Open AccessA genetic approach to motion planning of redundant mobile manipulator systems considering safety and configuration
Author(s) -
Chen Mingwu,
Zalzala Ali M. S.
Publication year - 1997
Publication title -
journal of robotic systems
Language(s) - English
Resource type - Journals
eISSN - 1097-4563
pISSN - 0741-2223
DOI - 10.1002/(sici)1097-4563(199707)14:7<529::aid-rob2>3.0.co;2-p
Subject(s) - workspace , motion planning , genetic algorithm , mobile manipulator , torque , mobile robot , minimax , path (computing) , grid , control theory (sociology) , obstacle , engineering , computer science , control engineering , mathematical optimization , robot , artificial intelligence , mathematics , control (management) , physics , geometry , law , political science , programming language , thermodynamics
This article presents a genetic algorithm approach to multi‐criteria motion planning of mobile manipulator systems. For mobile robot path planning, traveling distance and path safety are considered. The workspace of a mobile robot is represented as a grid by cell decomposition, and a wave front expansion algorithm is used to build the numerical potential fields for both the goal and the obstacles. For multi‐criteria position and configuration optimization of a mobile manipulator, least torque norm, manipulability, torque distribution and obstacle avoidance are considered. The emphasis of the study is placed on using genetic algorithms to search for global optimal solutions and solve the minimax problem for manipulator torque distribution. Various simulation results from two examples show that the proposed genetic algorithm approach performs better than the conventional methods.