NF - 07 - 1 - 0216 52555 - MA - MUR . 15 Conference Proceeding

Sorry Dave, I'm afraid I can't do that: Explaining unachievable robot tasks using natural language Report Title This paper addresses the challenge of enabling non-expert users to command robots to perform complex highlevel 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. Conference Name: Robotics: Science and Systems IX Conference Date: June 24, 2013 Sorry Dave, I’m Afraid I Can’t Do That: Explaining Unachievable Robot Tasks Using Natural Language Vasumathi Raman∗, Constantine Lignos†, Cameron Finucane‡, Kenton C.T. Lee†, Mitch Marcus† and Hadas Kress-Gazit‡ ∗Department of Computer Science, Cornell University, Ithaca, NY 14850 Email: [email protected] †Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104 Email: [email protected], [email protected], [email protected] ‡Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, NY 14850 Email: [email protected], [email protected] Abstract—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.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.