Talking Robotics


Organizers: Patrícia Alves-Oliveira, Silvia Tulli, Miguel Vasco, Joana Campos — contact us: talkingrobotics at gmail dot com, twitter, youtube


David Porfirio is a fifth-year PhD student at the University of Wisconsin–Madison. His interests lie in designing and investigating human-robot interaction authoring tools that make the process of programming social robots easy and approachable for experts and non-experts alike. To achieve this goal, his work spans using programming languages techniques such as formal verification to assist interaction designers’ reason about interaction social norms, program synthesis to assist designers in implementing these interactions, and program repair to automatically fix these interactions.

Speaker Links: Website - Github - Google Scholar


Robots serve as interaction partners to humans in the workplace, at home, and for leisure activities, but designing social human-robot interactions is non-trivial. Challenges arise from the need to create interaction experiences that are successful with respect to both task and social outcomes. First, interaction designers must manipulate a robot’s individual interaction modalities, such as speech and locomotion, to produce social behaviors. Utilizing the robot’s sensory input to design the interaction logic and produce a natural interaction flow increases the burden on designers. Furthermore, the success of a human-robot interaction is defined by variable criteria, depending on the norms, constraints, and user preferences of the interaction context. High variability between different interaction contexts may cause an interaction that is successful in one context to fail in a different context. The focus of my research is on how human-robot interaction authoring tools can mitigate these challenges. Specifically, I seek to answer how authoring tools can support designers in creating robust interaction designs by (1) filling in gaps in designer knowledge and expertise and (2) eliciting knowledge already possessed by the designer and assisting with the integration of this knowledge into interaction designs. In this talk, I will discuss the research threads that I have investigated and my plans for future work.

Papers covered during the talk