In automatic picking by robot, it is the important to estimate the grasping parameters (grasping position, direction and angle) of the object. In this paper, we propose a method for approximating an object with primitive shape in order to estimate the grasping parameters. The basic idea of this research is to approximate the object by object primitive (hexahedron/cylinder/sphere), based on the object's surface. First, we classify the surface shape that constitutes the object using 3D-Deep Neural Network. Then, we approximate the object with object primitive using the recognition result of 3D-DNN. After that, we estimate the grasping parameters based on preset grasping rules. The success rate of approximating the object primitive with our method was 94.7%. This result is 6.7% higher than the 3D ShapeNets using 3D-DNN. Also, as an experimental result of grasping simulation using Gazebo, the success rate of grasping with our method was 85.6%.
Takuya Torii, Manabu Hashimoto, "Reliable Primitive Approximation for Estimation of Robot Grasping Parameters Using 3D-DNN" in Proc. IS&T Int’l. Symp. on Electronic Imaging: Intelligent Robotics and Industrial Applications using Computer Vision, 2018, pp 301-1 - 301-6, https://doi.org/10.2352/ISSN.2470-1173.2018.09.IRIACV-301