The future is closer than you think. Wayne Gerdes – CleanMPG – Aug. 16, 2016 Ford intends to place a high-volume, fully autonomous SAE level 4-capable vehicle in commercial operation by 2021 in a ride-hailing or ride-sharing service. To get there, the company is investing in or collaborating with four startups to enhance its autonomous vehicle development, doubling its Silicon Valley team and more than doubling its Palo Alto campus. Autonomous vehicles in 2021 are part of Ford Smart Mobility, the company’s plan to be a leader in autonomous vehicles, as well as in connectivity, mobility, the customer experience, and data and analytics. Ford’s Efforts in Autonomous Vehicles Like all OEMs, Ford has been working on Autonomous vehicles for more than a decade and has now publicly committed to a release date. Ford’s first fully autonomous vehicle will be a SAE level 4-capable vehicle. Plans are to design it to operate without a steering wheel, gas or brake pedal, for use in commercial mobility services such as ride sharing and ride hailing within geo-fenced areas and be available in high volumes. This year, Ford will triple its autonomous vehicle test fleet to be the largest test fleet of any automaker – bringing the number to about 30 self-driving Fusion Hybrid sedans on the roads in California, Arizona and Michigan, with plans to triple it again next year. Ford was the first automaker to begin testing its vehicles at Mcity, University of Michigan’s simulated urban environment, the first automaker to publicly demonstrate autonomous vehicle operation in the snow and the first automaker to test its autonomous research vehicles at night, in complete darkness, as part of LiDAR sensor development. To deliver an autonomous vehicle in 2021, Ford is announcing four key investments and collaborations that are expanding its strong research in advanced algorithms, 3D mapping, LiDAR, and radar and camera sensors: Velodyne: Ford has invested in Velodyne, the Silicon Valley-based leader in light detection and ranging (LiDAR) sensors. The aim is to quickly mass-produce a more affordable automotive LiDAR sensor. Ford has a longstanding relationship with Velodyne, and was among the first to use LiDAR for both high-resolution mapping and autonomous driving. SAIPS: Ford has acquired the Israel-based computer vision and machine learning company to further strengthen its expertise in artificial intelligence and enhance computer vision. SAIPS has developed algorithmic solutions in image and video processing, deep learning, signal processing and classification. Nirenberg Neuroscience LLC: Ford has an exclusive licensing agreement with Nirenberg Neuroscience, a machine vision company founded by neuroscientist Dr. Sheila Nirenberg, who cracked the neural code the eye uses to transmit visual information to the brain. This has led to a powerful machine vision platform for performing navigation, object recognition, facial recognition and other functions, with many potential applications. Nirenberg Neuroscience will help bring humanlike intelligence to the machine learning modules of its autonomous vehicle virtual driver system. Civil Maps: Ford has invested in Berkeley, California-based Civil Maps to further develop high-resolution 3D mapping capabilities. Civil Maps has pioneered an innovative 3D mapping technique that is scalable and more efficient than existing processes. This provides Ford another way to develop high-resolution 3D maps of autonomous vehicle environments. Autonomous Ford Fusion Testing on public roads with driver behind the wheel. Ford also is expanding its Silicon Valley operations by adding two new buildings and 150,000 square feet of work and lab space adjacent to the current Research and Innovation Center in Palo Alto. The facility will double the size of the current Palo Alto team by the end of 2017. Since the new Ford Research and Innovation Center Palo Alto opened in January 2015, the facility has rapidly grown to be one of the largest automotive manufacturer research centers in the region. Today, it is home to more than 130 researchers, engineers and scientists, who are increasing Ford’s collaboration with the Silicon Valley ecosystem. Research and Innovation Center Palo Alto’s multi-disciplinary research and innovation facility is the newest of nearly a dozen of Ford’s global research, innovation, IT and engineering centers. The expanded Palo Alto campus opens in mid-2017. UBER or LYFT, can I request a ride in a Nissan IDS or Ford Fusion Hybrid without a driver?
...and now Delphi/Mobileye by 2019. http://www.detroitnews.com/story/business/autos/2016/08/23/delphi-mobileye-autonomous-cars/89194014/ /and I've got to think Tesla will be at the front of the timeline as well. // it will be interesting to see what power train(s) will be included in these autonomous fleets.... I think there's a good chance BEVs will be the most common.
Every picture or video I see of an autonomous car is in ideal situations. I have serious concerns about full autonomy on typical New England roads and in anything other than bright sunny days. A blowing snow storm, or a broken pavement winding road without painted lines and gravel, leaves and rain, with obstructed views - will be less than great for any programmed computer. This is about 1,000 times more difficult than a really complex video game - the system has to synthesize multiple inputs - and "figure out" what is going on AND THEN prioritize the timing of any and all things that will affect the moving car. AND it has to have redundancy, and robust backups for everything.
I hate to see the finest engineers in the country(world) wasting their time on something as dumb as autonomous driving. I would REALLY hate being on the road with autonomous cars.
" Like other players in this space, Ford is creating high-fidelity, 3D maps of the roads its autonomous cars will travel. Those maps include details like the exact position of the curbs and lane lines, trees and signs, along with local speed limits and other relevant rules. The more a car knows about an area, the more it can focus its sensors and computing power on detecting temporary obstacles—like people and other vehicles—in real time. Those maps have another advantage: The car can use them to figure out, within a centimeter, where it is at any given moment. Say the car can’t see the lane lines, but it can see a nearby stop sign, which is on the map. Its LIDAR scanner tells it exactly how far it is from the sign. Then, it’s a quick jump to knowing how far it is from the lane lines." https://www.wired.com/2016/01/the-clever-way-fords-self-driving-cars-navigate-in-snow/ /I think we're all going to be amazed at the amount of data storage, processing power, and cloud connectivity that will be involved in moving AVs down the road.
That's what the system currently does. It's not if-then-else algorithms that typical computer software uses.
The scale of ALL that 3D information is way beyond anything we can store in the car. Plus keeping it up to date would be a nightmare. So, that means the car has to download everything - essentially a stream of 3D data. That is a bottleneck and a logistical nightmare, I think. Think 3D games - they preload all the models and textures. With a car, it has to compare preloaded data with actual data inputs, and synthesize the situation - and then prioritize ALL of it, and then react. What about a blowing snow storm? What about deep puddles, and blowing leaves? I fail to see any real benefits for most people, in all situations. Now, on limited access highways, cars can link up into "trains" and in emergencies, your car could take you to the hospital, etc. But for ALL driving ALL the time - I think autonomous driving is dangerous.
Update the car over WiFi when it's parked at home, or through a USB drive. It's not likely that updates will be very big, traffic signals, signs, roads, etc are all pretty standard without many changes from year to year. Updates will likely be limited to tweaks to how the car should react in various situations. Most people are error prone, distracted, tired, etc. In a few years, I think computers will be better drivers than the average person.
The day will come... until then, I'm all for limited uses for the autonomous driving tech, some of them already mentioned. You've seen in the news that Uber is getting into autonomous cars. Surprised me at first, but then I thought, sure, that was bound to happen. Inner city traffic could be better controlled if regular drivers were banned and only a fleet of autonomous vehicles remained. Trucks, taxis, buses, etc. I've always dreaded the driving conditions in NYC, Boston, Chicago, just about any major city with traffic issues and bad drivers. Driver assist technologies have come a long way with a long way to go. Already here are the stability controls in all new cars. Here's an interesting application that helps our Navy pilots: http://breakingdefense.com/2016/08/magi-carpet-ride-navy-software-eases-carrier-landings/
Bring on the safety backup systems! Make them standard on all vehicles. Also, put video mirrors on all vehicles - these will lower drag and we will have higher mileage. THEN we can talk about autonomous driving in some situations. I think some folks are getting way ahead of what is needed, let alone feasible.
Random thought: With driver accommodations no longer needed,... Will autonomous "delivery vehicles" take on the same shape/characteristics as "world Solar Challenge" vehicles....including the solar panel top? With the latest solar panels, could an "in town" delivery vehicle have sufficient efficiency and solar charging to operate without plugging in? Starting simple ... How about pizza delivery? Lightweight, low and flat .. You could almost use an actual WSC vehicle. Routing could be limited to streets posted 45 mph or less for efficiency.
Too slow for pizza delivery, and I think many ordering delivery do so to avoid stepping outside. Toyota estimates the solar option on the Prius Prime will add 2 to 3 km per day on average through the year. The weight lightening used for the Solar Challenge cars isn't street legal. So solar on the car only simply isn't going to work.
I just saw this story. Race cars piloted by A.I. Pretty interesting and even has a dog it. http://www.bbc.com/news/technology-39027477
