Learn to Flap: Foil Non-parametric Path Planning via Deep Reinforcement Learning

To optimize flapping foil performance, the application of deep reinforcement learning (DRL) on controlling foil non-parametric motion is conducted in the present study. Traditional control techniques and simplified motions cannot fully model nonlinear, unsteady and high-dimensional foil-vortex interactions. A DRL-training framework based on Proximal Policy Optimization and Transformer architecture is proposed. The policy is initialized from the sinusoidal expert display. We first demonstrate the effectiveness of the proposed DRL-training framework which can optimize foil motion while enhancing foil generated thrust. By adjusting reward setting and action threshold, the DRL-optimized foil trajectories can gain further enhancement compared to sinusoidal motion. Via flow analysis of wake morphology and instantaneous pressure distributions, it is found that the DRL-optimized foil can adaptively adjust the phases between motion and shedding vortices to improve hydrodynamic performance. Our results give a hint for solving complex fluid manipulation problems through DRL method.