According to a recent press release from the Robotics Institute, part of Carnegie Mellon’s School of Computer Science, researchers have developed a new high-tech headlight that can dodge raindrops. Srinivasa Narasimhan, associate professor of robotics, says, “If you’re driving in a thunderstorm, the smart headlights will make it seem like it’s a drizzle.”
According to the article, although rain appears “as elongated streaks that seem to fill the air,” the high-speed camera system in the smart headlights can see each streak as a “sparsely spaced, discrete drop.” Mr. Narasimhan says this leaves plenty of space between drops for the system to distribute light. “A human eye will not be able to see that flicker of the headlights,” Prof. Narasimhan says. “And because the precipitation particles aren’t being illuminated, the driver won’t see the rain or snow either.”
The system takes only 13 milliseconds to detect and track the motion of the precipitation (be it rain, snow, or sleet), apply a computer algorithm that will predict where particles will fall, and divert the projection of light in that area— a time that Prof. Narasimhan says he and his team hope to decrease to the few milliseconds required for highway use. The article claims that at low speeds, the headlights could already “eliminate 70 to 80 percent of visible rain during a heavy storm, while losing only 5 or 6 percent of the light from the headlamp.”
The press release describes the test apparatus as consisting of a camera coupled with an off-the-shelf DLP projector. The article describes the feasibility of application, saying, “Road-worthy systems likely would be based on arrays of light-emitting diode (LED) light sources in which individual element could be turned on or off, depending on the location of raindrops. New LED technology could make it possible to combine LED light sources with image sensors on a single chip, enabling high-speed operation at low cost.”
Although entirely eliminating weather conditions from the driver’s field of view is impossible, reducing the driver’s distraction can substantially improve highway safety. The release even mentions the system’s ability to detect oncoming cars and adjust the smart headlight’s beams away from other drivers as an additional benefit.
Prof. Narasimhan comments on the headlight’s practicality, saying,”One good thing is that the system will not fail in a catastrophic way. If it fails, it is just a normal headlight.”
Along with Prof. Narasimhan, the team consisted of Takeo Kanada, professor of computer science and robotics, Anthony Rowe, assistant research professor of electrical and computer engineering, Robert Tamburo, Robotics Institute project scientist, and Raoul de Charette, a visiting doctoral student from Mines ParisTech, France. The Office of Naval Research, the National Science Foundation, the Samsung Advanced Institute of Technology and Intel Corp sponsored the team’s research.