Evolutionary Acquisition of Starting Pose for Reduced D.O.F's Quadruped Robot

Abstract

In this paper, an application of genetic algorithm for generation of evolutionary starting pose of a quadrupedal robot which reduced degrees of freedom is described. Each leg of the quadrupedal robot has a slider-crank mechanism and is driven by an actuator. Furthemore we introduced the forward movement mode and the rotating mode because the all direction movement should be made possible.To generate the suitable starting pose, the inital angle of four legs are coded under real-coded amd tuned by an estimation function in each mode with the real-coded genetic algorithm.as a result of generation, the cooperation of the legs are realized to move toward the all direction. And the robot can walk with the generated starting poses avoided obstacles.