Loading...

Human-Robot Interaction through Sound Source Localization for “Arash” Social Robot

Eydi, Abdollah | 2018

695 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 50972 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Meghdari, Ali; Vossoughi, Gholamreza; Alemi, Minoo
  7. Abstract:
  8. Over the years, The robots have entered the human community in addition to the factories and industrial centers, and a new branch in the field of robotics called social robots has been created. Such robots can become a personal companion for children and elderly people who accompany that person at home or outside. Social robots can even be used as a platform for health services or as a vendor in stores. The interaction of humans and robots in social robots and communicating with the audience is the main part of this series of robots. Human-robot interaction can be divided into three parts: visual, auditory and facial or body movements. Also, the behavior of a social robot must be as natural as possible in the eyes of the target audience, especially the children. Therefore, sound source localization is one of the most important capabilities for interaction, especially the verbal interaction of a robot with human beings. The purpose of this research is to design and build a sound source localization system for the Arash social robot. The system in the Arash social robot composed of 4 microphones and a camera on the robot's head. After the noise separation of the sound source, the robot predicts the direction of the source with algorithms based on correlation and intensity differences. The accuracy of localization algorithms has also been improved by using the camera and identifying the faces of individuals. As a result of using this algorithm, when the signal-to-noise ratio is greater than 20 dB, the Arash robot can withstand noise and accurately estimates the direction of the speaker's horizontal and vertical angles with a precision of 10 °
  9. Keywords:
  10. Sound Source Localization ; Social Robotics ; Human Robot Interaction (HRI) ; Arash Robot

 Digital Object List

 Bookmark

No TOC