Speakers
- Dr. Andreas Zöttl — University of Vienna
- Henry Shum — University of Waterloo
- Yuan-Nan Young
Abstract
Microswimmers consist of different body parts which enable them to deform their shape periodically to move in viscous fluids at low Reynolds number, realized, for example by waving cilia or flagella, or by deforming their entire cell body. Our aim is to understand how microswimmers can change their deformation and swimming gaits based on sensory input from their environment and from their internal state. When coupled to a physical environment a microswimmer cannot just decide where to go, but needs to deform its shape in order to go somewhere. We model the microswimmer decision-making of the sensory-based deformation using reinforcement learning. Using genetic algorithms of evolving artificial neural networks allows us to extract simple decision-making strategies.
Looking for more in the field?
Explore more events from Journal of Engineering Mathematics Seminar Series and Springer Nature's Engineering.