Using V2x Communications And Data Fusion To Achieve Lane-Level Positioning For Road Vehicles

Precise positioning is a key issue for road vehicles in navigation, safety, and autonomous driving applications. While global positioning system (GPS) is widely accepted, it is still a challenge to achieve lane-level positioning. In this work, we consider the fusion of multi-sensory data using particle filter (PF), which is flexible in integrating different information in complex outdoor environments. We focus on three types of popular sensors: controller area network (CAN bus), GPS, and roadside camera. We propose a PF model that can adopt these types of sensory inputs for vehicle positioning. We show that in scenarios where vision sensory inputs are available, lane-level precision can be achieved. When there is no vision coverage, seamless localisation with reasonable precision can still be supported by GPS. Field trial results are presented to validate our model.