ThinkingVLA: ロボット操作のための視覚と言語の推論を交互に行う手法
ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation
ロボット操作タスクにおいて、視覚と言語の推論を交互に行う統一アーキテクチャを提案し、長期的な操作タスクでの性能を向上させた。
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: Tianyi Lu, Hui Zhang, Zijie Diao, Junke Wang, Shengqi Xu, Xingyao Lin, Guojin Zhong, Ziyi Ye, Peng Wang, Zuxuan Wu, Yu-Gang Jiang
分類: cs.RO
原文アブストラクト
Most Vision-Language-Action (VLA) models map observations directly to actions without explicit reasoning, limiting their capacity for reasoning-intensive long-horizon tasks. To address this, existing approaches adopt Chain-of-Thought (CoT) reasoning to enable subgoal decomposition and spatial anticipation. However, those methods lack a unified architecture for effective cross-modal reasoning and fail to explicitly include inverse reasoning ability based on the target state. We argue that manipulation planning naturally decomposes into prediction, anticipating the next visual state, and inverse dynamics, inferring the actions to reach it. Bridging both requires a unified autoregressive architecture that interleaves textual and visual reasoning in a single generation process. We propose \textbf{ThinkingVLA}, a generative model that realizes this decomposition within a unified Mixture-of-Transformers architecture. ThinkingVLA consists of a forward CoT that identifies the immediate subgoal and guides the visual forecasting; the predicted image then serves as the target state, grounding an inverse CoT that reasons about spatial relationships and action intent based on the predicted image; and the final action is generated conditioned on this full reasoning context. Extensive experiments on simulation and real-world benchmarks demonstrate that ThinkingVLA consistently outperforms state-of-the-art baselines, with particularly large gains on long-horizon manipulation tasks.
