Cognitive robotics and new safety technologies for human-robot collaboration TechTricks365

Researchers at the Fraunhofer Institute for Factory Operation and Automation IFF have developed cognitive robot capabilities that can handle complex tasks in manufacturing that were previously impossible to automate. In addition, they are also unveiling PARU and computer-aided safety (CAS), the first safety technologies and planning tools for close human-machine collaboration that can also ensure safety in AI-generated robot movements.

The researchers will be demonstrating what cognitive robotics can do and how dynamic workspace monitoring works at automatica 2025 in Munich from June 24 to 27, 2025 (Hall A4, Booth 319).

Researchers at Fraunhofer IFF are harnessing new AI-based solutions to give robots the cognitive abilities they need to operate autonomously in unstructured, changing environments and to automate complex processes such as assembly and disassembly in industrial environments or handling objects in health care settings.

Projection-based and camera-based safety technologies allow robots with AI-based motion control to respond reliably to changes, adapt to new tasks and operate an application securely. This opens up a broad range of new fields of application that were previously closed off to conventional robotics, which is limited to specific, narrowly defined tasks.

“Cognitive robots can learn from experience, make independent decisions and adapt to various scenarios. For pick-and-place tasks involving picking up components and placing them where they need to go, a cognitive robot no longer needs to learn what the individual workpieces look like before it can grab them.

“Instead, it uses a camera to register the object’s size, shape, texture and condition and adjusts its behavior accordingly. In the process, it can handle different environmental conditions and even different packaging materials,” says Magnus Hanses, head of the Cognitive Robotics group at Fraunhofer IFF.

Using simulation to train AI models

The experts use simulated environments to train the AI models used. For example, they simulate assembly and disassembly processes such as removing a motherboard from a computer. Any number of virtual robots can work in digital space at the same time and at a much faster pace without any safety concerns.

There are many advantages to learning in the digital simulation, but it also has one vulnerability. The virtual learning environment is never 100% the same as the real world. The challenge for the researchers is to close this reality gap, also known as the Sim2Real gap, as much as possible.

There are two possible approaches here. The simulation can either be designed to be as realistic as possible, or it can encompass the widest possible range of real-world versions, so the neural network used for the AI learns to generalize and find its way around unfamiliar environments.

One way the researchers are achieving this is through domain randomization. This approach allows them to create a large number of simulated environments with random properties and train a model that works in all of them.

“There are many different parameters, such as lighting, that affect the simulation. We can change this set of parameters during the training. The robot doesn’t learn to solve the exact simulation. Instead, it comes to understand the abstract concept behind it. The reality becomes just another version of a simulation for the AI, if you will,” Hanses explains.

PARU—unique, patented speed and separation monitoring

But the field of cognitive robotics is still facing another challenge: Right now, there is no way to ensure the safety of AI-generated robot movements in line with safety standards. For AI-based robots to be able to interact with humans in a safe environment, the researchers at Fraunhofer IFF have developed PARU, a patented new technology for monitoring workspaces. PARU uses advanced projector and camera technology to project visible warning and protective fields directly around the machine and recognize when people enter the safety zones.

“After the projector and the two cameras are calibrated, virtual expectation images are generated as the first step. Then the projector projects a visible light curtain around the robot and the component that is to be picked up in accordance with the distance formula set out in the relevant standard, ISO/TS 15066. This light curtain acts as a safety line, visualizing for employees the protective space that humans must keep clear,” explains Norbert Elkmann, head of the Robotic Systems department at Fraunhofer IFF.

“If any part of a worker’s body comes into contact with the line, the line is interrupted. The cameras recognize that there is a discrepancy between what they expect to see and the real-world image. Depending on the situation, the robot halts is movement right away or slows its speed.”

Visible safety lines foster trust

The safety areas are adjusted dynamically to the machine’s movements, as PARU always considers the robot’s current status—making it ideal for use in cognitive robotics. “Our technology is unique. No other system allows for a smaller distance between humans and robots while observing the specifications set by the applicable standards and also needing so little space. This is possible because the cameras and sensors recognize not only torsos, arms, and heads, but even fingers,” Elkmann says.

Another advantage is that the projection can also show the worker where the robot will be moving as its next step, further enhancing trust in working with machines. The additionally coded visible safety lines work independently of ambient lighting angles and conditions. If the cameras or projectors stop working, the entire system is automatically switched off.

CAS: Intelligent software solutions for adaptive robot systems

Also at automatica 2025, Fraunhofer IFF will be presenting computer-aided safety (CAS), a package of digital safety solutions that make human-robot collaboration (HRC) applications efficient, cost-effective and safe.

Product-ready software modules are available for efficient calculation of safe distances and speeds. Digital assistants support the risk assessment and safety approval processes and make it easier for new entrants in particular to comply accurately and efficiently with the full range of obligations under the EU’s Machinery Directive.

Unlike the collision measurement feature, the safety approval tool works entirely digitally. It takes parameters such as collision force and pain threshold into account to determine the robot’s maximum permitted speed.

The modules can optionally be incorporated into any kind of robot controls or existing simulation environments for planning purposes to precisely align economic specifications with applicable safety requirements. This prevents planning errors and saves on engineering costs.

CAS was devised based on data collected from years’ worth of unique tests with subjects, which have yielded new threshold limits and other key biomechanical indicators for safe HRC. Collision and clamping loads set on a specially-designed pendulum were used to identify the pain threshold through tests of more than 100 human subjects. The ethics committee and the Department of Trauma Surgery at Otto von Guericke University Magdeburg supported Fraunhofer IFF during the studies.

The researchers from Fraunhofer IFF will be showcasing how their AI-controlled robots, the new PARU safety technology and the CAS software modules work in practice (including working together) at the joint Fraunhofer booth in Hall A4 at the automatica trade show from June 24 to 27, 2025.