Debugging and monitoring robotic applications is a very intricate and error-prone task. To this end, we propose a mixed-reality approach to facilitate this process along a concrete scenario. We connected the Microsoft HoloLens smart glass to the Robot Operating System (ROS), which is used to control robots, and visualize arbitrary flight data of a quadrocopter. Hereby, we display holograms correctly in the real world based on a conversion of the internal tracking coordinates into coordinates provided by a motion capturing system. Moreover, we describe the synchronization process of the internal tracking with the motion capturing. Altogether, the combination of the HoloLens and the external tracking system shows promising preliminary results. Moreover, our approach can be extended to directly manipulate source code through its mixed-reality visualization and offers new interaction methods to debug and develop robotic applications.

No abstract

Automated driving in urban scenarios requires efficient planning algorithms able to handle complex situations in realtime. A popular approach is to use graph-based planning methods in order to obtain a rough trajectory which is subsequently optimized. A key aspect is the generation of trajectories implementing comfortable and safe behavior already during graph-search, while keeping computation times low.To capture this aspect, on the one hand, a branching strategy is presented in this work that leads to better performance in terms of quality of resulting trajectories and runtime. On the other hand, admissible heuristics are shown which guide the graph-search efficiently, where the solution remains optimal.

No abstract

No abstract