Optimizing for what matters: The top grasp hypothesis

In this paper, we consider the problem of robotic grasping of objects when only partial and noisy sensor data of the environment is available. We are specifically interested in the problem of reliably selecting the best hypothesis from a whole set. This is commonly the case when trying to grasp an object for which we can only observe a partial point cloud from one viewpoint through noisy sensors. There will be many possible ways to successfully grasp this object, and even more which will fail. We propose a supervised learning method that is trained with a ranking loss. This explicitly encourages that the top-ranked training grasp in a hypothesis set is also positively labeled. We show how we adapt the standard ranking loss to work with data that has binary labels and explain the benefits of this formulation. Additionally, we show how we can efficiently optimize this loss with stochastic gradient descent. In quantitative experiments, we show that we can outperform previous models by a large margin.

[1]  Klaus Obermayer,et al.  Support vector learning for ordinal regression , 1999 .

[2]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[3]  Peter K. Allen,et al.  An SVM learning approach to robotic grasping , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[4]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[5]  Tie-Yan Liu,et al.  Learning to rank: from pairwise approach to listwise approach , 2007, ICML '07.

[6]  Ashutosh Saxena,et al.  Robotic Grasping of Novel Objects using Vision , 2008, Int. J. Robotics Res..

[7]  Stefan Schaal,et al.  Learning locomotion over rough terrain using terrain templates , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Takeo Kanade,et al.  Automated Construction of Robotic Manipulation Programs , 2010 .

[9]  Quoc V. Le,et al.  Learning to grasp objects with multiple contact points , 2010, 2010 IEEE International Conference on Robotics and Automation.

[10]  Ashutosh Saxena,et al.  Efficient grasping from RGBD images: Learning using a new rectangle representation , 2011, 2011 IEEE International Conference on Robotics and Automation.

[11]  Luc Van Gool,et al.  Branch&Rank: Non-Linear Object Detection , 2011, BMVC.

[12]  Larry H. Matthies,et al.  End-to-end dexterous manipulation with deliberate interactive estimation , 2012, 2012 IEEE International Conference on Robotics and Automation.

[13]  J. Andrew Bagnell,et al.  Robust Object Grasping using Force Compliant Motion Primitives , 2012, Robotics: Science and Systems.

[14]  Yichuan Tang,et al.  Deep Learning using Linear Support Vector Machines , 2013, 1306.0239.

[15]  Danica Kragic,et al.  Data-Driven Grasp Synthesis—A Survey , 2013, IEEE Transactions on Robotics.

[16]  Gaurav S. Sukhatme,et al.  An autonomous manipulation system based on force control and optimization , 2014, Auton. Robots.

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

[18]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[19]  Jeannette Bohg,et al.  Leveraging big data for grasp planning , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Joseph Redmon,et al.  Real-time grasp detection using convolutional neural networks , 2014, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Stefan Schaal,et al.  Exemplar-based prediction of global object shape from local shape similarity , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).