Semantic-Aware Real-Time Scheduling in Robotics

Abstract

This paper introduces semantic-aware real-time (SeART), an extension to conventional operating systems, which deals with complex real-time robotics applications. SeART addresses the problem of selecting a subset of tasks to be scheduled depending on the current operating context: mission objectives, other tasks currently executed, the availability or unavailability of sensors and other resources, as well as temporal constraints. Toward this end, SeART is able to represent the semantics of tasks to be scheduled, i.e., what tasks are meant for, and to use this information in the scheduling process. This paper describes in detail the SeART architecture by focusing on representations and reasoning procedures, and presenting a case-study which is related to mobile robotics for autonomous objects transportation.