JEPA-WAM: ロボット操作のためのワールドアクションモデルにおける段階レベル結合埋め込み予測
JEPA-WAM: Stage-Level Joint-Embedding Prediction for World-Action Models in Robot Manipulation
ロボット操作タスクにおいて、短期的な物理的未来と段階的な意味的未来を区別し、段階レベルの潜在目標を予測するJEPA-WAMを提案。50のタスクで成功率90.25%を達成し、実行ステップ数を削減した。
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: Xiao Liu, Yuguang Yang, Xi Wang, Kai Jiang, Cheng Chi, Yong Xu, Wenchao Ding, Yilun Chen, Yan Wang
分類: cs.RO
原文アブストラクト
Generalist robot policies aim to map multimodal observations and linguistic task instructions to actions across diverse tasks. However, existing methods typically represent the future as a fixed, short video-action chunk. This short-term future captures local scene evolution for action execution, but it does not explicitly describe the stage-level future that specifies how a task should progress from its current stage to the next. We therefore distinguish two complementary futures for robot manipulation: a short-term physical future to capture local scene evolution and a stage-level semantic future to represent task progress. We introduce JEPA-WAM, which augments a Motus-based World Action Model (WAM) with Stage-JEPA, a goal-conditioned Joint-Embedding Predictive Architecture (JEPA) predictor. Given the current observation and task instruction, Stage-JEPA uses a frozen V-JEPA2 encoder to extract the current-state representation and predicts the latent target of the next inferred stage. Across 50 RoboTwin 2.0 tasks in clean and randomized environments, JEPA-WAM achieves 90.25% overall success and reduces the mean number of execution steps in successful rollouts by 5.97% relative to the strongest baseline.