Improving Vehicle Localization Confidence Under Different Road Geometries

A significant challenge to the scalability of automated driving systems is the potential unavailability of GPS information for localization. To address this issue, a methodology using a static map of road and lane geometry is proposed that ensures reliable navigation for automated vehicles in GPS-denied situations. In this study, a dead reckoning system based on vehicle kinematics is implemented by onboard sensor data from the vehicle's Controller Area Network (CAN). The drift in the dead reckoning position estimate is reduced by using an arc-length based map matching approach. However, the map-matching approach has some inaccuracies in the longitudinal position estimate leading to error accumulation, the drift in the dead reckoning position estimate is eliminated by using an arc-length based map matching approach. This innovative approach was tested and validated at various safety-critical intersection scenarios, including four-way intersection, roundabout, slip-lane intersection, and curved road. This approach guarantees the continuous and reliable localization of automated vehicles, thereby significantly enhancing their safety and operational reliability in environments with compromised or unavailable GPS signals.