XLXishun Liao

Xishun Liao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xishun Liao has a total of 66 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PopTraj: Hierarchical Multi-Source Generation of Household-Coordinated Weekly Activity--Location Trajectories with Urban Populations Synthesis

    by Haoxuan Ma, Yifan Liu, Bo Yang, Yiwen Zhang, Chris Stanford, Eli Fox, Xishun Liao, Jiaqi Ma

    Synthetic human mobility trajectories support urban planning, transportation simulation, and epidemic analysis by representing when, where, and how people conduct activities. However, existing approaches often model individuals independently or over single days, limiting joint representation of overnight activity, demographic heterogeneity, household interactions, and multiday regularities. The required evidence is fragmented across census, survey, geographic, and anonymous GPS data that cannot be linked at the individual level. We present PopTraj, a hierarchical multi-source generation framework for producing household-coordinated weekly activity-location trajectories for synthetic urban populations. PopTraj organizes generation into three source-aligned levels. A sample-free synthesizer reconstructs a household population from aggregate census constraints. A survey-calibrated language model produces a coordinated-schedule teacher corpus, which is distilled into a Hybrid 3D conditional variational autoencoder for scalable generation. Finally, HEARTH completes each dictated week as home-anchored excursions, using a vector-quantized persona latent to connect GPS-learned behavioral archetypes with a survey-derived demographic prior. In a metropolitan-scale Tokyo deployment, PopTraj generates 395K synthetic person-weeks. HEARTH achieves a mean divergence of 0.0252 across six realism metrics, compared with 0.0412 for the strongest of nine baselines. The deployed schedule pipeline reduces household coordination error by more than 16-fold relative to six learned baselines, while the persona prior halves demographic divergence with little change in aggregate realism. Source-removal, architecture, and error-propagation analyses show that the persona prior supplies demographic separation and the household schedule supplies cross-level coordination. PopTraj therefore provides a scalable route from unlinked population statistics and anonymous mobility data to simulation-ready human mobility trajectories.

  • Deep Activity Model: A Generative Deep Learning Approach for Human Mobility Pattern Synthesis

    by Xishun Liao, Qinhua Jiang, Brian Yueshuai He, Yifan Liu, Chenchen Kuai, Jiaqi Ma

    Human mobility plays a crucial role in transportation, urban planning, and public health, but current approaches face important limitations. Existing deep learning models tend to overlook the semantic interdependencies among activities and households and rely on restricted GPS data, while activity-based models depend on rigid assumptions and extensive data, making them costly and difficult to adapt to new regions, especially those with limited conventional travel data. We propose a generative Transformer model that uses socio-demographic and household attributes to synthesize daily activity chains, with a location module assigning spatial zones to produce complete daily trajectories. To address these limitations, we propose a generative Transformer model that uses socio-demographic and household attributes to synthesize daily activity chains, with a location module assigning spatial zones to produce complete daily trajectories. Trained on open-source and widely available household travel survey data and then fine-tuned with local data, the model captures national activity patterns and transfers effectively to California, Washington, and Mexico City. This approach offers significant potential for advancing synthetic human mobility modeling and provides urban planners and policymakers with improved tools for simulating transportation systems and supporting decisions in urban development and public health. Its practical utility is demonstrated through large-scale traffic simulations in Los Angeles County. Compared to the SCAG Activity-Based Model (ABM), the proposed method produces consistent spatial demand patterns, achieving an activity location cosine similarity of 0.997 and a network-level vehicle-miles-traveled Mean Absolute Percentage Error (MAPE) of 4.97%. Compared to real-world observations from Caltrans PeMS, the simulated traffic achieves MAPE of 5.85% for traffic volume and 4.36% for speed on California’s I-405 corridor. This demonstrates the practicality of learning-based synthetic mobility for regional simulation and planning.


  • Top Cited Papers

    A Review of Personalization in Driving Behavior: Dataset, Modeling, and Validation

    by Xishun Liao, Zhouqiao Zhao, Matthew J. Barth, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Jiaqi Ma, Guoyuan Wu

    Personalization in driving behavior research is crucial for developing intelligent vehicles that can safely coexist with human-driven vehicles in mixed-traffic environments. By accounting for the diversity of human driving behaviors, personalized modeling can improve predictive capabilities of intelligent vehicles and foster a more balanced traffic ecosystem. This paper presents a systematic review on personalization in driving behavior, evaluating their potential to enhance road safety, transportation efficiency, and human-centric mobility. It proposes a taxonomy to categorize personalized driving behaviors and surveys relevant datasets, modeling methodologies, and techniques for validating personalized driver models. Focusing on personalized driving behavior, the study emphasizes the need for intelligent vehicles to adapt to the complex and heterogeneous behaviors exhibited by human drivers to enhance predictability, responsiveness, and ultimately create a safe and efficient traffic environment. Lastly, key challenges are identified, along with promising future research directions to advance personalized driving behavior research.


  • Open Access

    NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks

    by Chris Stanford, Suman Adari, Xishun Liao, Yueshuai He, Qinhua Jiang, Chenchen Kuai, Jiaqi Ma, Emmanuel Tung, Yinlong Qian, Lingyi Zhao, et al.


  • Mobility AI Agents and Networks

    by Haoxuan Ma, Yifan Liu, Qinhua Jiang, Brian Yueshuai He, Xishun Liao, Jiaqi Ma

    Intelligent vehicles and smart mobility systems are at the forefront of transportation evolution, yet effective management of these new mobility technologies and services are non-trivial. This perspective proposes an Intelligent Mobility System Digital Twin (MSDT) framework as a solution. Our framework uniquely maps human beings and vehicles to AI agents and the mobility systems to AI networks, creating realistic digital simulacra of the physical mobility system. By integrating AI agents and networks, this framework offers unprecedented capabilities in prediction and automated simulation of the entire mobility systems, thereby improving planning, operations, and decision-making in smart cities


  • Game Theoretic Application to Intersection Management: A Literature Review

    by Ziye Qin, Ang Ji, Zhanbo Sun, Guoyuan Wu, Peng Hao, Xishun Liao

    The emergence of vehicle-to-everything (V2X) technology offers new insights into intersection management. This, however, has also presented new challenges, such as the need to understand and model the interactions of traffic participants, including their competition and cooperation behaviors. Game theory has been widely adopted to study rationally selfish or cooperative behaviors during interactions and has been applied to advanced intersection management. In this paper, we review the application of game theory to intersection management and sort out relevant studies under various levels of intelligence and connectivity. First, the problem of urban intersection management and its challenges are briefly introduced. The basic elements of game theory specifically for intersection applications are then summarized. Next, we present the game-theoretic models and solutions that have been applied to intersection management. Finally, the limitations and potential opportunities for subsequent studies within the game-theoretic application to intersection management are discussed.


  • Top Cited Papers

    Foundation Intelligence for Smart Infrastructure Services in Transportation 5.0

    by Xu Han, Zonglin Meng, Xin Xia, Xishun Liao, Brian Yueshuai He, Zhaoliang Zheng, Yutong Wang, Hao Xiang, Zewei Zhou, Letian Gao, et al.

    This perspective paper delves into the concept of foundation intelligence that shapes the future of smart infrastructure services as the transportation sector transitions into the era of Transportation 5.0. First, the discussion focuses on a suite of emerging technologies essential for foundation intelligence. These technologies encompass digital twinning, parallel intelligence, large vision-language models, traffic simulation and transportation systems modeling, vehicle-to-everything (V2X) connectivity, and decentralized/distributed systems. Next, the paper introduces the present landscape of Transportation 5.0 applications as illuminated by the foundational intelligence, and casts a vision towards the future including cooperative driving automation, smart intersection/infrastructure, parallel traffic management, virtual drivers, and mobility systems planning and operations, laying out prospects that are poised to redefine the mobility ecosystem. Last, through a comprehensive outlook, this paper aspires to offer a guiding framework for the intelligent evolution in data generation and model calibration, digital twinning and simulation, scenario development and experimentation, feedback loop for management and control, and continuous learning and adaptation, fostering safety, efficiency, reliability, and sustainability in the future smart transportation infrastructure.


  • Open Access

    Real-time Learning of Driving Gap Preference for Personalized Adaptive Cruise Control

    by Zhouqiao Zhao, Xishun Liao, Amr Abdelraouf, Kyungtae Han, Rohit Gupta, Matthew J. Barth, Guoyuan Wu

    Advanced Driver Assistance Systems (ADAS) are increasingly important in improving driving safety and comfort, with Adaptive Cruise Control (ACC) being one of the most widely used. However, pre-defined ACC settings may not always align with driver's preferences and habits, leading to discomfort and potential safety issues. Personalized ACC (P-ACC) has been proposed to address this problem, but most existing research uses historical driving data to imitate behaviors that conform to driver preferences, neglecting real-time driver feedback. To bridge this gap, we propose a cloud-vehicle collaborative P-ACC framework that incorporates driver feedback adaptation in real time. The framework is divided into offline and online parts. The offline component records the driver's naturalistic car-following trajectory and uses inverse reinforcement learning (IRL) to train the model on the cloud. In the online component, driver feedback is used to update the driving gap preference in real time. The model is then retrained on the cloud with driver's takeover trajectories, achieving incremental learning to better match driver's preference. Human-in-the-loop (HuiL) simulation experiments demonstrate that our proposed method significantly reduces driver intervention in automatic control systems by up to 62.8%. By incorporating real-time driver feedback, our approach enhances the comfort and safety of P-ACC, providing a personalized and adaptable driving experience.

  • Top Cited Papers

    Driver Digital Twin for Online Prediction of Personalized Lane-Change Behavior

    by Xishun Liao, Xuanpeng Zhao, Ziran Wang, Zhouqiao Zhao, Kyungtae Han, Rohit Gupta, Matthew J. Barth, Guoyuan Wu

    Connected and automated vehicles (CAVs) are supposed to share the road with human-driven vehicles (HDVs) in a foreseeable future. Therefore, considering the mixed traffic environment is more pragmatic, as the well-planned operation of CAVs may be interrupted by HDVs. In the circumstance that human behaviors have significant impacts, CAVs need to understand HDV behaviors to make safe actions. In this study, we develop a Driver Digital Twin (DDT) for the online prediction of personalized lane change behavior, allowing CAVs to predict surrounding vehicles’ behaviors with the help of the digital twin technology. DDT is deployed on a vehicle-edge-cloud architecture, where the cloud server models the driver behavior for each HDV based on the historical naturalistic driving data, while the edge server processes the real-time data from each driver with his/her digital twin on the cloud to predict the personalized lane change maneuver. The proposed system is first evaluated on a human-in-the-loop co-simulation platform, and then in a field implementation with three passenger vehicles driving along an on/off ramp segment connecting to the edge server and cloud through the 4G/LTE cellular network. The lane change intention can be recognized in 6 seconds on average before the vehicle crosses the lane separation line, and the Mean Euclidean Distance between the predicted trajectory and GPS ground truth is 1.03 meters within a 4-second prediction window. Compared to the general model, using a personalized model can improve prediction accuracy by 27.8%. The demonstration video of the proposed system can be watched at https://youtu.be/5cbsabgIOdM.