Search for: All records

The introduction of collaborative robots (cobots) into the workplace has presented both opportunities and challenges for those seeking to utilize their functionality. Prior research has shown that despite the capabilities afforded by cobots, there is a disconnect between those capabilities and the applications that they currently are deployed in, partially due to a lack of effective cobot-focused instruction in the field. Experts who work successfully within this collaborative domain could offer insight into the considerations and process they use to more effectively capture this cobot capability. Using an analysis of expert insights in the collaborative interaction design space, we developed a set of Expert Frames based on these insights and integrated these Expert Frames into a new training and programming system that can be used to teach novice operators to think, program, and troubleshoot in ways that experts do. We present our system and case studies that demonstrate how Expert Frames provide novice users with the ability to analyze and learn from complex cobot application scenarios. 

When text datasets are very large, manually coding line by line becomes impractical. As a result, researchers sometimes try to use machine learning algorithms to automatically code text data. One of the most popular algorithms is topic modeling. For a given text dataset, a topic model provides probability distributions of words for a set of “topics” in the data, which researchers then use to interpret meaning of the topics. A topic model also gives each document in the dataset a score for each topic, which can be used as a non-binary coding for what proportion of a topic is in the document. Unfortunately, it is often difficult to interpret what the topics mean in a defensible way, or to validate document topic proportion scores as meaningful codes. In this study, we examine how keywords from codes developed by human experts were distributed in topics generated from topic modeling. The results show that (1) top keywords of a single topic often contain words from multiple human-generated codes; and conversely, (2) words from human-generated codes appear as high-probability keywords in multiple topic. These results explain why directly using topics from topic models as codes is problematic. However, they also imply that topic modeling makes it possible for researchers to discover codes from short word lists. 

Rapid advances in technology also come with increased training needs for people who engineer and interact with these technologies. One such technology is collaborative robots, cobots, which are designed to be safer and easier to use than their traditional robotic counterparts. However, there have been few studies of how people use cobots and even fewer identifying what a user must know to properly set up and effectively use cobots for their manufacturing processes. In this study, we interviewed nine experts in robots and automation in manufacturing settings. We employ a quantitative ethnographic approach to gain qualitative insights into the cultural practices of robotics experts and corroborate these stories with quantitative warrants. Both quantitative and qualitative analyses revealed that experts put safety first when designing and monitoring cobot applications. This study improves our understanding of expert problem-solving in collaborative robotics, defines an expert model that can serve as a basis for the development of an authentic learning technology, and illustrates a useful method for modeling expertise in vocational settings. 

For many outside the profession, teaching looks simple and straightforward; however, for those working in classrooms, it can be a challenging task. In this paper we argue that teaching is a complex profession that requires both novice and expert educators alike to engage students in sets of activities aimed at transforming their understanding of a subject area. This work requires complex planning, enacting instruction, and reflecting on outcomes. In a moment to moment basis teachers must make decisions and iterate on previously made decisions in order to provide effective opportunities for students to engage with the materials, skills or content to be learned. In this paper, we aim to highlight the complexity of the decision-making process and, in doing so we make the argument that individual teachers’ decisionmaking draws upon a personal epistemic frame which includes factors such as skills, knowledge, identity, values, and epistemology. We provide examples of previous research efforts that have attempted to explore such factors and the limitations, both philosophical and methodological shortcomings of such attempts. Finally, we propose that the use of Quantitative Ethnography and Epistemic Frame Theory provides new opportunities to interrogate teachers’ practices and decision-making as a way to better understand the complexity of teacher work. 

Collaborative robots, or cobots, represent a breakthrough technology designed for high-level (e.g., collaborative) interactions between workers and robots with capabilities for flexible deployment in industries such as manufacturing. Understanding how workers and companies use and integrate cobots is important to inform the future design of cobot systems and educational technologies that facilitate effective worker-cobot interaction. Yet, little is known about typical training for collaboration and the application of cobots in manufacturing. To close this gap, we interviewed nine experts in manufacturing about their experience with cobots. Our thematic analysis revealed that, contrary to the envisioned use, experts described most cobot applications as only low-level (e.g., pressing start/stop buttons) interactions with little flexible deployment, and experts felt traditional robotics skills were needed for collaborative and flexible interaction with cobots. We conclude with design recommendations for improved future robots, including programming and interface designs, and educational technologies to support collaborative use.