Obstacle avoidance method for unmanned aerial vehicle flying in indoor coal yard

Abstract

The invention discloses an obstacle avoidance method for an unmanned aerial vehicle flying in an indoor coal yard. The obstacle avoidance method comprises the following steps: a laser range finder, an inertial navigation device and a visual camera are carried on the unmanned aerial vehicle; in the flight process of the unmanned aerial vehicle, the unmanned aerial vehicle obtains related information of dynamic obstacles in the environment through a laser range finder and a visual camera according to a path planned by the system and based on the path; and the related information is calculated through a microcomputer Raspberry Pi, and the possibility that the unmanned aerial vehicle collides with the dynamic obstacle in front of the flight is predicted based on the information, wherein the prediction result comprises continuous flight along the planned route and dynamic obstacle avoidance. According to the obstacle avoidance method, the unmanned aerial vehicle can jump out of the local optimal value, and the method is complete in structure and can be suitable for complex scenes with multiple obstacles.

Description

technical field [0001] The invention relates to the field of stocktaking of coal yards in thermal power plants, in particular to an obstacle avoidance method for unmanned aerial vehicles flying in indoor coal yards. Background technique [0002] Inventory of coal storage in closed coal sheds of thermal power plants is an indispensable link for thermal power generation enterprises. At present, coal panning is mainly divided into artificial coal panning and laser pan coal panning. [0003] The main principle of manual coal panning is: first, the accumulated coal is shaped by a bucket wheel stacker-reclaimer (the carrier used to stack coal), generally into a relatively regular trapezoid or rectangle. Then measure it manually with a tape measure, calculate its volume, and then get the weight according to the density. [0004] The main principle of the laser automatic coal panning instrument is: use a high-precision laser scanner to collect the surface of the stockyard. Process...

AI Technical Summary

Problems solved by technology

[0006] 1. Indoor coal yards are generally large, and UAVs need to consume a lot of resources to store the distribution of obstacles in the flying environment. The requirements for the microprocessor Raspberry Pi are relatively high, and it affects the algorithm processing speed, which is not conducive to the development of UAVs. real-time obstacle avoidance

[0007] 2. The UAV assigns values ​​to each grid of the environment map according to the laser rangefinder and visual camera, and then calculates the resultant force of the UAV based on the information of each grid, but the static grid assignment method does not fully consider the impact of dynamic obstacles on the grid. The dynamic influence of confidence, which may cause oscillations in the obstacle avoidance path

[0009] In the invention patent with the publication number CN105629985A "Indoor Quadrotor UAV 360° Three-dimensional Obstacle Avoidance System", it uses mechanical device anti-collision and relatively simple fuzzy control rules (detecting obstacles to turn left and right) as an obstacle avoidance strategy. Not suitable for complex scenes

Images