Smart Automotive Headlights for Safe Driving

Source Organization:Carnegie Mellon University
University:Carnegie Mellon University
Principal Investigator:Srinivasa G. Narasimhan
PI Contact Information:srinivas@cs.cmu.eduTel: 412-268-1199
Project Manager:Srinivasa G. Narasimhan
Funding Source(s) and Amounts Provided (by each agency or organization):Intel Science and Technology Center – Embedded Computing, $100000
Total Dollars:$55,000
Agency ID/Contract/Grant Number:
Start and End Dates:01/2013-12/2013
Project Status:Complete
Subject Categories:Vehicles and Equipment
Safety and Human Factors
Abstract:The long term goal of the project is to develop the next generation headlights for vehicles, that are programmable, multi-task, react to the road environment and enhance driver safety. Smart headlights will better illuminate the road, spotlight obstacles, signs and lanes, project directions on the road, reduce glare and increase visibility in dangerous rain and snowstorms. The U.S. National Highway Safety Administration reports that annually 400000 crashes and 4000 fatalities happen during rain and snowstorms at night. The additional cost of the headlight will be small (a few hundred dollars per vehicle) compared to the direct and indirect savings due to reduced crashes. The project has strong commercialization potential, with vehicle exterior lighting becoming more and more adaptive recently. For 2013, the goal will be to design and build a prototype headlight with 500 Hz reaction capability and algorithms that can detect and highlight obstacles as well as reduce glare for oncoming drivers. This prototype will be tested in laboratory conditions and outdoors.
Describe Implementation of Research Outcomes (or why not implemented):Midway through 2013, we have completed the initial design of the headlight (see top figure) that consists of three components: a camera to observe the environment, a processing unit that analyzes the captured imagery and a spatial light modulator that controls the headlight beams in space and time for the required task.

One of the tasks for this headlight is to stream light between precipitation particles so that the drivers can see better at night during rain and snow storms (see illustration). A prototype has been built according to this design. In the rest of the year, we will develop algorithms for this hardware prototype.
Impacts/Benefits of Implementation (actual, not anticipated):The project presents a revolutionary new design for vehicular exterior lighting. The prototype built in this project already can be used for many tasks to help drivers – reduce glare, highlight signs and obstacles. Developing and incorporating this prototype into commercial vehicles is a longer term goal that is certain to reduce crashes and increase driver safety.
Project URL: