A pair of Apple computer science researchers just submitted a paper focused on a software approach to helping self-driving vehicles more easily spot pedestrians and cyclists, while actually using fewer sensors, to the independent online journal arXiv.
Going to need more than 140 characters to go over 🍎's Project Titan. I call it "The Thing" pic.twitter.com/sLDJd7iYSa
— MacCallister Higgins (@macjshiggins) October 17, 2017
I saw one of these a few weeks ago pull up to an Apple shuttle stop-sit there for a few then drove off. pic.twitter.com/gUudZY1TIA
— lostmybeard (@idiggapple) October 18, 2017
The submission marks ones of the first times that Apple has publicly acknowledged that is has been working on the development of self-driving vehicle tech — the new paper also represents Apple’s first publicly disclosed paper on self-driving vehicles.
Another reason that the new paper — submitted by researchers Oncel Tuzel and Yin Zhou on November 17th — is particularly notable is that Apple has in the past generally been very secretive as regards tech that it is working on, which is generally viewed as a liability by many machine learning and artificial intelligence developers.
With regard to the new paper itself, it concerns a new software approach to pedestrian and cyclist detection dubbed “VoxelNet” — which helps computers better detect 3-dimensional objects.
Very unsurprisingly, Apple has declined to comment on the news.
Reuters provides more: “Academics are used to freely sharing their work with peers at other organizations. Yielding to that dynamic, Apple in July established the Apple Machine Learning Journal for its researchers. Their work rarely appears outside the journal, which so far has not published any research on self-driving cars.
“Self-driving cars often use a combination of normal two-dimensional cameras and depth-sensing ‘LiDAR’ units to recognize the world around them. While the units supply depth information, their low resolution makes it hard to detect small, faraway objects without help from a normal camera linked to it in real time.
“But with new software, the Apple researchers said they were able to get ‘highly encouraging results’ in spotting pedestrians and cyclists with just LiDAR data. They also wrote they were able to beat other approaches for detecting three-dimensional objects that use only LiDAR. The experiments were computer simulations and did not involve road tests.”
It’s not clear what the new paper amounts to in practice as of yet, perhaps nothing, but the publication of a paper on the subject is certainly out of the ordinary for the firm.
With regard to real-world teasing, you may recall that Apple filed a self-driving car testing plan with regulators in California back in April.