From what little is known, Apple has been focusing more on the software side rather than on hardware, and a new research paper published Friday by the company on Cornell University's arXiv repository seems to confirm that theory.
Apple computer scientists revealed a new method that self-driving could use to detect pedestrians and cyclists in a recently-published research paper, giving a rare glimpse into the US technology giant's work in the field.
The paper was submitted last week to an independent online journal by Yin Zhou and Oncel Tuzel, who proposed an improved way for helping computers detect three-dimensional objects, reports Autonews. The paper was published in an global web journal known as arXiv. This technology works on the principle of speed calculation. This in turn is used to create an image of the object's shape.
Additionally, LiDAR works best for objects that are at smaller distances from the machine. The equipment provides depth information, however their low resolution makes it hard to detect small objects that are far away without the help from a normal camera that is linked in real-time.
Denser point clouds offer a clearer, more accurate picture of an object, but Apple's researchers say their new method, which they call VoxelNet, makes even sparse point clouds useful for object detection. The paper is also a sign that both AI and self-driving are challenging to a point that Apple can no longer go it alone on research. The 3D detection network is pitched as an alternative to LiDAR, a laser-surveying method used in some self-driving vehicle models to measure and determine potential obstacles. They have christened the method "VoxelNet". In June, Apple CEO Tim Cook gave some suggestion the company is taking the development of self-driving vehicles seriously, identifying it as an exciting prospect.
Earlier this year, Apple was granted a permit by Californian authorities to allow it to test self-driving cars.