Talk: Designing Emotionally-Intelligent Robots: Modeling Human Affect, Interactions, and Collaborations

Abstract:
Recent advances in Robotic perception technologies are gradually enabling humans and robots to co-exist, co-work, and share spaces in different environments. Robots are increasingly required to navigate in socially-acceptable yet collision-free paths in a crowd in places such as campuses, airports, and shopping malls; to interact and understand people in their homes, workplaces, and hospitals; and to share responsibility for completing tasks, meaning that robots are becoming social partners and teammates with humans. In the future, these socially intelligent robots will likely enter almost all human domains, including healthcare facilities, factories, airports, warehouses, schools, etc.

Designing and building robots that can communicate and connect with people is necessary but not sufficient. Knowing the perceived affective states and social-psychological constructs (such as behavior, emotions, psychology, motivations, and beliefs) of humans in such scenarios allows the robot to make more informed decisions and navigate and interact in a socially-aware manner.  For robots to better function better as teammates, collaborators, and one-day family members, they must be able to better detect and predict human psychology.

In this talk, I will focus on our work on emotionally-aware robot navigation and interaction. In particular, I will present our efficient robotic perception systems for learning emotions, trust, and intentions by combining and collate information from the various modalities by which humans express emotion. These modalities include, but are not limited to, facial expressions, speech and voice modulations, written text, body postures, gestures, and walking styles. Finally, I will touch on how these new prediction technologies help address a variety of research problems, including applications in healthcare and understanding driver behaviors for autonomous vehicles.

Bio:
Dr. Aniket Bera is an Assistant Research Professor in the Department of Computer Science with joint/affiliated appointments with the Maryland Robotics Center, Maryland Transportation Institute, and the Brain and Behavior Institute. Prior to this, he was a Research Assistant Professor at the University of North Carolina at Chapel Hill, where he also received his Ph.D. in 2017 and was advised by Dr. Dinesh Manocha. His core research interests are in Social Robotics and Affective Computing. He is a faculty with the GAMMA group and has advised and co-advised over 20 MS and Ph.D. students. He has authored over 50 papers, and his work has won multiple awards. He also works with the University of Maryland Medical School in Baltimore on multiple projects to build social robot-based therapy systems to help patients with mental disorders and training systems for therapists. His research involves novel combinations of methods and collaborations in affective computing, computational psychology, and machine learning to develop real-time computational models. Dr. Bera has previously worked in many research labs, including Disney Research and Intel Labs, and his work has been featured in many media outlets, including Forbes, WIRED, FastCompany, etc. A more detailed description can be found at http://cs.umd.edu/~ab