Skip to content

About

23 open-source sensor, robotics and security builds, each built against a real, published Canadian defence requirement: passive radar, hydrophones, LoRa mesh, GPS-denied rovers, thermal drones.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

Repository files navigation

Canadian Defence Hardware Program

Canadian Defence Hardware Program

23 open-source sensor, robotics and security builds, each one built against a real, published Canadian defence requirement.

builds: 23 domains: sky · water · ground · trust License: MIT write-ups: tyfsadik.org

The builds · Architecture · Status · Get started

Why this exists

In 2026 Canada started saying, in public documents, exactly what it wants built. I read those documents as free requirements specs and started building against them in my own lab:

  • Defence Drone Initiative (DDI), launched July 23, 2026. First priority areas: low-cost tactical ISR drones, and ground robots for resupply, casualty evacuation, and terrain too hazardous for personnel.
  • Army MINERVA challenges, the Army states it has bought foreign robotic systems of mixed quality, with problems in cold-weather operation and components from unstable supply chains, and that it currently lacks a drone that can do ISR in Arctic conditions. The Arctic drone call closed September 24, 2026; the full text reads like an evaluator's checklist.
  • DRDC field trials, GPS-denied navigation, convoying, cold-weather performance, and resilient operation, exercised on events like Operation NANOOK.
  • NRC + DRDC counter-drone work, a detection system that picks up the signature of a drone's rotating propellers without emitting any radio signal that could reveal its own location.
  • Airspace deconfliction, the Army is studying how to manage airspace shared by many uncrewed aircraft at once.

These calls are aimed at companies, not students, so I treat them as requirements documents, not application forms. Every build below answers one of them at hobby scale, with real hardware, honestly reported measurements, and published datasets or dashboards landing as each build matures, see each page's status section for what is done, in progress, or still a target.

Program architecture

flowchart TD
  subgraph Sky["SKY"]
    PR["Passive radar node<br/>KrakenSDR + RTL-SDR ADS-B"]
    ADD["Acoustic drone detector<br/>MEMS mic array"]
    TSD["Thermal SAR drone<br/>Lepton + Hailo HAT+"]
    DECONF["Airspace deconfliction<br/>ESP32 beacons + SITL"]
  end
  subgraph Water["WATER"]
    PAVM["Hydrophone vessel monitor<br/>+ AIS truth"]
  end
  subgraph Ground["GROUND"]
    SM["Seismic perimeter mesh<br/>ESP32 LoRa nodes"]
    ROV["GPS-denied rover<br/>ROS 2 + EKF"]
    CONV["Convoy robots<br/>LoRa mesh"]
  end
  subgraph Trust["TRUST & ENV"]
    CS["Cold-soak rig<br/>battery dataset"]
    SEC["Secure OTA updates<br/>TPM + signed images"]
  end
  BUS[["Signed detections bus<br/>MQTT / Zenoh + store-and-forward"]]
  FUSE["Kalman tracker + fusion service"]
  COP["Common operating picture dashboard<br/>tracks + confidence + alert queue"]
  HUMAN["Human in the loop<br/>every decision"]
  Sky --> BUS
  Water --> BUS
  Ground --> BUS
  SEC -.->|signed OTA| Sky
  SEC -.->|signed OTA| Ground
  CS -.->|cold derating data| FUSE
  BUS --> FUSE --> COP --> HUMAN
Loading

Every node is receive-only or self-contained, signs its output, and feeds one fused picture with a human deciding.

The builds

Sky

Air sensing, drones and counter-drone.

Build What it does Stage Built with
Sky: Passive Aerial Early-Warning Node Receive-only passive radar that sees aircraft by their broadcast reflections In progress Python (NumPy DSP)
Passive Acoustic Drone Detector A microphone array that hears drone rotors and points to where they are In progress Python
Counter-Drone Sensor Fusion Simulator Simulated radar, RF, acoustic and camera tracks fused into one triaged picture Simulation Python
Counter-Drone Test-and-Scoring Harness with Sensor-Fleet Operations Scenario cards and honest metrics for scoring counter-drone sensors Planned 2027 Python
Mini Airspace Deconfliction Manager Who is flying where: geofences, conflict prediction and human override In progress Python
Thermal Search-and-Rescue Drone A thermal drone that finds people in snow and brush with on-board AI Built Python
Arctic ISR Drone (Cold, Glove-Operable, Thermal, TAK) A cold-weather thermal drone with glove controls and TAK markers Planned 2027 Python
Operation LENTUS-Style Disaster Response Drone Mapping Simulated drone flights that map floods and wildfires for responders Simulation Python

Water

Maritime sensing and survey.

Build What it does Stage Built with
Water: Passive Acoustic Vessel Monitor A dock hydrophone that identifies passing boats by their sound In progress Python
Autonomous Boat for Seabed Surveys and Anomaly Detection An autonomous boat that maps the seabed and flags anomalies Planned 2027 Python

Ground

Ground sensors, rovers and cold-weather data.

Build What it does Stage Built with
Ground: Seismic & Acoustic Perimeter Mesh Solar LoRa sensor nodes that tell vehicles from footsteps In progress C++ (ESP32) + Python
GPS-Denied Navigation Rover A ROS 2 rover that keeps navigating after GPS is cut In progress C++ (ROS 2) + Python
Convoy-Following Robots on a Degraded Mesh Convoy robots that hold formation through radio link drops In progress C++ (ESP32)
GPS-Denied Cargo Ground Vehicle for Snow A cargo rover for snow that navigates without GPS Planned 2027 Python
Cold-Soak Battery Characterization Rig How drone batteries really behave in a Canadian winter, measured In progress Python + C++ (ESP32)

Fusion

Bringing every sensor into one picture.

Build What it does Stage Built with
Multi-Domain Common Operating Picture One live picture fusing every air, water and ground sensor In progress Python
Arctic Domain Awareness Digital Twin A digital twin of Canada's North that flags dark vessels Simulation Python

Trust

Security, accountability and how code reaches the fleet.

Build What it does Stage Built with
Decision Black Box A tamper-evident flight recorder for human decisions Simulation Go
Secure Robot-Fleet Updates Signed over-the-air updates with automatic rollback for robots In progress Go
Secure Autonomy for the Robot and Drone Fleet Hardening a robot and drone fleet against spoofing and tampering Planned 2027 Python
DDIL-Proof DevOps CI/CD that keeps shipping over denied and broken networks Simulation Go
Zero-Trust Air-Gapped Software Supply Chain Signed, reproducible software carried across an air gap Simulation Go
Sovereign AI and Data Enclave A private AI enclave where every answer respects clearance labels Planned 2027 Python

Stages: Built is finished hardware. In progress is hardware on the bench with code running. Simulation is a software build that runs entirely on simulated or open data. Planned 2027 is a published build guide with working simulation code, written against a real spec before the hardware is bought.

Status

  • Did: bought and benched the full workshop (Phase 0) and the Phase 1-6 hardware; ADS-B receiver live with a real-time aircraft map; ROS 2 + Gazebo + ArduPilot SITL simulation environment running on the homelab cluster; first cold-soak freezer runs logged.
  • Doing: KrakenSDR passive-radar processing chain (range-Doppler plots scored against ADS-B); rover EKF tuning with GNSS-cut drift tests; hydrophone + AIS capture rig; ESP32 LoRa mesh firmware; thermal detection pipeline on the Hailo HAT+.
  • Next: publish the cold-soak dataset (runtime, voltage sag, failure mode vs temperature); multi-node passive-radar fusion; signed OTA rollout across the rover fleet with cold-chamber rollback tests; the multi-domain common operating picture tying every node together with chaos tests.

Designed means the protocol is written, built means the hardware is running, measured means results are published.

Phase Designed Built Measured
Phase 0: Workshop and shared infrastructure Yes Yes (benched) Not applicable
Phase 1: Sky node (passive radar + ADS-B truth) Yes ADS-B receiver live with real-time aircraft map; KrakenSDR processing chain in progress ADS-B map operational; no radar scoring published yet
Phase 2: Water node (hydrophone + AIS) Yes In progress (capture rig) No measurements published yet
Phase 3: Ground mesh and deconfliction beacons Yes In progress (ESP32 LoRa mesh firmware) No measurements published yet
Phase 4: Rovers (GPS-denied navigation + convoy) Yes In progress (ROS 2 + Gazebo + ArduPilot SITL environment running; EKF tuning) No published drift figures yet
Phase 5: Drone (thermal SAR + acoustic detector) Yes In progress (thermal detection pipeline on Hailo HAT+) No measurements published yet
Phase 6: Cold-soak rig + secure fleet updates Yes Rig built; first freezer runs logged; secure updates in progress Initial runs logged; dataset not yet published
Multi-domain COP Yes In progress (dashboard live on homelab cluster, seismic mesh feeding it) Chaos-test metrics pending

Get started

Every build is its own repo with a demo that runs on simulated data, so you can try any of them without hardware:

git clone https://github.com/TYFSADIK/acoustic-drone-detector
cd acoustic-drone-detector && pip install -r requirements.txt && python demo.py

To work on the whole program, clone the repos side by side and set up the shared toolchain once:

./scripts/setup-dev.sh                # Go, Python, OPA, cosign, syft, mosquitto, PlatformIO
python -m program.status .. --md      # test status of every build
In this repo Purpose
INTEGRATION.md How all the builds connect physically and logically, and the order to build them in
interfaces/detection.schema.json The signed detection message every sensor publishes
program/status.py Runs every build's tests and reports the results
docs/project-page.md The full program write-up: requirement sources, roadmap, bills of materials by phase, workshop safety

Ground rules

  • Receive-only and defensive. Sensors listen; nothing jams, spoofs or interferes with anyone else's systems.
  • Honest numbers. Results are published only when there is a real run series behind them. Targets are labelled as targets.
  • Open data and my own hardware only. Simulations use fictional scenarios and public data sources.

License

MIT. Designed, built and documented by Taki Sadik.

About

23 open-source sensor, robotics and security builds, each built against a real, published Canadian defence requirement: passive radar, hydrophones, LoRa mesh, GPS-denied rovers, thermal drones.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages