“Contextual Awareness for Robust Robot Autonomy”

Contextual awareness refers to having autonomous robots reason about their capabilities and limitation and improve on those limitations through the help of others. This project explored three areas of contextual awareness – detecting when anomalous behaviors occur, reacting to situations where plans are failing, and learning new plans through human demonstration. Each of these areas is important in achieving robust, reliable robot autonomy. The work on detecting anomalous behavior focused on finding subtle anomalies that could not be detected from single events; the work on reacting to failing plans focused on deciding when to switch between risk-neutral and risk-seeking policies, for domains in which the goal is to achieve above a certain threshold of reward; and the work on learning new plans focused on complex manipulator trajectories, where multiple human examples are combined so as to smooth out noise in the examples without losing important details. The first and third areas were demonstrated using actual robots; the second area was demonstrated using a video game simulator. Contextual awareness refers to having autonomous robot systems reason about their capabilities and limitation and improve on those limitations through the assistance of others. The idea is for robots t