Mobile robot navigation and obstacle avoidance using fuzzy radial basis function neural networks

Authors:
Maarouf Saad;Guillaume Latombe;Karnon Suen;Vahé Nerguizian
Affiliations:
Electrical Engineering, École de Technologie Supérieure, Montreal, Quebec, Canada;Electrical Engineering, École de Technologie Supérieure, Montreal, Quebec, Canada;Electrical Engineering, École de Technologie Supérieure, Montreal, Quebec, Canada;Electrical Engineering, École de Technologie Supérieure, Montreal, Quebec, Canada
Venue:
ESPOCO'05 Proceedings of the 4th WSEAS International Conference on Electronic, Signal Processing and Control
Year:
2007

Citing 4
Cited 0

Radial basis functions for multivariable interpolation: a review

Algorithms for approximation
Original Contribution: On the training of radial basis function classifiers

Neural Networks
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a nonlinear multivariable fitting model to allow an autonomous mobile robot to reach a goal while avoiding obstacles. Radial Basis Function (RBF) neural networks are used to find the non-linear functions. These networks are designed using fuzzy clustering. This approach has the advantages to be very fast, very simple to implement, with well established convergence properties, and a good representation of the covariance matrix since all the data belong to all the classes at the same time with different membership levels. According to several parameters computed for a specific position of the robot, the non-linear functions allow the calculation of the robot's next position. A way to integrate the RBF networks into a more complex and efficient algorithm is also proposed. Simulation and experimental results show the effectiveness of the proposed approach.