Seongjin Choi

Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun

This paper proposes a dynamic regression (DR) framework that enhances existing deep spatiotemporal models by incorporating structured learning for the error process in traffic forecasting. The framework relaxes the assumption of time independence by modeling the error series of the base model (i.e., a well-established traffic forecasting model) using a matrix-variate autoregressive (AR) model. The AR model is integrated into training by redesigning the loss function. The newly designed loss function is based on the likelihood of a non-isotropic error term, enabling the model to generate probabilistic forecasts while preserving the original outputs of the base model. Importantly, the additional parameters introduced by the DR framework can be jointly optimized alongside the base model. Evaluation on state-of-the-art (SOTA) traffic forecasting models using speed and flow datasets demonstrates improved performance, with interpretable AR coefficients and spatiotemporal covariance matrices enhancing the understanding of the model.

Seongjin Choi, Nicolas Saunier, Vincent Zhihao Zheng et al.

Deep learning-based multivariate and multistep-ahead traffic forecasting models are typically trained with the mean squared error (MSE) or mean absolute error (MAE) as the loss function in a sequence-to-sequence setting, simply assuming that the errors follow an independent and isotropic Gaussian or Laplacian distributions. However, such assumptions are often unrealistic for real-world traffic forecasting tasks, where the probabilistic distribution of spatiotemporal forecasting is very complex with strong concurrent correlations across both sensors and forecasting horizons in a time-varying manner. In this paper, we model the time-varying distribution for the matrix-variate error process as a dynamic mixture of zero-mean Gaussian distributions. To achieve efficiency, flexibility, and scalability, we parameterize each mixture component using a matrix normal distribution and allow the mixture weight to change and be predictable over time. The proposed method can be seamlessly integrated into existing deep-learning frameworks with only a few additional parameters to be learned. We evaluate the performance of the proposed method on a traffic speed forecasting task and find that our method not only improves model performance but also provides interpretable spatiotemporal correlation structures.

Pouya Parsa, Kawon Han, Seongjin Choi

Frontier autonomous-driving models -- especially vision-language-action (VLA) models, whose forward pass approaches $\sim$60~TFLOPs -- are outgrowing economical onboard deployment, since peak hardware sits idle most of the day. Cloud inference can instead share GPUs across active vehicles, but the vehicle must upload through a capacity-limited uplink, reach a GPU without queueing, and return a decision within the closed-loop budget. This paper asks: can the cloud drive? We answer with an analytical framework coupling communication limits, a roofline GPU service model, stochastic latency, and utilization-aware cost across three model classes, three offloading strategies, and three communication generations, applied to New York City. Separating a reactive 100~ms budget from a 300~ms deliberative tier (presuming an onboard reactive fallback), we find three \emph{nested} binding regimes. Communication binds first in dense cells: 5G fails early, 5G-Advanced is the practical threshold for feature-level offloading, and 6G adds headroom. Compute binds next under the reactive budget: near-term VLA is latency-infeasible regardless of bandwidth, because autoregressive FP16 decode is memory-bandwidth-bound (~114 ms on 2025 hardware). Its floor clears 100 ms around 2027; 6G then admits feature-level VLA by ~2028, 5G-Advanced only at light loading and not the dense corridor, and the deliberative tier from 2026. Cost binds last: once admissible, utilization-pooled cloud GPUs undercut onboard hardware for VLA, whose baseline (up to \$8,500 per vehicle-year) is expensive and idle; feature-level offloading (S2) is where the VLA cost crossover concentrates. Latency decides which model is admissible in which year; cost decides whether it is economical.

Sicong Jiang, Zilin Huang, Kangan Qian et al.

The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.

Fuqiang Liu, Sicong Jiang, Luis Miranda-Moreno et al.

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world applications remain under-explored, particularly concerning their susceptibility to adversarial attacks. In this paper, we introduce a targeted adversarial attack framework for LLM-based time series forecasting. By employing both gradient-free and black-box optimization methods, we generate minimal yet highly effective perturbations that significantly degrade the forecasting accuracy across multiple datasets and LLM architectures. Our experiments, which include models like LLMTime with GPT-3.5, GPT-4, LLaMa, and Mistral, TimeGPT, and TimeLLM show that adversarial attacks lead to much more severe performance degradation than random noise, and demonstrate the broad effectiveness of our attacks across different LLMs. The results underscore the critical vulnerabilities of LLMs in time series forecasting, highlighting the need for robust defense mechanisms to ensure their reliable deployment in practical applications. The code repository can be found at https://github.com/JohnsonJiang1996/AdvAttack_LLM4TS.

Sicong Jiang, Seongjin Choi, Lijun Sun

Cooperative Adaptive Cruise Control (CACC) plays a pivotal role in enhancing traffic efficiency and safety in Connected and Autonomous Vehicles (CAVs). Reinforcement Learning (RL) has proven effective in optimizing complex decision-making processes in CACC, leading to improved system performance and adaptability. Among RL approaches, Multi-Agent Reinforcement Learning (MARL) has shown remarkable potential by enabling coordinated actions among multiple CAVs through Centralized Training with Decentralized Execution (CTDE). However, MARL often faces scalability issues, particularly when CACC vehicles suddenly join or leave the platoon, resulting in performance degradation. To address these challenges, we propose Communication-Aware Reinforcement Learning (CA-RL). CA-RL includes a communication-aware module that extracts and compresses vehicle communication information through forward and backward information transmission modules. This enables efficient cyclic information propagation within the CACC traffic flow, ensuring policy consistency and mitigating the scalability problems of MARL in CACC. Experimental results demonstrate that CA-RL significantly outperforms baseline methods in various traffic scenarios, achieving superior scalability, robustness, and overall system performance while maintaining reliable performance despite changes in the number of participating vehicles.

Seunghee Ryu, Donghoon Kwon, Seongjin Choi et al.

We introduce \textbf{BO4Mob}, a new benchmark framework for high-dimensional Bayesian Optimization (BO), driven by the challenge of origin-destination (OD) travel demand estimation in large urban road networks. Estimating OD travel demand from limited traffic sensor data is a difficult inverse optimization problem, particularly in real-world, large-scale transportation networks. This problem involves optimizing over high-dimensional continuous spaces where each objective evaluation is computationally expensive, stochastic, and non-differentiable. BO4Mob comprises five scenarios based on real-world San Jose, CA road networks, with input dimensions scaling up to 10,100. These scenarios utilize high-resolution, open-source traffic simulations that incorporate realistic nonlinear and stochastic dynamics. We demonstrate the benchmark's utility by evaluating five optimization methods: three state-of-the-art BO algorithms and two non-BO baselines. This benchmark is designed to support both the development of scalable optimization algorithms and their application for the design of data-driven urban mobility models, including high-resolution digital twins of metropolitan road networks. Code and documentation are available at https://github.com/UMN-Choi-Lab/BO4Mob.

Mitch Kosieradzki, Seongjin Choi

For intelligent transportation systems and autonomous vehicles to operate safely and efficiently, they must reliably predict the future motion and trajectory of surrounding agents within complex traffic environments. At the same time, the motion of these agents is inherently uncertain, making accurate prediction difficult. In this paper, we propose \textbf{TrajFlow}, a generative framework for estimating the occupancy density of dynamic agents. Our framework utilizes a causal encoder to extract semantically meaningful embeddings of the observed trajectory, as well as a normalizing flow to decode these embeddings and determine the most likely future location of an agent at some time point in the future. Our formulation differs from existing approaches because we model the marginal distribution of spatial locations instead of the joint distribution of unobserved trajectories. The advantages of a marginal formulation are numerous. First, we demonstrate that the marginal formulation produces higher accuracy on challenging trajectory forecasting benchmarks. Second, the marginal formulation allows for fully continuous sampling of future locations. Finally, marginal densities are better suited for downstream tasks as they allow for the computation of per-agent motion trajectories and occupancy grids, the two most commonly used representations for motion forecasting. We present a novel architecture based entirely on neural differential equations as an implementation of this framework and provide ablations to demonstrate the advantages of a continuous implementation over a more traditional discrete neural network based approach. The code is available at https://github.com/UMN-Choi-Lab/TrajFlow.

Donggyu Min, Seongjin Choi, Dong-Kyu Kim

This paper focuses on dynamic origin-destination matrix estimation (DODE), a crucial calibration process necessary for the effective application of microscopic traffic simulations. The fundamental challenge of the DODE problem in microscopic simulations stems from the complex temporal dynamics and inherent uncertainty of individual vehicle dynamics. This makes it highly challenging to precisely determine which vehicle traverses which link at any given moment, resulting in intricate and often ambiguous relationships between origin-destination (OD) matrices and their contributions to resultant link flows. This phenomenon constitutes the credit assignment problem, a central challenge addressed in this study. We formulate the DODE problem as a Markov Decision Process (MDP) and propose a novel framework that applies model-free deep reinforcement learning (DRL). Within our proposed framework, the agent learns an optimal policy to sequentially generate OD matrices, refining its strategy through direct interaction with the simulation environment. The proposed method is validated on the Nguyen-Dupuis network using SUMO, where its performance is evaluated against ground-truth link flows aggregated at 5-minute intervals over a 30-minute horizon. Experimental results demonstrate that our approach achieves a 43.2% reduction in mean squared error (MSE) compared to the best-performing conventional baseline. By reframing DODE as a sequential decision-making problem, our approach addresses the credit assignment challenge through its learned policy, thereby overcoming the limitations of conventional methods and proposing a novel framework for calibration of microscopic traffic simulations.

Tengfeng Lin, Zhixiong Jin, Seongjin Choi et al.

Addressing pedestrian safety at intersections is one of the paramount concerns in the field of transportation research, driven by the urgency of reducing traffic-related injuries and fatalities. With advances in computer vision technologies and predictive models, the pursuit of developing real-time proactive protection systems is increasingly recognized as vital to improving pedestrian safety at intersections. The core of these protection systems lies in the prediction-based evaluation of pedestrian's potential risks, which plays a significant role in preventing the occurrence of accidents. The major challenges in the current prediction-based potential risk evaluation research can be summarized into three aspects: the inadequate progress in creating a real-time framework for the evaluation of pedestrian's potential risks, the absence of accurate and explainable safety indicators that can represent the potential risk, and the lack of tailor-made evaluation criteria specifically for each category of pedestrians. To address these research challenges, in this study, a framework with computer vision technologies and predictive models is developed to evaluate the potential risk of pedestrians in real time. Integral to this framework is a novel surrogate safety measure, the Predicted Post-Encroachment Time (P-PET), derived from deep learning models capable to predict the arrival time of pedestrians and vehicles at intersections. To further improve the effectiveness and reliability of pedestrian risk evaluation, we classify pedestrians into distinct categories and apply specific evaluation criteria for each group. The results demonstrate the framework's ability to effectively identify potential risks through the use of P-PET, indicating its feasibility for real-time applications and its improved performance in risk evaluation across different categories of pedestrians.

Pouya Parsa, Keya Li, Kara M. Kockelman et al.

Automatic license plate recognition (ALPR) and vehicle make and model recognition underpin intelligent transportation systems, supporting law enforcement, toll collection, and post-incident investigation. Applying these methods to videos captured by handheld smartphones or non-static vehicle-mounted cameras presents unique challenges compared to fixed installations, including frequent camera motion, varying viewpoints, occlusions, and unknown road geometry. Traditional ALPR solutions, dependent on specialized hardware and handcrafted OCR pipelines, often degrade under these conditions. Recent advances in large vision-language models (VLMs) enable direct recognition of textual and semantic attributes from arbitrary imagery. This study evaluates the potential of VLMs for ALPR and makes and models recognition using monocular videos captured with handheld smartphones and non-static mounted cameras. The proposed license plate recognition pipeline filters to sharp frames, then sends a multimodal prompt to a VLM using several prompt strategies. Make and model recognition pipeline runs the same VLM with a revised prompt and an optional self-reflection module. In the self-reflection module, the model contrasts the query image with a reference from a 134-class dataset, correcting mismatches. Experiments on a smartphone dataset collected on the campus of the University of Texas at Austin, achieve top-1 accuracies of 91.67% for ALPR and 66.67% for make and model recognition. On the public UFPR-ALPR dataset, the approach attains 83.05% and 61.07%, respectively. The self-reflection module further improves results by 5.72% on average for make and model recognition. These findings demonstrate that VLMs provide a cost-effective solution for scalable, in-motion traffic video analysis.

Jungwoo Cho, Seongjin Choi

Integrating Urban Air Mobility (UAM) into airspace managed by Air Traffic Control (ATC) poses significant challenges, particularly in congested terminal environments. This study proposes a framework to assess the feasibility of UAM route integration using probabilistic aircraft trajectory prediction. By leveraging conditional Normalizing Flows, the framework predicts short-term trajectory distributions of conventional aircraft, enabling UAM vehicles to dynamically adjust speeds and maintain safe separations. The methodology was applied to airspace over Seoul metropolitan area, encompassing interactions between UAM and conventional traffic at multiple altitudes and lanes. The results reveal that different physical locations of lanes and routes experience varying interaction patterns and encounter dynamics. For instance, Lane 1 at lower altitudes (1,500 ft and 2,000 ft) exhibited minimal interactions with conventional aircraft, resulting in the largest separations and the most stable delay proportions. In contrast, Lane 4 near the airport experienced more frequent and complex interactions due to its proximity to departing traffic. The limited trajectory data for departing aircraft in this region occasionally led to tighter separations and increased operational challenges. This study underscores the potential of predictive modeling in facilitating UAM integration while highlighting critical trade-offs between safety and efficiency. The findings contribute to refining airspace management strategies and offer insights for scaling UAM operations in complex urban environments.

Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun

Deep probabilistic time series forecasting has gained attention for its ability to provide nonlinear approximation and valuable uncertainty quantification for decision-making. However, existing models often oversimplify the problem by assuming a time-independent error process and overlooking serial correlation. To overcome this limitation, we propose an innovative training method that incorporates error autocorrelation to enhance probabilistic forecasting accuracy. Our method constructs a mini-batch as a collection of $D$ consecutive time series segments for model training. It explicitly learns a time-varying covariance matrix over each mini-batch, encoding error correlation among adjacent time steps. The learned covariance matrix can be used to improve prediction accuracy and enhance uncertainty quantification. We evaluate our method on two different neural forecasting models and multiple public datasets. Experimental results confirm the effectiveness of the proposed approach in improving the performance of both models across a range of datasets, resulting in notable improvements in predictive accuracy.

Tengfeng Lin, Zhixiong Jin, Seongjin Choi et al.

The mortality rate for pedestrians using wheelchairs was 36% higher than the overall population pedestrian mortality rate. However, there is no data to clarify the pedestrians' categories in both fatal and nonfatal accidents, since police reports often do not keep a record of whether a victim was using a wheelchair or has a disability. Currently, real-time detection of vulnerable road users using advanced traffic sensors installed at the infrastructure side has a great potential to significantly improve traffic safety at the intersection. In this research, we develop a systematic framework with a combination of machine learning and deep learning models to distinguish disabled people from normal walk pedestrians and predict the time needed to reach the next side of the intersection. The proposed framework shows high performance both at vulnerable user classification and arrival time prediction accuracy.

Seongjin Choi

A `trajectory' refers to a trace generated by a moving object in geographical spaces, usually represented by of a series of chronologically ordered points, where each point consists of a geo-spatial coordinate set and a timestamp. Rapid advancements in location sensing and wireless communication technology enabled us to collect and store a massive amount of trajectory data. As a result, many researchers use trajectory data to analyze mobility of various moving objects. In this dissertation, we focus on the `urban vehicle trajectory,' which refers to trajectories of vehicles in urban traffic networks, and we focus on `urban vehicle trajectory analytics.' The urban vehicle trajectory analytics offers unprecedented opportunities to understand vehicle movement patterns in urban traffic networks including both user-centric travel experiences and system-wide spatiotemporal patterns. The spatiotemporal features of urban vehicle trajectory data are structurally correlated with each other, and consequently, many previous researchers used various methods to understand this structure. Especially, deep-learning models are getting attentions of many researchers due to its powerful function approximation and feature representation abilities. As a result, the objective of this dissertation is to develop deep-learning based models for urban vehicle trajectory analytics to better understand the mobility patterns of urban traffic networks. Particularly, this dissertation focuses on two research topics, which has high necessity, importance and applicability: Next Location Prediction, and Synthetic Trajectory Generation. In this study, we propose various novel models for urban vehicle trajectory analytics using deep learning.

Seongjin Choi, Jiwon Kim, Hwasoo Yeo

Recently, an abundant amount of urban vehicle trajectory data has been collected in road networks. Many studies have used machine learning algorithms to analyze patterns in vehicle trajectories to predict location sequences of individual travelers. Unlike the previous studies that used a discriminative modeling approach, this research suggests a generative modeling approach to learn the underlying distributions of urban vehicle trajectory data. A generative model for urban vehicle trajectories can better generalize from training data by learning the underlying distribution of the training data and, thus, produce synthetic vehicle trajectories similar to real vehicle trajectories with limited observations. Synthetic trajectories can provide solutions to data sparsity or data privacy issues in using location data. This research proposesTrajGAIL, a generative adversarial imitation learning framework for the urban vehicle trajectory generation. In TrajGAIL, learning location sequences in observed trajectories is formulated as an imitation learning problem in a partially observable Markov decision process. The model is trained by the generative adversarial framework, which uses the reward function from the adversarial discriminator. The model is tested with both simulation and real-world datasets, and the results show that the proposed model obtained significant performance gains compared to existing models in sequence modeling.

Seongjin Choi, Jiwon Kim, Hwasoo Yeo

With the increasing deployment of diverse positioning devices and location-based services, a huge amount of spatial and temporal information has been collected and accumulated as trajectory data. Among many applications, trajectory-based location prediction is gaining increasing attention because of its potential to improve the performance of many applications in multiple domains. This research focuses on trajectory sequence prediction methods using trajectory data obtained from the vehicles in urban traffic network. As Recurrent Neural Network(RNN) model is previously proposed, we propose an improved method of Attention-based Recurrent Neural Network model(ARNN) for urban vehicle trajectory prediction. We introduce attention mechanism into urban vehicle trajectory prediction to explain the impact of network-level traffic state information. The model is evaluated using the Bluetooth data of private vehicles collected in Brisbane, Australia with 5 metrics which are widely used in the sequence modeling. The proposed ARNN model shows significant performance improvement compared to the existing RNN models considering not only the cells to be visited but also the alignment of the cells in sequence.