SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Shaoting, Li, Derun, Mou, Linzhan, Liu, Yong, Xu, Ningyi, Zhao, Hang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916654135377920
author Zhu, Shaoting
Li, Derun
Mou, Linzhan
Liu, Yong
Xu, Ningyi
Zhao, Hang
author_facet Zhu, Shaoting
Li, Derun
Mou, Linzhan
Liu, Yong
Xu, Ningyi
Zhao, Hang
contents The application of vision-language models (VLMs) has achieved impressive success in various robotics tasks. However, there are few explorations for these foundation models used in quadruped robot navigation through terrains in 3D environments. In this work, we introduce SARO (Space Aware Robot System for Terrain Crossing), an innovative system composed of a high-level reasoning module, a closed-loop sub-task execution module, and a low-level control policy. It enables the robot to navigate across 3D terrains and reach the goal position. For high-level reasoning and execution, we propose a novel algorithmic system taking advantage of a VLM, with a design of task decomposition and a closed-loop sub-task execution mechanism. For low-level locomotion control, we utilize the Probability Annealing Selection (PAS) method to effectively train a control policy by reinforcement learning. Numerous experiments show that our whole system can accurately and robustly navigate across several 3D terrains, and its generalization ability ensures the applications in diverse indoor and outdoor scenarios and terrains. Project page: https://saro-vlm.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2407_16412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model
Zhu, Shaoting
Li, Derun
Mou, Linzhan
Liu, Yong
Xu, Ningyi
Zhao, Hang
Robotics
The application of vision-language models (VLMs) has achieved impressive success in various robotics tasks. However, there are few explorations for these foundation models used in quadruped robot navigation through terrains in 3D environments. In this work, we introduce SARO (Space Aware Robot System for Terrain Crossing), an innovative system composed of a high-level reasoning module, a closed-loop sub-task execution module, and a low-level control policy. It enables the robot to navigate across 3D terrains and reach the goal position. For high-level reasoning and execution, we propose a novel algorithmic system taking advantage of a VLM, with a design of task decomposition and a closed-loop sub-task execution mechanism. For low-level locomotion control, we utilize the Probability Annealing Selection (PAS) method to effectively train a control policy by reinforcement learning. Numerous experiments show that our whole system can accurately and robustly navigate across several 3D terrains, and its generalization ability ensures the applications in diverse indoor and outdoor scenarios and terrains. Project page: https://saro-vlm.github.io/
title SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model
topic Robotics
url https://arxiv.org/abs/2407.16412