The O3R platform is the holistic solution for the central, synchronized processing of image and sensor information in autonomous mobile robots such as AGVs. The simplified integration and reliable interaction of cameras and sensors enables the robust implementation of relevant functions such as collision protection, navigation and positioning. In addition, stationary tasks for the analysis and dimensioning of objects can also be implemented, which can be managed more effectively using multiple cameras. This can be the measurement of pallets, tree trunks, packages or suitcases.

Powerful and open

The central unit for sensory processing The core of the system is a high-performance computing unit called the Video Processing Unit (VPU), which uses yocto Linux on NVIDIA Jetson TX2 embedded hardware. Based on a Docker architecture, open development environments such as Python, C++, CUDA and ROS are supported. Up to six camera heads can be connected to the processing unit, as well as additional sensors via a Gigabit Ethernet interface, e.g. for measuring distances.
All relevant “senses” that an AGV needs for safe autonomous navigation are thus available at a central point.

Camera head with imager from our own development

Ifm also offers suitable, powerful camera heads as part of the platform solution right from the start: The 2D/3D cameras have an opening angle of either 60° or 105° and are equipped with the latest time-of-flight imager from pmdtechnologies ag . The company of the ifm group of companies develops all sensors for the vision products of the automation specialist and tailors them precisely to the respective requirements.
Thanks to the modulated infrared light, the 2D/3D camera captures objects with maximum reliability, even when exposed to increased ambient light.