ROSE is a PyTorch/MMDetection3D-based framework for robust roadside Camera–LiDAR 3D object detection under adverse weather. The code implements physics-guided cross-modal augmentation (RISA), teacher–student self-supervised coupling, adaptive training analysis, and tools for training, evaluation, and visualization on DAIR-V2X-style datasets.

The replication package for the paper “A multi-agent asynchronous cooperative on-ramp merging strategy with decision-making priorities in mixed traffic” is available. It contains source code, configurations, pretrained checkpoints, simulation outputs, and scripts for the proposed attention-order framework. The package reproduces the proposed model simulations, learning-curve analysis, ordering agreement, safety evaluation, and finite-stage-game Stackelberg Equilibrium.

This code-only replication package accompanies the revised manuscript “Crash Risk Prediction Guided by Large Language Models Using Pre-Crash Trajectories” submitted to Communications in Transportation Research (Manuscript ID: COMMTR-2026-0063.R1).

The package contains the implementation of the lightweight temporal graph student, offline LLM-guided knowledge distillation and fine-tuning workflows, evaluation and deployment benchmarking scripts, configuration files, environment specifications, a documented data interface, and a synthetic end-to-end smoke test. It also includes a Replication Explanatory File and a SHA-256 integrity manifest.

The basic code of RAVE (End-to-end Hierarchical Visual Localization with Rasterized and Vectorized HD Map)

This replication package contains all data and code necessary to reproduce the results reported in the manuscript "Physics-Informed Platooning with Learning-Augmented Calibration and Compensation: A Real-World Study" (COMMTR-2026-0163).

Hardware: Intel Core i5-9400F, 32GB RAM
Software: Python 3.8+, PyTorch 1.12+, d3rlpy 2.0+, Ubuntu 20.04/ROS Noetic

This paper introduces a novel deep learning framework that enhances vehicle re-identification (ReID) accuracy by integrating visual and temporal data. Vehicle ReID, which identifies target vehicles from large volumes of traffic data, is essential for continuous tracking in large-scale monitoring scenarios involving multiple Unmanned Aerial Vehicles (UAVs). UAV-based monitoring, while offering a comprehensive bird’s-eye view (BEV), faces key challenges: loss of uniquely identifiable features and reliance on visual data, which struggles with vehicles of similar appearance. To overcome these issues, our approach incorporates traffic-oriented features based on shockwave theory to model predictable vehicle travel times. Methods have been tested with data from one of the largest drone experiments with 10 drones monitoring 20 intersections for one week in the city of Songdo in Seoul Area. Experimental results demonstrate a 36.8\% improvement in ReID accuracy over traditional methods, highlighting the potential of UAV-based solutions for robust and scalable traffic monitoring.

This replication package includes all materials necessary for readers to understand and reproduce the analyses presented in the manuscript. As this study is a review paper that does not involve empirical datasets, experimental code, or algorithmic simulations, the materials provided focus on enabling transparent replication of the literature search and bibliometric procedures used in the study. All literature used in the analysis is fully cited within the review paper, ensuring complete traceability of the sources.

This paper proposes a lightweight vision and language large model based approach for pedestrian crossing intention prediction.We introduce a two-stage tuning strategy designed to enhance the model’s explicit and implicit reasoning capabilities. In our experiments, we first use Gemini to generate chain-of-thought annotations from the raw data. We then fine-tune a lightweight Qwen 2.5 model on the resulting CoT dataset using the proposed two-stage procedure. Experiments are conducted on two public datasets, PIE and JAAD. This replication package includes all materials required for readers to understand and reproduce the analyses reported in the paper.

This paper introduces latency-aware trajectory prediction, a new task that explicitly accounts for latency and repurposes it as a useful signal. We present LatenAux, a consolidated auxiliary learning paradigm that first decouples prediction into two tasks: a primary task that predicts valid-horizon trajectories from historical data, and an auxiliary task that utilizes latency-inclusive observations. By allowing the auxiliary branch access to latency-crafted inputs, LatenAux is then committed to transferring latency-aware knowledge to the primary branch via a progressive feature alignment strategy. Extensive experiments on two large-scale real-world datasets demonstrate the effectiveness and superiority of LatenAux, showing that it consistently supports latency-aware modeling and delivers more accurate and reliable trajectory forecasts.

Accurate short-horizon trajectory prediction is crucial for safe and reliable autonomous driving. However, existing vision-language models (VLMs) often fail to accurately understand driving scenes and generate trustworthy trajectories. To address this challenge, this paper introduces KEPT, a knowledge-enhanced VLM framework that predicts ego trajectories directly from consecutive front-view driving frames. KEPT integrates a temporal frequency–spatial fusion (TFSF) video encoder, which is trained via self-supervised learning with hard-negative mining, with a k-means & HNSW retrieval-augmented generation (RAG) pipeline. Retrieved prior knowledge is added into chain-of-thought (CoT) prompts with explicit planning constraints, while a triple-stage fine-tuning paradigm aligns the VLM backbone to enhance spatial perception and trajectory prediction capabilities. This replication package includes all materials required for readers to understand and reproduce the analyses reported in the paper.

All the materials source coding and results coding of  Vehicle-Infrastructure Cooperative General Object Detection through Feature Flow and Differentiable Pose-based Spatial Alignment

This replication package contains the dataset (CTSU) and source code used in TrafficPerceiver.

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

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.

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.

The basic code and date  of DLE

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

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.

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.