Programming a robotic is a complex task, as it demands the user to have a good command of specific programming languages and awareness of the robot's physical constraints. We propose a framework that simplifies robot deployment by allowing direct communication using natural language. It uses large language models (LLM) for prompt processing, workspace understanding, and waypoint generation. It also employs Augmented Reality (AR) to provide visual feedback of the planned outcome. We showcase the effectiveness of our framework with a simple pick-and-place task, which we implement on a real robot. Moreover, we present an early concept of expressive robot behavior and skill generation that can be used to communicate with the user and learn new skills (e.g., object grasping).

Magnetic fields are known to play a prominent role in the dynamics and the energy budget of astrophysical systems on galactic and smaller scales, but their role on larger scales is still elusive [1]. In galaxies and galaxy clusters, the observed magnetic fields are assumed to result from the amplification of much weaker seed fields. Such seeds could be created in the early universe, e.g. during phase transitions or inflation, and then amplified by plasma processes. If the generation mechanism of such primordial fields (e.g. by sphaleron processes) breaks CP, then the field will have a non-zero helicity. Since helical fields decay slower than non-helical ones, a small non-zero initial helicity is increasing with time, making the intergalactic magnetic field (IGMF) either completely left-or right-helical today. A clean signature for a primordial origin of the IGMF is therefore its non-zero helicity. In a series of works, Vachaspati and collaborators worked out possible observational consequences of a helical IGMF, introducing the " statistics" as a statistical estimator for the presence of helicity in the IGMF [2].