Multi-Observer Vehicle Localization Case Study with Roadside Radar and Connected Vehicle Sensing
Author1, Author2, Author3, Author4, Author5
Abstract
This paper presents a multi-observer vehicle localization framework that fuses data from roadside radar and connected vehicle LiDAR to improve vehicle positioning in mixed traffic conditions.
Reality Card
The study demonstrates that decision-level fusion of radar and LiDAR data can provide scenario-dependent benefits for vehicle localization, with the AEKF method achieving small gains over a LiDAR-only baseline.
Under full LiDAR availability, fusion performance is dominated by LiDAR observations, but AEKF achieves small gains over the LiDAR-only baseline.
Real-world evidence on decision-level fusion between radar and LiDAR sources remains limited, and the benefits are scenario-dependent.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.