Real-time position and pose prediction for a self-propelled undulatory swimmer in 3D space with artificial lateral line system.
Bioinspir Biomim
; 19(4)2024 Jun 05.
Article
em En
| MEDLINE
| ID: mdl-38722349
ABSTRACT
This study aims to investigate the feasibility of using an artificial lateral line (ALL) system for predicting the real-time position and pose of an undulating swimmer with Carangiform swimming patterns. We established a 3D computational fluid dynamics simulation to replicate the swimming dynamics of a freely swimming mackerel under various motion parameters, calculating the corresponding pressure fields. Using the simulated lateral line data, we trained an artificial neural network to predict the centroid coordinates and orientation of the swimmer. A comprehensive analysis was further conducted to explore the impact of sensor quantity, distribution, noise amplitude and sampling intervals of the ALL array on predicting performance. Additionally, to quantitatively assess the reliability of the localization network, we trained another neural network to evaluate error magnitudes for different input signals. These findings provide valuable insights for guiding future research on mutual sensing and schooling in underwater robotic fish.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Natação
/
Simulação por Computador
/
Redes Neurais de Computação
/
Sistema da Linha Lateral
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article