Towards a General Communication Concept for Human Supervision of Autonomous Robot Teams
Karen Petersen, Oskar von Stryk · 2011
Abstract—Towards a general concept for human supervision of autonomous robot teams supporting the specific strengths of humans and robots, a communication concept between robots and a human supervisor is presented in this paper. The communication goal is to let the supervisor control a robot team with high-level commands, e. g., by adapting mission details and influencing task allocation in a manner that is applicable to different task allocation methods in general. For this purpose, the supervisor needs a high-level overview of the current state of mission and robots, which can be obtained with the presented approach. Relevant, important events are detected by the robots using complex event processing, and are labeled by topic and priority. A policy system controls the amount of messages that are sent to the supervisor. Notifications are used to inform the supervisor about the mission progress, unexpected events and errors. Queries are used to transfer decisions to the supervisor, to make use of implicit knowledge and experience in critical situations. The robots ’ level of autonomy can be adapted using policies, that require decisions to be either taken autonomously by the robots, or with support by the supervisor, using different query modes. Example scenarios from different applications including urban search and rescue will be used for validating the proposed concept. Keywords-human-robot team interaction; supervisory control; complex event processing; policies I.