ROBOT MAP BUILDING FROM SONAR SENSORS AND DSmT

Knowledge acquisition in map building is characterized with uncer- tainty and imprecision. This uncertainty is especially severe in the course of build- ing grid maps using sonar. Jean Dezert and Florentin Smarandache have recently proposed a new information fusion paradigm (DSmT), whose major advantage is that it deals with uncertainty and conflict of information. In this article, based on the Dezert-Smarandache Theory, the authors demonstrate how to fuse information from homogeneous or heterogeneous sensors differing in reliability. Then, they build the belief model of sonar grid map and construct the generalized basic belief assignment function (gbbaf). Pioneer II mobile robot has served as experimental platform and a 3D-Map has been built online based on DSmT. Finally, this work has established a firm foundation for a firm foundation for the simultaneous study of a dynamic unknown environment and multi-robots' map building.

[1]  Sebastian Thrun,et al.  Simultaneous localization and mapping with unknown data association using FastSLAM , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[2]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[3]  P. Smets.  Data fusion in the transferable belief model , 2000, Proceedings of the Third International Conference on Information Fusion.

[4]  Wolfram Burgard,et al.  Robust Monte Carlo localization for mobile robots , 2001, Artif. Intell..

[5]  Viii Supervisor.  Sonar-Based Real-World Mapping and Navigation , 2001 .

[6]  Hans P. Moravec,et al.  High resolution maps from wide angle sonar , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[7]  David W. Murray,et al.  Simultaneous Localization and Map-Building Using Active Vision , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Eric Lefevre,et al.  Reply to the Comments of R. Haenni on the paper "Belief functions combination and conflict management , 2003, Inf. Fusion.

[9]  Henri Prade,et al.  Representation and combination of uncertainty with belief functions and possibility measures , 1988, Comput. Intell..

[10]  Jean Dezert,et al.  Partial ordering of hyper-powersets and matrix representation of belief functions within DSmT , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[11]  Wolfram Burgard,et al.  Active Markov localization for mobile robots , 1998, Robotics Auton. Syst..