Songyang Yan
I study autonomous driving systems through simulation testing, scenario generation, safety evaluation, and configuration repair.
- Focus
- Autonomous driving testing
- Current
- Doctoral research and visiting research
- Base
- Tokyo, Japan / Xi'an, China
Research Areas
Simulation-first evaluation for safer autonomous systems
My work combines software engineering, cyber-physical simulation, and empirical safety evaluation for autonomous driving systems.
Simulation-based safety evaluation
Scenario generation and coverage
Closed-loop co-simulation
Configuration bug localization and repair
Selected Publications
Recent papers and tools
Publication entries are sorted by year and link to full detail pages.
View all publicationsCapCo: Automating Carla-Apollo Co-Simulation and Scenario Fuzzing
co-simulationscenario fuzzingCARLAApolloConFixer: Robustness Semantics Based Configuration Bug Fixing for Automated Driving Systems
configuration bugsrobustness semanticsformal methodsautomated drivingOn-Demand Scenario Generation for Testing Automated Driving Systems
scenario generationADS testingFSEsimulationSelf Drive Guard: A Simulation Platform for Autonomous Driving Systems
simulation platformsoftware-in-the-loopscenario descriptionverification
Projects
Research systems and engineering work
CARLA Leaderboard 2.0
Remote core development work for the CARLA Autonomous Driving Leaderboard, focused on new scenarios, map testing, route validation, and performance optimization.
CARLAsimulation testingbenchmarkingscenario validation
Changan Intelligent Traffic-Flow and Scenario Generation
Scenario-generation algorithm and simulation-framework work delivered to Changan Automobile AI Research Institute.
scenario generationtraffic flowsimulation frameworkautomated driving testing
IEEE ADWG P3534
Standards drafting work for operational and safety requirements for autonomous vehicles in port environments.
IEEE ADWGautonomous vehiclesport environmentssafety requirements
Writing
Notes and essays
June 6, 2026
From Benchmarks to Operational Requirements
A short reflection on how benchmark engineering and standards drafting meet in autonomous driving systems.
benchmarksstandardsautonomous drivingJune 5, 2026
Scenario Generation as a Testing Interface
A short technical note on treating scenario generation as a controllable interface for automated driving system testing.
scenario generationADS testingsimulation