CAD model based autonomous locomotion of quadruped robot by using correction of trajectory planning with RNN

It is very difficult to make a mathematical model of the multi-leg locomoti on robot and to design a motion control system for it, because of the robot 's large-scale nonlinear property. In this paper we propose a new approach for dealing with such a large-scale nonlinear system and realizing the stab le walking in various environments by using correction of trajectory planni ng with recurrent neural network (RNN) based on a CAD model. Firstly, a CAD model of a quadruped locomotion robot was developed using DADS/Plant, whic h is a software that treats multi-body dynamics. Then, the centralized hier archical neural network (HNN) controller, which is used to make the robot r ealize a desired motion; was designed on the basis of this CAD model. Furth ermore, on the basis of the same CAD model, the superior RNN controller, wh ich is used to correct the trajectory planning of each joint of the robot, was utilized to solve such problems as the stability of the center of gravi ty of the robot body and the coordination of each robot foot during walking on an irregular terrain with obstacles and stairs. Consequently, the auton omous locomotion of the robot was realized. Simulations and experiments wer e performed to verify the effectiveness of the presented approach.