Research papers · Posted 2024.10.17 · Publication / acceptance: author-reported
GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulation
GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulation
Overview
GraphSCENE learns temporal scene-graph relationships among vehicles, agents and infrastructure to generate requested traffic scenarios. Ontology constraints preserve semantic validity, while simulator rendering demonstrates their use as autonomous-vehicle test environments.
Publication and version information
Publication, acceptance or venue information is author-reported on arXiv. The exact source wording is preserved below.
Author-supplied source information
Author-supplied information on arXiv.
Accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)
Version: arXiv v3 — manuscript revision