Oct. 2026
🎙️ Our work on predicting future gait instability from multimodal physiological and biomechanical data was presented at ASPIRE—The HFES 70th International Annual Meeting.
Pronounced “Shing-jee-en”
Fourth-year Ph.D. candidate in Industrial and Systems Engineering, University of Wisconsin–Madison
My research centers on reciprocal adaptation: people constantly adjust to the automation they work with, and automation should learn to adjust back. To make that possible, I build computational models of the human operator with POMDP-based Active Inference that capture what a person believes, how uncertain they are, and how both shape their actions. These models are building blocks for human digital twins, which let vehicles and other intelligent systems anticipate and support the person in the loop.
Oct. 2026
🎙️ Our work on predicting future gait instability from multimodal physiological and biomechanical data was presented at ASPIRE—The HFES 70th International Annual Meeting.
Oct. 2026
🎉 I was selected as a recipient of the 2026 HFES Student Member with Honors Award.
Sep. 2026
📝 My first author work Modeling Driver Adaptation Patterns During Remote Driving was published in Human Factors.
May 2026
📝 My first author work Identifying Critical Breakpoints and Latency Effects During Remote Backup Driving was published in IEEE Transactions on Human-Machine Systems.
May 2026
📝 Our work Automated Assessment of PPE Compliance with Fast Lightweight Deep Learning Based Computer Vision was published in IISE Transactions on Occupational Ergonomics and Human Factors.
May 2026
🎙️ I attended the 2026 NSF M3X PI Meeting, representing our team and presenting our research on Active Inference.
Apr. 2026
🎙️ Undergraduate students I mentored presented our work on latency mitigation effects in remote driving at the UW–Madison Undergraduate Research Symposium.
Jan. 2026
🎉 I passed my Ph.D. preliminary examination.
Jan. 2026
🎙️ I attended the 2026 TRB Annual Meeting and presented our work on human adaptation patterns in remote driving under latency.
Oct. 2025
🎙️ Our work on trust modeling in automated driving with physiological data was presented at ASPIRE—The HFES 69th International Annual Meeting.
Apr. 2025
🎙️ I attended the 2025 Safe Mobility Conference and presented our work on latency effects on human in remote driving.
Mar. 2025
📝 Our work What leads to reliance on automated vehicles? An inferential analysis of responses to variable AV performance was published in Applied Ergonomics.
Oct. 2024
🎉 I passed my Ph.D. qualifying examination.
Sep. 2024
🎙️ I attended ASPIRE—The HFES 68th International Annual Meeting and presented our works on discrete event simulation of remote operator workload and reliance decision modeling in automated vehicles
Jan. 2024
🎙️ Our work on statistical pattern–based analysis of visual scanning behavior in driving was presented at the 2024 TRB Annual Meeting.
Aug. 2023
🏫 I joined the University of Wisconsin–Madison as a Ph.D. student in Industrial and Systems Engineering (Human Factors track).
Automated vehicles will inevitably meet situations they cannot resolve alone, and remote operators are emerging as the bridge to large-scale deployment. Yet remote operation separates the operator from the vehicle: perception arrives through video, actions are delayed by the network, and awareness must be rebuilt from afar. Making it safe, and setting the standards that govern it, hinges on understanding the human in the loop. This project models how remote operators adapt, toward human digital twins that let vehicles anticipate the limits of the people supporting them.
Driving automation is shifting the driver’s role from operator to supervisor, and its gains in safety and mobility depend on people relying on it appropriately. Over-reliance leaves drivers unprepared when the system reaches its limits; under-reliance forfeits the benefits it was built to deliver. Because trust evolves with every interaction, keeping reliance calibrated is a continuing process, not a one-time design choice. This project examines how reliance develops over time and across situations, toward automation that adapts to the person it serves.