Kehua Chen

Kehua Chen

Auto-generated profile, based on publicly available information

Kehua Chen

Department of Civil and Environmental Engineering, University of Washington, Seattle, WA, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MPMingxing Peng
Mingxing Peng
KCKehua Chen
Kehua Chen
XGXusen Guo
Xusen Guo
QZQiming Zhang
Qiming Zhang
HZHui Zhong
Hui Zhong
HYHai Yang
Hai Yang
Intelligent Transportation Systems (ITS) play a crucial role in enhancing traffic efficiency and safety. Recently, diffusion models have emerged as transformative tools for addressing the complex challenges faced within ITS, including traffic uncertainty, data multimodality, and data imperfections. This paper presents a comprehensive survey of diffusion models in ITS, exploring both theoretical and practical dimensions. We begin by introducing the theoretical foundations of diffusion models and their key variants, such as conditional and latent diffusion models, highlighting their probabilistic modeling nature, capacity to model complex multimodal traffic data, and support for controllable generation. Next, we analyze the major challenges in ITS and explain how diffusion models offer robust, flexible, and controllable solutions, thereby elucidating their unique advantages in this domain. We then conduct a multi-perspective examination of current applications of diffusion models across ITS domains, including autonomous driving, traffic simulation, traffic forecasting, and traffic safety. Finally, we discuss state-of-the-art diffusion model techniques and highlight key research directions within ITS that merit further exploration. Through this structured overview, we aim to equip researchers with a comprehensive understanding of diffusion models in ITS, thereby fostering their future applications in the transportation domain. An open-source repository accompanying this survey is available at: https://github.com/Pemixing/Diffusion-Models-in-ITS-A-Survey

9 April 2024 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
KCKehua Chen
Kehua Chen
YLYuxuan Liang
Yuxuan Liang
JHJindong Han
Jindong Han
SFSiyuan Feng
Siyuan Feng
MZMeixin Zhu
Meixin Zhu
HYHai Yang
Hai Yang

3 October 2024 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
XCXianda Chen
Xianda Chen
KCKehua Chen
Kehua Chen
MZMeixin Zhu
Meixin Zhu
HYHao (Frank) Yang
Hao (Frank) Yang
SSShaojie Shen
Shaojie Shen
Yinhai WangYinhai Wang
Yinhai Wang

1 February 2020 in Chemical Engineering Journal
Verified
Journal Article
Closed access
EOEdward O’dWyer
Edward O’dWyer
KCKehua Chen
Kehua Chen
HWHongcheng Wang
Hongcheng Wang
AWAijie Wang
Aijie Wang
NSNilay Shah
Nilay Shah
Miao GuoMiao Guo
Miao Guo

15 November 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZYZihan Yu
Zihan Yu
MZMeixin Zhu
Meixin Zhu
KCKehua Chen
Kehua Chen
XCXiaowen Chu
Xiaowen Chu
XWXuesong Wang
Xuesong Wang
Learning-based approaches hold great potential for autonomous urban driving motion planning. Compared to traditional rule-based methods, they offer greater flexibility in planning safe and human-like trajectories based on human driver demonstration data and diverse traffic scenarios. Frenet planning is widely applied in autonomous driving motion planning due to itssimplerepresentationofself-drivingvehicleinformation.However,it is challenging to select proper terminal statesand generate human-like trajectories. To address this issue, we propose a learning-based Frenet planning network (LF-Net) that learns a policy to sample and select the most human-like terminal states and then generate safe trajectories. The LF-Net includes 1) a Transformer-based sub-network that encodes environmental and vehicle interaction features, 2) a classification and scoring subnetwork based on cross-attention mechanisms that captures the relationship between potential terminal states and environmental features to generate the optimal terminal states set, and 3) a trajectory generator based on LQR that fits a trajectory between the selected terminal state and the initial state. Experimental results on the real-world large-scale Lyft dataset demonstrate that the proposed method can plan safe and human-like driving behavior, and performs better than baseline methods.

31 December 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
KCKehua Chen
Kehua Chen
YLYuhao Luo
Yuhao Luo
MZMeixin Zhu
Meixin Zhu
HYHai Yang
Hai Yang
Lane changing presents a dynamic scenario characterized by intricate interactions among vehicles. Within mixed-autonomy traffic environment, modeling a human-like lane-change trajectory enables human drivers to better understand and predict autonomous vehicles’ behaviors, thereby enhancing road safety and travel efficiency. In this study, we achieve human-like interactive lane-change modeling based on a novel framework named Diff-LC . The human-like modeling of LCV behaviors relies on an advanced diffusive planner, and the implemented trajectory is selected based on the recovered LCV reward function learned through Multi-Agent Adversarial Inverse Reinforcement Learning (MA-AIRL). To account for interactions between FVs and LCVs, we further employ a diffusive predictor to forecast future behaviors of FVs conditioned on both historical and planned trajectories. Additionally, we leverage the recovered reward function of FVs to enable controllable prediction of trajectories. In the experimental part, we begin by analyzing the significance of features in the recovered reward functions and then proceed to compare the distinctions between the LCV and the FV. To validate the effectiveness of the proposed framework, we compare the diffusive predictor and planner with several state-of-the-art methods. The results demonstrate that motions planned by Diff-LC closely reach the intended positions with small displacement errors and exhibit highly similar speed and jerk distributions to those of human drivers. We also conduct a dynamic simulation to evaluate Diff-LC’s performance across different traffic conditions. Finally, we explore customized generation using the Diffusion Posterior Sampling method. The codes can be found at https://github.com/zeonchen/Diff-LC/.