Approximate reasoning-based sensor fusion: a real case study

The theme of this paper is to generate a consensus among sensors by combining measurements and resolving conflicts at various levels of sensor fusion. Resolving conflicts and reaching consensus among sensors are accomplished using two methods: Bayesian rules and the theory of fuzzy logic (a new fusion formula). Methods of fusion, Bayesian approach and the fuzzy fusion formula are analyzed and then used to fuse the generated models. Results obtained using the two methods are compared and evaluated.