Who dies? What happens when an autonomous car needs to make a decision between crashing into another car, or that child crossing the street? How long will it have to take that decision? Who dies?While iPhones are pretty complicated, cars are both complex and life-threatening.A software glitch in a smartphone is annoying, but poor car code could threaten lives. That’s what makes Apple’s recently published autonomous vehicle research paper very interesting.Under the radar of Thanksgiving, two Apple researchers this week published a paper in which they discussed their research into LiDAR (Light Detection and Ranging) technology. It’s a remote sensing method that uses light to detect objects and figure out distance from those objects.(Facetiously, I keep seeing it as like Face ID for cars).What’s most important is that the Apple researchers think they have found a way to make LiDAR more accurate – an important step in the development of Apple Car: “Our experiments on the KITTI car detection task show that VoxelNet outper- forms state-of-the-art LiDAR based 3D detection methods by a large margin. On more challenging tasks, such as 3D detection of pedestrians and cyclists, VoxelNet also demonstrates encouraging results showing that it provides a better 3D representation.” (Link) Microsoft is also working in this spaceSmarter smart carsThe ability to acquire and translate more accurate imaging makes the system more accurate.You want your system to be incredibly accurate – if an accident does take place, the more time the car’s ‘brain’ has to decide what actions to take the better. We just have to hope the penalties for self-driving cars harming innocent pedestrians outweigh the insurance cost consequences of striking another vehicle.It is unusual for Apple to publish research that associates with an unfinished product. However, the company knows that the best minds in machine intelligence want and need to work together to find solutions to highly challenging problems.That’s why this year it launched its own machine intelligence blog, where its researchers publish deep technical analysis of what they are working on.When it comes to cars, the challenges are much, much bigger than what kind of fabric you use in the seats. Smart cars need to be better, safer and more reliable to use than their human-driven equivalents, or what’s the use?Bag of hurtWe know that autonomous cars are coming.We know they will be made by multiple manufacturers and that they will need sophisticated collision evasion, object detection, self-direction, and highly responsive autonomous intelligence systems capable of both understanding incoming data and making immediate and effective response.Problems aren’t just technical.Regulatory, manufacturing, design, ethical and legal challenges also exist. To resolve these Apple has been making a host of investments in this space. It has also (allegedly) spoken with existing vehicle manufacturers to get them to make the vehicles.With so many complex challenges to solve, it’s no surprise Apple had to “reboot” the project, but this evidently did not mean the company quit its ambition.Publication of this new research seems to confirm that.instead it suggests Apple is working hard to ensure carOS will be the best available solution in the space.I imagine this means cars using its software may not be the first to hit the roads, but once they do hit the street Apple hopes they are the best. You should expect nothing less from smart vehicles. Who dies if the software sucks?I guess we’ll find that out pretty soon as the first solutions hit the roads in quantity in the next few years.One more thing: Who is going to make the mobile chips used by these rides?Do you have any insights on Apple Car? Drop me a line via the social links below.Google+? If you use social media and happen to be a Google+ user, why not join AppleHolic's Kool Aid Corner community and get involved with the conversation as we pursue the spirit of the New Model Apple?Got a story? Please drop me a line via Twitter and let me know. I'd like it if you chose to follow me there so I can let you know about new articles I publish and reports I find.
Wir nutzen Cookies auf unserer Website. Einige von ihnen sind essenziell für den Betrieb der Seite, während andere uns helfen, diese Website und die Nutzererfahrung zu verbessern (Tracking Cookies). Sie können selbst entscheiden, ob Sie die Cookies zulassen möchten. Bitte beachten Sie, dass bei einer Ablehnung womöglich nicht mehr alle Funktionalitäten der Seite zur Verfügung stehen.
Who dies? What happens when an autonomous car needs to make a decision between crashing into another car, or that child crossing the street? How long will it have to take that decision? Who dies?While iPhones are pretty complicated, cars are both complex and life-threatening.A software glitch in a smartphone is annoying, but poor car code could threaten lives. That’s what makes Apple’s recently published autonomous vehicle research paper very interesting.Under the radar of Thanksgiving, two Apple researchers this week published a paper in which they discussed their research into LiDAR (Light Detection and Ranging) technology. It’s a remote sensing method that uses light to detect objects and figure out distance from those objects.(Facetiously, I keep seeing it as like Face ID for cars).What’s most important is that the Apple researchers think they have found a way to make LiDAR more accurate – an important step in the development of Apple Car: “Our experiments on the KITTI car detection task show that VoxelNet outper- forms state-of-the-art LiDAR based 3D detection methods by a large margin. On more challenging tasks, such as 3D detection of pedestrians and cyclists, VoxelNet also demonstrates encouraging results showing that it provides a better 3D representation.” (Link) Microsoft is also working in this spaceSmarter smart carsThe ability to acquire and translate more accurate imaging makes the system more accurate.You want your system to be incredibly accurate – if an accident does take place, the more time the car’s ‘brain’ has to decide what actions to take the better. We just have to hope the penalties for self-driving cars harming innocent pedestrians outweigh the insurance cost consequences of striking another vehicle.It is unusual for Apple to publish research that associates with an unfinished product. However, the company knows that the best minds in machine intelligence want and need to work together to find solutions to highly challenging problems.That’s why this year it launched its own machine intelligence blog, where its researchers publish deep technical analysis of what they are working on.When it comes to cars, the challenges are much, much bigger than what kind of fabric you use in the seats. Smart cars need to be better, safer and more reliable to use than their human-driven equivalents, or what’s the use?Bag of hurtWe know that autonomous cars are coming.We know they will be made by multiple manufacturers and that they will need sophisticated collision evasion, object detection, self-direction, and highly responsive autonomous intelligence systems capable of both understanding incoming data and making immediate and effective response.Problems aren’t just technical.Regulatory, manufacturing, design, ethical and legal challenges also exist. To resolve these Apple has been making a host of investments in this space. It has also (allegedly) spoken with existing vehicle manufacturers to get them to make the vehicles.With so many complex challenges to solve, it’s no surprise Apple had to “reboot” the project, but this evidently did not mean the company quit its ambition.Publication of this new research seems to confirm that.instead it suggests Apple is working hard to ensure carOS will be the best available solution in the space.I imagine this means cars using its software may not be the first to hit the roads, but once they do hit the street Apple hopes they are the best. You should expect nothing less from smart vehicles. Who dies if the software sucks?I guess we’ll find that out pretty soon as the first solutions hit the roads in quantity in the next few years.One more thing: Who is going to make the mobile chips used by these rides?Do you have any insights on Apple Car? Drop me a line via the social links below.Google+? If you use social media and happen to be a Google+ user, why not join AppleHolic's Kool Aid Corner community and get involved with the conversation as we pursue the spirit of the New Model Apple?Got a story? Please drop me a line via Twitter and let me know. I'd like it if you chose to follow me there so I can let you know about new articles I publish and reports I find.