Uniped locomotion training

摘要

The author investigated the use of artificial neural networks to control the jumping behavior of a three-link uniped robot. It is believed that the biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics shows that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation was developed to be used as the plant. Neurocontrollers were trained both on-line and off-line. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process that took weeks to learn 460 examples. After training, the neurocontroller's performance was rather poor. Afterward, the BP network was replaced by a Cerebellar Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to solving uniped locomotion control problems in terms of both learning efficiency and performance.