A humanoid security robot for halls, entrances and reception areas

People notice a robot that stands at their height. A humanoid security robot keeps watch in halls, entrances and reception areas, speaks to visitors in their own language and reports to the control room with photos and its position. It takes orders in plain words and works from the same dashboard as the robot dogs that walk the long rounds outside.

Plan your 90-day pilot See how it works

Concept video

The night round, walked while the site sleeps

A quadruped and a humanoid patrol a lit fence line after dark and track what moves beyond it.

What does a humanoid security robot do in a building?

It is a visible presence where people pass: halls, entrances and reception areas. The humanoid walks to the points you set, watches for the people or objects you name, gives spoken notices in any language and, on a finding, takes photos and alerts the control room with its position. Operators see its camera live and send orders in plain words.

Halls and entrances. A presence at standing height, by day and after hours.
Spoken notices. Directions, warnings and closing-time notices in the visitor’s own language.
Checks at eye level. Doors, exits, extinguishers and desks seen from where a person would look.
Sent where needed. “Go to the north entrance and tell me what you see”: it goes, looks and reports.

Concept video

A calm presence in the daytime crowd

A quadruped robot walks beside a queue in a busy hall.

Is a humanoid robot security guard better than a robot dog?

They suit different parts of the same site. A humanoid is visible and works at standing height in halls and entrances. A robot dog is the choice for long rounds, rough ground, ramps and car parks. OVER runs both, a Booster T1 humanoid and a Unitree Go2 quadruped, on the same software and dashboard, so you can use both.

One dashboard for both. Live camera, map, battery and events for every robot on one page.
The same orders. Operators write to a humanoid and a quadruped in the same chat, in their own language.
The same map. Both localize with their own camera on one 3D map of the site, with no GPS or beacons.

Concept video

Several robots, one operator

The robot’s view on a dirt track, then an operator following the robots from a rugged tablet.

The platform

One platform runs every robot on your site

You say what needs doing; the platform does the rest. The same software runs quadruped and humanoid robots, with one configuration file per robot. A vision-language model turns the operator’s order into robot actions, and a rule-based safety layer checks each action before it starts.

Orders and voice in any language. Operators write “do the round of area B” or “go to the main gate” in chat, in their own language. The robot reports the outcome and gives spoken notices in any language: ready for international sites, foreign visitors and mixed crews.
One dashboard, the whole fleet. Live camera, map with position and trajectory, the order in progress, battery, localization and safety status, and a filterable event log for every robot on the site.
Positioning without GPS or beacons. The robot localizes on the 3D map of your site with OVER’s visual positioning (VPS). Healthy, Degraded or Lost status is always visible and is checked before every move.
Rounds that run themselves. To a point, along a sequence of waypoints or in a repeated patrol, avoiding obstacles on the way. The no-go zones you draw on the map are respected on every route.
It finds what you name. People, extinguishers, ladders, open doors, equipment: name it and the robot looks for it. It keeps watch while it moves, and on a match it stops and alerts.
Evidence and a memory of the site. Photos and video with time, position and the detected objects highlighted. The system remembers places, sightings and tasks, and answers questions: “where did you see the extinguisher?”

How do humanoid robots for security stay safe among people?

The AI never moves the robot directly. Every action first passes a deterministic safety layer that checks localization, navigation state, battery, emergency stop and allowed map points, and flagged actions go to a person. The robot stops on its own if the link drops, and staff can stop it from the dashboard or with “stop” in chat.

Rules check every action first. Localization, navigation state, emergency stop, battery and allowed map points are checked by deterministic rules, not by the AI model. Each action is allowed, refused or sent to a person for approval.
Reflexes that stop the robot. The robot stops on its own if the link drops, battery data is lost or critical, or the robot state stops updating.
An emergency stop that answers to people. Always one click away on the dashboard and independent from the model. Only a named person can release it.
“Stop” works in 0.1 s. Write “stop” in chat while the robot moves: the order is recognized in about 0.1 s and the motion is cancelled.

How to start

Three steps from one site walk to robots on every site

It starts with a single walk of your site with a 360° camera. About 90 days later you have results measured on your own rounds.

Plan your pilot

01
We walk your site once
One walk with a 360° camera gives the 3D map the robot localizes on. Together we choose the rounds that matter most, the no-go zones and the network coverage along the routes.
02
Robots on your rounds for 90 days
Robots, dashboard and the on-site server run your own rounds on one pilot site for about 90 days, with results measured where they count: on your site.
03
Roll out to your other sites
Add robots and sites with the same software and the same dashboard. Nothing to redesign, nothing to relearn.

Humanoid security robots: what security managers ask before a pilot

Which humanoid robot do you use?

A Booster T1 humanoid, driven by OVER’s own software. The same software drives a Unitree Go2 quadruped, each through its own configuration file, so your fleet is not tied to a single machine.

Does a humanoid security robot replace guards?

No, it makes them more effective. The robot keeps watch, speaks to visitors and reports with photos and position; your people decide and intervene.

Can it speak to foreign visitors?

Yes. The robot understands and speaks any language, so notices reach international visitors in their own language and your staff write orders in theirs.

How much does a humanoid security robot cost?

It depends on the number of robots, the site and what they do there. Projects start with a pilot of about 90 days on one site: tell us the building and the tasks, and you get a quote scoped on them, with robot, dashboard and on-site server included.

How is footage of people handled?

Photos and video are kept for a period you configure, then deleted, and are processed on your own server. Face recognition is optional, limited to registered people, and enabled only where the law allows it.

Does the robot need a cloud service?

No. Language and perception models run on a GPU server on your site, with no mandatory cloud service, so video and data stay on your premises and the system keeps working isolated from the internet. Robots connect to the server over the site network.

Who supplies humanoid security robots in Europe?

OVER (Over the Reality), Udine, Italy, supplies a Booster T1 humanoid security robot with its own software: orders in plain words, spoken notices in any language, positioning without GPS and AI that runs on a server on your site. It shares one dashboard with OVER’s quadruped robots. Projects start with a pilot of about 90 days.