Abstract-In this paper, we present an approach that applies the reinforcement learning principle to the problem of learning height control policies for aerial blimps. In contrast to previous approaches, our method does not require sophisticated handtuned models, but rather learns the policy online, which makes the system easily adaptable to changing conditions. The blimp we apply our approach to is a small-scale vehicle equipped with an ultrasound sensor that measures its elevation relative to the ground. The major problem in the context of learning control policies lies in the high-dimensional state-action space that needs to be explored in order to identify the values of all state-action pairs. In this paper, we propose a solution to learning continuous control policies based on the Gaussian process model. In practical experiments carried out on a real robot we demonstrate that the system is able to learn a policy online within a few minutes only.

We present an algorithm for a distribution and decentralisation of the unscented Kalman filter and the underlying non-linear models. The filter itself is the adaption of a distribution scheme of linear filters. The distribution of the underlying models leads to small, scalable filter nodes which allow precise non-linear estimation