Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
AgentSim Public Demo Is Live
Published:
The AgentSim demo is public: three real logged drives, each with five generated safety-critical variants rendered as synchronized front-camera video.
Upcoming: RoboSense at the 2026 INFORMS Annual Meeting
Published:
I will present RoboSense at the 2026 INFORMS Annual Meeting on Nov 3, 2026.
FHWA Visit to UMTRI and Mcity
Published:
UMTRI covered a visit by FHWA delegates to AACE and Mcity, including a live demonstration of a near-miss alert system.
MMITSS Transit Signal Priority Demonstration at IEEE IV 2026
Published:
An MMITSS transit signal priority demonstration at Mcity for IEEE IV 2026 attendees and USDOT officials.
MMITSS Demonstration at the ITS America Conference & Expo 2026
Published:
An MMITSS phase-2 demonstration for Michigan DOT and other state DOT officials at ITS America 2026 in Detroit.
TeraSim Demo with NVIDIA and the City of San Jose Selected for the GTC 2026 Keynote
Published:
The TeraSim demo with NVIDIA and the City of San Jose was selected for NVIDIA CEO Jensen Huang’s GTC 2026 keynote.
Live V2X Transit Signal Priority Demo at UMTRI 60th Anniversary Symposium
Published:
Our CART Lab at Purdue University was invited to the University of Michigan Transportation Research Institute (UMTRI) 60th Anniversary Symposium (Oct 2-3, 2025, Ann Arbor, MI), where I gave a live demonstration of a Transit Signal Priority (TSP) system enabled by Vehicle-to-Everything (V2X) communication.
portfolio
AgentSim: Agentic World Model for AV/Physical AI Validation
Initiated and developed at Inchor (SaferDrive AI). LLM/VLM agents mutate real logged drives into safety-critical corner cases, replay them in closed loop, and a video world model renders the result.
RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring
A dynamic robotaxi routing framework that turns centrally controlled fleets into cooperative drive-by sensors for urban traffic monitoring. Under revision at Transportation Research Part C.
Developing a Cooperative Perception System
Project leader of a two-phase cooperative perception project: a V2X cooperative perception safety study funded by NSF (Transportation Research Record, 2024), then an infrastructure-vehicle cooperative perception system funded by CCAT.
Modeling Car-Following Behavior with Physics-Informed Neural Networks
Behavior-level reconstruction of human driving, from physics-constrained prediction to cognitively interpretable response: IDM-Follower (IEEE Transactions on Intelligent Vehicles, first author) and Neural Force (manuscript in preparation).
Cooperative Driving Automation System for Urban Areas (MMITSS)
MMITSS, an open-source connected-vehicle signal priority system: deployments at Mcity and on Ann Arbor’s Ellsworth Road corridor (USDOT FHWA), MMITSS for the Detroit QLine (WSP for Michigan DOT), integration into FHWA’s CDASim co-simulation (Leidos for USDOT FHWA), and a signal-aware connected vehicle.
TeraSim: City-Scale Traffic Simulation for AV Testing
Core developer of TeraSim, an open-source city-scale traffic simulation platform for AV safety testing: MotionTransformer-based naturalistic driving behavior (NNDE), and a city-scale NVIDIA Metropolis Blueprint demo with NVIDIA and the City of San Jose that was selected for the GTC 2026 keynote.
Safety Instinct for Physical AI: A CBF-Based Safety Cerebellum for Quadruped Robots
Independent research at Inchor (SaferDrive AI): a reinforcement learning waypoint controller for a Boston Dynamics Spot robot in NVIDIA Isaac Sim, with a Control Barrier Function safety filter that keeps a dynamic safety boundary around moving obstacles.
publications
Serviceability evaluation of highway tunnels based on data mining and machine learning: A case study of continental United States
Published in Tunnelling and Underground Space Technology, 2023
This paper presents a data mining and machine learning approach for evaluating the serviceability of highway tunnels, using the continental United States as a case study.
Recommended citation: 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.
Download Paper
Dynamic Routing of Connected and Automated Vehicles for Improving Network Coverage
Published in Transportation Research Board Annual Meeting 2024, 2024
This paper formulates the CAV routing problem considering network coverage as an objective and proposes heuristic algorithms with greedy search to solve the multi-objective optimization.
Recommended citation: Yilin Wang, Yiheng Feng* (2024). "Dynamic Routing of Connected and Automated Vehicles for Improving Network Coverage." Transportation Research Board Annual Meeting 2024, Poster Presentation.
IDM-Follower: A Model-Informed Deep Learning Method for Car-Following Trajectory Prediction
Published in IEEE Transactions on Intelligent Vehicles, 2024
We introduce a physics-informed neural network (PINN) model that integrates the Intelligent Driver Model (IDM) into a deep learning framework for car-following trajectory prediction. The proposed model exhibits robustness against real-time GPS noise.
Recommended citation: 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.
Download Paper
Cooperative Perception System for Aiding Connected and Automated Vehicle Navigation and Improving Safety
Published in Transportation Research Record, 2024
This paper presents a cooperative perception system connected by V2X between roadside LiDAR and CAV sensors, demonstrating safety benefits in detecting occluded vulnerable road users (VRUs).
Recommended citation: 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.
Download Paper
A Cooperative Perception Based Dynamic Vehicle Routing Framework for Urban Traffic Monitoring
Published in Transportation Research Board Annual Meeting 2026, 2026
We apply Cell Transmission Model (CTM) for traffic state prediction and propose a comprehensive MILP formulation for dynamic vehicle routing considering traffic monitoring performance. An extended version, RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring (Yilin Wang, Yiheng Feng), is under revision at Transportation Research Part C; see the open-source code, the arXiv preprint, and the project page.
Recommended citation: 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.
RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring
Published in arXiv preprint; under revision at Transportation Research Part C, 2026
Manuscript under revision at Transportation Research Part C: Emerging Technologies; the preprint was posted on arXiv on Sept 6, 2026. RoboSense is a dynamic routing framework that turns centrally controlled robotaxi fleets into cooperative drive-by sensors for urban traffic monitoring. It combines a cell-based network representation built on Cell Transmission Model (CTM) traffic-state prediction, a cell-level spatiotemporal coverage metric, and a rolling-horizon MILP that trades off passenger travel time against network monitoring coverage. Details: project page and code on GitHub.
Recommended citation: 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.
Download Paper
talks
Dynamic Routing of Connected and Automated Vehicles for Improving Network Coverage
Published:
Poster presentation on formulating the CAV routing problem considering network coverage as an objective and proposing heuristic algorithms with greedy search to solve the multi-objective optimization.
IDM-Follower: A Model-Informed Deep Learning Method for Car-Following Trajectory Prediction
Published:
Research presentation on integrating the Intelligent Driver Model (IDM) into a physics-informed neural network for car-following trajectory prediction.
A Cooperative Perception Based Dynamic Vehicle Routing Framework for Urban Traffic Monitoring
Published:
Poster presentation on a cooperative perception based dynamic vehicle routing framework using Cell Transmission Model (CTM) and MILP formulation for urban traffic monitoring.
RoboSense: Leveraging Robotaxi Fleets as Drive-by Sensors for Urban Traffic Monitoring
Published:
Scheduled presentation of RoboSense, a dynamic routing framework that turns centrally controlled robotaxi fleets into cooperative drive-by sensors for urban traffic monitoring. The preprint is on arXiv and the code is on GitHub.
