Access the full text.
Sign up today, get DeepDyve free for 14 days.
Tucker Hermans, James Rehg, A. Bobick (2012)
Guided pushing for object singulation2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
Ashutosh Saxena, Justin Driemeyer, A. Ng (2008)
Robotic Grasping of Novel Objects using VisionThe International Journal of Robotics Research, 27
Dov Katz, O. Brock (2008)
Manipulating articulated objects with interactive perception2008 IEEE International Conference on Robotics and Automation
Lillian Chang, Joshua Smith, D. Fox (2012)
Interactive singulation of objects from a pile2012 IEEE International Conference on Robotics and Automation
Dov Katz, Arun Venkatraman, M. Kazemi, Drew Bagnell, A. Stentz (2013)
Perceiving, learning, and exploiting object affordances for autonomous pile manipulationAutonomous Robots, 37
Dov Katz, Yuri Pyuro, O. Brock (2008)
Learning to Manipulate Articulated Objects in Unstructured Environments Using a Grounded Relational Representation, 04
Jacqueline Kenney, Thomas Buckley, O. Brock (2009)
Interactive segmentation for manipulation in unstructured environments2009 IEEE International Conference on Robotics and Automation
T Joachims (1999)
Advances in kernel methods—support vector learning
J. Bagnell, Felipe Cavalcanti, Lei Cui, T. Galluzzo, M. Hebert, M. Kazemi, Matthew Klingensmith, Jacqueline Libby, T. Liu, N. Pollard, M. Pivtoraiko, Jean-Sebastien Valois, Ranqi Zhu (2012)
An integrated system for autonomous robotics manipulation2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
Megha Gupta, G. Sukhatme (2012)
Using manipulation primitives for brick sorting in clutter2012 IEEE International Conference on Robotics and Automation
Shao-Wen Yang, C. Wang, Chun-Hua Chang (2010)
RANSAC matching: Simultaneous registration and segmentation2010 IEEE International Conference on Robotics and Automation
(1977)
The theory of affordances, volume Perceiving (pp. 67–82)
Karol Hausman, Ferenc Bálint-Benczédi, Dejan Pangercic, Zoltán-Csaba Márton, Ryohei Ueda, K. Okada, M. Beetz (2013)
Tracking-based interactive segmentation of textureless objects2013 IEEE International Conference on Robotics and Automation
Tucker Hermans, Fuxin Li, James Rehg, A. Bobick (2013)
Learning contact locations for pushing and orienting unknown objects2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)
Radford Neal (2006)
Pattern Recognition and Machine LearningPattern Recognition and Machine Learning
D. Forsyth, J. Ponce (2002)
Computer Vision: A Modern Approach
H. Hoof, Oliver Kroemer, Jan Peters (2013)
Probabilistic interactive segmentation for anthropomorphic robots in cluttered environments2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)
JJ Gibson (1977)
The theory of affordances, volume Perceiving
Quoc Le, David Kamm, A. Kara, A. Ng (2010)
Learning to grasp objects with multiple contact points2010 IEEE International Conference on Robotics and Automation
Nathan Ratliff, Matthew Zucker, J. Bagnell, S. Srinivasa (2009)
CHOMP: Gradient optimization techniques for efficient motion planning2009 IEEE International Conference on Robotics and Automation
A. Goh, R. Vidal (2007)
Segmenting Motions of Different Types by Unsupervised Manifold Clustering2007 IEEE Conference on Computer Vision and Pattern Recognition
Jing Zhang, Fanhuai Shi, Jianhua Wang, Yuncai Liu (2007)
3D Motion Segmentation from Straight-Line Optical Flow
Dov Katz, M. Kazemi, J. Bagnell, A. Stentz (2013)
Clearing a pile of unknown objects using interactive perception2013 IEEE International Conference on Robotics and Automation
Carl Barck-Holst, Maria Ralph, Fredrik Holmar, D. Kragic (2009)
Learning grasping affordance using probabilistic and ontological approaches2009 International Conference on Advanced Robotics
D. Comaniciu, P. Meer (2002)
Mean Shift: A Robust Approach Toward Feature Space AnalysisIEEE Trans. Pattern Anal. Mach. Intell., 24
T. Joachims (1998)
Making large scale SVM learning practicalTechnical reports
Emre Ugur, Erol Sahin, Erhan Öztop (2012)
Self-discovery of motor primitives and learning grasp affordances2012 IEEE/RSJ International Conference on Intelligent Robots and Systems
Tobias Lang, Marc Toussaint (2010)
Planning with Noisy Probabilistic Relational RulesJ. Artif. Intell. Res., 39
M. Kazemi, Jean-Sebastien Valois, J. Bagnell, N. Pollard (2012)
Robust Object Grasping using Force Compliant Motion Primitives, 08
R. Stolkin, A. Greig, M. Hodgetts, J. Gilby (2008)
An EM/E-MRF algorithm for adaptive model based tracking in extremely poor visibilityImage Vis. Comput., 26
Autonomous manipulation in unstructured environments will enable a large variety of exciting and important applications. Despite its promise, autonomous manipulation remains largely unsolved. Even the most rudimentary manipulation task—such as removing objects from a pile—remains challenging for robots. We identify three major challenges that must be addressed to enable autonomous manipulation: 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 a system capable of manipulating unknown objects in such an environment. Our robot is tasked with clearing a table by removing objects from a pile and placing them into a bin. To that end, we address the three aforementioned challenges. Our robot perceives the environment with an RGB-D sensor, segmenting the pile into object hypotheses using non-parametric surface models. Our system then computes the affordances of each object, and selects the best affordance and its associated action to execute. Finally, 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. To verify the performance of our system, we conducted dozens of trials and report on several hours of experiments involving more than 1,500 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.
Autonomous Robots – Springer Journals
Published: Aug 1, 2014
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.