German English

Robust and flexible robot automation in logistics

Used products:N31 | N36X36

Challenge

The logistics industry must handle growing volumes of goods while supply chains remain under pressure and efficiency requirements continue to rise. At the same time, many warehouse employees still perform picking and packing tasks. These tasks are labor-intensive, repetitive, and difficult to scale. As a result, the demand for robotic automation in logistics continues to grow.

Unknown and highly diverse objects

Modern logistics centers handle an almost unlimited variety of products. Items differ greatly in shape, size, weight, surface properties, and packaging. Often, these products are not classified in advance. Robots must still recognize, grasp, and move these unknown items safely. Traditional automation systems designed for fixed geometries quickly reach their limits in such environments.

Dynamic and demanding operating conditions

Logistics environments are also highly dynamic. Lighting conditions change, containers are densely packed, and objects often overlap. Damaged packaging or partially occluded items further complicate detection. Automation systems must work reliably even when products are randomly arranged or only partially visible. Efficient operation therefore requires robust detection methods and fast grasp planning.

Broad range of applications

Automation in logistics must cover a wide range of tasks. These include picking individual items, handling parcels, depalletizing goods, unloading trucks, or sorting luggage. Companies therefore need flexible systems that can adapt to different tasks and object types. Ideally, these systems should operate without extensive reconfiguration. Overall, the key challenge is to develop robotic systems that can handle unknown objects quickly, reliably, and economically under real logistics conditions. This capability is essential for the next stage of warehouse automation.

Application

Instead of relying on a proprietary end-to-end solution, Fizyr uses a modular plug-and-play software concept. The software integrates easily with many different robot platforms. System integrators can choose between collaborative robots (cobots) and traditional industrial robots. This flexibility allows them to tailor picking cells precisely to the requirements of each application. For visual perception, the system uses industrial cameras. These include several of our Ensenso 3D cameras, supported by additional 2D cameras that provide complementary image information.

Precise 3D data for handling unknown objects

The Ensenso 3D cameras provide the spatial information needed to understand each scene. They capture the shape, position, and orientation of objects. Depending on the application, up to four sensors cover the workspace. This setup creates a large field of view and allows the system to capture complex scenes reliably. The resulting 3D point clouds allow the software to detect tightly stacked, overlapping, or randomly arranged items. Based on this data, the system calculates suitable grasping points. Within milliseconds, the algorithms evaluate many possible grasp poses and select the best option. The system can also detect damaged or unsuitable items and remove them before they enter downstream processes.

Robust detection under challenging conditions

Logistics environments place high demands on machine vision. Different materials, reflective surfaces, or transparent packaging complicate object detection. Other challenges include polybags, overlapping objects, and low-contrast scenarios such as light-on-light or dark-on-dark scenes. Ensenso 3D cameras address these challenges by providing reliable depth information. Object detection therefore works independently of surface color or texture. Advanced stereo vision technology further improves measurement accuracy. It also enhances the quality of point clouds, even when scanning difficult materials.

Combining 3D and 2D information

While 3D sensors capture the spatial structure of the scene, additional 2D cameras provide visual details for classification and analysis. By combining both data sources, the system gains a more complete understanding of the objects. The software can classify products, perform quality checks, and determine suitable grasp strategies. This approach also works for previously unknown items with widely varying characteristics.

Overall, the high-performance 3D vision system enables flexible, fast, and reliable picking. It supports a wide range of logistics applications from item picking and parcel handling to depalletizing and truck unloading.

Outlook

E-commerce continues to grow rapidly. As a result, parcel volumes are increasing and logistics operations are becoming more complex. At the same time, labor shortages and changing working conditions are putting additional pressure on logistics companies. Automation therefore plays an increasingly important role. Solutions based on artificial intelligence and advanced machine vision help companies increase productivity, reduce costs, and improve workplace safety.

Global demand for high-quality components for automated picking systems is also rising. System integrators need solutions that are flexible, scalable, and easy to integrate into different system architectures.

The combination of modular software and precise 3D vision meets these requirements particularly well. As a plug-and-play solution, the system integrates easily into both existing and new installations. Operators can therefore adapt their automation systems quickly to new products, changing requirements, or higher throughput targets.

At the center of the solution is a robust 3D vision system. It continuously provides precise information about the shape, position, and condition of objects. These data are essential for reliable handling of a wide range of goods. They also form the foundation for next-generation goods-to-person systems.

Flexible, hardware-independent automation combined with precise 3D sensing will therefore play a key role in the future of logistics—from more efficient warehouse operations to fully connected, scalable distribution

This website is using cookies to provide a good browsing experience

These include essential cookies that are necessary for the operation of the site, as well as others that are used only for anonymous statistical purposes, for comfort settings or to display personalized content. You can decide for yourself which categories you want to allow. Please note that based on your settings, not all functions of the website may be available.

This website is using cookies to provide a good browsing experience

These include essential cookies that are necessary for the operation of the site, as well as others that are used only for anonymous statistical purposes, for comfort settings or to display personalized content. You can decide for yourself which categories you want to allow. Please note that based on your settings, not all functions of the website may be available.

Your cookie preferences have been saved.