menu
close

Bird-Like Drone Navigates Forest Obstacles at 45 MPH Without GPS

Researchers at the University of Hong Kong have developed a groundbreaking autonomous drone that can fly through dense forests at speeds up to 45 mph without relying on GPS or traditional navigation systems. The Safety-Assured High-Speed Aerial Robot (SUPER) uses advanced 3D LiDAR technology to detect obstacles as thin as 2.5 millimeters from up to 70 meters away. This biomimetic technology represents a significant advancement in autonomous flight capabilities, emulating birds' natural ability to navigate complex environments with remarkable speed and precision.
Bird-Like Drone Navigates Forest Obstacles at 45 MPH Without GPS

A team of engineers led by Professor Fu Zhang at the University of Hong Kong has created a revolutionary autonomous drone that mimics birds' natural navigation abilities, potentially transforming search and rescue operations and environmental monitoring.

The Safety-Assured High-Speed Aerial Robot (SUPER) can fly at speeds exceeding 45 mph through dense forests while avoiding obstacles as thin as power lines or twigs, using only onboard sensors and computing power. Unlike conventional drones that rely on GPS signals or pre-mapped routes, SUPER navigates completely autonomously in unknown environments.

The breakthrough lies in SUPER's sophisticated integration of hardware and software. The system utilizes a lightweight 3D LiDAR sensor capable of detecting obstacles up to 70 meters away with pinpoint accuracy. This is paired with an advanced planning framework that simultaneously generates two flight trajectories – one optimizing for speed by exploring unknown spaces and another prioritizing safety by remaining within known, obstacle-free zones.

"It's like giving the drone the reflexes of a bird, enabling it to dodge obstacles in real-time while racing toward its goal," explains Professor Zhang. The drone's compact design features a wheelbase of just 280 mm and a takeoff weight of 1.5 kg, with a thrust-to-weight ratio exceeding 5.0 for exceptional agility.

The research team envisions numerous applications for this technology, including autonomous delivery, power line inspection, and forest monitoring. In search and rescue missions, SUPER-equipped drones could swiftly navigate disaster zones day or night, locating survivors or assessing hazards more efficiently than current systems. The technology's ability to operate in GPS-denied environments and various lighting conditions makes it particularly valuable for emergency response scenarios.

The research has been published in Science Robotics, representing a significant milestone in autonomous flight technology that bridges the gap between laboratory research and real-world applications.

Source:

Latest News