针对复杂未知环境下的移动机器人路径规划问题，提出一种优化已搜索节点和已规划部分路径的改进RRT_Connect算法。算法引入了终点和已搜索节点目标偏向策略，该策略在随机采样函数中引入终点和已搜索节点偏向概率基准值，使随机采样点按随机概率设定为终点或已搜索节点；通过筛选有效新节点和一定范围内邻节点的父节点，优化路径规划成本，使规划路径趋于平滑。仿真结果表明，提出的改进RRT_Connect算法所规划的路径在平均转弯次数、平均规划路径长度和平均规划成功率等指标较改进前更优。
Path planning is an indispensable technology in the field of robot research. Aiming at the path planning problem of mobile robot in complex unknown environment, an improved RRT_Connect algorithm is proposed to optimize the searched nodes and planned partial paths. Firstly, the algorithm introduces bias strategy of endpoint and searched node, which introduces bias probability reference value of endpoint and searched node in random sampling function, so that random sampling point is set as endpoint or searched node according to random probability. Then, by screening the effective new nodes and the parents of neighboring nodes in a certain range, the path planning cost is optimized to make the planned path tend to be smooth. The simulation results show that the path planned by the proposed improved RRT_Connect algorithm is better than before in terms of the average number of turns, average planned path length and average planning success rate.
[1] Zhu Z X, Wang F X, He S, et al. Global path planning of mobile robots using a memetic algorithm[J]. International Journal of Systems Science, 2015, 46(11):1982-1993.
[2] Sivaranjani A, Vinod B. Artificial potential field incorporated deep-Q-network algorithm for mobile robot path prediction[J]. Intelligent Automation&Soft Computing, 2023, 35(1):1135-1150.
[3] Liu L S, Yao J X, He D W, et al. Global dynamic path planning fusion algorithm combining jump-A*algorithm and dynamic window approach[J]. IEEE Access, 2021, 9:19632-19638.
[4] 杨韵,王成彦,巫凯旋,等.移动机器人全局路径规划算法综述[J].信息记录材料, 2022, 23(3):29-32.
[5] 宋永杰,孟祥印,翟守才,等.改进Bi-RRT算法的AGV全局路径规划[J].机械设计与制造, 2022(8):287-291, 296.
[6] Wang X Y, Li X J, Guan Y, et al. Bidirectional potential guided RRT*for motion planning[J]. IEEE Access, 2019, 7:95046-95057.
[7] Kurenkov M, Potapov A, Savinykh A, et al. NFOMP:Neural field for optimal motion planner of differential drive robots with nonholonomic constraints[J]. IEEE Robotics and Automation Letters, 2022, 7(4):10991-10998.
[8] Ma N C, Wang J K, Liu J B, et al. Conditional generative adversarial networks for optimal path planning[J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(2):662-671.
[9] LaValle S M, Kuffner J J Jr. Randomized kinodynamic planning[J]. The International Journal of Robotics Research, 2001, 20(5):378-400.
[10] Chen Y Y, Fu Y X, Zhang B, et al. Path planning of the fruit tree pruning manipulator based on improved RRTConnect algorithm[J]. International Journal of Agricultural and Biological Engineering, 2022, 15(2):177-188.
[11] 王海芳,崔阳阳,李鸣飞,等.基于改进RRT*FN的移动机器人路径规划算法[J].东北大学学报(自然科学版), 2022, 43(9):1217-1224, 1249.
[12] 赵文龙, Abdou Y M S.基于改进RRT算法的移动机器人路径规划方法[J].计算机与数字工程, 2022, 50(8):1733-1738.
[13] Fan Q G, Cui G M, Zhao Z Q, et al. Obstacle avoidance for microrobots in simulated vascular environment based on combined path planning[J]. IEEE Robotics and Automation Letters, 2022, 7(4):9794-9801.
[14] Ayawli B B K, Mei X, Shen M Q, et al. Optimized RRTA*path planning method for mobile robots in partially known environment[J]. Information Technology and Control, 2019, 48(2):179-194.
[15] Sun Y X, Zhang C R, Sun P C, et al. Safe and smooth motion planning for mecanum-wheeled robot using improved RRT and cubic spline[J]. Arabian Journal for Science and Engineering, 2020, 45(4):3075-3090.
[16] Li B H, Chen B D. An adaptive rapidly-exploring random tree[J]. CAA Journal of Automatica Sinica, 2022, 9(2):283-294.
[17] Ganesan S, Natarajan S K, Srinivasan J. A global path planning algorithm for mobile robot in cluttered environments with an improved initial cost solution and convergence rate[J]. Arabian Journal for Science and Engineering, 2022, 47(3):3633-3647.
[18] 韦玉海,张辉,刘理,等.基于AMRRT-Connect算法的移动机器人路径规划[J].武汉大学学报(工学版), 2022, 55(5):531-538.
[19] Karaman S, Frazzoli E. Sampling-based algorithms for optimal motion planning[J]. The International Journal of Robotics Research, 2011, 30(7):846-894.
[20] 王赟.基于RRT轮式机器人路径规划方法研究[D].天津:天津工业大学, 2019.
[21] Qi J, Yang H, Sun H X. MOD-RRT*:A samplingbased algorithm for robot path planning in dynamic environment[J]. IEEE Transactions on Industrial Electronics, 2021, 68(8):7244-7251.
[22] Ryu H, Park Y. Improved informed RRT*using gridmap skeletonization for mobile robot path planning[J]. International Journal of Precision Engineering and Manufacturing, 2019, 20(11):2033-2039. rong-about-chinaand-technical-standards-pub-89110.
