Integration of Model Predictive Control with Deep Reinforcement Learning algorithm - Internship / Masterthesis

Motion planning and controlling for manipulation tasks in human environments is a still challenging problem. There are various approaches and motion control schemes like Model Predictive Control (MPC), are being research in Fraunhofer IPA for making safe human-robot interaction that is the main focus of the internship/master thesis.

Was Sie mitbringen

  • Very good knowleadge into Deep Reinforcement Learning
  • Very good programming skills in C++ and Python
  • Highly motivated to work on challenging tasks
  • Ability to work independently
  • Good English skills (spoken and written)

Was Sie erwarten können

  • The student task would be to adapt existed manipulation software and get familiar with it
  • On other hand, Deep Reinforcement Learning (DRL) is more and more popular now-a-days into various field
  • Finally student has to create interface such that DRL integrate with MPC.
Die Vergütung richtet sich nach den Richtlinien des Bundes über Praktikantenvergütungen.

Fraunhofer ist die größte Organisation für anwendungsorientierte Forschung in Europa. Unsere Forschungsfelder richten sich nach den Bedürfnissen der Menschen: Gesundheit, Sicherheit, Kommunikation, Mobilität, Energie und Umwelt. Wir sind kreativ, wir gestalten Technik, wir entwerfen Produkte, wir verbessern Verfahren, wir eröffnen neue Wege.

Kennziffer: IPA-2019-369 Bewerbungsfrist: -
counter-image