Map processing method, self-moving gardening device, and automatic mower

Abstract

Embodiments of the present application provide a map processing method, a self-moving gardening device, and an automatic mower. The map processing method comprises: controlling the self-moving gardening device to collect a first environment image in a local area and first pose information of the self-moving gardening device, the local area being adjacent to a position of a charging pile; generating an initial map according to the first environment image of the local area and the first pose information of the self-moving gardening device, so that the self-moving gardening device can automatically return to the charging pile based on the initial map; driving the self-moving gardening device to collect a second environment image of a remaining area and second pose information of the self-moving gardening device; the remaining area at least partially surrounds the local area; and determining a map of a first area according to the second environment image, the second pose information, and the initial map, the first area comprising the local area and the remaining area. The method can quickly and conveniently establish a map.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent devices, and in particular to a map processing method, a self-moving gardening device, and an automatic mower. BACKGROUND

[0002] The existing self-moving gardening device (which can also be referred to as a self-service gardening device or an intelligent gardening device or an automatic gardening device, etc.) such as an automatic mower can automatically mow grass without being watched or controlled by a person, thereby reducing the occupation of the user's time and reducing the user's repetitive labor.

[0003] The existing self-moving gardening device relies on manual limitation of the working area, such as burying a line along the edge of the working area and the edge of the obstacle, so that the self-moving gardening device recognizes the boundary and the obstacle by detecting the buried line, to prevent the self-moving gardening device from going out of the working area or colliding with the obstacle in the working area. The problem of this buried line method is that the user needs to consume a lot of time, or professional workers need to bury the line, and the price is expensive. For a scene where there are multiple working areas, there is a problem of complex line burying. SUMMARY

[0004] In view of the above problems, the present application provides a map processing method, a self-moving gardening device, and an automatic mower to at least solve the problem of poor mapping effect of the existing self-moving gardening device.

[0005] One or more embodiments of the present application provide a map processing method, comprising: controlling a self-moving gardening device to collect a first environment image in a local area and first pose information of the self-moving gardening device, the local area being adjacent to a location of a charging pile; generating an initial map according to the first environment image of the local area and the first pose information of the self-moving gardening device, so that the self-moving gardening device can automatically return to the charging pile based on the initial map; driving the self-moving gardening device to collect a second environment image of a remaining area and second pose information of the self-moving gardening device; the remaining area at least partially surrounds the local area; and determining a map of the first area according to the second environment image, the second pose information, and the initial map, the first area including the local area and the remaining area. According to another aspect of the present application, a map processing device is provided, comprising: a first driving module configured to control a self-moving gardening device to collect a first environment image in a local area and first pose information of the self-moving gardening device, the local area being adjacent to a location of a charging pile; a first determining module configured to generate an initial map according to the first environment image of the local area and the first pose information of the self-moving gardening device, so that the self-moving gardening device can automatically return to the charging pile based on the initial map; a second driving module configured to drive the self-moving gardening device to collect a second environment image of a remaining area and second pose information of the self-moving gardening device; the remaining area at least partially surrounds the local area; and a second determining module configured to determine a map of the first area according to the second environment image, the second pose information, and the initial map, the first area including the local area and the remaining area.

[0006] According to another aspect of the present application, a self-moving gardening device is provided, comprising a controller configured to perform the above method.

[0007] According to another aspect of the present application, an automatic mower is provided, comprising a controller configured to perform the above method.

[0008] Through the present embodiment, autonomous mapping of the self-moving gardening device can be achieved in this way, and when autonomous mapping is performed, the range where the charging pile is located is mapped first to form an initial map, so that the self-moving gardening device can conveniently return to the charging pile for charging when the power is low, thereby ensuring the reliability of the self-moving gardening device. After the initial map is established, the self-moving gardening device can move in the remaining area to collect a second environment image and generate a map of the first area in combination with the initial map and the second environment image, thereby achieving autonomous mapping of the self-moving gardening device, thereby saving cost and reducing labor intensity. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to make the technical solution of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the description of the embodiments or the prior art will be briefly introduced. Obviously, the accompanying drawings described below are some embodiments of the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative work on the basis of the embodiments in the present application shall fall within the protection scope of the present application.

[0010] Figure 1A A step flow chart of the map processing method provided for Embodiment One of the present application;

[0011] Figure 1B A schematic diagram of the working area containing multiple areas for Embodiment One of the present application;

[0012] Figure 2 A step flow chart of the map processing method for Embodiment One of the present application;

[0013] Figure 3A A step flow chart of the map processing method provided for Embodiment Four of the present application;

[0014] Figure 3B A schematic diagram of moving within a certain range of the charging pile for Embodiment Four of the present application;

[0015] Figure 3B A schematic diagram of moving within the remaining area for Embodiment Four of the present application;

[0016] Figure 3C A schematic diagram of the original map of the first area for Embodiment Four of the present application;

[0017] Figure 3D A schematic diagram of exploring the unexplored area for Embodiment Four of the present application;

[0018] Figure 3E A schematic diagram of the first area and the target area for Embodiment Four of the present application;

[0019] Figure 3F A structure block diagram of the map processing device for Embodiment Four of the present application. DETAILED DESCRIPTION

[0020] In order to make the technical solution of the embodiments of the present application, the technical solution in the embodiments of the present application will be described clearly and completely below in combination with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of the present application.

[0021] For the convenience of illustration and understanding, before the control method of the self-moving gardening device is described, the structure and working scene of the self-moving gardening device are briefly described as follows:

[0022] In this embodiment, the self-moving gardening device can be an automatic mower, of course, in other embodiments, the self-moving gardening device can also be other self-help gardening devices, or other devices that can realize self-walking.

[0023] The automatic mower can be used for mowing the lawn to ensure that the height of the grass in the lawn meets the requirements. The automatic mower includes a driving unit, a controller, a positioning assembly, and a grass cutting knife, etc. The grass cutting knife is used for cutting grass. The positioning assembly can include one or several of satellite positioning, ultra-wideband wireless communication positioning (UWB), inertial measurement unit (IMU), image acquisition device, and wheel speed meter. The current pose of the automatic mower at the moment can be detected through the positioning assembly. The pose includes its position and attitude. The position can be expressed by its coordinates on the X-axis, Y-axis, and Z-axis of the positioning coordinate system. The attitude can be determined by its angles relative to the X-axis, Y-axis, and Z-axis.

[0024] The image acquisition device can acquire the environmental image of the position where the self-moving gardening device is located, and then the pose of the self-moving gardening device can be determined according to the environmental image.

[0025] The driving unit includes at least two groups of driving wheels and a driving assembly that controls the rotation direction and rotation speed of the at least two groups of driving wheels. The driving assembly can include a motor and a motor controller. Each group of driving wheels can be connected to one motor, and the driving wheels are driven to rotate by the rotation of the motor. The motor controller can be a frequency converter or a PLC chip, etc., which controls the rotation direction and rotation speed of the motor.

[0026] Taking the automatic mower including two groups of driving wheels, each group of driving wheels includes at least one driving wheel. The two groups of driving wheels rotate at the same speed to realize the forward or backward movement of the automatic mower, and the differential rotation of the two groups of driving wheels realizes the turning of the automatic mower.

[0027] The controller is electrically connected with the motor controller and the positioning assembly. According to the pose of the automatic mower at the moment detected by the positioning assembly, a control signal is generated and sent to the motor controller to control the rotation of the motor.

[0028] In addition, the controller can also be connected with a control device. The control device can be integrated on the automatic mower, or can be independent of the automatic mower. When the control device is integrated on the automatic mower, it can include a display screen, control buttons, and a matching circuit board. When the control device is independent of the automatic mower, the control device can be any appropriate intelligent terminal, such as a smart phone, a PAD, a smart watch, or a computer, etc.

[0029] Automatic lawnmowers connect to smart devices to enable data interaction. For example, a smartphone can run a control application for the automatic lawnmower, allowing users to operate the machine through the application.

[0030] To ensure that self-propelled gardening equipment can move automatically within its work area, a self-visual mapping of the work area can be performed using the following method. This allows the self-propelled gardening equipment to obtain a map of the work area, which not only guides its movement within the work area for automated operation but also allows it to identify the edges of the work area and obstacles. This enables the self-propelled gardening equipment to move automatically without the need for additional wiring or marker posts within the work area, reducing operating costs and workload.

[0031] The implementation process of this method is explained below:

[0032] Example 1

[0033] Reference Figure 4 The diagram shows a flowchart of the map processing method according to Embodiment 1 of this application.

[0034] Step S102: Drive the self-moving gardening equipment to move within a set range in the first area where the distance from the charging pile meets the set value, and collect environmental images and position information of the self-moving gardening equipment within the range.

[0035] like Figure 1A As shown, the working area of ​​the self-moving gardening equipment may include one or more areas, and charging stations may be set in some or all of these areas. In this embodiment, if a charging station is set in only one area, the area where the charging station is set is referred to as the first area. If a charging station is set in more than one area, any one of these areas can be selected as the first area.

[0036] Before mapping, the self-moving gardening equipment cannot know the environment of its working area. To ensure the reliability, safety, and stability of the mapping process, and to avoid mapping failures or interruptions due to insufficient battery power, requiring manual operation or relocation by the user, the self-moving gardening equipment is driven to move within a set distance from the charging station during mapping. It then collects environmental images within this range and determines the pose information corresponding to each environmental image. This allows for the creation of an initial map within this range, enabling the self-moving gardening equipment to automatically return to the charging station for charging when its battery is low, thus ensuring reliability.

[0037] The set value can be determined as needed, and no limitation is made thereto. For example, the set value can be manually configured by a user or other personnel, such as 10-15 meters, etc. Alternatively, the set value can be determined in proportion to the area of the first region, such as when the area of the first region is 100 square meters, the set value can be determined as a value that makes the area of the range 50 square meters. Alternatively, the set value can be determined according to the total power of the self-moving gardening device, such as when the total power is 10,000 mAh, the set value can be 10-15 meters, etc.

[0038] In an example, the self-moving gardening device can take the charging pile where it is located as a starting point, randomly select a direction, move in the direction, and take an environmental image of the location every certain period of time, and collect the pose information of the self-moving gardening device through a wheel speed meter and an IMU (inertial navigation system) to determine the pose information corresponding to the environmental image.

[0039] Step S104: generating an initial map according to the environmental image of the range and the pose information of the self-moving gardening device, so that the self-moving gardening device can automatically return to the pile based on the initial map.

[0040] The initial map can be established through motion reconstruction (SFM, Structure From Motion) according to the environmental image of the range and the corresponding pose information. The initial map includes feature points of objects in the range, such as feature points of grass, feature points of trees, feature points of stones, and feature points of potholes, etc.

[0041] The established initial map can enable the self-moving gardening device to plan a path and navigate and locate according to the initial map for automatic return to the pile. For example, if the self-moving gardening device detects that the battery power is low during movement, the self-moving gardening device can be guided to return to the charging pile for charging according to the initial map.

[0042] After the initial map is established, the remaining area outside the range for which the initial map has been established in the first region can be determined, and the remaining area is explored through steps S106 and S108, so as to complete the mapping of the first region.

[0043] Step S106: driving the self-moving gardening device to move in the remaining area outside the range of the first region, and collecting environmental images of the remaining area and pose information of the self-moving gardening device.

[0044] By driving the self-moving gardening device to move in the remaining area, an environmental image of the location of the self-moving gardening device can be collected every certain period of time, and the pose information corresponding to the environmental image can be determined through a wheel speed meter, an IMU, or a satellite positioning module, etc.

[0045] Step S108: determining the map of the first region according to the environmental image of the remaining region, the pose information of the self-moving horticulture device, and the initial map.

[0046] After the environmental image of the remaining region is collected, a map of the remaining region is established based on the environmental image and the corresponding pose information, and the map of the remaining region and the initial map are merged to obtain the map of the first region.

[0047] In this way, autonomous mapping of the self-moving horticulture device can be achieved, and when autonomous mapping is performed, the range where the charging pile is located is first mapped to form an initial map, thereby ensuring that the self-moving horticulture device can conveniently return to the pile for charging when the power is low, thereby ensuring the reliability of the self-moving horticulture device. After the initial map is established, the self-moving horticulture device can move in the remaining region to collect the environmental image of the remaining region and generate a map of the first region in combination with the initial map and the environmental image of the remaining region, thereby achieving autonomous mapping of the self-moving horticulture device, thereby saving costs and reducing labor intensity.

[0048] Embodiment Two

[0049] Referring to Figure 1B , a step flow diagram of a map processing method according to an embodiment of the present application is shown.

[0050] Step S202: controlling the self-moving horticulture device to collect a first environmental image in a local region and first pose information of the self-moving horticulture device, the local region being adjacent to the position of the charging pile.

[0051] As described in the previous embodiment, the working region of the self-moving horticulture device can include one or more regions. The region where the charging pile corresponding to the self-moving horticulture device is located can be referred to as the first region. A part of the first region adjacent to the position of the charging pile is referred to as the local region. For example, the local region can be a region within five meters around the charging pile.

[0052] The self-moving horticulture device can collect the first environmental image by traveling, etc. during movement in the local region, and the corresponding first pose information can be collected by the mounted sensor.

[0053] Step S204: generating an initial map according to the first environmental image of the local region and the first pose information of the self-moving horticulture device, so that the self-moving horticulture device can automatically return to the pile based on the initial map.

[0054] According to the first environment image and the corresponding first pose information, an initial map can be established by motion reconstruction (SFM, Structure From Motion). The initial map includes feature points of objects in the range, such as feature points of grass, feature points of trees, feature points of stones, feature points of potholes, and the like.

[0055] The established initial map can enable the self-moving horticultural device to automatically plan a path and navigate and locate according to the initial map. For example, if the self-moving horticultural device detects that the battery has a low power during movement, the self-moving horticultural device can be guided to return to the charging pile for charging according to the initial map.

[0056] Step S206: driving the self-moving horticultural device to collect a second environment image of a remaining area and second pose information of the self-moving horticultural device, the remaining area at least partially surrounding the local area.

[0057] The remaining area can be an area in the first area other than the local area. By driving the self-moving horticultural device to move in the remaining area, the second environment image and the corresponding second pose information can be collected during movement.

[0058] Step S208: determining a map of the first area according to the second environment image, the second pose information, and the initial map, the first area including the local area and the remaining area.

[0059] After the second environment image of the remaining area is collected, a map of the remaining area is established based on the second environment image and the corresponding second pose information, and the map of the remaining area and the initial map are merged to obtain the map of the first area.

[0060] In this way, the map of the first area can be conveniently established, and the self-moving horticultural device can return to the charging pile for charging in time when a problem such as insufficient power occurs during mapping. The method can realize autonomous mapping of the self-moving horticultural device, thereby saving cost and reducing labor intensity.

[0061] Embodiment Three

[0062] Reference Figure 2 FIG. 3 shows a step flow diagram of a map processing method according to an embodiment of the present application.

[0063] In this embodiment, the method includes the following steps:

[0064] Step S302: controlling the self-moving horticultural device to collect a first environment image in a local area and first pose information of the self-moving horticultural device, the local area being adjacent to the position of the charging pile.

[0065] In the embodiment, the working area of the self-moving gardening device includes two independent and unconnected areas. The processing mode of more than two independent areas is similar to that of two areas, and thus is not described herein.

[0066] In the case of two independent areas, the area provided with the charging pile can be selected as the first area. In the initial state, the self-moving gardening device can be arranged on the charging pile. The self-moving gardening device exits from the charging pile. The exit process can be: if the front of the self-moving gardening device faces the charging pile, the self-moving gardening device backs off from the charging pile and rotates 180 degrees in place.

[0067] After exiting from the charging pile, the self-moving gardening device can randomly travel in a circular area (i.e., a local area, the distance between the local area and the charging pile meets a set value, i.e., the initial exploration area shown in Figure 3A ). Figure 3B

[0068] During the travel process, the self-moving gardening device collects a first environment image through the image acquisition device mounted thereon and detects first pose information of the self-moving gardening device through a wheel speed meter or an IMU. The first environment image can be used to generate an initial map in a subsequent step, and can also be used for image recognition of the first environment image through a neural network model to identify whether there is an obstacle and to determine the direction and distance of the obstacle relative to the self-moving gardening device, so that the self-moving gardening device can avoid the obstacle.

[0069] Step S304: generating an initial map according to the first environment image of the local area and the first pose information of the self-moving gardening device, so that the self-moving gardening device can automatically return to the pile based on the initial map.

[0070] According to the first pose information, it can be determined whether the self-moving gardening device has traversed the local area. If the self-moving gardening device has traversed the local area, the first environment image can be processed based on the first pose information corresponding to the first environment image collected in the local area, such as obtaining an initial map corresponding to the local area through SFM (visual three-dimensional reconstruction) or visual SLAM.

[0071] If it is necessary to return to the pile for charging in the subsequent process, a new environment image can be collected, feature points in the collected environment image are matched with feature points in the initial map, and then the pose of the self-moving gardening device is determined according to the matched feature points, so that the self-moving gardening device can be navigated and automatically return to the pile.

[0072] ​Step S306: driving the self-moving gardening device to collect a second environment image of a remaining area and second pose information of the self-moving gardening device; the remaining area at least partially surrounds the local area.

[0073] In this embodiment, the mapping for one independent area can be referred to as single-area mapping, which refers to autonomous movement and drawing of a passable grass map and a visual feature map in a scenario where the peripheral area of the grass has boundaries and the internal area of the grass is interconnected.

[0074] In this example, the mapping for the first area can be referred to as single-area mapping. Since an initial map has been established for the local area within a certain range of the charging pile, during the mapping process, for the remaining area outside the local area range in the first area, the self-moving gardening device can be driven to move in the remaining area, collect a second environment image of the current position every certain period of time, and locate second pose information corresponding to the second environment image, as shown in FIG. 6. Figure 3B The collected second environment image can be identified by using a neural network model capable of obstacle recognition, so as to determine whether there is an obstacle. If there is an obstacle, the self-moving gardening device can avoid the obstacle and detour.

[0075] In a feasible manner, the self-moving gardening device can be driven to move in the remaining area by using a proper strategy.

[0076] The strategy is, for example:

[0077] 1. Random strategy: randomly rotating an angle; or driving along a straight line, if an obstacle is encountered, randomly rotating a certain angle away from the obstacle, avoiding the obstacle, and continuing to drive along the straight line.

[0078] 2. Edge following strategy: driving along the edge of the identified obstacle.

[0079] 3. Random strategy mixed with edge following strategy. For example, according to a certain time ratio, the above two strategies are mixed.

[0080] If it is detected that the self-moving gardening device is low on power during the collection of the second environment image in the remaining area, the self-moving gardening device will pause autonomous movement and return to the pile for charging according to the initial map. After the power is sufficient, the autonomous exploration and movement will continue.

[0081] During the movement, in combination with the grass area input by the user and the detected second pose information of the self-moving gardening device, it is determined whether to stop the single-area exploration. For example, if it is determined that the remaining area has been traversed, the single-area exploration can be stopped.

[0082] Step S308: determining a map of the first region according to the second environment image, the second pose information and the initial map, the first region including the local region and the remaining region.

[0083] In the present example, after determining to terminate the exploration, the self-moving horticultural device can automatically return to the pile according to the initial map. After returning to the pile, the self-moving horticultural device can be charged and obtain the map of the first region through the following process.

[0084] Process A1: determining the original map of the first region according to the initial map, the second environment image and the second pose information.

[0085] In one case, if the second pose information includes the pose determined based on the wheel speed meter and the IMU and does not include the position of the satellite positioning obtained based on the satellite positioning, the process A1 can be implemented as follows: using a three-dimensional reconstruction (SFM) method to establish a visual map of the remaining region according to the second environment image and the corresponding second pose information, and fusing the initial map and the visual map of the remaining region to obtain the original visual map of the first region. In addition, the neural network model for obstacle recognition is used to perform obstacle recognition on the second environment image and the environment map corresponding to the initial map, and based on the recognized obstacles and their positions, the passable map corresponding to the first region is obtained.

[0086] The original map of the first region includes the original visual map and the passable map. The original visual map can be used for positioning and navigation in the subsequent automatic working process, and since it includes the initial map, it can also be used for automatic return to the pile. The passable map can be used for path planning and obstacle avoidance because it contains obstacle information.

[0087] Alternatively, in another case, if the second pose information includes the pose of the image acquisition device of the self-moving horticultural device and the position of the satellite positioning of the self-moving horticultural device, the process A1 can be implemented as follows: determining the mapping pose of the pose of the image acquisition device in the geographic coordinate system according to the position of the satellite positioning of the self-moving horticultural device; determining the original map of the first region according to the initial map, the second environment image and the mapping pose.

[0088] For example, the satellite positioning position can be obtained based on RTK technology. The satellite positioning position (for example, latitude and longitude) corresponding to the collected environment image is obtained. By converting the latitude and longitude to the UTM coordinate system, the orthogonal (for example, with the positive east and the positive north as the coordinate axes) GNSS track position is obtained. Based on the GNSS track position and the pose of the image collection device, the conversion relationship between the GNSS track position and the pose of the image collection device can be determined, and then the mapping pose of the pose of the image collection device in the UTM coordinate system can be determined. In this way, the latitude and longitude and the covariance information (the covariance information indicates the confidence of the latitude and longitude, and if the satellite signal strength is better, the confidence indicated by the covariance information is high, indicating that the latitude and longitude is more reliable) of the latitude and longitude are carried in the pose information of the environment image, and then the reliability of the original map of the first area obtained by using the SFM method is better. In this way, the robustness of the original visual map and the passable map in the original map is improved.

[0089] The original map includes a plurality of feature points. The feature points can be feature points in the original map, or feature points of reference objects (such as grass, pits, trees, etc.) in the second environment image. A part of the feature points can be feature points of the initial map, and another part of the feature points can be feature points of at least one reference object in the second environment map.

[0090] Process B1: determining whether the original map of the first area has an unexplored part, and if so, performing supplementary mapping on the first area to obtain the map of the first area.

[0091] Since there can be unexplored parts in the first area due to obstacles and other reasons during exploration, after obtaining the original map of the first area, it can be determined whether there is an unexplored part, and if so, process B11 is performed, otherwise, process B12 is performed.

[0092] In order to accurately determine whether there is an unexplored part to ensure reliability, the determination of whether the original map of the first area has an unexplored part can be implemented as follows: determining the distribution information of each feature point in the original map of the first area; and determining whether the original map of the first area has an unexplored part according to the distribution information.

[0093] For example, the original visual map is divided into blocks, and the number of feature points in each block is counted as distribution information. Based on this distribution information, abnormal blocks with fewer than a set number of feature points (which can be determined as needed, such as 10, 20, etc.) can be identified. If multiple abnormal blocks are connected, and the connected area is greater than or equal to a set area (which can be determined as needed, such as greater than or equal to the area of ​​one self-moving gardening device), then it is identified as an unexplored area (the original map containing the first unexplored area is shown in the image). Figure 3C As shown in the image, this also identifies the location of unexplored areas. Conversely, abnormal blocks are ignored.

[0094] Process B11: Perform supplementary mapping on the first region.

[0095] Specifically, process B11 can be implemented as follows: driving the self-moving gardening device to move within the unexplored area, and acquiring a third environmental image of the unexplored area and a third pose information of the self-moving gardening device; using the third environmental image and the third pose information to update the original map of the first area to obtain a map of the first area.

[0096] Based on the location of the unexplored area, the self-moving gardening equipment can be driven to move into the unexplored area and automatically explore it. The exploration strategy can be the same as the one described above, so it will not be repeated here. A schematic diagram of the movement process within the unexplored area is shown below. Figure 3D As shown, a third environmental image of the unexplored area is acquired, and the corresponding third pose information is determined. This third pose information can be determined based on the existing original visual map, ensuring that the coordinate system of the third pose information of the newly acquired environmental image is consistent with the coordinate system of the original visual map. After acquiring the third environmental image, the self-moving gardening equipment can automatically return to its charging dock and update the original visual map and the traversable map using the SFM method, thereby obtaining a map of the first area.

[0097] This approach solves the problems of randomness in exploration strategies and limitations in the acquisition range of image acquisition devices, which can easily lead to unexplored areas, thus ensuring the reliability of the map.

[0098] When there is more than one unexplored region, the above process can be repeated for each unexplored region until the supplementary mapping of all unexplored regions is completed.

[0099] Process B12: Complete the mapping of a single region.

[0100] Optionally, to improve the adaptability of the method, for work areas with more than one single region, the method further includes the following steps:

[0101] Step S310: determining whether there is a second region outside the region with the existing map in the working region, and if there is a second region, establishing a map corresponding to the second region.

[0102] The second region can be a region outside the region with the existing map. For example, the working region includes region A and region B, where the first region is region A, and the mapping of region A has been completed. Then region B can be the second region. Or, for another example, the working region includes region A, region B and region C, where the first region is region A, and the mapping of region A has been completed, and the mapping of region B as the second region has also been completed, then region C can be a new second region for mapping.

[0103] A feasible way to determine the second region can be: through the display device, asking the user whether there is a second region, if the user indicates that there is, then a map corresponding to the second region is established. Or, if the user indicates that there is not, then the mapping is completed.

[0104] Of course, other feasible ways can also be used to determine whether there is a second region, which is not limited.

[0105] If there is a second region, then the map corresponding to the second region can be established by the following process:

[0106] Process A2: determining a target region from the second region.

[0107] If the second region is only one, it is directly determined as the second region. Or, if the second region is more than one, one of them can be randomly determined as the target region, or the second region closest to the location of the self-moving garden device can be selected as the target region according to the existing map, or a second region can be specified by the user as the target region.

[0108] Optionally, in order to conveniently guide the self-moving garden device to move to the target region, step S310 can include process B2.

[0109] Process B2: determining a passageway between the region where the self-moving garden device is located and the target region.

[0110] For the case where the environment image of at least part of the target region has been collected, if the map of the region where the self-moving garden device is located contains at least part of the target region, the passageway is determined according to the map of the region where the self-moving garden device is located, such as Figure 3EThe first region map can be converted into an image or a two-dimensional grid form, in which the grass region and the non-grass region are divided. The grass region at the current location and all visible grass regions are extracted by image morphology, in which the visible but not at the current location grass region can be the grass of the target region. The isolation region between the two grasses is divided by image morphology, and a passable channel is selected from the isolation region and marked on the map.

[0111] The passable channel can be: the shortest path through the isolation region; or, when the self-moving gardening device includes a depth sensor that can collect three-dimensional information, an even passable channel is calculated according to the topography of the isolation region; or, the user is shown the collected map and topography, and the user draws a passable channel or selects a recommended passable channel.

[0112] For the case where the environment image of the target region is not collected, the passable channel can be set by user designation. The user can remotely control the self-moving gardening device to the target region to be mapped by remote control, and the self-moving gardening device will automatically identify the impassable region between the grasses and record the path as the passable channel.

[0113] After moving to the target region through the passable channel, process C2 can be performed. Of course, in other embodiments, process B2 can be omitted, and the self-moving gardening device can move to the target region by other suitable means.

[0114] Process C2: Collect a fourth environment image of the target region, and determine a map of the target region according to the fourth environment image.

[0115] After reaching the target region, the self-moving gardening device can explore the target region according to the strategy, and collect a fourth environment image at the current location every certain period of time, and determine the fourth pose information corresponding to the fourth environment image. Then, after collecting the fourth environment image, the map of the target region is generated based on the fourth environment image and the fourth pose information. The map includes a visual map and a passable map.

[0116] Based on the visual map and the passable map, it can also be determined whether there is an unexplored region. If there is an unexplored region, repeated exploration can also be performed, so as to update the visual map and the passable map until the mapping of the target region is completed.

[0117] The passable map can be generated based on the pose of the image acquisition device of the visual map and in combination with the identified obstacle information. In the passable map, the passable region, the obstacle and the unknown region are represented as three different colors. The maximum boundary of the passable region is extracted as the outer boundary of the lawn using the image morphology method. If there is an unknown region on or in the boundary, and the unknown region is connected with the passable region, the unknown region is regarded as a region that needs to be further explored.

[0118] Process D2: determining whether a termination condition is met, and if the termination condition is not met, returning to determine a target region from the second region and continue execution.

[0119] The termination condition can be that the difference between the area of the mapped region and the area of the working region specified by the user is less than or equal to an area threshold (which can be determined as needed, for example, 0, or other values greater than 0). If the termination condition is met, the mapping is completed. If the termination condition is not met, a new target region is determined from the remaining second region, and mapping is performed thereon until the termination condition is met, and the mapping is completed.

[0120] Based on this method, manual deployment of buried lines can be avoided, automatic mapping of the self-moving gardening equipment can be realized, unknown regions can be automatically explored, regions that need to be further explored can be determined, and exploration of unknown regions can be automatically completed after user confirmation, thereby improving the efficiency of mapping multiple lawns.

[0121] Embodiment Four

[0122] Reference Figure 3F Figure 4 Fig. 4 shows a structural block diagram of a map processing device according to an embodiment of the present application.

[0123] The device comprises:

[0124] A first driving module 402 is configured to control the self-moving gardening equipment to collect a first environment image in a local region and first pose information of the self-moving gardening equipment, wherein the local region is adjacent to the position of the charging pile.

[0125] A first determining module 404 is configured to generate an initial map based on the first environment image of the local region and the first pose information of the self-moving gardening equipment, so that the self-moving gardening equipment can automatically return to the pile based on the initial map.

[0126] A second driving module 406 is configured to drive the self-moving gardening equipment to collect a second environment image of a remaining region and second pose information of the self-moving gardening equipment, wherein the remaining region at least partially surrounds the local region.

[0127] The second determining module 408 is configured to determine a map of the first region according to the second environment image, the second pose information and the initial map, the first region including the local region and the remaining region.

[0128] Optionally, the second determining module 408 is configured to determine an original map of the first region according to the initial map, the second environment image and the second pose information; determine whether the original map of the first region has an unexplored part, and if so, perform supplementary mapping on the first region to obtain the map of the first region.

[0129] Optionally, the original map includes a plurality of feature points, the feature points including at least one of feature points in the initial map and feature points of at least one reference object in the second environment map, and the second determining module 408 is configured to determine distribution information of the feature points in the original map of the first region when determining whether the original map of the first region has an unexplored part; and determine whether the original map of the first region has an unexplored part according to the distribution information.

[0130] Optionally, the second determining module 408 is configured to drive the self-moving horticultural device to move in the unexplored region and collect a third environment image of the unexplored region and third pose information of the self-moving horticultural device when performing supplementary mapping on the first region to obtain the map of the first region; and update the original map of the first region using the third environment image and the third pose information to obtain the map of the first region.

[0131] Optionally, the pose information of the self-moving horticultural device includes a pose of an image collection device of the self-moving horticultural device and a satellite positioning position of the self-moving horticultural device, and the second determining module 408 is configured to determine a mapping pose of the image collection device in a geographical coordinate system according to the satellite positioning position of the self-moving horticultural device when determining the original map of the first region according to the initial map, the second environment image and the second pose information; and determine the original map of the first region according to the initial map, the second environment image and the mapping pose.

[0132] Optionally, the apparatus further includes:

[0133] The third determining module 410 is configured to determine whether there is a second region outside the region having an existing map in the working region, and if so, establish a map corresponding to the second region.

[0134] Optionally, the third determining module 410 is configured to determine a target region from the second region when the map corresponding to the second region is established; acquire a fourth environment image of the target region, and determine a map of the target region according to the fourth environment image; and determine whether a termination condition is met, and return to determine a target region from the second region to continue the execution if the termination condition is not met.

[0135] Optionally, the third determining module 410 is further configured to determine a passageway between the region where the self-moving garden device is located and the target region when the map corresponding to the second region is established.

[0136] Optionally, the third determining module 410 is configured to determine the passageway according to the map of the region where the self-moving garden device is located if the map of the region where the self-moving garden device is located contains at least part of the target region when the passageway between the region where the self-moving garden device is located and the target region is determined.

[0137] The apparatus can achieve the effects corresponding to the above method, and thus will not be described again.

[0138] Embodiment Five

[0139] In this embodiment, a self-moving garden device is provided, which comprises a controller configured to execute the above method and achieve the corresponding effects, and thus will not be described again.

[0140] Embodiment Six

[0141] In this embodiment, an automatic mower is provided, which comprises a controller configured to execute the above method and achieve the corresponding effects, and thus will not be described again.

[0142] It should be noted that, in the description of the present application, the terms "first", "second" are only used for the convenience of describing different components or names, and cannot be understood as indicating or implying the order relationship, relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features.

[0143] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0144] It should be noted that, although the specific embodiments of the present application are described in detail with reference to the accompanying drawings, it should not be understood as limiting the scope of protection of the present application. Various modifications and variations made by those skilled in the art within the scope described in the claims are still within the scope of protection of the present application.

[0145] The examples of the embodiments of the present application are intended to simply illustrate the technical features of the embodiments of the present application, so that those skilled in the art can directly understand the technical features of the embodiments of the present application, and are not improper limitations on the embodiments of the present application.

[0146] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A map processing method characterized by comprising: The method comprises: controlling a self-moving horticulture device to collect a first environment image of a local area and first pose information of the self-moving horticulture device, the local area being adjacent to a location of a charging pile, and a range of the local area satisfying a set value from the charging pile; generating an initial map based on the first environment image of the local area and the first pose information of the self-moving horticulture device, so that the self-moving horticulture device can automatically return to the charging pile based on the initial map, the initial map including feature points of objects in the range of the local area; driving the self-moving horticulture device to collect a second environment image of a remaining area and second pose information of the self-moving horticulture device, the remaining area at least partially surrounding the local area; determining a map of a first area including the local area and the remaining area based on the second environment image, the second pose information, and the initial map.

2. The method of claim 1, wherein, The method further comprises: determining whether the working area includes a second area outside an area having an existing map, and if so, establishing a map corresponding to the second area. The method further comprises:

3. The method of claim 2, wherein, determining a target area from the second area. ​ ​ 4. The method of claim 2, wherein, ​ ​ ​ 5. The method of claim 2, wherein, ​ ​ ​ ​ 6. The method of claim 1, wherein, ​ ​ 7. The method of claim 6, wherein, ​ ​ collecting a fourth environment image of the target region, and determining a map of the target region according to the fourth environment image; determining whether a termination condition is met, and if the termination condition is not met, returning to the step of determining a target region from the second region and continuing to execute.

8. The method of claim 7, wherein, The establishing the map corresponding to the second region further includes: determining a passageway between the region where the self-moving horticulture device is located and the target region.

9. The method of claim 8, wherein, The determining the passageway between the region where the self-moving horticulture device is located and the target region includes If the map of the region where the self-moving horticulture device is located contains at least part of the target region, determining the passageway according to the map of the region where the self-moving horticulture device is located.

10. A map processing apparatus characterized by comprising: It includes: The first driving module is configured to control the self-moving horticulture device to collect a first environment image in a local region and first pose information of the self-moving horticulture device, the local region is adjacent to the position of the charging pile, and the range of the local region satisfies a set value from the charging pile; The first determining module is configured to generate an initial map according to the first environment image of the local region and the first pose information of the self-moving horticulture device, so that the self-moving horticulture device can automatically return to the pile based on the initial map, and the initial map includes feature points of objects in the range of the local region; The second driving module is configured to drive the self-moving horticulture device to collect a second environment image of a remaining region and second pose information of the self-moving horticulture device; the remaining region at least partially surrounds the local region; The second determining module is configured to determine a map of a first region according to the second environment image, the second pose information, and the initial map, the first region including the local region and the remaining region.

11. A self-moving horticulture device, characterized in that, It includes a controller configured to perform the method of any one of claims 1-9.

12. An automatic lawnmower, characterized in that It includes a controller configured to perform the method of any one of claims 1-9.

Images