A real-time obstacle avoidance method for UAV based on binocular vision technology

Abstract

The invention discloses a real-time obstacle avoidance method for unmanned aerial vehicles based on binocular vision, including 1) collecting a parallax map through binocular cameras, performing three-dimensional reconstruction, and calculating depth; Obstacles within the range of the obstacle radius Zmax; 3), traverse the image, and calculate the obstacle situation of each pixel; 4), calculate the obstacle filling rate in each small grid unit: the filling rate is greater than 50%, there are obstacles; filling If the filling rate is within 10% to 50%, it is considered unknown and there is a risk; if the filling rate is less than 10%, it is considered safe. 5), analyze the size and distribution of the safe area, and then output and control the movement speed of the UAV front and back, left and right, up and down, and the rotational angular rate; 6), while performing binocular visual obstacle avoidance, allow the user to operate the remote control, Generate additional front and rear, left and right, up and down movement speed v and rotation angular rate ω of the UAV, and integrate them with the flight control system naturally and stably, so as to quickly and stably perform autonomous obstacle avoidance.

Description

technical field [0001] The invention belongs to the field of unmanned aerial vehicle flight control, and in particular relates to a real-time obstacle avoidance method for an unmanned aerial vehicle based on binocular vision. Background technique [0002] With the development of the UAV market, higher and higher requirements are put forward for the automatic perception and control of UAVs, especially in the aspect of active obstacle avoidance, so that UAVs can fly autonomously and safely in complex environments without accidents. Collision and bombing situation. At present, there are a few UAV companies that install millimeter-wave radar, ultrasonic radar, optical flow, infrared and other sensors on UAVs for obstacle avoidance applications. Unexpected situations such as missed detection and false detection are caused. In addition, there are currently related studies on UAV obstacle avoidance judgment through binocular vision, but most of them have not been well integrated ...

AI Technical Summary

Problems solved by technology

At present, a small number of UAV companies install millimeter-wave radar, ultrasonic radar, optical flow, infrared and other sensors on UAVs for obstacle avoidance applications. Cause unexpected situations such as missed detection and false detection

In addition, there are currently related studies on UAV obstacle avoidance judgment through binocular vision, but most of them have not been well integrated with the flight control system due to control strategy problems, and the control of pitch, yaw, and roll is naturally and stably Integrate into the system control loop

Images