穿越稠密障碍物的自适应动态窗口法
|
摘要
针对应用广泛的局部避障算法—–动态窗口法(DWA)穿越稠密障碍物时存在路径不合理、速度和安全性不能兼顾等问题,提出参数自适应的DWA算法,根据机器人与障碍物距离和障碍物的密集度自动调整目标函数中的权值,以自适应环境的动态变化,从而获得移动机器人的最佳运行速度和合理路径.该方法可明显改善机器人穿越稠密障碍物区域时的性能;同时,该方法还可避免机器人从密集障碍物区域外绕行以及轨迹不平滑现象.仿真实验表明:改进的DWA算法在复杂环境中通过逐步优化可使运行轨迹更加合理,能够同时兼顾路径平滑性和安全性;机器人在离稠密障碍物较远处保持高速,通过狭窄通道或者稠密障碍物区域时速度适当降低,安全性更高,实验中总迭代次数和运行时间可缩短20%以上.
Dynamic window approaches(DWAs) are widely used in local obstacle avoidance of mobile robots. A selfadaptive DWA algorithm is proposed for the problem that the classical DWA exists unreasonable path in dense obstacles and it cannot ensure both speed and security. In order to adapt to the dynamic environment, the weight of speed in the target function is adjusted automatically based on the distance and orientation between the robot and obstacles. The optimal velocity and reasonable planned path of the mobile robot are obtained using the self-adaptive DWA. Thus the performance of the robot crossing an area of dense obstacle is significantly improved. The problems that the robot might move around the dense obstacles and result in an unsmooth path are solved. Our experiments show that the proposed algorithm can make running track more reasonable through gradual optimization in the complex environment than old one, and it ensures the smoothness and security of robot route simultaneously. When the robot is far from the dense obstacles, the robot keeps high speed. When the robot passes through a narrow passage or a dense obstacle area, the speed appropriately reduces and the safety grows high. The total number of iterations and the run-time can be reduced more than 20 % in our experiments.
Dynamic window approaches(DWAs) are widely used in local obstacle avoidance of mobile robots. A selfadaptive DWA algorithm is proposed for the problem that the classical DWA exists unreasonable path in dense obstacles and it cannot ensure both speed and security. In order to adapt to the dynamic environment, the weight of speed in the target function is adjusted automatically based on the distance and orientation between the robot and obstacles. The optimal velocity and reasonable planned path of the mobile robot are obtained using the self-adaptive DWA. Thus the performance of the robot crossing an area of dense obstacle is significantly improved. The problems that the robot might move around the dense obstacles and result in an unsmooth path are solved. Our experiments show that the proposed algorithm can make running track more reasonable through gradual optimization in the complex environment than old one, and it ensures the smoothness and security of robot route simultaneously. When the robot is far from the dense obstacles, the robot keeps high speed. When the robot passes through a narrow passage or a dense obstacle area, the speed appropriately reduces and the safety grows high. The total number of iterations and the run-time can be reduced more than 20 % in our experiments.
引文
[1]丛岩峰.基于滚动优化原理的路径规划方法研究[D].吉林:吉林大学通信工程学院, 2007.(Cong Y F. The path planning method research based on rolling optimization theory[D]. Changchun:College of Communication Engineering, Jilin University, 2007.)
[2]马仁利,关正西.路径规划技术的现状与发展综述[J].现代机械, 2008(3):22-25.(Ma R L, Guan Z X. Summarization for present situation and future development of path planning technology[J].Modern Machinery, 2008(3):22-25.)
[3] Borenstein J. The vector field histogram-fast obstacle avoidance for mobile robots[J]. IEEE Trans on Robotics&Automation, 2002, 7(3):278-288.
[4] Ulrich I, Borenstein J. VFH+:Reliable obstacle avoidance for fast mobile robots[M]. Tamil Nadu:Jayalakshmi Institute of Technology, 1998:1572-1577.
[5] Ulrich I, Borenstein J. VFH*:Local obstacle avoidance with look-ahead verification[C]. IEEE Int Conf on Robotics and Automation. San Francisco:IEEE, 2000:2505-2511.
[6] Simmons R. The curvature-velocity method for local obstacle avoidance[C]. IEEE Int Conf on Robotics and Automation. Minneapolis:IEEE Xplore, 1996:3375-3382.
[7] Fox D, Burgard W, Thrun S, et al. The dynamic window approach to collision avoidance[J]. Robotics&Automation Magazine, 1997, 4(1):23-33.
[8] Seder M, Petrovic I. Dynamic window based approach to mobile robot motion control in the presence of moving obstacles[C]. IEEE Int Conf on Robotics and Automation.Roma:IEEE, 2007:1986-1991.
[9] Masahiro Shiomi. Towards a socially acceptable collision avoidance for a mobile robot navigating among pedestrians using a pedestrian model[J]. Int J of Social Robotics, 2014, 6(3):443-455.
[10] Doopalam Tuvshinjargal. Hybrid motion planning method for autonomous robots using kinect based sensor fusion and virtual plane approach in dynamic environments[J]. J of Sensors, 2015(5):1-13.
[11] Ana Lopes A, Rodrigues J, Perdigao J, et al. A new hybrid motion planner:Applied in a brain-actuated robotic wheelchair[J]. IEEE Robotics&Automation Magazine,2016, 23(4):82-93.
[12] Beomjoon Kim. Socially adaptive path planning in human environments using inverse reinforcement learning[J]. Int J of Social Robotics, 2016, 8(1):51-66.
[13]曲道奎,杜振军,徐殿国,等.移动机器人路径规划方法研究[J].机器人, 2008, 30(2):97-101.(Qu D K, Du Z J, Xu D G, et al. Research on Path Planning for a mobile robot[J]. Robot, 2008, 30(2):97-101.)
[14] Trautman P, Ma J, Murray R M, et al. Robot navigation in dense human crowds:The case for cooperation[C]. IEEE Int Conf on Robotics and Automation. Karlsruhe:IEEE,2013:2153-2160.
[2]马仁利,关正西.路径规划技术的现状与发展综述[J].现代机械, 2008(3):22-25.(Ma R L, Guan Z X. Summarization for present situation and future development of path planning technology[J].Modern Machinery, 2008(3):22-25.)
[3] Borenstein J. The vector field histogram-fast obstacle avoidance for mobile robots[J]. IEEE Trans on Robotics&Automation, 2002, 7(3):278-288.
[4] Ulrich I, Borenstein J. VFH+:Reliable obstacle avoidance for fast mobile robots[M]. Tamil Nadu:Jayalakshmi Institute of Technology, 1998:1572-1577.
[5] Ulrich I, Borenstein J. VFH*:Local obstacle avoidance with look-ahead verification[C]. IEEE Int Conf on Robotics and Automation. San Francisco:IEEE, 2000:2505-2511.
[6] Simmons R. The curvature-velocity method for local obstacle avoidance[C]. IEEE Int Conf on Robotics and Automation. Minneapolis:IEEE Xplore, 1996:3375-3382.
[7] Fox D, Burgard W, Thrun S, et al. The dynamic window approach to collision avoidance[J]. Robotics&Automation Magazine, 1997, 4(1):23-33.
[8] Seder M, Petrovic I. Dynamic window based approach to mobile robot motion control in the presence of moving obstacles[C]. IEEE Int Conf on Robotics and Automation.Roma:IEEE, 2007:1986-1991.
[9] Masahiro Shiomi. Towards a socially acceptable collision avoidance for a mobile robot navigating among pedestrians using a pedestrian model[J]. Int J of Social Robotics, 2014, 6(3):443-455.
[10] Doopalam Tuvshinjargal. Hybrid motion planning method for autonomous robots using kinect based sensor fusion and virtual plane approach in dynamic environments[J]. J of Sensors, 2015(5):1-13.
[11] Ana Lopes A, Rodrigues J, Perdigao J, et al. A new hybrid motion planner:Applied in a brain-actuated robotic wheelchair[J]. IEEE Robotics&Automation Magazine,2016, 23(4):82-93.
[12] Beomjoon Kim. Socially adaptive path planning in human environments using inverse reinforcement learning[J]. Int J of Social Robotics, 2016, 8(1):51-66.
[13]曲道奎,杜振军,徐殿国,等.移动机器人路径规划方法研究[J].机器人, 2008, 30(2):97-101.(Qu D K, Du Z J, Xu D G, et al. Research on Path Planning for a mobile robot[J]. Robot, 2008, 30(2):97-101.)
[14] Trautman P, Ma J, Murray R M, et al. Robot navigation in dense human crowds:The case for cooperation[C]. IEEE Int Conf on Robotics and Automation. Karlsruhe:IEEE,2013:2153-2160.