UrbanV2X: A Multisensory Vehicle-Infrastructure Dataset for Cooperative Navigation in Urban Areas
🤖 AI Summary
A lack of realistic, multimodal datasets hinders research on vehicle-infrastructure cooperative navigation in high-density urban environments.
Method: This paper introduces the first publicly available, synchronized multi-source perception dataset jointly captured from both vehicle-mounted and roadside units, encompassing camera, LiDAR, 4D radar, UWB, IMU, and high-precision GNSS-RTK/INS data. It pioneers end-to-end sensor time synchronization (PTP) and joint calibration across vehicle and infrastructure sensors within a real-world C-V2X testbed in Hong Kong, resolving spatiotemporal alignment challenges for heterogeneous sensors in complex urban scenarios.
Contribution/Results: The released open dataset enables benchmarking of cooperative localization, perception, and navigation algorithms. Experimental evaluation demonstrates significantly improved localization robustness under challenging conditions—such as severe occlusion and degraded GNSS signal—thereby filling a critical gap in city-scale, multimodal, vehicle-infrastructure cooperative benchmarks.
Application Category
📝 Abstract
Due to the limitations of a single autonomous vehicle, Cellular Vehicle-to-Everything (C-V2X) technology opens a new window for achieving fully autonomous driving through sensor information sharing. However, real-world datasets supporting vehicle-infrastructure cooperative navigation in complex urban environments remain rare. To address this gap, we present UrbanV2X, a comprehensive multisensory dataset collected from vehicles and roadside infrastructure in the Hong Kong C-V2X testbed, designed to support research on smart mobility applications in dense urban areas. Our onboard platform provides synchronized data from multiple industrial cameras, LiDARs, 4D radar, ultra-wideband (UWB), IMU, and high-precision GNSS-RTK/INS navigation systems. Meanwhile, our roadside infrastructure provides LiDAR, GNSS, and UWB measurements. The entire vehicle-infrastructure platform is synchronized using the Precision Time Protocol (PTP), with sensor calibration data provided. We also benchmark various navigation algorithms to evaluate the collected cooperative data. The dataset is publicly available at https://polyu-taslab.github.io/UrbanV2X/.
Problem
Research questions and friction points this paper is trying to address.
Addresses the lack of real-world datasets for vehicle-infrastructure cooperative navigation in complex urban environments.
Presents a multisensory dataset from vehicles and roadside infrastructure to support smart mobility research.
Provides synchronized, calibrated sensor data to benchmark navigation algorithms for cooperative autonomous driving.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multisensory dataset from vehicles and roadside infrastructure
Synchronized data using Precision Time Protocol
Benchmarking navigation algorithms with cooperative data
🔎 Similar Papers
No similar papers found.
