智能机器人自适应巡检路径栅格地图邻域搜索算法

doi:10.13229/j.cnki.jdxbgxb.20250291

摘要/Abstract

摘要：

智能机器人巡检过程中的动态障碍物使巡检路径呈现非连续可访问性条件，导致路径可行域突变，难以获取重构路径的可行解，降低了巡检路径规划的转弯平滑度。为此，提出智能机器人自适应巡检路径栅格地图邻域搜索算法。采用栅格地图法对巡检环境建模，通过边界条件处理机制定义路径可行域。引入转弯代价函数改进A^*算法，以栅格地图可行域为巡检环境模型，生成初步转弯平滑巡检路径。针对动态环境下路径突变导致的失效问题，提出基于自适应大规模邻域搜索的巡检路径可行域动态重构方法，利用破坏算子移除部分巡检任务生成不完整路径，引入修复算子重新整合巡检任务，结合变邻域下降搜索策略深入探索解空间，通过自适应邻域算子评分与选择机制实现初步全局巡检路径的局部优化。实验结果表明：该算法可成功避开栅格地图中的动、静态障碍物，实现智能机器人巡检路径规划，巡检路径长度相对较短，路径优化度、转弯平滑度系数、全局搜索能力以及环境适应性评分分别为95.24%、0.917、0.764、91.45。

关键词: 栅格地图, 改进A^*算法, 启发函数, 转弯代价, 邻域搜索, 变邻域下降

Abstract:

The dynamic obstacles during the inspection process of intelligent robots result in discontinuous accessibility conditions for the inspection path， leading to abrupt changes in the feasible domain of the path and difficulty in obtaining feasible solutions for reconstructing the path， thereby reducing the smoothness of turning in the inspection path planning. To this end， an intelligent robot adaptive inspection path grid map neighborhood search algorithm is proposed. Adopting the grid map method to model the inspection environment， and defining the feasible path domain through the boundary condition processing mechanism. Introducing a turning cost function to improve the A^* algorithm， using a grid map feasible region as the inspection environment model， to generate a preliminary smooth inspection path for turns. Aiming at the failure problem caused by path mutations in dynamic environments， a feasible region dynamic reconstruction method for inspection paths based on adaptive large-scale neighborhood search is proposed. The destruction operator is used to remove some inspection tasks and generate incomplete paths， and the repair operator is introduced to reorganize inspection tasks. Combined with the variable neighborhood descent search strategy， the solution space is deeply explored. The local optimization of the preliminary global inspection path is achieved through the adaptive neighborhood operator scoring and selection mechanism. The experimental results show that the algorithm can successfully avoid dynamic and static obstacles in grid maps and achieve intelligent robot inspection path planning. The inspection path length is relatively short， and the path optimization degree， turning smoothness coefficient， global search ability， and environmental adaptability scores are 95.24%， 0.917， 0.764， and 91.45， respectively.

Key words: raster map, improve the A^* algorithm, heuristic function, cost of turning, neighborhood search, variable neighborhood descent

中图分类号:

TP24

张楠,张和茂,章涛,张艳军. 智能机器人自适应巡检路径栅格地图邻域搜索算法[J]. 吉林大学学报(工学版), 2026, 56(7): 2026-2033.

Nan ZHANG,He-mao ZHANG,Tao ZHANG,Yan-jun ZHANG. Adaptive inspection path grid map neighborhood search algorithm for intelligent robots[J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(7): 2026-2033.

图/表 6

图1

表1

图2

图3

表2

图4

参考文献 15

[1]	金书奎, 寇子明, 吴娟. 煤矿水泵房巡检机器人路径规划与跟踪算法的研究[J].煤炭科学技术,2022,50(5): 253-262.
	Jin Shu-kui, Kou Zi-ming, Wu Juan. Research on path planning and tracking algorithm of inspection robot in coal mine water[J]. Coal Science and Technology, 2022,50(5): 253-262.
[2]	邢文芳,冯寄东,徐元,等.双程UFIR滤波算法及其在INS/双目视觉机器人组合导航的应用[J].传感技术学报,2023,36(7):1073-1078.
	Xing Wen-fang, Feng Ji-dong, Xu Yuan, et al. Double-Pass UFIR filtering and its application in ins/binocular vision robot integrated navigation[J]. Chinese Journal of Sensors and Actuators,2023,36(7):1073-1078.
[3]	Jiang S H, Sun S J, Li C. Path planning for outdoor mobile robots based on IDDQN[J]. IEEE Access, 2024, 12:51012-51025.
[4]	李洁静,吴倩,耿轶钊,等.复杂环境下矿用巡检机器人的路径规划方法[J].煤炭技术,2023,42(10):236-239.
	Li Jie-jing, Wu Qian, Geng Yi-zhao, et al. Path Planning method for mining inspection robots in complex environments[J].Coal Technollgy, 2023,42(10):236-239.
[5]	岳程斐, 张枭, 王宏旭,等. 在轨操控机器人拓邻域搜索三维路径规划[J].宇航学报, 2022, 43(2): 206-213.
	Yue Cheng-fei, Zhang Xiao, Wang Hong-xu, et al. Three-dimensional path planning of on-orbit manipulation robot based on neighborhood continuation Search [J].Journal of Astronautics,2022,43(2):206-213.
[6]	李鹏, 闵小翠, 王建华. 基于改进蚁群算法的巡检机器人避障路径规划方法设计[J]. 机械与电子, 2022, 40(2): 71-74, 80.
	Li Peng, Min Xiao-cui, Wang Jian-hua. Design of obstacle avoidance path planning method for inspection robot based on improved ant colony algorithm[J].Machinery & Electronics, 2022, 40(2): 71-74, 80.
[7]	杨立炜, 付丽霞, 郭宁, 等.多因素改进蚁群算法的路径规划[J].计算机集成制造系统,2023,29(8):2537-2549.
	Yang Li-wei, Fu Li-xia, Guo Ning, et al. Path planning with multi-factor improved ant colony algorithm [J].Computer Integrated Manufacturing Systems,2023,29(8):2537-2549.
[8]	辛鹏, 王艳辉, 刘晓立, 等. 优化改进RRT和人工势场法的路径规划算法[J]. 计算机集成制造系统,2023, 29(9): 2899-2907.
	Xin Peng, Wang Yan-hui, Liu Xiao-li, et al. Path planning algorithm based on optimize and improve RRT and artificial potential field[J].Computer Integrated Manufacturing Systems, 2023,29(9):2899-2907.
[9]	赵崇娟, 朱奕弢, 胡钰莹, 等.基于改进A^*算法的变电站自动巡检路径规划研究[J].机械设计, 2024,41(): 153-158.
	Zhao Chong-juan, Zhu Yi-tao, Hu Yu-ying, et al. research on automatic inspection path planning for substations based on improved A algorithm[J]. Machine Design, 2024,41(Sup.1):153-158.
[10]	许建民, 宋雷, 邓冬冬, 等. 基于多尺度A^*与优化DWA算法融合的移动机器人路径规划[J].系统仿真学报, 2025, 37(1): 257-270.
	Xu Jian-min, Song Lei, Deng Dong-dong, et al. Path planning of mobile robot based on the integration of multi-scale A^* and optimized DWA algorithm[J].Journal of System Simulation, 2025, 37(1): 257-270.
[11]	边艳华, 解路, 苗超. 基于深度强化学习和大邻域搜索的矿山巡检机器人路径规划算法[J]. 金属矿山, 2024, 41(2): 212-218.
	Bian Yan-hua, Xie Lu, Miao Chao. Path planning algorithm of mine inspection robot based on deep reinforcement learning and large neighborhood search[J].Metal Mine, 2024, 41(2): 212-218.
[12]	姜媛媛, 张阳阳.改进8邻域节点搜索策略A^*算法的路径规划[J]. 电子测量与仪器学报, 2022, 36(5): 234-241.
	Jiang Yuan-yuan, Zhang Yang-yang. Improved path planning of A^* algorithm of domain node search strategy 8[J].Journal of Electronic Measurement and Instrumentation, 2022, 36(5): 234-241.
[13]	王硕, 周海波, 张建军, 等. 拓展A^*算法的机器人室内三维地图路径规划[J]. 计算机仿真, 2022, 39(2): 394-398.
	Wang Shuo, Zhou Hai-bo, Zhang Jian-jun, et al. Extended A* algorithm for indoor 3D map path planning of robots[J].Computer Simulation,2022,39(2): 394-398.
[14]	吕文艳. 金属弧焊机器人加工轨迹智能规划研究[J].模具技术, 2024(2): 26-34.
	Lv Wen-yan. Research on intelligent planning of machining trajectory for metal arc welding robot[J]. Die and Mould Technology,2024(2):26-34.
[15]	吕东许, 李少梅, 周炤, 等.基于改进变邻域搜索算法的多批次协同任务规划[J].包装工程, 2023, 44(5): 222-229.
	Lv Dong-xu, Li Shao-mei, Zhou Zhao, et al. Multi-batch collaborative task planning based on improved variable neighborhood search algorithm[J].Packaging Engineering,2023, 44(5): 222-229.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	数值
机器人质量/kg	30
机器人尺寸/（mm·mm·mm）	832·514·450
续航时间/h	8
最大坡度/（^o）	30
云台水平调节范围/（^o）	360
云台垂直调节范围/（^o）	-90~90

算法	指标
算法	路径优化度/%	转弯平滑度系数	全局搜索能力	环境适应性评分/分
基于A^*算法的路径规划	88.47	0.851	0.705	85.19
基于改进A^*算法的路径规划	91.58	0.873	0.739	88.72
本文算法	95.24	0.917	0.764	91.45