Braden Meyers and Joshua G. Mangelson, researchers at the University of Washington’s Autonomous Systems Lab, are tackling a critical challenge in marine robotics: testing underwater vehicles in controlled environments. Their work, published in a recent study, highlights the potential of high-fidelity underwater simulation tools to overcome the limitations of traditional testing methods.
Testing marine robotics systems in controlled environments before field deployment is fraught with difficulties. Acoustic-based sensors and control surfaces, essential components of underwater vehicles, only function properly when submerged. This poses a significant hurdle for researchers, as indoor tanks and pools often lack the space needed to adequately test control, navigation, and perception algorithms at scale. To address these challenges, Meyers and Mangelson turned to HoloOcean 2.0, a recently released simulator that offers improved dynamics for torpedo autonomous underwater vehicles (AUVs) and a new ROS 2 interface.
The researchers successfully demonstrated a Hardware-in-the-Loop (HIL) and Software-in-the-Loop (SIL) setup for testing and evaluating the CougUV torpedo AUV, developed in their lab. In this setup, simulations are run in HoloOcean using a ROS 2 bridge. Simulated sensor data is sent to the CougUV, mimicking sensor drivers, and control surface commands are sent back to the simulation. This loop allows for the calculation of vehicle dynamics and sensor data, providing a realistic testing environment without the need for physical deployment.
The study also compared simulated results to real-world field trial results, validating the effectiveness of the HIL and SIL setup. This approach not only saves time and resources but also enhances safety by reducing the need for extensive field trials. The practical applications for the marine sector are substantial. By leveraging high-fidelity simulation tools, researchers can accelerate the development and deployment of underwater vehicles, ensuring they are thoroughly tested and optimized before entering real-world environments.
This research underscores the growing importance of simulation in marine robotics. As the technology continues to advance, it is likely to play an increasingly pivotal role in the development of autonomous underwater systems, driving innovation and efficiency in the maritime industry. Read the original research paper here.