WALA: 行動ラベル付きデモと行動フリー動画から実行可能な潜在行動を学習する
WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos
行動ラベル付きデモと行動フリー動画の両方から実行可能な潜在行動を学習するフレームワークWALAを提案し、ロボットポリシーの性能と汎化性を向上させた。
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: Jiahao Liu, Zhongpu Xia, Shuai Tian, Huangrui Li, Yuhang Zheng, Ning Ma, Xin Fu, Xiaotian Liu, Jing Li, Yixian Li, ShangQing Zhou, Zebin Xing, Linbo Wang, Chaoyue Li, Haoran Li, Dongbin Zhao
分類: cs.RO
原文アブストラクト
Generalizable robot policies typically rely on action-labeled robot demonstrations, which are expensive to collect and difficult to scale. In contrast, large-scale human and robot videos contain rich physical interactions but often lack executable robot action labels. We present WALA, a framework for learning executable latent actions from both action-labeled demonstrations and action-free videos. WALA first pretrains a semantic-geometric latent action model from videos by modeling the evolution between current observations and sparsely sampled future observations. Instead of reconstructing raw pixels, WALA predicts future deltas in the DINOv3 feature space and dense depth space, preserving task-relevant semantic and geometric structure while reducing sensitivity to appearance details. During policy training, the pretrained encoder provides stable latent action targets, and the decoder serves as a trainable latent world model. The latent actions generated by the vision-language backbone are jointly supervised by robot action prediction, latent action target matching, and future dynamics prediction. This enables action-labeled demonstrations to provide executable control supervision, while action-free videos contribute dynamics supervision without requiring robot action annotations. Experiments show that WALA achieves strong performance on RoboTwin, sets a new state-of-the-art result on RoboCasa with 75.2% average success, and improves both policy performance and generalization in real-world manipulation tasks.
