ChainVLA: 統一実行状態による長期的操作のためのビジョン・言語・行動クエリの連鎖
ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation
長期的な操作タスクにおいて、過去の行動の結果と現在の動作を連鎖させる新しいVLAポリシーを提案。進行状況コンテキストとモーションテールを統合し、高い成功率を達成。
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: Yuzhi Huang, Weijue Bu, Ziyi Xiong, Jie Wu, Fanding Huang, Jingyan Jiang, Zhi Wang
分類: cs.RO
原文アブストラクト
Humans perform long-horizon manipulation by retaining knowledge of what earlier actions have established while continuously adapting the motion underway. By contrast, action-chunked vision-language-action (VLA) policies repeatedly replan from the current input at each query. Existing methods preserve either long-term task evidence through memory or short-term motion through action reuse and ensembling, leaving the cross-query handoff incomplete. We introduce ChainVLA, a 1.2B-parameter VLA policy that chains successive queries through a joint and revisable execution state. Progress Context combines a recurrent Working State with sparse event memory to carry observation-derived task progress, while Motion Tail feeds the preceding prediction's unexecuted continuation into state construction and action generation. Together, the two components condition a decoder that regenerates each action horizon under the latest observation, allowing the carried state to guide the next prediction without fixing it. ChainVLA reaches 62.8% average success on RMBench and 98.8% across four LIBERO suites, while removing Motion Tail or Progress Context reduces RMBench success to 11.2% and 3.0%, respectively. These asymmetric ablations are consistent with motion continuity helping preserve the observation stream from which task progress is inferred.