Grasping Strategies for Picking Items in an Online Shopping Warehouse

The purpose of this study is to investigate the most effective methodologies for the grasping of items in an environment where success, robustness and time of the algorithmic computation and its implementation are key constraints. The study originates from the Amazon Robotics Challenge 2017 (ARC’17) which aims to automate the picking process in online shopping warehouses where the robot has to deal with real world problems of restricted visibility and accessibility. A two-finger and a vacuum grippers were chosen for their practicality and ubiquity in industry. The proposed solution to grasping was retrieval of a final position and orientation of the end effector using an Xbox 360 Kinect sensor information of the object. Antipodal Grasp Identification and Learning (AGILE) and Height Accumulated Features (HAF) feature based methods were chosen for implementation on the two finger gripper due to their ease of applicability, same type of input, and reportedly high success rate. A comparison of these methods was done.

[1]  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.

[2]  Ville Kyrki,et al.  Category-based task specific grasping , 2015, Robotics Auton. Syst..

[3]  Robert Platt,et al.  Using Geometry to Detect Grasps in 3D Point Clouds , 2015, 1501.03100.

[4]  Markus Vincze,et al.  Learning grasps with topographic features , 2015, Int. J. Robotics Res..

[5]  Kuan-Ting Yu,et al.  A Summary of Team MIT's Approach to the Amazon Picking Challenge 2015 , 2016, ArXiv.

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

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

[8]  Oliver Brock,et al.  Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems , 2016, IJCAI.

[9]  Markus Vincze,et al.  Learning grasps for unknown objects in cluttered scenes , 2013, 2013 IEEE International Conference on Robotics and Automation.

[10]  Oussama Khatib,et al.  Grasping with application to an autonomous checkout robot , 2011, 2011 IEEE International Conference on Robotics and Automation.

[11]  Lawson L. S. Wong,et al.  Learning Grasp Strategies with Partial Shape Information , 2008, AAAI.

[12]  Peter K. Allen,et al.  Semantic grasping: planning task-specific stable robotic grasps , 2014, Auton. Robots.

[13]  Danica Kragic,et al.  Task-Based Robot Grasp Planning Using Probabilistic Inference , 2015, IEEE Transactions on Robotics.

[14]  Danica Kragic,et al.  Selection of robot pre-grasps using box-based shape approximation , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Danica Kragic,et al.  From object categories to grasp transfer using probabilistic reasoning , 2012, 2012 IEEE International Conference on Robotics and Automation.

[16]  Henrik I. Christensen,et al.  Automatic grasp planning using shape primitives , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).