Real-Time Traffic State Measurement Using Autonomous Vehicles Open Data
Zhaohan Wang, Profita Keo, Meead Saberi
Abstract
Autonomous vehicle (AV) technologies are expected to disrupt the existing urban transportation systems. AVs’ multi-sensor system can generate large amount of data, often used for localization and safety purposes. This study proposes and demonstrates a practical framework for real-time measurement of local traffic states using LiDAR data from AVs. Fundamental traffic flow variables including volume, density, and speed are computed along with the traffic time-space diagrams. The framework is tested using the Waymo Open dataset. Results provide insights into the possibility of real-time traffic state estimation using AVs’ data for traffic operations and management applications.
Topics & Concepts
Computer scienceFloating car dataReal-time computingTraffic flow (computer networking)State (computer science)LidarVolume (thermodynamics)Traffic speedAdvanced Traffic Management SystemTraffic congestion reconstruction with Kerner's three-phase theoryIntelligent transportation systemTransport engineeringTraffic congestionComputer networkEngineeringGeographyRemote sensingAlgorithmQuantum mechanicsPhysicsTraffic Prediction and Management TechniquesTraffic control and managementAutonomous Vehicle Technology and Safety