Optimal Trajectory Generation for a Humanoid Robot Based on Fuzzy and Genetic Algorithm

Abstract

This paper is concerned with the generation of gait trajectory for a humanoid robot based on genetic algorithm (GA). A humanoid robot has some problems of the structural instability basically, which leads to consider the complex control of multiple joints caused by nonlinearities. In addition, the walking trajectory of a humanoid robot should be considered to its smoothness and be reduced the torque to save the electric power, because a mobile robot has battery to move autonomously on its body. If movements of walking joint don’t maintain optimally, it is difficult for a robot to have efficient working time. Also, if a gait trajectory doesn’t have optimal state, the expected life span of joints is decreased. To solve these problems, optimal gait trajectory by using artificial intelligence like GA can be introduced. In this paper, a GA is considered for searching the optimal via points as well as optimal control gains. All the processes are investigated and verified through simulations with the parameters of real humanoid system.