Research papers · Posted 2026.06.05 · Preprint

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

Zhennan Fei, Rickard Johansson, Mikael Andersson, Matthias Eng, Mattias Eriksson, Kaveh Kianfar, Sadegh Rahrovani, Chris van der Ploeg, Michael Borth, Maren Buermann, Michiel Braat, Henk Goossens, Zijian Han, Majid Khorsand Vakilzadeh, Gabriel Rodrigues de Campos · arXiv · English

Overview

The framework injects causally modeled perception errors into scenario-based software-in-the-loop simulation. Fog, rain and object-merging conditions produce realistic detection and localization insufficiencies for ADAS and automated-driving SOTIF evaluation.

Version: v1

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

Overview

Participation enquiry

Your enquiry has been sent.

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

Overview

Related resources

Connected Dependability Cage: Run-Time Function and Anomaly Monitoring for the Development and Operation of Safe Automated Vehicles

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

First-principles Based 3D Virtual Simulation Testing for Discovering SOTIF Corner Cases of Autonomous Driving