Skip to main content

MIT developed an algorithm that will make drones more agile at high speeds

mit drone algorithm high speed dji mavic pro 06
Image used with permission by copyright holder
We don’t think we are going out on a limb when we say that autonomous drones are going to be big. But, like the archetypal protagonist at the start of any hero’s quest, they need to learn a few things first.

One such challenge is how to fly quickly while managing to dodge obstacles. The reason this is hard for drones is because their cameras can only process images up to a certain speed since they have to do it frame by frame. Anything faster than 30 mph causes a bit of a headache.

Recommended Videos

That is where a new research project from the Massachusetts Institute of Technology comes into play. It builds on a technology called the Dynamic Vision Sensor (DVS), invented by researchers in Zurich. The DVS continuously visualizes scenes by looking for changes in brightness. This is similar to the way that the human brain senses visual information and means that it can work at short, microsecond intervals much faster than regular cameras.

The problem is the amount of processing time it requires due to the huge mass of data. By the time an obstacle has been detected and a control outputted, a drone would have already crashed.

MIT’s work represents a step forward. It is an algorithm that is able to isolate very specific changes in brightness, which has the effect of reducing complex scenes to their most essential elements.

“The DVS has had a lot of empirical successes,” lead author Prince Singh, a graduate student in MIT’s Department of Aeronautics and Astronautics, told Digital Trends. “However, there [hasn’t previously been] a concrete algorithm that can process the sensor’s ambiguous data to, for instance, control a dynamic system such as a drone. My work addresses the control of any system that has a linearized representation by making sense of the DVS’s ambiguous data. This work unifies the empirical successes observed, and most importantly, one doesn’t need knowledge of the problem’s geometry, as was the case for works until now.”

Singh is currently presenting the work at the Institute of Electrical and Electronics Engineers American Control Conference in Seattle. Next up, the plan is to publish a paper on the work. Hopefully, it won’t be too long after that before drones — and other autonomous robots — can take advantage of this high-speed breakthrough.

Luke Dormehl
Former Digital Trends Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Trump administration prepares to end Biden’s EV tax incentive, report says
president biden drives 2022 ford f 150 lightning electric pickup truck prototype visits rouge vehicle center

If you’re looking to buy or lease an electric vehicle (EV) and benefit from the Biden administration’s $7,500 tax incentive, you’d better act soon.

The transition team of the incoming Trump administration is already planning to end the credit, according to a report from Reuters citing sources with direct knowledge of the matter.

Read more
Hertz is selling used Teslas for under $20K, Chevrolet Bolt EVs under $14K
2018 Chevrolet Bolt EV

Tesla CEO Elon Musk recently nixed hopes of a regular Tesla model ever selling for $25,000.

But he was talking about new models. For car rental company Hertz, the race to sell used Teslas and other EVs at ever-lower prices is not only still on but accelerating.

Read more
Never mind slowing sales, 57% of drivers will likely have an EV in 10 years

Sales of electric vehicles (EVs) have slowed globally over the past few years. But should EV makers cater more to the mainstream, it’s likely that 57% of drivers will have an EV in 10 years, consulting firm Accenture says.

Last year, nearly 14 million EVs were sold globally, representing a 35% year-on-year increase. But it was much slower than the 55% sales growth recorded in 2022 and the 121% growth in 2021.

Read more