To date, most AIs in robotics have been used to recognize, grasp and precisely position objects.

Using the object to fulfill a certain purpose has not yet been sufficiently researched.

In order to optimize the software in our research project and to identify and rectify errors in time, the system is regularly trained and tested during the development phase.

With a mixture of real hardware and simulation, the system can be tested under various conditions. Through error detection, our algorithms are adapted to achieve even better results and rectify detected errors.

Here you can find all articles about our research project.

Image Credits: AI generated with Canva Pro