The Missing Self-Driving Puzzle Piece? Hyper Local Maps
BERLIN—Thanks to advances in sensor and artificial intelligence, autonomous vehicles are almost as smart every bit competent human being drivers. Just while a person instinctively knows how to quickly deal with, say, a road or lane closure due to construction, democratic vehicles could hands become confused and take too long to deal with the state of affairs every bit traffic backs up.
This is why we're seeing advances in mapping software, as well as acquisitions and partnerships that focus on the need for hyper-local, constantly updated maps. Office of the motivation for Intel ownership sensor-maker Mobileye for $15 billion was to gain access to the company'southward Road Management Experience, which crowd-sources images from cameras in millions of cars to create highly accurate and constantly updated maps.
Similarly, German automotive supplier Bosch partnered with mapping giant TomTom to develop a platform that captures billions of reflections created by a car'south radar signals bouncing off roadside objects. Called Radar Road Signature, "it uses radar sensors to e'er measure objects then you get a kind of fingerprint of the route," Gerhard Steiger, president of the automotive supplier's Chassis Systems Control Sectionalization, told me in an interview last week.
"You tin can upload that to the deject and add information technology to the navigation map and really localize a machine," Steiger explained. "Maps will have to be more localized. Regular navigation maps won't cut it since autonomous vehicles need more than precise information."
Hither, which was acquired two years ago by three German luxury automakers for $2.7 billion to build mapping software, is also working on localized and what it calls "self-healing" maps. (Here is likewise working with Mobileye and BMW on the REM platform to constantly update its maps.)
In addition to getting data from Audi, BMW, and Mercedes-Benz vehicles, Here too provides mapping software for four out of five cars in North America and Europe with in-nuance navigation. So it'due south uniquely positioned to supply next-generation maps for democratic driving and is creating what information technology calls a Reality Index for cocky-driving cars to better grasp their environs.
Rich Data From Premium Cars
As with Mobileye'south REM and the Bosch-TomTom Radar Road Signature, Here is collecting data from vehicles using sensors and photographic camera. Only in this instance, "information technology's very rich data since from premium cars made by our shareholders," Ralf Herrtwich, head of automotive, told me in an interview this week at the company's HQ in Berlin.
"When nosotros build our HD Alive Maps, there'due south 2 portions to it," Herrtwich explained. "The original collection of scanned roads. But then roads change—even if information technology's just a construction zone—and it'southward necessary as presently as something changes to have that reflected in the map.
"A vehicle that detects something divergent on the route sends us that written report," Herrtwich noted. "We may non trust every report, but if 3 vehicles written report the aforementioned thing, you know something inverse and you adjust the map according to what we larn—and and so nosotros accept a self-healing map."
Here is also looking beyond cars and collecting data for its Reality Index from drones and IoT devices to provide even more granular location information for democratic vehicles and hereafter mobility services. "It will be a database that provides information in existent fourth dimension to self-driving cars well-nigh everything that'south happening in the surround," Herrtwich said.
Then democratic vehicles may be more than enlightened of what'south around them than humans.
Almost Doug Newcomb
Source: https://sea.pcmag.com/news/16566/the-missing-self-driving-puzzle-piece-hyper-local-maps
Posted by: ethertoncalawn.blogspot.com
0 Response to "The Missing Self-Driving Puzzle Piece? Hyper Local Maps"
Post a Comment