CORAL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles

• URL: http://arxiv.org/abs/2607.09557v1
• Date: Fri, 10 Jul 2026 16:02:55 GMT
• Title: CORAL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles
• Abstract summary: Fine grain control and positioning of autonomous underwater vehicles (AUVs) is critical for sampling, maintenance, and survey applications.<n>Traditional control methods for AUVs are labor intensive and are not robust to changes in the vehicle configuration or environmental conditions.<n>We are the first to successfully deploy a zero-shot RL policy on a 6-DOF AUV in which policy training is performed on surrogate drag models (SDMs) trained on CFD data.
• Score: 14.192376456398456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine grain control and positioning of autonomous underwater vehicles (AUVs) is critical for sampling, maintenance, and survey applications. Traditional control methods for AUVs are labor intensive and are not robust to changes in the vehicle configuration or environmental conditions. Reinforcement learning (RL) promises rapid controller development while handling a range of deployment parameters via domain randomization (DR). However, DR is still limited by the capacity of the underlying simulation to model real physics. In particular, drag physics are difficult to model and are a large contributor to sim-to-real gaps. Meanwhile, computational fluid dynamics (CFD) provides high fidelity drag models but is challenging to leverage within reinforcement learning frameworks due to its computational overhead. Thus, in this paper we exploit the idea of training surrogate approximations of CFD models of a given vehicle, enabling fast inference within RL pipelines. We are the first to successfully deploy a zero-shot RL policy on a 6-DOF AUV in which policy training is performed on surrogate drag models (SDMs) trained on CFD data. We find 31% lower energy usage compared to a controller using simplified physics while traversing between waypoints 11% faster with 19% less error. Our SDM based RL controller better predicts zero-shot transfer and is more robust across reward shaping design choices. When using DR to complete a task with perturbed parameters, we find that the CFD policy is the only controller that successfully transfers. The policies are evaluated in a controlled tank environment and in the field providing extensive testing of the policies' capabilities.

Related papers

• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• Sim-to-reality adaptation for Deep Reinforcement Learning applied to an underwater docking application [0.0]
  Deep Reinforcement Learning (DRL) offers a robust alternative to traditional control methods for autonomous underwater docking.<n>This paper presents a systematic approach for autonomous docking using the Girona Autonomous Underwater Vehicle (AUV) by leveraging a high-fidelity digital twin environment.
  arXiv  Detail & Related papers  (2026-03-12T15:01:25Z)
• Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles [1.4883782513177095]
  Reinforcement learning (RL) provides a powerful alternative but training is typically slow and sim-to-real transfer remains challenging.<n>This work introduces a GPU-accelerated RL training pipeline built in JAX and MuJoCo-XLA (MJX)<n>By jointly JIT-compiling large-scale parallel physics simulation and learning updates, we achieve training times of under two minutes.
  arXiv  Detail & Related papers  (2025-12-15T14:12:32Z)
• Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes [2.6511518230332753]
  Holonomic autonomous underwater vehicles (AUVs) have the hardware ability for agile maneuvering in both translational and rotational degrees of freedom (DOFs)<n>This paper presents the first general zero-shot sim2real deep reinforcement learning-based (DRL) velocity controller enabling path following and agile 6DOF maneuvering with a training duration of just 3 minutes.
  arXiv  Detail & Related papers  (2025-12-09T14:42:26Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows [109.99020160824553]
  We propose an efficient deep reinforcement learning framework for modeling and control of turbulent flows.<n>It is model-based RL for predictive control (PC), where both the policy and the observer models for turbulence control are learned jointly.<n>We find that PINO-PC achieves a drag reduction of 39.0% under a bulk-velocity Reynolds number of 15,000, outperforming previous fluid control methods by more than 32%.
  arXiv  Detail & Related papers  (2025-10-03T00:18:26Z)
• Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection [71.84636717632206]
  Unmanned aerial vehicles (UAVs) for reliable and energy-efficient data collection from spatially distributed devices holds great promise in supporting Internet of Things (IoT) applications.<n>We propose a joint language model (LLM) to learn effective UAV control policies.<n>LLM-CRDT outperforms benchmark online and offline methods, achieving up to 36.7% higher energy efficiency than current state-of-the-art DT approaches.
  arXiv  Detail & Related papers  (2025-09-17T13:05:08Z)
• Physics Enhanced Residual Policy Learning (PERPL) for safety cruising in mixed traffic platooning under actuator and communication delay [8.172286651098027]
  Linear control models have gained extensive application in vehicle control due to their simplicity, ease of use, and support for stability analysis. Reinforcement learning (RL) models, on the other hand, offer adaptability but suffer from a lack of interpretability and generalization capabilities. This paper aims to develop a family of RL-based controllers enhanced by physics-informed policies.
  arXiv  Detail & Related papers  (2024-09-23T23:02:34Z)
• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [57.278726604424556]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers.<n>Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy.<n>We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance [1.099532646524593]
  This paper presents a novel approach, merging the Maximum Entropy Deep Reinforcement Learning framework with a classic model-based control architecture, to formulate an adaptive controller. Within this framework, we introduce a Sim-to-Real transfer strategy comprising the following components: a bio-inspired experience replay mechanism, an enhanced domain randomisation technique, and an evaluation protocol executed on a physical platform. Our experimental assessments demonstrate that this method effectively learns proficient policies from suboptimal simulated models of the AUV, resulting in control performance 3 times higher when transferred to a real-world vehicle.
  arXiv  Detail & Related papers  (2023-10-17T08:46:56Z)
• Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion [78.46388769788405]
  We introduce guided constrained policy optimization (GCPO), an RL framework based upon our implementation of constrained policy optimization (CPPO) We show that guided constrained RL offers faster convergence close to the desired optimum resulting in an optimal, yet physically feasible, robotic control behavior without the need for precise reward function tuning.
  arXiv  Detail & Related papers  (2020-02-22T10:15:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.