Obstacle Recognition Method and Device, Storage Medium, and Electronic Device

Abstract

The present application provides an obstacle recognition method and apparatus, a storage medium, and an electronic device. The method includes: projecting the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot; determining whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes first laser points; and determining the type of the obstacle according to the distribution of the first laser points in each grid on the grid map when it is determined that there is an obstacle in the target scene. By adopting the above technical solution, the problem of low accuracy of robot obstacle recognition in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of robots, and in particular, to an obstacle recognition method, an apparatus, a storage medium, and an electronic device.

Background Art

[0002] When a robot is working, it is necessary to identify and avoid obstacles encountered during work. Currently, generally, the laser point cloud information obtained from a structured light sensor installed in the robot is converted into three-dimensional information, and the type of obstacle is distinguished by the converted three-dimensional information. However, due to the influence of light, a part of inaccurate laser point cloud is obtained. When the laser point cloud information is converted into three-dimensional information, these inaccurate laser point clouds will affect the conversion result of the three-dimensional information, resulting in incorrect obstacle classification. If there is an incorrect obstacle classification, it may cause the robot to crush items that should not be passed through or not clean areas that should be cleaned.

[0003] It can be seen that the obstacle recognition method of the robot in the related art has the problem of low accuracy in identifying obstacles by the robot.

Summary of the Invention

[0004] The purpose of the present application is to provide an obstacle recognition method, an apparatus, a storage medium, and an electronic device, so as to at least solve the problem of low accuracy in identifying obstacles by the robot in the obstacle recognition method of the related art.

[0005] The purpose of the present application is achieved by the following technical solutions:

[0006] According to one aspect of the embodiments of the present application, an obstacle recognition method is provided, including: projecting the obtained first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot; determining whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; and determining the type of the obstacle according to the distribution of the first laser points in each grid on the grid map when it is determined that there is an obstacle in the target scene.

[0007] In an exemplary embodiment, determining whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map includes: obtaining the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; if the number of the first laser points on each grid in the grid map is less than a first quantity threshold, determining that there is no such obstacle in the target scene; otherwise, determining that there is such an obstacle in the target scene.

[0008] In an exemplary embodiment, when it is determined that there is an obstacle in the target scene, determining the type of the obstacle according to the distribution of the first laser points in each grid on the grid map includes: obtaining the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; determining the grids in the grid map where the number of the first laser points is greater than or equal to the first quantity threshold as obstacle grids; determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid.

[0009] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid includes: when the number of first target laser points in the obstacle grid is greater than or equal to a second quantity threshold, obtaining a second laser point cloud collected in the target scene by a second acquisition device, where the first target laser points are the first laser points in the obstacle grid whose height coordinates are greater than a first preset height coordinate; projecting the second laser point cloud onto the grid map; when there are second laser points on the obstacle grid, determining the type of the obstacle corresponding to the obstacle grid as a high-type obstacle.

[0010] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid further includes: when the number of second target laser points in the obstacle grid is greater than or equal to a third quantity threshold and the number of third target laser points is less than or equal to a fourth quantity threshold, determining the type of the obstacle corresponding to the obstacle grid as a suspended-type obstacle, where the second target laser points are the first laser points in the obstacle grid whose height coordinates are greater than or equal to a second preset height coordinate, and the third target laser points are the first laser points in the obstacle grid whose height coordinates are less than the second preset height coordinate.

[0011] In an exemplary embodiment, the above method further includes: when there is no second laser point on the obstacle grid, determining that there is no such obstacle at the position corresponding to the obstacle grid in the target scene.

[0012] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid according to the height coordinate of the first laser point in the obstacle grid includes: when the number of fourth target laser points in the obstacle grid is greater than or equal to a fifth quantity threshold and the number of fifth target laser points is less than or equal to a sixth quantity threshold, determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle, where the fourth target laser point is the first laser point in the obstacle grid whose height coordinate is less than or equal to a third preset height coordinate, and the fifth target laser point is the first laser point in the obstacle grid whose height coordinate is greater than the third preset height coordinate.

[0013] In an exemplary embodiment, after determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle, the method further includes: clustering the obstacle grids in the grid map to obtain an obstacle grid set; when the obstacle grids in the obstacle grid set satisfy the step cross-section feature and the straightness and length of the obstacle grids in the obstacle grid set meet the preset conditions, determining the type of the obstacle corresponding to the obstacle grid set as a step-type obstacle.

[0014] In an exemplary embodiment, after determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle, the method further includes: clustering the obstacle grids in the grid map to obtain an obstacle grid set; when the obstacle grids in the obstacle grid set satisfy the line-type cross-section feature, determining the type of the obstacle corresponding to the obstacle grid set as a line-type obstacle.

[0015] According to another aspect of the embodiments of the present application, there is also provided an obstacle recognition device, including: a projection unit, configured to project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot; a first determination unit, configured to determine whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a second determination unit, configured to, when it is determined that there is an obstacle in the target scene, determine the type of the obstacle according to the distribution of the first laser points in each grid on the grid map.

[0016] In an exemplary embodiment, the above-mentioned first determination unit includes: a first acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a first determination module, configured to, if the number of the first laser points on each grid in the grid map is less than a first quantity threshold, determine that there is no such obstacle in the target scene; otherwise, determine that there is such an obstacle in the target scene.

[0017] In an exemplary embodiment, the above-mentioned second determination unit includes: a second acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a second determination module, including: determining the grids in the grid map where the number of first laser points is greater than or equal to the first quantity threshold as obstacle grids; a third determination module, configured to determine the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid.

[0018] In an exemplary embodiment, the above-mentioned third determination module includes: a first acquisition sub-module, configured to, when the number of first target laser points in the obstacle grid is greater than or equal to a second quantity threshold, acquire a second laser point cloud collected by a second acquisition device in the target scene, where the first target laser points are the first laser points in the obstacle grid whose height coordinates are greater than a first preset height coordinate; a projection sub-module, configured to project the second laser point cloud onto the grid map; a first determination sub-module, configured to, when there are second laser points on the obstacle grid, determine the type of the obstacle corresponding to the obstacle grid as a high-type obstacle.

[0019] In an exemplary embodiment, the above-mentioned third determination module further includes: a second determination sub-module, configured to determine the type of the obstacle corresponding to the obstacle grid as a suspended type obstacle when the number of second target laser points in the obstacle grid is greater than or equal to a third quantity threshold and the number of third target laser points is less than or equal to a fourth quantity threshold, where the second target laser points are the first laser points in the obstacle grid whose height coordinates are greater than or equal to a second preset height coordinate, and the third target laser points are the first laser points in the obstacle grid whose height coordinates are less than the second preset height coordinate.

[0020] In an exemplary embodiment, the above-mentioned first determination sub-module is further configured to determine that there is no such obstacle at the position corresponding to the obstacle grid in the target scene when there is no such second laser point on the obstacle grid.

[0021] In an exemplary embodiment, the above-mentioned third determination module includes: a third determination sub-module, configured to determine the type of the obstacle corresponding to the obstacle grid as a low type obstacle when the number of fourth target laser points in the obstacle grid is greater than or equal to a fifth quantity threshold and the number of fifth target laser points is less than or equal to a sixth quantity threshold, where the fourth target laser points are the first laser points in the obstacle grid whose height coordinates are less than or equal to a third preset height coordinate, and the fifth target laser points are the first laser points in the obstacle grid whose height coordinates are greater than the third preset height coordinate.

[0022] In an exemplary embodiment, the above-mentioned device further includes: a first clustering module, configured to cluster the obstacle grids in the grid map to obtain an obstacle grid set after determining the type of the obstacle corresponding to the obstacle grid as a low type obstacle; a fourth determination module, configured to determine the type of the obstacle corresponding to the obstacle grid set as a step type obstacle when the obstacle grids in the obstacle grid set satisfy the step cross-section feature and the straightness and length of the obstacle grids in the obstacle grid set meet preset conditions.

[0023] In an exemplary embodiment, the above-mentioned device further includes: a second clustering module, configured to cluster the obstacle grids in the grid map to obtain an obstacle grid set after determining the type of the obstacle corresponding to the obstacle grid as a low type obstacle; a fifth determination module, configured to determine the type of the obstacle corresponding to the obstacle grid set as a line type obstacle when the obstacle grids in the obstacle grid set satisfy the line-like cross-section feature.

[0024] According to another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the above-mentioned obstacle recognition method when running.

[0025] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the above-mentioned processor executes the above-mentioned obstacle recognition method through the computer program.

[0026] In the embodiments of the present application, a first laser point cloud is formed by projecting a double-line structured light onto a target scene, and the first laser point cloud is projected onto a grid map. According to the number of first laser points on each grid in the grid map, it is determined whether there are obstacles in the target scene. In the case where it is determined that there are obstacles in the target scene, the type of the obstacle is determined according to the distribution of the first laser points in each grid on the grid map.

[0027] In the prior art, a small number of inaccurate laser points are generated due to the influence of light and are relatively scattered. However, in the present application, the first laser point cloud formed by projecting the double-line structured light onto the target scene is projected onto the grid map, so that the number of inaccurate laser points included in each grid of the grid map is small, the influence on judging the type of the obstacle is small, and the accuracy is higher. Furthermore, the problem of low accuracy of obstacle recognition by robots in the obstacle recognition method of related technologies is solved, and the accuracy of obstacle recognition by robots is improved.

Description of the Drawings

[0028] The drawings here are incorporated into the specification and form a part of this specification, showing the embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0030] Figure 1 is a schematic diagram of the hardware environment of an optional obstacle recognition method according to the embodiments of the present application;

[0031] Figure 2 is a schematic flowchart of an optional obstacle recognition method according to the embodiments of the present application;

[0032] Figure 3 is a schematic diagram of an optional robot passing through a suspended obstacle according to the embodiments of the present application;

[0033] Figure 4 is a structural block diagram of an optional obstacle recognition device according to an embodiment of the present application;

[0034] Figure 5 is a structural block diagram of an optional electronic device according to an embodiment of the present application.

Specific Embodiments

[0035] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence.

[0037] According to one aspect of the embodiments of the present application, an obstacle recognition method is provided. Optionally, in this embodiment, Figure 1 is a schematic diagram of the hardware environment of an optional obstacle recognition method according to an embodiment of the present application. The above-mentioned obstacle recognition method can be applied to, for example, Figure 1 the hardware environment composed of the robot 102 and the server 104 as shown. As Figure 1 shown, the robot 102 can be connected to the server 104 (for example, an Internet of Things platform or a cloud server) through a network to control the robot 102.

[0038] The above-mentioned network can include, but is not limited to, at least one of the following: a wired network, a wireless network. The above-mentioned wired network can include, but is not limited to, at least one of the following: a wide area network, a metropolitan area network, a local area network. The above-mentioned wireless network can include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity), Bluetooth, infrared. The robot 102 can include, but is not limited to: a sweeping robot, for example, an automatic mopping robot, a self-cleaning robot, etc. The server 104 can be a server of an Internet of Things platform.

[0039] The obstacle recognition method of the embodiments of the present application can be executed independently by the robot 102 or the server 104, or can be jointly executed by the robot 102 and the server 104. Among them, when the robot 102 executes the obstacle recognition method of the embodiments of the present application, it can also be executed by a client installed thereon.

[0040] Taking the execution of the obstacle recognition method in this embodiment by the server 104 as an example, Figure 2 is a schematic flow diagram of an optional obstacle recognition method according to an embodiment of the present application. AsFigure 2 As shown, the process of this method may include the following steps:

[0041] Step S202: Project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to the target scene, the first laser point cloud is a point cloud formed by projecting double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is arranged on a target robot;

[0042] The obstacle recognition method in this embodiment can be applied to scenarios where obstacles in the target scene are recognized, and then the robot is controlled to avoid the obstacles. The above-mentioned robot can be a sweeping robot, and its corresponding target scene can be the area to be cleaned, which is not limited here.

[0043] Optionally, the first acquisition device in this embodiment is a double-line structured light sensor. The robot is equipped with a double-line structured light sensor to explore the target scene by emitting double-line structured light. The double-line structured light is projected onto an object in the target scene to form a laser point cloud. The laser point cloud is collected by an infrared camera in the double-line structured light sensor or by other infrared cameras. Various information of the object, such as the position and depth information of the object, can be calculated through the characteristics of the laser points.

[0044] Optionally, the above-mentioned first acquisition device includes a laser for projecting double-line structured light and a camera for collecting the laser point cloud.

[0045] Optionally, when the robot enters a new environment, a map is generated according to the actual scene, and the map is divided into multiple small squares of the same size. Each small square becomes a grid. The size of the grid is generally determined by the size of the robot, which can be 1cm * 1cm or 10cm * 10cm, and is not limited here.

[0046] In this embodiment, the first laser point cloud obtained by the double-line structured light sensor is projected onto the grid map. When the grid map is divided, the grid is divided according to the ground coordinates (x, y). The coordinates of the laser points in the first laser point cloud are three-dimensional coordinates (x, y, z). The laser points are projected onto the corresponding grids according to the x coordinate and the y coordinate.

[0047] Step S204: Determine whether there are obstacles in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points;

[0048] In this embodiment, after the first laser point cloud is projected onto the grid map, first, based on the first laser point cloud in the grid, it is determined whether there are obstacles. If there are obstacles, the type of the obstacles is further determined. If there are no obstacles, the robot can pass directly.

[0049] Step S206, in the case where it is determined that there are obstacles in the target scene, determine the type of the obstacles according to the distribution of the first laser points in each grid on the grid map.

[0050] Optionally, some obstacles can be crossed by the robot without obstacle avoidance, while some obstacles cannot be crossed by the robot and obstacle avoidance actions need to be taken. Therefore, when there are obstacles, the type of the obstacles needs to be determined.

[0051] Through the above steps S202 to S206, the first laser point cloud collected by the first acquisition device that emits structured light by emitting light rays in the target scene is obtained, and the first laser point cloud is projected onto the grid map, where the grid map is a map generated according to the target scene; according to the first laser point cloud on the grid map, it is determined whether there are obstacles in the target scene; in the case where it is determined that there are obstacles in the target scene, determine the type of the obstacles according to the first laser point cloud on the grid map.

[0052] Since there is inaccurate laser point cloud affected by ambient light in the collected first laser point cloud, in the prior art, when converting the first laser point cloud into three-dimensional information, due to the influence of inaccurate laser points, the three-dimensional information is inaccurate when the laser point cloud is converted into three-dimensional information, so that the type of obstacles judged through the three-dimensional information will be inaccurate. In this embodiment, by projecting the laser point cloud onto the grid map, because the inaccurate laser points are not concentrated, there are only a few scattered inaccurate laser points falling into a single grid in the grid map after projection, which has little influence on judging the type of obstacles in a single grid, solving the problem that the obstacle recognition method of the robot in the related art has low accuracy in recognizing obstacles, and improving the accuracy of the robot in recognizing obstacles.

[0053] Specifically, if there are obstacles in a grid, there will be a large number of first laser points (accurate laser points). Even if there are inaccurate laser points, relying on the distribution of most laser points to judge the type of obstacles in this grid, the influence of inaccurate laser points is small; if there are no obstacles in a grid and there are inaccurate laser points, because the number is small, it will not be recognized as an obstacle grid, and the type of obstacles will not be further determined, excluding the influence of inaccurate laser points. Therefore, through the method in this embodiment, the interference of ambient light on the double-line structured light is excluded, and the influence of inaccurate laser points is obtained, thereby improving the accuracy of the robot in recognizing obstacles.

[0054] In an exemplary embodiment, it is determined whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points, including: obtaining the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; if the number of first laser points on each grid in the grid map is less than a first quantity threshold, it is determined that there is no such obstacle in the target scene; otherwise, it is determined that there is such an obstacle in the target scene.

[0055] In this embodiment, after the first laser point cloud is projected onto the grid map, the first laser points in the first laser point cloud are projected into the corresponding grids according to their coordinates. To determine whether there is an obstacle in the target scene, first, it is determined whether there is an obstacle on each grid in the grid map. If there is an obstacle in a grid, then the number of first laser points contained in this grid must be greater than or equal to a certain threshold (i.e., the above-mentioned first quantity threshold). Otherwise, if the number of first laser points contained in this grid is less than a certain threshold, then there is no obstacle in this grid.

[0056] After determining whether there is an obstacle in the grids of the grid map, it is determined whether there is still an obstacle in the target scene represented by the grid map based on the combination of individual grids. If there is no obstacle in all grids of the grid map, it is determined that there is no obstacle in the above-mentioned target scene. On the contrary, as long as there is at least one grid in the grids of the grid map where there is an obstacle, it is determined that there is an obstacle in the above-mentioned target scene.

[0057] Through this embodiment, it is further determined whether there is an obstacle in the target scene by whether there is an obstacle in a single grid. Before analyzing the type of obstacle, it is first confirmed whether there is an obstacle type, which improves the efficiency of the machine in recognizing obstacles and avoids analyzing the obstacle category when there is no obstacle in the target scene.

[0058] In an exemplary embodiment, when it is determined that there is an obstacle in the target scene, the type of the obstacle is determined according to the distribution of the first laser points in each grid on the grid map, including: obtaining the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; determining the grids in the grid map where the number of first laser points is greater than or equal to the first quantity threshold as obstacle grids; determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid.

[0059] In this embodiment, when it is determined that there are already obstacles in the target scenario, all the grid cells containing obstacles are found in the grid map and determined as obstacle grid cells. Then, the type of the obstacle in the obstacle grid cell is determined according to the height coordinate of the first laser point in the obstacle grid cell.

[0060] Specifically, the obstacle types in the target scenario can be initially divided into high obstacles, suspended obstacles, and low obstacles. Among them, for high obstacles, the robot needs to avoid; for suspended obstacles, the suspended height is greater than the height of the robot, and the robot does not need to avoid and can drive slowly over; for low obstacles, the robot can step over the obstacle height of the low obstacle, but stepping over some low obstacles will cause damage to the robot. Therefore, the obstacle types need to be further subdivided.

[0061] Specifically, the coordinates of the first laser points in the first laser point cloud obtained by the double-line structured light are three-dimensional coordinates (x, y, z), where the z coordinate is the coordinate height of the first laser point, and the value of the z coordinate represents the height of the corresponding first laser point from the ground.

[0062] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid cell according to the height coordinate of the first laser point in the obstacle grid cell includes: when the number of first target laser points in the obstacle grid cell is greater than or equal to the second quantity threshold, obtaining a second laser point cloud collected by a second acquisition device in the target scenario, where the first target laser points are the first laser points in the obstacle grid cell whose height coordinates are greater than the first preset height coordinate; projecting the second laser point cloud onto the grid map; when there are second laser points on the obstacle grid cell, determining the type of the obstacle corresponding to the obstacle grid cell as a high-type obstacle.

[0063] In this embodiment, the above-mentioned second acquisition device can be other acquisition devices different from the first acquisition device, such as a lidar sensor or an ultrasonic sensor, etc.

[0064] Taking the above-mentioned second acquisition device as a lidar sensor as an example, for a grid cell in the grid map, when the height coordinate of the first laser point projected in the grid cell conforms to the characteristics of the first laser point corresponding to a high obstacle, further, the second laser point cloud obtained by the lidar sensor is used to assist in verifying whether the corresponding obstacle type in the grid cell is a high obstacle.

[0065] Specifically, a high obstacle is an obstacle that the robot cannot step over. Then the height of the high obstacle must be higher than the maximum height that the robot can step over. Therefore, in the grid corresponding to the high obstacle in the grid map, the height coordinates of a certain number of first laser points are greater than the maximum height that the robot can step over. Therefore, the first laser points in the obstacle grid whose height coordinates are greater than the first preset height (i.e., the maximum height that the robot can step over) are denoted as first target laser points. When the number of first target laser points is greater than or equal to the second quantity threshold, that is, when the height coordinates of a certain number of first laser points are greater than the maximum height that the robot can step over, the above-mentioned obstacle grid is initially identified as a first high obstacle.

[0066] Since the double-line structured light sensor may be affected by ambient light, when irradiating the target obstacle and reflecting, the light rays may deviate, resulting in the deviation of the position of the first laser point in the grid map. To reduce this influence, when initially identifying the above-mentioned obstacle grid as a first high obstacle, the second laser point cloud obtained by the lidar sensor is used to further verify whether the corresponding obstacle type in the grid is a high obstacle.

[0067] Because to further determine the obstacle type in the grid, the second laser point cloud also needs to be projected onto the above-mentioned grid map. In the case where the number of the above-mentioned first target laser points in a grid is greater than or equal to the second quantity threshold, if the above-mentioned grid contains second laser points, the above-mentioned grid is determined as a high obstacle grid; otherwise, the above-mentioned grid is determined as a non-high obstacle grid.

[0068] Optionally, a lidar is installed in the robot, which is a radar system that detects the position, speed and other characteristic quantities of a target by emitting laser beams. Among them, the lidar sensor is installed at a fixed height in the robot and can only obtain second laser points at a fixed height. The lidar sensor can be set at the maximum height (the first preset height) that the robot can step over to assist the double-line structured light sensor in judging the obstacle type. Its working principle is to emit a detection signal (laser beam) to the target, and then compare the received signal (target echo) reflected from the target with the emitted signal. After appropriate processing, relevant information about the target can be obtained, such as target distance, azimuth, height, speed, attitude, and even shape and other parameters, so as to detect, track and identify targets such as airplanes and missiles. It consists of a laser transmitter, an optical receiver, a turntable and an information processing system, etc. The laser transmitter converts the electrical pulse into an optical pulse and emits it. The optical receiver then restores the optical pulse reflected from the target into an electrical pulse and sends it to the display for display (i.e., display in the form of a point cloud).

[0069] Optionally, in the above method, the obstacle grid can be initially identified as the first high obstacle, and all the first high obstacle grids are clustered to obtain the first high obstacle grid set. For each first high obstacle grid in the first high obstacle grid set, it is further divided into a high obstacle grid and a non-high obstacle grid according to the second laser point cloud obtained by the lidar sensor; when the proportion of non-high obstacle grids in the first high obstacle grid set is greater than the first threshold, all the grids in the first high obstacle grid set are determined to be non-high obstacle grids.

[0070] Optionally, when the obstacle type is determined to be a high obstacle, the robot needs to avoid the above high obstacle.

[0071] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid according to the height coordinate of the first laser point in the obstacle grid further includes: when the number of second target laser points in the obstacle grid is greater than or equal to the third quantity threshold and the number of third target laser points is less than or equal to the fourth quantity threshold, determining the type of the obstacle corresponding to the obstacle grid as a suspended type obstacle, where the second target laser point is the first laser point in the obstacle grid whose height coordinate is greater than or equal to the second preset height coordinate, and the third target laser point is the first laser point in the obstacle grid whose height coordinate is less than the second preset height coordinate.

[0072] In this embodiment, for a grid in the grid map, when the height coordinate of the first laser point projected in the above grid conforms to the characteristics of the first laser point corresponding to the suspended obstacle, the corresponding obstacle in the above grid is determined to be a suspended obstacle.

[0073] Optionally, Figure 3 is a schematic diagram of a robot passing through a suspended obstacle according to an optional embodiment of the present application. As Figure 3 shown, the obstacle that the robot can pass through from below the obstacle is a suspended obstacle. Then, for a suspended obstacle located at a height higher than the robot and there is no obstacle between the ground and the height of the robot, that is, in the corresponding grid, above the second preset height, there are many first laser points representing obstacles, and below the second preset height, there are no first laser points or only a small number of first laser points. Therefore, the first laser points in the obstacle grid whose height coordinates are greater than the second preset height (i.e., the height of the robot) are denoted as second target laser points, and the first laser points in the obstacle grid whose height coordinates are less than or equal to the second preset height (i.e., the height of the robot) are denoted as third target laser points. When the number of second target laser points is greater than or equal to the third quantity threshold and the number of third target laser points is less than or equal to the fourth quantity threshold, the above obstacle grid is identified as a suspended obstacle.

[0074] Optionally, when it is determined that the obstacle type is a suspended obstacle, the robot needs to slow down to pass the suspended obstacle ahead to ensure that the robot does not touch the obstacle. When encountering a suspended obstacle, it should stop in time and change the driving direction.

[0075] In an exemplary embodiment, when there is no second laser point on the obstacle grid, it is determined that there is no obstacle at the position corresponding to the obstacle grid in the target scene.

[0076] In an exemplary embodiment, determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid includes: when the number of fourth target laser points in the obstacle grid is greater than or equal to a fifth quantity threshold and the number of fifth target laser points is less than or equal to a sixth quantity threshold, determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle, where the fourth target laser points are the first laser points in the obstacle grid whose height coordinates are less than or equal to a third preset height coordinate, and the fifth target laser points are the first laser points in the obstacle grid whose height coordinates are greater than the third preset height coordinate.

[0077] In this embodiment, the height of the low obstacle is less than or equal to the highest height that the robot can step over. Then, for the grid corresponding to the low obstacle in the grid map, the height coordinates of most of the first laser points are less than or equal to the highest height that the robot can step over. Therefore, the first laser points in the obstacle grid whose height coordinates are less than or equal to the third preset height (i.e., the highest height that the robot can step over) are denoted as fourth target laser points, and the first laser points whose height coordinates are greater than the third preset height are denoted as fifth target laser points. When the number of fourth target laser points is greater than or equal to the fifth quantity threshold and the number of fifth target laser points is less than or equal to the sixth quantity threshold, the above obstacle grid is recognized as a low obstacle.

[0078] Optionally, although the height of the low obstacle allows the robot to step over it, when the robot steps over some low obstacles, it may cause damage to the machine. For example, when the low obstacle is a wire, when the robot steps over it, the wire is easily sucked in by the floor cleaning robot and gets entangled. If it is a wire, it may cause an electrical accident. Therefore, it is necessary to avoid obstacles for wire-like obstacles. Therefore, after confirming that the obstacle is a low obstacle, it is necessary to further classify the type of the low obstacle to determine whether the robot needs to perform an obstacle avoidance operation.

[0079] In an exemplary embodiment, after determining that the type of the obstacle corresponding to the obstacle grid is a low-type obstacle, the method further includes: clustering the obstacle grids in the grid map to obtain an obstacle grid set; when the obstacle grids in the obstacle grid set satisfy the step cross-section feature and the straightness and length of the obstacle grids in the obstacle grid set meet the preset conditions, determining that the type of the obstacle corresponding to the obstacle grid set is a step-type obstacle.

[0080] In this embodiment, since each grid in the grid map is a discrete element, clustering the grids and aggregating the grid combinations corresponding to different obstacles to obtain an obstacle grid set.

[0081] Preferably, the above step cross-section feature may be a shape feature. If the obstacle is a step-like obstacle, then the grid set corresponding to the obstacle in the grid map should present a rectangular shape. When the shape feature of the obstacle grid set after clustering is rectangular and relatively straight and the length exceeds the fuselage, determining that the type of the obstacle corresponding to the obstacle grid set is a step-type obstacle. The above step cross-section feature may also be other features, which are not limited herein.

[0082] It should be noted that when determining that the type of the low obstacle is a step-type obstacle, the robot does not need to avoid obstacles.

[0083] In an exemplary embodiment, after determining that the type of the obstacle corresponding to the obstacle grid is a low-type obstacle, the method further includes: clustering the obstacle grids in the grid map to obtain an obstacle grid set; when the obstacle grids in the obstacle grid set satisfy the line-like cross-section feature, determining that the type of the obstacle corresponding to the obstacle grid set is a line-type obstacle.

[0084] Preferably, the above line-like cross-section feature may be the degree of bending of the obstacle. If the low obstacle is a line-like obstacle, then the grid set corresponding to the low obstacle in the grid map should present a curved shape. The degree of bending of the grid set can be judged according to the continuity and degree of bending of the first laser point cloud, which is not limited herein.

[0085] It should be noted that when determining that the type of the low obstacle is a line-like obstacle, the robot needs to avoid obstacles.

[0086] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0087] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the method described in each embodiment of this application.

[0088] According to another aspect of the embodiments of this application, there is also provided an obstacle recognition device for implementing the above obstacle recognition method. Figure 4 is a structural block diagram of an optional obstacle recognition device according to the embodiments of this application, as Figure 4 shown. The device may include:

[0089] A projection unit 402, configured to project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot; a first determination unit 404, configured to determine whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a second determination unit 406, configured to determine the type of the obstacle according to the distribution of the first laser points in each grid on the grid map when it is determined that there is an obstacle in the target scene.

[0090] In an exemplary embodiment, the above-mentioned first determination unit includes: a first acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a first determination module, configured to determine that there is no obstacle in the target scene if the number of first laser points on each grid in the grid map is less than a first quantity threshold; otherwise, determine that there is an obstacle in the target scene.

[0091] In an exemplary embodiment, the above-mentioned second determination unit includes: a second acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; a second determination module, including: determining a grid in the grid map where the number of first laser points is greater than or equal to the first quantity threshold as an obstacle grid; a third determination module, configured to determine the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid.

[0092] In an exemplary embodiment, the above-mentioned third determination module includes: a first acquisition sub-module, configured to acquire a second laser point cloud collected by a second acquisition device in the target scene when the number of first target laser points in the obstacle grid is greater than or equal to a second quantity threshold, where the first target laser points are the first laser points in the obstacle grid whose height coordinates are greater than a first preset height coordinate; a projection sub-module, configured to project the second laser point cloud onto the grid map; a first determination sub-module, configured to determine the type of the obstacle corresponding to the obstacle grid as a high-type obstacle when there are second laser points on the obstacle grid.

[0093] In an exemplary embodiment, the above-mentioned third determination module further includes: a second determination sub-module, configured to determine the type of the obstacle corresponding to the obstacle grid as a suspended-type obstacle when the number of second target laser points in the obstacle grid is greater than or equal to a third quantity threshold and the number of third target laser points is less than or equal to a fourth quantity threshold, where the second target laser points are the first laser points in the obstacle grid whose height coordinates are greater than or equal to a second preset height coordinate, and the third target laser points are the first laser points in the obstacle grid whose height coordinates are less than the second preset height coordinate.

[0094] In an exemplary embodiment, the above-mentioned first determination sub-module is further configured to determine that there is no obstacle at the position corresponding to the obstacle grid in the target scene when there are no second laser points on the obstacle grid.

[0095] In an exemplary embodiment, the above-mentioned third determination module includes: a third determination sub-module, configured to determine the type of the obstacle corresponding to the obstacle grid as a low-type obstacle when the number of fourth target laser points in the obstacle grid is greater than or equal to a fifth quantity threshold and the number of fifth target laser points is less than or equal to a sixth quantity threshold, where the fourth target laser points are the first laser points in the obstacle grid whose height coordinates are less than or equal to a third preset height coordinate, and the fifth target laser points are the first laser points in the obstacle grid whose height coordinates are greater than the third preset height coordinate.

[0096] In an exemplary embodiment, the above-mentioned device further includes: a first clustering module, configured to cluster the obstacle grids in the grid map to obtain an obstacle grid set after determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle; a fourth determination module, configured to determine the type of the obstacle corresponding to the obstacle grid set as a step-type obstacle when the obstacle grids in the obstacle grid set satisfy the step cross-section feature and the straightness and length of the obstacle grids in the obstacle grid set meet preset conditions.

[0097] In an exemplary embodiment, the above-mentioned device further includes: a second clustering module, configured to cluster the obstacle grids in the grid map to obtain an obstacle grid set after determining the type of the obstacle corresponding to the obstacle grid as a low-type obstacle; a fifth determination module, configured to determine the type of the obstacle corresponding to the obstacle grid set as a line-type obstacle when the obstacle grids in the obstacle grid set satisfy the line-type cross-section feature.

[0098] It should be noted here that the examples and application scenarios implemented by the above-mentioned modules and the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above-mentioned modules, as a part of the device, can run in a hardware environment as shown in Figure 1 and can be implemented by software or by hardware, where the hardware environment includes a network environment.

[0099] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the above-mentioned storage medium can be used to execute the program code of any one of the above-mentioned obstacle recognition methods in the embodiments of the present application.

[0100] Optionally, in this embodiment, the above-mentioned storage medium can be located on at least one of multiple network devices in the network shown in the above embodiment.

[0101] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

[0102] S1, project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot;

[0103] S2, determine whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points;

[0104] S3, when it is determined that there is an obstacle in the target scene, determine the type of the obstacle according to the distribution of the first laser points in each grid on the grid map.

[0105] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments, and details are not described herein again.

[0106] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disc that can store program code.

[0107] According to another aspect of the embodiments of the present application, an electronic device for implementing the above obstacle recognition method is further provided, and the electronic device may be a server, a terminal, or a combination thereof.

[0108] Figure 5 is a structural block diagram of an optional electronic device according to the embodiments of the present application, as Figure 5 shown, including a processor 502, a communication interface 504, a memory 506, and a communication bus 508. Among them, the processor 502, the communication interface 504, and the memory 506 complete mutual communication through the communication bus 508, where,

[0109] The memory 506 is used to store a computer program;

[0110] The processor 502, when executing the computer program stored on the memory 506, implements the following steps:

[0111] S1, project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot;

[0112] S2. Determine whether there is an obstacle in the target scenario according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points.

[0113] S3. When it is determined that there is an obstacle in the target scenario, determine the type of the obstacle according to the distribution of the first laser points in each grid on the grid map.

[0114] Optionally, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 5 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0115] The above-mentioned memory may include a RAM, and may also include a non-volatile memory, for example, at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0116] As an example, the above-mentioned memory 506 may but is not limited to include the projection unit 402, the first determination unit 404, and the second determination unit 406 in the control device of the above-mentioned device. In addition, it may also include but is not limited to other module units in the control device of the above-mentioned device, which will not be elaborated in this example.

[0117] The above-mentioned processor may be a general-purpose processor, which may include but is not limited to: a CPU (Central Processing Unit), an NP (Network Processor), etc.; it may also be a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0118] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments, and will not be elaborated herein.

[0119] Those of ordinary skill in the art can understand that Figure 5 the structure shown is only schematic, and the device for implementing the above obstacle recognition method may be a terminal device, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a Mobile Internet Device (MID), a PAD, or other terminal devices. Figure 5 It does not limit the structure of the above electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, a display device, etc.) than those shown Figure 5 in the figure, or have a different configuration from that shown Figure 5 in the figure.

[0120] Those of ordinary skill 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 the relevant hardware of the terminal device through a program, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a ROM, a RAM, a magnetic disk, or an optical disc, etc.

[0121] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0122] If the integrated unit in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in the storage medium and includes several instructions for causing one or more computer devices (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0123] In the above embodiments of the present application, each embodiment is described with emphasis. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0124] In several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in electrical or other forms.

[0125] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0126] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0127] The above is only the preferred embodiment of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. An obstacle recognition method, characterized in that, Including: Projecting the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is arranged on a target robot; Determining whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; When it is determined that there is an obstacle in the target scene, determining the type of the obstacle according to the distribution of the first laser points in each grid on the grid map; Wherein, determining whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map includes: Obtaining the number of first laser points on each grid in the grid map; If the number of the first laser points on each grid in the grid map is less than a first quantity threshold, determining that there is no such obstacle in the target scene; Otherwise, determining that there is such an obstacle in the target scene; When it is determined that there is an obstacle in the target scene, determining the type of the obstacle according to the distribution of the first laser points in each grid on the grid map includes: Obtaining the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points; Determining the grids in the grid map where the number of first laser points is greater than or equal to the first quantity threshold as obstacle grids; Determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid; Wherein, the types of the obstacles include high-type obstacles, suspended-type obstacles, and low-type obstacles.

2. The method according to claim 1, wherein The determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid includes: When the number of first target laser points in the obstacle grid is greater than or equal to a second quantity threshold, obtaining a second laser point cloud collected by a second acquisition device in the target scene, where the first target laser points are the first laser points in the obstacle grid whose height coordinates are greater than a first preset height coordinate; Projecting the second laser point cloud onto the grid map; When there are second laser points on the obstacle grid, determining the type of the obstacle corresponding to the obstacle grid as the high-type obstacle.

3. The method according to claim 1, wherein The determining the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid further includes: When the number of second target laser points in the obstacle grid is greater than or equal to a third quantity threshold and the number of third target laser points is less than or equal to a fourth quantity threshold, determine the type of the obstacle corresponding to the obstacle grid as the suspended type obstacle, where the second target laser points are the first laser points in the obstacle grid with a height coordinate greater than or equal to a second preset height coordinate, and the third target laser points are the first laser points in the obstacle grid with a height coordinate less than the second preset height coordinate.

4. The method according to claim 2, characterized in that, The method further includes: When there is no second laser point on the obstacle grid, determine that there is no obstacle at the position corresponding to the obstacle grid in the target scene.

5. The method according to claim 1, characterized in that, The determining, according to the height coordinate of the first laser point in the obstacle grid, the type of the obstacle corresponding to the obstacle grid includes: When the number of fourth target laser points in the obstacle grid is greater than or equal to a fifth quantity threshold and the number of fifth target laser points is less than or equal to a sixth quantity threshold, determine the type of the obstacle corresponding to the obstacle grid as the low type obstacle, where the fourth target laser points are the first laser points in the obstacle grid with a height coordinate less than or equal to a third preset height coordinate, and the fifth target laser points are the first laser points in the obstacle grid with a height coordinate greater than the third preset height coordinate.

6. The method according to claim 5, characterized in that, After determining the type of the obstacle corresponding to the obstacle grid as the low type obstacle, the method further includes: Cluster the obstacle grids on the grid map to obtain an obstacle grid set; When the obstacle grids in the obstacle grid set satisfy the step cross-section feature and the straightness and length of the obstacle grids in the obstacle grid set meet the preset conditions, determine the type of the obstacle corresponding to the obstacle grid set as the step type obstacle.

7. The method according to claim 5, characterized in that After determining the type of the obstacle corresponding to the obstacle grid as the low type obstacle, the method further includes: Cluster the obstacle grids on the grid map to obtain an obstacle grid set; When the obstacle grids in the obstacle grid set satisfy the line-like cross-section feature, determine the type of the obstacle corresponding to the obstacle grid set as the line type obstacle.

8. An obstacle recognition device, characterized in that, It includes: A projection unit, configured to project the acquired first laser point cloud onto a grid map, where the grid map is a map generated according to a target scene, the first laser point cloud is a point cloud formed by projecting a double-line structured light onto the target scene, the double-line structured light is emitted by a first acquisition device, and the first acquisition device is disposed on a target robot; A first determination unit, configured to determine whether there is an obstacle in the target scene according to the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points. A second determination unit, configured to, when it is determined that there is an obstacle in the target scenario, determine the type of the obstacle according to the distribution of the first laser points in each grid on the grid map. Wherein, the first determination unit includes: a first acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points. A first determination module, configured to determine that there is no such obstacle in the target scenario if the number of the first laser points on each grid in the grid map is less than a first quantity threshold. Otherwise, determine that there is such an obstacle in the target scenario. The second determination unit includes: a second acquisition module, configured to acquire the number of first laser points on each grid in the grid map, where the first laser point cloud includes the first laser points. A second determination module, including: determining the grids in the grid map where the number of first laser points is greater than or equal to the first quantity threshold as obstacle grids. A third determination module, configured to determine the type of the obstacle corresponding to the obstacle grid according to the height coordinates of the first laser points in the obstacle grid. Wherein, the types of the obstacles include high-type obstacles, suspended-type obstacles, and low-type obstacles.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when running, executes the method according to any one of claims 1 to 7.

10. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images