Obstacle determination method and apparatus, and device and storage medium

Abstract

An obstacle determination method, comprising: acquiring a first initial point cloud, which is collected by a first sensor, and a spacing distance between a device and an obstacle, which spacing distance is collected by a second sensor at the same moment (202); acquiring a field of view of the second sensor, and obtaining a second initial point cloud on the basis of the field of view and the spacing distance; determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud (206); if there is no overlapping area between the first initial point cloud and the second initial point cloud, determining that the obstacle is a first-type obstacle (208); and if there is an overlapping area between the first initial point cloud and the second initial point cloud, determining that the obstacle is a second-type obstacle (210).

Description

Obstacle judgment method, device, equipment and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on June 25, 2023, with application number 2023107505612 and application name “Obstacle Judgment Method, Device, Equipment and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of automation technology, and in particular to an obstacle judgment method, device, equipment, storage medium and computer program product. Background Art

[0004] With the development of automation technology, various intelligent devices have emerged. Intelligent devices automatically perform related tasks based on planned paths, bringing great convenience to people's lives and work.

[0005] In traditional technologies, smart devices use lidar sensors and depth sensors to detect obstacles. However, for laser-invisible obstacles such as mirrors, glass, and transparent objects, smart devices cannot accurately locate them or require auxiliary tools for positioning, resulting in low operating efficiency of smart devices.

[0006] Summary of the Invention

[0007] According to various embodiments of the present application, a method for determining an obstacle is provided.

[0008] An obstacle determination method, comprising:

[0009] Obtaining a first initial point cloud collected by a first sensor and a distance between the device and the obstacle collected by a second sensor at the same time;

[0010] Acquire a field of view angle of the second sensor, and obtain a second initial point cloud based on the field of view angle and the interval distance;

[0011] Determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud;

[0012] If the first initial point cloud and the second initial point cloud do not have an overlapping area, then the obstacle is determined to be a first type obstacle;

[0013] If there is an overlapping area between the first initial point cloud and the second initial point cloud, the obstacle is determined to be a second type of obstacle.

[0014] An obstacle judgment device, comprising:

[0015] an acquisition module, configured to acquire a first initial point cloud acquired by the first sensor and a distance between the point cloud and the obstacle acquired by the second sensor;

[0016] a segmentation module, configured to obtain a field of view angle of the second sensor, and obtain a second initial point cloud based on the field of view angle and the interval distance;

[0017] a judgment module, configured to determine whether the first initial point cloud and the second initial point cloud have overlapping areas;

[0018] A determination module is configured to determine that the obstacle is a first type of obstacle if there is no overlapping area between the first initial point cloud and the second initial point cloud; and to determine that the obstacle is a second type of obstacle if there is an overlapping area between the first initial point cloud and the second initial point cloud.

[0019] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned dynamic edge path generation method when executing the computer program.

[0020] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned dynamic edge path generation method.

[0021] A computer program product includes a computer program, which implements the steps of the above-mentioned dynamic edge path generation method when executed by a processor.

[0022] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0024] FIG1 is a diagram illustrating an application environment of an obstacle determination method according to an embodiment;

[0025] FIG2 is a schematic flow chart of an obstacle determination method according to an embodiment;

[0026] FIG3 is a schematic diagram of a process of obtaining a second initial point cloud in one embodiment;

[0027] FIG4 is a schematic diagram of a process for determining whether there is an overlapping area in one embodiment;

[0028] FIG5 is a flow chart of the step of determining an obstacle avoidance method in one embodiment;

[0029] FIG6 is a schematic diagram of a device in one embodiment;

[0030] FIG7 is a schematic diagram of a map in one embodiment;

[0031] FIG8 is a structural block diagram of an obstacle determination device according to one embodiment;

[0032] FIG9 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0033] To facilitate understanding of the present application, a more comprehensive description of the present application will be provided below with reference to the accompanying drawings. The accompanying drawings illustrate preferred embodiments of the present application. However, the present application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the disclosure of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the invention pertains. The terms used in the specification of the invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0035] The obstacle determination method provided in the embodiment of the present application can be applied in the application environment shown in Figure 1. Among them, the device 102 communicates with the server 104 via the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Both the device 102 and the server 104 can be used alone to execute the obstacle determination method provided in the embodiment of the present application. The device 102 and the server 104 can also be used in conjunction to execute the obstacle determination method provided in the embodiment of the present application. The devices 102 and 102 can also be used in conjunction to execute the obstacle determination method provided in the embodiment of the present application. Taking device 102 alone as an example, executing the obstacle determination method provided in the embodiments of this application, the device obtains a first initial point cloud captured by a first sensor and the distance between the device and the obstacle captured by a second sensor at the same time. The device then obtains the field of view of the second sensor and, based on the field of view and the distance, generates a second initial point cloud. The device then determines whether there is any overlap between the first and second initial point clouds. If there is no overlap, the obstacle is determined to be a first-category obstacle. If there is any overlap, the obstacle is determined to be a second-category obstacle. Device 102 may be, but is not limited to, at least one of various intelligent devices, automated equipment, cleaning robots, delivery robots, tour guide robots, self-driving cars, and unmanned aerial vehicles. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers.

[0036] In one embodiment, as shown in FIG2 , a method for determining an obstacle is provided. The method is described by taking the method applied to device 102 as an example, and includes the following steps:

[0037] Step 202: Acquire a first initial point cloud collected by a first sensor and a distance between the device and an obstacle collected by a second sensor at the same time.

[0038] The first sensor refers to a sensor that emits light waves and can determine obstacle information based on the received reflected light waves. The first sensor includes, but is not limited to, a lidar sensor, a depth sensor, and an infrared sensor. A point cloud refers to a collection of multiple point coordinates. The first initial point cloud refers to the obstacle point cloud collected by the first sensor. The point coordinates in the first initial point cloud can be located in a coordinate system with the first sensor as the origin. The second sensor refers to a sensor that emits sound waves and can determine the distance to the obstacle based on the received reflected sound waves. The second sensor includes, but is not limited to, ultrasonic sensors, sonar sensors, and sound sensors. The distance refers to the straight-line distance between the device and the obstacle.

[0039] Exemplarily, the device obtains a first initial point cloud acquired by a first sensor and a distance between the device and an obstacle acquired by a second sensor at the same time.

[0040] In one embodiment, the device obtains a first initial point cloud collected by a first sensor and a distance between the device and an obstacle collected by a second sensor at the same time and in the same detection direction.

[0041] Step 204 : Acquire the field of view angle of the second sensor, and obtain a second initial point cloud based on the field of view angle and the interval distance.

[0042] The field of view (FOV) refers to the angular range that a sensor can detect. The FOV can be expressed in degrees or physical dimensions. The larger the FOV, the wider the range detected by the second sensor; the smaller the FOV, the narrower the range detected by the second sensor. The second initial point cloud refers to a set of point coordinates representing obstacles. The point coordinates in the second initial point cloud can be located in a coordinate system with the second sensor as the origin.

[0043] Exemplarily, the device obtains the field of view angle of the second sensor, and then performs calculations based on the field of view angle and the interval distance to obtain a second initial point cloud representing the obstacle.

[0044] In one embodiment, the device establishes an initial coordinate system with the second sensor as the origin, obtains a curve with the origin as the center and the interval distance as the radius based on the origin and the interval distance, takes the part of the curve corresponding to the field of view angle as the target curve, samples the target curve to obtain multiple sampling points, and obtains a second initial point cloud representing the obstacle based on the point coordinates corresponding to the multiple sampling points.

[0045] Step 206 : Determine whether there is any overlapping area between the first initial point cloud and the second initial point cloud.

[0046] Exemplarily, the device compares and determines the first initial point cloud with the second initial point cloud.

[0047] Step 208: If there is no overlapping area between the first initial point cloud and the second initial point cloud, the obstacle is determined to be a first type obstacle.

[0048] The first type of obstacles refers to obstacles that light waves can penetrate. The first type of obstacles are obstacles that are invisible to lasers, such as glass, mirrors, and transparent baffles.

[0049] Exemplarily, the device compares the first initial point cloud and the second initial point cloud, and if there is no overlapping area between the first initial point cloud and the second initial point cloud, it is determined that the obstacle is a first type of obstacle.

[0050] In step 210 , if there is an overlapping area between the first initial point cloud and the second initial point cloud, the obstacle is determined to be a second type of obstacle.

[0051] The second type of obstacles are those that light waves cannot penetrate. They are obstacles visible to the laser, such as tables, stools, and walls.

[0052] In one embodiment, the device obtains a first conversion relationship between a first coordinate system and a reference coordinate system, where the first coordinate system is a coordinate system with the first sensor as the origin, and a second conversion relationship between a second coordinate system and the reference coordinate system, where the second coordinate system is a coordinate system with the second sensor as the origin. Based on the first conversion relationship, the first initial point cloud is converted to obtain a first reference point cloud. Based on the second conversion relationship, the second initial point cloud is converted to obtain a second reference point cloud. The first reference point cloud and the second reference point cloud are compared. If the first reference point cloud and the second reference point cloud have the same point coordinates, the obstacle is judged to be a second-category obstacle. If the first reference point cloud and the second reference point cloud do not have the same point coordinates, the obstacle is judged to be a first-category obstacle.

[0053] In the above obstacle judgment method, if the obstacle detected by the second sensor is a first-category obstacle, the first sensor cannot collect the first initial point cloud of the obstacle. At this time, the first initial point cloud collected by the first sensor is another second-category obstacle. The second initial point cloud representing the obstacle is obtained through the interval distance between the device and the obstacle collected by the second sensor, and the field of view of the second sensor. If there is no overlapping area between the first initial point cloud and the second initial point cloud, it can be determined that the obstacle detected by the second sensor is a first-category obstacle, thereby improving the accuracy of obstacle judgment. If it is determined that the obstacle detected by the second sensor is a first-category obstacle, the obstacle can be avoided based on the interval distance, thereby avoiding a collision between the device and the obstacle, and the device making a large-scale detour or stopping operation, thereby improving the operating efficiency of the device.

[0054] In one embodiment, as shown in FIG3 , the second sensor is an ultrasonic sensor, and obtaining the field of view angle of the second sensor and obtaining the second initial point cloud based on the field of view angle and the interval distance includes:

[0055] Step 302: Divide the field of view angle based on preset division angles to obtain a plurality of offset angles.

[0056] Ultrasonic sensors use ultrasonic technology for detection and measurement, measuring the distance between a target object and the sensor. The preset division angle refers to the pre-set angle used to divide the field of view. Smaller preset division angles result in larger offset angles, while larger preset division angles result in smaller offset angles. The offset angle is the angle between the straight line between the obstacle point and the origin and the coordinate axis.

[0057] Exemplarily, the device obtains a preset division angle, and divides the field of view angle into a plurality of offset angles according to the preset division angle.

[0058] In one embodiment, the device obtains an initial coordinate system with the second sensor as the origin, converts the field of view angle into a detection angle range in the initial coordinate system, and divides the detection angle range based on a preset division angle to obtain multiple offset angles. For example, the field of view angle of the second sensor is 60, and the detection angle range of the field of view angle in the initial coordinate system is -30° to 30°. The preset division angle is 5°, and the resulting offset angles are -30°, -25°, -20°, -15°, -10°, -5°, 0°, 5°, 10°, 15°, 20°, 25°, and 30°.

[0059] Step 304 : Based on the interval distance and the offset angle, the initial coordinates of the obstacle point corresponding to the offset angle are calculated; the multiple obstacle points are used to represent the obstacle.

[0060] The obstacle point is a point used to represent an obstacle. It can be understood as a point within the field of view that is at a certain distance from the origin. The initial coordinates refer to the coordinates of the obstacle point in the coordinate system with the second sensor as the origin.

[0061] Exemplarily, the device calculates the initial coordinates of the obstacle point corresponding to the offset angle based on the interval distance and the offset angle.

[0062] In one embodiment, the device calculates the sine and cosine values ​​of the offset angle, obtains the X-axis coordinate based on the interval distance and the cosine value, obtains the Y-axis coordinate based on the interval distance and the sine value, and obtains the initial coordinates of the obstacle point corresponding to the offset angle based on the X-axis coordinate and the Y-axis coordinate.

[0063] In one embodiment, the calculation formula of the initial coordinate Pi (x, y) is as follows: x = d*cos(θi) Formula (1) y = d*sin(θi) Formula (2)

[0064] Where Pi(x,y) is the initial coordinate of the obstacle point corresponding to the i-th offset angle, x is the X-axis coordinate, y is the Y-axis coordinate, d is the interval distance, and θi is the i-th offset angle.

[0065] Step 306 : Obtain a second initial point cloud based on the initial coordinates of the obstacle points corresponding to the multiple offset angles.

[0066] Exemplarily, the device composes a second initial point cloud from initial coordinates of obstacle points corresponding to multiple offset angles.

[0067] In this embodiment, the initial coordinates of the obstacle point corresponding to each offset angle are calculated by the interval distance between the device and the obstacle, and the field of view angle corresponding to the second sensor. It can be understood that the obstacle point is a point where an obstacle may exist, and the initial coordinates corresponding to multiple obstacle points are combined to form a second initial point cloud. The second initial point cloud can more accurately represent the obstacle detected by the second sensor. The obstacle is located by the second initial point cloud, thereby improving the accuracy of obstacle positioning.

[0068] In one embodiment, as shown in FIG4 , the first sensor is a laser radar and / or a depth camera, and determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud includes:

[0069] Step 402 : Based on the first extrinsic parameter of the first sensor, the first initial point cloud is converted into a first intermediate point cloud in the target coordinate system; based on the second extrinsic parameter of the second sensor, the second initial point cloud is converted into a second intermediate point cloud in the target coordinate system.

[0070] LiDAR is a sensor that uses laser beams for detection and measurement. It can measure the distance, shape, and position of a target object. A depth camera, also known as a depth sensor or depth camera, is a sensor that generates depth images containing distance information. External parameters refer to parameters that characterize the position of a sensor relative to the device. These parameters can be obtained from the device's structural design drawings. The first external parameter refers to the position parameter of the first sensor relative to the device. The second external parameter refers to the position parameter of the second sensor relative to the device. The target coordinate system is a coordinate system with the center of the device as its origin.

[0071] Exemplarily, the device multiplies each first initial coordinate in the first initial point cloud by the first external parameter to obtain a first intermediate coordinate corresponding to each first initial coordinate, and combines multiple first intermediate coordinates into a first intermediate point cloud. It multiplies each second initial coordinate in the second initial point cloud by the second external parameter to obtain a second intermediate coordinate corresponding to each second initial coordinate, and combines multiple second intermediate coordinates into a second intermediate point cloud.

[0072] In one embodiment, the first intermediate coordinate is calculated as follows: Pri = Trc * Pci Formula (3)

[0073] Among them, Trc is the first external parameter, Pci is the i-th first initial coordinate, and Pri is the i-th first intermediate coordinate.

[0074] Step 404: Obtain the size of the grid map and the resolution corresponding to the grid map.

[0075] A grid map is a map centered on the device and created with a preset size. For example, a grid map is one meter long and one meter wide, centered on the device. Size refers to the length and width of the grid map. Size can be expressed as length and width. Resolution refers to the ratio between the actual map and the grid map. The actual map refers to the map used during device operation.

[0076] Exemplarily, the device obtains the size and corresponding resolution of the grid map.

[0077] Step 406 : Based on the size and resolution, project the first intermediate point cloud into the grid map to obtain a first grid point cloud, and project the second intermediate point cloud into the grid map to obtain a second grid point cloud.

[0078] Exemplarily, the device translates each first intermediate coordinate in the first intermediate point cloud based on the size to obtain a first translated point cloud, obtains a first grid point cloud based on the first translated point cloud and the resolution, translates each second intermediate coordinate in the second intermediate point cloud based on the size to obtain a second translated point cloud, and obtains a second grid point cloud based on the second translated point cloud and the resolution.

[0079] In one embodiment, the device translates each first intermediate coordinate in the first intermediate point cloud based on the size to obtain a first translated point cloud, divides each first translated coordinate in the first translated point cloud by the resolution to obtain a first grid point cloud, translates each second intermediate coordinate in the second intermediate point cloud based on the size to obtain a second translated point cloud, and divides each second translated coordinate in the second translated point cloud by the resolution to obtain a second grid point cloud.

[0080] In one embodiment, the device translates each first intermediate coordinate in the first intermediate point cloud based on the size to obtain a first translated point cloud, divides each first translated coordinate in the first translated point cloud by the resolution to obtain a first grid point cloud, translates each second intermediate coordinate in the second intermediate point cloud based on the size to obtain a second translated point cloud, and divides each second translated coordinate in the second translated point cloud by the resolution to obtain a second grid point cloud.

[0081] In one embodiment, the first grid coordinate is calculated as follows: Psxi = (Prxi - size_x / 2) | resolution Formula (4) Psyi = (Pryi - size_y / 2) | resolution Formula (5)

[0082] Among them, Psxi is the X-axis coordinate of the i-th first grid coordinate, Psyi is the Y-axis coordinate of the i-th first grid coordinate, Prxi is the X-axis coordinate of the i-th first intermediate coordinate, Pryi is the Y-axis coordinate of the i-th first intermediate coordinate, size_x is the length of the grid map, size_y is the width of the grid map, resolution is the resolution corresponding to the grid map, and | is the integer division symbol.

[0083] Step 408 : Compare the second coordinate in the second grid point cloud with the first coordinate in the first grid point cloud, and determine whether there is an overlapping area between the first initial point cloud and the second initial point cloud based on the comparison result.

[0084] If there is no overlapping area between the first initial point cloud and the second initial point cloud, that is, there is no first coordinate that is the same as the second coordinate, then the obstacle is determined to be a first type obstacle, wherein the first type obstacle is a laser invisible obstacle.

[0085] If the first initial point cloud and the second initial point cloud have an overlapping area, that is, there is a first coordinate that is the same as the second coordinate, then the obstacle is determined to be a second type of obstacle, wherein the second type of obstacle is a laser visible obstacle.

[0086] Exemplarily, the device obtains the current second coordinate in the second grid point cloud, compares the current second coordinate with the first coordinate in the first grid point cloud, and if there is a first coordinate that is the same as the current second coordinate, the obstacle is determined to be a second-type obstacle, and the comparison is stopped; if there is no first coordinate that is the same as the current second coordinate, the next second coordinate is obtained as the current second coordinate, and the above steps are repeated until the last second coordinate in the second grid point cloud, and the obstacle is determined to be a first-type obstacle.

[0087] In this embodiment, the first initial point cloud and the second initial point cloud are converted by the external parameters corresponding to the sensor to obtain the corresponding first intermediate point cloud and the second intermediate point cloud. The first intermediate point cloud and the second intermediate point cloud are located in the same target coordinate system, so that the first intermediate point cloud and the second intermediate point cloud are comparable. Then, the first intermediate point cloud and the second intermediate point cloud are projected into the grid map, and each first intermediate coordinate in the first intermediate point cloud is divided by the resolution. Because the result of the division is an integer part, there will be some first intermediate coordinates that have the same result of dividing the resolution, resulting in the number of first coordinates in the first grid point cloud being less than the number of first intermediate coordinates in the first intermediate point cloud. Similarly, the number of second coordinates in the second grid point cloud is less than the number of second intermediate coordinates in the second intermediate point cloud. Therefore, the number of comparisons can be reduced and the efficiency of judgment is improved.

[0088] In one embodiment, the obstacle determination method further includes:

[0089] Obtain a target map and an error threshold of the second sensor; the target map is a map used during device operation; if the obstacle is determined to be a first-category obstacle and the separation distance is less than the error threshold, update the target map based on the second initial point cloud to obtain an updated target map; if the obstacle is determined to be a second-category obstacle, update the target map based on the first initial point cloud to obtain an updated target map.

[0090] The error threshold is the minimum distance at which the second sensor experiences a false detection. The error threshold can be set based on the characteristics of the second sensor. For example, if the second sensor is ultrasonic sensor A, which accurately detects obstacles within 0.4 meters but may have errors in detecting obstacles beyond 0.4 meters, the error threshold for ultrasonic sensor A can be set to 0.4 meters.

[0091] Exemplarily, the device obtains a target map used during driving and an error threshold of the second sensor. When the obstacle is determined to be a first-category obstacle, the device compares the interval distance with the error threshold. If the interval distance is less than the error threshold, the target map is updated based on the second initial point cloud to obtain an updated target map. If the interval distance is greater than or equal to the error threshold, the target map is not updated. When the obstacle is determined to be a second-category obstacle, the target map is updated based on the first initial point cloud to obtain an updated target map.

[0092] In one embodiment, when the obstacle is determined to be a first-class obstacle, the device obtains the target map and the error threshold of the second sensor, compares the interval distance with the error threshold, and if the interval distance is less than the error threshold, determines whether the detection direction of the second sensor is the same as the running direction of the device. If the detection direction of the second sensor is the same as the running method of the device, the target map is updated based on the second initial point cloud to obtain an updated target map; if the detection direction of the second sensor is not the same as the running direction of the device, or the interval distance is greater than or equal to the error threshold, the target map is not updated.

[0093] In one embodiment, when the obstacle is determined to be a first-class obstacle, the device obtains the target map and the error threshold of the second sensor, compares the interval distance with the error threshold, and if the interval distance is less than the error threshold, obtains the second external parameter of the second sensor, and converts the second initial point cloud into a second intermediate point cloud in the target coordinate system based on the second external parameter. The target coordinate system is a coordinate system with the center of the device as the origin, obtains the conversion relationship between the target coordinate system and the target map, and converts the second intermediate point cloud based on the conversion relationship to obtain a second target point cloud. The second target point cloud is added to the target map to obtain an updated target map.

[0094] In one embodiment, when the obstacle is determined to be a first-class obstacle, the device obtains the target map and the error threshold of the second sensor, compares the interval distance with the error threshold, and if the interval distance is less than the error threshold, obtains the second external parameter of the second sensor, and converts the second initial point cloud into a second intermediate point cloud in the target coordinate system based on the second external parameter. The target coordinate system is a coordinate system with the center of the device as the origin, and then obtains the size and corresponding resolution of the grid map, as well as the conversion relationship between the grid map and the target map. Based on the size and resolution, the second intermediate point cloud is projected into the grid map to obtain a second grid point cloud. Based on the second grid point cloud and the conversion relationship, a second target point cloud is obtained, and the second target point cloud is added to the target map to obtain an updated target map.

[0095] In one embodiment, when the obstacle is determined to be a first-class obstacle, the device obtains the target map and the error threshold of the second sensor, compares the interval distance with the error threshold, and if the interval distance is less than the error threshold, obtains the second grid point cloud corresponding to the second initial point cloud, as well as the conversion relationship between the grid map and the target map. Based on the conversion relationship, the second grid point cloud is converted to obtain a second target point cloud, and the second target point cloud is added to the target map to obtain an updated target map.

[0096] In one embodiment, after the device obtains the updated target map, the device further includes generating an obstacle avoidance path corresponding to the obstacle based on the updated target map, where the obstacle avoidance path is used for the device to avoid the obstacle.

[0097] In this embodiment, if the obstacle is determined to be a first-category obstacle, and the separation distance is less than the error threshold, the target map is updated based on the second initial point cloud. A separation distance less than the error threshold not only indicates that the separation distance measurement is accurate, but also indicates that the smaller the separation distance, the smaller the arc length corresponding to the field of view angle, and the smaller the obstacle's location range. Therefore, by updating the target map based on the second initial point cloud corresponding to a separation distance less than the error threshold, the obstacle's location range in the target map is smaller. Operating the device based on the updated target map can avoid extensive detours and collisions with first-category obstacles, thereby improving device operational efficiency. If the obstacle is determined to be a second-category obstacle, the target map is updated based on the first initial point cloud to obtain an updated target map. The first initial point cloud is data acquired by the first sensor, and the second initial point cloud is data calculated based on the separation distance. Compared to the second initial point cloud, the first initial point cloud more accurately represents the obstacle. Therefore, if the obstacle is determined to be a second-category obstacle, updating the target map based on the first initial point cloud improves the accuracy of the updated target map.

[0098] In one embodiment, after updating the target map based on the second initial point cloud to obtain the updated target map, the method further includes:

[0099] Based on the preset clearing time, obstacles corresponding to the second initial point cloud in the updated target map are cleared to obtain a cleared target map.

[0100] The preset clearing duration refers to a pre-set duration. This duration is defined as the time it takes for the device to clear obstacles from the updated target map, starting with the time the updated target map is obtained. The preset clearing duration is calculated by adding the starting time to the preset clearing duration. The clearing time is the time it takes for the device to clear obstacles from the updated target map. The preset clearing duration can be determined based on the device's computing power, operating speed, and the field of view of the second sensor.

[0101] Exemplarily, after the time duration for obtaining the updated target map reaches a preset clearing time duration, the device clears the obstacles corresponding to the second initial point cloud in the updated target map to obtain a cleared target map.

[0102] In this embodiment, when the time for the device to obtain the updated target map reaches the preset clearing time, the device has generated an obstacle avoidance path for avoiding obstacles based on the obstacles in the target map, and cleared the obstacle data in the target map in time, thereby avoiding the device from performing ineffective avoidance when the obstacle is removed, reducing the time for the device to avoid obstacles, and thus improving the efficiency of the device operation.

[0103] In one embodiment, as shown in FIG5 , when the obstacle is determined to be a first-category obstacle, the method further includes:

[0104] Step 502: Determine an obstacle avoidance method corresponding to the obstacle based on the interval distance.

[0105] Obstacle avoidance methods refer to methods of avoiding obstacles, including but not limited to deceleration and detours.

[0106] Exemplarily, the device determines an obstacle avoidance method corresponding to the obstacle based on the interval distance.

[0107] In one embodiment, the device obtains a first threshold and a second threshold, the second threshold is smaller than the first threshold, and compares the interval distance with the first threshold and the second threshold. If the interval distance is greater than the first threshold, the device maintains the current state of operation. If the interval distance is less than or equal to the first threshold and greater than or equal to the second threshold, the detection direction of the second sensor is obtained. If the detection direction of the second sensor is the same as the running direction of the device, it is determined to use the obstacle avoidance method of decelerating operation. If the interval distance is less than the second threshold, it is determined to use the obstacle avoidance method of changing the running path.

[0108] In one embodiment, the device determines the obstacle avoidance method corresponding to the obstacle based on the interval distance. If the obstacle avoidance method is to change the operating path, the target map is updated based on the second initial point cloud. The target map refers to the map used during the operation of the device, and an updated target map is obtained.

[0109] Step 504: If the interval distance satisfies the preset deceleration distance interval, and the detection direction of the second sensor is the same as the running direction of the device, decelerate the running.

[0110] The preset deceleration distance interval refers to a pre-set distance range. If the distance between the two sensors meets this range, the device will decelerate. The detection direction refers to the direction in which the second sensor emits sound waves. For example, the detection direction can be divided into the running direction, the left direction, the right direction, and the opposite direction.

[0111] Exemplarily, the device obtains a preset deceleration distance interval, compares the interval distance with the preset deceleration distance interval, and if the interval distance is within the preset deceleration distance interval, obtains the detection direction of the second sensor and the device running direction. If the detection direction is the same as the device running direction, the device decelerates.

[0112] In one embodiment, while the device is decelerating, the updated interval distance between the device and the obstacle collected by the second sensor is continuously obtained. If the updated interval distance satisfies a preset deceleration distance interval, the device continues to decelerate, or runs at a set speed. If the updated interval interval is less than an error threshold of the second sensor, the target map is updated based on the updated interval distance and the field of view angle of the second sensor to obtain an updated target map. An obstacle avoidance path is generated based on the updated target map, and obstacles are avoided based on the obstacle avoidance path.

[0113] Step 506: If the separation distance is less than the error threshold of the second sensor, an obstacle avoidance path corresponding to the obstacle is generated based on the separation distance, and the obstacle is avoided based on the obstacle avoidance path.

[0114] The obstacle avoidance path refers to a path that avoids obstacles.

[0115] Exemplarily, the device compares the interval distance with the error threshold of the second sensor. If the interval distance is less than the error threshold of the second sensor, an obstacle avoidance path corresponding to the obstacle is generated based on the interval distance. The device operates based on the obstacle avoidance path to avoid the obstacle.

[0116] In one embodiment, the device compares the interval distance with an error threshold of the second sensor. If the interval distance is less than the error threshold of the second sensor, the device obtains a conversion relationship between the target map and the grid map, and based on the conversion relationship, converts the second grid point cloud obtained based on the interval distance to obtain a second target point cloud. The target map is updated based on the second target point cloud to obtain an updated target map. Based on the updated target map, an obstacle avoidance path corresponding to the obstacle is generated, and the obstacle is avoided based on the obstacle avoidance path.

[0117] In this embodiment, the device selects a suitable obstacle avoidance method according to the interval distance, avoids obstacles by using the suitable obstacle avoidance method, thereby improving the obstacle avoidance efficiency of the device and thus improving the operation efficiency of the device. Specifically, when the interval distance satisfies the preset deceleration distance interval, it indicates that the interval distance between the device and the obstacle is relatively large, and the device does not need to detour temporarily. If detour is performed at this time, the detour distance is longer, and the device is prevented from colliding with the first type of obstacle by decelerating operation, thereby improving the operation efficiency of the device. When the interval distance is less than the error threshold, it not only indicates that the interval distance measurement is accurate and the obstacle position range is small, but also indicates that the interval distance between the device and the obstacle is small, and the device is prone to collision with the obstacle. An obstacle avoidance path is generated based on the interval distance, and obstacles are avoided based on the obstacle avoidance path, which can avoid large-scale detours of the device and collisions with the first type of obstacles, thereby improving the operation efficiency of the device.

[0118] In one embodiment, generating an obstacle avoidance path corresponding to an obstacle based on the separation distance includes:

[0119] Obtain the reserved distance, determine the detour distance corresponding to the obstacle based on the interval distance and the reserved distance, and generate an obstacle avoidance path corresponding to the obstacle based on the detour distance.

[0120] The "reserved distance" refers to a pre-set fixed distance. The reserved distance can be determined based on the width or thickness of the first-category obstacle. This means that first-category obstacles are permeable to light waves, and generally have a relatively small width or thickness. The "reserved distance" represents the width or thickness of the first-category obstacle. The "detour distance" refers to the distance the device moves to the other side of an obstacle to avoid it.

[0121] Exemplarily, the device obtains a reserved distance, adds the interval distance to the reserved distance, obtains a detour distance corresponding to the obstacle, and then generates an obstacle avoidance path corresponding to the obstacle based on the detour distance.

[0122] In one embodiment, the device obtains a reserved distance, adds the interval distance to the reserved distance, obtains a detour distance corresponding to the obstacle, determines an obstacle point cloud based on the field of view angle of the second sensor and the detour distance, and generates an obstacle avoidance path corresponding to the obstacle based on the obstacle point cloud.

[0123] In this embodiment, the interval distance is less than the error threshold of the second sensor, indicating that the distance between the device and the obstacle is small. The device needs to move to the other side of the obstacle to avoid the obstacle. The interval distance is added to the reserved distance to obtain the detour distance corresponding to the obstacle. Then, an obstacle avoidance path corresponding to the obstacle is generated based on the detour distance. The device operates according to the obstacle avoidance path to avoid collision with the obstacle, thereby improving the operating efficiency of the device.

[0124] In an exemplary embodiment, the robot's sensor layout is shown in Figure 6, where 602 is the robot, which is equipped with five ultrasonic sensors, one lidar sensor, and one depth camera sensor. The five ultrasonic sensors are ultrasonic sensor 1, ultrasonic sensor 2, ultrasonic sensor 3, ultrasonic sensor 4, and ultrasonic sensor 5, with corresponding detection areas 604, 606, 608, 610, and 612, respectively. Each ultrasonic sensor has a field of view of 60 degrees. The depth camera sensor has a detection range of 614, and the lidar sensor has a detection range of 616.

[0125] Obtain the lidar point cloud collected by the lidar sensor and the depth point cloud collected by the depth camera sensor at the same time. Obtain the lidar extrinsics of the lidar sensor and the depth camera extrinsics of the depth camera sensor from the robot's structural design drawing. Use formula (3) to transform the lidar point cloud into the robot coordinate system to obtain the intermediate lidar point cloud. Use formula (3) to transform the depth point cloud into the robot coordinate system to obtain the intermediate depth point cloud. Obtain the length and width of the grid map and the corresponding resolution of the grid map. Use formulas (4) and (5) to project the intermediate lidar point cloud into the grid map to obtain the grid lidar point cloud. Use formulas (4) and (5) to project the intermediate depth point cloud into the grid map to obtain the grid depth point cloud.

[0126] The distance d between the robot and the obstacle, as captured by the ultrasonic sensor at the same moment, and the ultrasonic sensor's field of view of 60° are obtained. Using 5° as the preset division angle, the obtained offset angles are -30°, -25°, -20°, -15°, -10°, -5°, 0°, 5°, 10°, 15°, 20°, 25°, and 30°. Formulas (1) and (2) are used to calculate the coordinates of the obstacle point corresponding to each offset angle, and the multiple point coordinates are combined to form an ultrasonic point cloud. The ultrasonic extrinsic parameters of the ultrasonic sensor are obtained from the robot's structural design drawing. Formula (3) is used to transform the ultrasonic point cloud into the robot coordinate system to obtain an intermediate ultrasonic point cloud. Based on the length and width of the grid map and the corresponding resolution of the grid map, formulas (4) and (5) are used to project the intermediate ultrasonic point cloud onto the grid map to obtain a grid ultrasonic point cloud.

[0127] The grid ultrasonic point cloud is compared with the grid lidar point cloud and the grid depth point cloud. If at least one of the grid lidar point cloud and the grid depth point cloud has the same point coordinates as the grid ultrasonic point cloud, the obstacle detected by the ultrasonic sensor is determined to be a laser-visible obstacle. As shown in Figure 7, 702 is the robot, 704 is the grid lidar point cloud or the grid depth point cloud, and 706 is the grid ultrasonic point cloud. If 704 and 706 have an overlapping area, the obstacle detected by the ultrasonic sensor is determined to be a laser-visible obstacle. If the grid lidar point cloud and the grid depth point cloud do not have the same point coordinates as the grid ultrasonic point cloud, the obstacle detected by the ultrasonic sensor is determined to be a laser-invisible obstacle.

[0128] When it is determined that the obstacle detected by the ultrasonic sensor is a laser-visible obstacle, the raster ultrasonic point cloud is discarded, and the target map is updated based on the raster lidar point cloud and the raster depth point cloud to obtain an updated target map. An obstacle avoidance path is generated based on the updated target map, and the robot runs along the obstacle avoidance path to avoid the laser-visible obstacle.

[0129] When it is determined that the obstacle detected by the ultrasonic sensor is an obstacle invisible to the laser, the preset deceleration interval and error threshold are obtained. If the interval distance is within the preset deceleration interval and the obstacle is detected by ultrasonic sensor No. 2 or No. 3, it means that there is an obstacle invisible to the laser in front of the robot, and the robot decelerates. If the interval distance is less than the error threshold, the target map is updated based on the grid ultrasonic point cloud to obtain an updated target map, and then an obstacle avoidance path is generated based on the updated target map. The robot runs along the obstacle avoidance path to avoid the obstacle invisible to the laser.

[0130] The above obstacle judgment method converts the ultrasonic point cloud, lidar point cloud and depth point cloud at the same time into a raster map to obtain a raster ultrasonic point cloud, a raster lidar point cloud and a raster depth point cloud, so that the raster ultrasonic point cloud, the raster lidar point cloud and the raster depth point cloud are in the same map, making them comparable. Moreover, by using the integer division calculation method, the number of point coordinates in the raster ultrasonic point cloud, the raster lidar point cloud and the raster depth point cloud is reduced, and the number of comparisons between the raster ultrasonic point cloud and the raster laser lightning point cloud and the raster depth point cloud is reduced, thereby improving the efficiency of determining the obstacle type. If the obstacle detected by the ultrasonic sensor is a laser invisible obstacle, the corresponding obstacle avoidance method is determined according to the distance between the two obstacles, which not only avoids the collision between the robot and the laser invisible obstacle, but also avoids the robot from making large-scale detours, thereby improving the operation efficiency of the robot.

[0131] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0132] Based on the same inventive concept, embodiments of the present application also provide an obstacle determination device for implementing the aforementioned obstacle determination method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more obstacle determination device embodiments provided below can be found in the limitations of the obstacle determination method above and will not be repeated here.

[0133] In one embodiment, as shown in FIG8 , an obstacle determination device is provided, including: an acquisition module 802 , a division module 804 , a determination module 806 , and a determination module 808 , wherein:

[0134] An acquisition module 802 is configured to acquire a first initial point cloud acquired by a first sensor and a distance to an obstacle acquired by a second sensor;

[0135] A segmentation module 804 is configured to obtain a field of view angle of the second sensor, and obtain a second initial point cloud based on the field of view angle and the interval distance;

[0136] A judgment module 806 is used to determine whether there is an overlapping area between the first initial point cloud and the second initial point cloud;

[0137] The determination module 808 is configured to determine that the obstacle is a first type obstacle if there is no overlap between the first initial point cloud and the second initial point cloud; and to determine that the obstacle is a second type obstacle if there is an overlap between the first initial point cloud and the second initial point cloud.

[0138] In one embodiment, the division module 804 is further used to: divide the field of view angle based on a preset division angle to obtain multiple offset angles; calculate the initial coordinates of the obstacle point corresponding to the offset angle based on the interval distance and the offset angle; multiple obstacle points are used to characterize the obstacles; and obtain a second initial point cloud based on the initial coordinates of the obstacle points corresponding to the multiple offset angles.

[0139] In one embodiment, the judgment module 806 is also used to: convert the first initial point cloud into a first intermediate point cloud in the target coordinate system based on the first external parameter of the first sensor, and convert the second initial point cloud into a second intermediate point cloud in the target coordinate system based on the second external parameter of the second sensor; obtain the size of the grid map and the resolution corresponding to the grid map; based on the size and resolution, project the first intermediate point cloud into the grid map to obtain the first grid point cloud, and project the second intermediate point cloud into the grid map to obtain the second grid point cloud; compare the second coordinate in the second grid point cloud with the first coordinate in the first grid point cloud, and determine whether there is an overlapping area between the first initial point cloud and the second initial point cloud according to the comparison result.

[0140] In one embodiment, the determination module 808 is further configured to: if there is no overlapping area between the first initial point cloud and the second initial point cloud, determine that the obstacle is a first-category obstacle, including: if there is no first coordinate identical to the second coordinate, determine that the obstacle is a first-category obstacle, wherein the first-category obstacle is an obstacle invisible to laser; if there is an overlapping area between the first initial point cloud and the second initial point cloud, determine that the obstacle is a second-category obstacle, including: if there is a first coordinate identical to the second coordinate, determine that the obstacle is a second-category obstacle, wherein the second-category obstacle is an obstacle visible to laser.

[0141] In one embodiment, the obstacle judgment device also includes an update module, which is used to: obtain a target map and an error threshold of the second sensor; the target map is a map used during the operation of the device; when the obstacle is determined to be a first-class obstacle, if the interval distance is less than the error threshold, the target map is updated based on the second initial point cloud to obtain an updated target map; when the obstacle is determined to be a second-class obstacle, the target map is updated based on the first initial point cloud to obtain an updated target map.

[0142] In one embodiment, the updating module is further configured to: based on a preset clearing time, clear obstacles corresponding to the second initial point cloud in the updated target map to obtain a cleared target map.

[0143] In one embodiment, the obstacle judgment device also includes an obstacle avoidance module, which is used to: determine the obstacle avoidance method corresponding to the obstacle based on the interval distance; if the interval distance meets the preset deceleration distance range and the detection direction of the second sensor is the same as the running direction of the equipment, then decelerate the operation; if the interval distance is less than the error threshold of the second sensor, then generate an obstacle avoidance path corresponding to the obstacle based on the interval distance, and avoid the obstacle based on the obstacle avoidance path.

[0144] In one embodiment, the obstacle avoidance module is further configured to: obtain a reserved distance, determine a detour distance corresponding to the obstacle based on the interval distance and the reserved distance; and generate an obstacle avoidance path corresponding to the obstacle based on the detour distance.

[0145] Each module in the obstacle determination device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0146] In one embodiment, a computer device is provided, which may be device 102, and its internal structure diagram may be shown in Figure 9. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication, where the wireless communication can be achieved via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements an obstacle detection method.

[0147] Those skilled in the art will understand that the structure shown in Figure 9 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0148] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0152] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0153] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining an obstacle, the method comprising: Acquire a first initial point cloud collected by the first sensor and a distance between the device and the obstacle collected by the second sensor at the same time; Acquire a field of view angle of the second sensor, and obtain a second initial point cloud based on the field of view angle and the interval distance; Determine whether the first initial point cloud and the second initial point cloud have an overlapping area; If the first initial point cloud and the second initial point cloud do not have an overlapping area, then the obstacle is determined to be a first type of obstacle; and If there is an overlapping area between the first initial point cloud and the second initial point cloud, the obstacle is determined to be a second type of obstacle.

2. The method according to claim 1, characterized in that The second sensor is an ultrasonic sensor, and acquiring the field of view angle of the second sensor and obtaining the second initial point cloud based on the field of view angle and the interval distance includes: Based on preset division angles, the field of view angle is divided to obtain a plurality of offset angles; Based on the interval distance and the offset angle, calculating the initial coordinates of the obstacle point corresponding to the offset angle; the plurality of obstacle points are used to characterize the obstacle; and Based on the initial coordinates of the obstacle points corresponding to the multiple offset angles, a second initial point cloud is obtained.

3. The method according to claim 2, characterized in that The dividing of the field of view angle based on the preset dividing angle to obtain a plurality of offset angles includes: Acquire an initial coordinate system with the second sensor as the origin, and convert the field of view angle into a detection angle range in the initial coordinate system; and The detection angle range is divided based on preset division angles to obtain a plurality of offset angles.

4. The method according to claim 1, characterized in that: The first sensor is a laser radar and / or a depth camera, and the determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud includes: Based on a first extrinsic parameter of the first sensor, converting the first initial point cloud into a first intermediate point cloud in a target coordinate system, and based on a second extrinsic parameter of the second sensor, converting the second initial point cloud into a second intermediate point cloud in the target coordinate system; Obtain the size of the grid map and the resolution corresponding to the grid map; Based on the size and the resolution, projecting the first intermediate point cloud into the grid map to obtain a first grid point cloud, and projecting the second intermediate point cloud into the grid map to obtain a second grid point cloud; Comparing the second coordinates in the second grid point cloud with the first coordinates in the first grid point cloud, and determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud according to the comparison result; If there is no overlapping area between the first initial point cloud and the second initial point cloud, determining that the obstacle is a first-category obstacle includes: If there is no first coordinate that is the same as the second coordinate, determining that the obstacle is a first-category obstacle, wherein the first-category obstacle is an obstacle that is invisible to lasers; and If there is an overlapping area between the first initial point cloud and the second initial point cloud, determining that the obstacle is a second type of obstacle includes: If there is a first coordinate that is the same as the second coordinate, it is determined that the obstacle is a second-type obstacle, wherein the second-type obstacle is a laser visible obstacle.

5. The method according to claim 4, characterized in that The projecting, based on the size and the resolution, the first intermediate point cloud to the grid map to obtain a first grid point cloud, and the projecting, based on the size and the resolution, the second intermediate point cloud to the grid map to obtain a second grid point cloud comprises: Based on the size, each first intermediate coordinate in the first intermediate point cloud is translated to obtain a first translated point cloud; Dividing each first translation coordinate in the first translation point cloud by the resolution to obtain a first grid point cloud; Translating each second intermediate coordinate in the second intermediate point cloud based on the size to obtain a second translated point cloud; and Each second translation coordinate in the second translation point cloud is divided by the resolution to obtain a second grid point cloud.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Acquire a target map and an error threshold of the second sensor; the target map is a map used during the operation of the device; In the case where it is determined that the obstacle is a first type of obstacle, if the interval distance is less than the error threshold, updating the target map based on the second initial point cloud to obtain an updated target map; and When it is determined that the obstacle is a second type of obstacle, the target map is updated based on the first initial point cloud to obtain an updated target map.

7. The method according to claim 6, characterized in that After the target map is updated based on the second initial point cloud to obtain an updated target map, the method further includes: Based on a preset clearing time, the obstacles corresponding to the second initial point cloud in the updated target map are cleared to obtain a cleared target map.

8. The method according to claim 6, characterized in that In the case where it is determined that the obstacle is a first type of obstacle, if the interval distance is less than the error threshold, updating the target map based on the second initial point cloud to obtain an updated target map includes: When it is determined that the obstacle is a first type of obstacle, obtaining an error threshold of the target map and the second sensor; comparing the separation distance with the error threshold; If the interval distance is less than the error threshold, obtaining a second extrinsic parameter of the second sensor, and converting the second initial point cloud into a second intermediate point cloud in a target coordinate system based on the second extrinsic parameter; the target coordinate system is a coordinate system with the center of the device as the origin; acquiring a conversion relationship between the target coordinate system and the target map, and based on the conversion relationship, converting the second intermediate point cloud to obtain a second target point cloud; and The second target point cloud is added to the target map to obtain an updated target map.

9. The method according to claim 1, characterized in that: In the case where it is determined that the obstacle is a first type of obstacle, the method further includes: Based on the interval distance, determining an obstacle avoidance method corresponding to the obstacle; If the interval distance satisfies the preset deceleration distance interval, and the detection direction of the second sensor is the same as the running direction of the device, decelerate the running; and If the interval distance is less than the error threshold of the second sensor, an obstacle avoidance path corresponding to the obstacle is generated based on the interval distance, and the obstacle is avoided based on the obstacle avoidance path.

10. The method according to claim 9, characterized in that The generating the obstacle avoidance path corresponding to the obstacle based on the interval distance includes: Acquire a reserved distance, and determine a detour distance corresponding to the obstacle based on the interval distance and the reserved distance; and Based on the detour distance, an obstacle avoidance path corresponding to the obstacle is generated.

11. An obstacle determination device, comprising: An acquisition module, used to acquire a first initial point cloud acquired by the first sensor and a distance between the point cloud and the obstacle acquired by the second sensor; A division module, used for acquiring a field of view angle of the second sensor, and obtaining a second initial point cloud based on the field of view angle and the interval distance; A judgment module, used to determine whether the first initial point cloud and the second initial point cloud have an overlapping area; and A determination module is used to determine that the obstacle is a first type of obstacle if there is no overlapping area between the first initial point cloud and the second initial point cloud; if the first initial point cloud and the second initial point cloud have an overlapping area, then determine that the obstacle is a second type of obstacle.

12. The device according to claim 11, characterized in that The partitioning module is also used for: Based on preset division angles, the field of view angle is divided to obtain a plurality of offset angles; Based on the interval distance and the offset angle, calculating the initial coordinates of the obstacle point corresponding to the offset angle; The plurality of obstacle points are used to represent the obstacle; and Based on the initial coordinates of the obstacle points corresponding to the multiple offset angles, a second initial point cloud is obtained.

13. The device according to claim 11, characterized in that The judging module is also used for: Based on a first extrinsic parameter of the first sensor, converting the first initial point cloud into a first intermediate point cloud in a target coordinate system, and based on a second extrinsic parameter of the second sensor, converting the second initial point cloud into a second intermediate point cloud in the target coordinate system; Obtain the size of the grid map and the resolution corresponding to the grid map; Based on the size and the resolution, projecting the first intermediate point cloud into the grid map to obtain a first grid point cloud, and projecting the second intermediate point cloud into the grid map to obtain a second grid point cloud; Comparing the second coordinates in the second grid point cloud with the first coordinates in the first grid point cloud, and determining whether there is an overlapping area between the first initial point cloud and the second initial point cloud according to the comparison result; If there is no overlapping area between the first initial point cloud and the second initial point cloud, determining that the obstacle is a first-category obstacle includes: if there is no first coordinate that is the same as the second coordinate, determining that the obstacle is a first-category obstacle, wherein the first-category obstacle is an obstacle invisible to laser; and If there is an overlapping area between the first initial point cloud and the second initial point cloud, the obstacle is judged to be a second-category obstacle, including: if there is a first coordinate that is the same as the second coordinate, then the obstacle is determined to be a second-category obstacle, wherein the second-category obstacle is a laser visible obstacle.

14. The device according to claim 11, characterized in that The obstacle determination device further includes an updating module, which is used to: Acquire a target map and an error threshold of the second sensor; the target map is a map used during the operation of the device; In the case where it is determined that the obstacle is a first type of obstacle, if the interval distance is less than the error threshold, updating the target map based on the second initial point cloud to obtain an updated target map; and When it is determined that the obstacle is a second type of obstacle, the target map is updated based on the first initial point cloud to obtain an updated target map.

15. The device according to claim 14, characterized in that The update module is also used for: Based on a preset clearing time, the obstacles corresponding to the second initial point cloud in the updated target map are cleared to obtain a cleared target map.

16. The device according to claim 11, characterized in that The obstacle determination device further includes an obstacle avoidance module, which is used to: Based on the interval distance, determining an obstacle avoidance method corresponding to the obstacle; If the interval distance satisfies the preset deceleration distance interval, and the detection direction of the second sensor is the same as the running direction of the device, deceleration is performed; and If the interval distance is less than the error threshold of the second sensor, an obstacle avoidance path corresponding to the obstacle is generated based on the interval distance, and the obstacle is avoided based on the obstacle avoidance path.

17. The device according to claim 16, characterized in that The obstacle avoidance module is also used for: Acquire a reserved distance, and determine a detour distance corresponding to the obstacle based on the interval distance and the reserved distance; and Based on the detour distance, an obstacle avoidance path corresponding to the obstacle is generated.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 10 when executing the computer program.

19. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

20. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images