プランナクローニングによる視覚サーボポリシーの学習
Learning visual servo policies via planner cloning
シミュレーション上の完全状態モーションプランナの振る舞いを模倣する新しい行動クローニング手法PQCを提案し、障害物回避を伴う視覚サーボタスクで実機転移を含め約87%の成功率を達成した。
著者: Ulrich Viereck, Kate Saenko, Robert Platt
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Learning control policies for visual servoing in novel environments is an important problem. However, standard model-free policy learning methods are slow. This paper explores planner cloning: using behavior cloning to learn policies that mimic the behavior of a full-state motion planner in simulation. We propose Penalized Q Cloning (PQC), a new behavior cloning algorithm. We show that it outperforms several baselines and ablations on some challenging problems involving visual servoing in novel environments while avoiding obstacles. Finally, we demonstrate that these policies can be transferred effectively onto a real robotic platform, achieving approximately an 87% success rate both in simulation and on a real robot.
