Machine Learning Models to Enhance the Science of Cognitive Autonomy

Intelligent Autonomous Systems (IAS) are highly cognitive, reflective, multitask-able, and effective in knowledge discovery. Examples of IAS include software systems that are capable of automatic reconfiguration, autonomous vehicles, network of sensors with reconfigurable sensory platforms, and an unmanned aerial vehicle (UAV) respecting privacy by deciding to turn off its camera when pointing inside a private residence. Research is needed to build systems that can monitor their environment and interactions, learn their capabilities and limitations, and adapt to meet the mission objectives with limited or no human intervention. The systems should be fail-safe and should allow for graceful degradations while continuing to meet the mission objectives. In this paper, we provide an overview of our proposed new methodologies and workflows, and survey the existing approaches and new ones that can advance the science of autonomy in smart systems through enhancements in real-time control, auto-reconfigurability, monitoring, adaptability, and trust. This paper also provides the theoretical framework behind IAS.