Mobile robot localization using color signboard

Abstract

Accurate, flexible and low-cost localization is an important issue for achieving autonomous and cooperative motions of mobile robots. This paper proposes a localization method for indoor mobile robots by using vision and artificial signboard. The signboards are placed in an environment and attached to the robots to decide the absolute positions and relative positions, respectively, of the robots. The important contribution is using signboard for the relative localization. Use of forward-looking camera and eye-level signboard allows us to achieve both the absolute and relative localization in a multi-robot environment, however, it brings a potential problem that the signboard viewed with the camera tends to be occasionally occluded with mobile robots hovering in the environment. The signboard is therefore designed such that the forward-looking camera can reliably detect the signboard even though it is partially blocked with unforeseen obstructions. A color-coding pattern is printed on the signboard to identify a lot of signboards in the multi-robots environment. The Kalman filter and the Interacting Multiple Model method are applied to find accurate positions of the robots by using the identified signboards. Experimental results show the feasibility of the proposed localization method.