| CARVIEW |
Select Language
HTTP/2 200
last-modified: Mon, 04 Sep 2023 00:13:53 GMT
cache-control: max-age=3600
content-type: text/html; charset=utf-8
content-security-policy: frame-ancestors 'none'
x-frame-options: SAMEORIGIN
x-cloud-trace-context: 4d9f553ec39c1a738832d82d5a02ea4b
server: Google Frontend
via: 1.1 google, 1.1 varnish, 1.1 varnish
accept-ranges: bytes
age: 697196
date: Thu, 01 Jan 2026 00:28:29 GMT
x-served-by: cache-lga21925-LGA, cache-bom-vanm7210051-BOM
x-cache: HIT, MISS
x-timer: S1767227309.237011,VS0,VE206
content-length: 46202
[2308.09405] Robust Quadrupedal Locomotion via Risk-Averse Policy Learning
Skip to main content
[v1] Fri, 18 Aug 2023 09:12:21 UTC (4,891 KB)
[v2] Fri, 1 Sep 2023 07:11:28 UTC (7,082 KB)
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors.
Donate
Computer Science > Robotics
arXiv:2308.09405 (cs)
[Submitted on 18 Aug 2023 (v1), last revised 1 Sep 2023 (this version, v2)]
Title:Robust Quadrupedal Locomotion via Risk-Averse Policy Learning
Authors:Jiyuan Shi, Chenjia Bai, Haoran He, Lei Han, Dong Wang, Bin Zhao, Mingguo Zhao, Xiu Li, Xuelong Li
View a PDF of the paper titled Robust Quadrupedal Locomotion via Risk-Averse Policy Learning, by Jiyuan Shi and 8 other authors
View PDF
Abstract:The robustness of legged locomotion is crucial for quadrupedal robots in challenging terrains. Recently, Reinforcement Learning (RL) has shown promising results in legged locomotion and various methods try to integrate privileged distillation, scene modeling, and external sensors to improve the generalization and robustness of locomotion policies. However, these methods are hard to handle uncertain scenarios such as abrupt terrain changes or unexpected external forces. In this paper, we consider a novel risk-sensitive perspective to enhance the robustness of legged locomotion. Specifically, we employ a distributional value function learned by quantile regression to model the aleatoric uncertainty of environments, and perform risk-averse policy learning by optimizing the worst-case scenarios via a risk distortion measure. Extensive experiments in both simulation environments and a real Aliengo robot demonstrate that our method is efficient in handling various external disturbances, and the resulting policy exhibits improved robustness in harsh and uncertain situations in legged locomotion. Videos are available at this https URL.
| Comments: | 8 pages, 5 figures |
| Subjects: | Robotics (cs.RO) |
| Cite as: | arXiv:2308.09405 [cs.RO] |
| (or arXiv:2308.09405v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2308.09405
arXiv-issued DOI via DataCite
|
Submission history
From: Jiyuan Shi [view email][v1] Fri, 18 Aug 2023 09:12:21 UTC (4,891 KB)
[v2] Fri, 1 Sep 2023 07:11:28 UTC (7,082 KB)
Full-text links:
Access Paper:
- View PDF
- TeX Source
View a PDF of the paper titled Robust Quadrupedal Locomotion via Risk-Averse Policy Learning, by Jiyuan Shi and 8 other authors
References & Citations
export BibTeX citation
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.