盲区条件下一种基于记忆机制的移动机器人快速路径规划方法

摘要

如何在存在盲区的条件下实现机器人路径规划,是现实中的一大难点问题.本文利用路口点表征自由路径,通过估算盲区内路口点位置及其存在的概率,实现对历史感知数据的记忆与利用.建立评价函数对盲区内路口点及感知范围内的路口点进行评价,同时利用了历史感知信息与当前感知信息.与传统局部路径规划方法相比,该方法避免了盲区带来的徘徊、规划失败等问题.仿真表明了该方法的有效性.%It is a hard problem to path planning with blind zone,which confronting mobile robot in practice.In this paper a rapid path planning approach is proposed for that problem.In this approach,entry point is introduced to represent the free road which may guide the robot pass through the gaps between obstacles.By estimating the entry point in blind zone and estimating the probability it exist there,the historical sensor information is memorized.Both entry points in blind zone and in detectable zone are then evaluated using a evaluste function.So that both the current sensor information and the memorized sensor information are used.Compared with the traditional local path planning approaches,this approach avoid the trap problem and the hesitate problem comed with the blind zone.Simulation has proved the effect.