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

arXiv: https://arxiv.org/abs/2504.16923 · HTML: https://mlsanity.com/paper/2504.16923/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 30 of 30)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds](https://mlsanity.com/paper/2205.06908/) (2022)
- [Continuous Meta-Learning without Tasks](https://mlsanity.com/paper/1912.08866/) (2019)
- [Meta-Learning Priors for Efficient Online Bayesian Regression](https://mlsanity.com/paper/1807.08912/) (2018)
- [Learning Fast Adaptation with Meta Strategy Optimization](https://mlsanity.com/paper/1909.12995/) (2019)
- [Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning](https://mlsanity.com/paper/2003.01239/) (2020)
- [Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling](https://mlsanity.com/paper/2109.06407/) (2021)
- [Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads](https://mlsanity.com/paper/2004.11345/) (2020)
- [TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation](https://mlsanity.com/paper/2303.15771/) (2023)
- [Meta-Adaptive Nonlinear Control: Theory and Algorithms](https://mlsanity.com/paper/2106.06098/) (2021)
- [Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map](https://mlsanity.com/paper/2203.13429/) (2022)
- [Control-oriented meta-learning](https://mlsanity.com/paper/2204.06716/) (2022)
- [Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models](https://mlsanity.com/paper/2410.09163/) (2024)
- [Graph-based Multi-sensor Fusion for Consistent Localization of Autonomous Construction Robots](https://mlsanity.com/paper/2203.01389/) (2022)
- [Probabilistic Traversability Model for Risk-Aware Motion Planning in Off-Road Environments](https://mlsanity.com/paper/2210.00153/) (2022)
- [Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features](https://mlsanity.com/paper/2207.07920/) (2022)
- [A Multi-step Dynamics Modeling Framework For Autonomous Driving In Multiple Environments](https://mlsanity.com/paper/2305.02241/) (2023)
- [Safe Deep Policy Adaptation](https://mlsanity.com/paper/2310.08602/) (2023)
- [Model Predictive Control for Aggressive Driving Over Uneven Terrain](https://mlsanity.com/paper/2311.12284/) (2023)
- [Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics](https://mlsanity.com/paper/2009.10191/) (2020)
- [Learning Terrain-Aware Kinodynamic Model for Autonomous Off-Road Rally Driving With Model Predictive Path Integral Control](https://mlsanity.com/paper/2305.00676/) (2023)
- [Autonomous Drifting with 3 Minutes of Data via Learned Tire Models](https://mlsanity.com/paper/2306.06330/) (2023)
- [MAGIC-VFM: Meta-learning Adaptation for Ground Interaction Control with Visual Foundation Models](https://mlsanity.com/paper/2407.12304/) (2024)
- [Pay Attention to How You Drive: Safe and Adaptive Model-Based Reinforcement Learning for Off-Road Driving](https://mlsanity.com/paper/2310.08674/) (2023)
- [Learning-Based On-Track System Identification for Scaled Autonomous Racing in Under a Minute](https://mlsanity.com/paper/2411.17508/) (2024)
- [Low Frequency Sampling in Model Predictive Path Integral Control](https://mlsanity.com/paper/2404.03094/) (2024)
- [Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environments](https://mlsanity.com/paper/2411.06632/) (2024)
- [Dynamics Modeling using Visual Terrain Features for High-Speed Autonomous Off-Road Driving](https://mlsanity.com/paper/2412.00581/) (2024)
- [Ensemble Gaussian Processes for Adaptive Autonomous Driving on Multi-friction Surfaces](https://mlsanity.com/paper/2303.13694/) (2023)
- [OCCAM: Online Continuous Controller Adaptation with Meta-Learned Models](https://mlsanity.com/paper/2406.17620/) (2024)

## Built on by (most cited first, 3 of 3)

- [Data-Driven Modeling and Correction of Vehicle Dynamics](https://mlsanity.com/paper/2512.00289/) (2025)
- [Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains](https://mlsanity.com/paper/2607.13319/) (2026)
- [Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2609.12278/) (2026)

## Abstract (arXiv)

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