In addition to series production, there is a trend in industry towards the customisation of products. Besides the digital networking of entire systems, learning-capable systems that use artificial intelligence and robots that work hand in hand with humans play a key role when it comes to production in batch size 1. In the BionicWorkplace, all these requirements are combined in a future-oriented working environment.
A central component of the working environment is the BionicCobot . The pneumatic lightweight robot is based on the human arm in terms of its anatomical construction and – like its biological role model – solves many tasks with the help of its flexible and sensitive movements. Due to its pliability and intuitive operation, the BionicCobot can interact directly and safely with people. In doing so, it supports workers doing monotonous jobs and takes over tasks that are dangerous for humans.
In the BionicWorkplace, the bionic robot arm works together with numerous assistance systems and peripheral devices which are networked and communicate with each other. At the same time, artificial intelligence and machine learning methods turn the BionicWorkplace into a learning and anticipatory system that continuously optimises itself.
The whole workplace is ergonomically designed and can be individually adapted to human workers, right down to the lighting. At the centre of the worker’s field of vision is a large projection screen. It supplies the worker with all relevant information and adapts its contents dynamically to the respective requirements. Various sensors and camera systems are fitted all around the projection screen and constantly record the positions of workers, components and tools. This enables a human worker to interact directly with the BionicCobot and control it using movement, touch or speech.
The system recognises the worker and their movements by means of their special work clothing. These wearables consist of a long-sleeved top, which is equipped with inertia sensors, and a work glove with integrated infrared markers. With the help of the recorded sensor data, the BionicCobot is able to hand over objects to its human colleagues with pinpoint accuracy and move out of their way if necessary – an essential requirement for direct collaboration between humans and robots.
The intelligent software simultaneously processes all the camera images, position data and input from the various peripheral devices. It uses all this information to derive the optimal program sequence. The system then distributes the tasks sensibly to the robot and other tools in order to give the human worker the best support whilst working.
With every action solved, the system learns something new. This creates what is known as a semantic map, which grows continuously. Along the network paths, the stored algorithms constantly draw dynamic conclusions. As a result, there is a gradual shift from a controlled, programmed and set sequence to a much freer method of working.
Another element of the intuitive operating concept is remote manipulation. For this purpose, a 3D stereo camera with a viewing angle of 180 degrees records the whole workspace. At the same time, the worker, who is located in a different area, wears virtual reality glasses and the textile wearables. The worker can use these to access the images from the camera in real time and follow them. This allows the robot to be controlled from a separated area or from a safe distance.
Intelligent workplaces capable of learning, such as the BionicWorkplace, and the use of multifunctional tools will make collaboration between humans and machines even more intuitive, simple and efficient in future. Knowledge building blocks and new skills, once learned, can be shared unlimitedly and made available on a global scale. This would make it possible to network workplaces worldwide in the future.