Learning Nuggets for Cobot Education: A Conceptual Framework, Implementation, and Evaluation of Adaptive Learning Content

Abstract

Collaborative robots (cobots) are becoming a significant part of smart factories, due to their potential for collaborative operation, relatively low cost, and high flexibility of use. They are increasingly being deployed in Learning and Teaching Factories, but industrial application still lags behind earlier enthusiastic expectations. Aside from safety issues, educating different user groups is considered one of the main hurdles to increase acceptance by industry. To overcome the educational barrier, a hands-on technology-assisted learning system for robot usage in manufacturing has been created within the European innovation community EIT Manufacturing. It creates modular digital learning content; so-called “learning nuggets” that are complemented with physical on-site exercises and experiences to realize a hybrid cyber-physical learning environment. Technology-assisted learning is a major trend when it comes to teaching complex skills, especially when it pertains to the interaction of humans with complex machinery and information systems. Hence, one of the key elements of the Knowledge and Innovation Community of EIT Manufacturing implemented in 2018 is the establishment of a broad platform for technology-assisted learning. The envisioned online learning platform will enable micro-learning and provides a tailored and flexible learning experience for the user with the goal to realize learning paths that adapt to the individual’s needs, talents, experience, and learning style. This paper presents the underlying conceptual framework for adaptive learning, a portfolio of learning nuggets and their integration into adaptive, stakeholder-specific learning paths. Furthermore, it illustrates the implementation for different cobot/robot platforms as well as a first evaluation of results with respect to user satisfaction.

Keywords: Adaptive Technology Assisted Learning; Collaborative Robots; Hybrid Cyber-Physical Learning Environment; Learning Factory

JEL Classification: I20, I24, L60