Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization

TL;DR

This paper introduces a data-driven LSTM model trained on experimental hydrodynamic data to accurately predict forces on underwater quadruped robots, enabling optimized gait control and improved swimming performance.

Contribution

The paper develops a novel FED-LSTM model that surpasses traditional empirical formulas in predicting hydrodynamic forces, enhancing underwater quadruped robot gait optimization.

Findings

FED-LSTM outperforms empirical formulas in force prediction accuracy

Model reduces straight-line swimming errors and improves turn times

Hardware tests confirm model's robustness and stability

Abstract

This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FED-LSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater quadruped robot we constructed. Trained on experimental data from leg force and body drag tests conducted in both a recirculating water tank and a towing tank, FED-LSTM outperforms traditional Empirical Formulas (EF) commonly used for flow prediction over flat surfaces. The model demonstrates superior accuracy and adaptability in capturing complex fluid dynamics, particularly in straight-line and turning-gait optimizations via the NSGA-II algorithm. FED-LSTM reduces deflection errors during straight-line swimming and improves turn times without increasing the turning radius. Hardware experiments further validate the model's precision and stability over EF. This approach provides a robust framework for enhancing the swimming performance of legged robots, laying the groundwork for future advances in underwater robotic locomotion.