analiza aiqbench
This research proposes a novel framework that transforms drone vision data into virtual swarm-game states, enabling rigorous auditing of interception and sustainability metrics without deploying physical hardware. By integrating complex state variables like fatigue and entropy budgets into a repeated Markov layer, the study demonstrates significant improvements in localization accuracy and robustness through mathematical formalization. The work advances the intersection of computer vision, game theory, and robotics by providing scalable methods to analyze high-dimensional drone behavior via finite empirical-risk encoders.
Pattern-Derived Visual Swarm Games: Multi-Scale Drone-Vision States for Interception and Sustainability Audits
arXiv:2608.23575v1 Announce Type: new Abstract: We convert drone-vision annotation streams into virtual swarm-game states without controlling physical drones. VisDrone and UAVSwarm metadata are compressed into a Bloom representation; deterministic probes produce bounded capability vectors, image-space formations, finite zero-sum payoffs, and human-readable visual overlays. The audit scales from $6\times 6$ to $32\times 32$ finite games and adds a repeated Markov layer with stock, fatigue, adaptation, exposure, stress, budget, data-growth, model-improvement, and entropy-budget state variables. Local screen tuning raises robust screen security from $0.526$ to $0.593$, and the $32\times 32$ tuned screen reaches value $0.616$. A field readout audit shows that fixed-pixel rasters do not improve monotonically: $128\times 128$ accuracy is $67.2\%$ and hotspot error is $0.136$. The diagnosed error is shrinking image-plane bandwidth. A finite empirical-risk encoder over scale-normalized Gaussian bandwidths selects a scale-normalized encoder with $\lambda=1.50$, reaching $77.6\%$ accuracy at $128\times 128$ and reducing joint loss by $0.185$. A server-side audit checks $16{,}777{,}216$ target-localization states, and a 32-round repeated-game audit over $16{,}777{,}216$ trajectories selects a budget-adaptive policy with value $0.461$.
Abstract:We convert drone-vision annotation streams into virtual swarm-game states without controlling physical drones. VisDrone and UAVSwarm metadata are compressed into a Bloom representation; deterministic probes produce bounded capability vectors, image-space formations, finite zero-sum payoffs, and human-readable visual overlays. The audit scales from $6\times 6$ to $32\times 32$ finite games and adds a repeated Markov layer with stock, fatigue, adaptation, exposure, stress, budget, data-growth, model-improvement, and entropy-budget state variables. Local screen tuning raises robust screen security from $0.526$ to $0.593$, and the $32\times 32$ tuned screen reaches value $0.616$. A field readout audit shows that fixed-pixel rasters do not improve monotonically: $128\times 128$ accuracy is $67.2\%$ and hotspot error is $0.136$. The diagnosed error is shrinking image-plane bandwidth. A finite empirical-risk encoder over scale-normalized Gaussian bandwidths selects a scale-normalized encoder with $\lambda=1.50$, reaching $77.6\%$ accuracy at $128\times 128$ and reducing joint loss by $0.185$. A server-side audit checks $16{,}777{,}216$ target-localization states, and a 32-round repeated-game audit over $16{,}777{,}216$ trajectories selects a budget-adaptive policy with value $0.461$.
20 pages, 8 figures. Ancillary files include reproducibility code, dataset manifests, numerical tables, remote audit outputs, and Lean/Coq formal checks
Robotics (cs.RO); Computer Science and Game Theory (cs.GT); Image and Video Processing (eess.IV)
I.2.10; I.4.8; I.5.4; I.2.11; G.3; F.2.2
arXiv:2608.23575 [cs.RO]
(or arXiv:2608.23575v1 [cs.RO] for this version)
Text integral sub licența deschisă a publicației · 212 cuvinte
