Collaboration of multi-domain marine robots towards above and below-water characterization of floating targets
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper reports on a method to obtain a multidomain (environment) awareness on a floating target (non-responsive ship, iceberg, other floating structure) using a heterogeneous collaborative team of above, surface and underwater robots. This allows, for example, a ship approaching a non-responsive floating target to get information from a safe standoff prior to getting closer to further investigate or to attempt a boarding. The above-water unmanned aerial vehicle (UAV), integrated with optical cameras, obtains measurements of the above-water geometry using visual imagery to create an above-water three-dimensional model using photogrammetry methods. The below-water unmanned underwater vehicle is integrated with an imaging and profiling bathymetric sonars to capture the submerged hull geometry and features. An unmanned surface vehicle (USV) hosts an intelligent node which centrally controls the robotic collaboration by autonomously planning and distributing the mission for both the UUV and UAV. The results from the two are fused to yield a more complete picture of the floating target. We present results from simulations and a controlled in-water trial with an UUV, USV and UAV. The contributions from this work includes the robotic collaboration and autonomy across multiple domains, autonomous mission-planning and the fusing of multi-domain data. The scheduling of inter-dependent multi-robot task allocation is addressed in the autonomous mission-planning. The approach is validated in simulations and tested in-water. The in-water trials highlight the challenges and value of integrating sensors on distributed multi-domain robots towards a more complete picture on a floating target.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it