| Author: | Wong, Wing-yu |
| Title: | Behavior-based robot navigation using ultrasonic sensor array and neuro-fuzzy techniques |
| Degree: | M.Phil. |
| Year: | 2003 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Robotics Autonomous robots Fuzzy logic Intelligent control systems |
| Department: | Department of Mechanical Engineering |
| Pages: | xiv, 108, 31, 5 leaves : ill. ; 30 cm |
| Language: | English |
| Abstract: | A mobile robot that navigates in an environment can avoid the obstacles and direct to the goal. In order to do so, we have developed behavior-based robot navigation in structured environment. Basically, there are five basic motion behaviors. The mobile robot follows the wall on the left side (left wall following), the wall on the right side (right wall following), walks along the mid-line of the corridor (corridor following), performs right angle turns in a U-shaped or dead end environment (right angle turning), and avoids the obstacle and moves towards the goal (obstacle avoidance and goal seeking). Therefore, we implemented five behavior controllers to represent these features and a behavior selector that will command the robot to execute the most appropriate behavior at any location during navigation. Fuzzy logic is first used for each behavior controller. Afterwards, the results of the fuzzy logic controller are used as the training data for the neural network controller. Furthermore, neural network is used to implement the behavior selector. Simulation results showed that our fuzzy logic controller and neural network controller performed satisfactorily and our behavior selector enabled the robot to reach the goal safely in a structured environment. In order to verify our simulation results, we constructed a mobile robot and then we used it to conduct experiments and the results are satisfactory. In conclusion, we have successfully designed five basic behavior controllers using both fuzzy logic and neural network approaches to enable a mobile robot to navigate in a structured environment. We have also designed a behavior selector that can correctly command the robot to execute the appropriate behavior at any location within the structured environment. The simulation results and the experiments that we conducted showed that our behavior-based neuro-fuzzy navigator is effective. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b17330889.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 8.51 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/2570