外观
论文arXiv 2610.0842522 天前
MIM-VLA：从夹爪电机反馈中学习物理交互表征
原文链接：MIM-VLA: Learning Physical Interaction Representations from Gripper Motor Feedback（arXiv 2610.08425 · 发布日期：2026-10-06）
MIM-VLA: Learning Physical Interaction Representations from Gripper Motor Feedback
MIM-VLA将夹爪电机反馈编码为交互token，在真实物体阻力比较、真假辨别和易碎物抓取中验证。
核心要点
- VLA主要依赖视觉和机器人状态推断抓取，缺少接触后物理响应的显式表征。
- 方法将夹爪电流、位置、速度和信号有效性编码为128维交互token。
- MIM经人工复核的接触与交互阶段标签预训练，仅条件化SmolVLA的夹爪动作路径。
- 13组物体对实验中，MIM-VLA选择高阻力物体的比例为75.0%，基线为48.8%。
验证范围与局限：验证范围为三个真实世界设置：阻力比较、视觉相似真假物体主动探测和易碎物体轻柔抓取。
英文摘要 (Abstract)
Vision-language-action (VLA) policies infer grasp actions primarily from visual observations and robot state, but do not explicitly represent the physical response observed after contact. We present MIM-VLA, a motor-feedback-based architecture that encodes recent gripper current, position, velocity, and signal validity as a 128-dimensional interaction token. A motor-only Motor Interaction Module (MIM) is pretrained with human-reviewed contact and interaction-phase labels and then conditions only the gripper-action pathway of SmolVLA; arm actions and the position-control interface remain unchanged. The same token supports the MEM selector VLM that compares candidate interactions and produces evidence-conditioned selections and explanations. We evaluate MIM-VLA in three real-world settings: comparing the interaction resistance of visually different objects, disambiguating visually similar real and replica objects through active probing, and gently grasping fragile objects, including held-out instances. Across 13 object pairs, MIM-VLA selects the higher-resistance object in 75.0% of trials, compared with 48.8% for the SmolVLA baseline. For the evaluated tasks, the approach uses motor feedback already available from the gripper and does not require an additional tactile array, force-torque sensor, calibrated force estimate, or direct current control.
作者：Lee, Jaeyoung, Jiyeon Koo, Kim, Taehwa, Yerin Cha, Andrew Jaeyong Choi
来源
本页事实对应的公开页面，以原文为准。