ROBOTICS ENGINEERING COLLOQUIUM SERIES
Dr. Heiko Hamann
University of Lübeck, Germany
Minimize Surprise in Robots: An Innate Motivation for Collective Behavior
Friday, October 30, 2020
12:00 pm – 1:00 pm
Zoom: https://wpi.zoom.us/j/95199105857 (sign-in required)
Abstract: After a quick overview of other related research projects in my lab (bio-hybrid systems, swarm performance, collective decision-making), I will present our work on minimize surprise for multi-robot systems. Each robot has two artificial neural networks, a world model (“prediction machine”) and a behavioral module ("action selection network”), that are trained concurrently. There is no predefined task, instead the swarm is rewarded for making correct predictions about future sensory input. As an effect, robots discover behaviors introducing predictable spatiotemporal sensor patterns. I will present simulated results for flocking, aggregation, self-assembly, construction, and first results using real-world mobile robots.
Bio: Since 2017 Heiko Hamann is professor for service robotics at the University of Lübeck, Germany. He coordinated the EU-funded project flora robotica that develops and investigates closely linked symbiotic relationships between robots and natural plants to explore the potentials of a plant-robot society able to produce architectural artifacts and living spaces. His main research interests are swarm robotics and evolutionary robotics, especially collective decision-making and the emergence of swarm behaviors triggered by intrinsic motivation. He was assistant professor at the University of Paderborn, Germany and did his postdoctoral training at the Zoology department of the University of Graz, Austria.
since 2017 Professor, University of Lübeck, Germany
2013-2017 Professor, University of Paderborn, Germany
2009-2012 Postdoc, Karl-Franzens University Graz, Austria
2008 PhD in engineering, University of Karlsruhe, Germany
Discord server for discussion: join the #colloquium-discussion channel at https://discord.gg/aKgQqM4
Watch previous seminars: https://web.microsoftstream.com/channel/9b24549c-4cd4-4c7f-b7d4-0d8d1ccb7781