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

TL;DR

This paper introduces a data-driven conformal prediction model that estimates how actuator degradations and failures affect an automated vehicle's motion control, enhancing safety monitoring and decision-making.

Contribution

It presents a novel conformal prediction approach for real-time assessment of vehicle actuator health and its impact on motion control performance.

Findings

Effective estimation of actuator degradation impact

Improved safety monitoring in automated driving

Real-time heuristic for safe action selection

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 can provide a heuristic for determining the admissible action space.