Cognitive Map approach for mobility path optimization using multiple objectives genetic algorithm
Authors:
- 1 February 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 267-272
Abstract
This paper describes the evolutionary planning strategies for mobile robot to move along the streamlined collision-free paths in a known static environment. The Cognitive Map method is combined with genetic algorithm to derive the mobile robot optimal moving path towards its goal functions. In this study, multi-objectives genetic algorithm (MOGA) is utilized due to there are more than one objective need to be achieved while planning for the robot moving path. Goal-factor and obstacle-factor are the key parameters incorporated in the MOGA fitness functions. The simulation results showed that the hybrid Cognitive Map approach with MOGA is capable of navigating a robot situated among non-moving obstacles. The proposed hybrid method demonstrates good performance in planning and optimizing mobile robot moving path with stationary obstacles and goal.Keywords
This publication has 10 references indexed in Scilit:
- Neural network structure for navigation using potential fields2003
- Fast path planning available for moving obstacle avoidance by use of Laplace potential2002
- Global and local path planning in natural environment by physical modeling2002
- Genetic-based adaptive fuzzy controller for robot path planning2002
- Collision avoidance planning of a robot manipulator by using genetic algorithm. A consideration for the problem in which moving obstacles and/or several robots are included in the workspace2002
- Multiobjective evolutionary path planning via fuzzy tournament selection2002
- An evolutionary method for active learning of mobile robot path planning2002
- Genetic Algorithms1999
- A simple path planning system using fuzzy rules and a potential field1994
- Real-Time Obstacle Avoidance for Manipulators and Mobile RobotsThe International Journal of Robotics Research, 1986