2A1-E08 モデル学習とプランニングの密な結合による実ロボット行動学習法の提案

概要

論文の詳細を見る
This paper presents a new framework for learning dynamic robot behavior such that a wheeled mobile robot moves to the destination with wheel slippage. First, our method learns the body dynamics from a large number of sensory-motor instances using PaLM-tree algorithm, which approximates nonlinear mapping in arbitrary preciseness. The mapping specifies a transition model from state-action pair to next state. An optimal action sequence generating the transition from initial to goal states is obtained by the branch-and-bound algorithm using the estimated transition model. Then, new sensory-motor instances are gathered while the robot acts based on the learned action sequence. After such experiences are used for enriching the transition model, an optimal action sequence is obtained again. Our method cyclically performs model learning and planning. These cyclical process accelerates further behavior acquisition and learning model. In our experiment, after about 20 training runs, our learning system successfully obtained the desired behavior that involves body drifting and the transition model that looks very realistic.
一般社団法人日本機械学会の論文