Chinese drone autonomously avoids obstacles at 72 km/h
The Chinese drone SUPER can detect obstacles at great distances and therefore fly safely and autonomously at high speeds.
(Image: University of Hong Kong)
Scientists at the University of Hong Kong have developed a high-speed drone called the Safety-assured High-speed Aerial Robot, also known as SUPER, which can avoid obstacles at speeds of up to 45 mph, approximately 72 km/h. The drone uses various technologies such as 3D Lidar and artificial intelligence (AI) to precisely detect obstacles at a greater distance and select the correct flight route.
The drone is around 28 cm long and, as a quadcopter, has four electric motors. They allow the drone to accelerate to more than 72 km/h. This means that the drone is still a long way from the performance of remote-controlled racing drones, which can fly at speeds of over 160 km/h. However, it is characterized by its high maneuverability. However, it is characterized by high maneuverability and navigates independently through wooded areas, for example, using AI, as shown in the study “Safety-assured high-speed navigation for MAVs”, which was published in Science Robotics.
High detection performance thanks to 3D Lidar
To detect distances, the drone uses 3D Lidar, a pulse laser that is accurate to less than 1 cm at a distance of around 70 meters. For example, the 3D Lidar system can detect power cables that are only 2.5 mm thick. The drone can also react correspondingly well to small branches and twigs in its flight path. Current commercial drones, such as DJI's Mini 4 Pro, already have problems reliably locating such delicate obstacles at significantly lower speeds.
Videos by heise
The Lidar information is analyzed by an on-board computer on the SUPER drone, which uses it to determine two flight paths in real time. One flight path describes the safest route, the other an exploration route. The AI-based system automatically switches between the two flight paths and thus flies on an optimal route that takes safety and high speed into account at the same time.
The researchers tested the drone on various obstacle courses, including in the forest. The drone was able to master the courses at speeds of 20 m/s. This worked even in difficult lighting conditions. This also worked in difficult lighting conditions because the drone relies solely on Lidar and does not use cameras to detect objects.
Empfohlener redaktioneller Inhalt
Mit Ihrer Zustimmung wird hier ein externes Video (TargetVideo GmbH) geladen.
Ich bin damit einverstanden, dass mir externe Inhalte angezeigt werden. Damit können personenbezogene Daten an Drittplattformen (TargetVideo GmbH) übermittelt werden. Mehr dazu in unserer Datenschutzerklärung.
The researchers see a wide range of applications for the drone. Thanks to its autonomous navigation capabilities and high speed, it could be used for search and rescue missions. It could also be used to track criminals and for military reconnaissance purposes.
(olb)
