Perceiving, Learning, and Exploiting Object Affordances for Autonomous Pile Manipulation

Dov Katz, Arun Venkatraman, Moslem Kazemi, J. Andrew (Drew) Bagnell, and Anthony (Tony) Stentz
Robotics: Science and Systems Conference, June, 2013.


Download
  • Adobe portable document format (pdf) (6MB)
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
Autonomous manipulation in unstructured environ- ments presents roboticists with three fundamental challenges: object segmentation, action selection, and motion generation. These challenges become more pronounced when unknown man- made or natural objects are cluttered together in a pile. We present an end-to-end approach to the problem of manipulating unknown objects in a pile, with the objective of removing all objects from the pile and placing them into a bin. Our robot perceives the environment with an RGB-D sensor, segments the pile into objects using non-parametric surface models, computes the affordances of each object, and selects the best affordance and its associated action to execute. Then, our robot instantiates the proper compliant motion primitive to safely execute the desired action. For efficient and reliable action selection, we developed a framework for supervised learning of manipulation expertise. We conducted dozens of trials and report on several hours of experiments involving more than 1500 interactions. The results show that our learning-based approach for pile manipulation outperforms a common sense heuristic as well as a random strategy, and is on par with human action selection.

Keywords
perception, learning, manipulation

Notes
Sponsor: US Army Research Laboratory, Intel Science and Technology Center for Embedded Computing, DARPA ARM-S Project
Associated Center(s) / Consortia: National Robotics Engineering Center

Text Reference
Dov Katz, Arun Venkatraman, Moslem Kazemi, J. Andrew (Drew) Bagnell, and Anthony (Tony) Stentz, "Perceiving, Learning, and Exploiting Object Affordances for Autonomous Pile Manipulation," Robotics: Science and Systems Conference, June, 2013.

BibTeX Reference
@inproceedings{Katz_2013_7438,
   author = "Dov Katz and Arun Venkatraman and Moslem Kazemi and J. Andrew (Drew) Bagnell and Anthony (Tony) Stentz",
   title = "Perceiving, Learning, and Exploiting Object Affordances for Autonomous Pile Manipulation",
   booktitle = "Robotics: Science and Systems Conference",
   month = "June",
   year = "2013",
}