A New Gait Optimization Approach Based on Genetic Algorithm for Walking Biped Robots and a Neural Network Implementation

概要

論文の詳細を見る
In this paper, a Genetic Algorithm gait synthesis method for biped robots is proposed. The gait synthesis during walking is analyzed based on minimum consumed energy and minimum torque change. Except gait synthesis optimization, we also consider the stability, minimum torque change cost function, and the real time implementation. The stability is verified through the Zero Moment Point concept. For the real time implementation, a Radial Basis Function Neural Network, that is taught based upon Genetic Algorithm results, is considered. In this paper, we present the Neural Network results where the input variable is the step length. Simulation results and experiments show that proposed method has a good performance.
一般社団法人情報処理学会の論文
2002-04-15