Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Driving
This addresses the challenge of reliable autonomous navigation in diverse and unseen off-road environments, representing an incremental improvement with specific gains.
The paper tackled the problem of dynamics models struggling to generalize to unseen terrain in high-speed off-road autonomous driving by proposing a framework that combines meta-learned parameters with online adaptation, resulting in outperformance of baseline approaches in prediction accuracy, performance, and safety metrics in real-world testing.
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