arXiv subjects
Publications and source records attributed to Frank Hees.
This paper aims to explore the problem of trajectory prediction in heterogeneous pedestrian zones, where social dynamics representation is a big challenge. Proposed is an end-to-end learning framework for prediction accuracy improvement based on an attention mechanism to learn social interaction from multi-factor inputs.
Guided Policy Search enables robots to learn control policies for complex manipulation tasks efficiently. Therein, the control policies are represented as high-dimensional neural networks which derive robot actions based on states. However, due to the small number of real-world trajectory samples in Guided Policy Search, the resulting neural networks are only robust in the neighbourhood of the trajectory distribution explored by real-world interactions. In this paper, we present a new policy representation called Generative Motor Reflexes, which is able to generate robust actions over a broader state space compared to previous methods. In contrast to prior state-action policies, Generative Motor Reflexes map states to parameters for a state-dependent motor reflex, which is then used to derive actions. Robustness is achieved by generating similar motor reflexes for many states. We evaluate the presented method in simulated and real-world manipulation tasks, including contact-rich peg-in-hole tasks. Using these evaluation tasks, we show that policies represented as Generative Motor Reflexes lead to robust manipulation skills also outside the explored trajectory distribution with less training needs compared to previous methods.
Staying abroad during their studies is increasingly popular for students. However, there are various challenges for both students and universities. One important question for students is whether or not achievements performed at different universities can be taken into account for either enrolling at a foreign university or for completing the studies at their home university. In addition to university achievements, an increasing proportion of the 195 million students worldwide increasingly receive certificates from MOOCs or other social media services. The integration of such services into university teaching is still in the initial stages and presents some challenges. In this paper we describe the idea to manage all these study achievements worldwide in a blockchain, which might solve the national and international challenges regarding the recognition of student achievements. The aim of this paper is to encourage discussion in the global community instead of presenting a finished concept. Some of the open research questions are: How to ensure student data protection, how to deal with fraud and how to deal with the possibility that students can analytically calculate the easiest way through their studies?