Article

Autopilot System Based on Color Recognition Algorithm and Internal Model Control Scheme for Controlling Approaching Maneuvers of a Small Boat

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

Abstract

This paper designs and develops an autopilot system for guiding the trajectory of a small boat as it performs an approaching maneuver within a harbor. In the proposed approach, two canvas targets are arranged in cascade on the berth to serve as leading marks to define the leading line along which to guide the boat toward the berthing standby region. The leading marks are captured by a charge-coupled device (CCD) camera mounted on the bow of the boat, and the resulting image is processed using a color recognition scheme to identify the hue (H) and saturation (S) components. The H- and S-component images are subsequently processed using a noise filtering scheme to accurately detect the location of the two targets in the image. The centers of gravity (CGs) of the two leading marks are then calculated, and the separation distance between them is used to compute the deviated heading angle. This angle is then supplied to an internal model control (IMC) autopilot system as an error signal and is used to generate appropriate control commands to steer the boat toward the leading line. The feasibility of the autopilot system is verified by performing a series of experimental approaching maneuvers using a small boat in a real-world harbor setting.

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.

... The imperial palace of Ming and Qing Dynasties is a model of hand-made decorative fabrics used to decorate interior decoration, such as dragon and Phoenix drapery, golden and blue curtains, vanilla and orchid embellishment masks, as well as beautiful upholstery screens [3]. These gorgeous decorative fabrics complement each other with the open court space and the scattered layout, making the imperial palace a real art palace [4,5]. It can be seen that the perfect combination of decorative fabric and interior decoration [6][7][8], with its own cultural symbolic significance and overflowing cultural taste, plays a significant role in promoting the style of living environment, enhancing and highlighting the owner's life taste and aesthetic sentiment [9]. ...
Article
The popularity of covid-19 has led to the introduction of the policy of controlling the flow of personnel, which has a certain impact on the color recognition of the design objects of hand decorative elements. In the past, the research on convolution neural network design and color recognition is still in the traditional method, and the field of computer vision is not really combined with the traditional decorative fabric. This paper proposes a solution based on deep learning. Color learning and main color recognition can be processed as a whole. By introducing convolution neural network, the scheme can learn color features directly from the image itself, and the process of artificial design features is omitted. While simplifying the process of model building and training, the potential information association can be obtained, so as to obtain better recognition effect. In addition, due to the deep depth of the network, this paper uses the initial optimization module to avoid the performance degradation and over fitting in the training process. This method has an important reference value for the color design of modern hand decoration, and can promote the development of hand decoration during the popularity of covid-19.
... To build a good 3D virtual model, we need to use appropriate technology and tools according to the characteristics of the target object [4][5][6]. This paper mainly uses VRML technology and 3DS MAX technology to build three-dimensional virtual model. ...
Article
The transmission routes of novel coronavirus pneumonia include direct transmission, aerosol transmission and contact transmission. Therefore, the novel coronavirus pneumonia has been spread very quickly. This has a certain impact on the development of graphic design. Graphic design plays an important role in product design. However, the traditional aided design method is too complex, and it is difficult for designers to design works that meet their own needs. In the design of 3D virtual vision graphics, the distance calculation of time series is not accurate. This kind of error will bring some errors to the design of complex curved surface products. In order to measure the similarity of time series effectively, the calculation principle of Euclidean distance and dynamic bending distance is analyzed. Combined with the advantages of these two methods, a new distance calculation method based on morphological fitting is proposed. In this paper, through the research of ordered point sequence, the 3D virtual design method is used to improve the design effect, which has reference value for the design of works that meet the requirements of designers during the popularity of COVID-19.
... However, these controllers cannot provide perfect control performance and, at the same time, cannot guarantee operation with same level of accuracy for the entire operating range [2]. To address the nonlinear effects, various controllers based on other mathematical models, such as sliding-mode control [3] [4], back-stepping techniques [5] [6], linear quadratic control [7], surface control [8], fuzzy PID control [9], internal model control [10] [11], and active disturbance rejection control (ADRC) [12], have been developed. However, to reduce the complexity of the problem, these mathematical-model-based control systems, including PID controllers, require some considerable assumptions for the simplifications and linearization, as stated in [13] and [14]. ...
Article
Full-text available
This paper presents the development of neural-network-based control system using self-organizing-maps (SOMs) for the maneuvers of a double-propeller boat. The performance characteristics of the developed SOM controller system are compared with a widely-used supervised learning mechanism, the backpropagation neural network (BPNN) controller. The experimental results show that the proposed unsupervised SOM controller can control the boat model with very low error, although most artificial neural network (ANN)-based controllers are usually designed using supervised learning approaches. The important characteristic of the proposed SOM controller system is that it utilizes a mapping principle instead of an error calculation such as that in the BPNN controller system; consequently, the proposed SOM controller system is not very sensitive to non-ideal training data, which produces a low control error for the generated elliptical trajectory data. It is also confirmed in these experiments that when more mapping neurons are utilized in the SOM controller, a lower control error is achieved. It is expected that in a real implementation, the SOM controller could provide more robust control than the BPNN controller in handling small disturbances such as light winds and small waves.
... As its actual dynamics is highly non-linear, time-varying, and coupled [1], it may be too complex to design the USV controller using a mathematical approach. The Internal Model Control [2] [3], for example, was obviously derived from a mathematical simplification approach, and may not perform well when it is used as a USV controller in a highly nonlinear environment. ...
Article
Full-text available
This paper describes the development of a controller system for a developed double-propeller boat model using the unsupervised learning neural networks, namely the Self-Organizing Maps (SOM). The performance characteristics of the proposed SOM-based controller are then compared with that of the well-known Back-propagation Neural Networks (BPNN)-based controller through a direct inverse control scheme. Experimental results showed that the SOM-based controller can produce a low error, even lower than that of the widely used BPNN-based controller. Furthermore, the computational cost of the SOM-based controller is found to be more than 700 times faster than that of the BPNN-based controller. These findings suggest that the utilization of the proposed SOM-based controller for the control of a boat is highly effective.
... The main methodologies applied to vessel steering controller design could be summarized as the following classifications: conventional PID approach [1], Linear Quadratic Gaussian (LQG) control theory [2], Internal Model Control (IMC) method [3], Sliding Mode (SM) control [4] and Model Predictive Control (MPC) [5], etc. Most of the previous methods focused on hydrodynamic ship models or simplified variants, whereby the involved derivatives are usually prefixed. ...
Conference Paper
This paper contributes to vessel steering control system design via the Generalized Ellipsoidal Function Based Fuzzy Neural Network (GEBF-FNN) method. Based on vessel motion dynamics and Nomoto model, a vessel steering model including dynamical K and T parameters dependent on initial forward speed and required heading angle is proposed to develop a novel dynamical PID steering controller including dynamical controller gains to obtain rapid and accurate performance. The promising GRBF-FNN algorithm is applied to dealing with the identification of dynamical controller gains. Typical steering maneuvers are considered to generate data samples for training the GEBF-FNN based dynamical steering controller while the prediction performance is checked by series of steering commands. In order to demonstrate the effectiveness of the proposed scheme, simulation studies are conducted on benchmark scenarios to validate effective performance.
... The boat has two problems: one is velocity and heading control [4], against the influence of wind and streams; and the other problem is to have limited turning radii. The fuzzy controller makes possible to turn with a suitable velocity taking into account the radius of the circumference. ...
Article
Full-text available
This paper is linked to a research proposing autonomous ships for risky humanitarian operations, like sea demining or poisonous spill recovery on the sea. This mission is based upon placing waypoints and the autonomous ships are under a Fuzzy control. Since ships have limited turning radii, a specific path planning strategy is developed, so the ship trajectory turns around waypoints at a suitable distance. The system is being tested with scaled ships.
Conference Paper
Control and guidance of Autonomous Underwater Vehicle (AUV) is tedious process as it is an underactuated model where the numbers of inputs to the actuator are less than the number of degrees-of-freedom to be controlled; also the dynamics of AUV is affected by internal interruptions like sensor noise and exterior distractions namely hydrodynamic effects and ocean current. The difficulty of uncertainty in the vehicle dynamics can be handled by adaptive control, chosen based on its clarity using conventional controller like Proportional-Integral-Derivative (PID) and also by intelligent Fuzzy Logic Control (FLC). To increase the quality of these autonomous systems, model-based control strategies such as Internal Model Control (IMC) and Model Predictive Control (MPC) has been focused in this paper. The control operation includes motion planning and trajectory generation tasks which provide the desired vehicle depth location as a function of time and subsequently the controller determines required stern angle position, based on the sensor measurements. The comparative result shows that Model based control strategies exhibits better performance than the classical controls.
Article
This work adopts the popular concept of visual guidance scheme practiced by the mariners, namely, the fore-aft leading mark as the guiding aid and uses the image process technique along with autopilot to guide the FRP (Fiber Reinforced Plastic) boat towards a prescribed straight water channel. In order to have the boat steer to the leading line earlier, a modified algorithm of fore-aft leading mark guidance method is proposed and improvement of the ship trajectory convergence rate is verified via experimental studies. Use of a rotating stand; hence, improves the field of view of the CCD camera lessens the oscillating problem caused by sea disturbance. Moreover, it can prevent loss sight of the target to ensure the boat is continuously under visual guidance and control. An image processing unit mounted on the bow of the boat is used in capturing a set of targets placed on the shore. Proper thresholds of HSV (Hue, Saturation, and Value) are set and the RoI (Region of Interest) scheme is adopted during the image processing process to enhance identifibility of the leading mark. Moreover, filtering of the background light source disturbance is considered. The reference heading angles are calculated by two types of fore-aft leading mark guidance methods and fed into the fuzzy logic autopilot and the Internal Model Control (IMC) autopilot to steer the boat towards the leading line. Experimental studies indicate adoption of red LED (Light-emitting Diode) improves target recognition possibility, and the small size nature of the LED also reduces the error range of the computed center of leading mark as compared with color canvas targets. Specifically, the reference heading angle calculated by the proposed modified algorithm of fore-aft leading mark guidance method is larger, thus, reduces the time of convergence to the leading line and better resembles the real maneuvering behavior.
Article
This paper deals with tanker steering control based on a novel multiple-input multiple-output generalized ellipsoidal-basis-function-based fuzzy neural network (GEBF-FNN) with online updating of system structure and parameters. The main contributions of this paper are as follows. 1) A GEBF-FNN-based nonlinear steering model incorporating the nonlinearity underlying tanker dynamics is proposed. 2) The static local controller (SLC), whose controller gains are locally fixed with the initial forward speed and the desired heading for individual steering commands, is implemented. 3) The dynamic local controller (DLC) is further realized by employing adaptive controller gains pertaining to time-varying forward speed and heading dynamics. 4) The GEBF-FNN-based steering controller is developed by identifying a nonlinear mapping from the heading error, acceleration and forward speed to dynamic controller gains, and thereby contributing to a model-free adaptive control scheme. Simulation results and comprehensive studies on benchmark problems demonstrate that the GEBF-FNN-based model can capture the essential tanker dynamics, and the proposed SLC, DLC, and GEBF-FNN-based schemes achieve superior performance in terms of heading regulation and forward speed loss. In comparison with the SLC and traditional fuzzy controllers, the DLC and GEBF-FNN-based controllers achieve higher accuracy of heading regulation with less rudder efforts and minimal forward speed losses.
Article
In this paper, the problem of designing a boat parking assistance system for a small-scale vessel is addressed. A control-oriented model is derived from the physics underlying the system, and gray-box identification is carried out by designing suitable experiments. A 3-DOF cascade control scheme is then implemented to achieve semiautomatic parking and stationkeeping. The latter mode is also shown to represent a solid groundwork for future research on fully automatic maneuvering in a harbor. The proposed strategy is finally tested on stationkeeping and parking of a real vessel.
Conference Paper
Within a learning machine, we could improve the accuracy of every learning task while a few tasks learned together. This method is called multitask learning. It is popular to using simulated annealing algorithm or setting a constant as learning rate in multitask learning. Either is simple and efficiently. But neither use feedback information in machine effectively. A novel adaptive feedback learning algorithm (AFLA) for multitask learning is proposed in this paper. The AFLA is proposed to address the problem using feedback information in multitask learning machine. The AFLA uses the error signal as feedback information. And it applies error signal in learning rate. The experiments are carried on two datasets. With simulated annealing and constant comparisons, experimental results show that the AFLA can use error signal efficiently. At normal learning rate, the accuracy of AFLA is better than using simulated annealing algorithm and constant. At smaller learning rate, the accuracy of AFLA is 2-5 times as big as others.
Article
Full-text available
In the past, ship steering systems were based on controlling the ship heading to a desired heading by the measurement of a gyrocompass. As new measurements are available as well as the knowledge of advanced nonlinear control techniques, it is today possible to perform much more complicated maneuvers by automatic control. This has and will continue to increase the functionality and reliability of commercially available automatic ship navigation systems. Maneuvering a ship along a desired path is the present challenge.
Article
Full-text available
We present the design and implementation of a real-time, vision-based landing algorithm for an autonomous helicopter. The landing algorithm is integrated with algorithms for visual acquisition of the target (a helipad) and navigation to the target from an arbitrary initial position and orientation. We use vision for precise target detection and recognition and a combination of vision and GPS for navigation. The helicopter updates its landing target parameters based on vision and uses an on board behaviorbased controller to follow a path to the landing site. We present significant results from flight trials in the field which demonstrate that our detection, recognition and control algorithms are accurate, robust and repeatable.
Article
The typical objective in a course-changing manoeuver is to perform the manoeuver quickly with minimum overshoot. This often requires rapid and large rudder movements, which are inevitably limited by finite actuator power. Without proper precaution, controller integral wind-up will occur which may lead to stability problems for the system. A reference conditioning technique is proposed in this paper that generates a new reference signal such that the rudder command is always consistent with the actual rudder input. This ensures a quick course-changing manoeuver is achieved; hence, the rudder saturation and slew rate limitation are accommodated without otherwise compromising the performance. The internal model control method adopted in this paper is very attractive in the design of the autopilot, since it highlights inherent performance limitations and allows a coherent treatment of control strategies that might otherwise appear as uncorrelated.
Article
Model uncertainty is one of the major problems facing control system designers in practice. In this paper a general approach is outlined for the assessment of the effects of model uncertainty on control system performance. Also discussed are methods for the design of controllers which meet given performance specifications despite model uncertainty. The power of the new techniques as well as the failure of the traditional ones is illustrated on two examples widely studied in the process control literature: The design of Smith predictor controllers and the design of 2-point composition controllers for high purity distillation columns.
Article
This paper discusses the general concept of an automatic berthing system. The research considered the automatic berthing of a large merchant ship. A global positioning system (GPS)-based system, which provides the necessary information on position, velocity, attitude (roll, pitch, and heading), angular velocity, and time, was the principal sensor used. Field tests were conducted on board a hydrographic sounding ship to assess the quality of information obtained from a GPS-based system. The data were processed using the software with which the algorithms developed in this research were implemented. This paper also discusses various aspects concerning a real-time GPS-based system in relation to an automatic berthing system, such as integration of sensors, mathematical models, port infrastructure, and training of crews.
Article
In this paper the problem of high-precision motion control of remotely operated vehicles (ROVs) in the proximity of the seabed through vision-based motion estimation is addressed. The proposed approach consists of the integration of a cheap monocular vision system for the estimate of the vehicle's linear motion with a conventional dual-loop hierarchical architecture for kinematics and dynamics control. Results obtained by operating at sea the Romeo ROV are presented, demonstrating the system capability in performing station-keeping in the presence of external disturbance and relatively high accuracy in horizontal motion control.
Article
The maneuvering problem involves two tasks. The first, called the geometric task, is to force the system output to converge to a desired path continuously parametrized by a scalar θ. The second task, called the dynamic task, is to satisfy a desired dynamic behavior along the path. In this paper, this dynamic behavior is further specified as a speed assignment for θ(t). While the main concern is to satisfy the geometric task, the dynamic task ensures that the system output follows the path with the desired speed. An adaptive recursive design technique is developed for a parametrically uncertain nonlinear plant describing the dynamics of a ship. First the geometric part of the problem is solved. Then an update law is constructed that bridges the geometric design with the dynamic task. The design procedure is performed and tested by several experiments for a model ship in a marine control laboratory.
Article
An unmanned aerial vehicle usually carries an array of sensors whose output is used to estimate vehicle attitude, velocity, and position. This paper details the development of guidance, navigation, and control strategies for a glider, which is capable of flying a terminal trajectory to a known fixed object using only a single vision sensor. Controlling an aircraft using only vision presents two unique challenges: First, absolute state measurements are not available from a single image; and second, the images must be collected and processed at a high rate to achieve the desired controller performance. The image processor utilizes an integral image representation and a rejective cascade filter to find and classify simple features in the images, reducing the image to the most probable pixel location of the destination object. Then, an extended Kalman filter uses measurements obtained from a single image to estimate the states that would otherwise be unobservable in a single image. In this research, the flights are constrained to keep the destination object in view. The approach is validated through simulation. Finally, experimental data from autonomous flights of a glider, instrumented only with a single nose-mounted camera, intercepting a target window during short low-level flights, are presented. © 2006 Wiley Periodicals, Inc.
Design ideas and experiences gained during the development of an adaptive high precision track controller for ships are summarised. The controller is installed on a number of different ships, using a variety of position measurement systems. The design follows the spirit of the LQG paradigm combined with a model following feedforward strategy. The ship is kept to a manoeuvring trajectory through a combination of feedforward and LQG feedback control. The variances and weighting coefficients for the LQG controller are chosen systematically. The large number of design parameters is reduced by appropriate model scaling. In addition, a decomposition structure of the Kalman filter is exploited to reveal the important tuning parameters
Article
A ship optimal trajectory planning method based on the dynamic model of the ship is presented. First a mathematical modular model is introduced for describing the non-linear dynamics of the ship. Then the problem of optimal trajectory planning is discussed. The trajectory is obtained through the optimization of a time-energy criterion, taking into account constraints on the steering system, environment, non-linearities, and non-convexity of the state space equations. The discrete augmented Lagrangian approach is used to compute the optimal constrained controller. The method was programmed on a HP700 workstation. This approach was applied to automatic ship berthing maneuver
Article
A fuzzy guidance controller is developed for waypoint following guidance on a small autonomous boat. The boat is a prototype vehicle developed at the MIT Sea Grant College Program and is designed to perform autonomous oceanographic research. The fuzzy controller is programmed in C and down-loaded to a small onboard computer for execution. Navigation data is found in real-time using a digital compass and a differentially corrected GPS receiver. The fuzzy controller was found to be relatively easy to develop, simple to tune, and robust to external disturbances. Field test results are presented and show that the guidance controller performed well on complex paths
Ship Handling for the Mariner
  • D D Macelrevery
D. D. MacElrevery, Ship Handling for the Mariner. Centreville, MD: Cornell Maritime, 1995, ch. 1, 2, and 4.