Patrol that never repeats, never sleeps and never pursues.
What it is
The base layer of every MoLogica deployment. Robots run autonomous circuits on randomised routes, detect people, vehicles and heat signatures, raise alerts with images, and dock themselves to charge.
How a patrol runs
- 01You describe it. "Patrol the north fence, check the fuel-store padlock, then the vehicle yard." In plain language, from the control room.
- 02The fleet runs it. The robot builds and keeps its own map, reaches each goal within a few centimetres, re-plans around anything dropped in its path, and takes a different route after every dock.
- 03You see every result. Detections go to the control room with an image. The robot holds and watches. It never pursues.
Rules of engagement, built in
Never pursue. Alert first. Protect the guard. Log everything for evidence.
Takeover, two ways
- In plain language: "go back to the east gate, get closer, show me that lock." The robot does it, with every safety check still in place.
- By joystick: direct, millisecond control for the operator.
Both are logged as corrections. Corrected once, learned for next time.
Proof so far
In a simulated depot: autonomous mapping, goals reached within 2 to 4 cm, a five-lap endurance patrol with 20 of 20 legs and 5 of 5 docks in 15 minutes with no retries, and an end-to-end proof gate passed four times in a row on different random seeds.
Ready to see robots patrolling your site?
Before any hardware is bought, we can build a simulated copy of your site and show the fleet patrolling it at night while you configure the checks in plain language.