Information fusion sensors for vehicle localization using evidence theory

We describe a possible structure for a localization system providing 2-D position. The system uses global positioning system (GPS) sensor measures as well as odometric data and a digital road map to maintain a correct estimate of the location of a vehicle. The measurement results from these differences sensors are fused by using the evidence theory. The objective is to reduce the position error. Experimental results show the potential of the utilization of evidence theory to the localization problem.

[1]  A. Leick.  GPS satellite surveying , 1990 .

[2]  Hichem Maaref,et al.  New fusion methodology approach and application to mobile robotics: investigation in the framework of possibility theory , 2001, Inf. Fusion.

[3]  M. Benjelloun,et al.  Parametric estimation of Dempster-Shafer belief functions , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[4]  E. Krakiwsky,et al.  A Kalman filter for integrating dead reckoning, map matching and GPS positioning , 1988, IEEE PLANS '88.,Position Location and Navigation Symposium, Record. 'Navigation into the 21st Century'..

[5]  D. Powell,et al.  Land-vehicle navigation using GPS , 1999, Proc. IEEE.

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