ABSTRACT
Given the explosion of autonomous technology in transportation systems, medicine, and business settings, the need for humans as supervisors of and collaborators in complex autonomous control systems is also rapidly growing. Autonomous systems are often brittle and need humans for their more abstract abilities in knowledge synthesis, and judgment, requiring coordination and teamwork between humans and machines for both improved system safety and performance. This talk will discuss recent research in the Duke University Humans and Autonomy laboratory that focuses on modeling humans in such collaborative cyberphysical systems in order to better understand design implications for autonomy. Examples will focus on the modeling and design of drone control and pedestrian alerting systems.