Forward Looking Sonar Integrated Obstacle Avoidance System for a Towed Synthetic Aperture Sonar
Bibliographic record
Abstract
We develop & validate a scheme for integrated obstacle detection & avoidance on the Kraken Robotics towed KATFISH${ }^{\text{TM }}$UUV using an Imagenex Forward-Looking profiling multibeam Sonar (FLS). An operational definition of vehicle safety is used to design, develop, and integrate an obstacle detection scheme using only the expected vehicle motion and estimated or measured seabed. The accuracy of the FLS is improved by the addition of realtime seabed estimation through multi-look fusion of FLS measurements in an Unscented Kalman Filter (UKF). The Obstacle Detector (OD) system uses range measurements to estimate the vehicle's obstacle separation and make a GO/NO-GO decision on taking evasive action during operations. Seabed Estimation (SE) records and synthesizes subsequent seabed profile measurements by predicting seabed motion from Integrated Navigation System data, estimating the expected seabed, and comparing that result to the currently measured seabed. Obstacle detection is analyzed using the ReceiverOperator Characteristic Curve (ROC curve) and its associated “Area-Under-the-Curve” (AUC) while seabed estimation is compared to more-accurate but delayed nadir multibeam altimetry. An empirical test of the ROC achieves an AUC of$\mathbf{0. 9 8}$. It is found that OD has no delay at high sensitivities and up to 2 s of delay for very low sensitivities. Seabed estimation successfully improves the accuracy of the seabed estimate decreasing the standard deviation of the local seabed estimate by half from 0.2 m to 0.1 m. The integrated obstacle avoidance system is currently available to operators for realtime & remote decisionmaking. Work has successfully developed and advanced novel technologies for realtime safety of vehicles that is already proving useful in operations. The currently implemented system is flexible to changing operating needs and can be made more refined or robust as experience increases.
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 | 0.001 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".