Developing A Cooperative Perception System

Role: Project Leader | Funded by Center of Connected and Automated Transportation Period: Jan 2023 – Present

Phase 1: Cooperative Perception for CAV Navigation and Safety

• Built a cooperative perception system connected by V2X between roadside LiDAR and CAV sensors.
• Developed a detecting and navigating algorithm on CAV with sensor data fusion pipeline.
• Conducted field testing demonstrating the safety benefits in detecting occluded VRUs through cooperative perception.
• Result: Cooperative perception helps CAVs plan safer (higher post-encroachment time) and smoother (lower deceleration rates) trajectories.
• Publication: Cooperative Perception System for Aiding Connected and Automated Vehicle Navigation and Improving Safety

Phase 2: Infrastructure-Vehicle Cooperative Perception System

• Developing a cooperative perception system including multiple vehicles, infrastructure sensors, and drones.
• Extracting and processing multi-sensor data (LiDAR, Camera, etc.) to vehicle trajectories.
• Releasing open-source dataset for future research.