The FLAIROP (Federated Learning for Robot Picking) research project develops a distributed learning approach for pick-and-place robots to robustly recognize and grasp known as well as unknown objects.

The goal is to provide current AI solutions with more data while respecting data protection regulations. There should be no exchange of training data (e.g. images, grasp points, etc.).

The research project is investigating how training data from multiple plants or even companies can be used to increase performance compared to training with a single robot.

The project focuses on automated generation of learning data required for the algorithms for grasp detection, learning data generation and federated learning. Via a cloud structure, the data and algorithms will be made available for distributed learning. This represents the next stage of development of autonomously handling systems in the context of Industry 4.0.

So far, Federated Learning has been predominantly used in the medical sector for image analysis (protection of patient data). A transfer of the technology to the increasingly networked Industry 4.0 / Logistics 4.0 offers strong potential for the robust use of artificial intelligence and development of new, more powerful algorithms - while maintaining data protection guidelines.

For more information and updates on the project, please visit www.flairop.com.