High precision grasp pose detection in dense clutter

This paper considers the problem of grasp pose detection in point clouds. We follow a general algorithmic structure that first generates a large set of 6-DOF grasp candidates and then classifies each of them as a good or a bad grasp. Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network. We propose two new representations of grasp candidates, and we quantify the effect of using prior knowledge of two forms: instance or category knowledge of the object to be grasped, and pretraining the network on simulated depth data obtained from idealized CAD models. Our analysis shows that a more informative grasp candidate representation as well as pretraining and prior knowledge significantly improve grasp detection. We evaluate our approach on a Baxter Research Robot and demonstrate an average grasp success rate of 93% in dense clutter. This is a 20% improvement compared to our prior work.

[1]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[4]  Markus Vincze,et al.  Empty the basket - a shape based learning approach for grasping piles of unknown objects , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Markus Vincze,et al.  3DNet: Large-scale object class recognition from CAD models , 2012, 2012 IEEE International Conference on Robotics and Automation.

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

[7]  Alexander Herzog,et al.  Template-based learning of grasp selection , 2012, 2012 IEEE International Conference on Robotics and Automation.

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

[9]  Pieter Abbeel,et al.  Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization , 2013, Robotics: Science and Systems.

[10]  Danica Kragic,et al.  Learning a dictionary of prototypical grasp-predicting parts from grasping experience , 2013, 2013 IEEE International Conference on Robotics and Automation.

[11]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[12]  Pieter Abbeel,et al.  BigBIRD: A large-scale 3D database of object instances , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

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

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

[15]  Robert Platt,et al.  Using Geometry to Detect Grasp Poses in 3D Point Clouds , 2015, ISRR.

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

[17]  Olaf Kähler,et al.  Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices , 2015, IEEE Transactions on Visualization and Computer Graphics.

[18]  Stefan Schaal,et al.  Optimizing for what matters: The top grasp hypothesis , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Ales Leonardis,et al.  One-shot learning and generation of dexterous grasps for novel objects , 2016, Int. J. Robotics Res..

[20]  Abhinav Gupta,et al.  Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).