LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Changyi, Song, Yuxin Ray, Huo, Boda, Yu, Mingyang, Wang, Yikai, Liu, Shiqi, Yang, Yuxiang, Yu, Wenhao, Zhang, Tingnan, Tan, Jie, Luo, Yiyue, Zhao, Ding
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914014879023104
author Lin, Changyi
Song, Yuxin Ray
Huo, Boda
Yu, Mingyang
Wang, Yikai
Liu, Shiqi
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Tan, Jie
Luo, Yiyue
Zhao, Ding
author_facet Lin, Changyi
Song, Yuxin Ray
Huo, Boda
Yu, Mingyang
Wang, Yikai
Liu, Shiqi
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Tan, Jie
Luo, Yiyue
Zhao, Ding
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23175
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing
Lin, Changyi
Song, Yuxin Ray
Huo, Boda
Yu, Mingyang
Wang, Yikai
Liu, Shiqi
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Tan, Jie
Luo, Yiyue
Zhao, Ding
Robotics
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.
title LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing
topic Robotics
url https://arxiv.org/abs/2505.23175