逆強化学習とTD-MPCによるロボットアーム操作
Robotic Arm Manipulation with Inverse Reinforcement Learning & TD-MPC
人間の視覚デモンストレーションからコスト関数を逆強化学習で学習し、TD-MPCでロボットアームの操作軌道を最適化する手法を提案し、実機で検証した。
著者: Md Shoyib Hassan, Sabir Md Sanaullah
分類: cs.RO
原文アブストラクト
One unresolved issue is how to scale model-based inverse reinforcement learning (IRL) to actual robotic manipulation tasks with unpredictable dynamics. The ability to learn from both visual and proprioceptive examples, creating algorithms that scale to high-dimensional state-spaces, and mastering strong dynamics models are the main obstacles. In this work, we provide a gradient-based inverse reinforcement learning framework that learns cost functions purely from visual human demonstrations. The shown behavior and the trajectory is then optimized using TD visual model predictive control(MPC) and the learned cost functions. We test our system using fundamental object manipulation tasks on hardware.