Revision on fuzzy artificial potential field for humanoid robot path planning in unknown environment

Abstract

Path planning in a completely known environment has been experienced various ways. However, in real world, most humanoid robots work in unknown environments. Robots' path planning by artificial potential field and fuzzy artificial potential field methods are very popular in the field of robotics navigation. However, by default humanoid robots lack range sensors; thus, traditional artificial potential field approaches needs to adopt themselves to these limitations. This paper investigates two different approaches for path planning of a humanoid robot in an unknown environment using fuzzy artificial potential (FAP) method. In the first approach, the direction of the moving robot is derived from fuzzified artificial potential field whereas in the second one, the direction of the robot is extracted from some linguistic rules that are inspired from artificial potential field. These two introduced trajectory design approaches are validated though some software and hardware in the loop simulations and the experimental results demonstrate the superiority of the proposed approaches in humanoid robot real-time trajectory planning problems.