Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Levy, Jacob, Gibson, Jason, Vlahov, Bogdan, Tevere, Erica, Theodorou, Evangelos, Fridovich-Keil, David, Spieler, Patrick
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915255300390912
author Levy, Jacob
Gibson, Jason
Vlahov, Bogdan
Tevere, Erica
Theodorou, Evangelos
Fridovich-Keil, David
Spieler, Patrick
author_facet Levy, Jacob
Gibson, Jason
Vlahov, Bogdan
Tevere, Erica
Theodorou, Evangelos
Fridovich-Keil, David
Spieler, Patrick
contents High-speed off-road autonomous driving presents unique challenges due to complex, evolving terrain characteristics and the difficulty of accurately modeling terrain-vehicle interactions. While dynamics models used in model-based control can be learned from real-world data, they often struggle to generalize to unseen terrain, making real-time adaptation essential. We propose a novel framework that combines a Kalman filter-based online adaptation scheme with meta-learned parameters to address these challenges. Offline meta-learning optimizes the basis functions along which adaptation occurs, as well as the adaptation parameters, while online adaptation dynamically adjusts the onboard dynamics model in real time for model-based control. We validate our approach through extensive experiments, including real-world testing on a full-scale autonomous off-road vehicle, demonstrating that our method outperforms baseline approaches in prediction accuracy, performance, and safety metrics, particularly in safety-critical scenarios. Our results underscore the effectiveness of meta-learned dynamics model adaptation, advancing the development of reliable autonomous systems capable of navigating diverse and unseen environments. Video is available at: https://youtu.be/cCKHHrDRQEA
format Preprint
id arxiv_https___arxiv_org_abs_2504_16923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving
Levy, Jacob
Gibson, Jason
Vlahov, Bogdan
Tevere, Erica
Theodorou, Evangelos
Fridovich-Keil, David
Spieler, Patrick
Robotics
Machine Learning
Systems and Control
High-speed off-road autonomous driving presents unique challenges due to complex, evolving terrain characteristics and the difficulty of accurately modeling terrain-vehicle interactions. While dynamics models used in model-based control can be learned from real-world data, they often struggle to generalize to unseen terrain, making real-time adaptation essential. We propose a novel framework that combines a Kalman filter-based online adaptation scheme with meta-learned parameters to address these challenges. Offline meta-learning optimizes the basis functions along which adaptation occurs, as well as the adaptation parameters, while online adaptation dynamically adjusts the onboard dynamics model in real time for model-based control. We validate our approach through extensive experiments, including real-world testing on a full-scale autonomous off-road vehicle, demonstrating that our method outperforms baseline approaches in prediction accuracy, performance, and safety metrics, particularly in safety-critical scenarios. Our results underscore the effectiveness of meta-learned dynamics model adaptation, advancing the development of reliable autonomous systems capable of navigating diverse and unseen environments. Video is available at: https://youtu.be/cCKHHrDRQEA
title Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2504.16923