Autonomous Strategic Defense: An Adaptive Clustering Approach to Capture Order Optimization
Bibliographic record
Abstract
View Video Presentation: https://doi.org/10.2514/6.2022-2215.vid The proliferation of UAV technology has introduced a new risk to the security of high-value assets. Emerging advancement in cooperative multi-agent control of UAVs presents a means of automating a defensive response to these new threats. A practical realization of an automated defense strategy is limited by the computational constraints of onboard computers. The UAV’s onboard computer must solve multiple non-convex NP-hard navigation optimization problems to maximize the effectiveness of its defensive strategy. One such problem is the challenge of finding the optimal flight path for a single defender that must capture multiple slower invaders. This problem has been labeled as the n-Invader Capture Order Problem, abbreviated as n-ICOP. This research proposes an approximation method for reducing the solution space of n-ICOP. Given a specific constraint on computational resources, the method can adaptively reduce the computational load while optimizing the accuracy of the approximation. The new method splits the n-ICOP into a grouping problem and an ordered set problem, like the clustered variant of the Traveling Salesman Problem. The optimal grouping of invaders is estimated efficiently through the k-means clustering algorithm. The estimated grouping scheme reduces the complexity of an approximated n-ICOP solution because all strategies that separate members of a group are excluded from the search space. Simulations of the approximated n-ICOP solution were performed on a large data set of randomized defender-invader scenarios. Analysis suggests that this novel algorithm can reliably generate near-optimal strategies at a small fraction of the computational cost of a full exact solution. The results of the simulated trials demonstrate that the reduction in search space is substantial for the vast majority of randomized scenarios. This significant improvement in computational efficiency, with a sufficient degree of reliability, provides a practical means of solving for feasible n-ICOP solutions in a computationally limited environment.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".