二つの橋、一つの道：身体化軌跡結合データによるVLMから汎用VLAへの変換
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
視覚言語モデル(VLM)をロボット制御ポリシー(VLA)に変換する際のギャップを、ロボットの軌跡に基づく中間データ(ETCデータ)と3段階の訓練手法で段階的に橋渡しし、汎用性を高める手法を提案した論文。
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: Linqi Yin, Shiduo Zhang, Shenling Qiu, Chenxin Li, Zhaoyang Fu, Lei Xiao, Xiang Wang, Chenchen Yang, Zhe Xu, Pengfang Qian, Jingjing Gong, Xipeng Qiu, Xuanjing Huang, Yu-Gang Jiang
分類: cs.RO
原文アブストラクト
Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult. The root cause is a two-fold gap: VLMs are trained on internet-scale images with language-understanding objectives, while VLAs must perceive robot scenes and predict motor actions. Fine-tuning a VLM directly on robot action data forces the model to cross both gaps at once -- the learning curve is steep and the rich generalizations learned during pretraining tend to degrade rather than transfer. We argue that this gap can be bridged gradually with the right intermediate data. We introduce \emph{embodied trajectory-coupled (ETC) data} -- vision-language supervision derived from the same robot scenes and trajectories used for action learning. Because ETC data shares the visual context of robot operation while retaining familiar language-understanding objectives, it provides a natural stepping stone between VLM pretraining and VLA fine-tuning. Building on this, we design a three-stage training recipe. Distribution Bridging first adapts the VLM to embodied visual-language semantics. Objective Bridging then gradually shifts the model toward action prediction while preserving the acquired representations. Retentive Adaptation finally specializes the policy to the target deployment domain. We further show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions without requiring additional robot demonstrations. Simulation and real-robot experiments confirm that this gradual bridging strategy is the key to transferring VLM generalization into robust, deployable robot policies.
