視覚的予測による行動学習：人間の実演からロボットへ
What Would You Do? Acting by Learning to Predict
人間の視覚的な状態遷移のみから行動結果を予測するモデルを学習し、ロボットが卓上物体操作タスクを実演通りに実行できる手法を提案した。
著者: Adam Tow, Niko Sünderhauf, Sareh Shirazi, Michael Milford, Jürgen Leitner
分類: cs.RO
原文アブストラクト
We propose to learn tasks directly from visual demonstrations by learning to predict the outcome of human and robot actions on an environment. We enable a robot to physically perform a human demonstrated task without knowledge of the thought processes or actions of the human, only their visually observable state transitions. We evaluate our approach on two table-top, object manipulation tasks and demonstrate generalisation to previously unseen states. Our approach reduces the priors required to implement a robot task learning system compared with the existing approaches of Learning from Demonstration, Reinforcement Learning and Inverse Reinforcement Learning.
