外观
论文arXiv 2610.1485418 天前
DEFT-VLA：面向接触丰富机器人操作的阶段局部化力特化
原文链接：DEFT-VLA: Stage-Localized Force Specialization for Contact-Rich Robotic Manipulation（arXiv 2610.14854 · 发布日期：2026-10-10）
DEFT-VLA: Stage-Localized Force Specialization for Contact-Rich Robotic Manipulation
针对接触丰富操作中的阶段性感知冲突，DEFT-VLA以双专家和接触局部力注意课程训练，在真机任务上验证提升表现。
核心要点
- 问题在于非接触阶段力信息可能干扰，而接触后力反馈变得关键。
- 方法保留任务适配基础专家处理非接触行为，并引入力感知接触专家。
- 课程仅对接触专家进行力注意后训练，逐步恢复视觉并遮蔽状态token。
- 真机三项任务中较最强基线总体成功率提升20-40个百分点。
验证范围与局限：验证限于真机上的移液器吸头安装、双臂移液器吸液和白板擦拭任务。
英文摘要 (Abstract)
Contact-rich manipulation poses a stage-dependent sensory conflict: vision and proprioception are essential for localization and approach, when force is largely uninformative and potentially distracting, whereas force becomes critical after contact, when irrelevant visual details and correlated robot states may become shortcuts. We propose DEFT-VLA (Dual-Expert Force-specialized Training for Vision-Language-Action Manipulation), which retains the task-adapted base expert for vision-dominated non-contact behavior and introduces a force-aware contact expert for critical contact stages, localizing force-conditioned adaptation to where it is needed. We further introduce a contact-localized force-attending curriculum that applies force-attending post-training only to the contact expert, progressively restoring vision and masking state tokens to suppress shortcuts. Real-robot experiments on pipette tip attachment, bimanual pipette aspiration, and whiteboard wiping show that DEFT-VLA effectively exploits force feedback to improve contact-stage performance while maintaining strong non-contact behavior and robustness to held-out grasp heights. It improves overall task success by 20-40 percentage points over the strongest baseline on each task.
作者：Zan Huang, Yibo Qiu, Kan Ding, Xuanping Zhang, Ao Tian, Ronald X. Xu, Mingzhai Sun
来源
本页事实对应的公开页面，以原文为准。