Driverless car safety may be taking a further leap forward with new laser-based system that could allow vehicles to ‘see’ obstacles before they come into view.
A herd of cows or a broken-down car? Unexpected obstacles can prove a big risk to drivers -but cars of the future might be able to anticipate the danger. A team of researchers have come up with a new laser-based system which produces images of objects that are hidden around a corner – a development they say could allow driverless vehicles to see obstacles before they come into view – obviously having massive potential in terms of safety.
Current technology involves sending laser pulses towards a surface and measuring the time it takes for light to be reflected – then the data is used to build a three-dimensional model of the surface. The new technology takes the idea further by using lasers to see around corners: a laser and photon detector are placed in front of a wall next to an object and are separated from the object by a partition. Laser pulses are then fired at the wall at an angle but instead of collecting the light that bounces directly back off the wall toward the detector; the light that bounces off the wall, hits the object and is then scattered by it is collected as the second, third and fourth bounces encode the hidden objects.
Previous approaches to the problem have involved directing laser pulses at one point on the wall and then collecting signals from another point, whereas this technique points both the laser and the detector at the same point on the wall.
By using the timing of the signals to remove the signals from light that bounced back directly, those remaining are rapidly processed using an algorithm to reconstruct the hidden object – a simple tweak with huge potential as it uses less memory and processing to generate a higher resolution image.
After first developing an algorithm by creating computer models of how laser pulses would bounce off a model of a rabbit hidden by the partition, the team applied the system in real life, including capturing an image of an Exit sign.
It seems that the highly reflective nature of road signs and bicycle reflectors make the technology a good fit for driverless cars, as the research uses sensors similar to those already used in autonomous vehicles.
Inevitably, there are still obstacles to overcome. The initial scanning of the wall can take anywhere from a minute to a couple of hours and the system needs to be better at detecting objects that are not highly reflective or stationary, such as children or wild animals. It also needs to be used outdoors in bright, sunny conditions.
So, it looks like we’re on the way to having automated vehicles which can predict or detect what is happening ahead – not only what is going on in their own lane but also in the surroundings like pedestrian paths or on the other side of the corner.
It may seem like science fiction- but cars seeing round corners are well and truly on the way.