Neural Process-Based Reactive Controller for Autonomous Racing

2026-01-17

AI Summary

This work addresses the challenge of simultaneously achieving real-time performance, high control fidelity, and provable safety in high-speed autonomous racing. To this end, the authors propose a reactive controller based on a Physics-Informed Attentional Neural Process (PI-AttNP), augmented with a lightweight and generalizable Control Barrier Function (CBF) safety layer that enables analytical collision avoidance. By integrating attention mechanisms with physics-based inductive biases—a novel approach in the context of autonomous racing—the method achieves superior closed-loop performance in the F1TENTH simulation environment while rigorously satisfying real-time safety constraints.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Attention-based neural architectures have become central to state-of-the-art methods in real-time nonlinear control. As these data-driven models continue to be integrated into increasingly safety-critical domains, ensuring statistically grounded and provably safe decision-making becomes essential. This paper introduces a novel reactive control framework for gap-based navigation using the Attentive Neural Process (AttNP) and a physics-informed extension, the PI-AttNP. Both models are evaluated in a simulated F1TENTH-style Ackermann steering racecar environment, chosen as a fast-paced proxy for safety-critical autonomous driving scenarios. The PI-AttNP augments the AttNP architecture with approximate model-based priors to inject physical inductive bias, enabling faster convergence and improved prediction accuracy suited for real-time control. To further ensure safety, we derive and implement a control barrier function (CBF)-based filtering mechanism that analytically enforces collision avoidance constraints. This CBF formulation is fully compatible with the learned AttNP controller and generalizes across a wide range of racing scenarios, providing a lightweight and certifiable safety layer. Our results demonstrate competitive closed-loop performance while ensuring real-time constraint satisfaction.

Problem

• autonomous racing
• safe control
• collision avoidance
• real-time nonlinear control
• safety-critical systems

Innovation

• Attentive Neural Process
• Physics-Informed Learning
• Control Barrier Function
• Autonomous Racing
• Gap-Based Navigation