The first robotics and AI lab in the U.S. Caribbean, dedicated to marine science research and conservation.

The VICARlab

Caribbean coral reefs are changing faster than ever.

To protect them, we need to track those changes in real time, with finer detail, and over larger areas.

The VICAR Lab is bringing robotics, AI, and robust data infrastructure to reef monitoring.

Our mission is to understand how today's reefs are changing and why, while there is still time to save them.

Read more
Projects

Projects

We have several active projects applying autonomous methods to study reef life and habitat changes at scale and with a special focus on the local, long-term USVI coral monitoring program (est. 2001).

Deep water grouper monitoring with robots

Caribbean groupers form predictable spawning aggregations (FSAs) at specific sites each winter. These aggregations are critical for population persistence and uniquely vulnerable to fishing pressure when fish concentrate in space and time. The lab is using underwater videography and emerging AUV-based survey methods to document FSAs as a non-extractive monitoring tool, building visual records of aggregation behavior and abundance that complement acoustic and diver-based approaches used across the U.S. Virgin Islands.

3D tracking of bleached corals during record heat wave

Annotated 3D models of TCRMP sites are used to follow individual coral colonies through the 4th Global Coral Bleaching Event (2023 to 2024), the largest bleaching episode recorded in the U.S. Virgin Islands. Each colony is segmented, identified to species, and tracked across repeated visits, producing colony-level time series of size, tissue condition, mortality, and competitive interactions. The same models measure structural complexity at biologically meaningful scales, linking individual fate to habitat depth, exposure, and surrounding community composition.

AI-based fish tracking and counting from video

A computer-vision pipeline that detects and tracks individual fish across frames of underwater video. The same model can support automated abundance counts, species identification, and behavioral analysis. Applied to AUV transects and FSA footage, it offers a path to scaling fish-survey effort and to detecting previously undocumented spawning aggregations from existing video collections.

Ultra-high resolution mapping of 30 coral reefs

Diver-collected high-resolution imagery is reconstructed into dense 3D models of TCRMP reef sites, providing a structural and biological substrate that can be revisited and re-measured year over year. AI-assisted annotation (TagLab) and 3D visual analytics (VisCore) support colony-level identification, size and health change detection, structural complexity metrics, and competitive-interaction analysis across shallow and mesophotic habitats.

Geo-referenced underwater mapping (cm scale)

AUV-collected downward-facing imagery is reconstructed into georeferenced digital elevation models with centimeter-scale accuracy. The resulting orthomosaics and bathymetry layers drop directly into standard GIS workflows, where they can be overlaid on existing TCRMP spatial datasets, used to plan more precise follow-up AUV missions, and serve as a reusable substrate for ecological analysis.

Research Infrastructure

The projects underway are contributing to a new research infrastructure: equipment, software, and procedures with future applications and long-term value.

Maiden voyage of the lab’s newest, and smallest, robot

Early field tests of the lab's newest acquisition, the Hydrus microAUV from Advanced Navigation. The vehicle is small enough to be hand-deployed from a small boat (deployment is genuinely a flick of the wrist), which dramatically lowers the logistical bar for AUV-based reef survey work in the Virgin Islands.

Obstacle avoidance of self-driving underwater vehicles

Early test footage of a RangerBot AUV detecting and steering around a diver during a shallow-water transect at Reef Bay. The vehicle uses stereo vision and inertial sensing to detect obstacles in real time, a prerequisite for safe close-range survey work on complex reef terrain.

Robot maintenance and repairs

Summer 2025 interns Gidal Williams and Viana Biscoe installing a Doppler Velocity Log (DVL) on the lab's BlueROV2. DVL integration gives the vehicle bottom-relative velocity measurements, supporting precise station keeping and georeferenced navigation during inspection and survey missions.

Hardware

Hardware

This research infrastructure includes state-of-the-art robotics, computers, and cameras, available to CMES researchers, collaborators, and students.

VICARIUS

VICAR’s integrated undersea survey (VICARIUS) platform

VICARIUS is our core data infrastructure that connects mission planning, data processing, and analysis. It is built on interoperable software modules, each openly available through versioned repositories.

VICARIUS, short for VICAR's Integrated Undersea Survey platform, ties our repeated workflows together: AUV mission planning and post-mission processing, 3D photogrammetric reconstruction, AI model training and inference, segmentation and annotation review, classifier evaluation, and the data conventions that keep all of it traceable.

Shared infrastructure means a method developed for one student's thesis can be reused by the next, a model trained on one dataset can be applied to another, and results can be reproduced from raw inputs months or years later.

Software

This research infrastructure also includes custom software for analysis and management of the large amounts of data generated from these autonomous and high-resolution methods. These tools are being built in a central repository to preserve institutional knowledge and keep the work reproducible, transparent, and available to all.

Each module is one data tool for one purpose, including AI annotation, model training, 3D reconstruction, telemetry mapping, analyses of these and other data, and handy utilities. Some works in progress are shown here.

AI-accelerated platform for preparing AI training data

Researchers use AI-assisted masks to annotate corals in reef images, refine their outlines, and flag identifications for expert review.

Outreach

Outreach

The VICAR Lab shares its research and technology with students and the wider community through demonstrations, lab visits, and local events.

Team

Our team

Meet the researchers and students behind the lab.

TCRMP team conducting reef surveys
Divers ascending from surveys at Cane Bay Deep, Spring 2026. Photo: J. Quetel
Publications

Publications

VICAR Lab publications are in prep and will be listed here. Until then, check out previous publications on Lauren’s website and Tyler’s lab website.

The VICAR Lab is focused on applying rapidly advancing autonomous techniques and applying them at scale to monitor and research Caribbean coral reefs. We are based at the Center for Marine and Environmental Studies (CMES) in St. Thomas, U.S. Virgin Islands.

The lab takes its name from its role as the operational core of the Virgin Islands Center for Autonomous Research (VICAR), funded by a five-year, $7 million U.S. National Science Foundation EPSCoR E-RISE RII award (OIA-2446008). This award contributes to a broader research infrastructure supported by other major grants and private donations, including an earlier privately funded award that helped lay the groundwork for VICAR.

Our starting point is the Territorial Coral Reef Monitoring Program (TCRMP): 34 permanent reef sites across the U.S. Virgin Islands, monitored continuously for 25 years, with roughly 1.6 million expert observations of reef life. Those records document massive declines in coral abundance. Autonomous tools extend the reach of expert divers and improve the resolution and consistency of reef surveys, helping long-term monitoring keep pace with accelerating ecosystem change.

Diver above a bleached Caribbean reef during the 2023/2024 mass bleaching event
A reef survey diver over a bleached mesophotic coral reef, 2023. Photo: TCRMP.

Blog

Lab stories and updates are coming soon.

Sunset over St. Thomas, USVI