Unmanned aerial vehicle autonomous homing and obstacle avoidance method, system and device and medium

Abstract

The invention provides an unmanned aerial vehicle autonomous homing and obstacle avoidance method, system and device and a medium, and the method comprises the following steps: 1, an unmanned aerial vehicle reads elevation data according to the longitudes and latitudes of a target point and a starting point, and converts the elevation data into three-dimensional coordinates; 2, performing global path exploration by taking elevation data represented by three-dimensional coordinates and unmanned aerial vehicle dynamics constraints as restrictions, and generating a reachable route composed of a plurality of waypoints; step 3, smoothing the reachable route to enable the reachable route to become a better homing route; and 4, homing the unmanned aerial vehicle through the homing route, and avoiding obstacles in the homing process through a laser radar and a DWA algorithm. The method is realized based on an elevation map, and relates to an embedded system, laser radar environment perception and an obstacle avoidance algorithm, so that the unmanned aerial vehicle can safely and quickly realize autonomous homing in an unknown environment.

Description

Technical Field

[0001] The present invention relates to the technical field of UAV navigation and flight control, and particularly to a method, system, device and medium for autonomous return and obstacle avoidance of UAVs.

Background Art

[0002] In recent years, UAV technology has been continuously developed, and UAVs have gradually entered various fields of daily life such as household, commercial, medical, fire fighting, and security. According to analysis, most UAVs have the following problems in navigation and flight control:

[0003] ① UAVs can only complete tasks according to pre-set commands and lack the ability to flexibly solve emergencies;

[0004] ② The communication link is easily interfered by the outside world, resulting in the UAV losing contact and returning. The return route is generally pre-set and is not safe and intelligent enough;

[0005] ③ Since there is no prior information in an unknown environment, UAVs face many challenges in navigating in an unknown environment;

[0006] ④ To ensure the safety of UAVs to the greatest extent, rapid obstacle avoidance should be realized based on environmental perception; in view of these deficiencies of current UAVs, it is an inevitable trend to develop a UAV with functions of unknown environment perception, autonomous return, and autonomous obstacle avoidance.

[0007] Therefore, it is necessary to study a method, system, device and medium for autonomous return and obstacle avoidance of UAVs to address the deficiencies of the prior art and solve or mitigate one or more of the above problems.

Summary of the Invention

[0008] In view of this, the present invention provides a method, system, device and medium for autonomous return and obstacle avoidance of UAVs, which is implemented based on an elevation map and involves an embedded system, lidar environmental perception and obstacle avoidance algorithms, and can enable the UAV to safely and quickly achieve autonomous return in an unknown environment.

[0009] On the one hand, the present invention provides a method for autonomous return and obstacle avoidance of UAVs, and the method for autonomous return and obstacle avoidance of UAVs includes the following steps:

[0010] Step 1: The UAV reads elevation data according to the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates;

[0011] Step 2: With the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, global path exploration is carried out to generate a reachable route composed of multiple waypoints;

[0012] Step 3: Smooth the reachable route to make it a better return route;

[0013] Step 4: The UAV returns along the return route and avoids obstacles during the return flight through lidar and the DWA algorithm.

[0014] In the aspect and any possible implementation described above, a further implementation is provided. In step 3, the smoothing process is performed based on a preset RRT algorithm.

[0015] In the aspect and any possible implementation described above, a further implementation is provided. During the process of generating the reachable route composed of multiple waypoints in step 2, the climbing height and the detour distance are also limited.

[0016] In the aspect and any possible implementation described above, a further implementation is provided. Specifically, step 4 is as follows: During the return flight of the UAV, local obstacle avoidance is achieved through the DWA algorithm. The lidar is used for mapping, and the point cloud data is converted into a grid map. The UAV uses the waypoints planned globally as target points in sequence for obstacle avoidance.

[0017] In the aspect and any possible implementation described above, a further implementation is provided. The elevation data in step 1 includes the three-dimensional space environment data where the UAV is located, the terrain data where the obstacles are higher than the predetermined flight route height of the UAV, the starting point data, and the target position data.

[0018] In the aspect and any possible implementation described above, a further implementation is provided. The dynamic constraints of the UAV in step 2 include linear velocity, angular velocity, linear acceleration, and angular acceleration.

[0019] In the aspect and any possible implementation described above, a further implementation is provided. All information about the obstacles is included in the grid of the grid map in step 4.

[0020] In the aspect and any possible implementation described above, a further implementation of a UAV autonomous return and obstacle avoidance system is provided. The UAV autonomous return and obstacle avoidance system includes:

[0021] A coordinate acquisition module. The UAV reads elevation data based on the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates.

[0022] A reachable route generation module. With the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, a global path exploration is performed to generate a reachable route composed of multiple waypoints.

[0023] A return route acquisition module. The reachable route is smoothed to become a better return route.

[0024] Return flight obstacle avoidance module, which conducts the return flight of the UAV through the return flight route and avoids obstacles during the return flight through lidar and DWA algorithm.

[0025] In the aspects and any possible implementation manners described above, an electronic device is further provided, including a memory and a processor;

[0026] The memory is used for storing a computer program;

[0027] The processor is used for executing the computer program, and when the computer program is executed by the processor, the steps of the method for autonomous return flight and obstacle avoidance of the UAV are implemented.

[0028] In the aspects and any possible implementation manners described above, a computer-readable storage medium is further provided. The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for autonomous return flight and obstacle avoidance of the UAV are implemented.

[0029] Compared with the prior art, the present invention can obtain the following technical effects:

[0030] When a traditional UAV loses contact, the UAV automatically flies in turn in the reverse order of the original waypoint queue. Although this method is safe, if the UAV has executed most of the reconnaissance tasks before losing contact, the return flight at this time is a great test for the UAV's battery life and its own safety. The present invention finds the optimal return flight path through the global path search algorithm based on the elevation map to achieve autonomous return flight; and realizes autonomous obstacle avoidance through the environmental perception technology and the local path planning algorithm, solves the elevation map error problem, and optimally guarantees the safety of the UAV.

[0031] Of course, it is not necessary for any product implementing the present invention to achieve all the technical effects described above at the same time.

BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a three-dimensional path planning flowchart for autonomous return flight of a UAV provided by an embodiment of the present invention;

[0034] Figure 2 It is a real-time autonomous obstacle avoidance flowchart of a UAV provided by an embodiment of the present invention.

DETAILED DESCRIPTION

[0035] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0036] It should be clear that the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0037] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0038] The present invention provides a method for autonomous return and obstacle avoidance of an unmanned aerial vehicle (UAV). The method for autonomous return and obstacle avoidance of the UAV includes the following steps:

[0039] Step 1: The UAV reads elevation data according to the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates.

[0040] Step 2: With the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, global path exploration is carried out to generate an accessible flight path composed of multiple waypoints.

[0041] Step 3: Smooth the accessible flight path to make it a better return flight path.

[0042] Step 4: The UAV returns along the return flight path and avoids obstacles during the return flight through a lidar and the DWA algorithm.

[0043] The smoothing process in Step 3 is carried out based on a preset RRT algorithm.

[0044] During the process of generating the accessible flight path composed of multiple waypoints in Step 2, the climbing height and the detour distance are also limited.

[0045] Step 4 is specifically as follows: During the return flight of the UAV, local obstacle avoidance is realized through the DWA algorithm. The lidar is used for mapping, and the point cloud data is converted into a grid map. The UAV takes the waypoints planned globally as target points in turn for obstacle avoidance.

[0046] The elevation data in Step 1 includes the three-dimensional space environment data where the UAV is located, the terrain data where the obstacles are higher than the predetermined flight path height of the UAV, the starting point data, and the target position data.

[0047] The dynamic constraints of the UAV in Step 2 include linear velocity, angular velocity, linear acceleration, and angular acceleration.

[0048] In step 4, all information of obstacles is included in the grid of the grid map.

[0049] The present invention also provides an unmanned aerial vehicle (UAV) autonomous return and obstacle avoidance system, which includes:

[0050] A coordinate acquisition module, where the UAV reads elevation data according to the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates;

[0051] An accessible route generation module, which performs global path exploration with the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, and generates an accessible route composed of multiple waypoints;

[0052] A return route acquisition module, which smooths the accessible route to make it a better return route;

[0053] A return obstacle avoidance module, which performs UAV return through the return route and avoids obstacles during the return journey through lidar and the DWA algorithm.

[0054] The present invention also provides an electronic device, including a memory and a processor;

[0055] The memory is used to store a computer program;

[0056] The processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the described UAV autonomous return and obstacle avoidance method are implemented.

[0057] The present invention also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the described UAV autonomous return and obstacle avoidance method are implemented.

[0058] Embodiment 1:

[0059] The present invention provides a UAV autonomous return and obstacle avoidance method, including the following technical solutions:

[0060] Step 1: The UAV first reads elevation data according to the longitude and latitude of the target point and the starting point, and converts it into three-dimensional coordinates;

[0061] Step 2: Based on the RRT algorithm, with the elevation data and the dynamic constraints of the UAV as limitations, global path exploration is realized, weighing the advantages and disadvantages of climbing height and detouring, and an accessible route composed of multiple waypoints is generated;

[0062] Step 3: The generated accessible route is smoothed through an algorithm to make it a better return route;

[0063] Step 4: Considering the uncertainty of elevation data, to enable the UAV to return safely, local obstacle avoidance is achieved through the DWA algorithm during the UAV's return flight. This part mainly uses lidar to build a map, converts the point cloud data into a raster map, and the UAV will use the waypoints planned globally as target points for obstacle avoidance, ensuring the safe return of the UAV in complex terrain to the greatest extent and solving the problem of elevation map error. Since a reachable flight path has been generated previously, the drawback of local deadlock in the DWA algorithm is avoided.

[0064] As Figure 1 shown, it is the flowchart of the UAV's three-dimensional path planning, which mainly includes environment modeling, searching for reachable paths, and path optimization, as follows:

[0065] Step 1: Model the three-dimensional space environment where the UAV is located by reading elevation map data, including obstacles (terrain higher than the planned flight route of the aircraft), the starting point (the current position of the aircraft), and the target position, etc.

[0066] Step 2: Initialize the RRT with the starting point as the root node of the RRT tree.

[0067] Step 3: Randomly sample a point as the target point in the three-dimensional space according to the planned step size. To avoid overly random sampling points, increase the sampling probability near the starting point and the target position to speed up the search.

[0068] Step 4: Search for the node closest to the target position in the RRT tree as the current node.

[0069] Step 5: Generate a new node based on the current node and the target position obtained by random sampling, and detect whether there is a collision situation in the middle of the line connecting the newly generated node and the starting point. If there is a collision, discard the node; otherwise, add it to the RRT tree.

[0070] Step 6: Connect the new node to the current node to form a path, and generate a smooth path through techniques such as interpolation, fusion, and smoothing.

[0071] Step 7: Determine whether the new node is close to the target position. If the distance to the final target position is less than 20m, it is considered to have reached the target point, and the final path is generated.

[0072] Step 8: Iteratively search, repeat steps 3 to 8 until the final path is generated or the maximum number of iterations is reached.

[0073] Step 9: If the maximum number of iterations is reached, it is determined that the UAV cannot reach the target point at this flight altitude. Increase the maximum flight route altitude limit of the UAV according to the UAV dynamics constraints, and repeat Step 8. Optimize the generated path, including smoothing and local adjustment, etc., to improve the quality and feasibility of the path, and finally generate an optimal global return flight route.

[0074] As Figure 2 shown, it is the real-time autonomous obstacle avoidance flowchart of the UAV. The autonomous obstacle avoidance program runs on the UAV mission host in real time. Based on the global return flight route, it solves the problem of inaccurate elevation map. This algorithm mainly includes lidar SLAM environment perception, speed sampling, trajectory prediction and trajectory evaluation, etc.

[0075] Step 1: Use lidar SLAM mapping to construct a global map and obtain the starting position and target position of the UAV. At the same time, convert the point cloud data into raster map data through Octomap, where the raster contains all the information of the obstacles;

[0076] Step 2: Speed sampling: According to the dynamics constraints of the UAV, there are boundary limitations for the speed of the UAV. At this time, the speed space V m is shown in formula (1):

[0077] V m ={(v, ω)|v ∈ [v min , v max , ω ∈ [ω min , ω max} (1)

[0078] In the formula, v min , v max are the minimum linear velocity and maximum linear velocity of the UAV respectively, and ω min , ω max are the minimum angular velocity and maximum angular velocity of the UAV dynamics constraints respectively.

[0079] Since both the linear acceleration and angular acceleration of the UAV have boundary limitations. Considering the speed space V d sampled at the acceleration moment is shown in formula (2):

[0080]

[0081] In the formula, v c , ω c are the linear velocity and angular velocity of the UAV at the current moment respectively, and a vmax , a wmax are the maximum linear acceleration and angular acceleration of the UAV dynamics constraints respectively.

[0082] The local planning also needs to have a dynamic real-time obstacle avoidance function. The constraint condition V for the UAV not to collide with surrounding obstacles at a certain moment a is shown in Formula (3):

[0083]

[0084] In the formula, dist(v, w) represents the closest distance from the current position to the obstacle.

[0085] The final UAV speed sampling space V s is the intersection of three speed spaces, that is, as shown in Formula (4):

[0086] V s = V m ∩V d ∩V a (4)

[0087] Step 3: After determining the speed sampling space V s the DWA algorithm uniformly samples in this space at a certain sampling interval (resolution) to obtain multiple trajectories.

[0088] Step 4: After determining the UAV constraint speed range, some trajectories simulated by speeds are feasible, but there are still unqualified trajectories. Therefore, it is necessary to evaluate and select the best from the multiple groups of trajectories obtained by sampling. The best trajectory is selected by comparing the scores of each trajectory, and then the speed corresponding to the best trajectory is selected as the driving speed, and the control information such as speed and heading angle is sent to the UAV through ROS2 to achieve obstacle avoidance. The evaluation function for evaluating each trajectory is shown in Formula (5):

[0089] G(v, w) = σ(α·heading(v, w)) + σ(β·dist(v, w)) + σ(γ·

[0090] velocity(v, w))(5)

[0091] where heading(v, w) is the azimuth evaluation function, dist(v, w) is the distance evaluation function, and velocity(v, w) is the speed evaluation function. α, β, and γ are the coefficients of the evaluation function, and σ represents normalization.

[0092] The technical problem to be solved by the present invention is to enable the UAV to safely and quickly achieve autonomous homing in an unknown environment. When the UAV encounters protruding peaks or other harsh natural environments during the execution of a mission, and the UAV loses communication with the ground base station, the present invention can decisively determine that the UAV is out of contact and automatically make a decision to return. It has complete autonomous decision-making power and can flexibly respond to emergencies. The present invention finds the optimal homing path through a global path search algorithm based on an elevation map to achieve autonomous homing; it achieves autonomous obstacle avoidance through environmental perception technology and a local path planning algorithm, solves the problem of elevation map errors, and ensures the optimal safety of the UAV.

[0093] The above is a detailed introduction to the autonomous homing and obstacle avoidance method, system, device and medium for unmanned aerial vehicles provided in the embodiments of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0094] For example, certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that hardware manufacturers may use different nouns to refer to the same component. This specification and claims do not use differences in names as a way to distinguish components, but use differences in the functions of components as the criteria for distinction. As mentioned throughout the specification and claims, "including" and "comprising" are open-ended terms, so they should be interpreted as "including / including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve the technical problem within a certain error range and basically achieve the technical effect. The subsequent description of the specification is a preferred embodiment of the present application, but the description is for the purpose of illustrating the general principles of the present application, and is not used to limit the scope of the present application. The scope of protection of the present application shall be determined by the definition of the attached claims.

[0095] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a product or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such a product or system. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the product or system including the elements.

[0096] It should be understood that the term "and / or" used herein is merely a description of the associated relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. Additionally, the character " / " in this text generally indicates that the associated objects before and after are in an "or" relationship.

[0097] The above description shows and describes several preferred embodiments of the present application. However, as mentioned before, it should be understood that the present application is not limited to the form disclosed herein, should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications, and environments, and can be changed within the scope of the application concept described herein through the above teachings or the techniques or knowledge in the relevant field. And any changes and alterations made by those skilled in the art that do not depart from the spirit and scope of the present application shall fall within the protection scope of the appended claims of the present application.

Claims

1. A method for autonomous return and obstacle avoidance of an unmanned aerial vehicle, characterized in that The method for autonomous return and obstacle avoidance of the unmanned aerial vehicle (UAV) includes the following steps: Step 1: The UAV reads elevation data based on the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates; Step 2: With the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, global path exploration is carried out to generate an accessible route composed of multiple waypoints; Step 3: Smooth the accessible route to make it a better return route; Step 4: The UAV returns along the return route and avoids obstacles during the return journey through lidar and the DWA algorithm.

2. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 1, characterized in that, In the said Step 3, the smoothing process is carried out by means of a preset RRT algorithm and based on the RRT algorithm.

3. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 1, wherein In the process of generating the accessible route composed of multiple waypoints in the said Step 2, it also includes the limitation of the climbing height and the detour distance.

4. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 1, characterized in that The said Step 4 is specifically as follows: During the return journey of the UAV, local obstacle avoidance is realized through the DWA algorithm. The lidar is used for mapping, and the point cloud data is converted into a grid map. The UAV takes the waypoints planned globally as target points in turn for obstacle avoidance.

5. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 1, wherein In the said Step 1, the elevation data includes the three-dimensional space environment data where the UAV is located, the terrain data where the obstacle is higher than the predetermined flight route height of the UAV, the starting point data, and the target position data.

6. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 5, characterized in that, In the said Step 2, the dynamic constraints of the UAV include linear velocity, angular velocity, linear acceleration, and angular acceleration.

7. The method for autonomous return and obstacle avoidance of an unmanned aerial vehicle according to claim 4, wherein In the said Step 4, all the information of the obstacles is included in the grid of the grid map.

8. An autonomous return and obstacle avoidance system for an unmanned aerial vehicle, characterized in that, The UAV autonomous return and obstacle avoidance system includes: A coordinate acquisition module, where the UAV reads elevation data based on the longitude and latitude of the target point and the starting point, and converts the elevation data into three-dimensional coordinates; An accessible route generation module, which carries out global path exploration with the elevation data represented by three-dimensional coordinates and the dynamic constraints of the UAV as limitations, and generates an accessible route composed of multiple waypoints; A return route acquisition module, which smooths the accessible route to make it a better return route; A return obstacle avoidance module, which returns the UAV along the return route and avoids obstacles during the return journey through lidar and the DWA algorithm.

9. An electronic device, characterized in that, It includes a memory and a processor; The memory is used for storing computer programs; The processor is used for executing the said computer program. When the computer program is executed by the processor, it realizes the steps of a method for autonomous return and obstacle avoidance of a UAV as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored in the storage medium. When the computer program is executed by the processor, it realizes the steps of a method for autonomous return and obstacle avoidance of a UAV as described in any one of claims 1 to 7.

Images