CVVLSNet: Vehicle Location and Speed Estimation Using Partial Connected Vehicle Trajectory Data

TL;DR

This paper introduces CVVLSNet, a novel deep learning approach that accurately estimates vehicle locations and speeds using partial connected vehicle data, enhancing traffic management capabilities.

Contribution

It proposes a new vehicle state representation and a deep learning model that effectively estimates full traffic information from limited connected vehicle data.

Findings

Significantly outperforms existing methods across various traffic scenarios.

Effective at low connected vehicle penetration rates.

Incorporates physical vehicle constraints into the estimation process.

Abstract

Real-time estimation of vehicle locations and speeds is crucial for developing many beneficial transportation applications in traffic management and control, e.g., adaptive signal control. Recent advances in communication technologies facilitate the emergence of connected vehicles (CVs), which can share traffic information with nearby CVs or infrastructures. At the early stage of connectivity, only a portion of vehicles are CVs. The locations and speeds for those non-CVs (NCs) are not accessible and must be estimated to obtain the full traffic information. To address the above problem, this paper proposes a novel CV-based Vehicle Location and Speed estimation network, CVVLSNet, to simultaneously estimate the vehicle locations and speeds exclusively using partial CV trajectory data. A road cell occupancy (RCO) method is first proposed to represent the variable vehicle state information. Spatiotemporal interactions can be integrated by simply fusing the RCO representations. Then, CVVLSNet, taking the Coding-RAte TransformEr (CRATE) network as a backbone, is introduced to estimate the vehicle locations and speeds. Moreover, physical vehicle size constraints are also considered in loss functions. Extensive experiments indicate that the proposed method significantly outperformed the existing method under various CV penetration rates, signal timings, and volume-to-capacity ratios.