NebulaRecognition®

NebulaRecognition^® is our random or structured bin picking solution, utilizing an advanced object recognition algorithm paired with a robot cell builder and simulator. Our software runs entirely locally, from user-led object teaching to robot cell environment setup. 

NebulaRecognition^® is an intelligent, lightweight recognition engine that learns from point cloud samples and locates the model anywhere in the scene, regardless of its location (X, Y, Z) and orientation (Rx, Ry, Rz). The optimized algorithms of NebulaRecognition allow recognition to run fast — even on low power CPUs.  

NebulaRecognition^® does not require CAD files to learn. Additionally, many competitive object recognition techniques involve segmentation or deep neural networks, which are computationally costly and require weeks of “hand crafting” thus making them unscalable and unreliable. 

Teaching objects is quick, easy, and user-defined: to teach an object, simply trigger the sensor, click “Teach,” and erase the background.