Locomotion Control Using Environment Information Inputs

Abstract

A learning scheme is developed to control bipedal locomotion on different sloping surfaces. This scheme uses three neural networks: a neural network controller, a neural network emulator, and a slope information neural network. The neural network controller is pre-trained by a reference trajectory on horizontal surface. The emulator is pre-trained to identify the robotic dynamics. The slope information neural network provides compensated control signals to the robot on different slope angles by using the control signals on horizontal surface from the pre-trained controller. The training rule is a backpropagation algorithm with time delay. The proposed technique can generate gaits on different sloping surfaces by following reference trajectory with desired step length, crossing height and walking speed.