Due to the fact that automation has transpired to be the order of the day in the manufacturing industry, vocational training for workers functioning beside robots has been highly indispensable.
A research team headed by Fillia Makedon, a Professor in the Department of Computer Science and Engineering at The University of Texas at Arlington, has been awarded a National Science Foundation grant for US$999,638 to create iWork, a smart, robot-based system that evaluates the physical, collaborative and cognitive skills of the workers while carrying out simulated manufacturing operations.
For many years now, the Heracleia Human Centered Computing Laboratory run by Makedon has performed vocational simulation experiments to investigate the ideal techniques for training and preparing workers with or without disabilities for automated production in the future. The workers must be in a position to efficaciously and safely cooperate with state-of-the-art robots.
The experiments are developed such that they perform in real-time analysis of the cognitive skills (e.g. attention and task awareness), and also the cooperative and physical capacities of a worker to work alongside a robot, recognize defects and identify the specific requirements for customized training and/or rehabilitation.
Certain evaluations, for example, determining specific requirements or defects such as agility or vision problems, or carrying out erroneous operations, are automatically ascertained. Yet other evaluations, for example, in case if a worker does not concentrate on the exact place and performs erroneous operations, have to be fed to the computer first to enable it to evaluate the operations done by the worker and subsequently create a profile or conduct pattern that has to be rectified.
In addition to the state-of-the-art computational techniques for determining human capacity, intent and potential, the study is also closely related to manufacturing factories employing robots that hope to minimize the time needed for on-the-job training or retraining of people, and also to avoid accidents at the work spot.
The system employs a modular, closed loop “behavior discovery” data flow that can be readily personalized and includes four phases: assessment, recommendation, intervention and evaluation. At the end of each phase, the system advocates customized interventions for vocational training and rehabilitation, with the help of a human factors specialist.
iWork will assess and train both human workers, as well as robot co-workers as they collaborate, producing personalized, low-cost vocational training solutions that have huge economic and societal impacts and affect many economic sectors. Most importantly, it could impact millions of people seeking to retrain for a manufacturing job, including those facing a type of learning or aging disability or returning from military service with some health issues.
Fillia Makedon, Professor in the Department of Computer Science and Engineering, The University of Texas at Arlington
The latest grant is a direct continuation of Makedon’s earlier supported NSF grants, including two Major Research Instrumentation Program grants, a cyberphysical systems grant and a new large cyberhuman systems grant for investigating physical, cognitive and collaborative skills.
Vassilis Athitsos, an Associate Professor at the Department of Computer Science and Engineering in UTA, Morris Bell, a Yale University Psychology Expert, and Nicolette Hass, a Vocational Expert in the Psychology Department in UTA, were the members of Makedon’s team.
Furthermore, three industry partners will contribute in different ways:
- C8Sciences, an educational firm, will assess the system in relation to training of young adults.
- SoftBank Robotics will host the technical expertise for using a humanoid robot.
- InteraXon will supply hardware and software for improving system functionality for monitoring brain activity.
According to Duane Dimos, UTA Vice President for research, projects carried out by Makedon are pushing forward the insights into human-robot interaction.
“These projects are advancing knowledge in human-robot interactions that will lead to training improvements for workers, including those with minor disabilities, to interact effectively and safely with robots, which will boost the manufacturing industry’s ability to hire employees and be sure their training is adequate,” stated Dimos.
According to Hong Jiang, Wendell H. Nedderman Professor and Chair of the Computer Science and Engineering Department, the study points toward UTA’s advancing research competence in data-driven inventions under the University’s Strategic Plan 2020: Bold Solutions | Global Impact.
Professor Makedon has created an outstanding research effort in human-machine performance and machine learning at UTA.
Hong Jiang, Wendell H. Nedderman Professor and Chair of the Computer Science and Engineering Department