ニューラルスタイル変換に基づくエンドツーエンドの実例ベースsim-to-real強化学習方策転移とロボット切断への応用
End-to-end example-based sim-to-real RL policy transfer based on neural stylisation with application to robotic cutting
画像処理のニューラルスタイル変換を再解釈し、未ペア・未ラベルの実世界データから訓練データを合成することで、強化学習方策のsim-to-real転移を実現する手法を提案し、未知材料のロボット切断に適用して有効性を示した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jamie Hathaway, Alireza Rastegarpanah, Rustam Stolkin
分類: cs.RO
原文アブストラクト
Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world deployment due to the domain gap between simulated and physical systems, coupled with limited real-world sample availability. We propose a novel method for sim-to-real transfer of reinforcement learning policies, based on a reinterpretation of neural style transfer from image processing to synthesise novel training data from unpaired unlabelled real world datasets. We employ a variational autoencoder to jointly learn self-supervised feature representations for style transfer and generate weakly paired source-target trajectories to improve physical realism of synthesised trajectories. We demonstrate the application of our approach based on the case study of robot cutting of unknown materials. Compared to baseline methods, including our previous work, CycleGAN, and conditional variational autoencoder-based time series translation, our approach achieves improved task completion time and behavioural stability with minimal real-world data. Our framework demonstrates robustness to geometric and material variation, and highlights the feasibility of policy adaptation in challenging contact-rich tasks where real-world reward information is unavailable.
