Scheduling mobile exploration tasks for environment learning

Autonomous mobile service robots navigate in their environments in order to perform tasks requested by users. We envision service robots learning about their environment by scheduling exploration tasks in which they seek out new knowledge and using this knowledge to improve the services they offer. We present the Task Graph algorithm, which chooses times for user requests based on the robot's knowledge so as to increase the chance of success, and schedules exploration tasks in between user requests by reducing the problem to a graph search.