Programming by Demonstration for Health Robots
The purpose of this project is to demonstrate how in-depth AI analyses of process data can be used to make data-driven optimisation choices in a production context.

Background
Often the difference between a good and a bad ultrasound scan is the way the ultrasound probe is moved and angled in relation to the patient's anatomy. It is a knowledge that is built up through many years of experience and is difficult to automate through traditional robot programming.
Purpose / Vision
The purpose of this project is to test the use of Programming By Demonstration to program robotic movements for health robots.
Expected results
The expected result of this project is an adaptation of the PbD method to health applications, where the method is tested on two different use cases, where professionals from the health sector show the robot how to move and from these demonstrations a robot movement is calculated.
The focus of the project will be on
- Analysis and selection of algorithms to be worked on in collaboration between companies and universities
- Testing and implementing algorithms
Project participants
- Syddansk Universitet (Project lead)
Want to learn more about this project?
Curious to find out more about the project and how you can get involved? Get in touch with Ole.

Knowledge-based innovation and the Fehmarn Belt project