Some of Apple's computer scientists have published a paper on 3D object detection, Reuters reports. The paper, which was submitted to the online journal arXiv, is believed to be the first time Apple has a publicly disclosed paper regarding its autonomous-vehicle development.
The paper, which you can check out at this link, discusses a new software program called VoxelNet, which helps detect three-dimensional objects with fewer sensors than many companies are currently using. VoxelNet managed to produce "highly encouraging results" through the use of light-based lidar alone, as opposed to linking lidar with another system, like a standard camera. The results come from the use of simulators, not Apple's on-road efforts.
Unless you have a degree in computer science, your eyes probably glazed over by the second page. What's important here, beyond simplifying sensor layouts used for object detection, is that this offers a rare peek into Apple's quite-secretive Project Titan.
Project Titan was originally supposed to be a whole self-driving car, but the tech titanto focus on a platform alone, which it can develop and sell to automakers that lack the time, money or manpower to build a bespoke autonomous solution. This is the same route that Waymo, Uber and others are taking. Cars aren't cheap -- it would cost more than $1 billion just to engineer and certify the car itself, nevertheless its advanced self-driving systems.
While the program is no longer a secret, finding Apple testing in public has not been easy. Few sightings have been reported on -- a Lexus RX sporting Apple's system was , and a second, more advanced sensor array in October.