Making Human-Robot-Interaction HRI safer by testing the learning capabilities of industrial collaborative Robots

Master

The future of industrial robotics is rooted in the development of robots that can collaborate and learn with humans. These collaborative robots would have the ability to evolve and improve their behaviors through the usage of machine learning algorithms. However, understanding how to control and test the learning skills of uncaged, single- or multi-arm robots and their ability to safely interact with humans is challenging as their expected improvements are not precisely known. Testing such robots is becoming a crucial research area where the combination of skills in software testing, machine learning, and robotics is strongly required. The ambition of the multi-disciplinary T-LARGO project is to develop a new scientific and technological foundation enabling the testing of learning collaborative robots. The objective is the construction of an open test platform dedicated to collaborative robots, while its impact lies in major scientific breakthroughs on how to test and control robots equipped with artificial intelligence.

Goal

The goal is to make HRI more safe for both humans as well as robots by giving collaborative robots more intelligence using Deep Learning.

Learning outcome

  • Working with UR3 and UR5 collaborative robot along with a 3D camera
  • Working in an interactive and collaborative research environment
  • Opportunities to publish the results in conferences and journals

Qualifications

  • Knowledge of python and LaTeX
  • Basic knowledge of Machine Learning and Deep Learning
  • Basic knowledge of Robotics

Supervisors

  • Mohit Kumar Ahuja

Collaboration partners

ABB Robotics Norway

Contact person