Senior Principal Researcher
Toyota Motor North America, InfoTech Labs
Ph.D., Electrical and Computer Engineering, The University of Texas at Austin
My research is on connected and automated vehicles, where AI methods meet computing systems and vehicular networks. Current work covers multimodal scene understanding and language-guided driving, cooperative driving automation, vehicular edge computing, and mobility digital twins. It grows out of earlier research on low-power signal processing and computing platforms, from my Ph.D. at UT Austin through Intel Labs. I am the author of the forthcoming IEEE-Wiley book Generative AI for Connected and Autonomous Vehicles (2026).
Research
Four areas of current work. With academic and industry collaborators, I evaluate methods in simulation and co-simulation, on testbeds, and with passenger or prototype vehicles in the field.
Language and vision-language models that interpret multi-view driving scenes, carry out driving instructions, and converse with drivers, with benchmarks to evaluate them and methods to run them efficiently.
Representative: NuPlanQA, ICCV 2025 · LaMPilot, CVPR 2024
Contributions and publications →Cooperative maneuvers for connected vehicles, including ramp merging, intersection crossing, and platooning, using vehicle-to-cloud and vehicle-to-vehicle communication and evaluated in co-simulation and with test vehicles.
Representative: Liao et al., IEEE T-ITS 2022 · Wang et al., IEEE T-IV 2022
Contributions and publications →Computation offloading, resource allocation, and data delivery for connected vehicles, including crowdsourced live high-definition maps, real-time cooperative perception at the edge, and information freshness in vehicular networks.
Representative: Zhang et al., IEEE TVT 2024 · AdaMap, ACM/IEEE SEC 2023
Contributions and publications →Digital twins of drivers, vehicles, and traffic on a cloud–edge–device architecture, used to learn personalized driving behavior for driver assistance such as adaptive cruise control, lane-change prediction, and distraction recognition.
Representative: Wang et al., IEEE IoT-J 2022 · Liao et al., IEEE IoT-J 2023
Contributions and publications →Work on computing under energy and compute limits, from fixed-point signal processing and low-power platforms to on-device AI, is collected under Energy- and Resource-Efficient Computing →
Publications
Representative papers from the four areas, including a field study with passenger vehicles, and one earlier paper from the low-power computing work.
IEEE ITSC 2026 Presented
K. Han, Y. Chen, N. Ammar, and O. Altintas
Uses a persistent vigilance state to decide when costly reasoning modules run in a driving system, reducing compute in a synthetic testbench and a highway driving simulator.
IEEE ITSC 2025
K. Han, Y. Chen, R. Gupta, and O. Altintas
Real-time, dialogue-based driver assistance built from language models, vision-to-text scene interpretation, and function calling.
Proc. IEEE 2026
C. Cui, Y. Ma, S. Park, …, K. Han, and Z. Wang
A review and benchmark of large language models for autonomous driving, with experiments on autonomous vehicle platforms using cloud and edge deployment.
ICCV 2025
S. Park, C. Cui, Y. Ma, A. Moradipari, R. Gupta, K. Han, and Z. Wang
A multi-view visual question-answering benchmark and a dataset of one million real-world question-answer pairs for driving scene understanding.
IEEE T-ITS 2022
X. Liao, Z. Wang, X. Zhao, K. Han, P. Tiwari, M. Barth, and G. Wu
Cooperative ramp merging using digital twins over vehicle-to-cloud (4G/LTE) communication, with a field implementation on three passenger vehicles.
IEEE T-IV 2022
Z. Wang, K. Han, and P. Tiwari
Cooperative driving of connected vehicles at non-signalized intersections, assisted by digital twins.
IEEE IoT-J 2022
Z. Wang, R. Gupta, K. Han, H. Wang, A. Ganlath, N. Ammar, and P. Tiwari
Human, vehicle, and traffic digital twins on a cloud–edge–device architecture, demonstrated on personalized adaptive cruise control.
IEEE/ACM ICCAD 2015 Best Paper Award
W. Zuo, W. Kemmerer, J. Lim, L. Pouchet, A. Ayupov, T. Kim, K. Han, and D. Chen
Automated SystemC generation with analytical power and performance models for fast low-power design-space exploration.
Teaching
Course design and research training in generative AI for vehicles, and mentoring of Ph.D. research interns.
An advanced technical curriculum taught as internal research training at Toyota Motor North America's InfoTech Labs. The curriculum informs the IEEE-Wiley textbook Generative AI for Connected and Autonomous Vehicles (forthcoming 2026).
Part I · Spring 2025
15 weeks · participant rating 4.45/5
Language models, retrieval-augmented generation, function calling, fine-tuning, vision-language models, and agents for driving applications, with hands-on labs.
Part II · Spring 2026
11 sessions · participant rating 4.40/5
Diffusion and flow-matching models, VAEs and GANs, video-language models, distillation for edge inference, closed-loop simulation, and evaluation, safety, and trust.
Mentored 14 Ph.D. student research interns from 11 universities (2018–2025).
Earlier teaching includes UNIX Operating System I and II as a lecturer at Woosong University (1999–2000), and teaching assistantships for Senior Design Projects at The University of Texas at Austin (2003–2005) and Circuit and Systems Labs at Seoul National University (1996–1997).
Service
Publication record: 97 journal and conference publications (21 journal, 76 conference); 2 books and 1 book chapter; inventor on 63 granted U.S. patents and 59 U.S. patent applications. Full list →
News
October 2026
Presented at IEEE ITSC 2026: “Tonic Meta-Control for Adaptive Safety-Compute Allocation via Persistent Vigilance Dynamics.” Project page →
October 2026
Call for papers: 2nd International Workshop on AI-native Connected Mobility (ACM’27), held with IEEE CCNC 2027 in Las Vegas. Workshop page →
September 2026
Paper accepted in IEEE Transactions on Mobile Computing: “REAL: A Reinforcement Learning-based Intelligent Offloading Framework for Edge-Assisted MAR.”
August 2026
Paper accepted at EMNLP 2026 (Main Conference): “How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?” View paper →
August 2026
Completed Part II of the internal course Generative AI for Connected and Autonomous Vehicles at Toyota InfoTech Labs, covering diffusion, VideoLLMs, edge distillation, simulation, and AI trust.
May 2026
Camera-ready paper finalized for IEEE ITSC 2026: “Tonic Meta-Control for Adaptive Safety-Compute Allocation via Persistent Vigilance Dynamics.” Project page →
April 2026
Paper published in Proceedings of the IEEE: “LLM4AD: Large Language Models for Autonomous Driving.” View paper →
2026
Companion site for the IEEE-Wiley book Generative AI for Connected and Autonomous Vehicles is now available, with hands-on labs and instructor resources. Book webpage →
2025
Papers at IEEE ITSC 2025 (Scene-Aware Conversational ADAS), ICCV 2025 (NuPlanQA), IEEE/RSJ IROS 2025, and ACM/IEEE SEC 2025 (lm-Meter, PlatformX).
Contact
For research collaborations, workshops, or questions about this work.