Automated palletising and depalletising with AI
AI (Artificial Intelligence) enables the implementation of automation processes using image processing not only better but also easier, faster and more efficient. Data Spree from Berlin shows how production and logistics can benefit from AI in the future.
By Manuel Haß, Co-founder of Data Spree, and Chris Montague is Head of Edge Solution Sales EMEA at ADLINK
Especially in production and logistics, efficiency along the entire value chain is an essential factor in competition. Reliable automation of manual and time-intensive processes is crucial for a modern and efficient factory and warehouse.
Traditional palletising solutions - inflexible, complicated, expensive
Traditional palletising robots either function purely statically or have to be programmed from scratch in a very complex way. In this case, algorithms are developed by experts by hand, which often requires a lot of know-how and time. Often complex palletising tasks, such as chaotic sorting, difficult geometries or mixed pallets, cannot be realised at all or only with great difficulty using classic approaches. All this leads to high costs and to the fact that automation requirements cannot be met.
Solving complex palletising tasks efficiently with Vision AI
With AI-based image processing, complex palletising tasks can be automated reliably and quickly during ongoing operation. To enable orientation in three-dimensional space during the gripping process by the robot, 3D imaging methods such as time-of-flight or stereo vision camera systems are used. With Data Spree's Deep Learning DS software, the software logic can be implemented efficiently and easily in the background.
The first process step is to capture images of the objects to be palletised. Then the objects are assigned to classes, for example, package type A, package type B and package type C. This assignment is called data annotation or labelling.
The AI then iteratively trains the recognition and correct assignment, as well as the position, size and orientation of the objects. Here, the AI works similarly to the human brain and learns to recognise, assign and localise objects based on the image data - without the need to manually pre-define specific object features. With Deep Learning DS, you can quickly and easily perform this ‘learning process’ yourself. In addition, Data Spree also offers the complete process up to productive integration into the facility as a service.
This method thus allows the most diverse and complex palletising tasks to be implemented quickly and easily - and without a single line of programming code. Automation processes can thus be implemented very efficiently and robustly. A ready-to-use prototype can thus be created in just a few hours and expanded into a productive solution within a very short time. Data Spree's fast AI models additionally ensure real-time capability in high-frequency production and logistics operations. Another advantage is the flexibility of the learning system.
If products, product properties or objects change due to production or logistics changes, the AI can simply be ‘fed’ with new images and retrained. In this way, it is possible to react quickly and effectively to changes in production or logistics without having to start from scratch or buy and implement a new solution.
Quick and easy AI implementation and execution
The trained AI model can be individually integrated into any customer application through the open ONNX standard format. Data Spree's own execution environment Inference DS also offers a simple graphical user interface in which the AI model can be quickly executed via drag-and-drop principle on the respective hardware, such as a smart camera or industrial PC. This saves integration time - and above all costs.
This example shows a chaotic palette structure with different objects of various size, dimension, geometry and orientation. On the left side, you can see the output false-colour image, which is composed of depth information and grayscale image. On the right, the 3D point cloud with markers on the detected objects and the InfluxDB dashboard fully integrated via the ADLINK Data River to track the set of objects. This sample application achieves execution times of less than 30ms, making it excellent for fast palletising processes. Using the Inference DS robot plugin, the object coordinates can be easily output and sent to the appropriate controller. Thus, the customised palletising application is not only quickly completed, but also quickly and easily integrated.
As co-founder of the Berlin-based start-up Data Spree, Manuel Haß has implemented the shared vision of the automation of the future: making deep learning accessible to everyone in order to automate cognitive processes. After studying computer science at the TU Berlin and stations at ABB and Bosch, Manuel worked on autonomous vehicles at the DCAITI in Berlin before founding Data Spree.
Chris Montague is Head of Edge Solution Sales EMEA at ADLINK. An IoT professional with over 22 years experience in the hardware, software and IT solutions market, prior to ADLINK he worked for an IT consultancy, advising customers and delivering services from pre-sales to delivery for projects across multiple verticals. He had a Bachelor’s degree in Computer Science from Northumbria University and started his IT career writing code to optimise and streamline databases for large public sector clients.