In this paper, we present a prototypical system as platform for a new generation of robotic workers. Dealing with customization, individualization and finally customer driven batch sizes of products of highest quality requires robot technologies that are able to compensate uncertainties inherent in processes and environment. Existing production plants are planned for the majority of variants, but for a significant portion of all products the flexibility of human workers is still required for production. Therefore technologies are required allowing intuitive access to robotic system components without being a robot expert. The main contribution of the paper is a novel framework for robotic workers combining perception, autonomous planning and a user-centered design of human-robot interaction. We also present an industrial interface that allows the operator to immerse into complex industrial robot processes and to transfer task knowledge and strategies for commanding robots on a high-level. The framework and its embedded methods have been implemented and evaluated in a bin picking scenario for small batch sizes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.