MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Songbo, Luo, Shixin, Wu, Jun, Zhu, Qiuguo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913597391634432
author Li, Songbo
Luo, Shixin
Wu, Jun
Zhu, Qiuguo
author_facet Li, Songbo
Luo, Shixin
Wu, Jun
Zhu, Qiuguo
contents Legged robots possess inherent advantages in traversing complex 3D terrains. However, previous work on low-cost quadruped robots with egocentric vision systems has been limited by a narrow front-facing view and exteroceptive noise, restricting omnidirectional mobility in such environments. While building a voxel map through a hierarchical structure can refine exteroception processing, it introduces significant computational overhead, noise, and delays. In this paper, we present MOVE, a one-stage end-to-end learning framework capable of multi-skill omnidirectional legged locomotion with limited view in 3D environments, just like what a real animal can do. When movement aligns with the robot's line of sight, exteroceptive perception enhances locomotion, enabling extreme climbing and leaping. When vision is obstructed or the direction of movement lies outside the robot's field of view, the robot relies on proprioception for tasks like crawling and climbing stairs. We integrate all these skills into a single neural network by introducing a pseudo-siamese network structure combining supervised and contrastive learning which helps the robot infer its surroundings beyond its field of view. Experiments in both simulations and real-world scenarios demonstrate the robustness of our method, broadening the operational environments for robotics with egocentric vision.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environments
Li, Songbo
Luo, Shixin
Wu, Jun
Zhu, Qiuguo
Robotics
Legged robots possess inherent advantages in traversing complex 3D terrains. However, previous work on low-cost quadruped robots with egocentric vision systems has been limited by a narrow front-facing view and exteroceptive noise, restricting omnidirectional mobility in such environments. While building a voxel map through a hierarchical structure can refine exteroception processing, it introduces significant computational overhead, noise, and delays. In this paper, we present MOVE, a one-stage end-to-end learning framework capable of multi-skill omnidirectional legged locomotion with limited view in 3D environments, just like what a real animal can do. When movement aligns with the robot's line of sight, exteroceptive perception enhances locomotion, enabling extreme climbing and leaping. When vision is obstructed or the direction of movement lies outside the robot's field of view, the robot relies on proprioception for tasks like crawling and climbing stairs. We integrate all these skills into a single neural network by introducing a pseudo-siamese network structure combining supervised and contrastive learning which helps the robot infer its surroundings beyond its field of view. Experiments in both simulations and real-world scenarios demonstrate the robustness of our method, broadening the operational environments for robotics with egocentric vision.
title MOVE: Multi-skill Omnidirectional Legged Locomotion with Limited View in 3D Environments
topic Robotics
url https://arxiv.org/abs/2412.03353