Underactuated Biomimetic Autonomous Underwater Vehicle for Ecosystem Monitoring

TL;DR

This paper introduces an underactuated biomimetic underwater robot designed for ecosystem monitoring, featuring a fish-like mechanical design and reinforcement learning-based swimming behaviors tested in simulation.

Contribution

It presents a novel mechanical design and reinforcement learning approach for controlling an underactuated biomimetic underwater robot for ecosystem monitoring.

Findings

Successful preliminary mechanical design of tail oscillation mechanism

Simulation of swimming behaviors using FishGym platform

Reinforcement learning techniques proposed for behavior optimization

Abstract

In this paper, we present an underactuated biomimetic underwater robot that is suitable for ecosystem monitoring in both marine and freshwater environments. We present an updated mechanical design for a fish-like robot and propose minimal actuation behaviors learned using reinforcement learning techniques. We present our preliminary mechanical design of the tail oscillation mechanism and illustrate the swimming behaviors on FishGym simulator, where the reinforcement learning techniques will be tested on