mlsanityData to 14 Oct 2026

Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning

arXiv 2607.02037 ↗First posted 2 Jul 2026cs.RO cs.LGcited by 0

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

Abstract (arXiv)

Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deployment. We present an adaptive reinforcement learning approach for trajectory tracking that enables zero-shot cross-platform deployment using a single policy. Since the deployment platform's dynamics are unknown to the policy, we address cross-platform generalization with the standard partial-observability approach of conditioning on interaction history, employing a teacher-student architecture in which a learned module infers a latent representation of the platform dynamics. The policy is trained in simulation under randomized vessel dynamics and is deployed zero-shot to two real-world platforms without any fine-tuning, despite relying on a simple analytical dynamics model rather than a high-fidelity hydrodynamic simulator. In real-world experiments on two different platforms, the adaptive policy outperforms non-adaptive learning-based baselines by up to 58% in position mean absolute error while approaching the tracking accuracy of a platform-specific tuned controller.

Key facts. No citing papers in the map yet (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 12 of its 32 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

12 of 32 references.

References · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  3. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  4. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  5. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 141
  6. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 122
  7. 2022GenLoco: Generalized Locomotion Controllers for Quadrupedal Robotscited by 48
  8. 2023ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robotscited by 19
  9. 2020COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learningcited by 17
  10. 2023Deep Reinforcement Learning Based Tracking Control of an Autonomous Surface Vessel in Natural Waterscited by 6
  11. 2020Roboat II: A Novel Autonomous Surface Vessel for Urban Environmentscited by 4
  12. 2025Solgenia -- A Test Vessel Toward Energy-Efficient Autonomous Water Taxi Applicationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Sim-to-Real RL for ASVs using SysID
  2. 2026CORL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles
  3. 2024A Deep Reinforcement Learning Framework and Methodology for Reducing the Sim-to-Real Gap in ASV Navigation
  4. 2025Ocean Diviner: A Diffusion-Augmented Reinforcement Learning Framework for AUV Robust Control in Underwater Tasks
  5. 2026Dynamical System-Based Imitation Learning and Neuroadaptive Control for Trajectory Recovery in Autonomous Ships
  6. 2025RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation
  7. 2024Learning to Swim: Reinforcement Learning for 6-DOF Control of Thruster-driven Autonomous Underwater Vehicles
  8. 2024Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface Vehicles