Researchers from Santa Clara University, New Jersey Institute of Technology, and the University of Hong Kong have been able to successfully teach micro-robots how to swim via deep reinforcement learning, marking a substantial leap in the progression of micro-swimming capability.
According to the team, the micro-swimmers could learn — and adapt to changing conditions — through AI. Much like humans learning to swim require reinforcement learning and feedback to stay afloat and propel in various directions under changing conditions, so too must micro-swimmers, though with their unique set of challenges imposed by physics in the microscopic world.
By combining artificial neural networks with reinforcement learning, the team successfully taught a simple micros-swimmer to swim and navigate toward any arbitrary direction. When the swimmer moves in certain ways, it receives feedback on how good the particular action is. The swimmer then progressively learns how to swim based on its experiences interacting with the surrounding environment.
The AI-powered swimmer can switch between different locomotory gaits adaptively to navigate toward any target location on its own.
As a demonstration of the powerful ability of the swimmer, the researchers showed that it could follow a complex path without being explicitly programmed. They also demonstrated the robust performance of the swimmer in navigating under the perturbations arising from external fluid flows.
This is the first step in tackling the challenge of developing micro-swimmers that can adapt like biological cells in navigating complex environments autonomously, according to the team. Such adaptive behaviors are crucial for future biomedical applications of artificial micro-swimmers in complex media with uncontrolled and unpredictable environmental factors.