Development of Kinect based robot control system with obstacle avoidance capability

• Main Author: Chew, Boon Jin
• Other Authors: Cheah Chien Chern
• Format: Final Year Project
• Language: English
• Published: 2016
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
• Online Access: http://hdl.handle.net/10356/67877
• Institution: Nanyang Technological University

Obstacle avoidance has been a developing field of research in robotics for many years. Different sensors were used in the past to obtain information on the obstacles. In this project, obstacle information obtained using Microsoft Kinect sensor was used to design a robotic control system capable of avoiding them. The control system is tested on a Selective Compliance Assembly Robot Arm (SCARA) industrial robot. Artificial Potential Field and Region Control are used to develop the torque required to move the robot’s end effector to the desired position while avoiding any obstacles that are within the robot workspace. Tangential potential field is also used to ensure that the end effector will go about the obstacle smoothly. The final program is capable of handling circular and rectangular obstacles. This report will also cover the results and observations made during the course of testing, the challenges encountered, and measures taken to overcome them.