実演からの実用的なロボット学習:深層エンドツーエンド訓練によるアプローチ
Practical Robot Learning from Demonstrations using Deep End-to-End Training
人間がジョイスティックで実演した手先カメラ画像とエンドエフェクタ速度の対応をResNetで学習し、1時間以内にロボットのサーボタスクを獲得できることを示した。
著者: Akansel Cosgun, Thomas Rowntree, Ian Reid, Tom Drummond
分類: cs.RO
原文アブストラクト
Robots need to learn behaviors in intuitive and practical ways for widespread deployment in human environments. To learn a robot behavior end-to-end, we train a variant of the ResNet that maps eye-in-hand camera images to end-effector velocities. In our setup, a human teacher demonstrates the task via joystick. We show that a simple servoing task can be learned in less than an hour including data collection, model training and deployment time. Moreover, 16 minutes of demonstrations were enough for the robot to learn the task.
