让四足机器人通过触觉感知实现动态抓握与运动的统一控制
TAC-LOCO: Unified Whole-Body Control for Quadrupedal TACtile-Informed LOCO-Manipulation
- 用触觉+本体感知融合生成紧凑表征，统一控制腿、臂和夹爪
- 在外部扰动下抓握力降低47%，物体掉落率低于1%
- 适合需要稳定动态抓握的四足机器人应用
动态的腿式抓取操作要求机器人在不确定外部作用力下协调全身运动并保持对抓取物的稳定物理交互。尽管触觉传感在机器人抓取中被广泛研究，但其在全身动态控制中的作用仍基本未被探索。现有无触觉反馈的方法通常采用强力抓握而非根据交互状态调节抓力。我们提出TAC-LOCO，一种触觉增强的统一强化学习框架，将柔性夹爪上的触觉阵列观测编码为紧凑潜在表征，并与本体感知融合，实现对腿、臂和夹爪的统一控制。通过有效的抓握稳定性奖励设计，策略学会同时追踪身体速度和末端执行器轨迹，调节抓握力并防止物体滑脱，适用于渐进式负载变化和突发释放事件。我们在配备Interbotix WidowX 250机械臂和触觉夹爪的Unitree Go2上零样本部署该策略，展示了在不同外部交互下的动态触觉引导式抓取运动，抓握力降低47%，物体掉落率低于1%。
原文摘要 · Abstract (English)
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%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。