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

作　　者：张星宇 吴保磊[2] 王军 洪妙英 王佳慧 祁永强 Zhang Xingyu;Wu Baolei;Wang Jun;Hong Miaoying;Wang Jiahui;Qi Yongqiang(School of Mathematics,China University of Mining and Technology,Xuzhou 221116,China;School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116,China;School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[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

出　　处：《系统仿真学报》2025年第4期1008-1024,共17页Journal of System Simulation

基　　金：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)。

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。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 terrain is 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.

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 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]