Risk analysis and decision making for autonomous underwater vehicles
Bibliographic record
Abstract
Risk analysis for autonomous underwater vehicles (AUVs) is essential to enable AUVs to explore extreme and dynamic environments. This research aims to augment existing risk analysis methods for AUVs, and it proposes a suite of methods to quantify mission risks and to support the implementation of safety-based decision making strategies for AUVs in harsh marine environments. This research firstly provides a systematic review of past progress of risk analysis research for AUV operations. The review answers key questions including fundamental concepts and evolving methods in the domain of risk analysis for AUVs, and it highlights future research trends to bridge existing gaps. Based on the state-of-the-art research, a copula-based approach is proposed for predicting the risk of AUV loss in underwater environments. The developed copula Bayesian network (CBN) aims to handle non-linear dependencies among environmental variables and inherent technical failures for AUVs, and therefore achieve accurate risk estimation for vehicle loss given various environmental observations. Furthermore, path planning for AUVs is an effective decision making strategy for mitigating risks and ensuring safer routing. A further study presents an offboard risk-based path planning approach for AUVs, considering a challenging environment with oil spill scenarios incorporated. The proposed global Risk-A* planner combines a Bayesian-based risk model for probabilistic risk reasoning and an A*-based algorithm for path searching. However, global path planning designed for static environments cannot handle the unpredictable situations that may emerge, and real-time replanned solutions are required to account for dynamic environmental observations. Therefore, a hybrid risk-aware decision making strategy is investigated for AUVs to combine static global planning with dynamic local re-planning. A dynamic risk analysis model based on the system theoretic process analysis (STPA) and BN is applied for generating a real-time risk map in target mission areas. The dynamic window algorithm (DWA) serves for local path planning to avoid moving obstacles. The proposed hybrid risk-aware decisionmaking architecture is essential for the real-life implementation of AUVs, leading eventually to a real-time adaptive path planning process onboard the AUV.
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 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".