burakoktenli / hmaa-uav-governance Public

Authority-Governed UAV Autonomy for Contested Environments. Integrating Sensor Trust Fusion, Dynamic Authority Control, and Deterministic Recovery. 52-component hardware platform, interactive governance simulator, 250 structured simulation runs, swarm governance extension.

hmaa-uavauthority-governed-autonomyuav-governancedempster-shafersatahmaacaradrone-swarmcontested-environmentscc-by-4.0
6,600+ lines 16 files CC BY 4.0 DOI: 10.5281/zenodo.19128769
main 16 files · v1.0 · Mar 2026
Zenodo Open Simulator Project Page
HMAA-UAV_Oktenli_2026_Zenodo.pdfResearch paper (17 pages) · Governance architecture, DS equations, simulation resultsMar 2026
uav-simulation.htmlInteractive governance simulator · SATA-HMAA-CARA pipeline, fault injectionMar 2026
results_summary.csv250 simulation runs · 50 per scenario, 15 columnsMar 2026
hardware_bom.csv52-component bill of materials with verified sources and costsMar 2026
uav-ELECTRICAL.json48 electrical connections with interfaces and voltagesMar 2026
uav-MECHANICAL.json49 mechanical assembly connectionsMar 2026
uav-CONFIG.jsonFull system configuration with component specificationsMar 2026
uav-SCHEMATIC.svgElectrical schematic diagram (vector)Mar 2026
uav-BLUEPRINT.pdfFull engineering blueprintMar 2026
uav-GUIDE.mdAssembly guide with action itemsMar 2026
uav-render.pngPlatform 3D renderMar 2026
uav-swarm-architecture.pngSwarm governance architecture diagramMar 2026
CITATION.cffMachine-readable citation with ORCID and related DOIsMar 2026
LICENSECC BY 4.0Mar 2026
README.md

HMAA-UAV: Authority-Governed UAV Autonomy for Contested Environments

This repository contains the complete research artifacts for the HMAA-UAV project: an authority-governed unmanned aerial vehicle architecture for operations in contested environments. The system integrates SATA sensor trust fusion, HMAA authority computation, and CARA deterministic recovery into a single flight-decision pipeline.

Publication

DOI: 10.5281/zenodo.19128769
Author: Burak Oktenli · Georgetown University, MPS Applied Intelligence
ORCID: 0009-0001-8573-1667
License: CC BY 4.0 · Version: v1.0 · March 2026

Governance Pipeline

  • Stage 1: Sensor Inputs (GPS, LiDAR, Camera, IMU, Radar, UWB, Optical Flow, Barometer)
  • Stage 2: SATA Trust (per-sensor trust + weighted Dempster-Shafer fusion)
  • Stage 3: HMAA Authority (trust scalar to authority levels A3-A0)
  • Stage 4: Command Gate (clamp commands to authority envelope)
  • Stage 5: Flight Controller (MAVLink execution via Cube Orange+)
  • Stage 6: CARA Recovery (safe-land, return-safe, hover-hold, crawl-mode, degraded-teleop)

Hardware Platform

  • Dual-compute: Cube Orange+ (flight control) + Jetson Orin NX 16GB (governance)
  • 52 hardware components, 48 electrical connections, 49 mechanical assemblies
  • Livox Mid-360 LiDAR, dual GPS (ZED-F9P + Here3), FLIR Lepton 3.5 thermal
  • Pozyx UWB for GPS-denied positioning, Ainstein US-D1 radar altimeter
  • Total platform cost: ~$4,200

Simulation Results

  • 250 structured runs across 5 adversarial scenarios (50 per scenario)
  • Trust collapse detection: sub-200ms (simulated clock)
  • Authority transitions: ~150ms of simulated time
  • CARA recovery: 160 activations across all runs, 100% deterministic
  • Weight sensitivity: ±20% perturbation, 20 random sets

Related Work (Same Research Program)

  • SATA: 10.5281/zenodo.18936251
  • HMAA: 10.5281/zenodo.18861653
  • CARA: 10.5281/zenodo.18917790
  • ADARA: 10.5281/zenodo.19043924
  • MAIVA: 10.5281/zenodo.19015517
  • FLAME: 10.5281/zenodo.19015618

Author

Burak Oktenli
Georgetown University, M.P.S. Applied Intelligence
ORCID: 0009-0001-8573-1667
Website: burakoktenli.com