MAchIne learning for Design of industrial Robots MAID-Robot
|Coordinator||Linköpings universitet - Institutionen för ekonomisk och industriell utveckling|
|Funding from Vinnova||SEK 500 000|
|Project duration||November 2018 - November 2019|
|Venture||Banbrytande idéer inom industriell utveckling|
|Call||Banbrytande idéer inom industriell utveckling - 2018|
Purpose and goal
The project MAID-Robot want to streamline the development process for complex mechatronics products, such as industrial robots, by letting algorithms based on machine learning and artificial intelligence leverage on the large amounts of data available. The algorithms will make the development process more efficient, and will steer an optimization strategy that automatically proposes a product family consisting of a set of customized industrial robots that fits the customer needs.
Expected results and effects
The project involves a radical change in product development, as we suggest that machines and algorithms will automatically search large amounts of data and then propose customized products. The project is expected to shorten the lead time an order of magnitude, i.e. from years to months. In the same time, the products produced will better fit with the customers´ real needs. Thus, efficiency will increase both in the development processes of the product as well as when the products are used by the customers.
Planned approach and implementation
The project is run by the Department of Machine Design at Linköping University in collaboration with ABB. The project builds upon earlier collaboration between LiU and ABB Robotics and ABB Corporate Research. The project is broken down into 5 work packages. First, a state-of-the-art study is performed, and then an integrated digital framework for industrial robot design is created. Thereafter, ML algorithms are developed to drive the framework. Then the project enters into a test and validation phase. The final work package is consortium building for future applications.