Machine Learning Algorithms for Autonomous Underwater Vehicle (AUV) Navigation
Bibliographic record
Abstract
Autonomous underwater vehicles (AUVs) play an extremely important role in the fields of oceanography, marine science and underwater infrastructure assessment. Of course, underwater navigation isn't easy either due to varying ocean currents, limited vision, and there's no GPS. This article uses machine learning techniques to describe how AUV navigation can be improved in underwater environments with unknown environment, then enable more reliable decision making and real time obstacle avoidance. This thesis investigates many ML approaches for route planning, sensor data fusion, and obstacle detection including supervised, unsupervised learning and reinforcement learning. With great significance, reinforcement learning algorithms can optimize trial and error learning based navigation techniques to be adapted to novel situations. Additionally, deep leaning algorithms combined with data from sensors such as sonar and cameras are able to enable precise underwater landscape perception and mapping. We apply these algorithms to virtual and physical AUV missions and demonstrate that they result in significant increases in navigation precision, energy efficiency, and mission time. This research's careful consideration of the potential of machine learning for transforming AUV navigation makes more intelligent and autonomous underwater operations possible in many marine sectors.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".