CN111199677B - A method, device, storage medium and working equipment for automatically establishing a working map of an outdoor area - Google Patents

Abstract

Translated fromChinese

本发明公开了一种室外区域的工作地图自动建立方法，装置，存储介质及工作设备，本方案首先使得工作设备在需要建立工作地图的室外区域内的任意位置自行沿任意方向移动，直至达到位于移动方向上的工作区域边界，所述工作区域边界由工作设备在移动过程中自行识别确定；接着使得工作设备自行沿随机角度转向并移动，直至达到位于移动方向上的工作区域边界，所述工作区域边界由工作设备在移动过程中自行识别确定，并重复此过程；最后基于工作设备所到达的工作区域边界点的位置信息绘制出初次的工作区域地图。本方案能够使得室外工作设备能够自动并准确的构建精准的工作区域地图。

The invention discloses a method, device, storage medium and working equipment for automatically establishing a working map in an outdoor area. The solution firstly enables the working equipment to move in any direction in any position in the outdoor area where a working map needs to be established, until it reaches the position in the outdoor area. The working area boundary in the moving direction, the working area boundary is identified and determined by the working equipment during the movement process; then the working equipment is automatically turned and moved along a random angle until it reaches the working area boundary located in the moving direction, and the working area boundary is The area boundary is identified and determined by the working equipment itself during the moving process, and this process is repeated; finally, an initial working area map is drawn based on the position information of the working area boundary point reached by the working equipment. This solution enables the outdoor working equipment to automatically and accurately construct an accurate working area map.

Description

Automatic work map establishing method and device for outdoor area, storage medium and working equipment

Technical Field

The invention relates to an automatic control technology of outdoor working equipment, in particular to a technology for establishing a working map of the outdoor working equipment.

Background

The automatic working equipment can effectively release people from heavy physical activity based on unique performance, so that the demand of the automatic working equipment is increased day by day.

The automatic operation of the automatic working equipment, particularly outdoor automatic working equipment, is based on determining the working range of automatic operation, and the primary step of determining the working range of the indoor and outdoor automatic working equipment is to establish a corresponding working area map about the working range and determine a working area and a working forbidden area.

Therefore, it is the first condition and foundation for automatic working equipment to establish a working area map for the equipment to work smoothly and orderly.

Currently, indoor and outdoor automatic working equipment or systems generally determine a working area through the following methods:

(1) the method only uses a GPS RTK satellite to position a self-built map, needs manual assistance, and uses a manual handheld antenna to perform outdoor dotting and mapping on a working boundary and GPS RTK positioning data of a working forbidden area to close the map boundary through an algorithm or manually draw the map boundary;

(2) establishing a map only by using a laser radar, establishing a point cloud map, and manually drawing a boundary in upper computer software;

(3) only a camera module is used for establishing a feature point cloud, and the artificial outdoor walking along the boundary collects feature points to define a working boundary and a working forbidden region.

However, the three methods have more problems in practical application, such as the following:

(1) when a GPS RTK satellite is used for positioning and self-building a map, manual map boundaries or obstacle outlines are needed to be used for manual drawing; when the RTK precision is reduced under the condition that the multi-azimuth building is sheltered, the working area can be defined with errors.

(2) Building a map based on a laser radar, wherein the premise is that a vertical object with a certain height is required to be used as a boundary, such as a wall; meanwhile, boundaries need to be manually drawn in software, and the manually drawn boundaries have large errors with a field scene and almost fail once a large-range scene changes; moreover, since sunlight is full spectrum, the lidar is interfered under the condition of strong outdoor sunlight, and thus, an error exists in a generated map.

(3) The characteristic point cloud is established based on the camera module, the working boundary is defined by collecting the characteristic points by manual work outdoor along the boundary, the operation is complex, and the use convenience of automatic working equipment is greatly influenced.

Therefore, how to conveniently and accurately establish a corresponding work area map outdoors by using automatic working equipment is an urgent problem to be solved in the field.

Disclosure of Invention

In order to solve the problem of the existing scheme for establishing the outdoor working area map by the automatic working equipment, a new scheme for establishing the outdoor working area map by the automatic working equipment is needed.

Therefore, the invention aims to provide an automatic establishment method of a work map of an outdoor area, so as to realize automatic and accurate establishment of the outdoor work area map by automatic working equipment; and further provides an automatic establishment device of the outdoor regional work map. On the basis, the invention further provides a storage medium and working equipment.

In order to achieve the above object, the present invention provides an automatic establishment method of a work map of an outdoor area, comprising:

enabling the working equipment to move along any direction at any position in an outdoor area where a working map needs to be established until a working area boundary located in the moving direction is reached, wherein the working area boundary is automatically identified and determined by the working equipment in the moving process;

enabling the working equipment to turn and move along a random angle by itself until the working equipment reaches a working area boundary positioned in the moving direction, wherein the working area boundary is automatically identified and determined by the working equipment in the moving process, and repeating the process;

and drawing a primary working area map based on the position information of the working area boundary point reached by the working equipment.

Further, the method synchronously obtains the video image of the outdoor real working scene of the position of the working equipment in the moving process of the working equipment, and accordingly, the working area boundary located in the moving route direction of the working equipment is identified and determined.

Further, the method performs heterogeneous acceleration processing of deep learning based on the image information of the outdoor real working scene where the working equipment is located, and distinguishes the working area from the non-working area to identify the working area boundary.

Further, the method determines and records the position information of the boundary point of the working area where the working equipment is located when the working equipment reaches the boundary of the working area each time. The location information may be radio positioning information or satellite positioning information

Furthermore, after the working equipment finishes the collection of the boundary points of the working areas with the preset number, the method determines the position information of the boundary points of each working area.

Further, the method uses a deep learning algorithm to identify the input image information, distinguish the working area from the non-working area, and record the radio positioning information of the point when the boundary of the working area is reached, or the satellite positioning information.

Furthermore, in the method, the working equipment can be steered along a certain preset angle.

Further, the method constructs a closed graph based on the determined position information of all the boundary points of the working area to form a primary working area map, and uses the primary constructed working area map for subsequent path planning. Further, the method also comprises the step of perfecting the map of the primary work area.

Further, in the working process of the working equipment based on the primary working area map, the method continuously identifies and distinguishes the working area and the non-working area in real time, and records the position information of the boundary point of the corresponding working area when the boundary is reached; the constructed work area map is further refined based on the added position information of the work area boundary points.

In order to achieve the above object, an automatic establishment apparatus for an outdoor area work map according to the present invention includes:

the control unit controls the working equipment to move and turn;

a work area boundary identifying unit that identifies a work area boundary located in a moving direction of the work apparatus;

and the position information acquisition unit acquires the position information of the boundary point of the working area in the moving direction of the working equipment.

And the working map generating unit is used for drawing a primary working area map based on the position information of the working area boundary points acquired by the position information acquiring unit.

In order to achieve the above object, the present invention provides a storage medium including a stored program that executes the above work map automatic creation method.

In order to achieve the purpose, the working equipment provided by the invention is internally provided with control software, and the control software executes the automatic establishment method of the working map.

Based on the automatic establishment scheme of the work map of the outdoor area, provided by the invention, the outdoor work equipment can automatically and accurately establish an accurate work area map.

This scheme can realize that the working equipment is independent intelligent recognition work area when using, and the forbidden district of part work of automatic planning saves a large amount of manpowers relatively original technical scheme, exempts from the wiring, exempts from the survey and drawing, and the practicality is strong.

When the scheme is applied, the long-term maintenance is more convenient, and the map updating is quickly obtained by using the method the same as the method for establishing the map for the first time.

Drawings

The invention is further described below in conjunction with the appended drawings and the detailed description.

FIG. 1 is a basic flow diagram of a method for automatically creating a work map for an outdoor area in accordance with an embodiment of the present invention;

FIG. 2 is a schematic diagram of an embodiment of the present invention in which a work device automatically collects work area boundary points;

FIG. 3 is a schematic diagram of a map of a primary work area completed in an example of the present invention;

FIG. 4 is a diagram illustrating an exemplary configuration of an apparatus for automatically creating a work map of an outdoor area according to an embodiment of the present invention;

fig. 5 is a diagram illustrating an example of the components of the working device capable of automatically creating the working map of the outdoor area according to the embodiment of the present invention.

Detailed Description

In order to make the technical means, the original characteristics, the achieved purposes and the functions of the application easier to understand, the application is further described below by combining the specific drawings and the embodiments. It is to be understood that the described embodiments are merely exemplary of some, and not all, of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.

The first condition of the outdoor working equipment for automatically working in the outdoor area is to determine an outdoor working area and a working forbidden area, specifically, to establish a corresponding working area map for the outdoor working range, so as to determine the outdoor working area and the working forbidden area.

The scheme of the embodiment provides an automatic establishment method of a work map of an outdoor area, and based on the scheme, automatic and accurate establishment of the outdoor work area map by automatic work equipment can be achieved.

Referring to fig. 1, a basic flowchart of the automatic establishment method of the work map of the outdoor area according to the present embodiment is shown. It can be seen from the figure that the process of the automatic establishment method of the outdoor work map for the work equipment to automatically establish the work map in the outdoor area mainly comprises the following steps:

(1) placing the working equipment at any position in an outdoor area where a working map needs to be established;

(2) the working equipment is enabled to move along any direction at the throwing position by itself until reaching the working area boundary positioned in the moving direction, and the working area boundary is identified and determined by the working equipment by itself in the moving process;

(3) the working equipment is enabled to turn and move along a random angle by itself until the working equipment reaches the working area boundary positioned in the moving direction, the working area boundary is automatically identified and determined by the working equipment in the moving process, and the process is repeated;

(4) and drawing a primary working area map based on the position information of the working area boundary point reached by the working equipment.

It should be noted that the steps shown in the flowcharts of the figures herein may be implemented in a computer system such as a set of computer-executable instructions.

According to the above process, the method is implemented by first placing the working device at any position in the outdoor area where the working map needs to be created. The working equipment is preferably placed in an outdoor working area, so that the subsequent working area boundary acquisition is facilitated.

After the work equipment is launched, the work equipment is enabled to move in any direction at the launching position by itself until the work equipment reaches the boundary of the work area located in the moving direction, the work equipment is stopped by taking the launching position as a starting point until the work equipment reaches the boundary of the work area located in the moving direction, and the stopping position is taken as a boundary point of the work area, so that the collection of the boundary point of the first work area is completed.

It should be noted that the working area boundary here is only the working area boundary located in the moving direction of the working device, and is not the complete boundary of the entire working area; and is self-identified and determined by the working equipment during the moving process. The boundary of the working area is determined without manual intervention of setting auxiliary components (such as wiring along the boundary of the working area by manual work) or manual control, and is completely identified and confirmed by the working equipment.

Furthermore, according to the scheme, when the working equipment reaches the identified working area boundary located in the moving direction of the working equipment, the working equipment is made to stop moving, the position of the working equipment at the moment is recorded and is used as the working area boundary point, and therefore the collection of the first working area boundary point is completed.

In the embodiment, there are various methods for identifying and determining the boundary of the working area located in the moving direction by the working device during the moving process, and those skilled in the art can select an appropriate method according to actual conditions to achieve the purpose. For example, the working equipment can be enabled to synchronously acquire video images of outdoor real working scenes at the position of the working equipment during moving, and accordingly deep learning is carried out to identify and determine the working area boundary in the moving route direction of the working equipment.

Alternatively, the working area such as grass, snow, etc. may be distinguished by detecting the moisture on the surface of the earth by means of a capacitive moisture sensor. Or the Hall sensor detects the ground magnetic field to identify the corresponding working area paved with the electromagnetic boundary. Thus, when the sensor value conforms to the change of the preset model, or jumps greatly, the sensor value is already on the corresponding working boundary. Accordingly, radio positioning information, or satellite positioning information, is recorded for a point, i.e., the boundary point coordinates, while the working equipment reaches the boundary of the working area.

In this embodiment, the working device located at the release position only needs to move in any direction when being started, and the movement is preferably a linear movement.

In some embodiments, the working device located at the release position may also be moved in a predetermined angular direction when activated, and the specific angular direction may be set arbitrarily, and the movement is preferably a linear movement. This further improves the utility of the present solution.

Further, when the working device is started from the release position and moves (in any direction or in a preset angle direction), the working device may move at a constant speed or at a non-constant speed, and may be specifically set according to actual requirements, which is not limited herein.

Moreover, after the first working area boundary point is acquired, the working equipment is enabled to turn and move along random angles by itself until the working area boundary located in the moving direction is reached. The method comprises the steps that a working device carries out random angle steering by taking a first working area boundary point as a starting point, moves again after steering until reaching a working area boundary positioned in the moving direction, and takes a stop bit as a working area boundary point, so that the acquisition of a second working area boundary point is completed; likewise, the working area boundary in the moving direction is determined by the working device during the moving process.

In the process of acquiring the boundary point of the second working area, the determination scheme for the boundary of the working area and the boundary point of the working area, such as the corresponding scheme adopted in the acquisition of the boundary point of the first working area, is not described herein again.

In the process of collecting the boundary point of the second working area, the working equipment performs pivot steering by taking the boundary point of the first working area as a starting point, wherein the steering angle is randomly determined by the working equipment, and only the subsequent moving direction of the working equipment needs to deviate from the original moving direction. After the steering is completed, the working device is moved again in the steered direction, preferably in a linear direction.

In some application examples, when the working equipment turns at the boundary point of the first working area, the working equipment can also turn along a preset angle, and the specific angle direction can be set at will as long as the subsequent moving direction of the working equipment deviates from the original moving direction. At the same time, the subsequent working device is moved in the direction after the steering, and the movement is preferably moved in the linear direction. This further improves the utility of the present solution.

Moreover, the working device may move at a constant speed or at a non-constant speed during the process of starting from the boundary point of the first working area and moving to the boundary point of the second working area, and the specific speed may be set according to actual requirements, for example, the specific moving speed may be matched with the process of identifying the boundary of the working area by the working device.

In addition, after the second working area boundary point is acquired, the present embodiment continues to operate in the manner and scheme of acquiring the second working area boundary point, and acquires the third working area boundary point, the fourth working area boundary point, and so on until the required number of working area boundary points is acquired.

Referring to fig. 2, it is a diagram illustrating an example of the process of automatically acquiring the boundary points of the working area by the working equipment in this example. It can be seen from the figure that, in the embodiment, when the working equipment automatically collects the boundary points of the working area, the working equipment reaches the boundary points of the working area which are automatically identified, the random angle steering is performed, and the like, so that the working equipment randomly walks in ping-pong mode. Therefore, after repeated times, the working equipment can acquire the position information (namely coordinate information) of the boundary points of the plurality of working areas, and accordingly a preliminary working area map can be automatically constructed. The whole process does not need human intervention, autonomously learns the surrounding environment, autonomously establishes a working area map, and ensures that working equipment does not cross the boundary in the working area all the time.

In addition, the number of the boundary points of the work area to be collected in this example is generally determined according to actual requirements, such as the size of the actual field, the shape of the field, the surrounding environment of the field, and the like. For example, in order to ensure the accuracy of the subsequent drawing of the first work area map, it is usually necessary to determine more than 10 work area boundary points, and at least more than six boundary points need to be determined.

In addition, in this embodiment, after the required number of working area boundary points are acquired through the working area boundary point self-acquisition step, the primary working area map is drawn based on the acquired position information of the working area boundary points.

The position information of the boundary point of the working area can be used for simultaneously determining and recording the position information of the boundary point of the working area where the working equipment is located when the working equipment acquires the boundary point of the working area each time the working equipment reaches the boundary of the working area.

Alternatively, after the working equipment finishes collecting the boundary points of the working areas with a predetermined number, the position information of each boundary point of the working areas can be determined.

The position information of the point can be calculated by a motion sensor, can also be measured by a radio ranging module, can also be positioned by a GNSS satellite, or can be calculated by the sensors through a sensor fusion algorithm.

In addition, the location information here may be relative distance to the charging base station or location information, and may be latitude and longitude information.

Further, the present example forms the primary work area map by constructing a closed figure by a graphic algorithm after acquiring radiolocation information recorded at each time of reaching the work area boundary, or satellite positioning information (i.e., acquiring position information of a plurality of work area boundary points), at that point. And planning a subsequent working path of the working equipment based on the primarily constructed working area map.

In order to further improve the accuracy of the generated working area map, the embodiment further improves the generated outdoor primary working area map.

In the working process of the working equipment based on the path planned by the primary working area map, the working area and the non-working area are continuously identified and distinguished in real time, and the position information of the corresponding working area boundary point is continuously recorded when the boundary is reached (namely the position information of the newly added working area boundary point is formed); the constructed work area map is further refined based on the location information of the added work area boundary points, such as adding the location information of the added work area boundary points to a previous work area map.

Specifically, referring to fig. 3, in this embodiment, a path planning of a work area is performed based on a generated primary work area map, so that the work equipment performs overlay work based on the path planning, and in the work process, the primarily generated work area map is optimized and perfected through visual recognition by the work equipment, and a work map including a complete boundary is finally generated through multiple iterations.

Aiming at the automatic establishment method of the work map of the outdoor area, the embodiment further improves an automatic establishment device of the work map of the outdoor area.

Referring to fig. 4, a diagram of an exemplary configuration of an automatic establishment apparatus for an outdoor area work map according to the present embodiment is shown.

As can be seen from the figure, theautomatic establishment apparatus 100 for the outdoor area work map is mainly composed of a control unit 110, a work area boundary identification unit 120, a position information collection unit 130, and a work map generation unit 140, which are cooperated with each other.

The control unit 110 in the present device is used for controlling the movement and turning of the working device, and can move, stop, accelerate, decelerate, turn at random angles, and so on. The specific construction schemes are various, and those skilled in the art can select a suitable method according to actual conditions to achieve the purpose.

The working area boundary identification unit 120 is matched with the control unit 110, and automatically identifies the working area boundary positioned in the moving direction of the working equipment in the process that the control unit 110 controls the working equipment to move; meanwhile, when the working equipment reaches the working area boundary identified by the working area boundary identification unit 120 along the moving direction, the control unit 110 controls the working equipment to stop moving, the device sets the record stop position as the collected working area boundary point, at the moment, the control unit 110 controls the working equipment to turn randomly or according to a preset angle, and after the turning is finished, the working equipment is controlled to continue moving along the turning rear direction.

The position information collecting unit 130 is used for cooperating with the work area boundary identifying unit 120 and the control unit 110 to collect the position information of the work area boundary point in the moving direction of the work equipment.

The work map generating unit 140 draws a primary work area map based on the position information of the work area boundary points acquired by the position information acquiring unit 130.

In specific implementation, the automatic establishment apparatus for the outdoor area work map mainly includes a processor and a memory, the control unit 110, the work area boundary identification unit 120, the position information acquisition unit 130, and the work map generation unit 140 are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more cores may be provided.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

Based on the scheme, the embodiment further provides the working equipment capable of automatically establishing the outdoor area working map.

The working equipment is internally provided with corresponding control software which can execute the automatic establishment method of the working map of the outdoor area given by the embodiment.

Referring to fig. 5, the workingdevice 200 mainly includes an embeddedprocessor 201, a heterogeneousacceleration processing unit 202, acollision sensor 203, acamera 204, aradio ranging module 205, aninertial navigation sensor 206, a motordigital encoder 207, acommunication module 208, apower module 209, and a geographicposition information sensor 210.

Wherein, the embeddedprocessor 201 is in data connection with the heterogeneousacceleration processing unit 202; the embeddedprocessor 201 is connected with aninertial navigation sensor 206, a motordigital encoder 207, acommunication module 208 and apower module 209 in a control way; and the heterogeneousacceleration processing unit 202 controls and connects thecollision sensor 203, thecamera 204, theradio ranging module 205 and the geographicposition information sensor 210.

Theinertial navigation sensor 206 and the motordigital encoder 207 cooperate to form a corresponding motion sensor for detecting the motion state of the equipment, the pose of the machine is calculated through a sensor fusion algorithm to estimate the position in the map of the machine, and when the machine identifies the boundary of the working area through the camera, a rough coordinate is determined for the boundary point, so that the map of the working area is conveniently drawn.

Thecollision sensor 203 is mainly used for recording the current obstacles on the earth surface, supplements a machine vision recognition algorithm, and assists in establishing a work task area according to the obstacles on the earth surface.

The heterogeneousacceleration processing unit 202, serving as a core processing unit, mainly includes, by way of example: the GPU, the FPGA, the DSP, the NCU and the artificial intelligence ASIC improve the processing speed and efficiency of the algorithm through parallel computation or model preprocessing.

A geographicallocation information sensor 210, comprising: the satellite positioning system, GNSS RTK, GNSS RTD, obtain geographical position information such as longitude and latitude.

Aradio ranging module 205, preferably a base station radio ranging sensor, is used for spatial location reference to correct for accumulated errors in the operation of the device. The ultra-wideband Bluetooth wireless distance measurement system comprises one of an ultra-wideband UWB distance measurement module and a Bluetooth distance measurement module. Since the radio ranging accuracy is high and there is no accumulated error, a relatively accurate position can be calculated using a sensor fusion algorithm.

In the scheme, the heterogeneousacceleration processing unit 202 is matched with thecamera 204, the geographicposition information sensor 210, theradio ranging module 205 and the like, a large amount of data of a plurality of sensors are subjected to parallel acceleration processing through an algorithm and deep learning, reliable position characteristics depending on landform and earth surface characteristics are screened out, and the accurate position of the workingequipment 200 in a working map is determined.

As can be seen from the above, when the workingdevice 200 configured in this way is operated, the AI machine vision algorithm is fused with the corresponding sensor, the machine vision camera sensor is used for acquiring the image of the lower front of the machine, and the image is input to the heterogeneous acceleration processing unit for AI algorithm operation processing, so as to identify whether the image is a working area boundary.

Further, the operation process of the workingdevice 200 is as follows:

first, thework apparatus 200 is placed at an arbitrary position in the outdoor work area, and thework apparatus 200 is set to enter the map building mode.

Next, the workingdevice 200 starts to build a map for the first time; the workingequipment 200 walks linearly from a starting point, turns at a random angle when a machine vision algorithm identifies a non-machine preset working area, and walks randomly in ping-pong manner, so that at least more than six working area boundary points are collected, and preferably more than 10 working area boundary points are collected; and calculating the approximate coordinates of each working area boundary point through a sensor fusion algorithm.

Finally, thework apparatus 200 draws a primary work area map through a map generation algorithm.

In addition, thework apparatus 200 further improves the primary work area map drawn by the work apparatus in the subsequent work process.

Specifically, after the primary work area map is drawn, thework equipment 200 plans a path of the work area through the primary work area map, and performs the overlay work based on the path.

The workingequipment 200 is used for perfecting the initially generated working map through visual recognition and optimization in the later covering working process aiming at the initially generated working area map, and finally generating a working map containing a complete boundary through multiple iterations.

From the above, the solution provided in this example can automatically and accurately construct an accurate work area map, which has the following advantages over the prior art:

1. this scheme is a large amount of manpowers of saving compared with original technical scheme, exempts from the wiring, exempts from the survey and drawing for equipment is autonomic intelligent recognition work area, and automatic planning part work forbidden region.

2. The scheme is convenient for long-term maintenance, and the map is quickly updated by using the method the same as the method for establishing the map for the first time.

3. Compared with the common map, the map established by the scheme is multidimensional and contains visual boundary information, boundary point coordinate information, working range area and other information.

4. According to the scheme, the map is quickly established, the map is processed by the processor, more than six boundary points of the map in the area can be used, and the coordinates of all the points of the boundary can be output within a few seconds after the boundary point acquisition is completed.

Finally, it should be noted that the method, or specific system unit, or some of the units thereof in the above embodiment are purely software structures, and can be distributed on a physical medium such as a hard disk, an optical disk, or any electronic device (e.g. a smart phone, a computer readable storage medium) through a program code, and when the program code is loaded and executed by a machine (e.g. a smart phone is loaded and executed), the machine becomes an apparatus for implementing the invention. The methods and apparatus of the present invention may also be embodied in the form of program code transmitted over some transmission medium, such as electrical cable, fiber optics, or via any other form of transmission, wherein, when the program code is received and loaded into and executed by a machine, such as a smart phone, the machine becomes an apparatus for practicing the invention.

The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (12)

Translated fromChinese

1.室外区域的工作地图自动建立方法，其特征在于，包括：1. the automatic establishment method of the working map of the outdoor area, it is characterized in that, comprising:首先，使得工作设备在需要建立工作地图的室外区域内的任意位置自行沿任意方向移动，直至达到位于移动方向上的工作区域边界，所述工作区域边界由工作设备在移动过程中自行识别确定；First, make the work equipment move in any direction in any position in the outdoor area where the work map needs to be established, until it reaches the work area boundary located in the moving direction, and the work area boundary is identified and determined by the work equipment during the movement process;接着，使得到达工作区域边界的工作设备自行沿随机角度转向并移动，直至达到位于移动方向上的工作区域边界，所述工作区域边界由工作设备在移动过程中自行识别确定，并重复此过程；Next, make the working equipment that reaches the boundary of the working area turn and move along a random angle by itself, until it reaches the working area boundary located in the moving direction, and the working area boundary is identified and determined by the working equipment during the moving process, and this process is repeated;最后，基于工作设备每次所到达的工作区域边界点的位置信息绘制出初次的工作区域地图。Finally, an initial work area map is drawn based on the position information of the work area boundary points that the work equipment reaches each time.2.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法在工作设备的移动过程中同步获取工作设备所在位置的室外真实工作场景的视频图像，据此识别确定位于工作设备所在移动路线方向上的工作区域边界。2. The method for automatically establishing a working map of an outdoor area according to claim 1, wherein the method synchronously acquires the video image of the outdoor real working scene at the location of the working equipment during the moving process of the working equipment, and identifies accordingly. Determine the boundaries of the work area in the direction of the movement route of the work equipment.3.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法基于工作设备所在位置的室外真实工作场景的图像信息进行深度学习的异构加速处理，区分工作区域与非工作区域，以识别出工作区域边界。3. The method for automatically establishing a work map of an outdoor area according to claim 1, wherein the method performs heterogeneous acceleration processing of deep learning based on the image information of the outdoor real work scene where the work equipment is located, and distinguishes the work area. and non-working area to identify the working area boundary.4.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法在工作设备每次达到工作区域边界时，确定记录工作设备所在工作区域边界点的位置信息。4 . The method for automatically establishing a work map of an outdoor area according to claim 1 , wherein the method determines and records the position information of the boundary point of the work area where the work device is located each time the work device reaches the work area boundary. 5 .5.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法在工作设备完成预定数量的工作区域边界点采集后，再确定每个工作区域边界点的位置信息。5 . The method for automatically establishing a work map of an outdoor area according to claim 1 , wherein the method determines the position information of each work area boundary point after the work equipment completes the collection of a predetermined number of work area boundary points. 6 . .6.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法中工作设备可以沿某一预设角度进行转向。6 . The method for automatically establishing a working map of an outdoor area according to claim 1 , wherein in the method, the working equipment can be turned along a predetermined angle. 7 .7.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法基于确定的所有工作区域边界点的位置信息构建封闭图形，以形成初次的工作区域地图，将初次构建的工作区域地图用于后续的路径规划。7. The method for automatically establishing a working map of an outdoor area according to claim 1, wherein the method constructs a closed graph based on the position information of all the determined boundary points of the working area to form an initial working area map, The constructed work area map is used for subsequent path planning.8.根据权利要求1所述的室外区域的工作地图自动建立方法，其特征在于，所述方法中还包括对初次工作区域地图进行完善的步骤。8 . The method for automatically establishing a working map of an outdoor area according to claim 1 , wherein the method further comprises the step of perfecting the initial working area map. 9 .9.根据权利要求8所述的室外区域的工作地图自动建立方法，其特征在于，所述方法在工作设备基于初次工作区域地图进行工作过程中，继续实时识别区分工作区域和非工作区域，并且在到达边界时，继续记录相应的工作区域边界点的位置信息；基于所增加的工作区域边界点的位置信息来进一步完善所构建的工作区域地图。9. The method for automatically establishing a working map of an outdoor area according to claim 8, wherein the method continues to identify and distinguish the working area and the non-working area in real time during the working process of the working device based on the initial working area map, and When reaching the boundary, continue to record the position information of the corresponding work area boundary point; further improve the constructed work area map based on the added position information of the work area boundary point.10.室外区域工作地图的自动建立装置，其特征在于，包括：10. An automatic establishment device for a work map of an outdoor area, characterized in that it includes:控制单元，所述控制单元控制工作设备移动及转向；a control unit that controls the movement and steering of the work equipment;工作区域边界识别单元，所述工作区域边界识别单元识别位于工作设备移动方向上的工作区域边界；a work area boundary identification unit, the work area boundary identification unit identifies the work area boundary located in the moving direction of the work equipment;位置信息采集单元，所述位置信息采集单元采集工作设备所到达移动方向上的工作区域边界点的位置信息；a position information collection unit, the position information collection unit collects position information of the boundary point of the work area in the moving direction reached by the work equipment;工作地图生成单元，所述工作地图生成单元基于位置信息采集单元所采集的工作区域边界点的位置信息绘制出初次的工作区域地图。A work map generation unit, the work map generation unit draws an initial work area map based on the position information of the boundary points of the work area collected by the position information collection unit.11.存储介质，所述存储介质包括存储的程序，其特征在于，所述程序执行权利要求1-9中任一项所述的工作地图自动建立方法。11. A storage medium comprising a stored program, wherein the program executes the method for automatically establishing a work map according to any one of claims 1-9.12.工作设备，所述工作设备内置有控制软件，其特征在于，所述控制软件执行权利要求1-9中任一项所述的工作地图自动建立方法。12. A work device, wherein the work device has built-in control software, wherein the control software executes the method for automatically establishing a work map according to any one of claims 1-9.

Images