Aircraft autonomous obstacle avoidance system and method and aircraft

Abstract

The embodiment of the invention provides an aircraft autonomous obstacle avoidance system and method and an aircraft. A binocular camera and a millimeter wave radar are combined. A push broom stereo vision algorithm and an advanced image data fusion method are used to mark an obstacle and detect the obstacle. The position and shape and texture information of the obstacle in front of the aircraft can be quickly and accurately acquired. An accurate basis is provided for the aircraft to avoid the obstacle in real time. The autonomous flight and intelligence level of the aircraft is improved. Theenvironmental adaptability of the aircraft is enhanced. The aircraft can safely fly to complete a task in a complex environment.

Description

technical field [0001] The invention relates to the field of UAV perception and detection, in particular to an aircraft autonomous obstacle avoidance system, method and aircraft. Background technique [0002] The UAV market has ushered in a blowout development in recent years, and has been widely used in land surveying and mapping, disaster investigation, agricultural plant protection, aerial photography, power line inspection and other fields. In the face of increasingly complex application scenarios and flight environments, intelligent flight, simple operation, safety and reliability have become the main trends in the development of drones. UAV autonomous obstacle avoidance technology uses detection sensors to perceive the surrounding flight environment in real time, autonomously detect and avoid obstacles, and realize the autonomous flight of UAVs in complex environments. This not only improves the intelligence level of drones, but also lowers the operating threshold of ...

AI Technical Summary

Problems solved by technology

DJI's "Phantom 4" product uses stereo vision and ultrasonic sensors as the detection system to realize the autonomous obstacle avoidance of UAVs, but it is only suitable for rotor platforms, and has no impact on the flight speed and operating environment of UAVs. There are relatively large restrictions; Aerotenna of the United States uses an obstacle avoidance system based on millimeter-wave radar to realize the autonomous obstacle avoidance of rotor drones in simple scenarios, but its flight environment is simple and the flight platform is fixed

Chinese patent application (publication number: CN205049143U) provides a UAV autonomous obstacle detection system based on binocular vision, which only uses the traditional binocular stereo vision algorithm. Searching and positioning in a full range, the algorithm is complex, and the real-time performance is not high. Among many detection sensors, a single sensor has its shortcomings and shortcomings, which limits the effect and application of obstacle avoidance.

Images