Discovering Survival Hydrodynamics through Stochastic Optimization and Learning
We seek to understand the interplay of hydrodynamics and behavioural traits in single and multiple swimmers. To this effect we perform simulations using a hierarchy of swimmer models, ranging from simple dipoles to fully resolved incompressible viscous flows, of self propelled 3D fish-like bodies. The simulations are coupled with stochastic optimisation algorithms to investigate responses such as escape and predation patterns by single swimmers.The interplay of hydrodynamics and behavioural traits is investigated for collective swimmers using reinforcement learning algorithms. I will discuss our findings in relation to observations in natural swimmers and outline some lessons learned that may serve as inspiration for engineering devices