A unified benchmarking framework for cooperative autonomous driving with Multi-Agent Reinforcement Learning (MARL) capabilities, extending OpenCDA's full-stack simulation platform with distributed training infrastructure for intelligent multi-agent driving policies under CARLA+SUMO co-simulation.

Starter for research projects built on OpenCDA-MARL (work in progress)

Camera-LiDAR cross-modal matching for edge devices: pretrained matchers, targetless calibration, ONNX/TensorRT export, training, and one-shot adaptation.

CalibRefine: Deep Learning-Based Online Automatic Targetless LiDAR–Camera Calibration with Iterative and Attention-Driven Post-Refinement

Code for our paper: Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature

ROS 1 Package to collect, visualize, and process data from Hesai Lidar, TI mmWave Radar, and USB Camera for sensor fusion

Code for our paper: TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection

Code for our paper: Online Targetless Radar-Camera Extrinsic Calibration Based on the Common Features of Radar and Camera