Mobile robot path planning with surrounding point set and path improvement

Jihee Han, Yoon Ho Seo

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

The objective of the path planning problem for a mobile robot is to generate a collision-free path from a starting position to a target position with respect to a certain fitness function, such as distance. Although, over the last few decades, path planning has been studied using a number of methodologies, the complicated and dynamic environment increases the complexity of the problem and makes it difficult to find an optimal path in reasonable time. Another issue is the existence of uncertainty in previous approaches. In this paper, we propose a new methodology to solve the path planning problem in two steps. First, the surrounding point set (SPS) is determined where the obstacles are circumscribed by these points. After the initial feasible path is generated based on the SPS, we apply a path improvement algorithm depending upon the former and latter points (PI_FLP), in which each point in the path is repositioned according to two points on either side. Through the SPS, we are able to identify the necessary points for solving path planning problems. PI_FLP can reduce the overall distance of the path, as well as achieve path smoothness. The SPS and PI_FLP algorithms were tested on several maps with obstacles and then compared with other path planning methods As a result, collision-free paths were efficiently and consistently generated, even for maps with narrow geometry and high complexity.

Original languageEnglish
Pages (from-to)35-47
Number of pages13
JournalApplied Soft Computing Journal
Volume57
DOIs
Publication statusPublished - 2017 Aug 1

Keywords

  • Mobile robot
  • Particle swarm optimization
  • Path planning
  • Surrounding point set

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Mobile robot path planning with surrounding point set and path improvement'. Together they form a unique fingerprint.

  • Cite this