基于回溯搜索的生物激励完全遍历路径规划  

Bio-inspired completecoverage path planning based on backtracking search

作　　者：赵文勇 王丹丹[1] 徐守祥[1] 张瑞 马超[1] Zhao Wenyong;Wang Dandan;Xu Shouxiang;Zhang Rui;Ma Chao(Shenzhen Institute of Information Technology,Shenzhen,Guangdong,China 518172)

机构地区：[1]深圳信息职业技术学院,广东深圳518172

出　　处：《深圳信息职业技术学院学报》2018年第5期47-53,共7页Journal of Shenzhen Institute of Information Technology

基　　金：深圳信息职业技术学院校级科研培育项目(QN201715;QN201716);深圳市科技计划项目(KJYY20170724152553858;JCYJ20170306095702695)

摘　　要：本文基于生物激励神经网络算法、回溯算法、D*(D Star)算法的优点,提出了一种新的完全遍历路径规划方法——基于回溯搜索的生物激励完全遍历路径规划算法,实现机器人在未知环境下的完全遍历路径规划。本算法用生物激励神经网络实现实时地图构建与路径规划,用回溯法结合D*算法实现机器人在分离区域之间的最短路径规划。通过仿真研究,本算法能实现机器人在复杂环境下的完全遍历路径规划,通过对比实验,本算法相比于基于生物激励的神经网络算法,性能上有所改善和提高。Based on the advantages of bio-inspired neural network algorithm,backtracking algorithm and D*(D Star)algorithm,this paper proposes a new method of complete coverage path planning-a bio-inspired complete coverage path planning algorithm based on backtracking search to realize the complete coverage path planning of robot in unknown environment.The algorithm uses bio-inspired neural network to realize real-time map construction and path planning,and uses backtracking method combined with D*algorithm to realize the shortest path planning between robots in separate areas.Through simulation research,the algorithm can realize the complete coverage path planning of the robot in complex environment.Through comparison experiments,compared with the neural network algorithm based on biological inspiration,the performance of the algorithm is improved.

关 键 词：完全遍历路径规划 移动机器人 神经网络 回溯算法 D*算法 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]