Localization of mobile robot based on ID tag and WEB camera

Localization is one of the most important fundament for mobile robot. A localization system with low cost, easy accomplishment, simplicity, effectiveness and robustness is the aim of researchers all the time. Here, we proposed a novel method for localization of mobile robot using ID tag and Web camera. In our method, the path map in an indoor environment is expressed with node tree, every node is represented with two landmarks: ID tag and card with the same colour. Pairs of two landmarks are affixed to ceiling of distinct locations, and the middle point of every pair of landmarks in a node indicates the absolute position or the node because of the unique ID of tag, the absolute position of mobile robot can be expressed with the absolute position of node and, position and orientation relative to this node. Localization is implemented with two steps: detecting ID tag in one node with RF communication and measuring position and orientation of mobile robot relative to this node with camera. In this paper, related works are summarized and the advantages of our method are introduced, the scheme of system is described in detail, a fast image processing algorithm for extracting landmarks from background and strategies for system robustness are discussed. Localization experiments show that with this method the errors or relative position and orientation are less than 2.5 cm and 2.5 degree. Navigation showed us that localization with ID tag and Web camera is feasible for navigation in indoor environment. At last, strategies for improving system are discussed.

[1]  Sebastian Thrun,et al.  Integrating Grid-Based and Topological Maps for Mobile Robot Navigation , 1996, AAAI/IAAI, Vol. 2.

[2]  Yoshikazu Arai,et al.  Self-localization of Autonomous Mobile Robots using Information Buried in Environment. , 1998 .

[3]  Hugh F. Durrant-Whyte,et al.  An Autonomous Guided Vehicle for Cargo Handling Applications , 1995, ISER.

[4]  Gregory Dudek,et al.  Mobile robot localization from learned landmarks , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[5]  Wolfram Burgard,et al.  Mapping and localization with RFID technology , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[6]  Masaharu Takano,et al.  Position and Orientation Measurement of a Mobile Robot by Image Recognition of Simple Barcode Landmarks and Compensation of Inclinations , 2001 .

[7]  Gregory D. Hager,et al.  Image-based prediction of landmark features for mobile robot navigation , 1997, Proceedings of International Conference on Robotics and Automation.

[8]  Claus B. Madsen,et al.  Optimal landmark selection for triangulation of robot position , 1998, Robotics Auton. Syst..