For the best human-robot interaction experience, the robot's navigation policy should take into account personal preferences of the user. In this paper, we present a learning framework complemented by a perception pipeline to train a depth vision-based, personalized navigation controller from user demonstrations. Our refined virtual reality interface enables the demonstration of robot navigation trajectories under motion of the user for dynamic interaction scenarios. In a detailed analysis, we evaluate different configurations of the perception pipeline. As the experiments demonstrate, our new pipeline compresses the perceived depth images to a latent state representation and, thus, enables efficient reasoning about the robot's dynamic environment to the learning. We discuss the robot's navigation performance in various virtual scenes by enrolling a variational autoencoder in combination with a motion predictor and demonstrate the first personalized robot navigation controller that solely relies on depth images.

Duetotheavailabilityof highly efficient unmanned aircraft (UA) and the advancement of the necessary technologies, the use of UA for object manipulation and cargo transport is becoming a more and more relevant research area. A reliable identification and localization of cargo and interaction objects as well as maintaining the required flight precision are essential to guarantee a successful object handling. Within this paper we demonstrate the successful application of an autonomous UA equipped with a lightweight suction gripper for object interaction. We discuss the approach used for precise localization as well as the identification and pose estimation of individual gripping objects. Concluding, the overall system performance is evaluated within an industrial-oriented use case.