First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling

2024-10-31

arXiv.org

AI Summary

Under extreme driving conditions, rapid and accurate identification of vehicle dynamic parameters remains challenging, often leading to failure of stability control. Method: This paper proposes a Bayesian meta-learning-driven Model Predictive Control (MPC) framework that integrates Bayesian Last-Layer Meta-Learning with an uncertainty-guided active information acquisition mechanism, enabling reliable drift control near tire friction limits. Contribution/Results: Compared to conventional online adaptation, the proposed paradigm significantly enhances zero-shot generalization capability and accelerates online adaptation. Leveraging a Bayesian neural network combined with first-principles vehicle dynamics modeling, the method is experimentally validated on a Toyota Supra. It achieves dynamic drift control without prior knowledge of the operating scenario, demonstrating the critical role of active data acquisition in ensuring stability at the handling limits.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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, controllers on a vehicle executing highly dynamic maneuvers may push the tires to their friction limits, destabilizing the vehicle and allowing modeling errors to quickly compound and cause a loss of control. In this work, we present a Bayesian meta-learning MPC framework. 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. Experiments on a Toyota Supra show that (i) the framework enables reliable control in dynamic drifting maneuvers, (ii) online adaptation alone may not suffice for zero-shot control of a vehicle at the edge of stability, and (iii) active data collection helps achieve reliable performance.

Problem

• Ensuring reliable control in unstable vehicle dynamics
• Addressing slow online adaptation for dynamic maneuvers
• Reducing modeling errors at friction limits

Innovation

• Active information gathering for dynamics identification
• Bayesian last-layer meta-learning for rapid adaptation
• Model predictive control with uncertainty-guided data collection