Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/72961
Title: Sphero robot controlled by using brain computer interface offline
Authors: Sun, Yaxiong
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2017
Abstract: Communication is an important part in human life, it supports and help with human development. However, diseases can take away communication skill of a person. Without being able to communicate properly, the person will face psychological issues. One of the diseases is stroke. There is a study shown that nearly 800,000 people in the United States have a stroke every year and stroke is the No 5 cause of death in the United States, it kills nearly 130,000 people a year. [1].If a person impact stroke, she/he will lose the ability of communication and movement ability. In order to provide a method to help those people with problem communication, The Brain computer interface system has been developed. In this project, the writer studies the BCI system and analyze the brain signal to find out the characteristic of the specific brain signal, then to control the Sphero robot off line. If the writer can control the robot by using the brain signal, that means people can develop this method to help the disabled people. BCI system deals with the problem of establishing direct communication pathways between the brain and devices. The primary motivation is to enable patients with limited or no muscular control to use external devices by automatically interpreting their intent based on brain electrical activity measured by electroencephalography. In this project, firstly the writer studies the SDK and API information of the Sphero robot, because the SDK and API introduce the knowledge of how to use computer connect and control the robot. Secondly, the writer use EEG equipment to collect the brain signal when person focus some number. Thirdly, the SVM model has been used to analyze the brain signal, in this process, the time domain signal need to be converted to frequency domain signal. Lastly, transfer the analyzed the result to robot for movement. After finishing the project, the accuracy of result for analyzing data part is above 90% and it is accepted for this project.it also have some aspects need to be improved which will be introduced at the last in the report.
URI: http://hdl.handle.net/10356/72961
Schools: School of Computer Science and Engineering 
Research Centres: Centre for High Performance Embedded Systems 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Final Report_SUN YAXIONG.pdf
  Restricted Access
1.6 MBAdobe PDFView/Open

Page view(s) 50

473
Updated on Jun 13, 2024

Download(s) 50

40
Updated on Jun 13, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.