ランダム化画像から正規画像への変換に基づくモデル予測制御による実世界視覚ロボットマニピュレーション
Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation
ランダム化された画像からタスクに関連する特徴とそのダイナミクスを抽出するKRCモデルを提案し、実世界データを収集せずにシミュレーションから実世界へゼロショット転移できる視覚モデル予測制御を実現した。
著者: Tomoya Yamanokuchi, Yuhwan Kwon, Yoshihisa Tsurumine, Eiji Uchibe, Jun Morimoto, Takamitsu Matsubara
分類: cs.RO, cs.LG
原文アブストラクト
Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a significant human effort in transferring the models learned in simulations to new domains in the real world. To alleviate this problem, we first propose a novel model-learning framework called Kalman Randomized-to-Canonical Model (KRC-model). This framework is capable of extracting task-relevant intrinsic features and their dynamics from randomized images. We then propose Kalman Randomized-to-Canonical Model Predictive Control (KRC-MPC) as a zero-shot sim-to-real transferable visual MPC using KRC-model. The effectiveness of our method is evaluated through a valve rotation task by a robot hand in both simulation and the real world, and a block mating task in simulation. The experimental results show that KRC-MPC can be applied to various real domains and tasks in a zero-shot manner.
