Construction of a Smart Vision-Guided Robot System for Manipulation in a Dynamic Environment

摘要

This article outlines the construction of universal, user-friendly smart robot system for manipulation in a dynamic environment through AI-based vision system which incorporates processing on the edge. To successfully perform complex tasks in changing conditions, robots require both intelligence for adaptive decision-making and the ability to accurately perceive the environment and interface with it. The proposed system is built in a way that maximizes the modularity of the system. And thus, improves the ease at which the system can be modified to other specific goals after it has been operationalized. In this work, these characteristics are achieved by the use of synthetically generated data and Robot Operating System (ROS) as a middleware software. The first results prove the feasibility of training object detection networks on synthetically generated data sets. And also a combination of a 3D camera and industrial robot provides a convenient way for adding new objects to the database.