Malte Jung

Crowdsourcing human-robot interaction: new methods and system evaluation in a public environment

Supporting a wide variety of interaction styles across a diverse set of people is a significant challenge in human-robot interaction (HRI). In this work, we explore a data-driven approach that relies on crowdsourcing as a rich source of interactions that cover a wide repertoire of human behavior. We first develop an online game that requires two players to collaborate to solve a task. One player takes the role of a robot avatar and the other a human avatar, each with a different set of capabilities that must be coordinated to overcome challenges and complete the task. Leveraging the interaction data recorded in the online game, we present a novel technique for data-driven behavior generation using case-based planning for a real robot. We compare the resulting autonomous robot behavior against a Wizard of Oz base case condition in a real-world reproduction of the online game that was conducted at the Boston Museum of Science. Results of a post-study survey of participants indicate that the autonomous robot behavior matched the performance of the human-operated robot in several important measures. We examined video recordings of the real-world game to draw additional insights as to how the novice participants attempted to interact with the robot in a loosely structured collaborative task. We discovered that many of the collaborative interactions were generated in the moment and were driven by interpersonal dynamics, not necessarily by the task design. We explored using bids analysis as a meaningful construct to tap into affective qualities of HRI. An important lesson from this work is that in loosely structured collaborative tasks, robots need to be skillful in handling these in-the-moment interpersonal dynamics, as these dynamics have an important impact on the affective quality of the interaction for people. How such interactions dovetail with more task-oriented policies is an important area for future work, as we anticipate such interactions becoming commonplace in situations where personal robots perform loosely structured tasks in interaction with people in human living spaces.

A Structure for Design Theory

The field of engineering design research is being pulled into two opposing directions—toward scientific rigor on one hand, and a greater relevance for professional practice on the other. The development of design theories in the field reflects this dichotomy. We have formal design theories deriving from mathematical roots that rarely influence the practice. And we have a plethora of process models that serve as scaffolds for professional designing, but lack scientific validity. Can we create design theory that resolves this dichotomy and displays scientific rigor while being useful to professionals? In this chapter, we propose a structure for design theory that attempts to answer this question. Building on the structure of scientific theory from philosophy of science and the perception–action perspective from ethnographic research, we suggest a two-dimensional structure for design theory. The first dimension describes the theoretical constructs and relationships between them, and the second dimension provides the perceptual field and action repertoire that makes a theory relevant in situations of professional practice. We explain these two dimensions of design theory, while focusing on the second perception–action dimension that is our contribution to design research. We illustrate this by developing the perception–action dimension of C-K theory.

Emotion in Engineering Design Teams

Knowledge that is relevant to the practice of engineering can be categorized into three domains. First is the knowledge of the natural world that we fashion into engineering artifacts. This includes knowledge domains such as physics, chemistry, biology, and thermodynamics. Second is the knowledge of processes that we may use to transform the natural world into engineered artifacts. These include various engineering design methods, production processes, and mathematical methods. The third is the knowledge of the humans creating and using the engineering artifacts. This involves understanding and improving how engineers perceive, think, and act individually or collectively, such as in teams or organizations, when they are engaged in the daily practice of engineering; and also understanding how the users of these artifacts perceive and interact with them in the course of their life cycle. This domain uses and synthesizes knowledge from other fields such as psychology, group work, cognitive science, sociology, and anthropology that focus on the human as a subject of study. However, it differs in one key respect from these fields in that its focus on the human is rooted in an engineering value system that seeks to understand in order to re-create artifacts and situations for the better. The study of emotion is an important part of the domain of humans creating and using engineering artifacts.

Monitoring Design Thinking Through In-Situ Interventions

Building on existing knowledge of design and design thinking we apply several other fields of knowledge such as emotion coding, improvisation, ethnography, social psychology, and decision analysis into key metrics we call Design Thinking Metrics (DTM). We applied these metrics to analyze and assess videos of software design teams. We then conducted a workshop series with a professional software design team to use DTM as a perceptual tool to test a number of action-repertoires and building theory that could be used to improve Design Thinking practice. The result is multi-disciplinary perceptual monitoring of design thinking activity in professional software practice.

A Conceptual Framework for Understanding the Impact of Digital Libraries on Engineering Design Learning

Engineering design is an information intensive activity. Right from need finding to final prototyping, designers are constantly acquiring, assimilating, transforming and giving out information. In fact in a design process, designers act as autonomous learners actively seeking and processing information. However, the mechanism by which information influences design learning is not well understood. This paper presents a conceptual framework for studying the impact of information resources on design learning based on a survey conducted on engineering students participating in a two-week long global collaborative design exercise to build bicycles out of paper materials.Copyright

ConExSIR: A Dialogue-based Framework of Design Team Thinking and Discovery

Summary. This research presents a dialog-based framework of design team thinking and discovery that synthesizes an inquiry-based design thinking model and a con-ceptual-exploration process model. The framework is applied in order to code the dialog acts of teams engaged in conceptual design activity, and measure designteam processes related to generating design alternatives and making decisions. Preliminary results highlight relationships between the two models, and support the tentative conclusion that team performance on a conceptual design task is positively correlated with the frequency of a dialogue act termed, “limit-handling.” Remaining challenges include fully integrating and validating prior models and validating dialogue facilitation techniques to support conceptual design, decision analysis, and risk analysis.