Global path planning method of mobile robot in uncertain environment

Abstract

Path planning is one of the key technologies in the robot research. The aim of it is to find the shortest safe path in the objective environments. Firstly, the robot is transformed into particle by expanding obstacles method; the obstacle is transformed into particle by multi-round enveloping method. Secondly, we make the Voronoi graph of the particles of obstacle and find the skeleton topology about the feasible path. Following, a new arithmetic named heuristic bidirectional ant colony algorithm is proposed by joining the merit of ant colony algorithm, Dijkstra algorithm and heuristic algorithm, with which we can find the shortest path of the skeleton topology. After transforming the path planning into n-dimensions quadrate feasible region by coordinate transformation and solving it with particle swarm optimization, the optimization of the path planning is acquired.