Skip to main content

The DroNet algorithm teaches drones to navigate city streets like cars

Dronet: Learning to Fly by Driving
Drones can be dangerous. From hacking unprotected devices to falling from the sky, drones can cause a lot of digital and physical damage. As these little flying machines become commonplace in public spaces, researchers have even intentionally crashed them into mannequins and uncooked pork to study just how dangerous they can be. The result isn’t pretty, so pedestrians would be wise to be weary when they see one zipping toward them on a city street.

But a research team at the University of Zurich and the National Centre of Competence in Research Robotics in Switzerland may help put a little more consistency and certainty into how drones will move around us in the future. The researchers have developed a system that allows drones to navigate autonomously around obstacles and through unstructured streets by teaching the drone to act more like cars and bicycles.

“We have developed an algorithm that can safely drive a drone through the streets of a city and react promptly to unforeseen obstacles, such as other vehicles and pedestrians,” Davide Scaramuzza, head of the University of Zurich’s Robotics and Perception Group that developed the system, told Digital Trends.

Scaramuzza and his colleagues have called the training algorithm DroNet, short of Drone Network, a nod to the deep neural network that makes its magic happen. By observing and learning how cars and bicycles react to the dynamic environment of a city street, the DroNet algorithm lets the drones recognize static and moving obstacles, triggering it to slow down and avoid crashes.

“With this algorithm, we have taken a step forward toward integrating autonomous drones into our ‘everyday life,’” Scaramuzza said. “Instead of relying on sophisticated sensors, DroNet only requires a single camera — very much like that of every smartphone — on a drone.”

Most of today’s drones use GPS to navigate, which is great if they’re traveling above buildings but complicated if they are flying at low altitudes in densely populated streets. So, in order to teach the drone to navigate city streets safely, Scaramuzza and his team collected data from cars and bicycles in urban settings, and fed that data into the DroNet algorithm, which used the data to learn street etiquette — like staying in one’s own lane and decelerating when approaching obstacles.

Such a common sense system could become valuable as drones take up tasks like delivery and search and rescue. However, Scaramuzza and his team will first have to refine the algorithm to enable faster and more agile flying.

A paper detailing the study was published this week in the journal IEEE Robotics and Automation Letters.

Dyllan Furness
Dyllan Furness is a freelance writer from Florida. He covers strange science and emerging tech for Digital Trends, focusing…
4 simple pieces of tech that helped me run my first marathon
Garmin Forerunner 955 Solar displaying pace information.

The fitness world is littered with opportunities to buy tech aimed at enhancing your physical performance. No matter your sport of choice or personal goals, there's a deep rabbit hole you can go down. It'll cost plenty of money, but the gains can be marginal -- and can honestly just be a distraction from what you should actually be focused on. Running is certainly susceptible to this.

A few months ago, I ran my first-ever marathon. It was an incredible accomplishment I had no idea I'd ever be able to reach, and it's now going to be the first of many I run in my lifetime. And despite my deep-rooted history in tech, and the endless opportunities for being baited into gearing myself up with every last product to help me get through the marathon, I went with a rather simple approach.

Read more
This bracelet helps you fall asleep faster and sleep longer
woman-in-bed-wearing-twilight-apollo-on-ankle

This content was produced in partnership with Apollo Neuroscience.
Have you been struggling to get the recommended seven hours of sleep? It's always frustrating when you get in bed at a reasonable time, then toss and turn for a hours before you actually sleep. The quality of that sleep is important too. If you're waking up multiple times during the night, you're likely not getting the quality REM cycle sleep that truly rejuvenates your body. If traditional remedies like herbal teas and noise machines just aren't helping, maybe it's time to try a modern solution. Enter the Apollo wearable.

Now we understand being a little skeptical. How can a bracelet on your wrist or ankle affect your sleep patterns? Certainly the answer to a better night's sleep can't be so simple. We considered these same things when we first heard of it. We'll dive deeper into the science behind the Apollo wearable, but suffice it to say that many people have experienced deeper, uninterrupted sleep while wearing one.
A non-conventional approach to better sleep

Read more
The 11 best Father’s Day deals that you can get for Sunday
Data from a workout showing on the screen of the Apple Watch Series 8.

Father's Day is fast approaching and there's still time to buy your beloved Dad a sweet new device to show him how much you love him. That's why we've rounded up the ten best Father's Day tech deals going on right now. There's something for most budgets here, including if you're able to spend a lot on your loved one. Read on while we take you through the highlights and remember to order fast so you don't miss out on the big day.
Samsung Galaxy Tab A8 -- $200, was $230

While it's the Plus version of the Samsung Galaxy Tab A8 that features in our look at the best tablets, the standard variety is still worth checking out. Saving your Dad the need to dig out their laptop or squint at a small phone screen, the Samsung Galaxy Tab A8 offers a large 10.5-inch LCD display and all the useful features you would expect. 128GB of storage means plenty of room for all your Dad's favorite apps as well as games too. A long-lasting battery and fast charging save him the need for a power source too often too.

Read more