Absolute localization for low capability robots in structured environments using barcode landmarks

Research on multi-robot systems often demands the use of a large population of small, cheap, and low capability mobile robots. Many non-trivial behaviors demand these robots to be localized in real-time. This paper addresses the problem of absolute localization of such low capability robots using onboard sensors and local computation. The approach is based on the use of a pair of scan lines perceived by an onboard B&W camera to detect and decode artificial visual landmarks deployed along the environment. Each landmark consists on a dual-layer barcode which can encode its pose with respect to a global coordinate frame. Thus, the robot is not required to store a map of the landmark locations onboard. The method is based on an Extended Kalman Filter (EKF) fusing odometry readings with absolute pose estimates obtained from the camera. Experimental results using an e-puck robot with 8 KB of RAM and a 16 MIPs processor are presented, comparing the location estimates with both ground truth and odometry.