Apple's work on contact usself-driving cars has been more secretive than just about every other project in the autonomous car space — but now, two of the company's scientists have published some of their auto-focused research for the first time.
The paper, authored by Apple engineers Yin Zhou and Oncel Tuzel and published in the independent journal arXiv, details a new computer imaging software technique called "VoxelNet" that could improve a driverless car system's ability to detect pedestrians and cyclists.
The scientists claim their new method could be even more effective than the two-tiered LiDAR and camera systems that have become the industry standard for object detection in self-driving cars. Those expensive systems depend on cameras to help determine the small or faraway objects (like pedestrians or cyclists) detected by LiDAR sensors, which use light beams to detect and map 3D obstacles in the world around the the vehicle.
SEE ALSO: Uber just made its biggest move yet to adopt self-driving carsThe VoxelNet system — which was named after the "voxel" unit of value for a point in a three-dimensional grid — eliminates the need for a camera to help identify the objects detected by LiDAR sensors, allowing the autonomous platform to work on LiDAR alone. The scientists tested the software using models that showed pedestrians, cyclists, and other faraway objects.
The new technique was only tested in computer simulations, so Apple will still need to put VoxelNet to the test on the streets IRL before it can actually remove the cameras from its self-driving platform. The initial results were called "highly encouraging," however, so it might not be too long before the system described in the public research is put into use, by Apple or some other self-driving projects.
It's rare for Apple to show its hand by publishing research or explaining products before an official launch, but self-driving development is a different space for the iPhone maker. Public testing, which is essential to autonomous systems, requires government oversight, so public documents like state permits have tipped the company's hand.
It's hard to hide a fully equipped self-driving car from being spotted on public roads, too. Apple's rig has reportedly been identified twice, even though rumors claim its driverless platform could be relegated to use for an employee shuttle bus to start.
We reached out to Apple for comment on how the new LiDAR-only object detection system might be implemented, but haven't heard back. We'll update the story if we get a response.
Topics Apple Self-Driving Cars
Someone put a bra on a cow for a very wholesome reasonLG is bringing transparent TVs to CESEurovision cancels Chinese broadcast following LGBTQ censorshipHow to find, generate and post your Instagram Top 9The best iPhone accessories of 2021Venmo's most popular emoji of 2021 is actually pretty heartwarmingHow to use voiceHow NASA sun probe survived flying into the coronaAmazon's AWS is wreaking havoc on the internet againJokin' Chuck Schumer trolls Trump with #BeBest hashtagGoogle's Santa Tracker has actually helped improve Google itselfTesla to stop allowing drivers to play videogames while drivingVirtual watch parties could make a comeback in 2022The 5 most important TV features to look for in 20225 ways you never knew you could masturbateSneaky squirrels make a home, and a fire hazard, out of a car's engineMan with the 'golden arm' saved lives for 60 years, donates last timeHow to use voiceWell, Prince Harry and Meghan Markle bathing suits are a thing nowPink's response to an ageist troll should be in a museum 'Share to TikTok' feature lets you share from Spotify and Apple Music Best fitness tracker: Save up to 40% on Fitbit trackers at Amazon Best gaming TV deal: Save $400 on TCL 65 Best early Black Friday earbud deal: Save $50 on Bose Ultra Open earbuds at Target Arkadium mini crossword answers for November 6 NYT Connections Sports Edition hints and answers for November 6: Tips to solve Connections #43. Best Amazon deals of the day: Google Pixel Buds Pro 2, Fitbit Versa 4, Sony WH Best free Python courses NYT mini crossword answers for November 6 NYT Connections Sports Edition hints and answers for November 7: Tips to solve Connections #45. The world's best Calm Premium: Save 50% on a premium subscription. Best Black Friday doorbuster vacuum deal: Save $270 on Dyson Digital Slim NYT Connections hints and answers for November 7: Tips to solve 'Connections' #515. What's new to streaming this week? (Nov. 7, 2024) Apps that use AI to streamline your home life Best power station deal: Save 49% on Anker Solix C1000 Election Day mental health day: Give yourself a break How to unblock xHamster for free Best 4K TV deal: Get $300 off the 65
2.3135s , 10131.3984375 kb
Copyright © 2025 Powered by 【contact us】,Warmth Information Network