Skilltellect are the specialists in the development of intelligent computer vision systems for a variety of tasks related to robotization and production automation.
The Skilltellect team has trained their own neural network models and developed optimal machine vision algorithms that eliminate the need for precise object positioning, recognize and provide coordinates for complex and non-typical items such as:
- transparent objects
- shiny objects
- objects of complex shape
FEATURES OF OUR SOLUTIONS: Working with 2D and 3D cameras including selection of optics for the task, based on the customer's needs. Working with permanently fixed cameras and cameras installed directly on the robot. Output of object coordinates in the coordinates of the robot. Handle unstable object sizes (or positions). Cloud and local solution.
SOLVED TASKS:
- detection of the item positioning
- in dynamics
- in statics
- dimensioning of the items
- detection of item’s edges
- checking the condition of the object
- quality inspection of objects (QC)
- bar code reading
- optical character recognition
- search, selection and counting of specific models
AREAS OF APPLICATION
Bin-picking
A vision system that can distinguish randomly lying objects and obtain coordinates for the robot to pick them up. Then the integrator uses these coordinates to set the robot's movements and other commands.
Palletizing - depalletizing
A vision system that distinguishes randomly lying objects for automatic loading/unloading of goods onto/from the pallet(s) for further transportation, significantly reducing object positioning requirements.
Machine tending
Skilltellect's machine tending system allows loading and unloading of workpieces and items from machines for their further processing with significantly reduced requirements to workpiece positioning (workpieces are brought to the machine on a cart without moving them into trays with cells).
Quality inspection robot
The Skilltellect vision robot is capable of acting as an inspection specialist. Depending on the task, the optics can be installed either on the robot or on a tripod. Our software allows to find rejects, shortages, incorrect positioning of the object, etc.
Other autonomous robotic systems where machine vision is required
ADVANTAGES: our own software based on our trained neural networks and developed machine vision algorithms the use of easily available and inexpensive cameras the cost of a typical solution is about 3-4 times lower than using equipment from Cognex, Photoneo, KEYENCE, etc.
|
Fill out the survey to receive a detailed technical and commercial proposal for your solution.
|
Video
Gallery
