Path planning for recovery is studied on the engineering background of double unmanned surface vehicles(USVs)towing oil booms for oil spill recovery.Given the influence of obstacles on the sea,the improved artificial ...Path planning for recovery is studied on the engineering background of double unmanned surface vehicles(USVs)towing oil booms for oil spill recovery.Given the influence of obstacles on the sea,the improved artificial potential field(APF)method is used for path planning.For addressing the two problems of unreachable target and local minimum in the APF,three improved algorithms are proposed by combining the motion performance constraints of the double USV system.These algorithms are then combined as the final APF-123 algorithm for oil spill recovery.Multiple sets of simulation tests are designed according to the flaws of the APF and the process of oil spill recovery.Results show that the proposed algorithms can ensure the system’s safety in tracking oil spills in a complex environment,and the speed is increased by more than 40%compared with the APF method.展开更多
针对同步定位与建图(simultaneous localization and mapping,SLAM)技术对计算资源的高需求、有限环境适应性、累积误差问题、系统复杂度高、成本昂贵、大场景处理能力受限以及缺乏有效的回环检测机制的缺点,提出一种结合人工势场法和...针对同步定位与建图(simultaneous localization and mapping,SLAM)技术对计算资源的高需求、有限环境适应性、累积误差问题、系统复杂度高、成本昂贵、大场景处理能力受限以及缺乏有效的回环检测机制的缺点,提出一种结合人工势场法和深度强化学习的方法。利用图论模拟人工势场在机器人间的相互作用以及机器人与目的地之间的势场力,并采用孪生延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)算法来优化机器人对障碍物信息的感知和处理。仿真试验结果表明:该方法使机器人能够在未知环境中快速、准确地进行定位、移动,同时维持队形的稳定性和一致性。展开更多
基金Supported by the National Natural Science Foundation of China (Grant No. 52071097)Hainan Provincial Natural Science Foundation of China (Grant No. 522MS162)Research Fund from Science and Technology on Underwater Vehicle Technology Laboratory (Grant No. 2021JCJQ-SYSJJ-LB06910)。
文摘Path planning for recovery is studied on the engineering background of double unmanned surface vehicles(USVs)towing oil booms for oil spill recovery.Given the influence of obstacles on the sea,the improved artificial potential field(APF)method is used for path planning.For addressing the two problems of unreachable target and local minimum in the APF,three improved algorithms are proposed by combining the motion performance constraints of the double USV system.These algorithms are then combined as the final APF-123 algorithm for oil spill recovery.Multiple sets of simulation tests are designed according to the flaws of the APF and the process of oil spill recovery.Results show that the proposed algorithms can ensure the system’s safety in tracking oil spills in a complex environment,and the speed is increased by more than 40%compared with the APF method.
文摘针对同步定位与建图(simultaneous localization and mapping,SLAM)技术对计算资源的高需求、有限环境适应性、累积误差问题、系统复杂度高、成本昂贵、大场景处理能力受限以及缺乏有效的回环检测机制的缺点,提出一种结合人工势场法和深度强化学习的方法。利用图论模拟人工势场在机器人间的相互作用以及机器人与目的地之间的势场力,并采用孪生延迟深度确定性策略梯度(twin delayed deep deterministic policy gradient,TD3)算法来优化机器人对障碍物信息的感知和处理。仿真试验结果表明:该方法使机器人能够在未知环境中快速、准确地进行定位、移动,同时维持队形的稳定性和一致性。
