Cooperative agents and recognition systems (CARS) for drivers and passengers

Abstract

We present SRI's vision of the human-machine interface for a car environment. This interface leverages our work in human-computer interaction, speech, speaker and gesture recognition, natural language understanding, and intelligent agent architectures. We propose a natural interface that allows the driver to interact with the navigation system, control electronic devices, and communicate with the rest of the world much as would be possible in the office environment. Passengers would be able to use the system to watch TV or play games in their private spaces. The final prototype will be fully configurable (languages, voice output, and so forth), and will include speaker recognition technology for resetting preferences and/or for security.