A Causal Probabilistic Framework for Perception-Informed Closed-Loop Simulation of Autonomous Driving

2026-06-05

AI Summary

This study addresses the over-optimistic safety assessment of autonomous driving systems in conventional software-in-the-loop simulation, which typically assumes ideal perception and neglects environmental disturbances such as fog or rain that induce perceptual errors. To bridge this gap, the authors propose a perception-driven simulation framework integrating a causal probabilistic model to systematically inject physically plausible perception failures into standard scenario-based simulation pipelines. Grounded in the SOTIF (ISO 21448) validation framework, this approach effectively reproduces real-world perception failures and uncovers safety-critical risks that traditional simulations often miss. The method offers a scalable, realistic closed-loop testing pathway for verifying SOTIF compliance in advanced driver assistance and autonomous driving systems.

Abstract

Software-in-the-loop (SIL) simulation is a cornerstone for the validation of modern automotive safety functions. However, many current frameworks utilize ideal sensing, which bypasses the functional insufficiencies of perception algorithms, leading to over-optimistic safety assessments. This paper proposes a perception-informed SIL testing methodology that bridges the gap between ground-truth simulation and real-world perception behavior. We present a framework for incorporating causal probabilistic models into standardized, scenario-based simulation toolchains, applicable to both Advanced Driver Assistance Systems (ADAS) and Autonomous Driving Systems (ADS). Our approach enables the systematic injection of realistic perception errors, such as loss of detection, sizing inaccuracies, and positioning offsets, derived from physical triggering conditions like fog, rain, and object-merging scenarios. By evaluating these ``faults'' within a standardized simulation environment, we demonstrate that perception-informed testing reveals latent operational risks that ideal SIL environments fail to capture, providing a scalable pathway for SOTIF (ISO 21448) validation.

Problem

• perception-informed simulation
• autonomous driving
• software-in-the-loop
• perception errors
• SOTIF validation

Innovation

• causal probabilistic modeling
• perception-informed simulation
• software-in-the-loop (SIL)
• autonomous driving validation
• SOTIF