With AI (Artificial Intelligence), autonomous machines today can reliably assess complex scenarios in real time. The AI-based image processing software from Data Spree and the Time-of-Flight (ToF) camera technology from BECOM show together the possibilities for driverless transport systems (AGV).

In logistics in particular, efficiency along the entire process chain is a decisive factor in competition. Reliable and, above all, safe automation of the transport of goods is essential for modern and efficient logistics. Today, employees and autonomous systems must be able to work together safely in warehouses and production facilities, and the avoidance of accidents is the highest priority. With Artificial Intelligence from Data Spree and 3D camera technology from BECOM, autonomous vehicles can quickly and reliably detect people and obstacles and react accordingly.
 

A valuable helper thanks to 3D vision and Artificial Intelligence

The 3D ToF camera generates a depth image and a greyscale image with which it is possible to localise objects and distances to objects in three-dimensional space. ToF technology offers advantages over other methods of 3D imaging, for example it is largely independent of lighting conditions and has a high degree of robustness with regard to visual variations of the objects. Based on the 3D information, the AI reliably detects the presence, position and size of the trained obstacles, such as people in this case.

The three-dimensional position of the obstacle is then detected with centimetre accuracy based on the depth information. In addition, the AI can be trained according to other  obstacles, such as other AGVs, pallets, packages, etc. The training and creation of the AI can be implemented very quickly and without programming effort using the DataSpree tools and services, such as Deep Learning DS.

With the help of this AI-based 3D camera approach, a very robust and safe orientation logic for autonomous vehicles for logistics and production (AGVs) can be implemented. The real-time execution of the AI required for this takes place on the BECOM multi-ToF HUB and therefore offers a fully integrated interaction of imaging, AI logic and communication. The ToF sensors used are ideally suited for mobile applications thanks to their compact design and, by means of a combination of several sensors, can provide a complete 360° all-round view of the environment.

AI can deal with a wide variety of scenarios and situations, since the logic is based on real existing data and is not manually programmed. With the tools from Data Spree, the AI can be flexibly expanded at any time and can be trained on new, definable objects or classes. In this way, complex orientation patterns for AGVs can be implemented that were inconceivable with conventional methods.
 

Traditional algorithms - complex, inflexible and expensive

Classic image processing has to be programmed from scratch in a very complex process. In this process, algorithms are developed manually by experts, which requires a lot of know-how and time. These classically programmed algorithms work according to hand-made rules and decision criteria. Risks arise if there are deviations from these rules in operation. These deviations can be, for example, changing lighting conditions, environmental parameters, changes in the routes, procedures or processes. By means of training with real environmental data, Artificial Intelligence can correctly assess a wide variety of situations and environmental changes and react correctly.

That is why logistics must use Artificial Intelligence (AI) in the future

With AI-based image processing, as shown in the example, autonomous vehicles can interpret complex work situations and processes better and make human-machine interaction safer. Depending on the training, AI networks can be trained on various obstacles and objects, for example packages, pallets, high racks, containers, etc. This opens up limitless possibilities for autonomous vehicles, but also for collaborative robots or automation in general.

Smart processes automated with AI will be a key element in modern logistics in the future. Thanks to Artificial Intelligence, the many lines of programming code will be a thing of the past. Automated processes for transport, counting tasks or sorting can be implemented quickly and securely with AI-based image processing and the corresponding tools from Data Spree. An insight into this new type of image processing is particularly worthwhile in logistics, where time and costs are the decisive factors for success.