Login

Project

#157 Projects Smart Automotive Headlights for Safe Driving


Principal Investigator
Srinivasa Narasimhan
Status
Completed
Start Date
Jan. 1, 2014
End Date
Dec. 1, 2014
Research Type
Advanced
Grant Type
Research
Grant Program
MAP-21 TSET - Tier 1 (2012 - 2016)
Grant Cycle
2014 TSET UTC
Visibility
Public

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.    
Description
http://www.cs.cmu.edu/~ILIM/projects/IL/smartHeadlight/    
Timeline
01/2013-12/2013

2010-2011
The smart headlight was born as a stereoscopic system consisting of two monochrome cameras and a DLP projector. The camera /projector speed was 60 Hz and the system had a latency of 70 ms.

2012-2013
A beam splitter was used to optically co-locate a monochrome camera with a DLP projector. System speed was increased to 120 Hz and latency was reduced to 13 ms.    
Deployment Plan
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.    
Expected Accomplishments and Metrics
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.    

Individuals Involved

Email Name Affiliation Role Position
srinivas@cs.cmu.edu Narasimhan, Srinivasa Robotics Institute PI Faculty - Tenured

Budget

Amount of UTC Funds Awarded
$55000.00
Total Project Budget (from all funding sources)
$55000.00

Documents

Type Name Uploaded
Final Report Toward_Smart_Automative_Headlights.pdf March 21, 2018, 8:29 a.m.
Publication 157_-_2013_IEEE_International_Conference_on_Computer_Vision.pdf Jan. 10, 2019, 6:37 a.m.
Publication Toward Smart Automotive Headlights for Safe Driving. Nov. 28, 2020, 10:24 a.m.

Match Sources

No match sources!

Partners

No partners!