Learn More
The goal of this research is to enable mobile robots to navigate through crowded environments such as indoor shopping malls, airports, or downtown side walks. The key research question addressed in this paper is how to learn planners that generate human-like motion behavior. Our approach uses inverse reinforcement learning (IRL) to learn human-like(More)
Sex hormones, including testosterone, are hypothesized to have an influence on the human circadian system. We sampled male students in the period after adolescence. We used the Composite Scale of Morningness (CSM) to assess chronotype and saliva testosterone sampling in 106 University students (23.87±3.56 years; range 19-37) between 26.4.2011 and 6.5.2011,(More)
In this paper, we present a monocular, texture-based method for person detection and upper-body orientation classification. We build on a commonly used approach for person recognition that uses a Support Vector Machine (SVM) on Histograms of Oriented Gradients (HOG) [1] but replace the SVM by a decision tree with SVMs as binary decision makers. Thereby, in(More)
Men sleep shorter and go to bed and get up later than women, thus they are later chronotypes. This difference between the sexes is most pronounced between puberty and menopause indicating the possibility that morningness is subject to sexual dimorphism related to reproductive aspects. The objective of the study was to compare the sleep-wake behavior of(More)
In activity recognition, traditionally, features are chosen heuris-tically, based on explicit domain knowledge. Typical features are statistical measures, like mean, standard deviation, etc., which are tailored to the application at hand and might not fit in other cases. However, Feature Learning techniques have recently gained attention for building(More)
We use shift-invariant Non-negative Matrix Factorization (NMF) for decomposing continuous-valued time series into a number of characteristic primi-tives, i.e. the basis vectors, and their activations, which results in a model-independent and fully data driven parts-based representation. We interpret the basis vectors as short parts of motion that are shared(More)
We interpret biological motion trajectories as composed of sequences of sub-blocks or motion primitives. Such primitives, together with the information, when they occur during a motion, provide a compact representation of movement. We present a two-layer model for movement generation, where the higher level consists of a number of spiking neurons that(More)
Mobbing of predators occurs within a conspecific and heterospecific context but has not been quantified within the framework of a communication network and analysed with respect to heterospecific reciprocity. Here, we used playbacks of mobbing calls to show that mobbing is unequally distributed within a community of deciduous forest birds. Five species(More)
Individuals differ in their timing of sleep (bed times, rise times) and in their preference for morning or evening hours. Previous work focused on the relationship between academic achievement and these variables in secondary school students. The main aim of the study is to investigate the relationship between chronotype and academic achievement in(More)
Individuals differ in their circadian preferences (chronotype). There is evidence in the literature to support a season-of-birth effect on chronotype but the evidence is not convincing. In part, the relationship is obscured by a number of methodological differences between studies, including the measures used to define morningness, the way in which the(More)