Part 6/10
To date, most AIs in robotics have been used to recognize, grasp and precisely position objects. Using the objects to fulfill a certain purpose has not yet been sufficiently researched. Our software must therefore be regularly tested and trained with artificial intelligence during the development phase.
In order to test the software and optimize the algorithms, the system is trained with a mixture of real hardware and simulation. Specific software that can simulate motion sequences in robotics is used for the simulation. The simulation software can be used to test the use of different sensors or robot arms and deviations can be examined and considered during software development.
In addition to the simulation test, a realistic environment is being developed in order to test and train the AI-based software. The environment is recorded in different lightning conditions to train the system for use at different times of day and different locations. Any operating problems will also be identified by test persons at the University of Applied Sciences Offenburg.
These tests allow problems to be identified and eliminated from the start. The algorithms are adapted and the artificial intelligence is fed with the information obtained. In this way, tasks can be carried out identically in the simulation environment and in the real environment, despite different hardware.
kununu