ドメインランダム化を超えて:動画からの視覚的にロバストな敵対的模倣のためのイベント着想知覚
Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos
RGB動画を時間的強度勾配を符号化するイベントベース表現に変換し、見た目の違いに影響されないロボット模倣学習を実現した研究。
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: Andrea Ramazzina, Vittorio Giammarino, Matteo El-Hariry, Mario Bijelic
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
Imitation from videos often fails when expert demonstrations and learner environments exhibit domain shifts, such as discrepancies in lighting, color, or texture. While visual randomization partially addresses this problem by augmenting training data, it remains computationally intensive and inherently reactive, struggling with unseen scenarios. We propose a different approach: instead of randomizing appearances, we eliminate their influence entirely by rethinking the sensory representation itself. Inspired by biological vision systems that prioritize temporal transients (e.g., retinal ganglion cells) and by recent sensor advancements, we introduce event-inspired perception for visually robust imitation. Our method converts standard RGB videos into a sparse, event-based representation that encodes temporal intensity gradients, discarding static appearance features. This biologically grounded approach disentangles motion dynamics from visual style, enabling robust visual imitation from observations even in the presence of visual mismatches between expert and agent environments. By training policies on event streams, we achieve invariance to appearance-based distractors without requiring computationally expensive and environment-specific data augmentation techniques. Experiments across the DeepMind Control Suite and the Adroit platform for dynamic dexterous manipulation show the efficacy of our method. Our code is publicly available at Eb-LAIfO.
