Autonomous helicopter completes Marine resupply simulation

Drones have become a part of the modern battlefield, but what about autonomous full-size aircraft? Aurora Flight Sciences just successfully demonstrated its self-flying setup, the Autonomous Aerial Cargo Utility System (AACUS), enabling an older helicopter to fly itself at soldiers’ requests. In the future, troops in the field could use this tech to order autonomous supply deliveries with nothing more complicated than a tablet. Officials at ONR and their industry partners @AuroraFlightSci announced today a successful, final flight demonstration of an AACUS-enabled helicopter. #AACUS can be installed on any helicopter to increase its capability to full autonomy. https://t.co/qtEkrVpVSd pic.twitter.com/gHPUFMiTsW — ONR (@USNavyResearch) December 13, 2017 For the company’s live test before Navy officials, Aurora installed AACUS an existing UH-1H helicopter, which had been outfitted with LiDAR and cameras to avoid obstacles. Earlier demonstrations had proven its autonomous flight capability, according to a press release, but this test had the aircraft simulating cargo and utility missions. Soldiers loaded supplies on the aircraft and it successfully took off autonomously, taking one more step toward a self-flying delivery system that doesn’t require complex training for troops to use. While this test featured the AACUS-Enabled UH-1H, a setup that the FAA specially certified in October, the technology could theoretically be integrated into other rotary-wing aircraft. This demonstration was the final phase in its five-year testing program; Now the Marine Corps will experiment with the system and figure out whether to buy it. If so, it would be another feather in Boeing’s cap: The aerospace giant bought Aurora back in October. We think it’s pretty cool! https://t.co/6nDmudblum — AuroraFlightSciences (@AuroraFlightSci) December 13, 2017 Source: Office of Naval Reserch

More here:
Autonomous helicopter completes Marine resupply simulation

NVIDIA introduces a computer for level 5 autonomous cars

At the center of many of the semi-autonomous cars currently on the road is NVIDIA hardware. Once automakers realized that GPUs could power their latest features, the chipmaker–best known for the graphics cards that make your games look outstanding–became the darling of the car world. But while automakers are still dropping level 2 and sometimes level 3 vehicles into the market, NVIDIA has announced its first AI computer, the NVIDIA Drive PX Pegasus that it says is capable of level 5 autonomy. That means no pedals, no steering wheel, no need for anyone to ever take control. The new computer delivers 320 trillion operations per second, 10 times more than its predecessor. Before you start squirreling away cash for your own self-driving car, though, NVIDIA’s senior director of automotive, Danny Shapiro, notes that it’s likely going to be robotaxis that drive us around. In fact, the company said that over 25 of its partners are already working on fully autonomous taxis. The goal with this smaller more powerful computer is to remove the huge computer arrays that sit in the prototype vehicles of OEMs, startups and any other company that’s trying to crack the autonomous car nut. NVIDIA’s announcement should make all those companies happy. The computing needed to power a self-driving car’s AI and data crunching not to mention the huge amounts of data coming from potentially dozens of cameras, LiDAR sensors , short and long-range radar is staggering and usually means there’s a small server room stored in the trunk. All that processing power sucks up a ton of power from the vehicle and as more cars are going electric, the last thing an automaker wants is a system that cuts in the range of their new car. The new NVIDIA Drive PX Pegasus AI computer is the size of a license plate and uses far less power than the current model. But it’s going to be a while before anyone gets their hands one. The new computer will be available in the second half of 2018 with next generation GPUs that NVIDIA hasn’t actually announced yet. But there’s already one institution that’s ready to go autonomous: the Deutsche Post DHL. The delivery service is looking to deploy a pilot fleet with the current Drive PX in 2018. The hope is to have the car be able to shadow its delivery persons as they drop off packages. A driver could get out of the truck or van with a few packages for a block and when they are finished, the vehicle will be waiting for them outside the last house. So the autonomous future isn’t just about delivery people, it’s also about delivering your online purchases. Source: Nvidia

Continued here:
NVIDIA introduces a computer for level 5 autonomous cars

Air Force tests air-to-ground strikes with an autonomous F-16 wingman

There’s so much focus around autonomous cars these days it’s easy to forget that the military’s trying to plug artificial intelligence into fighting vehicles, too. And not just in computer mock-ups, like last June’s exhibition wherein a flight AI beat a retired USAF Colonel in simulated dogfights. In a recent test , military contractors used an unmanned system autonomously flying an F-16 combat jet as a wingman to support a human pilot in a separate aircraft. The system successfully met its goals to adapt, plan and execute maneuvers all on its own. #SkunkWorks partnered with @usairforce to demonstrate manned/unmanned teaming capabilities: https://t.co/lewPOLz1fI Photo via U.S. Air Force pic.twitter.com/FThukW424N — Lockheed Martin (@LockheedMartin) April 10, 2017 The two-week demonstration, Have Raider II, was the second in a series of tests run by key players in the aerospace industry, including Lockheed Martin, Skunk Works and the Air Force Research Laboratory. The first exhibition focused on keeping the autonomous F-16 flying in formation as a wingman, while the recent tests pushed the self-flying plane to react to changing threats during an air-to-ground strike mission and calculate new plans on the fly. Tech developed for this recent battery of tests will allow the autonomous system’s operators to insert new software components that will improve its flexibility. This is a big step in Loyal Wingman, a program dedicated to building a system to pilot autonomous planes that operate as wingmen to human pilots. Crucially, the unmanned aircraft are directed by the lead aviator, not ground control. This setup lets the human pilot offload some cognitive workload to their AI partners to preserve brainpower for mid-flight plans and mission management — assuming the computer doesn’t go rogue like all the bad sci-fi films predict. Source: Lockheed Martin

More:
Air Force tests air-to-ground strikes with an autonomous F-16 wingman

Here’s Google’s First Fully Functional Self-Driving Car Prototype

Google is a front runner in the autonomous auto future. Back in May , Google showed off an early prototype, a hack together little car with an exposed roof sensor and non-functioning headlight stickers. Today, in a short blog post , the team revealed the first fully functioning model. Read more…

Read the original:
Here’s Google’s First Fully Functional Self-Driving Car Prototype

Volvo plans self-driving cars in 2014, envisions accident-free fleet by 2020.

Long hailed as one of the safest car producers in the world, Volvo hopes to retain that reputation by introducing vehicles that can avoid passenger injuries on their own by the year 2020. Its plans hinge on eliminating the largest cause of road accidents — the drivers themselves. The head of development for the program is convinced that driver-less cars are the future and that Volvo will be the first one there. The main technology underpinning Volvo’s autonomous automobiles is wireless internet, which would enable each car to be assigned a certain point on the road and give different vehicles the ability to interact with each other. The company is preparing to release an initial batch of autonomous vehicles, capable of speeds of up to 31 miles per hour, in 2014. We know from the SARTRE project that the automaker has been able to achieve autonomous speeds of 53 miles per hour in traffic for long distances, though they aren’t disclosing when those higher-speed prototypes would be publicly available. Filed under: Transportation Comments Via: Autopia (Wired) Source: Driver’s Seat (WSJ)

View original post here:
Volvo plans self-driving cars in 2014, envisions accident-free fleet by 2020.