发表机构
University of Bremen; University of North Texas; Toyota Motor North America（不来梅大学; 北得克萨斯大学; 丰田北美汽车公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CAPABLE是结合自监督能力推理与残差强化学习的VLA策略自适应框架，在28个LIBERO任务中提升故障执行器成功率，可迁移至多关节及未见故障族，在Franka Panda上验证有效。
AI 中文摘要
视觉-语言-动作（VLA）策略假设其在训练时的实体上运行，当关节故障改变指令动作的物理执行方式时，这些策略可能失效。现有的故障恢复方法通常需要特定任务的重新训练、故障标签、显式诊断或特权实体信息。我们提出CAPABLE，这是一种针对冻结VLA策略的统一能力感知自适应框架，将自监督能力推理与残差强化学习相结合。CAPABLE通过跨关节共享的时间编码器、雅可比基础、跨关节注意力和自监督物理预测，从指令-响应历史和运动学中在线推断能力，即每个关节实际实现的指令运动程度，以及该运动对末端执行器行为的贡献程度。所得表示条件化残差策略，该策略在无故障标签或故障关节标识符的情况下，为VLA机械臂动作添加有界修正。在28个LIBERO任务中，CAPABLE将故障训练中未包含的执行器的成功率从24.8%提升至59.3%，在保持健康性能的同时，比参数匹配的全局历史基线高出17.4个百分点。对6个关节的留一执行器实验表明，这种迁移并非特定于某一执行器，额外评估表征了对未见故障族的迁移，并展示了在物理Franka Panda上的恢复效果。
英文摘要
Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing fault-recovery methods often require task-specific retraining, fault labels, explicit diagnosis, or privileged embodiment information. We introduce CAPABLE, a unified capability-aware adaptation framework for frozen VLAs that integrates self-supervised capability inference with residual reinforcement learning. CAPABLE infers capability, how much of the commanded motion each joint actually realizes and how that motion contributes to end-effector behavior, online from command-response history and kinematics using a temporal encoder shared across joints, Jacobian grounding, cross-joint attention, and self-supervised physical prediction. The resulting representation conditions a residual policy that adds bounded corrections to the VLA arm action without fault labels or faulty-joint identifiers. Across 28 LIBERO tasks, CAPABLE raises success on an actuator excluded from fault training from 24.8% to 59.3%, outperforming a parameter-matched global-history baseline by 17.4 points while preserving healthy performance. Leave-one-actuator-out experiments across six joints show that this transfer is not specific to one actuator, and additional evaluations characterize transfer to unseen fault families and demonstrate recovery on a physical Franka Panda. https://capable-vla.github.io/
