Wednesday, March 27, 2024

New radar allows cars to spot hazards hidden around corners

The development of autonomous cars is still advancing, and researchers at Princeton University have another piece from which the entire puzzle of autonomous cars can be assembled in the future. They decided to expand the capabilities of standard radar with new algorithms.

A team of researchers combined artificial intelligence and radar used to track speeders to develop an automated system that will allow cars to peer and spot hazards hidden around corners. Thanks to this, the car would “see” if a pedestrian, cyclist, or other car is not approaching the road, which should increase safety.

In principle, the new system is easy to integrate into any vehicle. It is based on the Doppler radar to reflect radio waves from surfaces such as buildings and parked automobiles. Mounted in front of the vehicle, they emit radar signal that hits the surface at an angle, so its reflection rebounds off like a cue ball hitting the wall of a pool table.

The signal goes on to strike objects hidden around the corner. Some of the radar signals bounce back to detectors mounted on the car, allowing the system to see objects around the corner and determine the speed of the object and the direction of movement. In real-world applications, a driver or autonomous driving system will be alerted to potential hazards.

The challenge is that radar’s spatial resolution – used for picturing objects around corners such as cars and bikes – is relatively low. However, the researchers believed that they could create algorithms to interpret the radar data to allow the sensors to function.

And as it turned out, with the help of artificial intelligence algorithms, they were actually able to obtain information about unseen objects. The advantage of such a technology would be that the radar will gain new functionality only thanks to algorithms capable of recognizing individual reflections. In addition, radar is a relatively cheap component compared to LiDAR. If anyone showed interest in the new knowledge, it could be incorporated into future cars soon.

It would certainly go through the very rigorous automotive development cycles,said Felix Heide, an assistant professor of computer science at Princeton University and one of the researchers. “In terms of integration and bringing it to market, it requires a lot of engineering. But the technology is there, so there is the potential for seeing this very soon in vehicles.”