Cognitive Robotics: Intelligent Software Solutions for Adaptive Robotic Systems

Fraunhofer IFF's Department of Robotic Systems develops innovative AI solutions to automate complex processes, such as industrial assembly and disassembly or object manipulation in the health care sector. Our technologies enable robots to respond reliably to changes and adapt to new tasks. In contrast to conventional robotics that are limited to specific, narrowly defined tasks, we are enabling new fields of use that were previously not possible. We make this possible through adaptive, AI-based generation of robot movements during execution. This involves recording the current status of the process and the environment at all times and deriving the optimal action from this information. This opens wholly new fields of use for robotic applications that are now unfeasible with common programming methods. Robots acquire the ability to understand their environment, make decisions, solve problems independently and learn from experience. To do this, we combine findings and methods from different disciplines, such as artificial intelligence, machine learning, control systems engineering and computer vision.

Privacy warning

With the click on the play button an external video from www.youtube.com is loaded and started. Your data is possible transferred and stored to third party. Do not start the video if you disagree. Find more about the youtube privacy statement under the following link: https://policies.google.com/privacy

How can robots adapt to new and unpredictable environments? Cognitive robotics enables the development of adaptive solution strategies, taking the automation of complex processes to the next level. This video showcases the automated disassembly of electronic waste as an example of how artificial intelligence is applied in robotics.

A key priority when developing AI-based robot motions is the generation of requisite training data. Advanced AI systems need a large number of training examples to develop robust and generalizable skills. The volume of data would not only make direct training on physical robots time-consuming and expensive but would also pose the risk of damage caused by malfunction. This is why we use advanced simulation environments in which the robotic system, its environment and the process are simulated. This makes it possible to train AI models efficiently and safely with a virtually unlimited number of scenarios and variants. There is always a certain difference between simulation and reality, the so-called sim2real gap. Our research is consequently concentrated on methods to close this gap. By systematically using simulated variability, we generate robust AI models that can handle these differences. We were able to demonstrate the successful sim2real transfer in numerous practical applications.

In a current research project, we are demonstrating the performance of our AI-based motion generation for robots, taking automated disassembly of end-of-life electronics as an example. This task places particular requirements on the robot controller’s flexibility and adaptability since neither the product being disassembled nor its condition is known in detail in advance. Since this variety makes standard, rules-based programming virtually impossible, we are opting for reinforcement and imitation learning methods that make it possible to learn from experience. The resultant possibilities are demonstrated in the video below, taking the automated removal of a motherboard from a computer’s housing as an example.

Our services:

  • Development of AI-based robot motions for processes that cannot be implemented with common programming methods
  • Efficient generation of training data in simulations and transfer of trained models to real robotic systems
  • Reduction of the work required to integrate robotic systems in highly variable environments or processes
  • Increased resilience of robotic applications
  • Development of new capabilities to automate hitherto unautomatable applications

References

 

Intelligent Disassembly of Electronics for Remanufacturing and Recycling

In the iDEAR project, we are developing solutions for efficient electronics disassembly and for material recycling and reuse. We want to ensure that raw materials are not wasted and that valuable resources are kept in circulation longer.

Robot-assisted health station for a digital health ecosystem

The Neighborhood Diagnostics project aims to improve healthcare in rural areas through a digital health ecosystem that enables decentralized diagnostics using smartphones, smart medical devices, and wearable devices.

 

ANNIE mobile assistance robot

The ANNIE assistance robot is a versatile mobile manipulator for industrial and commercial applications that cannot be economically solved by conventional automation.

Technologies

Flexible automation for greater productivity—AI for autonomous bin picking

In the ADAPT project, we are developing technologies for the automated handling of components in flexible production environments. The focus is on integrating state-of-the-art AI methods into the process steps of bin picking, from reliable object recognition under real conditions and adaptive handling of components and packaging material to optimization of cycle times through clever reorientation of the component during transport.

Robot Control Box

The Robot Control Box is an intelligent robot controller that can be universally connected to any industrial robot and enables adaptive, sensor-guided movements thanks to state-of-the-art algorithms, reducing integration effort and training costs. It expands the functionality of industrial robots through collision-free path planning, force- and image-guided automation processes, and the use of AI models.

Digital twins for cognitive robotics

Digital twins map the current state and capabilities of a robot and its environment in real time and make this data available for higher-level IT services such as AI and computer vision. We use them consistently throughout the entire life cycle of the robot, from design and production to operation and recycling, thereby promoting agile production through vertical and horizontal networking.

Tactile sensor technology for safe human-robot collaboration

Tactile sensor systems modeled on the human sense of touch enable the detection of contact and pressure distribution and are used in human-machine interactions, process monitoring, and precise gripping. We develop customized tactile sensor systems ranging from prototypes to complex systems, with main applications in tactile floors, robot skins, and grippers.

Projects

 

Heterogeneous, workload-optimized robot teams and production architectures

The Fraunhofer SWAP lighthouse project is researching technological concepts for future production by developing modular manufacturing units that collaborate in swarms and operate (partially) autonomously. The aim is to create manufacturing environments that are more flexible and efficient by breaking down the rigid process sequences of traditional production chains.

 

Mobile manipulator for material logistics and handling

The ISABEL project is developing autonomous service robots for material logistics and handling, specifically for semiconductor manufacturing and life science automation, with a focus on autonomous pick-and-place capabilities.

 

Collaborative robots for aircraft construction

The VALERI project is developing mobile and autonomous robots for aircraft production that will work alongside humans and take on time-consuming and monotonous tasks. The robots are made safe by innovative sensor technology and camera systems and could also be used in other areas of production in the future.

Research Group Cognitive Work Systems in Human-Centered Work Environments

The KaSys research group is developing a cognitive work system with autonomous functions that adapts manual handling and manufacturing processes to the individual performance capabilities of humans.

Real-time control and regulation of mobile robots

The fast robotics project replaced wired communication systems in robots with mobile communications technology to enable the processing of large amounts of real-time data and to outsource tasks to external servers. This led to the development of wireless real-time control for mobile robot systems, which improved the capabilities of the robots and opened up new application possibilities in various industries.

MFLEX 2025

The MFlex 2025 project developed flexible, mobile robot systems for efficient aircraft production. The modular automation solutions are precise and quick to reference. Intelligent software ensures easy programming and safe commissioning of the systems.

Multimodal bin picking

The pickit project extends traditional bin picking systems with tactile gripping technologies to improve the detection and handling of unsorted parts. The project aims to obtain additional object information via tactile pressure profiles, thereby making gripping processes more reliable and efficient.

Robot-assisted parts handling in industrial environments

The EU project PICKPLACE combines human and robotic capabilities to create safe, reliable, and flexible solutions for pick-and-packaging.