# 3D Underwater Path Planning via Generative Flow Field Surrogates

arXiv: https://arxiv.org/abs/2606.06077 · HTML: https://mlsanity.com/paper/2606.06077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Characterizing possible failure modes in physics-informed neural networks](https://mlsanity.com/paper/2109.01050/) (2021)
- [Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations](https://mlsanity.com/paper/1811.02033/) (2018)
- [Controllable Generative Adversarial Network](https://mlsanity.com/paper/1708.00598/) (2017)
- [Multi-goal path planning using multiple random trees](https://mlsanity.com/paper/2106.03407/) (2021)
- [A generalised novel loss function for computational fluid dynamics](https://mlsanity.com/paper/2411.17059/) (2024)
- [Reconstruction of 3D Porous Media From 2D Slices](https://mlsanity.com/paper/1901.10233/) (2019)
- [Speed, power and cost implications for GPU acceleration of Computational Fluid Dynamics on HPC systems](https://mlsanity.com/paper/2404.02482/) (2024)
- [Wake-Informed 3D Path Planning for Autonomous Underwater Vehicles Using A* and Neural Network Approximations](https://mlsanity.com/paper/2502.01918/) (2025)

## Abstract (arXiv)

Autonomous underwater vehicle (AUV) launch and recovery (LAR) into the hull of an advancing host platform requires traversal of a complex, three-dimensional propeller wake whose hydrodynamic structure cannot be characterised by a uniform current model. High-fidelity Reynolds-Averaged Navier-Stokes (RANS) Computational Fluid Dynamics (CFD) simulations resolve this structure with sufficient accuracy for path planning, but their computational cost renders them impractical for onboard use. We address this gap by integrating two conditional generative adversarial network (cGAN) architectures -- a regularised PatchGAN and a 2D3DGAN with self-attention -- as drop-in replacements for RANS CFD data within a three-dimensional, energy-weighted A* path planning framework. Both generators are driven by a hierarchical pipeline that synthesises full 1283 voxel flow field volumes from scalar operating condition inputs alone, with end-to-end inference times of approximately 28-146 μs, compared to hours for a single RANS computation. We benchmark all four environmental knowledge levels: uniform current, ground-truth CFD, PatchGAN, and 2D3DGAN~SA across 19,800 independently generated trajectories spanning 550 distinct flow conditions. Full CFD wake knowledge reduces energy expenditure by 5.7-12.5% and high-velocity wake-core encounters by up to 77.8% relative to uniform-current planning, with both benefits scaling with operating severity. The cGAN surrogates recover approximately 45-60% of the CFD energy benefit and high-velocity cell avoidance benefit while operating at inference speeds compatible with edge device use. These results provide the first systematic quantification of the downstream path planning value of cGAN-predicted hydrodynamic fields in a three-dimensional maritime robotics application.