Publications

2026

1. 

   Optimizing Autonomous Driving Datasets for Detection with Smaller Data Sizes and Equivalent Effectiveness

   Zexuan Jia*, and Gongjin Lan*

   IEEE Transactions on Emerging Topics in Computational Intelligence, 2026

   Accepted

   Abs Bib Code

   Autonomous driving significantly benefits from data-driven deep neural networks that require large-scale and high-quality datasets for training. Several well-known datasets such as nuScenes, CADC, and SUSCape have been applied to train deep models for autonomous driving. However, these datasets generally have many redundant and low-quality frames that take extra training time and affect the performance of the trained models. In this work, we propose a novel three-layer method by considering scene complexity, instance quality, and sensing uncertainty to remove redundant data and maintain valuable data for optimizing autonomous driving datasets with smaller data sizes and equivalent effectiveness. We apply the method to optimize four well-known datasets nuScenes, CADC, SUSCape, and Carla-4Scenes. Furthermore, we retrain the well-known perception algorithms on these optimized datasets. The experimental results show that these retrained perception algorithms on the optimized datasets perform equivalent even better accuracy with less training time. We conclude that our three-layer method successfully optimizes autonomous driving datasets with smaller sizes and equivalent effectiveness, which contributes to faster training with lower hardware requirements.

   @article{jia2026optimizing,
     title = {Optimizing Autonomous Driving Datasets for Detection with Smaller Data Sizes and Equivalent Effectiveness},
     author = {Jia*, Zexuan and Lan*, Gongjin},
     journal = {IEEE Transactions on Emerging Topics in Computational Intelligence},
     note = {Accepted},
     year = {2026},
   }

2. 

   Joint Prediction of Virtual Leader from Future Occupancy and Queueing Theory in Automated Vehicles

   Zexuan Jia, and Yunli Shao

   In IEEE Modeling, Estimation and Control Conference (MECC), 2026

   Accepted. A preview version appeared at the American Control Conference (ACC)

   Abs Bib HTML

   Long-horizon traffic prediction is critical for automated vehicles control near intersections and queue-forming road segments, enabling energy-efficient and congestion-aware planning. This work proposes a control-oriented representation of future longitudinal motion constraints as a virtual leader acting on the ego vehicle, and develops a hybrid framework for virtual-leader prediction. In the short term, a deep learning model predicts future occupancy and flow, from which a most likely collision-free virtual leader constraint is inferred. In the long term, a queueing-theory-based model extends this constraint based on the traffic stage estimated from the short-term prediction. On the Waymo Motion Dataset, the short-term predictor achieves an area under the curve (AUC) of 0.755 for occupancy prediction and an endpoint error (EPE) of 5.862 for flow prediction, using 4s of historical data and a 5s prediction horizon. For full-horizon virtual leader prediction, the proposed framework reduces the average displacement error (ADE) and final displacement error (FDE) by 18.7% and 38.4%, respectively, compared with a queueing-theory-only baseline. These results support the proposed approach as a promising framework for control-oriented virtual-leader-based motion constraint representation in complex traffic environments.

   @inproceedings{jia2026joint,
     title = {Joint Prediction of Virtual Leader from Future Occupancy and Queueing Theory in Automated Vehicles},
     author = {Jia, Zexuan and Shao, Yunli},
     booktitle = {IEEE Modeling, Estimation and Control Conference (MECC)},
     note = {Accepted. A preview version appeared at the American Control Conference (ACC)},
     year = {2026},
   }

2025

1. 

   LLM-based and Game-Theoretic Traffic Trajectory Generation for Autonomous Driving

   Zexuan Jia, and Huayu Xu

   In IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI), 2025

   Abs Bib HTML

   Autonomous driving significantly benefits from data-driven deep neural networks that require large-scale and high-quality datasets for training. To achieve higher performance or conduct critical testing, trajectories with game-theoretic properties are necessary. However, defining such scenarios and collecting large-scale data from reality or simulation is hard and costly. In this work, we propose a novel two-step method that generates traffic trajectories with game-theoretic properties, based on the Large Language Model (LLM). We apply the method to generate a challenging traffic trajectory dataset, which is validated on many downstream tasks, including perception and prediction. The experimental results show that the generated trajectories can achieve high-difficulty testing and advanced training. We conclude that our method successfully generates the challenging traffic trajectories, which contribute to collecting such critical data.

   @inproceedings{jia2025llmbased,
     title = {LLM-based and Game-Theoretic Traffic Trajectory Generation for Autonomous Driving},
     author = {Jia, Zexuan and Xu, Huayu},
     booktitle = {IEEE International Conference on Computer Communication and Artificial Intelligence (CCAI)},
     year = {2025},
   }

2023

1. 

   Active Data Acquisition in Autonomous Driving Simulation

   Jianyu Lai, Zexuan Jia, and Boao Li

   In Course Work, 2023

   Abs Bib HTML

   Autonomous driving algorithms rely heavily on learning-based models, which require large datasets for training. However, there is often a large amount of redundant information in these datasets, while collecting and processing these datasets can be time-consuming and expensive. To address this issue, this paper proposes the concept of an active data-collecting strategy. For high-quality data, increasing the collection density can improve the overall quality of the dataset, ultimately achieving similar or even better results than the original dataset with lower labeling costs and smaller dataset sizes. In this paper, we design experiments to verify the quality of the collected dataset and to demonstrate this strategy can significantly reduce labeling costs and dataset size while improving the overall quality of the dataset, leading to better performance of autonomous driving systems.

   @inproceedings{lai2023active,
     title = {Active Data Acquisition in Autonomous Driving Simulation},
     author = {Lai, Jianyu and Jia, Zexuan and Li, Boao},
     booktitle = {Course Work},
     year = {2023},
   }