ARES (fictional system), patrol simulation

Simulation time: Zulu (UTC) and local (UTC+1, fictional zone): local

Speed

What now: Choose a scenario and press Start.

Urgent 0Caution 0

Conditions and seed
Time

On a phone or tablet the 3D view starts on request (light mode). The map and the panels work without it.

Main view
3D view camera

ARES (fictional system), patrol simulation

An educational border patrol simulation on synthetic data: drones, a fixed-wing aircraft, camera masts and ground teams on the fictional border of State A and State B.

Choose a scenario, then press Start.

What you will see

  • A tactical map and a 3D view with asset and contact symbols. The M key swaps the views.
  • AI proposals with their reasons. Without your approval the assets only patrol.
  • The EO and IR camera picture, the event timeline and the reports.
Layers
Symbol key
  • Own asset: blue rectangle
  • Contact not yet assessed: yellow quatrefoil
  • No threat: assessed persons, animals
  • Armed contact, or an unidentified air object over our side
  • False alarm
  • A person needs help (always a green square)
  • Asset without a link
  • A plan or a proposal, not a fact

Frame logic as in the public APP-6 rules, our own drawings. Persons never get the red diamond.

00:00:00

2D map: drag, the wheel or a pinch zooms, the arrows pan. 3D view: drag to turn, W A S D: move. Click a symbol to open its card.

Assets

Drag a row onto a contact (map, 3D view, contact table). Without a mouse: the contact card, Send.

AssetStateBatteryLinkTo returnTask

Contacts 0

ContactClassAssessmentStateReading

No contacts yet. The sensors are working; the first report appears here.

Satellites

    A satellite pass appears here with the time its image arrives.

    Timeline

      The timeline starts with the first event.

      Reports

      Deterministic narrator: sentences from the log and the simulation state, no model.

        Reports appear with the first event.

        In-browser model (optional)

          Results

          The result appears after the first minute of simulation.

          Time to detect
          –
          mean, from crossing the line; 0 s when detected before the line
          Response time
          –
          mean, from detection to the first asset on scene
          Decision time
          –
          mean, from a proposal to its approval or rejection
          Line coverage
          0%
          points every 50 m seen in the last 5 minutes
          False alarms
          0
          wildlife, birds and wind on the fence
          Flight hours
          0 h
          sum of hours in the air, drones and fixed wing
          Contacts closed
          0
          handed over to the services, or the object left the area

          You and the algorithm

          We compute the same run (seed, scenario, weather) twice more: with the nearest-free-asset rule and with the Hungarian algorithm. Only the decisions to send assets change.

          Method: the same core and the same contacts from the seed. Every 5 s the algorithm assigns the free assets so that the total cost is lowest: a pair costs its travel time plus battery use, and a contact left without an asset costs by its risk.

          Fleet

          Change the number of assets and compute the effect: the same scenario and seed, 3 h of simulation without the window, the automatic mode, the same rule. The default fleet beside it.

          Method: two core runs in a separate browser thread, the same seed, scenario and scenario weather, the same assignment rule. Only the fleet differs. The window does not change until you use the fleet.

          What this page is

          This is an educational simulation on synthetic data, not an operational system. It is not for decisions about people. It identifies no one: the figures are anonymous and there is no biometrics. ARES is the name of a fictional system in this simulation.

          How we compute it
          • Terrain, border, forest and the movement of contacts come from the seed in the page address. The same seed gives the same run on every computer: the Rust core runs in WebAssembly without functions that differ between browsers.
          • Detection is a draw, not image recognition. The chance grows with the pixels on the object under the Johnson criteria (drone camera 640 × 512 pixels, field 36 × 29°) and falls in fog, rain and forest. Recognition covers the class only: person, vehicle, animal, unknown air object.
          • A contact track joins the sensor readings. The class probability rises with image quality, and the position uncertainty grows while nobody looks.
          • The multirotor uses its battery under the power model of Zeng, Xu and Zhang (2019) for a mass of 4.2 kg and a 199 Wh pack (2 × 99.5 Wh; from the model: about 24 min hovering, about 28 min cruising at 10 m/s), has limited acceleration and speed, and returns for a pack swap with a 25% reserve. The fixed wing cannot hover: it circles on a 250 m orbit and turns no tighter than a 30° bank allows. The teams drive at 12 m/s on roads and 4 m/s over terrain.
          • A group walks at the speed Tobler's function gives for the slope. A team on scene assesses the situation, gives first aid when someone needs it, and hands the persons over to the services.
          • Every 5 s the planner computes an assignment with the Hungarian method or the nearest free asset rule. In the proposal mode it stores the result as proposals and waits for your decision; in the automatic mode it dispatches by itself.
          • The run slider rebuilds the simulation from the seed and the log of your commands, step by step, so a replay gives exactly the same result.

          Parameters marked [A] are assumptions within ranges from public literature. They show differences; they do not rate real equipment.

          Esc

          Keyboard shortcuts

          An educational simulation on synthetic data. Not an operational system, not for decisions about people.Educational simulation. Not for decisions on people.