A comparison of contact distribution representations for learning to predict object interactions

Different contacts between objects afford different interactions between them. For example, while contacts below an object can provide support, contacts on opposing sides can be used for pinching. Hence, a robot can learn to predict which interactions are currently afforded based on the set of contacts. However, representing sets of contacts is not trivial, as the number of contacts is not fixed nor are the contacts ordered. In this paper, we compare different methods for representing contacts, including bag-of-features, probability product kernels, and random forests. These approaches model the distribution over the contacts without relying on task-specific features. The methods were evaluated on both simulated grasping data, as well as real robot grasps. The random forest and the normalized expected likelihood kernel approaches achieved the highest accuracies for the simulated experiments. In the case of the real robot data, the more robust exponential χ2 and Bhattacharyya kernels achieved higher accuracies.

[1]  Yun Jiang,et al.  Learning to place new objects in a scene , 2012, Int. J. Robotics Res..

[2]  Tony Jebara,et al.  Probability Product Kernels , 2004, J. Mach. Learn. Res..

[3]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[4]  Peter K. Allen,et al.  Graspit! A versatile simulator for robotic grasping , 2004, IEEE Robotics & Automation Magazine.

[5]  John F. Canny,et al.  Planning optimal grasps , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[6]  Peter K. Allen,et al.  Learning grasp stability , 2012, 2012 IEEE International Conference on Robotics and Automation.

[7]  Jaume Amores,et al.  Multiple instance classification: Review, taxonomy and comparative study , 2013, Artif. Intell..

[8]  Tony Jebara,et al.  Bhattacharyya Expected Likelihood Kernels , 2003, COLT.

[9]  Alex Smola,et al.  Kernel methods in machine learning , 2007, math/0701907.

[10]  Oliver Kroemer,et al.  A kernel-based approach to direct action perception , 2012, 2012 IEEE International Conference on Robotics and Automation.

[11]  Andrew Zisserman,et al.  Multiple kernels for object detection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  James M. Rehg,et al.  Learning contact locations for pushing and orienting unknown objects , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[13]  Alexander Herzog,et al.  Learning of grasp selection based on shape-templates , 2014, Auton. Robots.

[14]  Peter K. Allen,et al.  Examples of 3D grasp quality computations , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[15]  Manuel Lopes,et al.  Active Learning for Teaching a Robot Grounded Relational Symbols , 2013, IJCAI.

[16]  Siddhartha S. Srinivasa,et al.  Benchmarking in Manipulation Research: Using the Yale-CMU-Berkeley Object and Model Set , 2015, IEEE Robotics & Automation Magazine.

[17]  Vijay Kumar,et al.  Robotic grasping and contact: a review , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[18]  Robert D. Howe,et al.  A compliant, underactuated hand for robust manipulation , 2013, Int. J. Robotics Res..

[19]  Benjamin Rosman,et al.  Learning spatial relationships between objects , 2011, Int. J. Robotics Res..

[20]  Yiannis Aloimonos,et al.  Learning the spatial semantics of manipulation actions through preposition grounding , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Danica Kragic,et al.  ST-HMP: Unsupervised Spatio-Temporal feature learning for tactile data , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Patric Jensfelt,et al.  Learning spatial relations from functional simulation , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Oliver Kroemer,et al.  Predicting object interactions from contact distributions , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Danica Kragic,et al.  Generalizing grasps across partly similar objects , 2012, 2012 IEEE International Conference on Robotics and Automation.

[26]  Matei T. Ciocarlie,et al.  The Columbia grasp database , 2009, 2009 IEEE International Conference on Robotics and Automation.

[27]  Robert Jenssen,et al.  The Cauchy-Schwarz divergence and Parzen windowing: Connections to graph theory and Mercer kernels , 2006, J. Frankl. Inst..

[28]  Danica Kragic,et al.  Learning tactile characterizations of object- and pose-specific grasps , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[29]  George Karypis,et al.  The Set Classification Problem and Solution Methods , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[30]  Máximo A. Roa,et al.  Grasp quality measures: review and performance , 2014, Autonomous Robots.