arXiv subjects

Seongjin Choi

Publications and source records attributed to Seongjin Choi.

36 records · Page 2Linked to original sources

arXiv2025

A Survey on Vision-Language-Action Models for Autonomous Driving

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}.

cs.CV↗

arXiv2025

Scalable Dynamic Mixture Model with Full Covariance for Probabilistic Traffic Forecasting

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.

cs.LG↗

arXiv2025

Probabilistic Traffic Forecasting with Dynamic Regression

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.

cs.LG↗

arXiv2025

A Gentle Introduction and Tutorial on Deep Generative Models in Transportation Research

Deep Generative Models (DGMs) have rapidly advanced in recent years, becoming essential tools in various fields due to their ability to learn complex data distributions and generate synthetic data. Their importance in transportation research is increasingly recognized, particularly for applications like traffic data generation, prediction, and feature extraction. This paper offers a comprehensive introduction and tutorial on DGMs, with a focus on their applications in transportation. It begins with an overview of generative models, followed by detailed explanations of fundamental models, a systematic review of the literature, and practical tutorial code to aid implementation. The paper also discusses current challenges and opportunities, highlighting how these models can be effectively utilized and further developed in transportation research. This paper serves as a valuable reference, guiding researchers and practitioners from foundational knowledge to advanced applications of DGMs in transportation research.

cs.LG↗

arXiv2025

Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting

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.

cs.LG↗

arXiv2025

Toward Safe Integration of UAM in Terminal Airspace: UAM Route Feasibility Assessment using Probabilistic Aircraft Trajectory Prediction

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.

cs.LG↗

arXiv2024

Cellular sheaf Laplacians on the set of simplices of symmetric simplicial set induced by hypergraph

We generalize cellular sheaf Laplacians on an ordered finite abstract simplicial complex to the set of simplices of a symmetric simplicial set. We construct a functor from the category of hypergraphs to the category of finite symmetric simplicial sets and define cellular sheaf Laplacians on the set of simplices of finite symmetric simplicial set induced by hypergraph. We provide formulas for cellular sheaf Laplacians and show that cellular sheaf Laplacian on an ordered finite abstract simplicial complex is exactly the ordered cellular sheaf Laplacian on the set of simplices induced by abstract simplicial complex.

math.AT↗

arXiv2024

Better Batch for Deep Probabilistic Time Series Forecasting

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.

stat.ML↗

arXiv2024

Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control

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.

cs.LG↗

arXiv2024

A Real-time Evaluation Framework for Pedestrian's Potential Risk at Non-Signalized Intersections Based on Predicted Post-Encroachment Time

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.

cs.CV↗

arXiv2022

Optimal Parking Planning for Shared Autonomous Vehicles

Parking is a crucial element of the driving experience in urban transportation systems. Especially in the coming era of Shared Autonomous Vehicles (SAVs), parking operations in urban transportation networks will inevitably change. Parking stations will serve as storage places for unused vehicles and depots that control the level-of-service of SAVs. This study presents an Analytical Parking Planning Model (APPM) for the SAV environment to provide broader insights into parking planning decisions. Two specific planning scenarios are considered for the APPM: (i) Single-zone APPM (S-APPM), which considers the target area as a single homogeneous zone, and (ii) Two-zone APPM (T-APPM), which considers the target area as two different zones, such as city center and suburban area. S-APPM offers a closed-form solution to find the optimal density of parking stations and parking spaces and the optimal number of SAV fleets, which is beneficial for understanding the explicit relationship between planning decisions and the given environments, including demand density and cost factors. In addition, to incorporate different macroscopic characteristics across two zones, T-APPM accounts for inter- and intra-zonal passenger trips and the relocation of vehicles. We conduct a case study to demonstrate the proposed method with the actual data collected in Seoul Metropolitan Area, South Korea. Sensitivity analyses with respect to cost factors are performed to provide decision-makers with further insights. Also, we find that the optimal densities of parking stations and spaces in the target area are much lower than the current situations.

eess.SY↗

arXiv2022

A Framework for Pedestrian Sub-classification and Arrival Time Prediction at Signalized Intersection Using Preprocessed Lidar Data

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.

cs.LG↗

arXiv2021

Deep Learning based Urban Vehicle Trajectory Analytics

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.

cs.LG↗

arXiv2021

Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach

In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process. While most previous map-matching methods have focused on using rule-based algorithms to deal with the map-matching problems, in this paper, we consider the map-matching task from the data-driven perspective, proposing a deep learning-based map-matching model. We build a Transformer-based map-matching model with a transfer learning approach. We generate trajectory data to pre-train the Transformer model and then fine-tune the model with a limited number of ground-truth data to minimize the model development cost and reduce the real-to-virtual gap. Three metrics (Average Hamming Distance, F-score, and BLEU) at two levels (point and segment level) are used to evaluate the model performance. The results indicate that the proposed model outperforms existing models. Furthermore, we use the attention weights of the Transformer to plot the map-matching process and find how the model matches the road segments correctly.

cs.LG↗

arXiv2021

Development of Safety Monitoring System of Connected and Automated Vehicles considering the Trade-off between Communication Efficiency and Data Reliability

The safety of urban transportation systems is considered a public health issue worldwide, and many researchers have contributed to improving it. Connected automated vehicles (CAVs) and cooperative intelligent transportation systems (C-ITSs) are considered solutions to ensure urban transportation systems' safety using various sensors and communication devices. However, it is found difficult to deploy the C-ITS framework in South Korea, because CAVs produce a massive amount of data every minute but it cannot be transmitted via existing communication network. Thus, raw data must be sampled to reduce the size of the data over communication network and transmitted to the server for further processing. On the other hand, the sampled data must be highly accurate to ensure the safety of different agents in C-ITS. Thus, in this study, we designed and developed a C-ITS architecture and data flow, including messages and protocols for the safety monitoring system of CAVs, and determined the optimal sampling interval for data transmission while considering the trade-off between communication efficiency and reliability of safety performance indicators. Three safety performance indicators were introduced: severe deceleration, lateral position variance, and inverse time to collision. A field test is conducted to collect data from various sensors installed in the CAV, determining the optimal sampling interval. Kolmogorov-Smirnov test is conducted to ensure statistical consistency between sampled and raw datasets. The effects of the sampling interval on message delay, data accuracy, and communication efficiency were analyzed.

eess.SY↗

arXiv2021

Development of Simulation-based Lane Change Control System for Autonomous Vehicles

Originally, the decision and control of the lane change of the vehicle were on the human driver. In previous studies, the decision-making of lane-changing of the human drivers was mainly used to increase the individual's benefit. However, the lane-changing behavior of these human drivers can sometimes have a bad influence on the overall traffic flow. As technology for autonomous vehicles develop, lane changing action as well as lane changing decision making fall within the control category of autonomous vehicles. However, since many of the current lane-changing decision algorithms of autonomous vehicles are based on the human driver model, it is hard to know the potential traffic impact of such lane change. Therefore, in this study, we focused on the decision-making of lane change considering traffic flow, and accordingly, we study the lane change control system considering the whole traffic flow. In this research, the lane change control system predicts the future traffic situation through the cell transition model, one of the most popular macroscopic traffic simulation models, and determines the change probability of each lane that minimizes the total time delay through the genetic algorithm. The lane change control system then conveys the change probability to this vehicle. In the macroscopic simulation result, the proposed control system reduced the overall travel time delay. The proposed system is applied to microscopic traffic simulation, the oversaturated freeway traffic flow algorithm (OFFA), to evaluate the potential performance when it is applied to the actual traffic system. In the traffic flow-density, the maximum traffic flow has been shown to be increased, and the points in the congestion area have also been greatly reduced. Overall, the time required for individual vehicles was reduced.

eess.SY↗

arXiv2021

TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning

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.

cs.LG↗

arXiv2019

Attention-based Recurrent Neural Network for Urban Vehicle Trajectory Prediction

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.

cs.LG↗