Underwater Soft Fin Flapping Motion with Deep Neural Network Based Surrogate Model

TL;DR

This paper introduces a deep neural network-based surrogate model combined with reinforcement learning for precise force control of underwater soft fin robots, enhancing control accuracy and stability in complex environments.

Contribution

It develops a novel DNN surrogate model integrated with RL and grid-switching control for efficient and precise underwater fin actuation.

Findings

RL agent trained in surrogate simulation controls real fins effectively

The approach improves control accuracy in complex underwater conditions

Experimental results validate the method's effectiveness

Abstract

This study presents a novel framework for precise force control of fin-actuated underwater robots by integrating a deep neural network (DNN)-based surrogate model with reinforcement learning (RL). To address the complex interactions with the underwater environment and the high experimental costs, a DNN surrogate model acts as a simulator for enabling efficient training for the RL agent. Additionally, grid-switching control is applied to select optimized models for specific force reference ranges, improving control accuracy and stability. Experimental results show that the RL agent, trained in the surrogate simulation, generates complex thrust motions and achieves precise control of a real soft fin actuator. This approach provides an efficient control solution for fin-actuated robots in challenging underwater environments.