Robots driving safely
among people

The system in action: the camera feed with live person detection (left) and the detected positions placed in the facility map in real time (right).

When humans and industrial robots operate in the same environment, high safety standards are essential to prevent accidents. Safety has therefore been a key focus of an AAU-led research project aimed at expanding the use of robots in production environments. Led by Professor Preben Mogensen, the project has implemented an additional safety system developed by Ambolt AI.

The idea is simple: robots should move carefully when people are nearby. When the area is clear of people, they can speed up. This increases efficiency, but must never compromise safety. To ensure this, the setup includes two separate positioning systems for added security.

The primary system requires all personnel in the production area to wear a radio tag. If someone forgets their tag or the tag isn't read correctly, the backup safety system developed by Ambolt AI kicks in.

Only positions are stored

The backup system is based on Computer Vision with camera-based solutions. It's trained to detect humans, but no images are stored. Only the position is recorded, and only while the person is inside the work area. No personally identifiable data is saved.

To detect people in the area, the system uses an object detector trained specifically to identify humans. Once a person is detected, the system assumes the bottom of the bounding box represents where their feet meet the floor. This becomes the reference point for positioning. The position is then converted into coordinates and compared with the primary system. If both systems detect a person in the same location, everything proceeds as normal. If the secondary system detects someone not registered by the primary system, an alarm is triggered.

Point-cloud map built by the positioning system: walls and machines as scan points, the robot with its safety zones, and a detected person

Making robot use as simple as plug-and-play

To spread the use of robots in production environments, the implementation must be as easy as starting to use a household plug-and-play product. That's the overarching goal of the research project.
— Preben Mogensen, Professor, Aalborg University

Project facts

  • Official title: 5G-Robot – 5G Enabled Autonomous Mobile Robotic Systems
  • Innovation Fund Denmark investment: DKK 30 million
  • Total budget: DKK 52 million
  • Duration: 3 years

Technology partners

  • MIR (Mobile Industrial Robots A/S) and UR (Universal Robots) – leaders in mobile robots and robotic arms
  • Intelligent Systems and Technicon – digital industrial automation and system integration
  • 5G technology provided by Telenor and Nokia

Industrial end users

  • Novo Nordisk A/S
  • GRUNDFOS Holding A/S
  • Danfoss A/S
  • LEGO System A/S

Curious what this could look like in your business? Call +45 40 60 10 19 and talk directly with our CEO or sales team – or leave a message and we will call you back.

Let's talk

Call and talk directly with our CEO or sales team about your project or idea – or leave a short message and we will call you back.

+45 40 60 10 19