Robust localization, mapping, and navigation for quadruped robots
(2025) 12th European Conference on Mobile Robots, ECMR 2025 In 2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings- Abstract
Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a robust localization, mapping, and navigation system for low-cost quadruped robots. In pursuit of this objective, we combine contact-aided kinematic, visual-inertial odometry, and depth-stabilized vision, enhancing the system's stability and accuracy. Our results in simulation and two different real-world quadruped platforms show that our system... (More)
Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a robust localization, mapping, and navigation system for low-cost quadruped robots. In pursuit of this objective, we combine contact-aided kinematic, visual-inertial odometry, and depth-stabilized vision, enhancing the system's stability and accuracy. Our results in simulation and two different real-world quadruped platforms show that our system can generate an accurate 2D map of the environment, robustly localize itself, and navigate autonomously. Furthermore, we present in-depth ablation studies of the system's key components and their impact on localization accuracy. Videos, code, and additional experiments can be found on the project website.1
(Less)
- author
- Aditya, Dyuman
; Huang, Junning
; Bohlinger, Nico
; Kicki, Piotr
; Walas, Krzysztof
; Peters, Jan
; Luperto, Matteo
and Tateo, Davide
LU
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings
- series title
- 2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings
- editor
- Gasteratos, Antonios ; Bellotto, Nicola and Tortora, Stefano
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 12th European Conference on Mobile Robots, ECMR 2025
- conference location
- Padua, Italy
- conference dates
- 2025-09-02 - 2025-09-05
- external identifiers
-
- scopus:105018215248
- ISBN
- 9798331527051
- DOI
- 10.1109/ECMR65884.2025.11163249
- language
- English
- LU publication?
- no
- id
- 1ce95e82-d7d6-4a5b-8bf0-92e36309568c
- date added to LUP
- 2025-10-16 14:30:51
- date last changed
- 2025-11-03 16:17:54
@inproceedings{1ce95e82-d7d6-4a5b-8bf0-92e36309568c,
abstract = {{<p>Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a robust localization, mapping, and navigation system for low-cost quadruped robots. In pursuit of this objective, we combine contact-aided kinematic, visual-inertial odometry, and depth-stabilized vision, enhancing the system's stability and accuracy. Our results in simulation and two different real-world quadruped platforms show that our system can generate an accurate 2D map of the environment, robustly localize itself, and navigate autonomously. Furthermore, we present in-depth ablation studies of the system's key components and their impact on localization accuracy. Videos, code, and additional experiments can be found on the project website.<sup>1</sup></p>}},
author = {{Aditya, Dyuman and Huang, Junning and Bohlinger, Nico and Kicki, Piotr and Walas, Krzysztof and Peters, Jan and Luperto, Matteo and Tateo, Davide}},
booktitle = {{2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings}},
editor = {{Gasteratos, Antonios and Bellotto, Nicola and Tortora, Stefano}},
isbn = {{9798331527051}},
language = {{eng}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings}},
title = {{Robust localization, mapping, and navigation for quadruped robots}},
url = {{http://dx.doi.org/10.1109/ECMR65884.2025.11163249}},
doi = {{10.1109/ECMR65884.2025.11163249}},
year = {{2025}},
}