タスク指向の能動的探索でsim2realギャップを埋める方策学習
Learning Active Task-Oriented Exploration Policies for Bridging the Sim-to-Real Gap
タスクに関連するシステムパラメータを特定するための探索行動を明示的に学習し、モデルベース軌道最適化と組み合わせて実世界タスクを遂行する枠組みを提案・検証した論文。
著者: Jacky Liang, Saumya Saxena, Oliver Kroemer
分類: cs.RO
原文アブストラクト
Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The former is sensitive to the manually-specified training distribution of dynamics parameters and can result in behaviors that are overly conservative. The latter requires learning policies that concurrently perform the task and generate useful trajectories for system identification. In this work, we propose and analyze a framework for learning exploration policies that explicitly perform task-oriented exploration actions to identify task-relevant system parameters. These parameters are then used by model-based trajectory optimization algorithms to perform the task in the real world. We instantiate the framework in simulation with the Linear Quadratic Regulator as well as in the real world with pouring and object dragging tasks. Experiments show that task-oriented exploration helps model-based policies adapt to systems with initially unknown parameters, and it leads to better task performance than task-agnostic exploration.
