Autonomous underwater robots navigate and dock using onboard vision
Onboard Vision and MPC Navigation for Underwater Robots: An Open BlueROV2 Platform for Multi-Robot Experiments & Docking
Robotics
Summary
Underwater robots need to see and move precisely to work well in tight spaces. The authors created a robot system that uses cameras and smart math to understand where it is and follow planned paths underwater. They built tools to test their system in both simulated and real environments, including robots that can find and dock with each other. Their setup also shares software openly to help others build similar underwater robots. They tested their system’s ability to perceive, estimate position, and dock automatically underwater.
What this means in practice
- •For marine robotics engineers: Build and test underwater robots that autonomously navigate and dock using onboard stereo cameras and nonlinear control.
- •For robotics simulation teams: Simulate multi-robot underwater navigation and docking scenarios with open-source PX4 SITL and Gazebo tools supporting realistic physics and perception.
Authors
Victor Nan Fernandez-Ayala, Wiktor Kowalczyk, Cezary Banaszek, Dimos V. Dimarogonas
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.