/What Is the Robot Thinking? Embedded Feedback in the Intelligent Workcell Manufacturing Environment

What Is the Robot Thinking? Embedded Feedback in the Intelligent Workcell Manufacturing Environment

Harrison Billmers
Master's Thesis, Tech. Report, CMU-RI-TR-17-49, Robotics Institute, Carnegie Mellon University, August, 2017

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Today’s manufacturing industry relies on robots to complete tasks that require high speed, precision, and power beyond human capabilities. To ensure safety, these large robotic arms operate in isolated work cells separate from humans and are not designed to communicate with people. Some advanced safety systems, such as the Intelligent Workcell, monitor people’s movement within a workcell, allowing people and robots to work together safely in collaborative manufacturing settings. During collaboration, the worker needs to know what the robot is thinking and what it plans to do. We hypothesize that embedded feedback within the environment can effectively communicate the robot’s intentions. We developed, tested, and evaluated three visual feedback systems: a real-time display simulation of the virtualized workcell environment, arm-mounted embedded lighting, and an embedded floor display system. We conducted a user study employing a simulated manufacturing task to evaluate each feedback method for collaborative and overall performance. We found that feedback improves collaboration for human-robot assembly tasks by reducing average robot blockage time by at least 12% compared to the control group. Compared to the other feedback methods, the embedded floor display feedback allowed about 20% faster resolution of blockages when detected. Embedded arm-mounted light feedback helped participants preemptively avoid causing blockages. The embedded floor display was the most effective feedback modality evaluated, followed by partial performance gains from both the simulation and the embedded arm-mounted lights. We also provide recommendations for more extensive analysis of feedback systems in future work.

BibTeX Reference
@mastersthesis{Billmers-2017-27150,
author = {Harrison Billmers},
title = {What Is the Robot Thinking? Embedded Feedback in the Intelligent Workcell Manufacturing Environment},
year = {2017},
month = {August},
school = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-17-49},
}
2017-09-13T10:38:01+00:00