3D robot mapping: combining active and non active sensors in a probabilistic framework

Abstract

Map reconstruction and robot location are two essential problems in the field of robotics and artificial intelligence. A robot could need a model of the environment that can be incomplete and therefore the robot must work considering the uncertainty. Bayesian Units consider the uncertainty and allow the fusion of information from different sensors. In this paper a map reconstruction system in 3D based on Bayesian Units is presented. The reconstruction is carried out integrating the data obtained by a laser and by an omnivision system. In addition, to improve the quality of the reconstruction, the fusion of several Bayesian Units is defined using a competitive fusion operator. Finally, the obtained results as well as the validity of the system are shown.