Schubert, Richard (Technische Universität Braunschweig), Loba, Marvin (Technische Universität Braunschweig), Sünnemann, Jasper (TU Braunschweig), Stolte, Torben (Technische Universität Braunschweig), Maurer, Markus (TU Braunschweig)

Conformal Prediction of Motion Control Performance for an Automated Vehicle in Presence of Actuator Degradations and Failures

Scheduled for presentation during the Regular Session "Advanced Vehicle Safety Systems II" (ThAT8), Thursday, September 26, 2024, 10:30−10:50, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 8, 2024

Abstract

Automated driving systems require monitoring mechanisms to ensure safe operation, especially if system components degrade or fail. Their runtime self-representation plays a key role as it provides a-priori knowledge about the system’s capabilities and limitations. In this paper, we propose a data-driven approach for deriving such a self-representation model for the motion controller of an automated vehicle. A conformalized prediction model is learned and allows estimating how operational conditions as well as potential degradations and failures of the vehicle’s actuators impact motion control performance. During runtime behavior generation, our predictor provides a heuristic for determining the admissible action space.