With QBIIK, a system is to be developed and tested that combines the technology of autonomous systems with the capabilities of the human being in a useful way: The decentrally controlled vehicle orients itself in the room, navigates autonomously to the target and reaches for the required goods.
During the gripping process, the robot's autonomy is supported by various sensors: In addition to the use of a 3D camera, tactile proximity sensors explore the manipulator's surroundings and ensure collision-free gripping.
If the system is unable to recognize or grasp the goods due to unknown circumstances, it requests human assistance. With a VR human-machine interface the operator and can - for a short period of time - control and carry out the recognition and gripping process. QBIIK learns from the remote assistance and will carry out the steps autonomously in the future.
QBIIK is tested and developed in a real scenario and environment. In the first scenario in the production at Audi Sport, the supply of the supermarket is performed. Here, the with small load carriers (KLT) equipped trailer is docked from the camp to QBIIK. With the docked trailer the platform runs autonomously through the supermarket and discharges all KLT into the corresponding shelves. If problems occur, a user is automatically contacted for remote control. In this scenario, all important functions are tested: autonomous driving, autonomous grasping, VR remote control and the associated learning.
In a second scenario, the complexity of the articles is increased. Instead of recognizing and grasping KLTs, individual parts are picked. This considerably increases the difficulty of the object recognition and the gripping process. The second scenario is intended to identify further possible applications for QBIIK and to provide important key figures, e.g. how quickly an article can be learned.
Both autonomously and remotely controlled, QBIIK represents an agile picking system that contributes to increasing the flexibility and productivity of the picking process.
The use of new technologies, such as large-area tactile and proximity sensors, control devices with haptic feedback and the use of VR technology, gives teleoperation a new potential in industry 4.0.
The ability to learn how to adapt to the environment and to share the experience gained with other platforms across the cloud allows them to be easily deployed into existing processes. The combination of different sensors for the detection and robust gripping of various objects, such as transport crates and individual components of a vehicle, extends the range of application of the system in order picking.
A sophisticated system architecture combines self-developed sensor technology and state-of-the-art technologies into a novel picking system that meets the requirements of modern industry.