CV
My CV comes as two documents:
- Resume: a short industry resume.
- Full CV: the complete academic CV.
Project details are on the Projects pages.
Education
- Ph.D. in Civil Engineering (Transportation and Infrastructure Systems Engineering), Purdue University, Aug 2021 – May 2027 (expected)
- Dissertation (tentative title): A Cooperative Traffic Monitoring System with a Scenario Reconstruction
- Advisor: Dr. Yiheng Feng
- Research Area: Connected and Automated Vehicle, Cooperative Perception, Physics-informed Machine Learning, Robotaxi Operation and Control
- GPA: 3.8/4.00
- M.S. in Advanced Infrastructure Systems, Carnegie Mellon University, Aug 2019 – Dec 2020
- Research advisor: Dr. Pingbo Tang
- Area: Smart City, Deep Learning, Natural Language Processing
- Courses: Deep Learning, Reinforcement Learning, Geo-Informatics System
- GPA: 3.87/4.00
- B.S. in Civil Engineering, Tongji University, Aug 2015 – Jun 2019
- Area: Geo-technical and Underground Engineering
Research and Professional Experience
- Fall 2021 – Present: Graduate Research Assistant, Connected Automated and Resilient Transportation (CART) Lab, Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, IN
- Supervisor: Prof. Yiheng Feng
- Research area: connected and automated vehicles, cooperative perception, V2X communication.
- Robotaxi and CAV fleet routing for traffic monitoring, an individual dissertation project (RoboSense).
- Physics-informed and interpretable car-following models (IDM-Follower and Neural Force).
- Cooperative driving automation projects funded by USDOT, Michigan DOT, and Leidos: lead developer and researcher of the Smart Intersections project, mentor and developer for the Detroit QLine, CDASim development with Leidos, and a V2X-based connected automated vehicle (MMITSS).
- Project leader of a cooperative perception project: a CAV safety study funded by NSF, then an infrastructure-vehicle cooperative perception system funded by the Center for Connected and Automated Transportation (CCAT) (project page).
- Teaching assistant for CCE 361 and guest lecturer for CCE 565 (Teaching).
- Dec 2025 – Jun 2026: Simulation Technical Leader Intern, Inchor (SaferDrive AI), Ann Arbor, MI
- Supervisor: Prof. Henry Liu
- TeraSim: Naturalistic Driving Behavior (core developer, Dec 2025 – Mar 2026; project page)
- Core developer of TeraSim, an open-source city-scale traffic simulation platform for AV safety testing.
- Led integration of MotionTransformer as the foundation model of NNDE, generating naturalistic driving behavior at city scale alongside the NADE adversarial-scenario module; refactored the behavior-model pipeline from a dual-state design into a stateless prediction pipeline for large-scale inference.
- Implemented vehicle state synchronization, history tensor construction, and coordinate transformation for large-scale MotionTransformer inference.
- Implemented a full-stack Driving Foundation Model into product; secured and led the company’s collaboration with NVIDIA and the City of San Jose on agent-driven Smart City operation, supporting the deployment of the NVIDIA Metropolis Blueprint in the San Jose city POC on the simulation and traffic-control sides (video).
- For that project, led a city-scale urban simulation demo under the NVIDIA Metropolis Blueprint: an integrated “City Operations Agent” and digital twin that perceive, simulate, and optimize traffic operations; designed the full simulation pipeline, including city-scale vehicle injection, dynamic routing, and multi-phase demo orchestration.
- The TeraSim demo with NVIDIA and the City of San Jose was selected for NVIDIA CEO Jensen Huang’s GTC 2026 keynote.
- AgentSim: Agentic Synthetic Scenario Generation (initiator and lead architect, Mar 2026 – Present; demo)
- An end-to-end pipeline from a trajectory or text description to safety-critical scenarios with ego camera-view data.
- An agentic platform in which LLM/VLM agents collaborate to reconstruct, mutate, and render driving scenarios.
- The agents take a real logged drive and mutate it into safety-critical variants (a lead car braking hard, a cut-in, a red-light runner, a pedestrian crossing). Each variant runs in closed loop, so other road users follow their recorded paths until the mutation reaches them and then react; a video world model renders each variant as front-camera video.
- The closed-loop simulation base was built from scratch, embedded with neural behavior models and supporting multi-modal inputs, and the pipeline includes full scene reconstruction from trajectory-only data; the whole pipeline is benchmarked on the Waymo Open Dataset.
- Product development: built TeraSim and AgentSim into services for paying enterprise customers, delivering test scenarios and simulation environments with fast deployment and packaged delivery.
- Safety Instinct for Physical AI: independent project, Feb 2026 – Apr 2026 (project page).
- Jan 2020 – Dec 2020: Research Assistant, Carnegie Mellon University, Pittsburgh, PA
- Supervisor: Prof. Pingbo Tang
- Research on nuclear power plant operations, including workflow extraction and automatic error correction, using natural language processing.
Publications
Yilin Wang, Yiheng Feng* (2026). "RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring." Under revision at Transportation Research Part C: Emerging Technologies. Preprint: arXiv:2609.06813.
Yilin Wang, Yiheng Feng* (2026). "A Cooperative Perception Based Dynamic Vehicle Routing Framework for Urban Traffic Monitoring." Transportation Research Board Annual Meeting 2026, Poster Presentation.
Hanlin Chen, Vamsi K Bandaru, Yilin Wang, Mario A Romero, Andrew Tarko, Yiheng Feng* (2024). "Cooperative Perception System for Aiding Connected and Automated Vehicle Navigation and Improving Safety." Transportation Research Record, 2678(12), 1498-1510.
Yilin Wang and Yiheng Feng* (2024). "IDM-Follower: A Model-Informed Deep Learning Method for Car-Following Trajectory Prediction." IEEE Transactions on Intelligent Vehicles, vol. 9, no. 6, pp. 5014-5020.
Yilin Wang, Yiheng Feng* (2024). "Dynamic Routing of Connected and Automated Vehicles for Improving Network Coverage." Transportation Research Board Annual Meeting 2024, Poster Presentation.
Ya-Dong Xue, Wei Zhang, Yilin Wang*, et al. (2023). "Serviceability evaluation of highway tunnels based on data mining and machine learning: A case study of continental United States." Tunnelling and Underground Space Technology, Volume 142, 105418.
Talks
November 03, 2026
Conference Presentation at INFORMS 2026 Annual Meeting, San Francisco, CA, USA
January 01, 2026
Poster Presentation at Transportation Research Board Annual Meeting 2026, Washington, D.C., USA
June 01, 2024
Conference Presentation at IEEE Intelligent Vehicles Symposium (IV) 2024, Jeju Island, South Korea
January 01, 2024
Poster Presentation at Transportation Research Board Annual Meeting 2024, Washington, D.C., USA
Professional Service
- Reviewer
- Transportation Research Part C: Emerging Technologies: 3 manuscripts (2024, 2026)
- IEEE Transactions on Intelligent Transportation Systems: 2 manuscripts
- IEEE Transactions on Intelligent Vehicles (2024, 2025)
- Journal of Intelligent Transportation Systems: 5 manuscripts (2023–2025)
- Multimedia Tools and Applications: 2 manuscripts (2023, 2024)
- Tunnelling and Underground Space Technology: 1 manuscript (2026)
- Virtual Reality: 1 manuscript (2026)
- Transportation Research Board (TRB) Annual Meeting: 7 papers
- IEEE Intelligent Transportation Systems Conference (ITSC) (2024)
- Committee: IEEE-IV24 Workshop on Socially Interactive Autonomous Mobility, Committee Member (2024)
- Professional memberships: Transportation Research Board (TRB); IEEE Intelligent Transportation Systems Society; INFORMS
Honors and Awards
Skills
- Programming Languages: Python, C++, MATLAB, JavaScript
- Data Science & Machine Learning: PyTorch, CUDA, Hugging Face
- Simulation & Optimization: SUMO, CARLA, CARMA, NVIDIA Isaac Sim, Gurobi
- Cloud Technologies: AWS, SSH
- DevOps & Version Control: Linux, Docker, Conda
- Cooperation Platform & Project Management: Jira, Slack, GitHub
- Other Tools & Technologies: Microsoft Office, AutoCAD, ArcGIS
- Research Skills: Critical Thinking, Research Talk, Comprehensive Writing, Literature Review
