Skip to Main Content
The RBF network is designed for the mobile robot to acquire the accurate and real-time heading angle that is significant for the successful localization. Several designs related to the network architecture and training has been made to construct the RBF network using the OLS algorithm. The results of the experiment show that the designed neural network can greatly improve the accuracy of the localization. The proposed localization system with combined sensors based on the RBF neural network is reliable to ensure the intelligent behaviors of the robot. The technical presentations in this paper can facilitate the application of artificial neural networks in the environmental robotics.
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on (Volume:5 )
Date of Conference: 26-29 Aug. 2004