Skip to main content
  1. Home
  2. Emerging Tech
  3. Photography
  4. News

This auto-follow drone uses artificial intelligence to predict your next move

Add as a preferred source on Google

Selfie sticks are so 2015 — what you need is a personal cameraman in the form of a drone, that follows you around. The latest in such semi-autonomous unmanned aerial vehicles for hobbyists is called the Staaker. Three years in the making, Staaker was created by a team of engineers (including former Google X and CERN employees) and extreme sports enthusiasts that consulted with professional production companies on building a camera drone than can shoot epic movies with ease. A unique feature is that is also uses artificial intelligence to predict what you might do next.

Like other auto-follow drones, the Staaker uses a GPS wristband to track the user, but that’s where the similarities start to thin out. The drone works as a personal cameraman with a bit more of the “man” than other auto-follow drones – artificial intelligence technology allows the drone to anticipate or react to the next move, and then uses that information to set up the best shot. The artificial intelligence is combined with five different, user-activated follow modes (including circling around the user, following from behind, or turning the direction to get a scenic shot of the environment) that allows the user to control where and how the drone shoots. For safety, the Staaker maintains a two-meter (6.6 feet) cloud around the user, while it can follow from as far as a 1,150 feet.

Recommended Videos

“We use all the data [collected] from the tracker to predict what you are going to do next,” said CEO and founder of Staaker, OJ Seeland. “It picks up subtle signs and reacts to them.” If it “senses” you might maneuver toward the right during a downhill ride, for example, the flying machine will compensate.

 

The Stakker also boasts one of the fastest speeds and longest flight times for self-flying camera drones. The Staaker can fly up to 50 mph, while the battery has enough juice for up to 30 minutes of flight time depending on the usage. Interchangeable batteries mean it can be relaunched quickly without waiting for a recharge. According to the company, the Staaker is easy to launch with an eight-second prep time.

Building a fast, intelligent drone wasn’t easy — the company went through 50 prototypes over three years before finalizing the Staaker. “As a company we are committed to delivering the world’s first intelligent auto-follow drone with the best design qualities on the market,” Seeland said.  “We are really excited to show the world what we have built.”

As for the camera, the Staaker fits a GoPro Hero4 camera (not included) on a three-axis gimbal to shoot stabilized 4K video and 12 megapixel stills. When it lands, the gimbal automatically retracts to prevent the camera from hitting the ground. The Staaker could also function as a handheld rig, allowing filmmakers to utilize the gimbal when it is not in flight. The drone is designed to withstand harsh conditions with its water-resistant design, although the GoPro camera isn’t since it’s out of its protective housing – something to keep in mind when using the Staaker in wet conditions. However, the company says the drone itself has been stress-tested in a range of conditions from the Arctic Circle to Hawaii.

The company told us it went with the Hero4 because it’s the most ubiquitous among action cams available (the smaller Session, however, is not supported). It also worked directly with GoPro during development, Mike Luff, Staaker’s VP or marketing, said. While more resourceful users could create a mount for another action cam, the Staaker is designed to work with the Hero4. The Staaker provides power to the camera without any affecting the drone’s flying time, Luff said, although the user needs to manually start and stop recording on the camera before take-off. In future versions, the company may go with an embedded camera that’s more powerful.

The Stakker weighs in at just 3.5 pounds and folds for easier transport. There’s no need to attach or remove the propellers; once out of its case and unfolded, the Staaker is ready to fly. It’s so compact, in fact, that two Staaker cases can fit inside a large backpack.

Luff recently gave us a demo of a prototype, which he carried with him in a standard backpack. He easily controlled the drone with the tracker on his wrist, and it followed him as he ran around a field and responded to his controls without fail. Takeoff and landing were smooth, and using GPS, the Staaker can be set to land in a designated spot as well. Besides manually controlling the drone or setting an auto-follow mode, there is a small LCD on the tracker that shows battery level, as well as location should the Staaker somehow gets lost. In this first version, Staaker lacks any obstacle avoidance awareness, like trees, so that’s something the user needs to plan; the company will build that function into the second-generation version, Luff said. While he wasn’t able to demonstrate the drone’s 50-mph capability, Luff said he has tested the prototype while driving in a fast-moving car, and the Staaker had no issues keeping up.

While some auto-follow drones, like the Lily, are employing computer vision for tracking, Luff said the technology is ready yet. A tracking device, for now, is more dependable.

Shipping in December, the Staaker will list for $1,795, with the price including the drone as well as the waterproof tracker and carrying case. Pre-orders begin today with a $600 discount from the list price.

Hillary K. Grigonis
Hillary never planned on becoming a photographer—and then she was handed a camera at her first writing job and she's been…
Yet another study says AI is bad for elections, and the rabbit hole gets worse
AI may be an election bomb waiting for someone to light the fuse
Voters cast their ballots on Election Day

Another election, another study has concluded that asking an AI chatbot for political guidance is a spectacularly bad idea. Research conducted during Hungary’s 2026 parliamentary election found that ChatGPT and Google Gemini offered not just inaccurate but also inconsistent and unreliable voting advice. The chatbots misclassified voter profiles, overlooked relevant parties, recommended parties absent from the ballot, and sometimes produced materially different answers when given the same information repeatedly.

AI keeps failing the voter test

Read more
Samsung’s humanoid robot ambitions are real, but factories come first
Samsung’s new robotics division has humanoids in its sights, although its immediate business is far more practical factory automation
Robot Touch Human Finger

Samsung wants a place in the humanoid race, but its new robotics push begins with machines built for factories rather than homes.

The CEO-led RX robotics division will initially focus on manufacturing robots. Samsung has separately identified humanoids as a priority, although it hasn’t announced a commercial model or explained where one fits into the division’s immediate plans.

Read more
The future of AI may depend on this one behind-the-scenes change
Running Claude on Android.

Whenever a new AI model arrives, it's easy to get caught up in the bells and whistles. We talk about how much smarter it is, how quickly it answers questions, or how realistic its images have become. But here's the thing: none of that matters much if the AI can't reliably work with the apps and services people use every day.

That's why an upcoming update to the Model Context Protocol (MCP) caught my attention. It isn't a new chatbot or a fancy AI model. In fact, most people will never even know it's happening. But it could quietly make the AI ecosystem a lot healthier. If you've never heard of MCP before, don't worry. Think of it as a shared language that lets AI assistants safely talk to apps like Gmail, Slack, calendars, databases, and countless other services. Instead of every company inventing its own way to make those connections, MCP gives everyone a common rulebook.

Read more