Onboard Vision and MPC Navigation for Underwater Robots: An Open BlueROV2 Platform for Multi-Robot Experiments & Docking

2026-09-29

AI Summary

This study addresses the perception, estimation, and control challenges in autonomous navigation and docking of underwater robots within constrained environments. An open-source platform based on the BlueROV2 is developed, featuring a modular pressure-housing design. Methodologically, the system integrates stereo vision-based depth perception, a six-degree-of-freedom nonlinear dynamic model, and quaternion state estimation, employing nonlinear model predictive control (NMPC) to achieve high-precision trajectory tracking and automated docking. Supported by onboard hardware such as the Jetson Orin NX alongside PX4/Gazebo simulation environments, multi-robot collaborative experiments validate the system’s effectiveness in underwater perception accuracy, onboard computational performance, state estimation robustness, and autonomous docking capability. Ultimately, this work provides a comprehensive, low-cost hardware and software solution for practical underwater operations.

Abstract

Autonomous underwater robots require robust perception, estimation and control to operate in confined environments. This paper presents an open-source BlueROV2 platform combining onboard vision with nonlinear Model Predictive Control (NMPC) for autonomous navigation and docking. The platform integrates an NVIDIA Jetson Orin NX and an Intel RealSense D435i stereo camera in a modular pressure housing. Underwater-calibrated stereo depth and realtime object detection provide relative position measurements of nearby BlueROV2 vehicles in the camera and body frames. A quaternion-based estimator fuses external pose and inertial measurements, while an NMPC controller based on a nonlinear six-degree-of-freedom model tracks planned navigation and docking trajectories. To support reproducible development, we also provide open-source physics-based PX4 SITL and Gazebo environments, multi-robot simulation tools and a lowcost physical docking station. Experiments evaluate underwater perception, onboard computational performance, state estimation, trajectory tracking and autonomous docking.

Problem

• underwater robots
• autonomous navigation
• docking
• perception
• multi-robot

Innovation

• Nonlinear Model Predictive Control
• Underwater Vision
• State Estimation
• Autonomous Docking
• Open-source Platform