Future intelligent transport systems depend on the accurate positioning of multipletargets in the road scene, including vehicles and all other moving or static elements. The existingself-positioning capability of individual vehicles remains insufficient. Also, bottlenecks indeveloping on-board perception systems stymie further improvements in the precision and integrityof positioning targets. Vehicle-to-everything (V2X) communication, which is fast becoming astandard component of intelligent and connected vehicles, renders new sources of informationsuch as dynamically updated high-definition (HD) maps accessible. In this paper, we propose aunified theoretical framework for multiple-target positioning by fusing multi-source heterogeneousinformation from the on-board sensors and V2X technology of vehicles. Numerical and theoreticalstudies are conducted to evaluate the performance of the framework proposed. With a low-costglobal navigation satellite system (GNSS) coupled with an initial navigation system (INS), on-boardsensors, and a normally equipped HD map, the precision of multiple-target positioning attainedcan meet the requirements of high-level automated vehicles. Meanwhile, the integrity of targetsensing is significantly improved by the sharing of sensor information and exploitation of mapdata. Furthermore, our framework is more adaptable to traffic scenarios when compared withstate-of-the-art techniques.
A Unified Multiple-Target Positioning Framework for
Intelligent Connected Vehicles