Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception

2025-09-15

AI Summary

The black-box nature of AI perception modules undermines closed-loop stability and performance guarantees in autonomous driving systems, particularly under misdetection and measurement noise. Method: This paper proposes a safety-critical control framework that unifies these two representative perception errors—misdetections as a continuous-time Markov chain and measurement noise as a Wiener process—yielding an analyzable stochastic closed-loop model. Leveraging stochastic calculus and convex optimization, we conduct rigorous stability analysis and synthesize an output-feedback controller. Results: Evaluated on adaptive cruise control, the approach ensures both closed-loop stability and robust performance under realistic perception disturbances. It constitutes the first AI perception–control co-design that jointly achieves interpretable error modeling and formal performance guarantees.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Intelligent Robots: State Estimation
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Safety is a critical concern in autonomous vehicle (AV) systems, especially when AI-based sensing and perception modules are involved. However, due to the black box nature of AI algorithms, it makes closed-loop analysis and synthesis particularly challenging, for example, establishing closed-loop stability and ensuring performance, while they are fundamental to AV safety. To approach this difficulty, this paper aims to develop new modeling, analysis, and synthesis tools for AI-based AVs. Inspired by recent developments in perception error models (PEMs), the focus is shifted from directly modeling AI-based perception processes to characterizing the perception errors they produce. Two key classes of AI-induced perception errors are considered: misdetection and measurement noise. These error patterns are modeled using continuous-time Markov chains and Wiener processes, respectively. By means of that, a PEM-augmented driving model is proposed, with which we are able to establish the closed-loop stability for a class of AI-driven AV systems via stochastic calculus. Furthermore, a performance-guaranteed output feedback control synthesis method is presented, which ensures both stability and satisfactory performance. The method is formulated as a convex optimization problem, allowing for efficient numerical solutions. The results are then applied to an adaptive cruise control (ACC) scenario, demonstrating their effectiveness and robustness despite the corrupted and misleading perception.

Problem

• Modeling AI-induced perception errors in autonomous vehicles
• Establishing closed-loop stability for AI-driven vehicle systems
• Developing performance-guaranteed control synthesis methods

Innovation

• Modeling perception errors with Markov chains
• Using Wiener processes for measurement noise
• Convex optimization for control synthesis