Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912569895157760 |
|---|---|
| author | Han, Fei Guo, Pengming Chen, Hao Li, Weikun Ren, Jingbo Liu, Naijun Yang, Ning Fan, Dixia |
| author_facet | Han, Fei Guo, Pengming Chen, Hao Li, Weikun Ren, Jingbo Liu, Naijun Yang, Ning Fan, Dixia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03146 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization Han, Fei Guo, Pengming Chen, Hao Li, Weikun Ren, Jingbo Liu, Naijun Yang, Ning Fan, Dixia Robotics Machine Learning 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. |
| title | Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2505.03146 |