Abstract
Autonomous vehicles need to recognize and localize obstacles in their environment in order to avoid collisions. This paper presents a novel method for estimating the misalignment between a simultaneous localization and mapping (SLAM) map and and an Earth-fixed coordinate systems in order to allow highly accurate global localization of obstacles in the environment. The sensors used for this method are an Inertial Measurement Unit (IMU), satellite-based positioning (GNSS/GPS) and both 2D and 3D lidar sensors. Experimental validation on a tractor shows that the typical global localization accuracy is in the range of 100 mm…150 mm.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
