Self-driving cars use a number of different technologies to “see” the world around them. One of them is LIDAR, and some believe it could be the solution to the ever-present problem of light pollution that is plaguing cities.

Unfortunately, the idea of driving with your headlights off and using laser-guidance as your primary and potentially sole method of identifying obstacles is hazardous.

If you haven’t heard the term LIDAR before, you will likely hear all about it in the next few years. Basically, it stands for Light Detection and Ranging, and it’s the technology that enables self-driving cars to spot and track obstacles, roadways, and other critical data that keeps them from crashing.

See also: China moves into passing lane with self-driving regulations

It is one of three systems that autonomous vehicles use to do their thing, and all three of them are necessary to maintain an optimal level of safety.

Cameras are another, and those require light to function optimally. These do a number of things, including helping the car to see and identify moving objects, such as people and animals in the roadway.

The third is radar, which helps the car to be aware of vehicles both in front and behind it and is commonly seen in cars with adaptive cruise control.

In a recent interview with Inverse, Michael Clamann, a senior research scientist at Duke University, said: “The whole point of having multiple systems on these cars is that they have redundancy. There are certain things that LIDAR is good at, there are certain things that cameras are good at, and there are certain things that radar is good at.”

Will lasers set driverless cars on “kill”?

If we were to take two of those systems out of the equation, you’re left with a vehicle that, while it might be able to navigate and handle basic obstacle avoidance, would leave it inherently less safe.

Autonomous vehicles have a hard enough time as it is trying to predict the movements of obstacles. A deer, for example, is by its very nature unpredictable. Having headlights on gives passengers and “drivers” an opportunity to act when the vehicle is unable to accurately predict what is going to happen.

Additionally, LIDAR itself isn’t perfect. It doesn’t work very well in heavy rain or snow. It needs a clear point-to-point path to objects around it to properly identify their distance, size, and shape.

So, will self-driving cars help us to cut down on the amount of light pollution in our cities? Possibly, but not with the technologies currently available. Until a new generation of sensors and cameras are created, bright headlights will remain a familiar sight on our roadways.