First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
Not on the map. Why?
Abstract (arXiv)
Combining data-driven models that adapt online and model predictive control (MPC) has enabled effective control of nonlinear systems. However, when deployed on unstable systems, online adaptation may not be fast enough to ensure reliable simultaneous learning and control. For example, a controller on a vehicle executing highly dynamic maneuvers--such as drifting to avoid an obstacle--may push the vehicle's tires to their friction limits, destabilizing the vehicle and allowing modeling errors to quickly compound and cause a loss of control. To address this challenge, we present an active information gathering framework for identifying vehicle dynamics as quickly as possible. We propose an expressive vehicle dynamics model that leverages Bayesian last-layer meta-learning to enable rapid online adaptation. The model's uncertainty estimates are used to guide informative data collection and quickly improve the model prior to deployment. Dynamic drifting experiments on a Toyota Supra show that (i) the framework enables reliable control of a vehicle at the edge of stability, (ii) online adaptation alone may not suffice for zero-shot control and can lead to undesirable transient errors or spin-outs, and (iii) active data collection helps achieve reliable performance.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 31 Oct 2024.
Builds on
22 of 45 references.
References · 22
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-learning with differentiable closed-form solverscited by 397
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
- 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 161
- 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 159
- 2018Learning-based Model Predictive Control for Safe Explorationcited by 120
- 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
- 2020Active Learning for Nonlinear System Identification with Guaranteescited by 80
- 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 48
- 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
- 2023Optimistic Active Exploration of Dynamical Systemscited by 32
- 2019Actively Learning Gaussian Process Dynamicscited by 26
10 more
- 2020Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Frameworkcited by 19
- 2023Optimal Exploration for Model-Based RL in Nonlinear Systemscited by 18
- 2022Control-oriented meta-learningcited by 17
- 2022Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Controlcited by 13
- 2024Safe Active Learning for Time-Series Modeling with Gaussian Processescited by 12
- 2020Adaptive Meta-Learning for Identification of Rover-Terrain Dynamicscited by 8
- 2023Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamicscited by 7
- 2023Autonomous Drifting with 3 Minutes of Data via Learned Tire Modelscited by 7
- 2024Active Learning for Control-Oriented Identification of Nonlinear Systemscited by 7
- 2021Active Model Learning using Informative Trajectories for Improved Closed-Loop Control on Real Robotscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.