ONLINE PREDICTION FOR SAFE HUMAN-ROBOT COLLABORATION: A MODEL OF THE HUMAN ARM

Binchi Jacopo, Mangeruca Leonardo, Rucco Matteo, Orlando Ferrante, Minissale Alfio, Abba Fabio Francesco

2020

With the advent of new technologies and the transition of production to industry 4.0, a more flexible approach to manufacturing is pursued to achieve higher productivity. This transformation leads to overcoming traditional safety procedures and the development of new safety-assuring technologies for the minimization of risks connected with human-robot collaboration. In this work, we focus on the prediction of movements of operators’ upper torso and arms by developing a method which combines data-driven methodologies with formal methods. The approach is based on a predictive model of human motion compared against the planned robot trajectory and online monitoring of satisfaction of safety requirements with formal methods.

                           Read more here.

publications

PRELIMINARY DEVELOPMENT OF THE PSYCHOLOGICAL FACTORS ASSESSMENT FRAMEWORK

Eimontaite Iveta, Fletcher Sarah

17 April 2020

Robots, although not new in manufacturing, are still only just being directly integrated with human operators. Although timely and measured human factors integration in technology development can increase its acceptance, the impacts on manufacturing operators are still largely unknown. The proposed work described in this paper discusses the SHERLOCK project approach to human factors integration that aims to develop a standardised tool for evaluating the impacts of robotics in manufacturing This analysis will enable the development of the framework, which will allow quicker assessment of psychological factors and recommendations for operator needs and requirements in a variety of manufacturing applications.

                                  Read more here.

AN APPROACH FOR MONITORING THE EXECUTION OF HUMAN-BASED ASSEMBLY OPERATIONS USING MACHINE LEARNING

George Andrianakos, Nikos Dimitropoulos, George Michalos, Sotirios Makris

18 February 2020

Sensing systems have been introduced safeguarding the operators, while primitive workflow monitoring systems, primarily based on operator’s feedback, enhance the dynamic behaviour of the system. This paper presents an approach to automatically monitor the execution of human-based assembly operations using vision sensors and machine learning techniques. A reference example based on the assembly of a water pump is showcasing the effectiveness of the proposed approach in real-life application.

                                  Read more here.

2D FEATURES-BASED DETECTOR AND DESCRIPTOR SELECTION SYSTEM FOR HIERARCHICAL RECOGNITION OF INDUSTRIAL PARTS

Ibon Merino, Jon Azpiazu, Anthony Remazeilles, Basilio Sierra

5 December 2019

Detection and description of key points from an image is a well-studied problem in Computer Vision. Some methods like SIFT, SURF or ORB are computationally really efficient. This paper proposes a solution for a particular case study on object recognition of industrial parts based on hierarchical classification. Reducing the number of instances leads to better performance, indeed, that is what the use of the hierarchical classification is looking for.

Read more here.

BOUNDED COLLISION FORCE BY THE SOBOLEV NORM

Kevin Haninger, Dragoljub Surdilovic

12 August 2019

A robot making contact with an environment or human presents potential safety risks, including excessive collision force. Here, the Sobolev norm is adapted to be a system norm, giving rigorous bounds on the maximum force on a stiffness element in a general dynamic system, allowing the study of collision with more accurate models and feedback control.

Read more here.

WHAT DYNAMICS SHOULD IMPEDANCE-CONTROLLED ROBOTS RENDER?

Kevin Haninger, Dragoljub Surdilovic, Arturo Bastidas Cruz

24 May 2019

While impedance control is the standard framework for physically interactive robots, the design choice of what dynamics should be rendered requires additional information (assumptions on environment, in-situ data). The range of dynamics which can be rendered by a robot is informed by its mechatronic design (actuators, physical compliance, inner loop control), and these mechanical design decisions must be made in advance. How can a mechatronic design be evaluated when the system objectives and environment dynamics are not quantified?

Read more here.