Learns in one shot. Finds any angle. Runs a digital twin.
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.
Unlike competition, 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.
Please fill out the form to access the NebulaRecognition® brochure.
Features
Instant Learning
Instant learning time (with or without CAD)
Local Processing
Objects trained locally on lightweight C++ based software
Precise Point Cloud Recognition
Precision point cloud recognition engine
Multi-Object Recognition
Simultaneously recognizes multiple different objects
Rotation Recognition
Excels at recognizing rotated objects
Surface Dimension Recognition
Can recognize surfaces of specific dimensions
Feature Dimension Recognition
Can recognize ridges, cylinders, and pins of specific dimensions
High-Capacity Part Learning
Learns up to 99 parts per settings file
HD RGB Sensor
High definition, RGB point cloud sensor
Planner + Sequencer
Planner is the intuitive bin picking application builder designed to optimize picking and avoid collisions in the application environment. It’s a 3D robotic cell digital twin that communicates directly with your robot, guiding it to pick parts located by NebulaRecognition®.
All programming can be done in Sequencer, which is a drag-and-drop, node-based programming structure which allows you to design and customize your bin picking application.
Features
Digital Twin Environment
Highly customizable bin picking robot cell environment builder, driver, and simulator
Live Bin Picking Operation
Runs live bin picking session
Tracks Robot Motion in Real Time
Tracks robot motion real time
Collision-Free Robot IK Solver
Solves robot IK with collision avoidance for many robot models
Robot Position Teaching
Teach robot positions directly from software
Customizable Picking Location Assignment
Assign and customize picking locations
Drag-and-Drop Block Programming
Drag-and-drop block step programming for application sequence (0 – minimal robot programming)
Robot Motion and IO Control
Robot speed/acceleration, motion blending, engage tooling, and send IO commands to robot
Multiple Application Storage
Stores multiple bin picking applications
Dual Sensor Applications
Supports two-sensor applications
Robot-Mounted And Fixed Sensor Applications
Supports robot-mounted and/or fixed-sensor applications
Dynamic Bin Alignment
Bin alignment for automatic detection and repositioning when a new bin is placed for emptying
Terrace
The Terrace is the sensor behind NebulaRecognition®’s high-definition point cloud generation. The Terrace is qualified for both robot-mounted and fixed-sensor applications.
Contact us
NebulaRecognition® is a highly customizable and intelligent bin picking solution.
For more information, email us at info@recognitionrobotics.com or fill out this form.