Perception for Autonomous Systems: A Measurement Perspective on Localization and Positioning

Abstract

Autonomous systems are nowadays having an undisputed pervasiveness in modern society. Autonomous driving cars as well as applications of service robots (e.g., cleaning robots, companion robots, intelligent healthcare solutions, tour guided systems) are becoming more and more popular, and a general acceptance is now developing around such systems. Nonetheless, one of the major hurdles in building such applications relies on the capability of autonomous systems to understand their surroundings and then plan proper actions. The most popular solutions, which are gaining more and more attention, rely on artificial intelligence and deep learning as a means to perceive the structured and complex natural environment. Nonetheless, classical concepts of metrology, such as standard uncertainty, accuracy and precision, are still necessary for a clear and effective understanding of modern autonomous systems applications. In this paper, some fundamental measurement concepts will be reviewed in light of the autonomous systems domain, with an emphasis on localization and positioning problems for mobile robots. In particular, we will discuss and present the main issues and concepts that build around the statistical approach to measurements and the main role of uncertainties.