In this thesis, we tackle the problem of extending neural network navigation algorithms for various types of mobile robots and 2-dimensional range sensors. We propose a general method to interpret the data from various types of 2-dimensional range sensors and a neural network algorithm to perform the navigation task. Our approach can yield a global navigation algorithm which can be applied to various types of range sensors and mobile robot platforms. Moreover, this method allows the neural networks to be trained using only one type of 2-dimensional range sensor, which contributes positively to reducing the time required for training the networks. Experimental results carried out in simulation environments demonstrate the effectiveness of our approach in mobile robot navigation for different kinds of robots and sensors. Therefore, the successful implementation of our method provides a solution to apply mobile robot navigation algorithms to various robot platforms.
A Generalized Neural Network Approach to Mobile Robot Navigation and Obstacle Avoidance
2012-01-01
Electronic Theses and Dissertations
Theses
Electronic Resource
English
Research of Robot of Obstacle Avoidance and Navigation
Trans Tech Publications | 2012
|Autonomous obstacle avoidance underwater navigation subsea pipeline detection robot
European Patent Office | 2023
|