@Work focus


For testing new software and for machine learning, it is important to have a simulator that simulates the behavior of the real robot as accurately as possible. This does not stop with the mere movements, so also the kind of the control must be modeled after the original down to the smallest detail.
Localization and navigation


is an enormously important field in robotics. Without the knowledge of the current position, the search for a way to a goal is already doomed to failure. It is therefore important to recognize the current position in the room as quickly and as accurately as possible. It is then possible to plan a route to the destination that promises the greatest economy of movement. The omnidirectional platform of the YouBot creates completely new possibilities for a goal. This makes it possible to achieve the desired orientation during the journey and thus to save time during positioning at the target.

Manipulating objects

presents a great challenge. Since it is not possible to collect exact data through the various sensors, the localization of objects in space is based on pure assumptions, with the robot opting for the most probable position. Addressing these inaccuracies in the 3-dimensional space is a great area of ​​manipulation. The other large area concerns the arm control. It is important that the solutions of the inverse kinematics have to fulfill certain conditions. Thus the arm must not move into obstacles or into itself during the movement. It is also necessary to find out from which positions the arm can reach the object at all.
Artificial Intelligence

In order to achieve an autonomous action of our robot, it is inevitable to realize an artificial intelligence, which takes care of the decision-making based on sensory data and tasks. As in all other areas of robotics, we must also develop an approach that can deal with an inaccurate or incorrect picture of the environment and can bring this picture of the environment back into a consistent state. Our approach to artificial intelligence uses the SMACH project developed within ROS. This is an approach based on a state machine. In addition to the debugging and visualization capabilities provided by SMACH, the state-machine approach also offers many advantages that lead to a clearer and more consistent behavior of artificial intelligence.