移动打孔机器人多目的地路径规划方法研究

Path Planning for Multi-destination Mobile Drilling Robots

摘要

针对建筑施工场景下移动打孔机器人多目的地作业的全局路径优化需求,提出一种融合概率路线图(PRM)、改进A^*算法与模拟退火(SA)的组合路径规划方法.首先采用PRM算法构建复杂施工环境的无向图模型,实现可行域离散化;其次,针对传统A^*算法路径平滑度不足的问题,引入Floyd算法优化路径节点,提升轨迹平滑性与避障安全性;最后,基于模拟退火算法求解多孔位最优访问顺序,实现全局路径最短.仿真结果表明:改进A^*算法较传统A^*算法路径长度缩短约10.3%,规划时长降低约29.9%;在多孔位场景下,所提组合算法相比遗传算法、粒子群算法,全局路径更短、规划效率更高,可为建筑施工场景下移动打孔机器人多目标自主路径规划提供工程参考.

Abstract

To address the global path optimization requirement for mobile drilling robots performing multi-destination operations in construction scenarios, a composite path planning method integrating Probabilistic Roadmap (PRM), improved A^* algorithm, and Simulated Annealing (SA) is proposed. First, the PRM algorithm is employed to construct an undirected graph model of the complex construction environment, achieving discretization of the feasible domain. Second, to overcome the insufficient path smoothness of the traditional A ^* algorithm, the Floyd algorithm is introduced to optimize path nodes, enhancing trajectory smoothness and obstacle avoidance safety. Finally, the simulated annealing algorithm is applied to determine the optimal visiting sequence of multiple hole positions, minimizing the total path length. Simulation results demonstrate that the improved A^* algorithm reduces path length by approximately 9.9% and planning time by approximately 25.3% compared with the traditional A^* algorithm. In multi-hole scenarios, the proposed composite algorithm achieves shorter global paths and higher planning efficiency than genetic algorithm and particle swarm optimization approaches.

关键词

智能建造 / 移动打孔机器人 / 概率路线图(PRM) / 改进A^*算法 / 模拟退火 / 路径规划

Key words

intelligent construction / mobile drilling robot / Probabilistic Roadmap (PRM) / improved A^* algorithm / simulated annealing / path planning

参考文献

[1] 鲍跃全, 李惠. 人工智能时代的土木工程[J]. 土木工程学报, 2019, 52(05): 1-11.

[2] 安园园, 马晓宁. 改进遗传算法与多目标优化模型的航班路径规划[J]. 计算机工程与科学, 2024, 46(09): 1660-1666.

[3] 张猜, 黄林, 彭超达, 等. . 基于约束多目标优化的多区域无人机路径规划[J]. 计算机仿真, 2024, 41(07): 66-71.

[4] 曾俊海, 廉胤东, 彭雄峰, 等. . 面向矩阵式制造车间AGV调度的改进模拟退火算法[J]. 自动化与信息工程, 2024, 45(05): 32-39.

[5] 白俊峰, 白一辰, 席嘉璐, 等. . 基于改进A^*算法的车间物料配送路径规划[J]. 吉林大学学报(理学版), 2024, 62(06): 1401-1410.

[6] 孟浩德, 吴征天, 吴闻笛, 等. . 基于改进模拟退火算法的灭火小车多目标路径规划[J]. 计算机与数字工程, 2024, 52(02): 394-398.

[7] 吕竞则, 乔文俊, 刘顺. 基于膨胀栅格的多目标站点AGV路径规划方法[J]. 机械设计与研究, 2023, 39(06): 6-10.

[8] 王步伟, 潘鹏程. 基于改进鲸鱼优化算法的移动机器人多目标点路径规划[J]. 机器人技术与应用, 2023,(06): 14-19.

[9] 唐瑞东, 游向荣. 基于改进人工势场法的多目标点路径规划[J]. 农业装备与车辆工程, 2023, 61(08): 105-109.

[10] 余文凯, 章政, 金震, 等. . 多目的地自主移动机器人的路径规划[J]. 计算机工程与设计, 2020, 41(10): 2934-2941.

[11] 林韩熙, 向丹, 欧阳剑, 等. . 移动机器人路径规划算法的研究综述[J]. 计算机工程与应用, 2021, 57(18): 38-48.

[12] Kirkpatrick S, Gelatt C D, Vecchi M P. Optimization by simulated annealing[J]. Science, 1983, 220(4598): 671-680.

[13] Hart P E, Nilsson N J, Raphael B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(02): 100-107.

[14] 周伟, 潘金宝, 王林琳, 等. . 基于改进鲸鱼算法和A^*算法的地面放线机器人路径规划[J]. 现代制造工程, 2023(12): 68-75.

[15] 习凤, 林逢春. 结合模拟退火算法与遗传算法的动态协同路径规划研究[J]. 舰船科学技术, 2024, 46(19): 161-164.

[16] Tsai C F, Tsai C W, Yang T. A Modified multiple-searching method to genetic algorithms for solving traveling salesman problem[C]. 2002 IEEE Int Conf on Systems, Man, and Cybernetics. Hammamet: IEEE, 2002: 1-6.

[17] 李勇, 仝春灵. 基于多目标的车辆导航最优路径规划研究[J]. 科学技术创新, 2021,(26): 27-28.

基金资助

湖北工业大学博士基金资助项目(BSQD2019010)