两座桥梁，一条路径：从VLM到具有具身轨迹耦合数据的可泛化VLA
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
AI总结：
提出具身轨迹耦合（ETC）数据作为中间桥梁，通过三阶段训练策略（分布桥接、目标桥接、保留适应）将视觉语言模型（VLM）逐步转化为可泛化的视觉语言动作模型（VLA），解决从VLM到VLA的双重鸿沟。
摘要：
视觉语言模型（VLM）是强大的通用推理器，但将其转化为机器人控制策略（VLA）却异常困难。根本原因在于双重鸿沟：VLM在互联网规模的图像上训练，具有语言理解目标，而VLA必须感知机器人场景并预测电机动作。直接在机器人动作数据上微调VLM迫使模型同时跨越两个鸿沟——学习曲线陡峭，预训练期间获得的丰富泛化能力往往会退化而非迁移。我们认为，通过合适的中间数据可以逐步弥合这一鸿沟。我们引入了\emph{具身轨迹耦合（ETC）数据}——源自用于动作学习的相同机器人场景和轨迹的视觉语言监督。由于ETC数据共享机器人操作的视觉上下文，同时保留熟悉的语言理解目标，它提供了VLM预训练和VLA微调之间的自然垫脚石。基于此，我们设计了一个三阶段训练方案。分布桥接首先将VLM适应于具身视觉语言语义。目标桥接然后逐步将模型转向动作预测，同时保留已获得的表示。保留适应最后将策略专门化到目标部署领域。我们进一步证明，将任务相关的分布外ETC数据与少量动作数据混合，使模型能够泛化到新颖的视觉语言条件，而无需额外的机器人演示。仿真和真实机器人实验证实，这种逐步桥接策略是将VLM泛化能力迁移到鲁棒、可部署的机器人策略的关键。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
