Applying a learning framework for improving success rates in industrial bin picking

In this paper, we present what appears to be the first studies of how to apply learning methods for improving the grasp success probability in industrial bin picking. Our study comprises experiments with both a pneumatic parallel gripper and a suction cup. The baseline is a prioritized list of grasps that have been chosen manually by an experienced engineer. We discuss generally the probability space for success probability in bin picking and we provide suggestions for robust success probability estimates for difference sizes of experimental sets. By performing grasps equivalent to one or two days in production, we show that the success probabilities can be significantly improved by the proposed learning procedure.

[1]  Dmitry Berenson,et al.  Grasp planning in complex scenes , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[2]  Paul F. Whelan,et al.  A bin picking system based on depth from defocus , 2003, Machine Vision and Applications.

[3]  Thomas B. Moeslund,et al.  Bin-Picking based on Harmonic Shape Contexts and Graph-Based Matching , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[4]  Arun K. Sood,et al.  Range image segmentation combining edge-detection and region-growing techniques with applications sto robot bin-picking using vacuum gripper , 1990, IEEE Trans. Syst. Man Cybern..

[5]  Henrik Gordon Petersen,et al.  Motion planning efficient trajectories for industrial bin-picking , 2013, Int. J. Robotics Res..

[6]  Raúl Suárez Feijóo,et al.  Grasp quality measures , 2006 .

[7]  Peter K. Allen,et al.  Data-driven grasping , 2011, Auton. Robots.

[8]  Jing Xiao,et al.  Efficient and effective grasping of novel objects through learning and adapting a knowledge base , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Ole Madsen,et al.  Identifying and evaluating suitable tasks for autonomous industrial mobile manipulators (AIMM) , 2012 .

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

[11]  E. K. Bowen,et al.  Basic Statistics for Business and Economics , 1982 .

[12]  J. Devore,et al.  Applied statistics for engineers and scientists , 1994 .

[13]  Aiqiu Zuo,et al.  A Hybrid Stereo Feature Matching Algorithm For Stereo Vision-Based Bin Picking , 2004, Int. J. Pattern Recognit. Artif. Intell..

[14]  Tamim Asfour,et al.  Integrated Grasp Planning and Visual Object Localization For a Humanoid Robot with Five-Fingered Hands , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Jimmy A. Jørgensen,et al.  Grasp Synthesis for Dextrous Hands Optimised for Tactile Manipulation , 2010, ISR/ROBOTIK.

[16]  Matei T. Ciocarlie,et al.  Data-driven grasping with partial sensor data , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Feng Gao,et al.  Evaluating the quality of grasp configurations for dextrous hands , 1997, Proceedings of International Conference on Robotics and Automation.

[18]  Diane K. Michelson,et al.  Applied Statistics for Engineers and Scientists , 2001, Technometrics.

[19]  Stefan Schaal,et al.  Learning to grasp under uncertainty , 2011, 2011 IEEE International Conference on Robotics and Automation.

[20]  Oliver Kroemer,et al.  Learning grasp affordance densities , 2011, Paladyn J. Behav. Robotics.