ViT-A*: Legged Robot Path Planning using Vision Transformer A*

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

ViT-A: Legged Robot Path Planning using Vision Transformer A

Liu, Jianwei; Lyu, Shirui; Hadjivelichkov, Denis; Modugno, Valerio; Kanoulas, Dimitrios; (2024) ViT-A*: Legged Robot Path Planning using Vision Transformer A*. In: Proceedings of the 2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids). IEEE: Austin, Texas, USA. Green open access

[thumbnail of humanoids_2023_jianwei.pdf]

Preview

Text
humanoids_2023_jianwei.pdf - Accepted Version
Download (3MB) | Preview

Abstract

Legged robots, particularly quadrupeds, offer promising navigation capabilities, especially in scenarios requiring traversal over diverse terrains and obstacle avoidance. This paper addresses the challenge of enabling legged robots to navigate complex environments effectively through the integration of data-driven path-planning methods. We propose an approach that utilizes differentiable planners, allowing the learning of end-to-end global plans via a neural network for commanding quadruped robots. The approach leverages 2D maps and obstacle specifications as inputs to generate a global path. To enhance the functionality of the developed neural network-based path planner, we use Vision Transformers (ViT) for map pre-processing, to enable the effective handling of larger maps. Experimental evaluations on two real robotic quadrupeds (Boston Dynamics Spot and Unitree Go1) demonstrate the effectiveness and versatility of the proposed approach in generating reliable path plans.

Type:	Proceedings paper
Title:	ViT-A: Legged Robot Path Planning using Vision Transformer A
Event:	IEEE-RAS International Conference on Humanoid Robots
ISBN-13:	979-8-3503-0327-8
Open access status:	An open access version is available from UCL Discovery
DOI:	10.1109/Humanoids57100.2023.10374562
Publisher version:	https://doi.org/10.1109/Humanoids57100.2023.103745...
Language:	English
Additional information:	This version is the author accepted manuscript. // This work was supported by the UKRI Future Leaders Fellowship [MR/V025333/1] (RoboHike) and the CDT for Foundational Artificial Intelligence [EP/S021566/1]. For the purpose of Open Access, the author has applied a CC BY public copyright license to any Author Accepted Manuscript version arising from this submission.
Keywords:	Legged locomotion, Navigation, Neural networks, Humanoid robots, Transformers, Reliability engineering, Path planning
UCL classification:	UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI:	https://discovery.ucl.ac.uk/id/eprint/10178766