mlsanityData to 14 Oct 2026

Depth-Constrained ASV Navigation with Deep RL and Limited Sensing

arXiv 2504.18253 ↗First posted 25 Apr 2025cs.RO cs.AIcited by 1

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Autonomous Surface Vehicles (ASVs) play a crucial role in maritime operations, yet their navigation in shallow-water environments remains challenging due to dynamic disturbances and depth constraints. Traditional navigation strategies struggle with limited sensor information, making safe and efficient operation difficult. In this paper, we propose a reinforcement learning (RL) framework for ASV navigation under depth constraints, where the vehicle must reach a target while avoiding unsafe areas with only a single depth measurement per timestep from a downward-facing Single Beam Echosounder (SBES). To enhance environmental awareness, we integrate Gaussian Process (GP) regression into the RL framework, enabling the agent to progressively estimate a bathymetric depth map from sparse sonar readings. This approach improves decision-making by providing a richer representation of the environment. Furthermore, we demonstrate effective sim-to-real transfer, ensuring that trained policies generalize well to real-world aquatic conditions. Experimental results validate our method's capability to improve ASV navigation performance while maintaining safety in challenging shallow-water environments.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 43 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

18 of 43 references.

References · 18

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Constrained Policy Optimizationcited by 983
  3. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  4. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  5. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  6. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
  7. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  8. 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 111
  9. 2017Control of a Quadrotor with Reinforcement Learningcited by 92
  10. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 80
  11. 2021Memory-based Deep Reinforcement Learning for POMDPscited by 54
  12. 2020COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learningcited by 17
6 more
  1. 2020Model-Reference Reinforcement Learning for Collision-Free Tracking Control of Autonomous Surface Vehiclescited by 11
  2. 2019Taming an autonomous surface vehicle for path following and collision avoidance using deep reinforcement learningcited by 9
  3. 2016Adaptive Path Planning for Depth Constrained Bathymetric Mapping with an Autonomous Surface Vesselcited by 3
  4. 2023Gaussian Process Regression under Computational and Epistemic Misspecificationcited by 2
  5. 2024Nonlinear Model Predictive Control for Enhanced Navigation of Autonomous Surface Vesselscited by 2
  6. 2021Measuring Uncertainty in Signal Fingerprinting with Gaussian Processes Going Deepcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Deep Reinforcement Learning Framework and Methodology for Reducing the Sim-to-Real Gap in ASV Navigation
  2. 2026Sim-to-Real RL for ASVs using SysID
  3. 2024Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface Vehicles
  4. 2026Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning
  5. 2024Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning
  6. 2023A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles
  7. 2025Long-Term Mapping of the Douro River Plume with Multi-Agent Reinforcement Learning
  8. 2025ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research