Katia Lopez

Document Type

Honors Thesis


The problem of inefficient machinery in industries affects overall production and can cause significant errors. The Human Assistance for Robot Arm (HAFRA) project consists of a Universal Robot, specifically the UR5, an Intel RealSense depth camera, and software programs. The robot receives a position from the computer vision program, which uses the camera to detect an AruCo tag, and then suctions the envelopes from a conveyor belt and places them into a bin. The project also includes human assistance, which allows remote picking by an operator. A human is able to view an image and use the mouse cursor to select a pixel coordinate. This coordinate is converted to a real-world position and sent to the robot so it can continue picking. Human assistance increased the robot’s performance and achieved a success rate of nearly 100%. Industries with product lines can use HAFRA to optimize their tasks with precision.

Publication Date






To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.