LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing

TL;DR

LocoTouch enables quadrupedal robots to reliably transport unsecured objects over long distances using tactile sensing and learned control policies, demonstrating robustness and transferability from simulation to real-world scenarios.

Contribution

The paper introduces a high-density tactile sensor, a simulation environment with tactile feedback, and a two-stage learning pipeline for robust object transport in quadrupedal robots.

Findings

Successful zero-shot transfer from simulation to real-world transport tasks

Robust transport of diverse unsecured cylindrical objects

Effective locomotion gaits with adaptive and symmetric control

Abstract

Quadrupedal robots have demonstrated remarkable agility and robustness in traversing complex terrains. However, they struggle with dynamic object interactions, where contact must be precisely sensed and controlled. To bridge this gap, we present LocoTouch, a system that equips quadrupedal robots with tactile sensing to address a particularly challenging task in this category: long-distance transport of unsecured cylindrical objects, which typically requires custom mounting or fastening mechanisms to maintain stability. For efficient large-area tactile sensing, we design a high-density distributed tactile sensor that covers the entire back of the robot. To effectively leverage tactile feedback for robot control, we develop a simulation environment with high-fidelity tactile signals, and train tactile-aware transport policies using a two-stage learning pipeline. Furthermore, we design a novel reward function to promote robust, symmetric, and frequency-adaptive locomotion gaits. After training in simulation, LocoTouch transfers zero-shot to the real world, reliably transporting a wide range of unsecured cylindrical objects with diverse sizes, weights, and surface properties. Moreover, it remains robust over long distances, on uneven terrain, and under severe perturbations.