Hybrid intelligent path planning for articulated rovers in rough terrain

The paper develops a hybrid intelligent approach to path planning for high mobility robots operating in rough environments. Path planning consists of characterization of the environment using a fuzzy logic framework, and a two-stage genetic algorithm planner. A global planner determines the path that optimizes a combination of terrain roughness and path curvature. A local planner uses sensory information, and in case of detection of previously unknown and unaccounted for obstacles, performs an on-line replanning to get around the newly discovered obstacle. Fuzzy adaptation of the genetic operators is achieved by adjusting the probabilities of the operators based on a diversity measure of the paths population and traversability measure of the paths. Path planning for an articulated rover in a rugged Mars terrain is presented to demonstrate the effectiveness of the proposed path planner.