KoMoProd Human Robot Collaboration - Profactor GmbH

Enabling robotic systems to collaborate with humans is a challenging task, on different levels of abstraction. Such systems need to understand the circumstances under which they operate, by perceiving, planning, reasoning to team up with a human worker. The robotic system should have perspective taking capabilities in order to efficiently collaborate with the human. In this work we propose an integrated cognitive architecture that aims to develop perspective taking capabilities using human preferences. This is achieved by developing a ‘mental model’ that takes human preferences, the knowledge of the task, the properties of the objects involved, and the capabilities of the human and the robot. The mental model forms the basis of the cognitive architecture, to perceive, reason and plan in the human-robot collaborative scenario. We also evaluate the proposed architecture’s ability in collaborating with the human to complete an assembly process. The performance of the cognitive architecture is evaluated against varying human preferences and dynamic changes in the environment