Technology breakthrough allows self-driving cars to see in all weather conditions

A new sensor developed by US-based technology company Draper has made it possible for self-driving cars to see more reliably through rain, snow and fog.

Harsh weather conditions had previously made it more difficult for the sensors used in self-driving vehicles to clearly view conditions ahead.

However, Draper's Hemera LiDAR Detector has been developed in a way that allows it to collect much more information from light sources in the environment.

For example, most LiDAR systems can detect millions of photons (light particles), whereas this new system can collect billions of photons per second.

It will mean car manufacturers will be able to improve their existing LiDAR and is another stepping stone towards full-automation when vehicles no longer require a human driver. Draper will be offering the Hemera technology on licence to other vehicle manufacturers and suppliers to augment their current systems.

Joseph Hollmann, Ph.D., senior scientist for computational imaging systems development at Draper, said: “Typical LiDAR sensors can be confused by photons that are scattered by obscurants.

“We designed it to perform on bright days, when reflected sunlight can confuse LiDARs, and to avoid spoofing, which is being fooled into thinking that obstacles are present, when in reality there are no obstacles.”

Hemera has been designed so it can augment most existing LiDAR systems so car manufacturers and suppliers can preserve existing investments in LiDAR.

Sabrina Mansur, Draper’s self-driving vehicle program manager, said the company is currently working with car manufacturers to add Hemera to existing LiDAR systems.

Mansur said: “Hemera receives a lot more information from the scene, which in turn will make self-driving cars safer and more reliable.

“The ability to see through degraded visual environments, such as fog, snow and rain, will expand the scenarios in which autonomous cars will be able to operate.”