Adaptive control of a legged robot using an artificial neural network

Results are presented of a neural network strategy for the control of a dynamic, locomotive system, in particular a one-legged hopping robot. The control task is to make corrections to the motion of the robot that serve to maintain a fixed level of energy (and minimize energy losses), which yields a stable periodic limit cycle in the system´s state space. The robot is controlled by the use of an artificial neural network (ANN) with a continuous learning memory. The design and simulation of an autonomous learning apparatus is investigated to devise a strategy for controlling a one-legged hopping robot. Through continuous reinforcement for past successes and failures, the control system develops a stable strategy for accomplishing the desired control objectives.<>