Home/Harnessing Human Manipulation

Harnessing Human Manipulation

Matthew T. Mason, Nancy Pollard, Alberto Rodriguez and Ryan Kerwin
Conference Paper, Carnegie Mellon University, NSF/ARL Workshop on Cloud Robotics : Challenges and Opportunities, February, 2013

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.


This paper describes a new project to analyze the vast corpus of human manipulation videos available on the web, using citizen scientists. Humans understand human manipulation well enough to segment videos appropriately, to assign intent, and to recognize actions even from poor imagery. A large corpus of analyzed human manipulation would add to our understanding of manipulation, support automated analysis, facilitate collaborative manipulation and generally accelerate robotic manipulation research. The paper presents our initial results with a web interface used by nine “citizen scientists” to analyze sandwich making.

BibTeX Reference
title = {Harnessing Human Manipulation},
author = {Matthew T. Mason and Nancy Pollard and Alberto Rodriguez and Ryan Kerwin},
booktitle = {NSF/ARL Workshop on Cloud Robotics : Challenges and Opportunities},
school = {Robotics Institute , Carnegie Mellon University},
month = {February},
year = {2013},
address = {Pittsburgh, PA},