基于障碍物运动预测的移动机器人路径规划  

Path planning of mobile robot based on obstacle motion prediction

作　　者：杨奇峰 曲道奎[1,2,4] 徐方[1,2,4] YANG Qi-feng;QU Dao-kui;XU Fang(State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;University of Chinese Academy of Sciences,Beijing 100049,China;Shenyang SIASUN Robot&Automation Limited Company,Shenyang 110168,China)

机构地区：[1]中国科学院沈阳自动化研究所机器人学国家重点实验室,辽宁沈阳110016 [2]中国科学院机器人与智能制造创新研究院,辽宁沈阳110169 [3]中国科学院大学,北京100049 [4]沈阳新松机器人自动化股份有限公司,辽宁沈阳110168

出　　处：《计算机工程与设计》2021年第1期182-188,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(U1608253)。

摘　　要：针对移动机器人局部动态避障路径规划问题开展优化研究。基于动态障碍物当前历史位置轨迹,提出动态障碍物运动趋势预测算法。在移动机器人的动态避障路径规划过程中,考虑障碍物当前的位置,评估动态障碍物的移动轨迹;提出改进的D*Lite路径规划算法,大幅提升机器人动态避障算法的效率与安全性。搭建仿真验证环境,给出典型的单动态障碍物、多动态障碍物场景,对比验证了避障路径规划算法的有效性。The mobile robot dynamic obstacle avoidance path planning problem was studied.Based on the historical position of dynamic obstacles,a dynamic obstacle motion trend prediction algorithm was proposed.In the process of mobile robot dynamic obs-tacle avoidance path planning,not only the current position of obstacles was considered,but also the moving trajectory of dynamic obstacles was evaluated.An improved D*lite path planning algorithm was proposed,which greatly improved the efficiency and security of robot dynamic obstacle avoidance algorithm.The simulation environment was built,and the typical path planning of single dynamic obstacle and multi dynamic obstacle were compared.The experimental results verify the effectiveness of the algorithm proposed.

关 键 词：移动机器人 动态避障 路径规划 运动预测 动态障碍物 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]