外观
论文arXiv 2610.0439125 天前
AgenticTactileVLA：用于可泛化灵巧操作且无需 VLA 重新训练的接触引导执行时监督
提出AgenticTactileVLA，用本体接触反馈监督固定VLA执行，并在真机留出物体操作中验证提升。
宇树 G1原文链接：AgenticTactileVLA: Contact-Guided Execution-Time Supervision for Generalizable Dexterous Manipulation without VLA Retraining（arXiv 2610.04391 · 发布日期：2026-10-03）
AgenticTactileVLA: Contact-Guided Execution-Time Supervision for Generalizable Dexterous Manipulation without VLA Retraining
提出AgenticTactileVLA，用本体接触反馈监督固定VLA执行，并在真机留出物体操作中验证提升。
核心要点
- 同类抓取物体几何与柔顺性不同，闭合遮挡会削弱视觉反馈。
- 固定VLA给出接近与手部目标，监督器按接触证据细化或交还控制。
- 在Unitree G1与BrainCo Revo2手上，五个留出物体完成率达84.0%。
- 消融显示收益非仅来自延长闭合，选择性触发减少65.7%纠正。
验证范围与局限：验证范围为Unitree G1搭载BrainCo Revo2手的真机实验、五个VLA训练外物体及薄壁杯研究。
英文摘要 (Abstract)
Vision-language-action policies may predict a transferable manipulation strategy yet fail to realize it reliably on the encountered object: objects compatible with the same grasp differ in geometry and compliance, and visual feedback degrades under closure occlusion. AgenticTactileVLA is presented as an execution-time supervisor that shifts part of object-specific adaptation from prediction to physical interaction. A fixed VLA provides the approach and hand targets; the supervisor decides whether to remain transparent, refine finger flexion, retain or release the corrected configuration, return control to the VLA for retry, or select a compliant hand-control regime. It uses finger-position and motor-effort feedback as proprioceptive contact evidence and requires neither tactile sensors nor VLA retraining. On a Unitree G1 with a BrainCo Revo2 hand, a randomized matched-block evaluation on five objects held out from VLA training yields 61.3% completion for the base VLA, 72.0% for unconditional close-to-stall control, and 84.0% for the supervisor under a shared budget; the gain is positive on every object and persists under moderate pose perturbations. Ablations show the gain is not explained by extended closure alone, and that selective triggering reduces correction episodes by 65.7% with no detected change in completion. A retention audit shows acceptance predicts retention in 88.9% of held-out cases, while compliant objects expose conservative false rejection. A thin-walled-cup study demonstrates contextual routing to compliant control, matching an always-compliant reference. These results suggest that contact-guided execution-time adaptation can improve the object-level generalization of a fixed VLA to held-out objects by adapting physical realization without object-specific retraining.
作者：Elizaveta Semenyakina, Ivan Snegirev, Mikhail V. Kiselev, Miguel Altamirano Cabrera, Artem Lykov, Hajira Amjad, Dzmitry Tsetserukou
来源
本页事实对应的公开页面，以原文为准。