Democratizing ocean technology: low-cost innovations in underwater robotics
Bibliographic record
Abstract
In comparison to the ocean’s immense volume and diversity of research areas, the number of sensors required to make the majority of desired measurements is quite small. This inequality of supply and demand elevates prices, adding further barriers for developing nations or fledgling research programs with smaller budgets attempting ocean science. Our work aims to demonstrate the potential of combining commercially available, open-source products to create inexpensive, configurable, and user-friendly platforms that can be adapted for underwater navigation and integration with most commercial oceanographic sensors. Specifically, we will highlight modifications made to a Blue Robotics BlueROV2, which we have configured for various missions including vertical profiling of a coastal fjord and three-dimensional mapping of crude oil spills. The BlueROV2 offers an easily modified platform for physical mounting of sensors and streaming of sensor data via its onboard computer, a Raspberry Pi. Our custom circuit board is “sensor-agnostic”, powering sensors from a common source (the ROV battery) and using an Arduino that accepts analog or digital sensor inputs, allowing us to choose from a wide range of sensors. Physical modifications make use of inexpensive, readily available materials, and range from simple plastic brackets for small sensors to a skid for a sensor with half the ROV’s original weight, which utilizes pop bottles for buoyancy. While products such as Pixhawk, Raspberry Pi, Arduino, and BlueROV have inspired hobbyists and youth around the world, they paradoxically have not been as widely embraced in the academic community, who perhaps remain unaware of their research potential. Thus, while there has yet to be an analogous push to develop inexpensive, small, power-efficient, and open-source sensors, these platforms offer exciting opportunities to build a new generation of oceanographic tools with measurement abilities far exceeding those of their predecessors. We are at an ocean technology tipping point, and, as MacGyver says, “With a little bit of imagination, anything is possible.”
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.025 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".