Underwater Robot Navigation and Localization During Recovery by Optical Homing and Penning

For autonomous underwater robots the ability to operate for long periods of time and then return back safely is a critical feature in a range of important applications, such as subsea inspection, remote surveillance, and seasonal monitoring. A major challenge for a robot in such long-term missions is to estimate its location accurately since GPS signals cannot penetrate the ocean’s surface, and Wi-Fi or radio communication infrastructures are not available underwater. Using a dedicated surface vessel for acoustic referencing or coming up to the water surface for GPS signals are power hungry, computationally expensive, and often impossible (in stealth applications). This project will make scientific and engineering advances by using a novel optics-based framework and on-board AI technologies to solve this problem. The algorithms and systems will allow underwater robots to estimate their location with GPS-quality accuracy without ever resurfacing. More importantly, these features will enable long-term autonomous navigation and safe recovery of underwater robots without the need for dedicated surface vessels for acoustic guidance. Overall, the outcomes of this project will contribute to the long-term marine ecosystem monitoring and ocean climate observatory research as well as in remote stealth mission execution for defense applications. This project will advocate a novel solution to the foundational problem of underwater robot localization and navigation by introducing the notion of 'optical homing and penning'. This new optics-based framework will incorporate the scientific and engineering concepts for active robot localization and non-invasive navigation without compromising the stealth. The integrated research will develop three sets of novel technologies for (i) distant UUV (Unmanned Underwater Vehicle) positioning with blue-green laser speckles, (ii) accurate 3D orientation measurements from coded bokeh spectrums, and (iii) GPS-quality pose estimates by a directionally-controlled adaptive LIDAR. The combined optical sensory system will be deployable from specialized buoys acting as floating lighthouses. An intelligent visual SLAM system will also be developed for robust state estimation in deep waters when no lighthouse beacons are visible. Additionally, a ROS (Robot Operating System)-based simulator will be developed for evaluating UUV navigation and mission execution performance. For feasibility analysis and assessment, this project will formalize real-world deployment strategies on two UUV platforms through comprehensive ocean trials in the northern Gulf of Mexico and the Atlantic Ocean. These research activities will be complemented by (i) curricula development for three STEM courses, (ii) undergraduate robotics team mentoring programs, and (iii) women in robotics workshop initiatives at UF. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.