Path: EDN Asia >> News Centre >> Industrial/Mil/Aero >> Flying blind: Can we now add autonomy to drones?
Industrial/Mil/Aero Share print

Flying blind: Can we now add autonomy to drones?

21 Mar 2016  | Junko Yoshida

Share this page with your friends

When will we see autonomy in consumer drones?

"It's too easy to crash a drone," said Philip McNamara, a serial entrepreneur and organizer of Drones Data X Conference. Too often, consumers send their drones—which can cost more than $1,000—slamming into a wall or soaring into the grasp of a tree.

Adding "autonomy" to flying drones– a pre-requisite for the proliferation of drones–would involve "a large body of work" that has barely begun, McNamara explained.


Figure 1: DJI takes on the challenge of autonomous flying. (Source: DJI)

Taking on the challenge of autonomous flying are DJI, the world's leading maker of drones and aerial cameras based in Shenzhen, China, and Movidius (San Mateo, Calif.), a designer of low-power computer vision SoCs.

Remi El-Ouazzane, Movidius CEO, told EE Times, "Efforts to achieve full autonomy for drones have been accelerating." Whether drones are used for package deliveries or building inspection, they require a collision avoidance feature—critical in autonomous flying, he said.

One of the ways to add autonomy is to enable drones to see.

Based on a Movidius vision-processing SoC called Myriad 2 VPU, DJI launched its Phantom 4 aircraft, with "the ability to sense and avoid obstacles in real time and hover in a fixed position without the need for a GPS signal," according to Movidius. That's "an industry first in making advanced visual guidance systems a standard feature for consumer drones," the company added.


Figure 2: The DJI Phantom 4 is able to sense objects and respond by avoiding, or halting flight until further instruction. (Source: DJI)

Drones can now sense an object and fly around it, dodge people who get in their way, and go from point A to B. That's quite a feat. But drones have reached only "the first level" of full autonomous flying, in El-Ouazzane's opinion. "They can do a lot more in the future," he added.

By integrating computer vision that can learn on the fly, drones will be able to do "scene labeling, semantic extraction and ultimately a lot more neural networks-based learning," he explained. Drones, for example, can identify a specific person and serve as his flying videographer.

Why DJI?

McNamara called DJI "the absolute leaders in the drone space." He told EE Times that other companies are only "scampering behind them, trying to nip at their heels."

1 • 2 • 3 Next Page Last Page

Want to more of this to be delivered to you for FREE?

Subscribe to EDN Asia alerts and receive the latest design ideas and product news in your inbox.

Got to make sure you're not a robot. Please enter the code displayed on the right.

Time to activate your subscription - it's easy!

We have sent an activate request to your registerd e-email. Simply click on the link to activate your subscription.

We're doing this to protect your privacy and ensure you successfully receive your e-mail alerts.

Add New Comment
Visitor (To avoid code verification, simply login or register with us. It is fast and free!)
*Verify code:
Tech Impact

Regional Roundup
Control this smart glass with the blink of an eye
K-Glass 2 detects users' eye movements to point the cursor to recognise computer icons or objects in the Internet, and uses winks for commands. The researchers call this interface the "i-Mouse."

GlobalFoundries extends grants to Singapore students
ARM, Tencent Games team up to improve mobile gaming

News | Products | Design Features | Regional Roundup | Tech Impact