A tennis serve and upswing learning robot based on bi-directional theory

Abstract

We experimented on task-level robot learning based on bi-directional theory. 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 applied to a wide variety of motor behavior. However, some difficulties still remain. In this paper, we address two problems: (1) how to attain a final goal of complex movement when it consists of a sequence of subgoals, and (2) how to adapt to changes in behavior and the environment. To examine how to solve these problems, we propose two methods: (1) selecting the proper via-points for a control variable for each subgoal, and (2) re-estimating the relation between the via-points and the task during learning without conducting extra trials. We adopted a tennis serve and a pendulum upswing for our complicated tasks. ᭧

Learning by demonstration with critique from a human teacher

“…The learner then generalizes from these demonstrations in order to effectively execute the task itself. Work which has applied demonstration learning to the development of low level robot control policies includes: [3] learned the reward function used in control policy computations, [6] learned a heirarchy of neural networks for motion control, and [10] represented motor behaviors sparsely with via points. Local learning was used for motion control policy development by Atekson et al [2].…”

Learning by Experience and by Imitation in Multi-Robot Systems

“…Learning by imitation is considered a method to acquire complex behaviors and a way of providing seeds for future learning (Kuniyoshi and Inoue, 1993;Miyamoto and Kawato, 1998;Schaal, 1999). This kind of learning was applied in several problems like learning in humanoid robots, air hockey and marble maze games, and in robot soccer, where was implemented using a Hidden Markov Model and by teaching the robots with a Q-Learning algorithm.…”

The new robotics—towards human‐centered machines

“…Special control strategies can make motor skills easier or harder (e.g., Beek, 1989;Schaal et al, 1992). Some ideas exist how to generate generic representations of motor skill (Wada and Kawato, 1995;Miyamoto et al, 1996;Miyamoto and Kawato, 1998;Ijspeert et al, 2003), but, so far, a generic approach to skill acquisition is missing.…”