Modelling of Underwater Vehicles using Physics-Informed Neural Networks with Control
By: Abdelhakim Amer , David Felsager , Yury Brodskiy and more
Potential Business Impact:
Helps underwater robots learn to move better.
Physics-informed neural networks (PINNs) integrate physical laws with data-driven models to improve generalization and sample efficiency. This work introduces an open-source implementation of the Physics-Informed Neural Network with Control (PINC) framework, designed to model the dynamics of an underwater vehicle. Using initial states, control actions, and time inputs, PINC extends PINNs to enable physically consistent transitions beyond the training domain. Various PINC configurations are tested, including differing loss functions, gradient-weighting schemes, and hyperparameters. Validation on a simulated underwater vehicle demonstrates more accurate long-horizon predictions compared to a non-physics-informed baseline
Similar Papers
Physics-Informed Neural Network Modeling of Vehicle Collision Dynamics in Precision Immobilization Technique Maneuvers
Systems and Control
Predicts car crashes better and faster.
Physics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations
Machine Learning (CS)
Teaches computers to control fluid flow using physics.
Physics-Informed Neural Networks for Vessel Trajectory Prediction: Learning Time-Discretized Kinematic Dynamics via Finite Differences
Machine Learning (CS)
Predicts ship paths more accurately, even with bad data.