AI4DI - Skynet R&D Services

AI4DI aimed to strengthen and expand AI usage in the European industry digitization process, through the transfer of machine learning and AI from the cloud to the edge in manufacturing, mobility, and robotics. To achieve these goals, AI4DI connected factories, processes, and devices within digitised industry by utilizing ML and AI for human-machine collaboration, change detection, and the detection of abnormalities.

Funding

The project was co-funded by grants from Germany, Austria, Finland, France, Norway, Latvia, Belgium, Italy, Switzerland, and Czech Republic and - Electronic Component Systems for European Leadership Joint Undertaking (ECSEL JU), under grant agreement No 826060.

Contribution

In this project, EDI's robotics group led the Sub Supply Chain 3.2 “Smart Robot,” which consisted of different cognitive sensor modules forming the basis for three use cases that could supply different industries using AI-based solutions. Robotics group developed cognitive sensing to perceive and understand dynamically changing environments for randomly dropped object detection, pose estimation, and pick-up by an industrial robot - AI was used to analyze the data of a stereo vision system incorporating processing on the edge (FPGA-based SoC). The training process was accelerated in collaboration with VIF by introducing semi-automatic labelling approaches and the generation of synthetic, life-like labelled data. Furthermore, standardized, extensive automated testing and validation of the reliable localization and classification of objects was carried out. A technology demonstrator was developed: Smart robot with advanced vision, sensing, and human gesture understanding capabilities, which was evaluated by the Latvian Academy of Sciences in the annual Science Achievements Competition as one of the most significant scientific achievements in Latvia in 2022