Zsolt Kira

Biography

Zsolt Kira received his Ph.D. in 2010 from the Georgia Institute of Technology. He is interested in developing perception and machine learning algorithms for robotics, currently focusing on the two important areas described below. He has published multiple first-author publications in the robotics community, received several awards such as the best robotics paper award at AAMAS 2010, and has been invited to speak about his research at venues such as the Cognitive Vision Workshop at IROS 2009 and the 2010 SPIE invited session on Information Fusion and Cognitive Robotics. He is a member of ACM, IEEE, and IEEE Robotics and Automation Society.

Research Interests

Human-Robot Interaction: As robots become increasingly common, they will have to interact with humans in everyday environments. There overall question I am interested in is: How can robots perceive the outcome of such interactions with humans? Towards this end, I am interested in perception algorithms capable of accurately detecting social cues (e.g. facial expressions, body language) of the person that the robot is interacting with to estimate the person’s outcome from that interaction, i.e. whether it was a positive experience or not. I am also interested in how human operators can use these same natural gestures to control many robots at once, especially when the multi-robot system is a distributed swarm.

Robot-Robot Interaction: I am interested in how heterogeneous robots with different modalities can coordinate, communicate, and share knowledge. My dissertation made progress in showing how robots can teach each other, allowing the use of one robot's experiences to speed up learning on another robot (transfer learning). This work showed the applicability of information theoretic metrics to allow robots that differ perceptually to build models of their similarities and differences to facilitate such knowledge sharing. I plan to continue this line of research and explore information theory and statistical methods to allow the fusion of knowledge from multiple robots and modalities.