This project is a collaboration between Toyota's CSRC and MIT AgeLab

JUST ADDED: Videos and Research Results (see bottom of page)

With the rise of automotive entertainment and Telematics systems, U.S. roads and highways are increasingly filled with vehicles that feature in-vehicle systems operated by voice commands.

These voice command systems were created as an alternative to visual manual controls; thus, one of the countermeasures that address driver distraction. Voice controls are intended to help reduce the workload on the driver when performing tasks such as operating a radio, using a media player, making/receiving phones calls or searching for a destination.

But like all driver interfaces, voice interfaces must be well designed so that they help reduce the workload on the driver rather than increasing it. Because the demand may be not be adequately measured by traditional metrics such as lane deviations, there is a need to explore and analyze the physiological effects and workload demand of a voice command system on driver performance.


Toyota’s CSRC and the MIT AgeLab have partnered to study these workload demands and work toward developing tools to assess the development of production voice interface systems.

The CSRC and MIT AgeLab will research the safety impact of in-vehicle voice command technology, exploring numerous factors such as comparisons between driver workload when performing tasks manually and when utilizing a voice command system.

The study will track physiological-based measurements, such as heart rate data, to assess the workload factor on the driver while comparing various production interface systems to analyze how their differences can achieve varying results in reducing workload on the driver.

The study will comprise of 100+ participants, approximately half of whom will be trained on the operation of the voice interface, and the other half, which will not have any training. Both groups will perform tasks with visual-manual controls, and then with the voice interface system.


The study will also utilize both a fixed based driving simulator to collect physiological effects as well as an on-road driving experience to collect driving performance data.


The project will potentially contribute to NHTSA’s ongoing work to develop guidelines for voice interfaces, supporting and informing their studies with NHTSA’s goal of establishing voluntary industry guidelines by 2014.

This two-year project will compare users trained versus those not trained on voice interface systems.

YouTube Videos