A machine learning-based visual servoing approach for fast robot control in industrial setting

Abstract

Industry 4.0 aims to make collaborative robotics accessible and effective inside factories. Human–robot interaction is enhanced by means of advanced perception systems which allow a flexible and reliable production. We are one of the contenders of a challenge with the intent of improve cooperation in industry. Within this competition, we developed a novel visual servoing system, based on a machine learning technique, for the automation of the winding of copper wire during the production of electric motors. Image-based visual servoing systems are often limited by the speed of the image processing module that runs at a frequency on the order of magnitude lower with respect to the robot control speed. In this article, a solution to this problem is proposed: the visual servoing function is synthesized using the Gaussian mixture model (GMM) machine learning system, which guarantees an extremely fast response. Issues related to data size reduction and collection of the data set needed to properly train the learner are discussed, and the performance of the proposed method is compared against the standard visual servoing algorithm used for training the GMM. The system has been developed and tested for a path following application on an aluminium bar to simulate the real stator teeth of a generic electric motor. Experimental results demonstrate that the proposed method is able to reproduce the visual servoing function with a minimal error while guaranteeing extremely high working frequency

Optimized hybrid decoupled visual servoing with supervised learning

“…recurrent neural network (RNN), convolution neural network (CNN), reinforcement learning (RL) and extreme learning machine (ELM)) are widely used to tackle vision tracking problems which are difficult or computationally expensive to solve by classical control methods, such as singularity avoidance, local minima or complex computation of pseudo-inverse. [19][20][21] Supervised learning approaches contribute to estimating the data output from previous experiences; therefore, the data set must be labelled in advance. However, unsupervised learning approaches find unknown patterns in a set of data.…”

The Investigation of Motor Production Test Indicators in Qualitative Research Methods

“…In addition, cost planning also has great advantages. Manufacturing costs include tool costs, machine costs, and labor costs [31]. A study analyzes the cost of the stamping machine when manufacturing the motor stator.…”

Controle NMPC para o Seguimento de Caminhos Visuais com Velocidade de Navegação Variável

“…Partindo dos esquemas clássicos de controle servo-visual PBVS (Position Based Visual Servoing) e IBVS (Image Based Visual Servoing), até as abordagens mais atuais, como as baseadas em aprendizado de máquina (Castelli et al (2017)), existe ampla variedade de soluções para robôs manipuladores, especialmente em ambientes industriais (Ibarguren et al (2014); Chang et al (2017); Muñoz-Benavent et al (2019)). No campo da robótica móvel, existe um interesse crescente em estratégias de controle baseadas em visão, como por exemplo na indústria au-tomotiva, através de projetos classificados como ITS (Intelligent Transportation Systems) (Kim (2008)) e ADAS (Advanced Driver Assistance) (Kuo et al (2011)).…”