Sorry Dave, I'm Afraid I Can't Do That: Explaining Unachievable Robot Tasks Using Natural Language

摘要

This paper addresses the challenge of enabling nonexpert users to command robots to perform complex high-level tasks using natural language. It describes an integrated system that combines the power of formal methods with the accessibility of natural language, providing correct-by-construction controllers for high-level specifications that can be implemented, and easy-to-understand feedback to the user on those that cannot be achieved. This is among the first works to close this feedback loop, enabling users to interact with the robot in order to identify a succinct cause of failure and obtain the desired controller. The supported language and logical capabilities are illustrated using examples involving a robot assistant in a hospital.