基于滑移预测的月球车双层路径规划方法研究

doi:10.16182/j.issn1004731x.joss.23-1552

系统仿真学报 ›› 2025, Vol. 37 ›› Issue (4): 1008-1024.doi: 10.16182/j.issn1004731x.joss.23-1552

• 论文 •

基于滑移预测的月球车双层路径规划方法研究

张星宇¹, 吴保磊², 王军³, 洪妙英¹, 王佳慧³, 祁永强¹

^1.中国矿业大学数学学院，江苏徐州 221116
^2.中国矿业大学计算机科学与技术学院，江苏徐州 221116
^3.中国矿业大学信息与控制工程学院，江苏徐州 221116

收稿日期:2023-12-20 修回日期:2024-01-20 出版日期:2025-04-17 发布日期:2025-04-16
通讯作者: 祁永强
第一作者简介:张星宇(1998-)，女，硕士生，研究方向为智能机器人控制。
基金资助:
国家自然科学基金(61304088);中央高校基本科研专项基金(2013QNA37);中国博士后科学基金(2015M581886);校基本科研业务费项目-重大项目培育专项基金(2020ZDPY0217);中国矿业大学实验室开放基金(2020SYKF42);中国矿业大学融合创新培育专项基金(2023ZDPYRH11);中国矿业大学研究生创新计划(2023WLJCRCZL147)

Research on Dual-layer Path Planning Method for Lunar Rover Based on Slip Prediction

Zhang Xingyu¹, Wu Baolei², Wang Jun³, Hong Miaoying¹, Wang Jiahui³, Qi Yongqiang¹

^1.School of Mathematics, China University of Mining and Technology, Xuzhou 221116, China
^2.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China
^3.School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China

Received:2023-12-20 Revised:2024-01-20 Online:2025-04-17 Published:2025-04-16
Contact: Qi Yongqiang

摘要/Abstract

摘要：

针对月球车在路径规划过程中会面临由复杂地形引起的安全避障和偏离目标等挑战，提出了基于滑移预测的双层路径规划，通过自适应选择平坦地形来减少月球车车轮的滑移。利用数字高程信息计算地形综合复杂度，设计了具有三级奖励机制的Q-learning算法来避开高滑移区域，实现全局路径规划；采用深度相机来感知障碍物，设计基于自适应预测时间的动态窗口法进行自主避障，并引入局部地形适宜度完成局部路径规划。数值和虚拟仿真结果表明：该算法可以在复杂地形环境下高效开展路径规划，且收敛速度快、安全性高。

关键词: 滑移预测, 自适应预测时间, 三级奖励机制, 地形综合复杂度, 局部地形适宜度

Abstract:

In response to the challenges faced by lunar rovers in the process of path planning, such as safe obstacle avoidance and target deviation caused by complex terrain, a dual-layer path planning based on slip prediction is proposed. In this approach, flat terrain is adaptively selected to reduce the wheel slip of the lunar rover. The overall complexity of the terrainis calculated using digital elevation information, and a Q-learning algorithm with a three-level reward mechanism is designed to navigate around high-slip areas, achieving global path planning. A depth camera is used to perceive obstacles, a dynamic window method based on adaptive prediction time is designed for autonomous obstacle avoidance, and local path planning is accomplished by introducing local terrain suitability. Numerical and virtual simulation results indicate that this algorithm can efficiently conduct path planning in complex terrain environments, with fast convergence and high safety.

Key words: slip prediction, adaptive prediction time, three-level reward mechanism, comprehensive complexity of terrain, local terrain suitability

中图分类号:

TP391.9

张星宇,吴保磊,王军等 . 基于滑移预测的月球车双层路径规划方法研究[J]. 系统仿真学报, 2025, 37(4): 1008-1024.

Zhang Xingyu,Wu Baolei,Wang Jun,et al . Research on Dual-layer Path Planning Method for Lunar Rover Based on Slip Prediction[J]. Journal of System Simulation, 2025, 37(4): 1008-1024.

图/表 21

图1

图2

图3

图4

图5

图6

图7

图8

表1

地形可通行性分析参数

主要参数	量值
最大安全坡度角/(°)	30
最大越障高度/m	1
$ω 1$	0.4
$ω 2$	0.3
$ω 3$	0.3

表1

表2

全局路径规划参数

主要参数	量值
学习率	0.2
折扣因子	0.99
贪婪系数	0.9
最大训练次数	2 000
每次训练的最大步数	3 721
禁区距离阈值 $K d$	10
$r a r r i v a l$	-1 000
$r c o l l i s i o n$	1 000
$r f r e e$	-1

表2

图9

图10

图11

表3

图12

表4

局部路径规划参数

主要参数	量值	主要参数	量值
$w m a x$ /(rad/m)	100	$α 1$	0.005
$L g o a l$ /m	0.3	$α 2$	0.4
$L o b$ /m	0.3	$β$	0.25
$t$ /s	3.5	$γ$	0.1
$m$	10	$λ$	0.003

表4

图13

图14

图15

图16

图17

参考文献 26

1	李晓婉, 成芳, 赵航, 等. 月球导航的卫星可见性及信号强度分析[J]. 测绘科学, 2022, 47(7): 14-20.
	Li Xiaowan, Cheng Fang, Zhao Hang, et al. Analysis on Visibility and Signal Strength of Satellite for Lunar Navigation[J]. Science of Surveying and Mapping, 2022, 47(7): 14-20.
2	张天翼. 面向在轨应用的火星车滑移行为研究[D]. 长春: 吉林大学, 2022.
	Zhang Tianyi. Research on Slip Behavior of Mars Rover for On-orbit Application[D]. Changchun: Jilin University, 2022.
3	马浩. 基于视觉的月球/火星车滑移率预测研究[D]. 北京: 中国科学院大学(中国科学院遥感与数字地球研究所), 2019.
	Ma Hao. Vision Based Lunar/Mars Rover Slip Prediction Research[D]. Beijing: University of Chinese Academy of Sciences(Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences), 2019.
4	邢琰, 刘祥, 滕宝毅, 等. 月球表面巡视探测自主局部避障规划[J]. 控制理论与应用, 2019, 36(12): 2042-2046.
	Xing Yan, Liu Xiang, Teng Baoyi, et al. Autonomous Local Obstacle Avoidance Path Planning of Lunar Surface Exploration Rovers[J]. Control Theory & Applications, 2019, 36(12): 2042-2046.
5	周兰凤, 杨丽娜, 方华. 基于滑移预测的月球车路径规划研究[J]. 计算机应用与软件, 2019, 36(11): 47-50.
	Zhou Lanfeng, Yang Lina, Fang Hua. Lunar Rover Path Planning Based on Slip Prediction[J]. Computer Applications and Software, 2019, 36(11): 47-50.
6	成毅. 基于DEM的三维地形建模及集输管道路径优化研究[D]. 大庆: 东北石油大学, 2019.
	Cheng Yi. Research on 3D Terrain Modeling Based on DEM and Path Optimization of Gathering Pipeline[D]. Daqing: Northeast Petroleum University, 2019.
7	Hu Jiaming, Hu Yuhui, Lu Chao, et al. Integrated Path Planning for Unmanned Differential Steering Vehicles in Off-road Environment with 3D Terrains and Obstacles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(6): 5562-5572.
8	Zhang Wei, Wang Naixin, Wu Wenhua. A Hybrid Path Planning Algorithm Considering AUV Dynamic Constraints Based on Improved A^* Algorithm and APF Algorithm[J]. Ocean Engineering, 2023, 285, Part 1: 115333.
9	Liu Chao, Wu Lei, Xiao Wensheng, et al. An Improved Heuristic Mechanism Ant Colony Optimization Algorithm for Solving Path Planning[J]. Knowledge-Based Systems, 2023, 271: 110540.
10	Yang Hui, Qi Jie, Miao Yongchun, et al. A New Robot Navigation Algorithm Based on a Double-layer Ant Algorithm and Trajectory Optimization[J]. IEEE Transactions on Industrial Electronics, 2019, 66(11): 8557-8566.
11	Ning Xuefeng, Li Yuanjia, Liu Zehuai. Improved Genetic Algorithm-based Obstacle Avoidance Path Planning Method for Inspection Robots[C]//2023 2nd International Symposium on Control Engineering and Robotics (ISCER). Piscataway: IEEE, 2023: 346-350.
12	Qi Jie, Yang Hui, Sun Haixin. MOD-RRT*: A Sampling-based Algorithm for Robot Path Planning in Dynamic Environment[J]. IEEE Transactions on Industrial Electronics, 2021, 68(8): 7244-7251.
13	Chi Wenzheng, Ding Zhiyu, Wang Jiankun, et al. A Generalized Voronoi Diagram-based Efficient Heuristic Path Planning Method for RRTs in Mobile Robots[J]. IEEE Transactions on Industrial Electronics, 2022, 69(5): 4926-4937.
14	Ee Soong Low, Ong Pauline, Cheng Yee Low, et al. Modified Q-learning with Distance Metric and Virtual Target on Path Planning of Mobile Robot[J]. Expert Systems with Applications, 2022, 199: 117191.
15	Ee Soong Low, Ong Pauline, Cheng Yee Low. A Modified Q-learning Path Planning Approach Using Distortion Concept and Optimization in Dynamic Environment for Autonomous Mobile Robot[J]. Computers & Industrial Engineering, 2023, 181: 109338.
16	Kobayashi Masato, Zushi Hiroka, Nakamura Tomoaki, et al. Local Path Planning: Dynamic Window Approach with Q-learning Considering Congestion Environments for Mobile Robot[J]. IEEE Access, 2023, 11: 96733-96742.
17	Hun Lee Dhong, Sang Su Lee, Choon Ki Ahn, et al. Finite Distribution Estimation-based Dynamic Window Approach to Reliable Obstacle Avoidance of Mobile Robot[J]. IEEE Transactions on Industrial Electronics, 2021, 68(10): 9998-10006.
18	王旭扬, 梁志伟, 高翔, 等. 基于改进DWA算法的足球机器人局部轨迹规划[J]. 国外电子测量技术, 2023, 42(8): 1-9.
	Wang Xuyang, Liang Zhiwei, Gao Xiang, et al. Local Trajectory Planning of Soccer Robot Based on Improved DWA Algorithm[J]. Foreign Electronic Measurement Technology, 2023, 42(8): 1-9.
19	杨海兰, 祁永强, 吴保磊, 等. 动态环境下基于忆阻强化学习的移动机器人路径规划[J]. 系统仿真学报, 2023, 35(7): 1619-1633.
	Yang Hailan, Qi Yongqiang, Wu Baolei, et al. Path Planning of Mobile Robots Based on Memristor Reinforcement Learning in Dynamic Environment[J]. Journal of System Simulation, 2023, 35(7): 1619-1633.
20	Pei Muleilan, An Hao, Liu Bo, et al. An Improved Dyna-Q Algorithm for Mobile Robot Path Planning in Unknown Dynamic Environment[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(7): 4415-4425.
21	黄昱洲, 王立松, 秦小麟. 一种基于深度强化学习的无人小车双层路径规划方法[J]. 计算机科学, 2023, 50(1): 194-204.
	Huang Yuzhou, Wang Lisong, Qin Xiaolin. Bi-level Path Planning Method for Unmanned Vehicle Based on Deep Reinforcement Learning[J]. Computer Science, 2023, 50(1): 194-204.
22	Fox D, Burgard W, Thrun S. The Dynamic Window Approach to Collision Avoidance[J]. IEEE Robotics & Automation Magazine, 1997, 4(1): 23-33.
23	奚玉荣. 基于单目图像的三维火星地形重构方法研究[D]. 长春: 吉林大学, 2022.
	Xi Yurong. Research on 3D Martian Terrain Reconstruction Method Based on Monocular Image[D]. Changchun: Jilin University, 2022.
24	韩浦霞. 基于双目视觉的嫦娥三号月球高程值计算[D]. 天津: 天津理工大学, 2018.
	Han Puxia. The Calculation of the Lunar Elevation Value of Chang'E3 Based on Binocular Vision[D]. Tianjin: Tianjin University of Technology, 2018.
25	巩绪生. 基于三维地形的人机协同路径规划[D]. 长沙: 国防科学技术大学, 2006.
	Gong Xusheng. Human-machine Cooperation Path Planning Based on Three Dimensional Terrain[D]. Changsha: National University of Defense Technology, 2006.
26	郭延宁, 冯振, 马广富, 等. 行星车视觉导航与自主控制进展与展望[J]. 宇航学报, 2018, 39(11): 1185-1196.
	Guo Yanning, Feng Zhen, Ma Guangfu, et al. Advances and Trends in Visual Navigation and Autonomous Control of a Planetary Rover[J]. Journal of Astronautics, 2018, 39(11): 1185-1196.

指标	传统Q-learning算法	Q-learning+ 三级奖励机制	Q-learning+三级奖励机制+退回机制
路径安全性	0.14	0.25	0.21
路径长度/m	48.421 8	47.960 7	47.991 4
运行时间/s	125.33	1 969.40	1 843.20

[1]	万士正, 程禹, 张旭, 范旭伟. 自适应视场角制导半实物仿真能力拓展方法[J]. 系统仿真学报, 2025, 37(3): 563-570.
[2]	郭博, 铁鸣, 范文慧. 复合材料结构振动仿真及其多元统计分析方法[J]. 系统仿真学报, 2025, 37(3): 571-583.
[3]	张雷, 张雪超, 王超, 薄祥雷. 基于在线强化学习算法的救护车智能调控模型[J]. 系统仿真学报, 2025, 37(3): 584-594.
[4]	许明, 齐光尧, 奇格奇. 基于动态反投影网络的细粒度交通流推断模型[J]. 系统仿真学报, 2025, 37(3): 657-666.
[5]	林桂娟, 李子涵, 王宇. 基于全局关键点提取的改进A*算法全局路径规划研究[J]. 系统仿真学报, 2025, 37(3): 667-678.
[6]	李若晴, 赵瑶池, 胡祝华, 戚文璐, 刘广丰. TOHF：一种针对资源受限室内VSLAM的特征提取器[J]. 系统仿真学报, 2025, 37(3): 691-703.
[7]	曹晞, 刘波, 苏炳志, 聂涛. 基于MBSE和VAPS的民用直升机显控系统设计与验证[J]. 系统仿真学报, 2025, 37(3): 704-717.
[8]	陈雪, 曹建文. 基于动态耦合模型的CAE仿真优化方法[J]. 系统仿真学报, 2025, 37(3): 718-731.
[9]	陈朔, 胡昊, 方慧敏, 王海伟, 陈小龙, 梅成成, 朱佳男, 艾芊. 基于虚拟储能的电动汽车充放电调度策略及激励评价[J]. 系统仿真学报, 2025, 37(3): 732-741.
[10]	白宇鑫, 陈振亚, 石瑞涛, 苏蔚涛, 马卓强, 杨尚进. 基于改进哈里斯鹰算法的机器人路径规划研究[J]. 系统仿真学报, 2025, 37(3): 742-752.
[11]	张斌, 雷永林, 李群, 高远, 陈永, 朱佳俊, 鲍琛龙. 基于强化学习的导弹突防决策建模研究[J]. 系统仿真学报, 2025, 37(3): 763-774.
[12]	江达伟, 董阳阳, 张立东, 路宵, 董春曦. 基于深度学习的空中目标威胁评估技术研究[J]. 系统仿真学报, 2025, 37(3): 791-802.
[13]	张旭, 曾鹏, 李旭, 郑学合, 薛建恒, 王超. 助推段拦截导弹制导律的设计与仿真分析[J]. 系统仿真学报, 2025, 37(2): 335-344.
[14]	江雨燕, 马宁, 李艳, 甘如美江, 王付宇. 考虑动态预维护与绿色调度的协同优化问题[J]. 系统仿真学报, 2025, 37(2): 362-378.
[15]	崔焕焕, 官礼和. 优先配送绿色VRP的混合启发式求解算法[J]. 系统仿真学报, 2025, 37(2): 413-423.

基于滑移预测的月球车双层路径规划方法研究

Research on Dual-layer Path Planning Method for Lunar Rover Based on Slip Prediction

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献 26

相关文章 15

编辑推荐

Metrics

本文评价