Development of the intelligent software and hardware subsystem for capturing an object by robot manipulator

Abstract

In this paper, it is shown that based on an analysis of the implemented functions of existing robot manipulators the task of automation of the safe capture of objects by a robot during the assembly process is poorly developed. In the process of analysis, there were discovered technological solutions to three main tasks for the development of a subsystem for capturing objects by a robotic manipulator: determination of the dimensions and shape of the capturing object; determination of the distance from the robot manipulator to all the points of the capturing object, determination of the capture point of the object and clarification of the distance to the robot manipulator. It is shown that all of the above tasks are not sufficiently solved. Therefore, it was proposed to develop a methodology for creating an intelligent software and hardware subsystem for capturing an object by robot manipulator. The developed methodology consists of six steps: obtaining a stereo image and building an in-depth map; determination of the distance from the robot manipulator to all the points of the object; determination of the contour of the object; determination of the capture point of the object and clarification of the distance to the robot manipulator; determination of the degree of capturing the object; determination of the movement of the manipulator to capture an object at the desired point. To find the capture point, it is proposed to use the contour search method on the object’s depth map, and to search for the finest part on the contour, limit it to a segment and find its middle point. To implement the algorithm for determination of the distance to the object, the degree of its capture and movement to the desired point, the dependencies of the calculations on the depth map and the physical characteristics of the manipulator are formalized. The capabilities of the StereoPi microprocessor are analyzed and its use for the hardware solution of the capture function by the robotic arm is proposed. The simulation of the intelligent software and hardware subsystem for capturing an object of complex shape has been performed. Conclusions are drawn about the independence of the developed subsystem from the type of object and its viewing angle by a robot manipulator. In addition, an increase in the accuracy of capturing the object by a robot manipulator equipped with an intelligent subsystem is shown in comparison with its existing analog. Potential problems in the implementation of the proposed methodology are highlighted.