敵対的特徴学習による汎化可能な視覚運動制御
Adversarial Feature Training for Generalizable Robotic Visuomotor Control
深層強化学習で訓練した視覚運動ポリシーを、敵対的学習によるドメイン転送で新たなタスク環境へ汎化させる手法を提案し、実機のピッキングと注ぎタスクで有効性を示した。
著者: Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task. In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority.
