中国地质大学计算机学院分流,自主机器人路径规划的群体智能和分流函数.doc...

外文原文

Autonomous Robot Path Planning Based on Swarm

Intelligence and Stream Functions

Chengyu Hu, Xiangning Wu, Qingzhong Liang, and Yongji Wang

Department of Control Science and Engineering,

Huazhong University of Science & Technology, Wuhan, China 430074

huchengyu@, wangyjch@

School of Computer, China University of Geosciences, Wuhan, China 430074

WXN000sun@126.com, qzliang@

Abstract. This paper addresses a new approach to navigate mobile robot in

static or dynamic surroundings based on particle swarm optimization (PSO) and

stream functions (or potential flows). Stream functions, which are introduced

from hydrodynamics, are employed to guide the autonomous robot to evade the

obstacles. PSO is applied to generate each optimal step from initial position to

the goal location; furthermore, it can solve the stagnation point problem that

exists in potential flows. The simulation results demonstrate that the approach is

flexible and effective.

1 Introduction

In the last few decades we have witnessed a rapidly increasing interest in mobile robot navigation and path planning, as it has a lot of applications such as assembly, manufacturing, transportation and services. The definition of robot path planning given by most researchers is typically formulated as follows: given a robot and description of an environment, plan a path from an initial location to the goal location, which is collision-free and satisfies optimization criteria [1]. The path planning problem could be divided into two sub-problems, one is to establish the surroundings model, generate path by some traditional approaches; the other is to avoid obstacle in the surroundings.

There are many traditional approaches to establish the surroundings model. According to the knowledge of the environments, the methods can be classified as local methods and global methods. Visibility graph [4], free space approach [5] and grids [6] are envisioned as global methods. Artificial potential field [8], neural network