978-1-7281-3558-8/19/$31.00 ©2019 IEEE Autonomous 4DOF Robotic Manipulator Prototype for Industrial Environment and Human Cooperation Inês Garcia Industrial Electronics Dept University of Minho Guimarães, Portugal A70557@alunos.uminho.pt Fernando Gonçalves Mechanical Engineering Dept. University of Minho Guimarães, Portugal A70569@alunos.uminho.pt Tiago Ribeiro Industrial Electronics Dept. University of Minho Guimarães, Portugal A71157@alunos.uminho.pt Pedro Fernandes Industrial Electronics Dept University of Minho Guimarães, Portugal A68385@alunos.uminho.pt César Rocha Mechanical Engineering Dept. University of Minho Guimarães, Portugal A72264@alunos.uminho.pt Ricardo Boucinha Mechanical Engineering Dept. University of Minho Guimarães, Portugal A71482@alunos.uminho.pt Gil Lopes Industrial Electronics Dept ALGORITMI Center University of Minho Guimarães, Portugal gil@dei.uminho.pt A. Fernando Ribeiro Industrial Electronics Dept ALGORITMI Center University of Minho Guimarães, Portugal fernando@dei.uminho.pt Abstract— This paper describes the design and development of an autonomous robotic manipulator with four degrees of freedom. The manipulator is named RACHIE - "Robotic Arm for Collaboration with Humans in Industrial Environment". The idea was to create a smaller version of the industrial manipulators available on the market. The mechanical and electronic components are presented as well as the software algorithms implemented on the robot. The manipulator has as its primary goal the detection and organization of cans by color and defects. The robot can detect a human operator so it can deliver defective cans by collaborating with him/her on an industrial environment. To be able to perform such task, the robot has implemented a machine learning algorithm, a Haar feature-based cascade classifier, on its vision system to detect cans and humans. On the handler motion, direct and inverse kinematics were calculated and implemented, and its equations are described in this paper. This robot presents high reliability and robustness in the task assigned. It is low-cost as it is a small version of commercial ones, making it optimized for smaller tasks. Keywords—Handler, Robotic Manipulator, 4 DOF, Machine Learning, can detection, human cooperation, human detection, image processing, kinematics. I. INTRODUCTION Nowadays, the world of industrial and service robots is in continuous expansion. Increasingly, the implementation of robotic manipulators in an industrial environment is essential, both for the sake of reducing hazards of heavy jobs and increasing the manufacturing efficiency. Furthermore, the worldwide competition "RoboCup" has boosted the deployment of service robots in other environments, such as rescuing people from disasters to home chores in house environments, with the "RoboCup @Home" competition. However, one of the significant challenges of industrial robots and services is object manipulation. This paper describes an articulated autonomous robotic manipulator with four rotational degrees of freedom (DOF), developed by a group of students from Industrial Electronics and Computer Engineering as well as Mechanical Engineering. This robot is intended to be a small and low-cost manipulator, compared to the ones available on the market and it was designed for an industrial environment. The developed handler is called "RACHIE", which stands for "Robotic Arm for Collaboration with Humans in Industrial Environment", presented in Fig. 1. This paper focuses on the development of all the robot’s different systems. Thus, it is divided into five main sections, namely introduction, methodology, results, discussion, and conclusions. A. Goal Task In a preliminary phase, the following purpose was established for the robot: detection and transportation of cans of different colors, as well as their organization in their respective places around them. Another goal is the recognition of defective cans based on shape and color. The defective cans will be stored for later human intervention or handed over to the operator to analyze the problem and put them back on the shelf (Fig. 2). For the objects and human detection, the robot has a vision and image processing system as the external sensor of the manipulator, which uses machine learning. Therefore, this paper presents the mechanical design and structure; the implementation of actuators and sensors inside the various joints of the robot; the sizing and implementation of all the electronic Fig. 1. Picture of RACHIE, holding a can.