Presenter: Christoforos Mavrogiannis ([ Ссылка ])
Title: Leveraging structure for autonomous robot navigation in
multiagent human spaces
Abstract: Pedestrian scenes pose great challenges for robots due to
the lack of formal rules regulating traffic and the lack of explicit
coordination among navigating agents. However, humans navigate with
ease and comfort through a variety of complex multiagent domains,
such as busy train stations, crowded malls or academic buildings.
Human effectiveness in such domains can be largely attributed to
cooperation which introduces structure to multiagent behavior. In
this talk, I will discuss how we can uncover this structure through
the use of representations from low-dimensional topology. I will
describe how these representations can be used to build prediction
and planning algorithms for socially compliant navigation in
pedestrian domains and show how their machinery may transfer to other
challenging environments such as uncontrolled street intersections.
Finally, I will discuss how the lessons learned from these
applications inform ongoing efforts on deploying robots in real-world
pedestrian spaces.
Bio: Christoforos Mavrogiannis is a postdoctoral research associate
in the Paul G. Allen School of Computer Science & Engineering at the
University of Washington, working with Prof. Siddhartha Srinivasa.
His interests lie at the intersection of motion planning, multiagent
systems, and algorithmic human-robot interaction, and he often draws
tools from topology, motion planning, and machine learning. Chris has
been a best paper award finalist at the ACM/IEEE International
Conference on Human-Robot Interaction (HRI) and selected as an HRI
and RSS Pioneer. He has also been an active proponent of open-source
design, leading initiatives such as MuSHR and Openbionics. He holds
MS and PhD degrees from Cornell University, and a Diploma in
mechanical engineering from the National Technical University of Athens.
Organized by the Intelligent Systems Lab at TU Berlin ([ Ссылка ]).
Moderated by Andreas Orthey ([ Ссылка ], [ Ссылка ]) and Marc Toussaint ([ Ссылка ]). Find us on twitter at [ Ссылка ].
