Result description
In industrial automation applications, there exist a large variety of different component that can be found inside an industrial switchgear.
These components can differ by Brand Manufactures or typologies but even in size, color and more.
Given these challenges, it is difficult to design a vision system capable to identify these components without requiring the creation of a large dataset and the use of extensive human labelled data.
The proposed vision system exploit the detection of features (e.g. holes on the component’s surface) and match the information with the cad to extrapolate the component’s position to precise localize the components positions.
The detection precision is lower than 1mm and with the proposed method the robots are capable to center holes with dimension lower than 2mm without any effort.
Addressing target audiences and expressing needs
- Incubators / Accelerators
We need to get in contact with/for the specific need:
- actors interested in financing the final stage of development of the proposed solution
- companies developing the CAD software used to design the switchgears to integrate more the solution with the design software
- manufacturer of components to define the type and the format of data required to enable the handling of components by the developed platform
- experts in commercial strategies to understand and exploit the market potential
- Other Actors who can help us fulfil our market potential
R&D, Technology and Innovation aspects
A TRL7 demonstrator has been developed.
The next steps consists in:
- obtain new funds for the next development steps
- improving the efficency of the process
- validate the system over a relevant number of products
- validate the system in the industrial scenario
- develop a commercial strategy
- participate to fairs to disseminate the result
