The Artificial Passenger is a telematics device, developed by IBM, that interacts verbally with a driver to reduce the likelihood of falling asleep at the controls of a vehicle. It is based on inventions covered by U.S. Patent 6,236,968. The Artificial Passenger is equipped to engage a vehicle operator, holding conversations, playing verbal games, controlling the vehicle's stereo system, and so on. It also monitors the driver's speech patterns to detect fatigue, and in response may suggest that the driver take a break or get some sleep. The artificial passenger can also be integrated with wireless services to provide weather and road information, driving directions and other notification systems.
According to Dimitri Kanevsky, a former IBM researcher, currently at Google, The Artificial Passenger was developed using the Interactivity for Telematics (CIT) conversation system that features the driver's natural speech rather than the use of hands. The CIT is based on a natural language comprehension system (NLU) that is difficult to develop due to the low power computer systems available within the cars. IBM suggests that this system be located on a server and accessed through the wireless technologies of automobiles. IBM also says they are working on a "quasi-NLU" that uses less CPU resources and can be used inside the car. The CIT system includes another system called Dialog Manager (DM). The DM takes charge of the NLU system by interacting with vehicle, driver and external systems such as weather systems, email, telephones and more.
The NLU system receives a voice command from the controller and looks through a file system to come up with an action to perform and executes that action. [6] The DM works with questions asked by the driver, "How far is Gallatin Field Airport from here?" The NLU system will not yet be able to understand everything a driver says. The reasons for this are the different languages and dialects of the different regions. IBM is working on developing a system that recognizes where the driver is and recognizes the regional diction used in that area.
Another system used within this technology is the Learning Transformation (LT) system that monitors the actions of the occupants of the car and the cars surrounding it, learns patterns within the driver's speech and stores that data and learns of such data To try to improve the performance of the technology as a whole.
An artificial passenger (AP) is a device that would be used in a motor vehicle to make sure the driver stays awake. IBM has developed a prototype that holds a conversation with a driver, telling jokes and asking questions to determine if the driver can respond alert enough. Assuming IBM's approach, an artificial passenger would use a microphone for the driver and a voice generator and the vehicle's audio speakers to talk to the driver. The conversation would be based on a personalized driver profile. A camera could be used to evaluate the driver's "facial condition" and a voice analyzer to assess if the driver was becoming sleepy. If a driver seemed to show too much fatigue, the artificial passenger could be programmed to open all windows, sound a buzzer, increase the volume of background music, or even spray the driver with icy water. Conversational interactivity for telematics systems can significantly improve the driver-vehicle relationship and contribute to driving safety. However, the development of natural language understanding (NLU) for CIT is a difficult problem that normally requires significant computing resources that are not normally available in the local computer processors that car manufacturers provide for their cars. To solve this problem, NLU components must be located on a server that is remotely accessed by cars or NLU's ability to run on local computing devices (usually based on embedded chips) must be reduced.