Speakers

• Prof Alan Tsang — University of Hong Kong
• Henry Shum — University of Waterloo
• Bryan Quaife — Florida State University

Abstract

The recent surge in applying artificial intelligence (AI) to fluid mechanics and navigation problems has demonstrated the tremendous potential of AI in advancing novel designs of smart microrobotics capable of navigating complex fluid environments. In this talk, we will discuss our recent research on the reinforcement learning (RL) of reconfigurable microswimmers in low Reynolds number fluids. We will discuss a set of simple models of reconfigurable microswimmers consisting of spheres with movable arms. We will introduce two reinforcement learning (RL) approaches: one for a fully discrete reconfiguration system and another for a system with continuous variables. We will showcase how RL enables these reconfigurable microswimmers to self-learn how to swim, rotate, and navigate. We will also demonstrate how these microswimmers can learn to develop run-and-tumble navigation strategies akin to biological swimmers, by utilizing information obtained from local environmental cues. These results present a promising approach toward the development of smart microrobotics with autonomous navigation capabilities.

Looking for more in the field?

Explore more events from Journal of Engineering Mathematics Seminar Series and Springer Nature's Engineering.