Open Collections

A robotic workstation vision-based safety system for persons with physical disabilities

University of British Columbia

The overall goal of this research project was to investigate and develop a vision-based safety system that would either solely, or in combination with another system, provide an acceptable level of safety for a user with a severe physical disability while operating a rehabilitative robotic workstation developed by the Neil Squire Foundation A system was developed that uses a single camera to track the user in a horizontal plane and uses feedback from the robot controller to calculate the position of the robot using kinematic equations. The system is controlled by a computer that can communicate with the robot controller and stop the robot if it detects a safety zone violation. Prior to the development of a vision-based safety system, a safety analysis was performed considering general rehabilitative robotic equipment and a user with a severe physical disability. This analysis revealed injury mechanisms such as collisions, pinning, and pinching and identified levels of injuries from life threatening injuries to undesired contact with the robot. The safety analysis was then specifically targeted to the Neil Squire Foundation robot and used to determine the performance requirements of a variety of safety systems, including a vision-based safety system. Testing of the vision-based safety system on the robotic workstation with potential users showed that the system fulfilled all the project specifications, including preventing all unintentional contact between user and the robot

Thesis/Dissertation

application/pdf

2009-03-16

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/6076

Mechanical Engineering

University of British Columbia

UBCV

DSpace