WO2021237448A1

WO2021237448A1 - Path planning method, apparatus, and system

Info

Publication number: WO2021237448A1
Application number: PCT/CN2020/092311
Authority: WO
Inventors: 邹亭; 赵力尧
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2020-05-26
Filing date: 2020-05-26
Publication date: 2021-12-02
Also published as: CN113994171A

Abstract

A path planning method, apparatus, and system. The method comprises: generating a reference path according to reference information input by a user (S202), next, determining target operation objects in operation objects according to the relative positional relationship between each operation object in an operation area and the reference path (S204), then, sorting the target operation objects to generate a target path on the basis of the sorted target operation objects (S206), and executing an operation task according to the target path. The target path is generated by means of the reference information input by the user, and the user can customize an operation path according to needs in an actual operation scenario, so that the adjustment of the operation path is more flexible, and user needs in different scenarios can be met.

Description

Path planning method, device and system

Technical field

This application relates to the field of navigation technology, and specifically to a method, device and system for path planning.

Background technique

At present, in many fields, mobile platforms can be used instead of humans to complete some tasks. For example, drones can be used to take photos and inspections of electrical wiring equipment, drones can be used to spray crops, or unmanned vehicles can be used to perform operations on trees. Watering etc. Before using these movable platforms to perform work tasks, it is necessary to plan the work path of the movable platform in advance so that the movable platform can perform the work tasks according to the path. When determining the work path of the movable platform in the related technology, the user cannot independently define the work path, the flexibility is poor, and the user's needs in different work scenarios cannot be met.

Summary of the invention

In view of this, this application provides a path planning method, device and system.

According to the first aspect of the present application, a path planning method is provided, the method including:

Generate a reference path based on the reference information input by the user;

Determine the target work object in the work object according to the relative positional relationship between each work object in the work area and the reference path;

Sorting processing is performed on the target work objects to generate a target path based on the sorted target work objects.

According to a second aspect of the present application, there is provided a path planning device, wherein the device includes a processor, a memory, and a computer program executable by the processor stored on the memory, and the processor executes all When describing the computer program, the following steps are implemented:

Generate a reference path based on the reference information input by the user;

According to the third aspect of the present application, a path planning system is provided, which is characterized in that it includes a movable platform and a control terminal,

The control terminal is configured to generate a reference path according to the reference information input by the user, determine a target work object in the work object according to the relative positional relationship between each work object in the work area and the reference path, and perform processing on the target work object. Sorting processing to generate a target path based on the sorted target job objects, and send the target path to the movable platform;

The movable platform is used to perform work tasks according to the target path.

Using the solution provided in this application, a reference path can be generated based on the reference information input by the user, and then the target work object can be determined from the work objects according to the relative position relationship between each work object in the work area and the reference path, and then the target work objects can be sorted , In order to generate a target path according to the positions of the sorted target work objects, and make the movable platform perform work tasks according to the target path. The target path is generated by the reference information input by the user, and the user can customize the work path according to the needs of the actual work scene. The determination of the work path is more flexible and can meet the needs of the user in different scenarios.

Description of the drawings

In order to explain the technical solutions in the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

Figure 1(a) is a schematic diagram of an embodiment of the present application using a drone to take photos and inspect a bridge.

Fig. 1(b) is a schematic diagram of using drones to spray medicine on fruit trees in an embodiment of the present application.

Fig. 2 is a flowchart of a path planning method according to an embodiment of the present application.

Fig. 3 is a schematic diagram of generating a reference path according to a reference point input by a user on a map according to an embodiment of the present application.

Fig. 4(a) is a schematic diagram of generating a reference path according to a reference point according to an embodiment of the present application.

Fig. 4(b) is a schematic diagram of generating a reference path according to a reference point according to an embodiment of the present application.

Fig. 5 is a schematic diagram of generating a search area according to a search radius and a reference path according to an embodiment of the present application.

FIG. 6 is a schematic diagram of sorting target work objects to generate a target path according to an embodiment of the present application.

Fig. 7 is a schematic diagram of an application scenario of an embodiment of the present application.

FIG. 8 is a schematic diagram of the logical structure of a path planning device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of this application.

At present, many intelligent mobile platforms can be used to replace humans to complete some tasks. For example, drones can be used to take photos of electrical equipment, bridges, etc., to detect whether the equipment or bridges are faulty, or it can be Use drones to spray or irrigate crops, use unmanned vehicles or unmanned robots to water trees, etc., as shown in Figure 1(a), to use drones to target certain locations on the bridge (as shown in Figure 1). Middle A, B, C) Schematic diagram of photographing inspection. As shown in Figure 1(b), it is a schematic diagram of using drones to spray drugs on fruit trees. Before using the movable platform to perform the work task, you can plan the work path first, so that the movable platform can perform the work task according to the work path. Taking the drone spraying of crops with drugs as an example, it is necessary to determine the location of the crops to be sprayed by the drone, as well as the spraying sequence of these crops by the drone, and form the operating path of the drone. In the related art, when determining the work path of the movable platform, the user cannot independently define the work path, the flexibility is low, and the user's requirements for various work scenarios cannot be met.

Based on this, the present application provides a path planning method, which can enable users to independently define the work path of the movable platform. As shown in Figure 2, the path planning method includes the following steps:

S202: Generate a reference path according to the reference information input by the user;

S204: Determine a target operation object in the operation object according to the relative positional relationship between each operation object in the operation area and the reference path;

S206: Perform a sorting process on the target work objects to generate a target path based on the sorted target work objects.

The path planning method of the present application can be used for the operation path planning of various movable platforms when performing various tasks such as crop irrigation, crop medicine spraying, photographing inspections, etc. The movable platform can be a drone, an unmanned vehicle, or a vehicle. Intelligent mobile devices such as human robots. The working objects of this application can be crops and trees to be watered or sprayed with medicines, power equipment to be photographed for inspection or a specific part of a bridge to be photographed for inspection, etc., and this application is not limited. In some embodiments, the work object may be crops, and the movable platform may be a drone, and the drone is used to spray or water the crops with medicine.

Generally, the movable platform can be controlled by a control terminal. The control terminal can control the movement path, movement status, and operation status of the movable platform. The path planning method of this application can be used for the control terminal corresponding to the movable platform. , The control terminal can be various electronic devices that can communicate with the mobile platform, such as a remote control that is compatible with the mobile platform, a user's mobile phone, a tablet, a smart watch, and other terminals. In some embodiments, the control terminal may include a path planning device, and the path planning device may be an application program (APP) installed in the control terminal, and the path planning operation is performed through the APP.

Usually, the mobile platform can survey the task execution area before performing the operation task, and collect the image or geospatial data of the area. The mobile platform or the control terminal can generate a map depicting the overall view of the area based on the collected image or geospatial data. For example, it may be a digital surface model (Digital Surface Model, DSM) map, a two-dimensional map, or a three-dimensional map. The user can select the working area of the movable platform according to the map and determine the working path of the movable platform. In addition, each object in the image can be recognized according to the collected images and machine learning algorithms, and a semantic image of the area can be generated. The semantic image is marked with the categories of various objects in the area, and the area can be identified according to the semantic image. The job object in.

In order to realize the user's independent definition and planning of the work path of the movable platform, this application can independently input the reference information of the work path by the user. For example, the user can determine the expected work path according to the generated map, and input the corresponding work path according to the expected work path. Reference Information. Then the reference path is generated according to the reference information input by the user, and the target job object is determined from the job objects according to the relative positional relationship between the job objects in the job area preselected by the user and the reference path. The target job object is the current job to be performed Job object. Then the target job objects are sorted, so as to generate the target path when the movable platform executes the job task according to the positions of the target job objects after sorting processing. Among them, the target job object can be determined on the side of the control terminal, and the target job objects can be sorted and sent to the movable platform. The movable platform generates the target path according to the sorted target job objects, or the control terminal generates the target path After sending it to the mobile platform, this application is not restricted.

By planning the target path for the movable platform to execute the job task according to the user's independent input of reference information, the planning of the job path can be made more flexible, and the user can independently define the job path according to actual needs to meet the needs of different job scenarios.

The reference information may be information such as a reference point or a reference line input by the user according to the expected work path. In some embodiments, the user may directly input the coordinate information of the reference point or the reference line to generate the reference path. Of course, in some embodiments, if the control terminal includes a human-computer interaction interface, in order to allow the user to more intuitively see the distribution of work objects in the work area, and to facilitate the user to input reference information, before generating the reference path, you can first Provide the user with a human-computer interaction interface. The human-computer interaction interface can contain a map corresponding to the work area. The map can be a two-dimensional map or a three-dimensional map. The user can directly determine a reference point or a reference line on the map to generate Reference path. For example, the user can use the way of dots, according to the expected work path, click on several reference points on the map, and then generate a reference path based on the reference points. Of course, the user can directly draw a reference line on the map according to the expected work path, and then generate the reference path according to the reference line drawn by the user. The reference path can be in various forms such as a straight line, a curved line, or a polyline, and can be flexibly set according to actual needs, which is not limited in this application. As shown in Figure 3, it is a schematic diagram generated by a reference path in an embodiment of this application. The schematic diagram is a scene of determining the operation path when a drone is used to spray drugs on trees. It can be based on the reference point selected by the user on the map ( The white dots in the figure) generate a reference path.

Of course, in some embodiments, when the reference path is generated based on the reference points determined by the user on the map, the reference points selected by the user can be connected in sequence according to the order in which the user clicks to generate the reference path, as shown in Figure 4(a) As shown, each point is the reference point selected by the user, and the number corresponding to each point indicates the order of the user's dots. The reference points can be connected in sequence according to the order of dots to generate a reference path. Of course, in some embodiments, in order to avoid more round trips in the final path, after the user makes a point, the reference points can be connected in order according to the distance of each reference point, so as to obtain the shortest distance and more optimized reference. The path, as shown in Fig. 4(b), each point is the reference point selected by the user, and the number of each point indicates the order in which the user strikes. The reference points can be connected in order according to the distance of the reference points to obtain the reference path. Of course, after the user determines the reference point or reference line on the map, the control terminal can also perform a preliminary assessment of the generated reference path. If the path has more recursive phenomena, or the path has some other defects, it can Set a pop-up window to prompt the user so that the user can update or modify the reference path.

In one embodiment, the work object in the work area can be identified in combination with semantic images, for example, trees to be watered, power equipment to be photographed, etc. can be identified. Then, the target work object is determined according to the relative positional relationship between each work object and the reference path. The target work object can be a work object on or near the reference path, for example, the distance from the reference path is less than a certain threshold, or the reference path Job objects in a certain area around.

In some embodiments, when determining the target operation object according to the relative positional relationship between the operation object in the operation area and the reference path, the search area may be determined in the operation area according to the reference path and the search radius, and then the operation within the search area may be determined. The object is determined as the target job object. Take the scenario of using drones to spray drugs on trees as an example. As shown in Figure 5, the user selects a reference point on the map (the white point 51 in the figure), and then generates a reference path 52 based on the reference point, and according to the search radius R And the reference path 52 can determine a polygonal area 53, which is the search area, and all the trees in the search area are the target objects of the medicine to be sprayed. In some embodiments, after the search area is determined, the determined search area can be displayed on the map of the user interaction interface and the determined target work object can be marked, so that the user can determine whether the search area and the determined target work object are consistent with each other. Expected, whether it is necessary to adjust the reference path, etc.

Among them, the search radius can be preset or determined in real time. For example, in some embodiments, the search radius may be determined based on the size of the work object first, and then the search area may be determined based on the search radius and the reference path. Take the scenario of using no one to spray drugs on trees as an example. Trees are usually distributed in a certain order, as shown in Figure 5. If only a row of trees needs to be sprayed with drugs, you can The width determines the search radius. For example, the search radius can be set to half of the tree width, so that the search area determined based on the reference path and the search radius basically only includes this row of trees. Of course, if two adjacent rows of trees need to be sprayed each time, The search radius can be set according to the tree width and the distance between two rows of trees. The search radius can be flexibly set according to actual needs, and this application is not limited.

After determining the target job object that needs to perform the job task, the target job object can be sorted. The sorting is to determine the order in which the mobile platform performs the job operations on the target job object. The target job object can be determined according to the sorted target job object. The target path of the drone during operation. In some embodiments, the target work objects may be sorted according to the distance between the target work objects and the end points of the reference path. Among them, the end point can be the starting point or the end point of the reference path. For example, the distance between each target work object and the start or end point of the reference path can be determined, and the target work objects can be sorted according to the distance. Among them, for each target operation object, a certain point can be selected from the target operation object to represent the position of the target object. For example, the center of the target operation object or the center of other important parts can represent the target operation object. The characteristics of the job tasks in the scene are determined. Take the scenario where drones spray drugs on trees as an example. Usually drones spray drugs on the center of the tree so that the entire tree can be covered. Therefore, the center of the tree (the center of the tree) can be selected to represent the tree. Of course, if it is a scene where an unmanned car irrigates the tree, the tree is usually irrigated from the side of the tree, so a certain point on the side of the tree can be selected to represent the location of the tree.

In some embodiments, the reference path may include multiple successively connected line segments. When the target work object is sorted, the corresponding target work object may be determined according to the distance between each target work object and each line segment in the reference path. Line segments, and then sort the target job objects according to the sequence of the line segments corresponding to the target job objects.

In some embodiments, each line segment in the reference path may correspond to one or more target work objects. When the target work objects are sorted according to the sequence of the line segments corresponding to the target work objects, the target work objects can be sorted according to the target work object and the reference The distance of each line segment of the path divides the target work object into multiple groups, where each group corresponds to a line segment in the reference path, and the distance between the target work object in each group and the line segment in the reference path corresponding to the group The shortest. Then, the target job objects in each group can be sorted, and the target job objects can be sorted according to the sequence of the line segments of the reference path corresponding to each group and the order of the target job objects in the group.

In some embodiments, when sorting the target work objects in each group, the vertical feet of each target work object in each group on the line segment of the reference path corresponding to the group can be determined first, and then the vertical feet of each target work object in each group can be determined according to each group. The distance between the vertical feet of the target work object and the end point of the reference path sorts the target work objects in the group. Of course, the target work objects can also be sorted according to the distance between each target work object in the group and the end point of the line segment corresponding to the group.

For example, as shown in Figure 6, the circular point in the figure represents the reference point determined by the user, the triangular point represents the position of the tree center, and the dashed line 61 in the figure is the reference path generated from the reference point. The reference path includes successive connections. The line segment ①, line segment ②, line segment ③ of each line segment can correspond to a group. You can first determine the distance between the tree center of the tree AI in the search area and the line segment ①, line segment ②, line segment ③, and then divide the tree AI to the nearest distance For example, the tree AC is divided into the group corresponding to the line segment ①, the tree DF is divided into the group corresponding to the line segment ②, and the tree GI is divided into the group corresponding to the line segment ③. Then sort the tree centers in each group separately to determine the vertical feet from the tree centers of the trees in each group to the line segment corresponding to the group, and then determine the distance between each vertical foot and the end point of the reference path, and then determine the distance between each vertical foot and the end point of the reference path. Sort from near to far to determine the sorting order of the tree cores in each group. Then the tree core AI can be sorted again according to the order of the line segments to get the final sorting result. Finally, the tree core AI can be sorted according to the sorted tree core AI. The position gets the target path, as shown by the solid line 62 in the figure.

Of course, the method for sorting the target task objects is not limited to the methods listed in this application, and any method that can sort the target objects is applicable to this application.

Of course, for some scenarios, the work height needs to be considered when performing work tasks on the target work object. For example, when drones are used to irrigate and spray crops, they must have a certain spraying distance to achieve better results. Therefore, a height can be determined for each tree center position, and a three-dimensional target path with height information can be obtained.

Of course, there may be some obstacles in the operation scene, such as houses, telephone poles, etc. Therefore, when planning the operation path, obstacle avoidance processing is also required for the obstacles. Because different obstacles have different characteristics, when avoiding obstacles, you can determine the appropriate obstacle avoidance strategy according to the type of obstacle. For example, take drones performing operational tasks as an example. Since there may be obstacles such as telephone poles and houses in the operation scene, for larger obstacles such as houses, if the obstacle is bypassed, The UAV may need to travel a relatively long distance, which affects the efficiency of the operation. Therefore, the method of flying over the obstacle can be adopted to avoid the obstacle. For obstacles such as telegraph poles with high height and small volume, if you fly over from above, you will have to fly at a higher altitude, which will also affect the efficiency of the operation. Therefore, you can use the way to bypass the obstacles. Way. Among them, the type of obstacle can be determined according to the semantic map of the pre-generated work area. After the obstacle avoidance strategy is determined, the generated target path can be updated according to the obstacle avoidance strategy to obtain the path after obstacle avoidance processing.

In some embodiments, the generated target path may have more bends, for example, it fluctuates left and right in the horizontal direction, or swings up and down in the vertical direction. This will cause the drone to constantly adjust its direction when performing operations, such as one to the left, one to the right, one to go up, and one to go down, affecting its operational efficiency. Therefore, in some embodiments, the generated target path may be further smoothed, for example, the path may be smoothed in the horizontal direction or the vertical direction. Take the drone spraying drugs on trees as an example. The tree core is usually used as the location of the tree. In actual processing, it is also feasible to deviate from the tree core to a certain extent, and there is an allowable working height range when spraying, so , The coordinates of each point in the path can be adjusted in the horizontal direction or the vertical direction according to the allowable deviation range during operation to obtain a smoother operation path.

In order to further explain the path planning method provided by the present application, the following is explained in conjunction with a specific embodiment.

UAVs have been widely used in agriculture, such as spraying or watering fruit trees. In related technologies, when drones spray medicine on fruit trees, they automatically sort according to the position and spacing of fruit trees in the work area to determine the work path. In this way, the user cannot customize the job path, and is not flexible enough to meet user needs. Therefore, this embodiment provides a method that can realize the user's master planning of the work path.

As shown in FIG. 7, which is a schematic diagram of the application scenario of the embodiment of the application, the user can install a designated APP on the control terminal 72, and communicate with the drone 71 through the control terminal 72 to realize the planning of the operation path.

When it is necessary to perform drug spraying on fruit trees, UAV 71 can first survey the mission execution area, collect images and geospatial data of the mission execution area, and send them to the control terminal. The control terminal will generate data based on the data collected by the drone. Maps and semantic maps of the area, such as two-dimensional or three-dimensional maps, DSM maps, etc. The control terminal can display a map of the area to the user. The map can be two-dimensional or three-dimensional. The user can select the work area on the map and select a reference point on the map according to the expected work path. You can randomly click on the map to select a reference point. In order to avoid accidental touches, after receiving the user's instruction to click on the screen, a prompt message "whether to select this point as a reference point" can be displayed for the user to further confirm. After the user selects the reference point, the selected reference point can be displayed on the map for the user to view. After the user completes the selection of the reference points, the reference points can be connected in sequence according to the distance between the reference points to generate a reference path, as shown in Figure 3. Then you can determine the search radius according to the width of the fruit trees. For example, if you only need to spray one row of fruit trees at a time, you can determine the search radius to be half the width of the fruit trees. The spacing and tree width determine the search radius. Then the search area can be determined according to the reference path and the search radius, as shown in Figure 5, and the location of the center of each fruit tree in the work area can be determined by combining the semantic map and the DSM map, and then determine whether the location of each tree center is within the search area, if it is, Then the fruit tree is determined as the fruit tree to be sprayed.

As shown in Figure 3, the reference path can be connected by multiple line segments in sequence. After determining the fruit trees to be sprayed in the work area, the distance between the core of the fruit tree to be sprayed and each line segment in the reference path can be determined, and then the distance to be sprayed can be determined. The fruit tree is divided into groups corresponding to the nearest line segment. For the fruit trees to be sprayed in each group, the vertical foot of each fruit tree to be sprayed and the corresponding line segment of the group can be determined, and then the distance between the end point of the reference path and each vertical foot can be determined, according to the distance between the vertical foot and the end point of the reference path, from closest to Sort the fruit trees in the group to obtain the sorting result of the fruit trees in the group, and then obtain the sort order of all fruit trees to be sprayed according to the connection order of the line segments in the reference path and the sort order of the fruit trees in the group.

After determining the sort order of the cores of the fruit trees to be sprayed, the height corresponding to the position of each core can also be determined according to the working height during spraying. According to the position of the cores of the fruit trees to be sprayed, the sort order and the corresponding working height of each core is that The work path can be determined, and a medicine spray switch can be set for the position of the fruit tree.

Since there may also be obstacles such as houses and telephone poles in the work area, the semantic map can be used to determine the type of obstacles in the work area, and the appropriate obstacle avoidance strategy can be selected according to the obstacle type, and the generated obstacles can be updated according to the obstacle avoidance strategy. Job path. In order to obtain a smoother work path, the generated work path can also be smoothed in the horizontal or vertical direction. The user-defined work path can make the determination of the work path more flexible and improve the user experience.

Correspondingly, the present application also provides a path planning device. As shown in FIG. 8, the device 80 includes a processor 81, a memory 82, and a computer program executable by the processor 81 stored on the memory 82, so When the processor 81 executes the computer program, the following steps are implemented:

Generate a reference path based on the reference information input by the user;

In some embodiments, the processor is further configured to: before generating the reference path according to the reference information input by the user:

A human-computer interaction interface is provided, the human-computer interaction interface includes a map corresponding to the work area, and the reference information includes a reference point or a reference line determined by a user on the map.

In some embodiments, when the processor is configured to determine the target work object in the work object according to the relative positional relationship between the work object in the work area and the reference path, it is specifically configured to:

Determining a search area in the work area according to the reference path and the search radius;

The work object located in the search area is determined as the target work object.

In some embodiments, the processor is further configured to:

The search radius is determined according to the size of the work object.

In some embodiments, when the processor is used to sort the target job object, it is specifically used to:

The target work object is sorted according to the distance between the target work object and the end point of the reference path.

In some embodiments, the reference path includes a plurality of line segments connected in sequence, and when the processor is used to sort the target job object, it is specifically used to:

Determine the line segment corresponding to the target work object according to the distance between the target work object and each of the line segments;

The target work object is sorted according to the sequence of the line segments corresponding to the target work object.

In some embodiments, there are one or more target job objects corresponding to each line segment, and the processor is used for sorting the target job objects according to the sequence of the line segments corresponding to the target job objects, specifically using At:

Divide the target work object into a plurality of groups, wherein each group corresponds to one line segment, and the distance between the target work object in each group and the line segment corresponding to the group is the shortest;

Sort the target job objects in each group;

The target job objects are sorted according to the sequence of the line segments corresponding to the group and the sequence of the target job objects in the group.

In some embodiments, when the processor is used to sort the target objects in each group, it is specifically used to:

Determine the vertical feet of the target work object in each group on the line segment corresponding to the group;

Sort the target work objects in the group according to the distance between the end point of the reference path or the end point of the line segment corresponding to the group and the vertical foot.

In some embodiments, when the processor is configured to generate a target path based on the sorted target job objects, it is specifically configured to:

The target path is determined according to the sorted target work object's position and work height.

In some embodiments, the processor is further configured to:

Determine the types of obstacles in the work area;

An obstacle avoidance strategy is determined according to the type of the obstacle, and the target path is updated according to the obstacle avoidance strategy.

In some embodiments, the processor is further configured to:

Smoothing the target path.

In some embodiments, the work object includes crops.

Wherein, various implementation details of the path planning performed by the path planning device can refer to the descriptions in the above-mentioned path planning method embodiments, which will not be repeated here.

In addition, this application also provides a path planning system, which includes a movable platform and a control terminal,

Correspondingly, an embodiment of this specification also provides a computer storage medium in which a program is stored, and the program is executed by a processor to implement the path planning method in any of the foregoing embodiments.

The embodiments of this specification may adopt the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program codes. Computer usable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices.

As for the device embodiment, since it basically corresponds to the method embodiment, the relevant part can refer to the part of the description of the method embodiment. The device embodiments described above are merely illustrative, where the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply one of these entities or operations. There is any such actual relationship or order between. The terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements that are not explicitly listed. Elements, or also include elements inherent to such processes, methods, articles, or equipment. If there are no more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or equipment that includes the element.

The methods and devices provided by the embodiments of the present invention are described in detail above. Specific examples are used in this article to illustrate the principles and implementations of the present invention. The descriptions of the above embodiments are only used to help understand the methods and methods of the present invention. Core idea; At the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as a limitation of the present invention .

Claims

A path planning method, characterized in that the method includes:

Generate a reference path based on the reference information input by the user;

Determine the target work object in the work object according to the relative positional relationship between each work object in the work area and the reference path;

Sorting processing is performed on the target work objects to generate a target path based on the sorted target work objects.
The method according to claim 1, wherein before generating the reference path according to the reference information input by the user, the method further comprises:

A human-computer interaction interface is provided, the human-computer interaction interface includes a map corresponding to the work area, and the reference information includes a reference point or a reference line determined by a user on the map.
The method according to claim 1 or 2, wherein the determining the target work object in the work object according to the relative positional relationship between the work object in the work area and the reference path comprises:

Determining a search area in the work area according to the reference path and the search radius;

The work object located in the search area is determined as the target work object.
The method according to claim 3, further comprising:

The search radius is determined according to the size of the work object.
The method according to any one of claims 1 to 4, wherein the sorting processing of the target job object comprises:

The target work object is sorted according to the distance between the target work object and the end point of the reference path.
The method according to any one of claims 1 to 4, wherein the reference path includes a plurality of line segments connected in sequence, and the sorting processing of the target work object comprises:

Determine the line segment corresponding to the target operation object according to the distance between the target operation object and each of the line segments;

The target work object is sorted according to the sequence of the line segments corresponding to the target work object.
The method according to claim 6, wherein there are one or more target job objects corresponding to each line segment, and the target job objects are sorted according to the sequence of the line segments corresponding to the target job objects, include:

Divide the target work object into a plurality of groups, wherein each group corresponds to one line segment, and the distance between the target work object in each group and the line segment corresponding to the group is the shortest;

Sort the target job objects in each group;

The target job objects are sorted according to the sequence of the line segments corresponding to the group and the sequence of the target job objects in the group.
The method according to claim 7, wherein the sorting of the target objects in each group comprises:

Determine the vertical feet of the target work object in each group on the line segment corresponding to the group;

Sort the target work objects in the group according to the distance between the end point of the reference path or the end point of the line segment corresponding to the group and the vertical foot.
The method according to claim 1, wherein the generating the target path based on the sorted target job objects comprises:

The target path is determined according to the sorted target work object's position and work height.
The method according to claim 1, further comprising:

Determine the types of obstacles in the work area;

An obstacle avoidance strategy is determined according to the type of the obstacle, and the target path is updated according to the obstacle avoidance strategy.
The method according to claim 1, wherein the method further comprises:

Smoothing the target path.
The method according to any one of claims 1-11, wherein the work object includes crops.
A path planning device, characterized in that the device includes a processor, a memory, and a computer program executable by the processor stored in the memory, and when the processor executes the computer program, the following steps are implemented:

Generate a reference path based on the reference information input by the user;

Determine the target work object in the work object according to the relative positional relationship between each work object in the work area and the reference path;

Sorting processing is performed on the target work objects to generate a target path based on the sorted target work objects.
The apparatus according to claim 13, wherein the processor is further configured to: before generating the reference path according to the reference information input by the user:

A human-computer interaction interface is provided, the human-computer interaction interface includes a map corresponding to the work area, and the reference information includes a reference point or a reference line determined by a user on the map.
The apparatus according to claim 13 or 14, wherein the processor is configured to determine the target work object in the work object according to the relative positional relationship between the work object in the work area and the reference path, and is specifically configured to :

Determining a search area in the work area according to the reference path and the search radius;

The work object located in the search area is determined as the target work object.
The device according to claim 15, wherein the processor is further configured to:

The search radius is determined according to the size of the work object.
The device according to any one of claims 13-16, wherein when the processor is used to sort the target job object, it is specifically used to:

The target work object is sorted according to the distance between the target work object and the end point of the reference path.
The device according to any one of claims 13-16, wherein the reference path includes a plurality of line segments connected in sequence, and when the processor is used for sorting the target job object, it is specifically used for:

Determine the line segment corresponding to the target operation object according to the distance between the target operation object and each of the line segments;

The target work object is sorted according to the sequence of the line segments corresponding to the target work object.
The device according to claim 18, wherein there are one or more target operation objects corresponding to each line segment, and the processor is configured to perform processing on the target operation object according to the sequence of the line segments corresponding to the target operation object. When sorting, it is specifically used for:

Divide the target work object into a plurality of groups, wherein each group corresponds to one line segment, and the distance between the target work object in each group and the line segment corresponding to the group is the shortest;

Sort the target job objects in each group;

The target job objects are sorted according to the sequence of the line segments corresponding to the group and the sequence of the target job objects in the group.
The device according to claim 19, wherein when the processor is configured to sort the target objects in each group, it is specifically configured to:

Determine the vertical feet of the target work object in each group on the line segment corresponding to the group;

Sort the target work objects in the group according to the distance between the end point of the reference path or the end point of the line segment corresponding to the group and the vertical foot.
The device according to claim 13, wherein the processor is configured to generate a target path based on the sorted target job objects, and is specifically configured to:

The target path is determined according to the sorted target work object's position and work height.
The device according to claim 13, wherein the processor is further configured to:

Determine the types of obstacles in the work area;

An obstacle avoidance strategy is determined according to the type of the obstacle, and the target path is updated according to the obstacle avoidance strategy.
The device according to claim 13, wherein the processor is further configured to:

Smoothing the target path.
The device according to any one of claims 13-23, wherein the work object includes crops.
A path planning system, which is characterized by comprising a mobile platform and a control terminal,

The control terminal is configured to generate a reference path according to the reference information input by the user, determine the target work object in the work object according to the relative positional relationship between each work object in the work area and the reference path, and perform the operation on the target work object. Sorting processing to generate a target path based on the sorted target job objects, and send the target path to the mobile platform;

The mobile platform is used to execute work tasks according to the target path.