the evaluation of some metaheuristics for modeling the Spectral Energy Distribution of a galaxy as a combination of predefined Simple Stellar Populations Spectra.
Article
Differential evolution algorithm is one of the most efficient metaheuristic approaches. In this paper, a review and analysis is presented in order to help for future research in differential evolution algorithm. It covers an analysis of about 142 papers of the previous work in the modifications of the algorithm including the main parameters of the classical steps of the algorithm and hybridization with other algorithms. The analysis also shows the applications that optimized using the differential evolution algorithm.
Article
This study proposes a path planning method based on behavioral decision-making (PPM-BBD). An optimized path is planned for autonomous underwater vehicle (AUV) to save energy during the diving process. The key idea is to apply success-history based adaptive differential evolution algorithm including linear population size reduction (L-SHADE) to the optimization of energy. In addition, motion constraints are considered during the diving process to ensure that the path points are reachable. We take the sequence of motion angles as the population, and propose an angle modification strategy to apply to the population evolution process, so that the angle sequence remains in the space of feasible solutions. The modification strategy lays a theoretical foundation for the application of L-SHADE in this path planning problem. The performance of PPM-BBD is evaluated on data from simulation test. The most suitable control parameters are determined through simulation experiments. The effects of PPM-BBD with L-SHADE and five types of DE are compared. The experimental evaluation was performed through sea trials in Tuandao Bay, Qingdao, China. Results show that PPM-BBD saves at least 9% energy compared to the other algorithms. It is concluded that it is workable to obtain a reachable path with optimized energy consumption during diving process.
Article
As a promising autonomous observation platform for ocean phenomena, underwater glider can achieve space motion by adjusting its net buoyancy and attitude. In some high accuracy exploration missions, underwater glider needs to move on a specific trajectory, and the position that the glider resurfaces should be accurate enough. In fact, many uncertain factors will affect the glider motion and reduce the motion accuracy, especially the current. In this paper, we present a feedback control strategy for improving the glider motion accuracy in currents. The feedback control is achieved by intermittently adjusting the movable mass block rotation amount, which is energy-saving. Especially, the feedback control strategy considers the force condition change of the glider in different water depths and the different motion states of the glider in currents. Besides, we introduce the surrogate models to calculate the adjustment time length of movable mass block rotation amount, which can ensure that the feedback control has a higher reaction speed. To verify the effectiveness of the above strategy, the dynamic model of underwater glider is established, and the model is validated by using experimental data. The simulation results under specific working conditions illustrate that the feedback control strategy can effectively improve the glider motion accuracy in currents. To achieve the optimal control, we further propose a method to optimize the relevant parameters of feedback control strategy, considering the multiple working conditions and the energy consumption metric. The simulation results under specific working conditions verify the effectiveness of proposed optimization method. The research works can provide certain guidance for the achievement of the glider precision operation.
Article
Full-text available
In this paper we propose a deterministic route planner for a sailboat suitable for areas where high quality wind and currents forecasts are available. An optimization based approach is used with the objective of minimizing the time required to arrive at a destination. Several simulations have been performed using high resolution regional forecasts from HIRLAM and MyOcean models in order to test the validity of this method.
Conference Paper
Full-text available
This paper presents a differential evolution (DE) algorithm for real-parameter optimization. The algorithm includes the self-adaptive jDE algorithm with one of its strongest extensions, population reduction, combined with multiple mutation strategies using a structured population. The two mutation strategies used are run dependent on the population size, which is reduced with growing function evaluation number. The population is structured with a separate part where only DE/best strategy is executed and then the best vectors are exchanged with the main population part. Algorithm performance assessment results are presented for 10, 30, and 50 dimension settings for all of the 28 problems included in the Problem Definitions and Evaluation Criteria for the CEC 2013 Special Session and Competition on Real-Parameter Optimization.
Article
Full-text available
In a recently published paper in JMLR, Demˇ sar (2006) recommends a set of non-parametric sta- tistical tests and procedures which can be safely used for comparing the performance of classifiers over multiple data sets. After studying the paper, we realize that the paper correctly introduces the basic procedures and some of the most advanced ones when comparing a control method. How- ever, it does not deal with some advanced topics in depth. Regarding these topics, we focus on more powerful proposals of statistical procedures for comparing n n classifiers. Moreover, we illustrate an easy way of obtaining adjusted and comparable p-values in multiple comparison procedures.
Article
Full-text available
The underwater glider is set to become an important platform for oceanographers to gather data within oceans. Gliders are usually equipped with a conductivity–temperature–depth (CTD) sensor, but a wide range of other sensors have been fitted to gliders. In the present work, the authors aim at measuring the vertical water velocity. The vertical water velocity is obtained by subtracting the vertical glider velocity relative to the water from the vertical glider velocity relative to the water surface. The latter is obtained from the pressure sensor. For the former, a quasi-static model of planar glider flight is developed. The model requires three calibration parameters, the (parasite) drag coefficient, glider volume (at atmospheric pressure), and hull compressibility, which are found by minimizing a cost function based on the variance of the calculated vertical water velocity. Vertical water velocities have been calculated from data gathered in the northwestern Mediterranean during the Gulf of Lions experiment, winter 2008. Although no direct comparison could be made with water velocities from an independent measurement technique, the authors show that, for two different heat loss regimes (≈0 and ≈400 W m−2), the calculated vertical velocity scales are comparable with those expected for internal waves and active open ocean convection, respectively. High noise levels resulting from the pressure sensor require the water velocity time series to be low-pass filtered with a cutoff period of 80 s. The absolute accuracy of the vertical water velocity is estimated at ±4 mm s−1.
Article
Full-text available
A new heuristic approach for minimizing possibly nonlinear and non differentiable continuous space functions is presented. By means of an extensive testbed, which includes the De Jong functions, it will be demonstrated that the new method converges faster and with more certainty than Adaptive Simulated Annealing as well as the Annealed Nelder&Mead approach, both of which have a reputation for being very powerful. The new method requires few control variables, is robust, easy to use and lends itself very well to parallel computation.
Article
Full-text available
Underwater gliders have revealed as a valuable scientific platform, with a growing number of successful environmental sampling applications. They are specially suited for long range missions due to their unmatched autonomy level, although their low surge speed makes them strongly affected by ocean currents. Path planning constitutes a real concern for this type of vehicle, as it may reduce the time taken to reach a given waypoint or save power. In such a dynamic environment it is not easy to find an optimal solution or any such requires large computational resources. In this paper, we present a path planning scheme with low computational cost for this kind of underwater vehicle that allows static or dynamic obstacle avoidance, frequently demanded in coastal environments, with land areas, strong currents, shipping routes, etc. The method combines an initialization phase, inspired by a variant of the A* search process and ND algorithm, with an optimization process that embraces the physical vehicle motion pattern. Consequently, our method simulates a glider affected by the ocean currents, while it looks for the path that optimized a given objective. The method is easy to configure and adapt to various optimization problems, including missions in different operational scenarios. This planner shows promising results in realistic simulations, including ocean currents that vary considerably in time, and provides a superior performance over other approaches that are compared in this paper.
Article
Full-text available
Underwater gliders are autonomous vehicles that profile vertically by controlling buoyancy and move horizontally on wings. Gliders are reviewed, from their conception by Henry Stommel as an extension of autonomous profiling floats, through their development in three models, and including their first deployments singly and in numbers. The basics of glider function are discussed as implemented by University of Washington in Seaglider, Scripps Institution of Oceanography in Spray, and Webb Research in Slocum. Gliders sample in the archetypical modes of sections and of "virtual moorings." Preliminary results are presented from a recent demonstration project that used a network of gliders off Monterey. A wide range of sensors has already been deployed on gliders, with many under current development, and an even wider range of future possibilities. Glider networks appear to be one of the best approaches to achieving subsurface spatial resolution necessary for ocean research.
Article
Full-text available
This paper presents a differential evolution (DE) based approach to chess evaluation function tuning. DE with opposition-based optimization is employed and upgraded with a history mechanism to improve the evaluation of individuals and the tuning process. The general idea is based on individual evaluations according to played games through several generations and different environments. We introduce a new history mechanism which uses an auxiliary population containing good individuals. This new mechanism ensures that good individuals remain within the evolutionary process, even though they died several generations back and later can be brought back into the evolutionary process. In such a manner the evaluation of individuals is improved and consequently the whole tuning process. KeywordsChess evaluation function tuning–Differential evolution–History mechanism–Opposition-based optimization
Article
Full-text available
A new heuristic approach for minimizing possiblynonlinear and non-differentiable continuous spacefunctions is presented. By means of an extensivetestbed it is demonstrated that the new methodconverges faster and with more certainty than manyother acclaimed global optimization methods. The newmethod requires few control variables, is robust, easyto use, and lends itself very well to parallelcomputation.
Article
Full-text available
Differential evolution (DE) has been shown to be a simple, yet powerful, evolutionary algorithm for global optimization for many real problems. Adaptation, especially self-adaptation, has been found to be highly beneficial for adjusting control parameters, especially when done without any user interaction. This paper presents differential evolution algorithms, which use different adaptive or self-adaptive mechanisms applied to the control parameters. Detailed performance comparisons of these algorithms on the benchmark functions are outlined.
Article
Full-text available
This paper proposes the employment of the differential evolution (DE) to offline optimize the covariance matrices of a new reduced delayed-state Kalman-filter (DSKF)-based algorithm which estimates the stator-flux linkage components, in the stationary reference frame, to realize sensorless control of induction motors (IMs). The DSKF-based algorithm uses the derivatives of the stator-flux components as mathematical model and the stator-voltage equations as observation model so that only a vector of four variables has to be offline optimized. Numerical results, carried out using a low-speed training test, show that the proposed DE-based approach is very promising and clearly outperforms a classical local search and three popular metaheuristics in terms of quality of the final solution for the problem considered in this paper. A novel simple stator-flux-oriented sliding mode (SFO-SM) control scheme is online used in conjunction with the optimized DSKF-based algorithm to improve the robustness of the sensorless IM drive at low speed. The SFO-SM control scheme has closed loops of torque and stator-flux linkage without proportional-plus-integral controllers so that a minimum number of gains has to be tuned.
Conference Paper
Full-text available
In this paper we investigate a Self-Adaptive Differential Evolution algorithm (jDE) where F and CR control parameters are self-adapted and a multi-population method with aging mechanism is used. The performance of the jDE algorithm is evaluated on the set of benchmark functions provided for the CEC 2009 special session on evolutionary computation in dynamic and uncertain environments.
Conference Paper
Full-text available
This paper describes an underwater glider motion control system intended to enhance locomotive efficiency by reducing the energy expended by vehicle guidance. In previous work, the authors derived an approximate analytical expression for steady turning motion by applying regular perturbation theory to a realistic vehicle model. The analysis results suggested the use of a well-known time-optimal path planning procedure developed for the Dubins car, an often-used model of a wheeled mobile robot. For underwater gliders operating at their most efficient flight condition, time-optimal glide paths correspond to energy-optimal glide paths. Thus, an analytically informed strategy for energy-efficient locomotion is to generate sequences of steady wings-level and turning motions according to the Dubins path planning procedure. Because the turning motion results are only approximate, however, and to compensate for model and environmental uncertainty, one must incorporate feedback to ensure convergent path following. This paper describes the dynamic modelling of the complete multi-body control system and the development and numerical implementation of a motion control system. The control system can be combined with a higher level guidance strategy involving Dubins-like paths to achieve energy-efficient locomotion.
Article
Full-text available
Differential evolution (DE) is an efficient and powerful population-based stochastic search technique for solving optimization problems over continuous space, which has been widely applied in many scientific and engineering fields. However, the success of DE in solving a specific problem crucially depends on appropriately choosing trial vector generation strategies and their associated control parameter values. Employing a trial-and-error scheme to search for the most suitable strategy and its associated parameter settings requires high computational costs. Moreover, at different stages of evolution, different strategies coupled with different parameter settings may be required in order to achieve the best performance. In this paper, we propose a self-adaptive DE (SaDE) algorithm, in which both trial vector generation strategies and their associated control parameter values are gradually self-adapted by learning from their previous experiences in generating promising solutions. Consequently, a more suitable generation strategy along with its parameter settings can be determined adaptively to match different phases of the search process/evolution. The performance of the SaDE algorithm is extensively evaluated (using codes available from P. N. Suganthan) on a suite of 26 bound-constrained numerical optimization problems and compares favorably with the conventional DE and several state-of-the-art parameter adaptive DE variants.
Article
Full-text available
In this paper, a novel subpixel mapping algorithm based on an adaptive differential evolution (DE) algorithm, namely, adaptive-DE subpixel mapping (ADESM), is developed to perform the subpixel mapping task for remote sensing images. Subpixel mapping may provide a fine-resolution map of class labels from coarser spectral unmixing fraction images, with the assumption of spatial dependence. In ADESM, to utilize DE, the subpixel mapping problem is transformed into an optimization problem by maximizing the spatial dependence index. The traditional DE algorithm is an efficient and powerful population-based stochastic global optimizer in continuous optimization problems, but it cannot be applied to the subpixel mapping problem in a discrete search space. In addition, it is not an easy task to properly set control parameters in DE. To avoid these problems, this paper utilizes an adaptive strategy without user-defined parameters, and a reversible-conversion strategy between continuous space and discrete space, to improve the classical DE algorithm. During the process of evolution, they are further improved by enhanced evolution operators, e.g., mutation, crossover, repair, exchange, insertion, and an effective local search to generate new candidate solutions. Experimental results using different types of remote images show that the ADESM algorithm consistently outperforms the previous subpixel mapping algorithms in all the experiments. Based on sensitivity analysis, ADESM, with its self-adaptive control parameter setting, is better than, or at least comparable to, the standard DE algorithm, when considering the accuracy of subpixel mapping, and hence provides an effective new approach to subpixel mapping for remote sensing imagery.
Article
Full-text available
Trial vector generation strategies and control parameters have a significant influence on the performance of differential evolution (DE). This paper studies whether the performance of DE can be improved by combining several effective trial vector generation strategies with some suitable control parameter settings. A novel method, called composite DE (CoDE), has been proposed in this paper. This method uses three trial vector generation strategies and three control parameter settings. It randomly combines them to generate trial vectors. CoDE has been tested on all the CEC2005 contest test instances. Experimental results show that CoDE is very competitive.
Conference Paper
Full-text available
In this paper we present self-adaptive differential evolution algorithm jDElsgo on large scale global optimization. The experimental results obtained by our algorithm on benchmark functions provided for the CEC 2010 competition and special session on Large Scale Global Optimization are presented. The experiments were performed on 20 benchmark functions with high dimension D = 1000. Obtained results show that our algorithm performs highly competitive in comparison with the DECC-G*, DECC-G and MLCC algorithms.
Article
Full-text available
Differential evolution (DE) is a simple, yet efficient, evolutionary algorithm for global numerical optimization, which has been widely used in many areas. However, the choice of the best mutation strategy is difficult for a specific problem. To alleviate this drawback and enhance the performance of DE, in this paper, we present a family of improved DE that attempts to adaptively choose a more suitable strategy for a problem at hand. In addition, in our proposed strategy adaptation mechanism (SaM), different parameter adaptation methods of DE can be used for different strategies. In order to test the efficiency of our approach, we combine our proposed SaM with JADE, which is a recently proposed DE variant, for numerical optimization. Twenty widely used scalable benchmark problems are chosen from the literature as the test suit. Experimental results verify our expectation that the SaM is able to adaptively determine a more suitable strategy for a specific problem. Compared with other state-of-the-art DE variants, our approach performs better, or at least comparably, in terms of the quality of the final solutions and the convergence rate. Finally, we validate the powerful capability of our approach by solving two real-world optimization problems.
Article
A new heuristic approach for minimizing possiblynonlinear and non-differentiable continuous spacefunctions is presented. By means of an extensivetestbed it is demonstrated that the new methodconverges faster and with more certainty than manyother acclaimed global optimization methods. The newmethod requires few control variables, is robust, easyto use, and lends itself very well to parallelcomputation.
Article
This paper presents a vectorized matrix parameters encoding aspect for an evolutionary computer vision approach to procedural tree modeling. A serialized fixed-size floating-point encoded tree parameter set consists of a set of auxiliary local and other global parameters. The main goal of paper is to lower problem dimensionality needed for encoding local parameters. For evolution simulation, differential evolution algorithm is used. The optimizer evolves a parameterized procedural model by fitting a set of its rendered images to a set of automatically preprocessed reference photo images. The reconstructed tree morphology is then used for reconstructed tree animation, to generate similar geometrical tree models based on similar morphology. Examples of reconstructed model animation are shown, such as simulation of its growth, sway in the wind, or adding leaves.
Article
Differential evolution (DE) is a prominent stochastic optimization technique for global optimization. After its original definition in 1995, DE frameworks have been widely researched by computer scientists and practitioners. It is acknowledged that structuring a population is an efficient way to enhance the algorithmic performance of the original, single population (panmictic) DE. However, only a limited amount of work focused on Distributed DE (DDE) due to the difficulty of designing an appropriate migration strategy. Since a proper migration strategy has a major impact on the performance, there is a large margin of improvement for the DDE performance. In this paper, an enhanced DDE algorithm is proposed for global numerical optimization. The proposed algorithm, namely DDE with Multicultural Migration (DDEM) makes use of two migration selection approaches to maintain a high diversity in the subpopulations, Target Individual Based Migration Selection (TIBMS) and Representative Individual Based Migration Selection (RIBMS), respectively. In addition, the diversity amongst the individuals is controlled by means of the proposed Affinity Based Replacement Strategy (ABRS) mechanism. Numerical experiments have been performed on 34 diverse test problems. The comparisons have been made against DDE algorithms using classical migration strategies and three popular DDE variants. Experimental results show that DDEM displays a better or equal performance with respect to its competitors in terms of the quality of solutions, convergence, and statistical tests.
Article
Differential evolution (DE) is a well-known algorithm for global optimization over continuous search spaces. However, choosing the optimal control parameters is a challenging task because they are problem oriented. In order to minimize the effects of the control parameters, a Gaussian bare-bones DE (GBDE) and its modified version (MGBDE) are proposed which are almost parameter free. To verify the performance of our approaches, 30 benchmark functions and two real-world problems are utilized. Conducted experiments indicate that the MGBDE performs significantly better than, or at least comparable to, several state-of-the-art DE variants and some existing bare-bones algorithms.
Article
Solving high-dimensional global optimization problems is a time-consuming task because of the high complexity of the problems. To reduce the computational time for high-dimensional problems, this paper presents a parallel differential evolution (DE) based on Graphics Processing Units (GPUs). The proposed approach is called GOjDE, which employs self-adapting control parameters and generalized opposition-based learning (GOBL). The adapting parameters strategy is helpful to avoid manually adjusting the control parameters, and GOBL is beneficial for improving the quality of candidate solutions. Simulation experiments are conducted on a set of recently proposed high-dimensional benchmark problems with dimensions of 100, 200, 500 and 1,000. Simulation results demonstrate that GjODE is better than, or at least comparable to, six other algorithms, and employing GPU can effectively reduce computational time. The obtained maximum speedup is up to 75.
Article
Differential Evolution (DE) is one of the most popular optimization methods for real-valued problems and a large number of its variants have been proposed so far. However, bringing together different ideas that already led to successful DE versions is rare in the literature. In the present paper a novel DE algorithm is proposed, in which three among the most efficient concepts already applied separately within DE framework are gathered together, namely: (1) the adaptation of algorithm control parameters and probabilities of using different mutation strategies; (2) the use of Nelder–Mead algorithm as a local search method hybridized with DE; and (3) the splitting mutation into Global and Local models, when Local mutation model is based on the concept of neighborhood of individuals organized on a ring topology. The performance of the novel algorithm, called Adaptive Memetic DE with Global and Local neighborhood-based mutation operators is compared with 13 different DE variants on a set of 25 popular problems which include rotated, shifted and hybrid composition functions. It is found that, although none DE algorithm outperforms all the others for the majority of problems, on average the proposed approach perform better than all 13 DE algorithms selected for comparison.
Article
Gliders are autonomous underwater vehicles that achieve long operating range by moving at speeds comparable to those of, or slower than, typical ocean currents. This paper addresses routing gliders to rapidly reach a specified waypoint or to maximize the ability to map a measured field, both in the presence of significant currents. For rapid transit in a frozen velocity field, direct minimization of travel time provides a trajectory “ray” equation. A simpler routing algorithm that requires less information is also discussed. Two approaches are developed to maximize the mapping ability, as measured by objective mapping error, of arrays of vehicles. In order to produce data sets that are readily interpretable, both approaches focus sampling near predetermined “ideal tracks” by measuring mapping skill only on those tracks, which are laid out with overall mapping skill in mind. One approach directly selects each vehicle's headings to maximize instantaneous mapping skill integrated over the entire array. Because mapping skill decreases when measurements are clustered, this method automatically coordinates glider arrays to maintain spacing. A simpler method that relies on manual control for array coordination employs a first-order control loop to balance staying close to the ideal track and maintaining vehicle speed to maximize mapping skill. While the various techniques discussed help in dealing with the slow speed of gliders, nothing can keep performance from being degraded when current speeds are comparable to vehicle speed. This suggests that glider utility could be greatly enhanced by the ability to operate high speeds for short periods when currents are strong.
Article
Abstract The use of evolutionary strategies (ESs) to solve problems,with multiple objectives (known as Vector Optimization Problems(VOPs)) has attracted much,attention recently. Being population based approaches, ESs offer a means to find a set of Pareto-optimal solutions in a single run. Differential Evolution (DE) is an ES that was developed to handle optimization problems,over continuous domains. The objective of this paper is to introduce a novel Pareto‐frontier Differential Evolution(PDE) algorithm to solve VOPs. The solutions provided by the proposed algorithm for two standard test problems, outperform the Strength Pareto Evolutionary Algorithm , one of the state-of-the-art evolutionary algorithm for solving VOPs.
Article
Methods for constructing simultaneous confidence intervals for all possible linear contrasts among several means of normally distributed variables have been given by Scheffé and Tukey. In this paper the possibility is considered of picking in advance a number (say m) of linear contrasts among k means, and then estimating these m linear contrasts by confidence intervals based on a Student t statistic, in such a way that the overall confidence level for the m intervals is greater than or equal to a preassigned value. It is found that for some values of k, and for m not too large, intervals obtained in this way are shorter than those using the F distribution or the Studentized range. When this is so, the experimenter may be willing to select the linear combinations in advance which he wishes to estimate in order to have m shorter intervals instead of an infinite number of longer intervals.
Article
Intense, buoyant anticyclonic eddies spawned from the west Greenland boundary current were observed with high-resolution autonomous Seaglider hydrography and satellite altimetry as they entered the Labrador Sea interior. Surveys of their internal structure establish the transport of both low-salinity water in the upper ocean and warm, saline Irminger water at depth. The observed eddies can contribute significantly to the rapid restratification of the Labrador Sea interior following wintertime deep convection. These eddies have saline cores between 200 and 1000 m, low-salinity cores above 200 m, and a velocity field that penetrates to at least 1000 m, with 0-1000-m average speeds exceeding 40 cm s-1. Their trajectory, together with earlier estimates of the gyre circulation, suggests why the observed region of deep convection is so small and does not occur where wintertime cooling by the atmosphere is most intense. The cyclostrophic surface velocity field of the anticylones from satellite altimetry matched well with in situ dynamic height baroclinic velocity calculations.
Book
Problems demanding globally optimal solutions are ubiquitous, yet many are intractable when they involve constrained functions having many local optima and interacting, mixed-type variables.The differential evolution (DE) algorithm is a practical approach to global numerical optimization which is easy to understand, simple to implement, reliable, and fast. Packed with illustrations, computer code, new insights, and practical advice, this volume explores DE in both principle and practice. It is a valuable resource for professionals needing a proven optimizer and for students wanting an evolutionary perspective on global numerical optimization. A companion CD includes DE-based optimization software in several programming languages.
Article
The optimization of the atomic and molecular clusters with a large number of atoms is a very challenging topic. This article proposes a parallel differential evolution (DE) optimization scheme for large-scale clusters. It combines a modified DE algorithm with improved genetic operators and a parallel strategy with a migration operator to address the problems of numerous local optima and large computational demanding. Results of Lennard-Jones (LJ) clusters and Gupta-potential Co clusters show the performance of the algorithm surpasses those in previous researches in terms of successful rate, convergent speed, and global searching ability. The overall performance for large or challenging LJ clusters is enhanced significantly. The average number of local minimizations per hit of the global minima for Co clusters is only about 3-4% of that in previous methods. Some global optima for Co are also updated. We then apply the algorithm to optimize the Pt clusters with Gupta potential from the size 3 to 130 and analyze their electronic properties by density functional theory calculation. The clusters with 13, 38, 54, 75, 108, and 125 atoms are extremely stable and can be taken as the magic numbers for Pt systems. It is interesting that the more stable structures, especially magic-number ones, tend to have a larger energy gap between the highest occupied molecular orbital and the lowest unoccupied molecular orbital. It is also found that the clusters are gradually close to the metal bulk from the size N > 80 and Pt38 is expected to be more active than Pt75 in catalytic reaction. © 2013 Wiley Periodicals, Inc.