A Method for the Runtime Validation of AI-based Environment Perception in Automated Driving System

TL;DR

The paper addresses the challenge of validating AI-based environment perception in autonomous driving where formal requirements are incomplete. It proposes a Dependability Cage-based runtime monitoring framework with a function monitor (Safe Zone and AI Perception Validator) that enforces consistency between camera- and LiDAR-based perception within a dynamically computed ROI, and outlines plans for fail-operational reactions. The authors demonstrate feasibility with a lab-based qualitative evaluation on a 1:8 model car using camera and LiDAR, showing the monitor can identify both consistent and inconsistent perception outputs. This approach contributes to safety assurance under ISO 26262/21448 by providing runtime evidence of perception reliability in unknown environments and paves the way for integration with a situation monitor and automatic degradation strategies.

Abstract

Environment perception is a fundamental part of the dynamic driving task executed by Autonomous Driving Systems (ADS). Artificial Intelligence (AI)-based approaches have prevailed over classical techniques for realizing the environment perception. Current safety-relevant standards for automotive systems, International Organization for Standardization (ISO) 26262 and ISO 21448, assume the existence of comprehensive requirements specifications. These specifications serve as the basis on which the functionality of an automotive system can be rigorously tested and checked for compliance with safety regulations. However, AI-based perception systems do not have complete requirements specification. Instead, large datasets are used to train AI-based perception systems. This paper presents a function monitor for the functional runtime monitoring of a two-folded AI-based environment perception for ADS, based respectively on camera and LiDAR sensors. To evaluate the applicability of the function monitor, we conduct a qualitative scenario-based evaluation in a controlled laboratory environment using a model car. The evaluation results then are discussed to provide insights into the monitor's performance and its suitability for real-world applications.

Figures (8)

• Figure 1: High-level Architecture of the Dependability Cage for Runtime Validation AI-based Environment Perception Systems.
• Figure 2: Architecture of the Function Monitor for AI-based Perception Systems.
• Figure 3: AI Perception Validator Algorithm.
• Figure 4: Model Car
• Figure 5: Model Car: bird's-eye view in a Lab Environment.