Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies
For quadrupedal robots performing contact-rich manipulation, this work provides a scalable framework that integrates tactile sensing to improve performance over vision-based methods.
The paper presents a tactile-aware loco-manipulation policy learning pipeline for quadrupedal robots, combining a tactile-conditioned visuotactile high-level policy trained from human demonstrations with a tactile-aware whole-body control policy learned via reinforcement learning. The method achieves a 28.54% average performance improvement over vision-only and visuotactile baselines on real-world contact-rich tasks.
Quadrupedal loco-manipulation is commonly built on visual perception and proprioception. Yet reliable contact-rich manipulation remains difficult: vision and proprioception alone cannot resolve uncertain, evolving interactions with the environment. Tactile sensing offers direct contact observability, but scalable tactile-aware learning framework for quadrupedal loco-manipulation is still underexplored. In this paper, we present a tactile-aware loco-manipulation policy learning pipeline with a hierarchical structure. Our approach has two key components. First, we leverage real-world human demonstrations to train a tactile-conditioned visuotactile high-level policy. This policy predicts not only end-effector trajectories for manipulation, but also the evolving tactile interaction cues that characterize how contact should develop over time. Second, we perform large-scale reinforcement learning in simulation to learn a tactile-aware whole-body control policy that tracks diverse commanded trajectories and tactile interaction cues, and transfers zero-shot to the real world. Together, these components enable coordinated locomotion and manipulation under contact-rich scenarios. We evaluate the system on real-world contact-rich tasks, including in-hand reorientation with insertion, valve tightening, and delicate object manipulation. Compared to vision-only and visuotactile baselines, our method improves performance by 28.54% on average across these tasks.