Park, Joonho (Ajou University), Oh, Gyungtaek (Ajou University), Park, Haneul (Ajou University), So, Jaehyun (Ajou University)

Integration of Testing Scenarios for Automated Vehicles Using a Route Optimization Algorithm

Scheduled for presentation during the Regular Session "S42b-Safety and Risk Assessment for Autonomous Driving Systems" (FR-EA-T42), Friday, November 21, 2025, 13:50−14:10, 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

This study aims to determine the most efficient execution route for a predefined set of autonomous vehicle test scenarios within K-City, a controlled testing environment in Republic of Korea. Each of the 47 scenarios is associated with a set of feasible zones, and the objective is to select one zone per scenario and derive an optimal route that minimizes total travel distance. To solve this problem, a hybrid method combining Genetic Algorithm and Integer Programming was applied. GA identifies valid combinations of scenario-to-zone assignments, while IP computes the shortest path that satisfies the required zone visit counts. The approach was validated through both a simplified 5×5 grid network and the actual K-City road network. The results demonstrated that the proposed method significantly reduces redundant movement and produces an execution route that is practical for real-world testing. The final path was segmented into five manageable subroutes to address operational constraints such as setup time and personnel fatigue.