A Safe and Energy Efficient Robotic System for Industrial Automatic Tests on Domestic Appliances: Problem Statement and Proof of Concept

Abstract

In this paper, the design and the development of a robotic platform conceived to perform accelerated life tests on a newly manufactured domestic appliances is presented. The proposed system aims at improving the safety of human operators that share the workspace with the robotic platform which is a common scenario of test laboratories. A deep learning algorithm is used for the human detection and pose estimation, while the integration between a conventional motion planning algorithm with a fast 3D collision checker has been implemented as a global planner plugin for the ROS navigation stack. With the twofold objective of improving safety and saving energy in the battery-powered mobile manipulator used in this project, the problem of minimizing the overall kinetic energy is addressed through a properly designed task priority controller, in which the manipulator inertia matrix is used to weight the joint speeds while satisfying multiple robotic tasks according to a hierarchy designed to interact with the appliances while preserving the safety of the human operators. Simulations are carried out to evaluate the overall control architecture and preliminary results indicate the effectiveness of the developed system in the test laboratory floors.