Navigation of autonomous mobile systems

Abstract

Self-driving vehicles are an example of a disruptive technology that will alter the automotive, transportation, and logistics industries. Although self-driving vehicles do not rely solely on HD-maps, this technology could significantly expand the functionality of autonomous driving. Pre-generated HD-maps allow vehicles to see beyond the sensor's field of view, providing an accurate representation of the road ahead and information about the surrounding environment. SLAM has been the primary research subject for some problems for a while. It is a promising solution to most problems with mobile robots self-exploring different environments. It is used in several areas including self-driving vehicles. For example, slow speed robotics applications in confined environments are significantly easier than fast moving cars in highly dynamic environments. Hence, SLAM in autonomous vehicles still has numerous challenges. The first objective of this study is to discuss whether the difference between HD-maps prevalent across the industry from the SLAM approach in the field of robotics is a problem. Second is to discuss how the gap between HD-map and SLAM approaches can be filled by developing a new mapping solution which is actually relevant to the autonomous vehicle's operation.