Real-time driver state detection A vision system for controlling an industrial robot with hand movements Integration of a camera and virtual reality with a robotic arm Application of computer vision in the recognition and interpretation of sign letters Mapping of characteristic points of the human face using machine learning and Blender software Six-legged robotic insect Two-way communication based on the MQTT protocol within the virtual and real environment

Mixed reality applications

Focus of this work is an approach in which a robot is using a virtual or inner representation of its own body to ensure a safe and efficient interaction within the physical world. By analyzing correlations within its surroundings, the robot is able to plan task-oriented and socially accepting responses. This approach is inspired by the phenomenon called bodily awareness, which is found in humans. Compared to conventional approaches where robots are pre-programed to react on finite number of environmental occurrences or states, the proposed approach gives the robot an ability to adapt to changes through a constant interaction. To achieve this, a robot interaction space is discretized and constantly analyzed. As a part of the new cognitive model, a virtualized image of the robot body is used to avoid all possible collisions. The model also contains a probabilistic component to provide the most appropriate solution to given environmental conditions where the environment is naturally highly dynamic and unpredictable.