AGV-based path planning method and system

Abstract

The present invention discloses a path planning method and system based on AGV, wherein the path planning method based on AGV comprises: during the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and obtains a first image; the positions and distances of multiple obstacles are located on the current map, and the corresponding position points are marked on the navigation path of the AGV; when the current map is marked with position points, the second traversal of the AGV is triggered; during the second traversal, the navigation path of the AGV is adjusted based on the position space between the multiple obstacles, and the AGV passes through the multiple obstacles to synchronously detect the multiple obstacles and form a second image; during the second traversal, the second image is monitored, and the shape of each obstacle in the second image is extracted to obtain the blank area of ​​the obstacle; based on the blank area, the supplement operation of the AGV is triggered, and the path adjustment is performed on the basis of the navigation path of the second traversal, so as to complete the area supplement during the second traversal.

Description

Technical Field

[0001] The present invention relates to the field of AGV technology, and in particular to a path planning method and system based on AGV. Background Art

[0002] With the development of science and technology, AGV is gradually applied to the industrial field and unmanned operation is gradually realized. Among them, AGV needs to build a map when entering a new environment and complete the obstacle detection in this map. At this time, the detection time in this map is relatively long, and the shape and position of the obstacle in the map are finally fixed, resulting in low detection efficiency of AGV. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a path planning method and system based on AGV, which realizes the gradual refinement of obstacles and maps based on multiple path traversals of AGV, and adjusts the previous traversal path during each traversal to facilitate the refined path operation based on the gradually clarified obstacles, and completes the synchronous detection of multiple obstacles in the second traversal to improve the working efficiency of obstacle detection. In addition, the blank area is supplemented in the third traversal to avoid missed detection of obstacles, improve the blank area of ​​obstacles, and improve the detection efficiency and detection accuracy of AGV.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a path planning method based on AGV, comprising: performing path traversal based on the navigation path of the AGV;

[0005] During the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes first shapes of a plurality of the obstacles and interval distances between the plurality of the obstacles;

[0006] Locate the positions and distances of the plurality of obstacles to the current map, and mark the corresponding position points on the navigation path of the AGV;

[0007] When the location point is marked on the current map, the second traversal of the AGV is triggered, and the mapping state is converted to the working state, wherein the AGV can expand the current map based on the external environment when in the mapping state;

[0008] During the second traversal, the navigation path of the AGV is adjusted based on the position spaces between the multiple obstacles, and the AGV passes through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image;

[0009] In a second traversal, the second image is monitored, and the shape of each obstacle in the second image is extracted to obtain a blank area of ​​the obstacle;

[0010] The replenishment operation of the AGV is triggered based on the blank area, and the path adjustment is performed based on the navigation path of the second traversal to complete the replenishment of the area during the second traversal.

[0011] In addition, an embodiment of the present invention further provides an AGV system, the AGV system comprising: a path module: used for performing path traversal based on the navigation path of the AGV;

[0012] An acquisition module: used for, during the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes a first shape of a plurality of the obstacles and a spacing distance between the plurality of the obstacles;

[0013] Annotation module: used to locate the positions and distances of the plurality of obstacles to the current map, and to annotate the corresponding position points on the navigation path of the AGV;

[0014] Conversion module: used for triggering the second traversal of the AGV when the location point is marked on the current map, and converting the map-building state to the working state, wherein the AGV can expand the current map based on the external environment when in the map-building state;

[0015] Detection module: used for adjusting the navigation path of the AGV based on the position space between the multiple obstacles during the second traversal, and passing through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image;

[0016] Monitoring module: used for monitoring the second image in the second traversal, and extracting the shape of each obstacle in the second image to obtain the blank area of ​​the obstacle;

[0017] Adjustment module: used for triggering the supplementation operation of the AGV based on the blank area, and performing path adjustment based on the navigation path of the second traversal to complete the supplementation of the area during the second traversal.

[0018] In an embodiment of the present invention, through the method in the embodiment of the present invention, the obstacles and maps are gradually refined based on multiple path traversals of the AGV, and the previous traversal path is adjusted during each traversal to facilitate the refined path operation based on the gradually clarified obstacles, and multiple obstacles are synchronously detected in the second traversal to improve the work efficiency of obstacle detection. In addition, the blank areas are supplemented in the third traversal to avoid missed detection of obstacles, improve the blank areas of obstacles, and improve the detection efficiency and detection accuracy of the AGV. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of a path planning method based on AGV in an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of the structure of the AGV system in the embodiment of the present invention;

[0022] Figure 3 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example

[0025] See also Figure 1 , Figure 1 It is a flow chart of the AGV-based path planning method in an embodiment of the present invention.

[0026] like Figure 1 As shown, a path planning method based on AGV, the method comprising:

[0027] S11: Path traversal based on the navigation path of the AGV;

[0028] In the specific implementation process of the present invention, the specific steps may be: obtaining the outer contour space of the indoor environment; forming the navigation path based on multiple corners of the outer contour space, wherein the navigation path extends along adjacent corners to form a closed-loop path; performing path optimization based on the navigation path, and performing path reconstruction for repeated areas in the navigation path to form a single-direction path; associating the two single-direction paths to the navigation path, and performing path traversal based on the navigation path.

[0029] Among them, the navigation path is planned based on the outer contour space of the indoor environment. The navigation path is extended based on the layout of multiple corners and forms a closed-loop path, so that the AGV can cover all the corners of the outer contour space of the indoor environment on the closed-loop path and facilitate turning at angles.

[0030] In addition, path optimization is performed based on the navigation path, and path reconstruction is performed on repeated areas in the navigation path to form a path in a single direction, thereby reducing repeated driving on repeated paths and improving the driving effect of the AGV. In addition, the navigation path as a whole is associated with the path in a single direction, and the overlapping areas are replaced to achieve driving in a single direction.

[0031] S12: During the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes first shapes of a plurality of the obstacles and interval distances between the plurality of the obstacles;

[0032] In the specific implementation process of the present invention, the specific steps may be: performing a first traversal based on the navigation path, at which time the AGV gradually approaches the obstacle; the AGV calculates the first speed based on the detection area of ​​the obstacle; when the distance between the AGV and the obstacle meets the threshold, the speed of the AGV is gradually adjusted toward the first speed, and when the AGV's speed meets the first speed, it moves along the outer periphery of the obstacle; the AGV detects the obstacle during driving and avoids the obstacle, wherein the AGV circles around the obstacle based on an extended virtual line and moves in the opposite direction when touching the extended virtual line to move away from the obstacle; based on the detection of the AGV relative to the obstacle, a first image is constructed along the texture of the obstacle, wherein the first image includes a first shape of a plurality of the obstacles and the spacing distances between the plurality of the obstacles.

[0033] Among them, the first speed is calculated according to the detection area of ​​the obstacle, and the driving speed of the AGV can be controlled on the detection area, so as to improve the driving effect of the AGV; the AGV detects the obstacle during driving and avoids the obstacle, wherein the AGV circles around the extended virtual line of the obstacle as a reference, and moves in the opposite direction when touching the extended virtual line to stay away from the obstacle, thereby ensuring that the AGV does not collide with the obstacle when detecting the obstacle, avoiding the movement of the obstacle, so as to improve the position accuracy of the obstacle in the map.

[0034] Also, based on the detection of the AGV relative to the obstacle, a first image is constructed along the texture of the obstacle, wherein the first image includes first shapes of multiple obstacles and spacing distances between multiple obstacles.

[0035] S13: locating the positions and distances of the plurality of obstacles to the current map, and marking corresponding position points on the navigation path of the AGV;

[0036] In the specific implementation process of the present invention, the specific steps may be: constructing a blank map based on the outer contour space of the indoor environment; calibrating the blank map according to the navigation path, and expanding the blank map; adding the first image to the blank map, and locating the obstacles in the first image to the blank map to form the current map; marking the corresponding position points on the navigation path of the AGV and displaying them on the current map; marking the distances between multiple obstacles on the current map, and limiting the space between multiple obstacles to form a limited area; performing local calculations on the limited area to determine the moving path of the AGV within the limited area.

[0037] Among them, obstacles are added to a blank map, and the blank map is updated in real time to form a current map. At this time, the corresponding location points are marked on the navigation path of the AGV and displayed on the current map. By comparing the obstacles on the map, the distances between multiple obstacles can be obtained, and the area is limited based on the space between the multiple obstacles to form a limited area; the limited area is locally calculated to determine the movement path of the AGV in the limited area, thereby ensuring the movement between multiple obstacles.

[0038] S14: When the location point is marked on the current map, triggering the second traversal of the AGV, and converting from the map-building state to the working state, wherein the AGV can expand the current map based on the external environment when in the map-building state;

[0039] In the specific implementation process of the present invention, the specific steps may be: when the current map is marked with the location point, the second traversal of the AGV is triggered, and at this time, the AGV is adjusted from the first traversal to the second traversal; the AGV completes the operation in the mapping state based on the current map, wherein the AGV can expand the current map based on the external environment when it is in the mapping state; the AGV is converted from the mapping state to the working state, and in the working state, it improves the obstacle shape of the current map; the obstacle shape of the current map is triggered, and the editing area of ​​the obstacle shape is unlocked, and the editing area is dynamically adjusted with the dynamic detection of the AGV, and at this time, the speed of the AGV is the second speed, and the second speed is less than the first speed.

[0040] Among them, the AGV uses multiple traversals relative to the obstacle, completes its own transfer movement in different traversals, and performs multi-level refinement on the obstacle. At this time, when the location point is marked on the current map, the second traversal of the AGV is triggered, and the obstacle shape of the current map is improved in the second traversal to achieve the expansion of the obstacle shape of the current map.

[0041] In addition, the obstacle shape of the current map is triggered, and the editing area of ​​the obstacle shape is unlocked. The editing area is dynamically adjusted with the dynamic detection of the AGV. At this time, the speed of the AGV is the second speed, which is less than the first speed. By adjusting different speeds, the AGV can detect obstacles on different paths and ensure the editing of the obstacle shape.

[0042] S15: During the second traversal, the navigation path of the AGV is adjusted based on the position spaces between the multiple obstacles, and the AGV passes through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image;

[0043] In the specific implementation process of the present invention, the specific steps include: during the second traversal, dividing the position space between multiple obstacles into multiple adjacent grids; obtaining the area of ​​the position space based on the calculation of multiple grids; determining the navigation path of the AGV according to the area, and adjusting the guide rail direction of the AGV along the line direction of the grid, and adjusting the navigation path of the AGV; passing between multiple obstacles based on the navigation path of the AGV to synchronously detect multiple obstacles and form a second image, which further refines the obstacles based on the first image.

[0044] The AGV passes through multiple obstacles in the second traversal and detects multiple obstacles synchronously to synchronously acquire the shapes of multiple obstacles, thereby obtaining a second image, further refining the obstacles on the second image, improving the degree of obstacle refinement, and improving the refinement efficiency in synchronous acquisition.

[0045] S16: In the second traversal, the second image is monitored, and the shape of each obstacle in the second image is extracted to obtain the blank area of ​​the obstacle.

[0046] In the specific implementation process of the present invention, the specific steps include: in the second traversal, monitoring the second image and dividing the second image into regions; freezing the region corresponding to the shape of the obstacle in the second image, and traversing the edge region to obtain a blank space; extending based on the blank space to form a blank area of ​​the obstacle; obtaining an extended line of the second image according to the edge of the blank area; adjusting the supplementary direction of the blank area based on the extension direction of the extended line, and serving as a positioning part.

[0047] Among them, the missing area of ​​the obstacle is determined based on the blank area, and the obstacle is supplemented by extending and filling the blank area to improve the obstacle. The AGV performs a supplement operation based on the blank area, and adjusts the supplement direction of the blank area based on the extension direction of the extension line, and serves as a positioning part.

[0048] S17: triggering a supplement operation of the AGV based on the blank area, and adjusting the path based on the navigation path of the second traversal to complete the supplement of the area during the second traversal.

[0049] In the specific implementation process of the present invention, the specific steps include: triggering the supplement operation of the AGV based on the blank area, wherein the structural part of the obstacle is detected along the boundary of the blank area; adjusting the supplement starting point of the AGV according to the structural part of the obstacle; and adjusting the path based on the supplement starting point of the AGV and the navigation path of the second traversal to expand the content of the blank area.

[0050] The method also includes acquiring a partial image as the path of the AGV is adjusted during the second traversal; determining an image of a blank area based on a comparison between the partial image and the positioning part, and supplementing the blank area.

[0051] In an embodiment of the present invention, through the method in the embodiment of the present invention, the obstacles and maps are gradually refined based on multiple path traversals of the AGV, and the previous traversal path is adjusted during each traversal to facilitate the refined path operation based on the gradually clarified obstacles, and multiple obstacles are synchronously detected in the second traversal to improve the work efficiency of obstacle detection. In addition, the blank areas are supplemented in the third traversal to avoid missed detection of obstacles, improve the blank areas of obstacles, and improve the detection efficiency and detection accuracy of the AGV.

[0052] Example

[0053] See also Figure 2 , Figure 2 It is a schematic diagram of the structural composition of the AGV system in an embodiment of the present invention.

[0054] like Figure 2 As shown, an AGV system, the AGV system comprises:

[0055] Path module 21: used for path traversal based on the navigation path of the AGV;

[0056] Acquisition module 22: used for, during the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes first shapes of a plurality of the obstacles and interval distances between the plurality of the obstacles;

[0057] The marking module 23 is used to locate the positions and distances of the plurality of obstacles to the current map, and mark the corresponding position points on the navigation path of the AGV;

[0058] Conversion module 24: used for triggering the second traversal of the AGV when the location point is marked on the current map, and converting the map-building state to the working state, wherein the AGV can expand the current map based on the external environment when in the map-building state;

[0059] Detection module 25: used for adjusting the navigation path of the AGV based on the position space between the multiple obstacles during the second traversal, and passing through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image;

[0060] Monitoring module 26: used for monitoring the second image in the second traversal, and extracting the shape of each obstacle in the second image to obtain the blank area of ​​the obstacle;

[0061] The adjustment module 27 is used to trigger the supplementation operation of the AGV based on the blank area, and to adjust the path based on the navigation path of the second traversal, so as to complete the supplementation of the area during the second traversal.

[0062] The present invention provides a path planning method and system based on AGV, which realizes the gradual refinement of obstacles and maps based on multiple path traversals of AGV, and adjusts the previous traversal path during each traversal to facilitate the refined path operation based on gradually clarified obstacles, and completes the synchronous detection of multiple obstacles in the second traversal to improve the working efficiency of obstacle detection. In addition, the blank area is supplemented in the third traversal to avoid missed detection of obstacles, improve the blank area of ​​obstacles, and improve the detection efficiency and detection accuracy of AGV.

[0063] Example

[0064] See also Figure 3 , refer to the following Figure 3 The electronic device 40 according to this embodiment of the present invention will be described. Figure 3 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0065] like Figure 3 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0066] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0067] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0068] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0069] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0070] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 45. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 46. Figure 3 As shown, the network adapter 46 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0071] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0072] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0073] In addition, the AGV-based path planning method and system provided in the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A path planning method based on AGV, characterized in that: include: Path traversal based on the navigation path of AGV; During the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes first shapes of a plurality of the obstacles and interval distances between the plurality of the obstacles; Locate the positions and distances of the plurality of obstacles to the current map, and mark the corresponding position points on the navigation path of the AGV; When the location point is marked on the current map, the second traversal of the AGV is triggered, and the mapping state is converted to the working state, wherein the AGV can expand the current map based on the external environment when in the mapping state; During the second traversal, the navigation path of the AGV is adjusted based on the position spaces between the multiple obstacles, and the AGV passes through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image; In a second traversal, the second image is monitored, and the shape of each obstacle in the second image is extracted to obtain a blank area of ​​the obstacle; Triggering a supplement operation of the AGV based on the blank area, and adjusting the path based on the navigation path of the second traversal to complete the supplement of the area during the second traversal; In the second traversal, monitoring the second image and extracting the shape of each obstacle in the second image to obtain a blank area of ​​the obstacle includes: In a second traversal, monitoring the second image, and dividing the second image into regions; Freezing an area corresponding to the shape of the obstacle in the second image, and traversing edge areas to obtain blank areas; Extending based on the blank area to form a blank area of ​​the obstacle; Acquire an extended line of the second image according to the edge of the blank area; adjusting the supplement direction of the blank area based on the extension direction of the extension line and serving as a positioning part; The triggering of the supplement operation of the AGV based on the blank area and adjusting the path based on the navigation path of the second traversal to complete the supplement of the area during the second traversal includes: triggering a supplementary operation of the AGV based on the blank area, wherein a structural portion of the obstacle is detected along a boundary of the blank area; adjusting the supplementary starting point of the AGV according to the structural part of the obstacle; A path adjustment is performed based on the supplementary starting point of the AGV and the navigation path of the second traversal to expand the content of the blank area.

2. The AGV-based path planning method according to claim 1, characterized in that: The path traversal based on the navigation path of the AGV includes: Get the outer contour space of the indoor environment; forming the navigation path based on a plurality of corners of the outer contour space, wherein the navigation path is extended along adjacent corners to form a closed loop path; Performing path optimization based on the navigation path, and performing path reconstruction for repeated areas in the navigation path to form a path in a single direction; The two single-direction paths are associated with the navigation path, and path traversal is performed based on the navigation path.

3. The AGV-based path planning method according to claim 2, characterized in that: During the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes a first shape of a plurality of the obstacles and a spacing distance between the plurality of the obstacles, including: Performing a first traversal based on the navigation path, at which time, the AGV gradually approaches the obstacle; The AGV calculates the first speed based on the detection area of ​​the obstacle; When the distance between the AGV and the obstacle meets a threshold, the speed of the AGV is gradually adjusted toward the first speed, and the AGV moves along the outer periphery of the obstacle when its speed meets the first speed; The AGV detects the obstacle during its travel and avoids the obstacle, wherein the AGV circles around the obstacle based on an extended virtual line and moves in the opposite direction when touching the extended virtual line to stay away from the obstacle; Based on the detection of the AGV relative to the obstacle, a first image is constructed along the pattern of the obstacle, wherein the first image includes first shapes of multiple obstacles and interval distances between multiple obstacles.

4. The AGV-based path planning method according to claim 3, characterized in that: The positioning of the positions and distances of the plurality of obstacles to the current map and marking corresponding position points on the navigation path of the AGV includes: Constructing a blank map based on the outer contour space of the indoor environment; calibrating the blank map according to the navigation path, and performing map expansion on the blank map; The first image is added to the blank map, and the obstacles in the first image are located on the blank map to form the current map; Marking corresponding location points on the navigation path of the AGV and displaying them on the current map; Marking the distances between the multiple obstacles on the current map, and limiting the space between the multiple obstacles to form a limited area; A local calculation is performed on the limited area to determine a moving path of the AGV in the limited area.

5. The AGV-based path planning method according to claim 4, characterized in that: When the location point is marked on the current map, the second traversal of the AGV is triggered, and the mapping state is converted into the working state, wherein the AGV can expand the current map based on the external environment when in the mapping state, including: When the location point is marked on the current map, the second traversal of the AGV is triggered, and at this time, the AGV is adjusted from the first traversal to the second traversal; The AGV completes the operation in the mapping state based on the current map, wherein the AGV can expand the current map based on the external environment when in the mapping state; The AGV is transformed from a mapping state to a working state, and improves the obstacle shape of the current map in the working state.

6. The AGV-based path planning method according to claim 5, characterized in that: During the second traversal, the navigation path of the AGV is adjusted based on the position space between the plurality of obstacles, and the AGV passes through the plurality of obstacles to synchronously detect the plurality of obstacles and form a second image, wherein the second image further refines the obstacles based on the first image, including: During the second traversal, a plurality of adjacent grids are divided based on the position space between the plurality of obstacles; Obtaining the area of ​​the position space based on calculations of multiple grids; Determine a navigation path of the AGV according to the area, adjust the guide rail direction of the AGV along the line direction of the grid, and adjust the navigation path of the AGV; Based on the navigation path of the AGV passing through the multiple obstacles, the multiple obstacles are synchronously detected and a second image is formed. The second image further refines the obstacles based on the first image.

7. The AGV-based path planning method according to claim 6, characterized in that: The method of triggering the supplement operation of the AGV based on the blank area and adjusting the path based on the navigation path of the second traversal to complete the supplement of the area during the second traversal also includes: Acquiring a partial image as the path of the AGV is adjusted during the second traversal; Based on the comparison between the partial image and the positioning portion, the image of the blank area is determined, and the blank area is supplemented.

8. An AGV system, characterized in that: The AGV system includes: Path module: used for path traversal based on the navigation path of AGV; An acquisition module: used for, during the first traversal, the AGV moves along the outer periphery of the obstacle at a first speed and acquires a first image, wherein the first image includes a first shape of a plurality of the obstacles and the interval distances between the plurality of the obstacles; Annotation module: used to locate the positions and distances of the plurality of obstacles to the current map, and to annotate the corresponding position points on the navigation path of the AGV; Conversion module: used for triggering the second traversal of the AGV when the location point is marked on the current map, and converting the map-building state to the working state, wherein the AGV can expand the current map based on the external environment when in the map-building state; Detection module: used for adjusting the navigation path of the AGV based on the position space between the multiple obstacles during the second traversal, and passing through the multiple obstacles to synchronously detect the multiple obstacles and form a second image, wherein the second image further refines the obstacles based on the first image; Monitoring module: used for monitoring the second image in the second traversal, and extracting the shape of each obstacle in the second image to obtain the blank area of ​​the obstacle; An adjustment module: used for triggering a supplement operation of the AGV based on the blank area, and performing a path adjustment based on the navigation path of the second traversal, so as to complete the supplement of the area during the second traversal; In the second traversal, monitoring the second image and extracting the shape of each obstacle in the second image to obtain a blank area of ​​the obstacle includes: In a second traversal, monitoring the second image, and dividing the second image into regions; Freezing an area corresponding to the shape of the obstacle in the second image, and traversing edge areas to obtain blank areas; Extending based on the blank area to form a blank area of ​​the obstacle; Acquire an extended line of the second image according to the edge of the blank area; adjusting the supplement direction of the blank area based on the extension direction of the extension line and serving as a positioning part; The triggering of the supplement operation of the AGV based on the blank area and adjusting the path based on the navigation path of the second traversal to complete the supplement of the area during the second traversal includes: triggering a supplementary operation of the AGV based on the blank area, wherein a structural portion of the obstacle is detected along a boundary of the blank area; adjusting the supplementary starting point of the AGV according to the structural part of the obstacle; A path adjustment is performed based on the supplementary starting point of the AGV and the navigation path of the second traversal to expand the content of the blank area.

Images