Affiliation:
1. Department of Electrical and Electronics Engineering Bilkent University Bilkent 06533 Ankara, Turkey
Abstract
In this study, physical models are used to model reflections from target primitives commonly encountered in a mobile robot's envi ronment. These targets are differentiated by employing a multi- transducer pulse/echo system that relies on both time-of-flight data and amplitude in the feature-fusion process, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief, which are subsequently fused by employ ing multiple logical sonars at geographically distinct sites. Feature datafrom multiple logical sensors arefused with Dempster's rule of combination to improve the performance of classification by reduc ing perception uncertainty. Using three sensing nodes, improvement in differentiation is between 10% and 35% withoutfalse decision, at the cost of additional computation. The method is verified by exper iments with a real sonar system. The evidential approach employed here helps to overcome the vulnerability of the echo amplitude to noise, and enables the modeling of nonparametric uncertainty in real time.
Subject
Applied Mathematics,Artificial Intelligence,Electrical and Electronic Engineering,Mechanical Engineering,Modelling and Simulation,Software
Reference34 articles.
1. Ayrulu, B., Barshan, B., and Utete, S.W. 1997 (April 20-25, Albuquerque, NM). Target identification with multiple logical sonars using evidential reasoning and simple majority voting. Proc. 1997 IEEE Int. Conf. on Robotics and Automation. New Jersey: IEEE, pp. 2063-2068.
2. Multitarget-Multisensor Tracking,1990
3. Location and curvature estimation of "spherical" targets using a flexible sonar configuration
Cited by
21 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献