doi:10.3850/978-981-08-7304-2_1476

ABSTRACT

Many authors have been used sensor fusion in different applications. In this paper we are using Sensor fusion for detection of various objects(shapes) like I,L,C shapes. These find use when the sensor suitable of a mobile robot comprises several different sensors, some complementary and some redundant. Integrating the sensor readings, the robot seeks to accomplish tasks such as constructing a map of its environment, locating itself in that map, and recognizing objects that should be avoided or sought. Here we are using bayesian theory technique in sensor fusion for mobile robot navigation. We know there are various types of techniques in sensor fusion like kalman filtering, dampstershafer (DS) theory, artificial neural network, bayesian theory etc. for various applications like mobile robot navigation, biomedical applications, surveillance, security & so on. In the bayesian method, it is classified as an inference. It allows the sensory information to be combined according to the rules of probability theory. The formulation of bayesian rule allows the combination of a priory probability of a hypothesis, conditional probability of an observation given a hypothesis and a posteriori probability of a hypothesis. This theory has used to model uncertainty in many disciples such as sensor fusion.

Keywords: Bayesian Theory, Evidential Reasoning, Mobile Robots, Sensor Fusion, Data fusion, Posteriori probability.

© 2011 ICCA 2010 Organizers