Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: English
- Document No: 39292 (58)
- University: Sharif University of Technology, International Campus, Kish Island
- Department: Science and Engineering
- Advisor(s): Sadati, Hossein
- Abstract:
- Humanoid robots are robots that are similar in appearance and performance to humans. Designing and controlling a humanoid robot to perform such supposedly ordinary tasks as walking, running, writing, talking, driving, riding bikes, and the like is such a difficult task from the control point of view that it seems to be quite ambitious and inaccessible. In this thesis, the previous efforts of scientists and researchers are presented using different intelligent controllers. Additionally, the dynamic analysis of selective biped (seven-link biped robot) is illustrated. In this research, we present a method to control the walking of the biped robot while retaining stability. In this method the concept of intelligent controls is used such as Neural Network and Fuzzy Logic. The method, referred to here as ELICZ, stands for Emotional Learning based on Intelligent Control using Zero Moment Point (ZMP). A noted advantage of this method is to diminish the problems and disadvantages of classic Reinforcement Learning controllers, hence avoiding failures in the system. The simulation and experimental results of the biped model demonstrate that the performance of our proposed method is acceptable.
It is expected that this method, when used in other functions of the humanoid robots, will achieve good results - Keywords:
- Intelligent Control ; Reinforcement Learning ; Humanoid Robot ; Locomotion
Digital Object List
محتواي پايان نامه
Bookmark