Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for selecting a modality for interfacing between a user and a robot. In some implementations, a system determines that a particular action requires user confirmation before being performed. The system receives position data indicating a level of proximity of a user to a robot and environmental data indicating environmental conditions sensed by the robot. The system selects a particular mode for obtaining confirmation of the action from among multiple modes of interfacing with users based on one or more of the position data and the environmental data. The system provides a request confirmation of the action using the particular mode for presentation to the user.