发表机构
Purdue University; University of Florida（普渡大学; 佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究动态移动操纵中触觉传感在全身控制的作用，提出 TAC-LOCO 框架，编码触觉观测与本体感觉统一控制肢体，经奖励设计使策略能应对多种情况，部署后实现降力及低掉落率。
AI 中文摘要
动态移动操纵要求有腿机器人在不确定外力下与被抓物体保持稳定物理交互时协调全身运动。虽然触觉传感在机器人操纵中已被广泛研究，但其在动态全身控制中的作用仍很大程度未被探索。现有无触觉反馈的工作通常紧握而非根据交互调节抓握。我们提出 TAC-LOCO，一种触觉增强的统一强化学习框架，将柔顺夹爪的触觉阵列观测编码为紧凑的潜在表示，并与本体感觉结合用于腿、臂和夹爪的统一控制。通过有效的抓握稳定性奖励设计，策略学会在逐渐负载变化和突然释放事件下同时跟踪身体速度和末端执行器轨迹、调节抓握力并防止物体滑动。我们在配备 Interbotix WidowX 250 臂和触觉夹爪的 Unitree Go2 上进行零样本策略部署，展示了在不同外部交互下的动态触觉感知移动操纵，抓握力降低 47%，物体掉落率小于 1%。
英文摘要
Dynamic loco-manipulation requires legged robots to coordinate whole-body motion while maintaining stable physical interaction with grasped objects under uncertain external forces. While tactile sensing has been widely studied for robotic manipulation, its role in dynamic whole-body control remains largely unexplored. Existing works without tactile feedback commonly grasp firmly rather than regulate the grasp according to the interaction. We propose TAC-LOCO, a tactile-augmented unified reinforcement learning framework that encodes tactile array observations from compliant grippers into a compact latent representation and joins it with proprioception for unified control of the legs, arm, and gripper. With effective grasp stability reward design, the policy learns to simultaneously track body velocity and end-effector trajectories, moderate grasp force, and prevent object slip under both gradual load changes and sudden release events. We deploy the policy zero-shot on a Unitree Go2 with an Interbotix WidowX 250 arm and tactile gripper, demonstrating dynamic tactile-informed loco-manipulation under varying external interactions, achieving a 47% reduction in grasping force and an object drop rate of less than 1%.
