Cambrian vision system
The system is based on AI. To make accurate predictions the AI model uses just the image data from the stereo camera that can be mounted on the robot or above the workplace. It doesn’t not need any external lights such as structured light or infrared light to make predictions. Hence it is very robust for any light external light conditions. The AI model is able to calculate exact part locations and suitable grasp points within 200ms.
The system can pick a wide range of different parts, including typical plastic and metal parts and also transparent, thin, or very shiny metal parts. The standard camera module can pick parts from sub millimeter range to parts fitting in a 20cm cube. For larger parts we provide a slightly larger camera module.
The system is quick to install and various attachment plates to common UR ecosystem grippers are provided.