A faster way to teach a robot : vimarsana.com

A new technique enables a human to efficiently fine-tune a robot that failed to complete a desired task with very little effort on the part of the human. Their system uses algorithms, counterfactual explanations, and feedback from the user to generate synthetic data it uses to quickly fine-tune the robot.

Related Keywords

Julie Shah , Tianmin Shu , Pulkit Agrawal , Andreea Bobu , Aviv Netanyahu , International Conference On Machine , York University , National Science Foundation Graduate Research Fellowship , Stevens Institute Of Technology , University Of California At Berkeley , Hyundai Motor Corporation , Watson Ai Lab , Artificial Intelligence Laboratory , Interactive Robotics Group , National Science Foundation Institute For Artificial Intelligence , Andi Peng , New York University , Stevens Institute , Computer Science , International Conference , Open Philanthropy , National Science Foundation Institute , Artificial Intelligence , Human Robot Interaction , Istribution Shift , Data Augmentation , Ounterfactual Explanations ,