A neuromorphic learning strategy for the control of a one-legged hopping machine

Abstract

Summary form only given, as follows. An adaptive, neural network strategy is described 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). While for many dynamic systems energy conservation may not be a key control criterion, legged locomotion is an energy intensive activity, implying that energy conservation is a primary issue in control considerations. The authors effect the control of the robot by the use of an artificial neural network (ANN) with a continuous learning memory. Results are presented in the form of computer simulations that demonstrate the ANN's ability to devise proper control signals that will develop a stable hopping strategy using imprecise knowledge of the current state of the robotic leg.<>