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

DJI’s new obstacle avoidance tech aims to make drones crash proof

Add as a preferred source on Google

It may not be as glamorous as building vehicles that go faster, fly higher, or shoot more beautiful images, but making drones less likely to crash into walls and people’s faces is pretty critical to advancing the technology as a whole. Thankfully, DJI is on the case.

Earlier today, the company unveiled a new drone — but arguably more interesting was the new Guidance system unveiled quietly alongside it. Guidance is essentially a multimodal sensing system that gives the company’s newly unveiled Matrice 100 drone (more on that in a moment) autonomous obstacle avoidance capabilities.

Recommended Videos

The system consists of an array of five ultrasonic rangefinders (aiming left, right, forward, backward, and down), a set of integrated visual cameras running some of “the most advanced computer vision algorithms in the world,” and an onboard CPU to process all the data.

guidance moduleRelated: DJI’s new Phantom 3 drone gets 4K cam, live HD streaming, ‘follow me’ autopilot

Using these two types of sensor in concert, Guidance gives drones the ability to hover in place and maintain its position without GPS. Even when flying at high speeds, DJI’s high-precision stereo algorithms provide positioning info over practically any type of terrain, allowing the drone to achieve hovering that’s accurate to within centimeters, and scan its immediate environment to detect/avoid obstacles in real time, without any input from the pilot.

In the future, these kinds of systems could be built directly into consumer drones, making it much more difficult to send your DJI Phantom 3 careening into the trunk of a tree, or fly your Inspire 1 a little bit too close to Enrique Iglesias.

For now, however, the technology only exists as an attachment for DJI’s newly-announced Matrice 100 drone. Unlike the company’s more consumer-focused Phantom or Inspire series drones, Matrice is designed with developers in mind. It’s modular, customizable, and built with a dizzying array of ports, expansion bays, and mounts for adding adding stuff onto the drone. The idea is that this will make it easier for people to experiment with different configurations, and outfit the drone with whatever sensors they need for a particular job.

Drew Prindle
Former Senior Editor, Features
Drew Prindle is an award-winning writer, editor, and storyteller who currently serves as Senior Features Editor for Digital…
Researchers hid a prompt injection inside a PNG, and AI fell for it
Hacker

AI coding assistants like Claude are becoming every developer's favorite coworker. They can review code, explain confusing functions, and even write entire features with a single prompt. But new research suggests that this growing trust could also become their biggest weakness.

A team of security researchers (professor Sudipta Chattopadhyay and researcher Murali Ediga) has demonstrated an unusual attack that doesn't target the AI model directly. Instead, it targets what the AI doesn't pay enough attention to during code reviews. Rather than hiding malicious instructions in lines of code, the researchers tucked them inside an image file. Since many AI review tools treat images as decorative assets rather than as something worth inspecting, the pull request can appear perfectly harmless and sail through the review.

Read more
AI has already fallen into the wrong hands and they’re using it to make bombs
Logo, Text

Artificial intelligence has quickly become the go-to tool for everything from writing emails and summarizing meetings to helping students study or developers debug code. But the same technology that saves people time can also be misused, and a new report suggests that terrorist organizations are finding ways to do exactly that.

According to a research paper shared with The New York Times ahead of its publication, researchers found evidence that members of Boko Haram have been using popular AI chatbots to support both day-to-day activities and combat-related tasks. Interviews with 27 former members conducted in Nigeria over the past two years suggest that tools such as ChatGPT, Gemini, Claude, Grok, Meta AI, and DeepSeek were used to gather technical information, troubleshoot weapons, and even assist with planning attacks.

Read more
Claude Code can now browse the web without opening Chrome
The desktop app now includes an in-app browser that can read websites, click links, and interact with web apps.
Claude Code Featured

Developers spend a surprising amount of time bouncing between their code editor, browser tabs, API documentation, GitHub issues, and design files. Anthropic thinks Claude Code should simply do all of that without constantly asking users to switch windows. The company has announced a new in-app browser for Claude Code on desktop, allowing its AI coding assistant to open websites, read documentation, inspect designs, and interact with web pages directly from within the application.

A browser built into Claude Code

Read more