Compensation of observability problem in a multi-robot localization scenario using CEKF

Abstract

Many localization techniques today rely on absolute landmark measurements to efficiently track the robot's position in space. Although absolute landmarks are essential for correctly estimating its position, they might be rare in an unknown environment. This means that the robot would have to traverse long distances without any outside reference point resulting in system degradation. In case of a robot team though, each robot can rely on both absolute or relative position measurements between robots. This paper describes an approach for a multi-robot localization system, based on a single centralized extended Kalman filter (CEKF) to track the position and orientation changes of a group of robots. Moreover, it is shown that if the robots in the group collect only relative measurements the system suffers from observability problem. It is proven that an increasing number of mobile robots capable of relative measurements only, reduces the observability problem and compensates for the need of external absolute landmarks thus providing efficient localization.