Autonome Lernende Roboter (ALR)
Prof. Dr.  Gerhard Neumann

Prof. Dr. Gerhard Neumann

  • Adenauerring 4

    Gebäude 50.21

    76131 Karlsruhe

About me

I am a full professor at the KIT and heading the chair "Autonomous Learning Robots" since Jan. 2020. Before that, I was group leader at the Bosch Center for AI and industry on campus professor at the University of Tübingen (from March to Dec. 2019) and full professor at the University of Lincoln in the UK (2016-2019). I completed my PhD in 2012 at the TU Graz and was afterwards PostDoc and Assistant Professor at the TU Darmstadt.

I am convinced that our society will gain great benefits from autonomous robots in the following years. For example, in my research, I am concentrating on two robotic applications that have huge societal needs, nuclear and agri-culture robotics. Clean-up and decommissioning of nuclear waste will be one of the biggest challenges for our and the next generations with enormous predicted costs. Nuclear decommissioning is an obvious application for robotics as handling nuclear waste is too dangerous for humans. Apart from that, our agri-tech industry is relying heavily on low-wage labour, such as fruit picking, and is often struggling to find workers that are willing to do the straining work. Paying the fruit pickers typically amounts for 50% to 60% of the costs of producing the crop. Robotics has a huge potential to completely change this industry as the farming process can be more and more automated. What have these two very different application fields in common? They represent very challenging real world scenarios that are quite different from the lab environments typically considered in robotics research. Such environments are unknown and unstructured, consisting of objects of unpredictable shapes or even other, unknown agents such as humans. The robot can encounter so many different situations while interacting with such environments that pre-programming such tasks seems to be infeasible. In addition, the field of autonomous, learning robots has recently gained a lot of momentum due to recent successes of deep learning in robotics. However, the complexity of the envisaged tasks still seems to be out of reach for such methods.

My research is therefore focused on the intersection of machine learning, robotics and human-robot interaction. My goal is to create data-efficient machine learning algorithms that that are suitable for complex robot domains. A strong focus of my research is to develop new methods that allow a human non-expert to intuitively teach a robot complex skills as well as to allow a robot to learn how to assist and collaborate with humans in an intelligent way. In my research, I always aim for a strong theoretical basis for my developed algorithms which are derived from first order principles. Yet, I also believe that an exhaustive assessment of the quality of an algorithm in a practical application is of equal importance.