Gesture Controlled AI-Robot Using Kinect

EasyChair Preprint 4875

Abstract

Gesture recognition for human computer interaction is an area of active research in artificial intelligence and computer vision. To estimate gesture recognition performance in a real-life environment, we collect the gesture data that takes into account cluttered backgrounds, various poses and movement of robots, and then we evaluate the performance of robot. This involves skeleton tracking, where the skeleton data is produced from the depth images obtained via Microsoft Kinect sensor. The human gestures in 3 D space is captured by the kinect processed and replicated by the robot.  An Arduino controller is used to govern the motion of robot which takes the input as joint angles from the kinect sensor and feeds it back to robot circuit and thus controls the robot actions. The primary goal of gesture recognition research is to create a system, which can identify specific human gestures and use them for device control. The gesture control robot will save huge cost of labour in future. The basic advantage of this robot is that it will be cost effective and no remote control is required.

Keyphrases: Kinect, Robotic movements, gesture

@booklet{EasyChair:4875,
  author    = {B Jayasurya and Jino Justin and C Kharat Pooja and Mrutyunjay A Hasaraddi and T Kavitha},
  title     = {Gesture Controlled AI-Robot Using Kinect},
  howpublished = {EasyChair Preprint 4875},
  year      = {EasyChair, 2021}}