Schade, Nick (Technical University Braunschweig), Pannek, Jürgen (Institute for Intermodal Transportation and Logistic System, Tec)

From Single to Multi-Ego: Scenario Fusion for Multi-Ego Validation of Autonomous Vehicles

Scheduled for presentation during the Regular Session "S27b-Safety and Risk Assessment for Autonomous Driving Systems" (TH-EA-T27), Thursday, November 20, 2025, 14:30−14:50, Broadbeach 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

In the field of autonomous driving simulations, the generation of complex and diverse traffic scenarios is imperative for robust testing and validation of these systems. However, real-world datasets frequently comprise primarily single-ego scenarios, wherein only a single autonomous vehicle (AV), the ego vehicle, is considered. This paper proposes an approach to enrich simulation-based validation systems by fusing multiple single-ego scenarios through similarity identification techniques, enabling the synthesis of realistic and behaviorally consistent multi-ego scenarios. Consequently, the necessity of test runs for a single system under test may be reduced, while concurrently enabling the assessment of interactions among reactive traffic participants and different system under tests. Through an illustrative case study, we demonstrate the proposed method and identify open challenges regarding the similarity detection and generation of unknown scenarios.