To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the conc...To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the concept of particle sight distance,an improved algorithm,called SD-IPSO,is proposed for the real-time autonomous navigation of USVs in marine environments.The algorithm refines the individual behavior pattern of particles in the population,effectively improving both local and global search capabilities while avoiding premature convergence.The effectiveness of the algorithm is validated using standard test functions from CEC-2017 function library,assessing it from multiple dimensions.Sensitivity analysis is conducted on key parameters in the algorithm,including particle sight distance and population size.Results indicate that compared with PSO,SD-IPSO demonstrates significant advantages in optimization accuracy and convergence speed.The application of SD-IPSO in path planning is further investigated through a 14-point traveling salesman problem(TSP)example and navigation autonomous tests of USVs in marine environments.Findings demonstrate that the proposed algorithm exhibits superior optimization capabilities and can effectively address the path planning challenges of USVs.展开更多
This paper presents an investigation on the target-guided coordinated control(TACC)of unmanned surface vehicles(USVs).In the scenario of tracking non-cooperative targets,the status information of the target can only b...This paper presents an investigation on the target-guided coordinated control(TACC)of unmanned surface vehicles(USVs).In the scenario of tracking non-cooperative targets,the status information of the target can only be obtained by some USVs.In order to achieve semi-encirclement tracking of noncooperative targets under maritime security conditions,a fixed-time tracking control method based on dynamic surface control(DSC)is proposed in this paper.Firstly,a novel TACC architecture with decoupled kinematic control law and decoupled kinetic control law was designed to reduce the complexity of control system design.Secondly,the proposed DSC-based target-guided kinematic control law including tracking points pre-allocation strategy and sigmoid artificial potential functions(SigAPFs)can avoid collisions during tracking process and optimize kinematic control output.Finally,a fixed-time TACC system was proposed to achieve fast convergence of kinematic and kinetics errors.The effectiveness of the proposed TACC approach in improving target tracking safety and reducing control output chattering was verified by simulation comparison results.展开更多
The trajectory tracking control problem for underactuated unmanned surface vehicles(USV) was addressed, and the control system took account of the uncertain influences induced by model perturbation, external disturban...The trajectory tracking control problem for underactuated unmanned surface vehicles(USV) was addressed, and the control system took account of the uncertain influences induced by model perturbation, external disturbance, etc. By introducing the reference, trajectory was generated by a virtual USV, and the error equation of trajectory tracking for USV was obtained, which transformed the tracking problem of underactuated USV into the stabilization problem of the trajectory tracking error equation. A backstepping adaptive sliding mode controller was proposed based on backstepping technology and method of dynamic slide model control. By means of theoretical analysis, it is proved that the proposed controller ensures that the solutions of closed loop system have the ultimate boundedness property. Simulation results are presented to illustrate the effectiveness of the proposed controller.展开更多
Wave driven unmanned surface vehicle(WUSV) is a new concept ocean robot drived by wave energy and solar energy,and it is very suitable for the vast ocean observations with incomparable endurance.Its dynamic modeling i...Wave driven unmanned surface vehicle(WUSV) is a new concept ocean robot drived by wave energy and solar energy,and it is very suitable for the vast ocean observations with incomparable endurance.Its dynamic modeling is very important because it is the theoretical foundation for further study in the WUSV motion control and efficiency analysis.In this work,the multibody system of WUSV was described based on D-H approach.Then,the driving principle was analyzed and the dynamic model of WUSV in longitudinal profile is established by Lagrangian mechanics.Finally,the motion simulation of WUSV and comparative analysis are completed by setting different inputs of sea state.Simulation results show that the WUSV dynamic model can correctly reflect the WUSV longitudinal motion process,and the results are consistent with the wave theory.展开更多
To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal po...To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal policy opti-mization(DPPO)algorithm,which is a modified actor-critic-based type of reinforcement learning algorithm,is adapted to improve the controller performance in repeated trials.The LSTM network structure is introduced to solve the strong temporal cor-relation USV control problem.In addition,a specially designed path dataset,including straight and curved paths,is established to simulate various sailing scenarios so that the reinforcement learning controller can obtain as much handling experience as possible.Extensive numerical simulation results demonstrate that the proposed method has better control performance under missions involving complex maneuvers than trained with limited scenarios and can potentially be applied in practice.展开更多
To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model wit...To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.展开更多
The path following problem for an underactuated unmanned surface vehicle(USV) in the Serret-Frenet frame is addressed. The control system takes account of the uncertain influence induced by model perturbation, externa...The path following problem for an underactuated unmanned surface vehicle(USV) in the Serret-Frenet frame is addressed. The control system takes account of the uncertain influence induced by model perturbation, external disturbance, etc. By introducing the Serret-Frenet frame and global coordinate transformation, the control problem of underactuated system(a nonlinear system with single-input and ternate-output) is transformed into the control problem of actuated system(a single-input and single-output nonlinear system), which simplifies the controller design. A backstepping adaptive sliding mode controller(BADSMC)is proposed based on backstepping design technique, adaptive method and theory of dynamic slide model control(DSMC). Then, it is proven that the state of closed loop system is globally stabilized to the desired configuration with the proposed controller. Simulation results are presented to illustrate the effectiveness of the proposed controller.展开更多
A safe and reliable path planning algorithm is fundamental for unmanned surface vehicles(USVs)to perform autonomous navigation tasks.However,a single global or local planning strategy cannot fully meet the requirement...A safe and reliable path planning algorithm is fundamental for unmanned surface vehicles(USVs)to perform autonomous navigation tasks.However,a single global or local planning strategy cannot fully meet the requirements of complex maritime environments.Global planning alone cannot effectively handle dynamic obstacles,while local planning alone may fall into local optima.To address these issues,this paper proposes a multi-dynamic-obstacle avoidance path planning method that integrates an improved A^(*)algorithm with the dynamic window approach(DWA).The traditional A^(*)algorithm often generates paths that are too close to obstacle boundaries and contain excessive turning points,whereas the traditional DWA tends to skirt densely clustered obstacles,resulting in longer routes and insufficient dynamic obstacle avoidance.To overcome these limitations,improved versions of both algorithms are developed.Key points extracted from the optimized A^(*)path are used as intermediate start-destination pairs for the improved DWA,and the weights of the DWA evaluation function are adjusted to achieve effective fusion.Furthermore,a multi-dynamic-obstacle avoidance strategy is designed for complex navigation scenarios.Simulation results demonstrate that the USV can adaptively switch between dynamic obstacle avoidance and path tracking based on obstacle distribution,validating the effectiveness of the proposed method.展开更多
The path-following control of the asymmetry underactuated unmanned surface vehicle(USV) under external disturbances such as unknown constant and irrational ocean currents is discussed, and an adaptive sliding-mode pat...The path-following control of the asymmetry underactuated unmanned surface vehicle(USV) under external disturbances such as unknown constant and irrational ocean currents is discussed, and an adaptive sliding-mode path-following control system is proposed, which comprises a path-variable updated law,a modified integral line-of-sight(ILOS) guidance law based on a time-varying lookahead distance and adaptive feedback linearizing controllers combined with sliding-mode technique. A more accurate USV model without the assumption of having diagonal inertia and damping matrices is first presented, aiming at improving the performance of the path-following control. Next, the coordinate transformation is adopted to decouple the sway dynamic from the rudder angle, and the path-following errors dynamics without non-singular problem are presented in the moving Frenet-Serret frame. Then, based on the cascaded theorem and the adaptive sliding-mode method, the adaptive control law of position errors and course error are designed, among which the lookahead distance and integral gain are all computed as different functions of cross-track error to estimate and compensate the sideslip angle caused by external disturbances adaptively. Finally, according to the Lyapunov and cascaded theorem, the control system proposed is proved to be uniform globally asymptotic stability(UGAS) and uniform semiglobal exponential stability(USGES) when the control objectives are all achieved. Simulation results illustrate the precision and high-quality performance of this new controller.展开更多
文摘To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the concept of particle sight distance,an improved algorithm,called SD-IPSO,is proposed for the real-time autonomous navigation of USVs in marine environments.The algorithm refines the individual behavior pattern of particles in the population,effectively improving both local and global search capabilities while avoiding premature convergence.The effectiveness of the algorithm is validated using standard test functions from CEC-2017 function library,assessing it from multiple dimensions.Sensitivity analysis is conducted on key parameters in the algorithm,including particle sight distance and population size.Results indicate that compared with PSO,SD-IPSO demonstrates significant advantages in optimization accuracy and convergence speed.The application of SD-IPSO in path planning is further investigated through a 14-point traveling salesman problem(TSP)example and navigation autonomous tests of USVs in marine environments.Findings demonstrate that the proposed algorithm exhibits superior optimization capabilities and can effectively address the path planning challenges of USVs.
文摘This paper presents an investigation on the target-guided coordinated control(TACC)of unmanned surface vehicles(USVs).In the scenario of tracking non-cooperative targets,the status information of the target can only be obtained by some USVs.In order to achieve semi-encirclement tracking of noncooperative targets under maritime security conditions,a fixed-time tracking control method based on dynamic surface control(DSC)is proposed in this paper.Firstly,a novel TACC architecture with decoupled kinematic control law and decoupled kinetic control law was designed to reduce the complexity of control system design.Secondly,the proposed DSC-based target-guided kinematic control law including tracking points pre-allocation strategy and sigmoid artificial potential functions(SigAPFs)can avoid collisions during tracking process and optimize kinematic control output.Finally,a fixed-time TACC system was proposed to achieve fast convergence of kinematic and kinetics errors.The effectiveness of the proposed TACC approach in improving target tracking safety and reducing control output chattering was verified by simulation comparison results.
基金Project(51409061)supported by the National Natural Science Foundation of ChinaProject(2013M540271)supported by China Postdoctoral Science Foundation+1 种基金Project(LBH-Z13055)Supported by Heilongjiang Postdoctoral Financial Assistance,ChinaProject(HEUCFD1403)supported by Basic Research Foundation of Central Universities,China
文摘The trajectory tracking control problem for underactuated unmanned surface vehicles(USV) was addressed, and the control system took account of the uncertain influences induced by model perturbation, external disturbance, etc. By introducing the reference, trajectory was generated by a virtual USV, and the error equation of trajectory tracking for USV was obtained, which transformed the tracking problem of underactuated USV into the stabilization problem of the trajectory tracking error equation. A backstepping adaptive sliding mode controller was proposed based on backstepping technology and method of dynamic slide model control. By means of theoretical analysis, it is proved that the proposed controller ensures that the solutions of closed loop system have the ultimate boundedness property. Simulation results are presented to illustrate the effectiveness of the proposed controller.
基金Project(2012-Z05)supported by the State Key Laboratory of Robotics,ChinaProjects(61233013,51179183)supported by the National Natural Science Foundation of China
文摘Wave driven unmanned surface vehicle(WUSV) is a new concept ocean robot drived by wave energy and solar energy,and it is very suitable for the vast ocean observations with incomparable endurance.Its dynamic modeling is very important because it is the theoretical foundation for further study in the WUSV motion control and efficiency analysis.In this work,the multibody system of WUSV was described based on D-H approach.Then,the driving principle was analyzed and the dynamic model of WUSV in longitudinal profile is established by Lagrangian mechanics.Finally,the motion simulation of WUSV and comparative analysis are completed by setting different inputs of sea state.Simulation results show that the WUSV dynamic model can correctly reflect the WUSV longitudinal motion process,and the results are consistent with the wave theory.
基金supported by the National Natural Science Foundation(61601491)the Natural Science Foundation of Hubei Province(2018CFC865)the China Postdoctoral Science Foundation Funded Project(2016T45686).
文摘To solve the path following control problem for unmanned surface vehicles(USVs),a control method based on deep reinforcement learning(DRL)with long short-term memory(LSTM)networks is proposed.A distributed proximal policy opti-mization(DPPO)algorithm,which is a modified actor-critic-based type of reinforcement learning algorithm,is adapted to improve the controller performance in repeated trials.The LSTM network structure is introduced to solve the strong temporal cor-relation USV control problem.In addition,a specially designed path dataset,including straight and curved paths,is established to simulate various sailing scenarios so that the reinforcement learning controller can obtain as much handling experience as possible.Extensive numerical simulation results demonstrate that the proposed method has better control performance under missions involving complex maneuvers than trained with limited scenarios and can potentially be applied in practice.
基金financial support from National Natural Science Foundation of China(Grant No.61601491)Natural Science Foundation of Hubei Province,China(Grant No.2018CFC865)Military Research Project of China(-Grant No.YJ2020B117)。
文摘To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.
基金Project(51409061)supported by the National Natural Science Foundation of ChinaProject(2013M540271)supported by China Postdoctoral Science Foundation+1 种基金Project(LBH-Z13055)supported by Heilongjiang Postdoctoral Financial Assistance,ChinaProject(HEUCFD1403)supported by Basic Research Foundation of Central Universities,China
文摘The path following problem for an underactuated unmanned surface vehicle(USV) in the Serret-Frenet frame is addressed. The control system takes account of the uncertain influence induced by model perturbation, external disturbance, etc. By introducing the Serret-Frenet frame and global coordinate transformation, the control problem of underactuated system(a nonlinear system with single-input and ternate-output) is transformed into the control problem of actuated system(a single-input and single-output nonlinear system), which simplifies the controller design. A backstepping adaptive sliding mode controller(BADSMC)is proposed based on backstepping design technique, adaptive method and theory of dynamic slide model control(DSMC). Then, it is proven that the state of closed loop system is globally stabilized to the desired configuration with the proposed controller. Simulation results are presented to illustrate the effectiveness of the proposed controller.
基金supported by the National Nature Science Foundation of China(62203299,62373246,62388101)the Research Fund of State Key Laboratory of Deep-Sea Manned Vehicles(2024SKLDMV04)+1 种基金the Oceanic Interdisciplinary Program of Shanghai Jiao Tong University(SL2023MS007)the Startup Fund for Young Faculty at SJTU(24X010502929)。
文摘A safe and reliable path planning algorithm is fundamental for unmanned surface vehicles(USVs)to perform autonomous navigation tasks.However,a single global or local planning strategy cannot fully meet the requirements of complex maritime environments.Global planning alone cannot effectively handle dynamic obstacles,while local planning alone may fall into local optima.To address these issues,this paper proposes a multi-dynamic-obstacle avoidance path planning method that integrates an improved A^(*)algorithm with the dynamic window approach(DWA).The traditional A^(*)algorithm often generates paths that are too close to obstacle boundaries and contain excessive turning points,whereas the traditional DWA tends to skirt densely clustered obstacles,resulting in longer routes and insufficient dynamic obstacle avoidance.To overcome these limitations,improved versions of both algorithms are developed.Key points extracted from the optimized A^(*)path are used as intermediate start-destination pairs for the improved DWA,and the weights of the DWA evaluation function are adjusted to achieve effective fusion.Furthermore,a multi-dynamic-obstacle avoidance strategy is designed for complex navigation scenarios.Simulation results demonstrate that the USV can adaptively switch between dynamic obstacle avoidance and path tracking based on obstacle distribution,validating the effectiveness of the proposed method.
基金supported by the National Social Science Foundation of China(15GJ003-278)the National Natural Science Foundation of China(71501182)
文摘The path-following control of the asymmetry underactuated unmanned surface vehicle(USV) under external disturbances such as unknown constant and irrational ocean currents is discussed, and an adaptive sliding-mode path-following control system is proposed, which comprises a path-variable updated law,a modified integral line-of-sight(ILOS) guidance law based on a time-varying lookahead distance and adaptive feedback linearizing controllers combined with sliding-mode technique. A more accurate USV model without the assumption of having diagonal inertia and damping matrices is first presented, aiming at improving the performance of the path-following control. Next, the coordinate transformation is adopted to decouple the sway dynamic from the rudder angle, and the path-following errors dynamics without non-singular problem are presented in the moving Frenet-Serret frame. Then, based on the cascaded theorem and the adaptive sliding-mode method, the adaptive control law of position errors and course error are designed, among which the lookahead distance and integral gain are all computed as different functions of cross-track error to estimate and compensate the sideslip angle caused by external disturbances adaptively. Finally, according to the Lyapunov and cascaded theorem, the control system proposed is proved to be uniform globally asymptotic stability(UGAS) and uniform semiglobal exponential stability(USGES) when the control objectives are all achieved. Simulation results illustrate the precision and high-quality performance of this new controller.
