A communication system for autonomous cars could reduce the chance of a collision with an unseen obstacle or person by allowing the vehicles to gain a 3D view of an area. The system was developed by researchers at the Massachusetts Institute of Technology.
CarSpeak lets vehicles "see" out of the robotic eyes of other cars on the road, the New Scientist reported.
An autonomous car connected to the system would be able to cruise through blind corner, provided with a continuous 3D view of the area created from information captured by other cars, or by a sensor fixed in place to help with the blind spot.
That continuous 3D view consists of a cloud of millions of points generated by on-board laser mapping equipment, and it involves a huge amount of data.
Sending all the information to every car on the road would quickly overwhelm any wireless network.
"There are hundreds of cars on the highway, and getting sensory data from all of them would be huge data congestion. But most of them want to know about what's going on at the next exit," New scientist quoted Dina Katabi, project leader for CarSpeak at MIT, as saying.
So, instead, CarSpeak allows cars to request a view of specific sections of the environment that they are unable to "see" themselves, with other cars passing information back to the requesting car.
The system works out which regions are facing the most demand and then assigns more bandwidth to those sections as needed, speeding the process up.
The system has been tested on golf buggies in Singapore.
Vehicles running CarSpeak navigated through their test environment more than twice as fast as vehicles using simple wireless to relay data, and were 14 times less likely to be involved in a collision with an unseen obstacle.
According to Swarun Kumar, a lead researcher on CarSpeak, the next step will be a larger-scale test with multiple full-sized cars.
The research was presented at the SIGCOMM conference in Finland last month.