Principal Investigator: Bilge Mutlu
CoPrincipal Investigator(s): David Shaffer, Andrew Ruis
Organization: University of Wisconsin-Madison
Abstract:
Collaborative robots are emerging as a new family of advanced technologies that are designed to work side-by-side with people in industrial settings. These robots can improve the productivity and flexibility in manufacturing and logistics industries, while also assisting workers in repetitive, and unhealthy or unsafe work conditions. Unlike traditional factory robots that are programmed and configured by engineers to function independently for long periods of time, collaborative robots require human workers to frequently interact with the robot, including training the robot, making the necessary changes in the environment for the robot to function, and supervising the robot’s work to ensure its successful operation. The integration of collaborative robots into and operation within existing industrial settings require expert skills that many workers lack, and that current educational programs do not cover, highlighting a skills mismatch from the demands of an increasingly automated future of work. This project will develop an understanding of what skills workers will need to perform these tasks effectively and to design a hybrid digital-physical educational technology that will support worker education and training in these skills in classrooms and industrial-training facilities. The research team will evaluate the effects of the technology on skill development among trainees and make recommendations for future job-training programs.
The new hybrid technology will include an expert system computer program that will provide learners with explanations, visualizations, and simulations of key concepts and a robotic assistant that will provide physical demonstrations. This hybrid physical-digital learning environment will be used in expert-led instruction of traditional and non-traditional students in collaborative robotics. The research team will (1) develop an empirical model of expertise in working with collaborative robots through observations of and interviews with experts and analyses of expert-training programs and (2) iteratively design, build, and test a digital-physical hybrid learning environment, integrating an Expert-View Dashboard (EVD), to support expert-led instruction in educational and industrial-training settings. The resulting educational technology will provide educators and trainers with a powerful educational tool that will supplement the development of expertise in working with autonomous, intelligent, and collaborative technologies to meet the demands of an increasingly automated jobs landscape.
This award reflects NSF’s statutory mission and has been deemed worthy of support through evaluation using the Foundation’s intellectual merit and broader impacts review criteria.
