Multisensor fusion-based nmanned aerial vehicle SLAM (simultaneous localization and mapping) navigation method and system

Abstract

The invention discloses a multisensor fusion-based unmanned aerial vehicle SLAM (simultaneous localization and mapping) navigation method and a multisensor fusion-based unmanned aerial vehicle SLAM navigation system. The multisensor fusion-based unmanned aerial vehicle SLAM navigation method comprises the following steps: acquiring image information of the surrounding environment of an unmanned aerial vehicle in real time, and acquiring pose information of the unmanned aerial vehicle according to the image information; acquiring depth information of the unmanned aerial vehicle and an obstaclein real time, fusing the pose information and the depth information to construct an obstacle depth map, and acquiring global position information of the unmanned aerial vehicle according to the obstacle depth map; according to the global pose information and the obstacle depth map, generating a flight path of the unmanned aerial vehicle by an online dynamic path planning method, and controlling autonomous obstacle-avoiding flight of the unmanned aerial vehicle according to the flight path. Through the multisensor fusion-based unmanned aerial vehicle SLAM navigation method and the multisensor fusion-based unmanned aerial vehicle SLAM navigation system, real-time localization and mapping of the unmanned aerial vehicle in a complex environment can be achieved; compared with the conventional unmanned aerial vehicle navigation technology, the navigation technology adopted by the invention has the advantages as follows: real-time localization and mapping and autonomous navigation are achieved, and the intelligence degree and the navigation accuracy of the unmanned aerial vehicle are improved.

Description

technical field [0001] The invention relates to the technical field of navigation positioning and control, in particular to a multi-sensor fusion-based SLAM navigation method and system for an unmanned aerial vehicle. Background technique [0002] Unmanned Aerial Vehicle (UAV) is an unmanned aerial vehicle controlled by radio remote control equipment and its own program. In recent years, the wide application of unmanned aerial vehicle (UAV) in many fields has attracted people's attention. For example, it can carry out reconnaissance and attack in the military; A type of unmanned aerial vehicle, which has the characteristics of good maneuverability, simple structure, and stable control, and is suitable for flight operations in complex environments. For drone navigation, the most critical link is how to obtain the pose information of the drone. [0003] Traditional UAV navigation technologies, such as GPS, inertial sensors, ultrasonic sensors and other technologies, are base...

AI Technical Summary

Problems solved by technology

However, existing SLAMs have certain limitations. Existing monocular visual SLAMs, such as LSD-SLAM and ORB-SLAM, have disadvantages such as easy loss of feature point matching and slow matching speed in a single background environment; Visual SLAM has relatively high requirements for algorithms and airborne hardware, and has low recognition ability for small obstacles; existing depth cameras can only be used indoors, and are greatly affected by natural light outdoors; laser SLAM, such as hectorSLAM, gmapping, there are problems such as large amount of calculation, large noise, difficulty in loop detection, easy loss of matching, etc.

Images