Talk: Extracting Implicit Social Information from the Space Around Us, 12/8

Dr. Claire Liang, MIT CSAIL
12-1 pm ET Monday, December 8
UMBC ITE 406 and online

We already have robots among us. From Coco delivery robots on the streets of Chicago, to a Moxi in a hospital, to airport guide robots around the world, robots in public spaces are becoming a new normal. However, in the real world, we find that these robots fall short, not because they are incapable of their tasks, but because of the complexities of sharing a space with people. Robots that are "more hassle than they're worth" get cast aside. This talk explores how understanding information that lies implicitly in the physical space the same way that humans do results in both social fluency as well as better task performance for embodied agents. Uncovering the secret social information hidden in our shared physical space can create robots that fit in seamlessly and are welcomed rather than tolerated.

Claire Liang is a CSAIL Postdoctoral Fellow in the MIT Interactive Robotics Group, working with Professor Julie Shah. She got her Ph.D. in the Verifiable Robotics Research Group with Professor Hadas Kress-Gazit at Cornell University. Claire works in algorithmic human robot interaction with a focus on lightweight mathematical abstractions of human-intuitive spatial information. She draws from methods in topology and computational geometry, supplying provable guarantees and quantifiable metrics of seemingly immeasurable human and social-spatial information drawn while permitting the removal of typical a priori resource demands. She also approaches systems with an objective of ecological validity-- real world deployability of systems across user groups and collaborative participatory design to ensure true usability in the wild.

Online via WebEx