Catering to Real-Time Requirements of Cloud-Connected Mobile Manipulators

In this contribution, we explore real-time requirements of mobile manipulators, a class of intelligent robots, in the context of the ongoing fast-robotics (https://de.fast-zwanzig20.de/industrie/fast-robotics/) project. The project aims at implementing such robots based on (edge-) cloud-services using wireless communication in order to make them more capable and efficient. Instead of trying to universally achieve hard real-time in such a system, we present a mixed real-time approach with an application centered fault tolerance scheme based on transition points and pre-computed alternate plans. We argue that deliberatively addressing uncertainties in timing is similarly important than handling uncertainties e.g. in perception for future intelligent robots.