Figure - available from: EURASIP Journal on Advances in Signal Processing
This content is subject to copyright. Terms and conditions apply.
Source publication
Unmanned aerial vehicles (UAVs) are considered a promising example of an automatic emergency task in a dynamic marine environment. However, the maritime communication performance between UAVs and offshore platforms has become a severe challenge. Due to the complex marine environment, the task allocation and route planning efficiency of multiple UAV...
Similar publications
This article presents the results of work of power supply system of an unmanned aerial vehicle (UAV) powered by solar cells. The goal of work was to develop simulation model which allow us to calculate the flight time for the input assumptions. The UAV power supply system main elements are photovoltaic cells and batteries. In the model we also incl...
Unmanned aerial vehicles (UAVs) do not collide with obstacles, generate a path in real-time, and must fly to the target point. The sampling-based rapidly exploring random tree (RRT) algorithm has the advantages of fast computation and low computational complexity. It is suitable for real-time path generation, but the optimal path cannot be guarante...
Vehicle re-identification (Re-ID) involves identifying the same vehicle captured by other cameras, given a vehicle image. It plays a crucial role in the development of safe cities and smart cities. With the rapid growth and implementation of unmanned aerial vehicles (UAVs) technology, vehicle Re-ID in UAV aerial photography scenes has garnered sign...
With UAVs on the rise, accurate detection and identification are crucial. Traditional unmanned aerial vehicle (UAV) identification systems involve opaque decision-making, restricting their usability. This research introduces an RF-based Deep Learning (DL) framework for drone recognition and identification. We use cutting-edge eXplainable Artificial...
Simulation, robotics, and Radio Frequency Identification (RFID) technology have significant roles in the new industrial revolution, and their application are key aspects of making Industry 4.0 a reality. Developing efficient use cases in Industry 4.0 almost always requires accurate simulation tools to be used in the digital world. The problem of si...
Citations
... Typically, we apply optimization methods to an environment state to find a set of working parameters that maximize an objective function. These methods could be simple, like discrete brute-force (BF), line-search (LS), and simulated annealing (SA), or more complex, like genetic algorithm (GA), particle swam optimization (PSO), bat algorithm optimization (BAO), and ant colony optimization (ACO) [36][37][38]. However, in rapidly changing environments, if finding working parameters takes a long time, then the system might not adapt to the change and may fail to work properly. ...
In this paper, a secure uplink non-orthogonal multiple access (NOMA) internet of things (IoT) system using an energy harvesting (EH) unmanned aerial vehicle (UAV) is studied. The communication protocol includes three phases: The first phase is an EH phase, in which a UAV relay (UR) and IoT user/devices (IDs) harvest radio frequency energy from a base station (BS). Information transmission from IDs to the UAV relay is the second phase. The third phase then relays the information from the UR to the BS. Furthermore, in the second and third phases, a UAV eavesdropper (UE) wiretaps the signals from the IDs and UAV relay. For this system, we derived the closed-form outage and intercept probabilities to evaluate the system and secrecy performances. We then propose a random-cut continuous genetic algorithm (RCGA) to minimize the outage probability and obtain training data. Finally, we train a deep learning model to predict the optimal configuration parameters, allowing for rapid adaptation to environmental conditions.
... This scenario is more realistic for mobile robotics, because mobile robots are usually compactly designed to serve a single task at a time, and in most cases, the task only needs one robot to complete it or the task can be decomposed into elements so that a single robot can pick it up. Typical applications of the ST-SR-TA problem include mobile robot swarm surveillance [5,6], factory robot automation [7,8], wireless sensor networks (WSNs) [9], transportation networks [10], etc. Tremendous efforts have been made to solve this problem in the literature, mostly attributing this problem to a vehicle routing problem (VRP) [11,12] or a multiple-traveling-salesman problem (mTSP) [7], then using heuristic or meta-heuristic methods to solve it. However, there exist some challenges that need to be addressed: (1) Heuristics are fast but yield a low solution quality, while meta-heuristics provide a better quality but require significant computational time. ...
... Note that in line 1, the parameter of the baseline model is initialized as the same as the current model and is updated periodically if the performance is improved, as shown in line 14. Line 2 generates a set of evaluation instances used as an auxiliary to judge if the performance is improved or not; line 4 is crucial, where both single-and multiple-depot MRTA instances, with a variable number of robots and tasks, are generated for training, aiming at the generalization capability of the policy network; line 8-10 calculate the rewards of the baseline; line [11][12] update the parameters of policy network by gradient back forward algorithm; and bootstrapping is realized in lines 13-15 by updating the baseline model parameters under certain criteria. ...
Task allocation plays an important role in multi-robot systems regarding team efficiency. Conventional heuristic or meta-heuristic methods face difficulties in generating satisfactory solutions in a reasonable computational time, particularly for large-scale multi-robot task allocation problems. This paper proposes a novel graph deep-reinforcement-learning-based approach, which solves the problem through learning. The framework leverages the graph sample and aggregate concept as the encoder to extract the node features in the context of the graph, followed by a cross-attention decoder to output the probability that each task is allocated to each robot. A graph normalization technique is also proposed prior to the input, enabling an easy adaption to real-world applications, and a deterministic solution can be guaranteed. The most important advantage of this architecture is the scalability and quick feed-forward character; regardless of whether cases have a varying number of robots or tasks, single depots, multiple depots, or even mixed single and multiple depots, solutions can be output with little computational effort. The high efficiency and robustness of the proposed method are confirmed by extensive experiments in this paper, and various multi-robot task allocation scenarios demonstrate its advantage.
... While being sound and optimal, these methods are applicable to only small-scale systems. Thus, extensive work can be found on designing meta-heuristic algorithms for finding sufficiently good solutions in a reasonable time, e.g., genetic algorithms [13], colony optimization [14,15], particle swarm optimization [16,17], learning-based algorithms [18][19][20], or large language models [21,22]. However, these methods often lack a formal guarantee on the correctness and quality of the planning results. ...
... All subtasks satisfy the ordering constraints in the R-posets. For instances, as shown in Fig. 4D, although agents 6, 14 have arrived in region w7 before 100 s to collaborate on the subtask 16 = M � w7,w7 (in blue), they have to wait until that agent 10 has fulfilled the subtask 14 = C � w7,w7 , due to the ordering constraints that (ω 14 , ω 16 ) ∈ ⪯ , {ω 14 , ω 16 } ∈ ≠. The constraints introduced by objects are also satisfied, e.g., task ω 7 (in green) cannot be executed at 380 s before subtask ω 6 (in purple) has been finished, since the required object 3 has not been transferred to region o 4 . ...
Efficient coordination and planning is essential for large-scale multi-agent systems that collaborate in a shared dynamic environment. Heuristic search methods or learning-based approaches often lack the guarantee on correctness and performance. Moreover, when the collaborative tasks contain both spatial and temporal requirements, e.g., as linear temporal logic (LTL) formulas, formal methods provide a verifiable framework for task planning. However, since the planning complexity grows exponentially with the number of agents and the length of the task formula, existing studies are mostly limited to small artificial cases. To address this issue, a new planning paradigm is proposed in this work for system-wide temporal task formulas that are released online and continually. It avoids two common bottlenecks in the traditional methods, i.e., (a) the direct translation of the complete task formula to the associated Büchi automaton and (b) the synchronized product between the Büchi automaton and the transition models of all agents. Instead, an adaptive planning algorithm is proposed, which computes the product of relaxed partially ordered sets (R-posets) on-the-fly and assigns these subtasks to the agents subject to the ordering constraints. It is shown that the first valid plan can be derived with a polynomial time and memory complexity with respect to the system size and the formula length. Our method can take into account task formulas with a length of more than 400 and a fleet with more than 400 agents, while most existing methods fail at the formula length of 25 within a reasonable duration. The proposed method is validated on large fleets of service robots in both simulation and hardware experiments.
... where ε E = 2 2R E − 1 and R E is the leakage threshold. Similar to (22), the intercept probability at the UE in the second phase is obtained as (33). ...
... Usually, given an environment state, some optimization methods will be applied to search for a set of working parameters such that some objective function is optimized. These methods could be simple, like discrete brute-force (BF), line-search (LS), and simulated annealing (SA), or more complex, like genetic algorithm (GA), particle swam optimization (PSO), bat algorithm optimization (BAO), and ant colony optimization (ACO) [33][34][35]. However, in rapidly changing environments, if finding working parameters takes a long time, then the system might not adapt to the change and may fail to work properly. ...
In this paper, a secure uplink non-orthogonal multiple access (NOMA) internet of things (IoT) system using an energy harvesting unmanned aerial vehicle (UAV) is studied. The communication protocol includes three phases: The first phase is an energy harvesting phase in which the IoT devices and UAV relay harvest radio frequency energy from a power beacon. The second phase is information transmission from IoT devices to a UAV relay. The third phase is relaying transmission from the UAV relay to the base station. Furthermore, a UAV eavesdropper (UE) wiretaps the signals from the IoT devices and UAV relay in the second and third phases. For this system, we derived the closed-form outage and intercept probabilities to evaluate the system and secrecy performances. The constrained optimization algorithm for minimizing the outage probability is then deployed to obtain training data. Finally, a deep learning model is trained to predict the optimal configuration parameters, enabling rapid adaptation to environmental conditions.
... The meta heuristic algorithm can get approximate optimal solution in these problems [13][14][15]. Therefore, the meta heuristic algorithms such as Particle Swarm Optimisation (PSO) [16] and their improved algorithms are widely used in task pre-allocation [10,17,18]. The existing improved PSO mainly enhanced in three aspects: the formula of velocity and position [19,20], the parameters updating formula [21,22] and combination with other algorithms [23,24]. ...
Nowadays, multi unmanned aerial vehicle (multi‐UAV) systems have been widely used in battlefield. The rationality of mission plan can directly affect the effectiveness of multi‐UAV system. The existing multi‐UAV task allocation model lack a comprehensive modelling of task pre‐allocation and task reallocation issues. However, in actual task execution, task pre‐allocation and task reallocation are a holistic problem. Therefore, based on the background of multi‐UAV cooperative reconnaissance, the authors establish a multi‐UAV cooperative reconnaissance task pre‐allocation and reallocation model (MCRTPR). There are two kinds of task allocation in MCRTPR model. One is task pre‐allocation, which is a static task allocation before the mission begin. Another is task reallocation, that is a dynamic task allocation during the mission. For task pre‐allocation, a particle swarm optimisation algorithm based on experience pool (EPPSO) is proposed. And for task reallocation, the authors design a partial task reallocation algorithm based on contract network protocol (CNP‐PTR). The experimental results show that, compared with some state‐of‐the‐art algorithms, EPPSO can get the lowest fitness value under various experimental conditions, and CNP‐PTR is able to handle task reallocation problem caused by multiple kinds of dynamic events.
... Noticeably, the search procedures to find solutions that yield better trade-offs are computational efforts whose stops need to be instructed. A study of the algorithm search stopping criteria used in drone-assisted routing problems heuristic-based approaches shows that the most common criteria are threefold: using a stopping criterion that considers that a certain number of iterations have been performed without finding any improvement in the solution; using a maximum number of iterations without considering any other factor, as in (Yan et al., 2021) or (Almuhaideb et al., 2021); or using a maximum computation time without considering any other factor. There are also algorithms in which two criteria are used simultaneously for stopping, such as Zhou, Zhang, Shi, Liu, and Huang (2018), which jointly employs a maximum number of iterations without improvement and a maximum number of iterations, and (Luo et al., 2021), where a maximum computation time and a maximum number of iterations without improvement are jointly employed with the application of a coefficient. ...
In the rapidly expanding field of e-commerce logistics, the optimisation of last-mile delivery solutions is paramount. This paper introduces a novel methodology that addresses this challenge by generating approximate Pareto fronts in a hybrid truck-drone delivery system. Specifically, we examine a generalized single truck multi-drone problem that allows multi-visit flight missions and rendezvous points distinct from launch locations. Our goal is providing decision-makers with a portfolio of optimal routing solutions that balance service time and environmental impact, criteria that are increasingly shaping decision-making in this domain. To achieve this, we introduce a bivector coding scheme inspired by flow-shop scheduling problems and implement a Simulated Annealing algorithm. This algorithm features an advanced stopping mechanism, negating the need for manual adjustments by utilizing a distinctive blend of a domination rate and a Kalman filter. Importantly, our framework employs an iterated greedy search algorithm to evolve from initial solutions towards identifying non-dominated solutions sets, which are then ranked using a hypervolume coefficient. To validate our methodology, we conduct a sensitivity analysis on two different size instances using a full factorial design of experiments. Our analysis reveals crucial insights into the impact of the number of drones, their autonomy, and their flight speed settings. From it, we conclude that it is a robust and adaptable framework for its practical application for obtaining Pareto fronts solutions among which picking the ultimate routing to be implemented.
... The study outlined in reference [24] introduces an integrated algorithm for the distributed collaborative dynamic task planning of UAVs, effectively tackling complex planning issues within dynamic task scenarios. Reference [25] proposes an intelligent marine task allocation and route planning algorithm for multiple UAVs, which combines improved particle swarm optimization with a genetic algorithm to address random task allocation for multiple UAVs and two-dimensional route planning for a single UAV through the introduction of partial matching crossover and secondary transposition mutation. ...
This paper puts forward a joint optimization algorithm of task assignment and flight path planning for a heterogeneous unmanned aerial vehicle (UAV) cluster in a multi-mission scenario (MMS). The basis of the proposed algorithm is to establish constraint and threat models of a heterogeneous UAV cluster to simultaneously minimize range and maximize value gain and survival probability in an MMS under the constraints of task payload, range, and task requirement. On one hand, the objective function for the heterogeneous UAV cluster within an MMS is derived and it is adopted as a metric for assessing the performance of the joint optimization in task assignment and flight path planning. On the other hand, since the formulated joint optimization problem is a multi-objective, non-linear, and non-convex optimization model due to its multiple decision variables and constraints, the roulette wheel selection (RWS) principle and the elite strategy (ES) are introduced in an ant colony optimization (ACO) to solve the complex optimization model. The simulation results indicate that the proposed algorithm is superior and more efficient compared to other approaches.
... Here, PSO is used as a quality mission start planner with high computational cost but little flexibility and resilience. Combination with other algorithms is also possible, as is the case in [14], where PSO is combined with genetic algorithms (GAs) by introducing crossover and mutation to the former. Similarly, in [15], simulated annealing (SA) is included in the inner loop of PSO to improve the local search and still preserve the fast convergence of PSO. ...
This paper summarizes in depth the state of the art of aerial swarms, covering both classical and new reinforcement-learning-based approaches for their management. Then, it proposes a hybrid AI system, integrating deep reinforcement learning in a multi-agent centralized swarm architecture. The proposed system is tailored to perform surveillance of a specific area, searching and tracking ground targets, for security and law enforcement applications. The swarm is governed by a central swarm controller responsible for distributing different search and tracking tasks among the cooperating UAVs. Each UAV agent is then controlled by a collection of cooperative sub-agents, whose behaviors have been trained using different deep reinforcement learning models, tailored for the different task types proposed by the swarm controller. More specifically, proximal policy optimization (PPO) algorithms were used to train the agents’ behavior. In addition, several metrics to assess the performance of the swarm in this application were defined. The results obtained through simulation show that our system searches the operation area effectively, acquires the targets in a reasonable time, and is capable of tracking them continuously and consistently.
... Before a reconnaissance mission begins, multi-UAV systems need to assign tasks according to static prior information and obtain the initial mission plan. In recent years, many researchers have established models and proposed solutions to such task assignment problems [12][13][14][15][16]. However, there are many uncertainties in the actual task execution process, such as target movement, drone damage, and many other dynamic events [17]. ...
... Similarly, this article randomly initializes the locations of the twenty targets within the given range and randomly selects five targets to set the time window constraints. The initialization information of targets is shown in Table 2. Before the mission starts, the offline task assignment algorithm is first used to obtain the initial mission plan: Plan = [ [2,13,5,4], [6,15,12], [1,14], [7,16,17,18], [], [], [8,19,9], [0, 10,11,3]]. The Plan is a two-dimensional list, where the sub-list represents the scheme of each UAV. ...
... The numbers next to the targets icon indicate targets' number, the same is true later. Before the mission starts, the offline task assignment algorithm is first used to obtain the initial mission plan: = [ [2,13,5,4], [6,15,12], [1,14], [7,16,17,18], [], [], [8,19,9], [0, 10,11,3]]. The is a two-dimensional list, where the sub-list represents the scheme of each UAV. ...
Multi-UAV systems have been widely used in reconnaissance, disaster relief, communication, and other fields. However, many dynamic events can cause a partial failure of the original mission during the mission execution process, in which case task reassignment should be carried out. How to reassign resources and tasks in multi-dynamic, multi-target, and multi-constraint events becomes a core issue in the enhancement of combat efficiency. This paper establishes a model of multi-UAV cooperative reconnaissance task reassignment that comprehensively considers various dynamic factors such as UAV performance differences, size of target areas, and time window constraints. Then, a two-stage distributed task assignment algorithm (TS-DTA) is presented to achieve multi-task reassignment in dynamic environments. Finally, this paper verifies the effectiveness of the TS-DTA algorithm through simulation experiments and analyzes its performance through comparative experiments. The experimental results show that the TS-DTA algorithm can efficiently solve the task reassignment problem in dynamic environments while effectively reducing the communication burden of UAV formations.
... Moreover, meta-heuristic algorithms do not require information on the gradient of the objective function, which makes them more applicable. As a result, meta-heuristic algorithms have been widely applied to various practical problems (Yang et al. 2022, Ornek et al. 2022, such as jobshop scheduling problems (JSP) (Gao et al. 2020), automatic control (Tabak and İlhan 2022), text document clustering (Abualigah 2019), image processing (Djemame et al. 2019), and route planning (Yan et al. 2021). ...
This paper presents an improved arithmetic optimization algorithm that incorporates hybrid elite pool strategies to address the limitations of the arithmetic optimization algorithm (AOA). In AOA, the linear mathematical optimization acceleration (MOA) function cannot balance global exploitation and local exploration well. Therefore, the accuracy and convergence speed of the algorithm cannot be guaranteed. To improve the performance of AOA, this paper reconstructed a nonlinear MOA function, which is expected to balance the exploitation and the exploration of AOA. Furthermore, four hybrid elite pool strategies are integrated to enhance the ability to escape local optima. The proposed algorithm inherits the fast convergence of AOA and develops the performance of escaping local optima. Numerical experiment results on benchmark functions and engineering problems show that the proposed algorithm outperforms other compared meta-heuristic algorithms in terms of convergence speed and accuracy.
