Abstract

As robots begin to enter our schools, workplaces, and homes, it is important that people are able to interact with them in a way that is comfortable and natural to them. Eventually this might be via natural language dialogue, but given the complexities of language that may be not be available for awhile. In the meantime, another approach is to allow people to communicate with robots using non-verbal communication, such as gestures and facial expressions. In addition to ensuring robots are capable of accurately sensing and interpreting human non-verbal cues, it is important humans are able to accurately understand the cues robots make.

This talk will describe several experiments we have conducted using humanoid and android robots which explore various aspects of this problem, including both how to synthesize human-like communicative cues on robots and how humans perceive such synthesis. I will also describe new research we are conducting on using robots as simulated patients, to be used in clinical communication training contexts. In particular, we are interested in teaching clinicians to be more patient when interacting with people with disorders that cause them to have delayed speech (e.g., dystonia, cerebral palsy), as well as people with disorders that may require unique interaction strategies (e.g., schizophrenia, autism spectrum disorder).