A TENNIS SERVE AND UPSWING LEARNING ROBOT BASED ON BIDIRECTIONAL THEORY

We experimented on task-level robot learning based on bi-directional t heory. The via-point representation was used for 'learning by watching '. In our previous work, we had a robot learn kendama (a Japanese game ) in order to demonstrate a single simple task. Our approach can be ap plied to a wide variety of motor behavior. However, some difficulties still remain. In this paper, we address two problems: (1) how to attai n a final goal of complex movement when it consists of a sequence of s ubgoals, and (2) how to adapt to changes in behavior and the environme nt. To examine how to solve these problems, we propose two methods: (1 ) selecting the proper via-points for a control variable for each subg oal, and (2) re-estimating the relation between the via-points and the task during learning without conducting extra trials. We adopted a te nnis serve and a pendulum upswing for our complicated tasks. (C) 1998 Elsevier Science Ltd. All rights reserved.