In Part I of this companion paper series, we introduced SWIFTraj, an open-source vehicle trajectory dataset collected by a UAV swarm. It provides long-distance continuous trajectories by connecting vehicle trajectories across consecutive UAV videos, with the longest trajectory exceeding 4.5 km, and covers an integrated network of freeways and connected urban roads. However, trajectory connection in UAV swarms is challenging because of video time-offset errors and irregular UAV layouts. To address these issues, this paper proposes a graph-based trajectory connection method. An undirected graph is used to represent flexible UAV layouts, an automatic time-alignment method is developed by minimizing trajectory matching costs, and cross-video vehicle association is performed using a Hungarian-algorithm-based matching table. Experiments on real-world and simulated data show that the proposed method achieves time alignment errors within three frames, about 0.1 s, and consistently high vehicle-matching F1-scores.

This paper presents a detailed description and characterization of a new open-source vehicle trajectory dataset, namely SWIFTraj, constructed from videos recorded by a swarm of 16 drones equipped with 5.4K-resolution cameras. The dataset is distinguished from existing open-source trajectory datasets in several aspects. First, it provides long-distance continuous trajectories of up to 4.5 km on a freeway, enabling in-depth investigation of traffic phenomena and their spatial and temporal evolution. Second, the data collection site covers an integrated network consisting of a long freeway corridor and parts of its connected urban network, facilitating traffic analysis and modeling from a network perspective. The dataset is publicly available at the SWIFTraj website (https://www.swiftraj.com). 

The package supports reproduction of the main numerical results reported in the study, including the MATLAB/Simulink simulations of a heterogeneous five-truck platoon, the longitudinal model predictive control with bounded RBF residual compensation, the LLM-guided scenario interpretation and deterministic validation process, and the scenario-adaptive lateral organization optimization.

The package includes MATLAB/Simulink model files, MATLAB scripts for lateral organization optimization and figure generation, Python scripts for LLM-guided scenario interpretation and safety validation, scenario input and output files, trained RBF model files, processed simulation data, and reference output figures/tables. The simulated scenarios are generic road and traffic segments and are not based on proprietary, confidential, or human-subject data. Detailed instructions for reproducing the main results are provided in the README file and the replication explanatory file.

The simulated scenarios are generic road and traffic segments and are not based on proprietary, confidential, or human-subject data.

The replication package contains processed real-world emission datasets and Python scripts used to reproduce the main analyses and figures presented in this study. The datasets include overall trip-average emissions, operating mode-specific emission results, and SCR upstream/downstream NOx data for China V and China VI heavy-duty diesel trucks tested using PEMS under real-road conditions. All analyses were conducted using Python 3.9 in PyCharm Community Edition 2023.1. Due to confidentiality restrictions, only processed and aggregated datasets are provided.

This replication package supports the manuscript “RESPOND: Risk-Enhanced Structured Pattern for LLM-driven Online Node-level Decision-making in Autonomous Driving” submitted to Communications in Transportation Research. The package includes source code, configuration files, structured memory files, simulation scripts, HighD evaluation scripts, visualization tools, and baseline implementation. It supports reproduction of the 5 × 3 risk-pattern encoding, Layer-1 exact memory, Layer-2 sub-pattern memory, hybrid Rule+LLM decision-making, reflection learning, personalization, highway-env simulation, and HighD real-world validation.

This dataset provides field-collected data from an electric vehicle (EV) platoon, specifically curated to analyze car-following behavior across different driving modes and control types.

By capturing data under both One-Pedal Driving (OPD) and Two-Pedal Driving (TPD)—and comparing Manual Driving against Adaptive Cruise Control (ACC)—the dataset offers a comprehensive look at how EV technology influences traffic flow.

Key Dataset Features

• Vehicle Composition: The data tracks a four-vehicle platoon consisting of one Internal Combustion Engine (ICE) lead vehicle followed by three EVs.

• Data Resolution: All trajectories are recorded at a high-frequency 10 Hz sampling rate.

• Sensor Integration: The dataset includes synchronized GPS trajectories for all four vehicles, ensuring precise spatial and temporal alignment.

Reinforcement learning (RL) is promising for end-to-end driving, but suffers from low sample efficiency and limited semantic interpretability. Vision-language models (VLMs) provide rich knowledge, yet their high inference cost hinders integration into RL training. We propose Found-RL, a platform for enhancing AD RL with foundation models. Its core is an asynchronous batch inference framework that decouples VLM reasoning from the simulation loop, reducing latency and enabling learning from VLM feedback. On this platform, we use VMR and AWAG to distill VLM action guidance into the policy, and adopt CLIP-based reward shaping with Conditional Contrastive Action Alignment for dense supervision. Experiments show that lightweight RL policies with millions of params can approach billion-parameter VLMs while maintaining real-time speed (~500 FPS). Code, data, and models are available at https://github.com/ys-qu/found-rl.

In the data file, NGSIM refers to the NGSIM trajectory data mentioned in the paper.
In the data file, WHUT contains the TVD trajectory data.
All code is stored in the “code” folder.
The filenames in the “code” folder correspond to the comparison model code and my complete model code, respectively.
Code Execution Order:
1. First, set up a virtual environment according to the requirements in `requirements.txt`.
2. Use the code in the “Data Preprocessing” section to build a standard training dataset. Note that you must manually adjust the prediction step size in the dataset to match that of each code file to ensure consistency.
3. Place the constructed data in a location accessible to all scripts, then run each script individually. To facilitate execution by readers, each .py file includes the model architecture, training code, testing code, validation code, and code for visualizing and saving results.

Due to privacy constraints, we have provided anonymized samples with randomly shuffled data distributions to illustrate the data structure used in our experiments.

This repository is the replication package for COIN: Collaborative Interaction-Aware Multi-Agent Reinforcement Learning for Self-Driving Systems. It provides the codebase, dependencies, and instructions needed to reproduce the training and evaluation results of COIN in multi-agent self-driving scenarios.

ABSTRACT: Advanced driver assistance systems (ADASs) can greatly enhance road safety by providing real-time warnings to drivers in imminent crash situations. However, the provided warning time may deviate from its designed time. There is limited research on how warning uncertainties influence drivers’ behavior, safety performance, and trust. This study conducted a driving simulator study to examine how uncertainties in warnings impact driving behaviors and trust using a roundabout driving scenario. Two warning error distributions were constructed to represent low and high warning uncertainty levels. Thirty-six participants were recruited and randomly divided into two groups under the two uncertainty levels in a driving simulator experiment. The betweengroup analysis shows that the lower warning uncertainty level group results in higher trust and that trust increases (or decreases) over time under low (or high) uncertainty levels. The within-group analysis shows that higher warning errors downgrade drivers’ trust and safety performance when the errors are high. 

Heavy-haul railways are critical for transporting freight. However, prolonged wheel–rail interactions cause frequent rail defects, particularly in small-radius curve sections. Ultrasonic A-scan signals are essential for the non-destructive evaluation of internal rail defects. In real heavy-haul environments, these signals suffer from strong non-Gaussian coupled noise. Such noise includes structural noise, low-frequency irrelevant components, and high-frequency electrical noise. Noise aliasing obscures defect echoes and increases the risk of missed detections. Conventional denoising methods are limited by poor noise–signal separability, mode mixing, and inadequate adaptability to complex non-Gaussian signals. To address these challenges, an A-scan signal model under noise-coupled conditions is constructed by analyzing the statistical and time–frequency characteristics of different noise components.

The replication package contains the questionnaire, datasets and analysis process used for the study.

The basic code and date  of DLE

STPredictor is an explainable ship trajectory prediction framework powered by large language models. It reformulates trajectory prediction as a language modeling task using natural-language prompts and integrates Chain-of-Thought reasoning for more transparent and reliable predictions. Experiments on two large-scale AIS datasets show strong performance and improved interpretability over existing baselines.

This replication package provides the complete source code and configuration files used in the study “CogDrive: Cognition-Driven Multimodal Prediction-Planning Fusion for Safe Autonomy.”

The package enables full reproduction of the proposed cognition-driven multimodal trajectory prediction and safety-aware planning framework, including model architecture implementation, training procedures, evaluation scripts, and planning modules.

The provided code supports both open-loop prediction evaluation and closed-loop planning simulations as reported in the manuscript. All scripts are organized to facilitate reproducibility of the main experimental results on public autonomous driving benchmarks.

This paper identifies, analyzes, and addresses case-level forgetting in continual learning for trajectory prediction. We propose the Dynamically Expandable Interactive Trajectory Predictor (DEITP), a novel framework that preserves previously learned knowledge through a dynamic model expansion mechanism. The mechanism regulates expansion timing by assessing model similarity, thereby controlling model growth while preventing catastrophic forgetting. Furthermore, to operate in realistic task-free settings where task identity is unavailable at test time, we introduce a task identification strategy based on a familiarity autoencoder that selects the most appropriate expert for prediction. Extensive experiments on real-world datasets demonstrate that DEITP substantially mitigates forgetting and achieves zero-forgetting performance when task identities are known.

The entire project package is uploaded. Simply unzip it and run the train and test functions separately; the data have already been preprocessed.