Use cases

Use case 1: Loading and unloading trucks and autonomous transportation


This use case covers the entire process of loading and unloading trucks, stacking load carriers and autonomous external transportation. The aim is to develop solutions that enable reliable perception, navigation in open or non-standardized environments and safe movement of partially nested pallets in confined working areas.

Challenges:

  • Automated loading and unloading of trucks: Traditional systems require structural adaptations to loading ramps and special truck trailers, are cost-intensive and not very flexible.
  • Autonomous pallet handling in warehouses and production facilities: Limited space requires the intermediate stacking of pallets during handling.
  • Autonomous outdoor transportation: Vehicles must be able to move in unstructured and dynamic environments. Precise localization and obstacle detection are essential to ensure safe transport.

Through the use of advanced sensor technology, intelligent algorithms and seamless integration into existing processes, this use case offers forward-looking solutions that are suitable for widespread use.

Use Case 2: Picking and kitting


This use case covers the picking of individual items and palletizing in both warehouse logistics and production. The focus is on automating these processes in unstructured environments with a large variety of parts to be processed.

Challenges:

  • Picking and palletizing in the warehouse: At present, goods are often still picked and placed manually, which leads to high physical strain and high staff turnover. Existing automated warehouses are often inflexible and cannot adapt to fluctuating throughput requirements.
  • Order picking and palletizing in production: Even in manufacturing, these processes are usually still carried out manually, as automated systems currently do not achieve the same speed and flexibility as humans. The aim is to develop intelligent gripping and sorting algorithms that enable efficient and economical automation.

Advanced sensor technology, machine learning and intelligent gripping systems are intended to improve the automation of these processes in order to increase efficiency, flexibility and ergonomics in warehouse and production environments.

Use case 3: Automation of production


This use case deals with the automation of production processes with low quantities and a high number of variants (high-mix, low-volume). The aim is to develop multifunctional robot assistants that can perform standard tasks and learn new tasks through natural interaction or autonomous learning.

Challenges:

  • Multifunctional robots for industrial and logistical handling tasks: The increasing number of small batches and unstructured environments requires flexible robot systems. In laboratory and production environments in particular, robots must be able to handle small and fragile objects safely and manage with limited master data.
  • Robotic systems for cleaning production facilities in the pharmaceutical industry: Cleaning processes are often still carried out manually, which compromises hygiene standards and leads to bottlenecks. Automated systems need to recognize different geometries, find optimal gripping positions and apply effective cleaning strategies.
  • Multifunctional robot cells for precision assembly: The assembly of small and sensitive electronic components is highly complex. The challenges include handling sensitive components, placing them precisely and reliably picking up parts with reflective or transparent surfaces.
  • Multifunctional robot cells for welding processes: Existing solutions for adaptive welding are often unsuitable for large workpieces. Robots must be able to detect the position of workpieces, locate precise weld seams and navigate collision-free in the environment.

AI-supported perception, advanced gripping strategies and optimized motion planning are intended to maximize the automation potential in these areas and create new economic solutions.

Use case 4: AI-supported commissioning


This use case focuses on the use of AI to speed up and reduce costs during the commissioning and reconfiguration of robot systems. The aim is to achieve variant-flexible and economical automation of production.

Challenges:

  • Commissioning/teaching new use cases for production & logistics:
    Specialized expertise is currently required to use robots flexibly for manipulation tasks. Simulations often cannot be transferred directly to reality, as collaborative robots, for example, are less rigid. In addition, adapted programs are usually only suitable for static scenarios.
  • Commissioning and optimization of motion processes in static multi-robot systems:
    The planning of such systems is time-consuming and cost-intensive, as complex modelling processes require extensive expert knowledge.
  • AI-supported system configuration and safety:
    The biggest hurdle for small and medium-sized companies when it comes to automation often lies in the selection and integration of robots and peripheral devices and not just in the code-free programming of the systems. The aim is to increase efficiency and user-friendliness even in the early stages of development.

The use of AI can significantly optimize previous manual and resource-intensive processes, thereby lowering the barriers to flexible automation.