A UAS capability description framework: Reactive, adaptive, and cognitive capabilities in robotics

Abstract

This paper offers a framework that helps in characterizing, analyzing, and developing Unmanned Autonomous Systems (UAS) capabilities including autonomy, adaptability, and machine cognition. We propose a technical reference model that brings these levels of capabilities together into a three-dimensional graphical model. Based on this technical reference model, we offer a system-theoretic analysis framework that includes three views into systems capabilities - reactive, adaptive and cognitive. For illustration purposes, this framework is applied to the analysis of capabilities of autonomous systems derived from four fundamental schools of thought in robotics - deliberative, reactive, hybrid and probabilistic. This exercise helps in understanding where the state of the art currently is in terms of UAS capabilities, what capabilities modern UAS lack, and what capabilities could be expected in the near future. The approach presented in this work provides a useful foundation for capability development and capability testing in UAS.