CN114815894A - A path optimization method, device, electronic device, unmanned aerial vehicle and storage medium - Google Patents

Abstract

Embodiments of the present invention provide a path optimization method, device, electronic device, unmanned aerial vehicle, and storage medium, and relate to the technical field of unmanned aerial vehicles, including: acquiring a plurality of data scanned by the laser radar within a preset time period Continuous obstacle position data; in the case of dynamic obstacle position data in each of the obstacle position data, predict the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data, and obtain the dynamic obstacle The predicted motion data; obtain the environmental wind parameters and the attitude data of the UAV, and the environmental wind parameters include the wind power and wind direction of the environment where the UAV is located; based on the locust algorithm, according to the predicted motion data, the According to the environmental wind parameters and the attitude data, the initial flight path of the UAV is optimized. The present invention can at least partially solve the problem of how to avoid dynamic obstacles during the flight of the UAV.

Description

A path optimization method, device, electronic device, unmanned aerial vehicle and storage medium

technical field

The present invention relates to the technical field of unmanned aerial vehicles, and in particular, to a path optimization method, device, electronic equipment, unmanned aerial vehicle and storage medium.

Background technique

Unmanned aerial vehicle technology develops with each passing day, nowadays, various fields can use unmanned aerial vehicle to carry out some tasks.

The UAV path planning problem is an important part of the UAV scheduling system framework. In the existing UAV path planning, some static obstacles are usually considered, and these static obstacles are avoided when planning the path. .

However, how to avoid dynamic obstacles when the UAV is flying is still a problem to be solved.

SUMMARY OF THE INVENTION

The present invention provides a path optimization method, device, electronic device, unmanned aerial vehicle and storage medium, which can at least partially solve the above technical problems.

Embodiments of the present invention can be implemented as follows:

In a first aspect, the present invention provides a path optimization method, which is applied to an unmanned aerial vehicle, where the unmanned aerial vehicle includes a lidar, and the method includes:

Acquire a plurality of continuous obstacle position data scanned by the lidar within a preset time period;

In the case that there is dynamic obstacle position data in each of the obstacle position data, predict the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data, and obtain the predicted motion data of the dynamic obstacle;

Acquiring environmental wind parameters and attitude data of the drone, where the environmental wind parameters include wind force and wind direction of the environment where the drone is located;

Based on the locust algorithm, the initial flight path of the UAV is optimized according to the predicted motion data, the environmental wind parameters and the attitude data.

Optionally, the UAV further includes a visible light camera, and the method further includes:

Acquire a plurality of continuous image data of the target area captured by the visible light camera within the preset time period, where the target area is the area where the obstacle corresponding to the dynamic obstacle position data is located;

Predict the motion state of the dynamic obstacle according to a plurality of continuous image data, and obtain auxiliary motion data of the dynamic obstacle;

Based on the auxiliary motion data, the predicted motion data is optimized to obtain optimized predicted motion data;

The optimization of the initial flight path of the unmanned aerial vehicle includes: based on the locust algorithm, according to the optimized predicted motion data, the environmental wind parameters and the attitude data, to the initial flight path of the unmanned aerial vehicle. The flight path is optimized.

Optionally, in the case that there are more than two dynamic obstacles corresponding to the dynamic obstacle position data, the method further includes:

respectively obtaining the optimized predicted motion data corresponding to each of the dynamic obstacles;

Merging a plurality of the optimized predicted motion data to obtain coordinated motion data;

The optimization of the initial flight path of the unmanned aerial vehicle includes: based on the locust algorithm, according to the cooperative motion data, the environmental wind parameters and the attitude data, performing the optimization on the initial flight path of the unmanned aerial vehicle. optimization.

Optionally, before optimizing the initial flight path of the UAV, the method further includes:

Based on the Lyapunov function, the error of the cooperative motion data is eliminated.

Optionally, the method further includes the step of obtaining the initial flight path, the step including:

Obtain a UAV map, where the UAV map includes a target point, a starting point, and a static obstacle point marked by the user;

The initial flight path is generated according to the starting point, the target point and the static obstacle point.

Optionally, the method further includes:

Determine whether there is position data corresponding to the static obstacle position in the obstacle position data;

If there is, the obstacle position data other than the position data corresponding to the static obstacle points are screened out as the dynamic obstacle position data.

In a second aspect, the present invention provides a path optimization device, which is applied to an unmanned aerial vehicle. The unmanned aerial vehicle includes a laser radar, and the device includes:

an obstacle location data acquisition unit, configured to acquire a plurality of continuous obstacle location data scanned by the lidar within a preset time period;

A prediction unit, configured to predict the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data under the condition that there is dynamic obstacle position data in each of the obstacle position data, and obtain the prediction of the dynamic obstacle sports data;

an environmental parameter acquisition unit, configured to acquire environmental wind parameters and attitude data of the drone, where the environmental wind parameters include wind force and wind direction of the environment where the drone is located;

The path optimization unit, based on the locust algorithm, optimizes the initial flight path of the UAV according to the predicted motion data, the environmental wind parameters and the attitude data.

In a third aspect, the present invention provides an unmanned aerial vehicle, comprising a radar, a wind sensor, a gyroscope, and a controller, wherein the controller is respectively connected in communication with the radar, the wind sensor, and the gyroscope;

the radar is used for acquiring and feeding back position data of obstacles to the controller;

The wind sensor is used for acquiring and sending ambient wind parameters to the controller;

The gyroscope is used to acquire and send the attitude data of the UAV to the controller;

The controller is configured to execute the path optimization method described in any one of the above.

In a fourth aspect, the present invention provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implements any one of the methods described above when the processor executes the program A step of.

In a fifth aspect, the present invention provides a storage medium, the storage medium includes a computer program, and when the computer program runs, it controls an electronic device where the computer-readable storage medium is located to implement the steps of any one of the methods described above.

The beneficial effects of the embodiments of the present invention include, for example:

When the UAV encounters a dynamic obstacle, the initial flight path of the UAV is optimized by predicting the motion state of the dynamic obstacle, so that the UAV can effectively avoid the dynamic obstacle and prevent the UAV from flying. There are cases where the drone is damaged by hitting a dynamic obstacle.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

FIG. 2 is a flowchart of steps of a path optimization method provided by an embodiment of the present invention;

3 is a flowchart of steps of a method for obtaining an initial flight path according to an embodiment of the present invention;

4 is a schematic diagram of a UAV map according to an embodiment of the present invention;

FIG. 5 is a frame diagram of a path optimization apparatus provided by an embodiment of the present invention.

Icon: 100-electronic equipment; 110-memory; 120-processor; 130-communication module; 300-path optimization device; 301-obstruction position data acquisition unit; 302-prediction unit; 303-environmental parameter acquisition unit; 304- Path optimization unit.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.

Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

In addition, where the terms "first", "second" and the like appear, they are only used to differentiate the description, and should not be construed as indicating or implying relative importance.

It should be noted that the features in the embodiments of the present invention may be combined with each other without conflict.

Please refer to FIG. 1 , which is a schematic block diagram of an electronic device 100 provided by the present application, including a memory 110 , a processor 120 and a communication module 130 . The memory 110 , the processor 120 and the communication module 130 . Each element is directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

The memory 110 is used for storing programs or data. The memory 110 may be, but not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM), or Erasable Programmable Read-Only Memory (EPROM), Electrical Erasable Programmable Read-Only Memory (EEPROM), etc.

The processor 120 is used to read/write data or programs stored in the memory, and perform corresponding functions.

The communication module 130 is configured to establish a communication connection between the electronic device and other communication terminals through the network, and to send and receive data through the network.

It should be understood that the structure shown in FIG. 1 is only a schematic structural diagram of the electronic device 100 , and the electronic device 100 may further include more or less components than those shown in FIG. 1 , or have different components from those shown in FIG. 1 . For example, the electronic device 100 may further include a path optimization unit, a prediction unit, and the like. Each component shown in FIG. 1 may be implemented in hardware, software, or a combination thereof.

Most of the existing technical solutions are to obtain the position of the obstacle through the radar mounted on the drone, and then plan the next route of the drone according to the obtained position, so as to avoid the obstacle, or to use the image captured by the mounted camera. processing to obtain the obstacle position, or a combination of the two to improve the obstacle position accuracy. They are all "passive" to make obstacle avoidance instructions.

However, in actual flight missions, many obstacles are not stationary, and must be avoided for approaching obstacles; for distant obstacles, sometimes it is not necessary to change the original flight route of the UAV; The time may happen to intersect with the UAV on the flight path, which needs to be predicted in advance. Therefore, it is very necessary to assess whether there is a collision risk on the UAV path and optimize the UAV path in advance.

Referring to FIG. 2, a path optimization method provided in the embodiment of this specification is applied to an unmanned aerial vehicle. The unmanned aerial vehicle includes a laser radar, and the method includes the following steps:

Step S120: Acquire a plurality of continuous obstacle position data scanned by the lidar within a preset time period.

Step S130: In the case where there is dynamic obstacle position data in each of the obstacle position data, predict the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data, and obtain the predicted motion data of the dynamic obstacle .

Step S140: Obtain environmental wind parameters and attitude data of the drone, where the environmental wind parameters include wind force and wind direction of the environment where the drone is located.

Step S150: Based on the locust algorithm, according to the predicted motion data, the environmental wind parameters and the attitude data, optimize the initial flight path of the UAV.

The above steps are respectively described below.

In step S120, a plurality of continuous obstacle position data scanned by the lidar within a preset time period are acquired.

The preset time period can be an end time after the lidar scans the obstacle position data, or it can be a period of time that starts timing when the lidar starts.

The lidar set on the UAV starts to scan and monitor whether there are obstacles in real time when the UAV starts to fly according to the predetermined initial route. Lidar is a radar system that emits a laser beam to detect the position, velocity and other characteristic quantities of a target. When there is an obstacle, a detection signal (laser beam) is sent to the obstacle, and then the received signal (target echo) reflected from the obstacle is compared with the transmitted signal, and after proper processing, the obstacle can be obtained. related information, such as target distance, orientation, height, speed, attitude, and even shape and other parameters, so as to identify obstacles and obtain these data, that is, data obstacle position data.

Taking the preset time period as the end time after the lidar scans the obstacle position data as an example, after the lidar scans the obstacle position data, it scans once every 0.5 seconds within 5 seconds to obtain multiple consecutive the obstacle position data, and then send these obstacle position data to the processor.

Optionally, as shown in FIG. 3 , the method further includes the step of obtaining the initial flight path, and the step includes:

Step S111: obtaining a UAV map, where the UAV map includes a target point, a starting point, and a static obstacle point marked by the user;

Step S112: Generate the initial flight path according to the starting point, the target point and the static obstacle point.

As shown in Figure 4, the drone map can be a map imported by the user from an external device into the drone. The drone map can include the starting point of the drone and the target point that the drone needs to reach. Positions and static obstacle positions marked by the user on the UAV map.

After the processor obtains the UAV map imported by the user, it can automatically generate a path that can avoid the static obstacle points according to the target point, the starting point and the static obstacle points marked by the user, that is, the initial flight path .

Optionally, the method further includes:

Determine whether there is position data corresponding to the static obstacle position in the obstacle position data;

If there is, the obstacle position data other than the position data corresponding to the static obstacle points are screened out as the dynamic obstacle position data.

Obstacles scanned by lidar can include dynamic obstacles and static obstacles. In order to filter out dynamic obstacles in obstacles scanned by lidar, as an optional By combining the obstacle location data scanned by the lidar, it is determined from the obstacle location data which obstacle location data is the location data corresponding to the static obstacle points marked by the user on the UAV map.

In step S130, in the case where there is dynamic obstacle position data in each of the obstacle position data, the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data is predicted, and the predicted motion of the dynamic obstacle is obtained. data.

The obstacles scanned by the lidar can include dynamic obstacles and static obstacles. When there is dynamic obstacle position data in the obstacle position data, the processor can process the radar data obtained by the lidar, and then analyze the dynamic obstacles. The next motion state is predicted. For example, the lidar obtains the position information of the position of the dynamic obstacle A every 0.5 seconds for 5 consecutive seconds, then the processor can calculate the speed and direction of its movement according to the position information of the dynamic obstacle A, Further, the next movement speed and movement direction of the dynamic obstacle A are predicted, and the predicted movement data of the dynamic obstacle A is obtained.

Optionally, the UAV further includes a visible light camera, and the method further includes:

Acquire a plurality of continuous image data of the target area captured by the visible light camera within the preset time period, where the target area is the area where the obstacle corresponding to the dynamic obstacle position data is located;

Predict the motion state of the dynamic obstacle according to a plurality of continuous image data, and obtain auxiliary motion data of the dynamic obstacle;

Based on the auxiliary motion data, the predicted motion data is optimized to obtain optimized predicted motion data.

In order to make the UAV's prediction of dynamic obstacle motion more accurate, a visible light camera can be mounted on the UAV. A visible light camera can be a camera that can be used in conjunction with a lidar to lock the target and shoot 360 degrees.

The target area can be the area where the dynamic obstacle scanned by the lidar is located. When the processor determines the dynamic obstacle through the obstacle position data obtained by the lidar, the visible light camera can determine the target area according to the dynamic obstacle position data, and the visible light camera can determine the target area. Continuous image data in the target area can be captured within a preset time period. By processing the continuous images, the motion state of the dynamic obstacle can also be predicted, and the auxiliary motion data of the dynamic obstacle can be obtained. For example, the image data captured by the visible light camera is the image of the target area. By processing the image data, a spatial coordinate system can be established in the image, and the position of the dynamic obstacle in the image can be determined by the spatial coordinate system. Further, from the position of the dynamic obstacle in the image in the multiple continuous image data, the speed and direction of the dynamic obstacle in the preset time period are calculated, so as to predict the motion state of the dynamic obstacle and obtain the dynamic obstacle. Assisted motion data for obstacles.

After the auxiliary motion data is obtained, the predicted motion data can be optimized through the auxiliary motion data to obtain optimized predicted motion data, thereby improving the accuracy of the predicted motion data.

Kalman filter is a kind of filter that uses recursion to realize target orientation estimation. It can estimate and predict the position information of the target system at the next moment from a series of noise-containing measurements, predict the trajectory of the target, and use certainty comparisons. The high tracking result is used to correct the prediction result, that is, the estimated value of the current state can be calculated only by obtaining the estimated value of the state at the previous moment and the observed value of the current state, so there is no need to record the historical information of the observation or the estimate. Therefore, as an optional embodiment, Kalman filtering can be used to filter the image captured by the visible light camera, so as to predict the motion state of the dynamic obstacle.

向前一个状态向量

的映射。基本结构状态的估计值。前一个状态向量

用

表示为：Let a nonlinear function f be used to describe the current state vector

previous state vector

mapping. An estimate of the basic structural state. previous state vector

use

Expressed as:

为k时刻的观测向量，那么k-1时刻的观测向量

表征为一个非线性函数：

is the observation vector at time k, then the observation vector at time k-1

Characterized as a nonlinear function:

是一个根据f向x求偏导的雅可比矩阵，

是根据h向w求偏导的雅可比矩阵，

是根据f向v求偏导的雅可比矩阵，

是根据f向w求偏导的雅各布矩阵。这里

是从具有协方差

的零均值多元正态分布中得出的，也同时是还具有协方差

的零均值高斯白噪声。Adjoint Conditions for Characterizing Kalman Filters

is a Jacobian matrix that takes the partial derivative of f to x,

is the Jacobian matrix of partial derivatives from h to w,

is the Jacobian matrix of partial derivatives from f to v,

is the Jacobian matrix that takes the partial derivative from f to w. here

is from having covariance

from a multivariate normal distribution with zero mean, which also has covariance

zero mean Gaussian white noise.

The Kalman filtering process can be conceptualized as two stages: "prediction" and "correction". The following are the Kalman filter calculation steps:

Computational State Evaluation Propagation

是非线性状态转移函数，x_k-1代表无人机的位置和方向，u_k-1代表无人机的简单移动，0代表噪声干扰。in

is the nonlinear state transfer function, x _k-1 represents the position and orientation of the drone, u _k-1 represents the simple movement of the drone, and 0 represents noise interference.

Get Error Covariance Propagation

Calculation of Kalman Gain Matrix

是用来校正状态

及其协方差

更新的无人机状态向量

见以下方程：Update the state estimate and error covariance to evaluate the updated UAV environment position. The Kalman filter gain here

is used to correct the state

and its covariance

Updated drone state vector

See the following equations:

和

表示具有零均值和协方差矩阵的新独立随机变量。这种滤波可得到无人机路径跟踪区域中障碍物的准确位置。in

and

represents a new independent random variable with zero mean and covariance matrix. This filtering can obtain the accurate location of obstacles in the area of the UAV's path tracking.

Optionally, in the case that there are more than two dynamic obstacles corresponding to the dynamic obstacle position data, the method further includes:

respectively obtaining the optimized predicted motion data corresponding to each of the dynamic obstacles;

Combine a plurality of the optimized predicted motion data to obtain coordinated motion data.

When there are two or more dynamic obstacles, the optimized predicted motion data corresponding to each dynamic obstacle can be obtained separately, and then the optimized predicted motion data corresponding to each dynamic obstacle can be combined. Obtain coordinated motion data for all dynamic obstacles.

Optionally, the method further includes:

Based on the Lyapunov function, the error of the cooperative motion data is eliminated.

The Lyapunov function is used to determine the reliability of the framework when balancing. The characteristics of the error dynamic model are:

where _θdi represents the path angle with respect to the ideal point, and the differentiation of the above formula can be described by the path boundary. The goal of the cooperative path tracking process is to eliminate the error dynamic model feature _ek = [ _pek , _qek , _θek ] of each UAV to [0 00]. The ultimate goal is that the drones take advantage of their situation to minimize the following error to a pre-defined path and each other's position to maintain cooperative movement.

表示开发焦点的假设无人机的速度。From the above formula, it can be seen that the input of each UAV contains the ground speed V _gk , the heading angle rate ω _k and the assumed speed of other UAVs. At this time, when a group of UAVs are traveling along the route, the UAV we are tracking is regarded as a target point, and the target point is looking for an ideal route, P _d(sd) =(p _d(sd) , q _d(sd) ), where s _d represents the curve length boundary,

The speed of the hypothetical drone representing the development focus.

是预测目标点的跟踪误差。现在，

可由下式得到：Let p _e0 =p _d -p ₀ , q _e0 =q _d -q ₀ , the error

is the tracking error of the predicted target point. Now,

It can be obtained by the following formula:

表示基本速度

是连续的，Ke是控制参数。可知，当误差

较小时，无人机速度向最大方向协调，当误差

较大时，无人机速度向最小方向协调。in,

Indicates base speed

is continuous, and Ke is the control parameter. It can be seen that when the error

When it is smaller, the speed of the UAV is coordinated to the maximum direction, when the error

When it is larger, the speed of the drone is coordinated to the minimum direction.

Step S150: Based on the locust algorithm, according to the predicted motion data, the environmental wind parameters and the attitude data, optimize the initial flight path of the UAV.

The locust algorithm is derived from the characteristics of locust activity. Finding food sources is an important behavior of locust swarms. The main bionic principle is to map the small-scale movement of larvae to local development with short steps, and the large-scale movement of adults to long-step. Global exploration is carried out in a way similar to "step-tank coordination". The behavior cycle can be divided into two phases: exploration and development. The numerical model of this behavior is as follows:

where Xi represents the position of locust _i , Si _represents social influence, G represents gravitational influence, and A is wind advection influence.

In the above formula, s(r)=fe- ^r /le- ^r represents the social influence coefficient, where f and l are the attraction strength parameter and the attraction scale parameter, respectively. N represents the population size. d _ij =|X _j -X _i |, represents the distance between individual i and individual j.

其中g表示引力，

表示指向地心的单位向量。Gravity effect on locusts

where g is the gravitational force,

Represents a unit vector pointing to the center of the Earth.

u表示恒定漂移因子(意为即使没有风也会发生的飞行运动偏移)，e_w表示指向风向的单位向量。wind advection

u is the constant drift factor (meaning the flight motion excursion that occurs even in the absence of wind), and e _w is the unit vector pointing in the wind direction.

After many iterations, the convergence was found to be poor, so the numerical model was optimized as:

是当前最优个体在当前维度的位置，并引入了缩小舒适区的递减系数c，其公式为：where ub and lb are the upper and lower limits of the current dimension, respectively,

is the position of the current optimal individual in the current dimension, and introduces a decreasing coefficient c that reduces the comfort zone. Its formula is:

Where cmax represents the extreme value (close to 1), cmin represents the minimum value, I represents the current iteration, and MaxI represents the maximum number of cycles. By introducing this decreasing coefficient c, locusts can better control their "closeness circle" with others, thereby avoiding excessive aggregation and reducing the probability of the algorithm falling into a local optimum.

Lay5 layer 5: It includes a single node, which is set to S', to perform a basic adder, the equivalent result is expressed as:

The output of the algorithm is the collision avoidance and avoidance motion of the UAV, so as to achieve the effect of optimizing the flight path of the UAV.

Based on the same inventive concept, as shown in FIG. 5 , an embodiment of the present invention provides a path optimization device 300, which is applied to an unmanned aerial vehicle. The unmanned aerial vehicle includes a laser radar, and the path optimization device 300 includes:

An obstacle location data acquisition unit 301, configured to acquire a plurality of continuous obstacle location data scanned by the lidar within a preset time period;

The prediction unit 302 is configured to predict the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data when there is dynamic obstacle position data in each of the obstacle position data, and obtain the motion state of the dynamic obstacle. Predict motion data;

An environmental parameter acquisition unit 303, configured to acquire environmental wind parameters and attitude data of the UAV, where the environmental wind parameters include wind force and wind direction of the environment where the UAV is located;

The path optimization unit 304, based on the locust algorithm, optimizes the initial flight path of the UAV according to the predicted motion data, the environmental wind parameters and the attitude data.

Regarding the above path optimization apparatus 300, the specific functions of each unit have been described in detail in the embodiments of the path optimization method provided in this specification, and will not be described in detail here.

Based on the same inventive concept, the embodiments of the present specification provide an unmanned aerial vehicle, including a radar, a wind sensor, a gyroscope, and a controller, and the controller is respectively connected to the radar, the wind sensor, and the gyroscope in communication; The controller feeds back the position data of the obstacle; the wind sensor is used to obtain and send the environmental wind parameters to the controller; the gyroscope is used to obtain and send the attitude data of the UAV to the controller; the controller is used to execute the preceding path The steps of any one of the optimization methods.

Based on the same inventive concept, the embodiments of the present specification provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the steps of any of the foregoing path optimization methods.

By adopting the above-mentioned solution in the embodiment of the present invention, at least part of the following effects can be achieved:

1. When the UAV encounters a dynamic obstacle, the initial flight path of the UAV can be optimized by predicting the motion state of the dynamic obstacle, so that the UAV can effectively avoid the dynamic obstacle and prevent the unmanned aerial vehicle from flying. The man-machine crashed into a dynamic obstacle and the UAV was damaged.

2. Set the visible light camera to obtain auxiliary motion data, which makes the prediction of the motion state of dynamic obstacles more accurate.

3. Obtain cooperative motion data, and based on the Lyapunov function, eliminate the error of cooperative motion data and improve the UAV's ability to avoid obstacles to multiple dynamic obstacles.

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes .

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical scope disclosed by the present invention can easily think of changes or substitutions. All should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (10)

1. A path optimization method, applied to a drone including a lidar, the method comprising:

acquiring a plurality of continuous obstacle position data scanned by the laser radar in a preset time period;

predicting the motion state of a dynamic obstacle corresponding to the dynamic obstacle position data under the condition that the dynamic obstacle position data exists in each obstacle position data to obtain predicted motion data of the dynamic obstacle;

acquiring environmental wind parameters and attitude data of the unmanned aerial vehicle, wherein the environmental wind parameters comprise wind power and wind direction of the environment where the unmanned aerial vehicle is located;

and optimizing the initial flight path of the unmanned aerial vehicle according to the predicted motion data, the environmental wind parameters and the attitude data based on the locust algorithm.

2. The path optimization method of claim 1, wherein the drone further includes a visible light camera, the method further comprising:

acquiring a plurality of continuous image data of a target area shot by the visible light camera in the preset time period, wherein the target area is an area where an obstacle corresponding to the dynamic obstacle position data is located;

predicting the motion state of the dynamic obstacle according to a plurality of continuous image data to obtain auxiliary motion data of the dynamic obstacle;

optimizing the predicted movement data based on the auxiliary movement data to obtain optimized predicted movement data;

the optimizing the initial flight path of the unmanned aerial vehicle comprises: and optimizing the initial flight path of the unmanned aerial vehicle according to the optimized predicted motion data, the environment wind parameter and the attitude data based on the locust algorithm.

3. The method for optimizing a route according to claim 2, wherein when the number of the dynamic obstacles corresponding to the dynamic obstacle position data is two or more, the method further comprises:

respectively acquiring optimized predicted movement data corresponding to each dynamic obstacle;

merging a plurality of optimized predicted motion data to obtain cooperative motion data;

the optimizing the initial flight path of the unmanned aerial vehicle comprises: and optimizing the initial flight path of the unmanned aerial vehicle according to the cooperative motion data, the environmental wind parameter and the attitude data based on the locust algorithm.

4. The path optimization method of claim 3, wherein prior to said optimizing the initial flight path of the drone, the method further comprises:

and eliminating the error of the cooperative motion data based on the Lyapunov function.

5. The path optimization method of claim 1, further comprising the step of obtaining the initial flight path, the step comprising:

acquiring an unmanned aerial vehicle map, wherein the unmanned aerial vehicle map comprises a target point location, a starting point location and a static barrier point location marked by a user;

and generating the initial flight path according to the starting point position, the target point position and the static obstacle point position.

6. The path optimization method of claim 5, wherein the method further comprises:

judging whether the position data corresponding to the static obstacle point position exists in the obstacle position data or not;

and if so, screening the obstacle position data except the position data corresponding to the static obstacle point position as the dynamic obstacle position data.

7. A path optimisation device, characterized in that, is applied to a drone, the drone includes a lidar, the device includes:

the obstacle position data acquisition unit is used for acquiring a plurality of continuous obstacle position data scanned by the laser radar in a preset time period;

the prediction unit is used for predicting the motion state of the dynamic obstacle corresponding to the dynamic obstacle position data under the condition that the dynamic obstacle position data exists in each obstacle position data to obtain the predicted motion data of the dynamic obstacle;

the environment parameter acquiring unit is used for acquiring environment wind parameters and attitude data of the unmanned aerial vehicle, wherein the environment wind parameters comprise wind power and wind direction of the environment where the unmanned aerial vehicle is located;

and the path optimization unit is used for optimizing the initial flight path of the unmanned aerial vehicle according to the predicted motion data, the environmental wind parameters and the attitude data based on the locust algorithm.

8. An unmanned aerial vehicle is characterized by comprising a radar, a wind sensor, a gyroscope and a controller, wherein the controller is respectively in communication connection with the radar, the wind sensor and the gyroscope;

the radar is used for acquiring and feeding back position data of the obstacle to the controller;

the wind power sensor is used for acquiring and sending environmental wind parameters to the controller;

the gyroscope is used for acquiring and sending attitude data of the unmanned aerial vehicle to the controller;

the controller is used for executing the path optimization method of any claim 1-6.

9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the path optimization method according to any one of claims 1 to 6 when executing the program.

10. A storage medium comprising a computer program, wherein the computer program controls an electronic device in which the storage medium is located to execute the path optimization method according to any one of claims 1 to 6 when the computer program runs.

Images