Method, device and medium for removing obstacles in a non-travelable area of a mobile carrier
Through instant positioning and map construction SLAM algorithm and bird's-eye view processing technology, the problem of low efficiency of high-precision map display is solved, efficient acquisition and processing of obstacle information in the autonomous driving system is realized, and the efficiency of the autonomous driving system is improved.
Patent Information
- Application Number
- CN202010685784.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-07-16
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-07-16
AI Technical Summary
In the prior art, the efficiency of displaying obstacles in the unmovable area of the mobile carrier based on high-precision maps is low, resulting in low efficiency of the autonomous driving system when acquiring information about surrounding obstacles.
The SLAM algorithm is used to build an environmental map, and the positioning and orientation information of the mobile carrier is obtained in real time, a bird's-eye view is generated, and environmental information of the infeasible areas is deleted in the bird's-eye view to improve the efficiency of obstacle display.
By deleting obstacle information in incoming areas without high-precision maps, the deployment efficiency of SLAM maps in different scenarios is improved and the display efficiency of dynamic obstacles is improved.
Smart Images

Figure CN111912418B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to a method, device and medium for deleting obstacles in a non-drivable area of a mobile carrier, and belongs to the field of computer technology. Background Art
[0002] With the rapid development of autonomous driving technology, the autonomous driving system needs to obtain information about surrounding obstacles during the autonomous driving process in order to achieve the purpose of safe driving on the road.
[0003] The existing method for obtaining obstacle information around a mobile carrier includes: obtaining a high-precision map; deleting obstacles outside the lane area in the high-precision map and only displaying obstacles inside the lane area. For example, displaying the vehicle in front of the mobile carrier and not displaying the green belt near the mobile carrier.
[0004] However, since HD maps are high-precision, finely defined maps with accuracy at the decimeter level, their production efficiency is low, which leads to the problem of low efficiency in displaying the mobile environment of mobile carriers based on the HD maps. Summary of the invention
[0005] The present application provides a method, device and medium for deleting obstacles in a non-travelable area for a mobile carrier, which can solve the problem of low efficiency in displaying obstacles in a non-travelable area for a mobile carrier based on a high-precision map. The present application provides the following technical solutions:
[0006] In a first aspect, a method for removing obstacles in a non-drivable area of a mobile carrier is provided, the method comprising:
[0007] During the movement of the mobile carrier on the mobile plane, an environmental map of the current mobile environment of the mobile carrier is constructed based on a simultaneous positioning and mapping SLAM algorithm, wherein the environmental map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier;
[0008] Acquiring real-time positioning information of the mobile carrier based on the initial positioning information in real time;
[0009] Acquiring real-time orientation information of the mobile carrier based on the initial orientation information in real time;
[0010] Acquire a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, the bird's-eye view being used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, the preset spatial range comprising a spatial range in a direction of travel indicated by the real-time orientation information and a spatial range in a vertical direction perpendicular to the direction of travel;
[0011] For the local map in the environmental map corresponding to the bird's-eye view, environmental information of the non-drivable area in the local map is deleted from the bird's-eye view to obtain a processed bird's-eye view.
[0012] Optionally, deleting the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain a processed bird's-eye view includes:
[0013] Determining an image intersection between the bird's-eye view image and the local map;
[0014] Performing a logical AND operation on the intersection of the bird's-eye view and the image to obtain the processed bird's-eye view;
[0015] or,
[0016] A logical AND operation is performed on the bird's-eye view and the local map to obtain the processed bird's-eye view.
[0017] Optionally, for the local map in the environmental map corresponding to the bird's-eye view, before deleting the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain the processed bird's-eye view, the method further includes:
[0018] The environment map is binarized to obtain a binarized environment map; the binarized environment map includes a first pixel area and a second pixel area, the first pixel area is used to indicate a drivable area, and the second pixel area is used to indicate a non-drivable area.
[0019] Optionally, the method further comprises:
[0020] Determine whether to start the static obstacle removal function;
[0021] When it is determined to start the static obstacle deletion function, the step of triggering the execution of the local map corresponding to the bird's-eye view in the environmental map, deleting the environmental information of the non-drivable area in the local map in the bird's-eye view, and obtaining a processed bird's-eye view is performed.
[0022] Optionally, a laser detection component is installed on the mobile carrier, and the laser detection component is used to collect point cloud data of reflectors within the preset spatial range; the step of obtaining the real-time positioning information and the bird's-eye view corresponding to the real-time orientation information includes:
[0023] Acquire point cloud data collected by the laser detection component at the position corresponding to the real-time positioning information; the point cloud data includes three-dimensional coordinates of sampling points, sampling point density and reflection signal intensity; the three-dimensional coordinates are used to indicate the three-dimensional position of the corresponding sampling point relative to the laser detection component;
[0024] The sampling points are projected onto a two-dimensional plane according to the three-dimensional coordinates with a height direction perpendicular to the moving plane as a projection direction to obtain the bird's-eye view; the two-dimensional plane is parallel to the moving plane; or, the two-dimensional plane is the moving plane.
[0025] Optionally, taking a height direction perpendicular to the moving plane as a projection direction and projecting the sampling points onto a two-dimensional plane according to the three-dimensional coordinates to obtain the bird's-eye view includes:
[0026] Acquiring a relative position relationship between the laser detection assembly and the mobile carrier;
[0027] Based on the relative position relationship, the three-dimensional coordinates of the sampling points are converted into a common coordinate system to obtain the converted three-dimensional coordinates; the common coordinate system is a coordinate system established based on the position of the mobile carrier;
[0028] The converted three-dimensional coordinates are projected onto a two-dimensional plane according to the projection direction to obtain the bird's-eye view.
[0029] Optionally, for the local map in the environmental map corresponding to the bird's-eye view, after deleting the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain the processed bird's-eye view, the method further includes:
[0030] Obstacle recognition is performed on the processed bird's-eye view to obtain a dynamic obstacle recognition result of the processed bird's-eye view.
[0031] In a second aspect, a device for deleting obstacles in a non-travelable area of a mobile carrier is provided, the device comprising:
[0032] A map construction module, used to construct an environmental map of the current mobile environment of the mobile carrier based on a simultaneous positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, wherein the environmental map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier;
[0033] A real-time positioning module, configured to obtain the real-time positioning information of the mobile carrier in real time based on the initial positioning information; and obtain the real-time orientation information of the mobile carrier in real time based on the initial orientation information;
[0034] a bird's-eye view acquisition module, used to acquire a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, wherein the bird's-eye view is used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, wherein the preset spatial range includes a spatial range in a direction of travel indicated by the real-time orientation information and a spatial range in a vertical direction perpendicular to the direction of travel;
[0035] The bird's-eye view processing module is used to delete the environmental information of the non-drivable area in the local map corresponding to the bird's-eye view in the bird's-eye view, so as to obtain a processed bird's-eye view.
[0036] In a third aspect, a device for deleting obstacles in a non-drivable area for a mobile carrier is provided, the device comprising a processor and a memory; a program is stored in the memory, and the program is loaded and executed by the processor to implement the method for deleting obstacles in a non-drivable area for a mobile carrier as described in the first aspect.
[0037] In a fourth aspect, a computer-readable storage medium is provided, wherein a program is stored in the storage medium, and when the program is executed by the processor, the method for deleting obstacles in a non-drivable area of a mobile carrier as described in the first aspect is used.
[0038] The beneficial effects of the present application are as follows: by constructing an environmental map of the current mobile environment of the mobile carrier based on the real-time positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, the environmental map includes the initial positioning information of the mobile carrier in the initial state and the initial orientation information of the mobile carrier; acquiring the real-time positioning information of the mobile carrier in real time based on the initial positioning information; acquiring the real-time orientation information of the mobile carrier in real time based on the initial orientation information; acquiring a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, the bird's-eye view being used to represent the actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, the preset spatial range including the spatial range in the direction of travel indicated by the real-time orientation information and the spatial range in the vertical direction perpendicular to the direction of travel; for the local map in the environmental map corresponding to the bird's-eye view, deleting the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain a processed bird's-eye view; the problem of low efficiency in displaying obstacles in the non-drivable area of the mobile carrier based on the high-precision map can be solved; the deployment efficiency of the SLAM map in different scenarios can be improved; and the environmental information in the non-drivable area can be deleted without using a high-precision map.
[0039] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present application in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 It is a structural schematic diagram of a device for removing obstacles in a non-drivable area of a mobile carrier provided by an embodiment of the present application;
[0041] Figure 2 is a flow chart of a method for deleting obstacles in a non-drivable area of a mobile carrier provided by an embodiment of the present application;
[0042] Figure 3 is a schematic diagram of a binarized environment map provided by an embodiment of the present application;
[0043] Figure 4 It is a schematic diagram of extracting a local map from an environment map provided by an embodiment of the present application;
[0044] Figure 5 It is a schematic diagram of deleting environmental information of a non-drivable area in the content of a local map from a bird's-eye view provided by an embodiment of the present application;
[0045] Figure 6 It is a block diagram of a device for deleting obstacles in a non-drivable area of a mobile carrier provided by an embodiment of the present application;
[0046] Figure 7 This is a block diagram of a device for deleting obstacles in a non-drivable area for a mobile carrier provided by another embodiment of the present application. DETAILED DESCRIPTION
[0047] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.
[0048] First, several terms involved in this application are introduced.
[0049] Simultaneous localization and mapping (SLAM): refers to the robot moving from an unknown position in an unknown environment, positioning itself according to position estimation and map during the movement, and realizing autonomous positioning and navigation of the robot at the same time.
[0050] The principles of the SLAM algorithm include: obtaining the robot's posture information and environmental observation data in real time; estimating the spatial uncertainty of the posture information and environmental observation data, thereby estimating the robot's positioning information; and building a map based on the environmental observation data and positioning information to obtain an environmental map. Among them, the environmental observation data is obtained by observing environmental landmarks. Usually, the environmental map obtained based on the SLAM algorithm includes the robot's drivable area, non-drivable area, and area to be detected. SLAM algorithms include but are not limited to: Gmapping, Karto, Hector, Cartographer, etc. This embodiment does not limit the type of SLAM algorithm.
[0051] Binarization: Setting the grayscale value of pixels on an image to 0 or 255 is the process of making the entire image appear obviously black and white.
[0052] Figure 1 1 is a schematic diagram of the structure of a device 100 for removing obstacles in a non-travelable area of a mobile carrier provided in an embodiment of the present application. The mobile carrier refers to a carrier that moves on a moving plane at a certain speed. Optionally, the mobile carrier may be a vehicle or a cleaning robot, etc. This embodiment does not limit the implementation of the mobile carrier. Figure 1 As shown, the device at least includes: a control component 110 and a sensor component 120 communicatively connected to the control component 110.
[0053] The sensor component 120 is installed on the mobile carrier. The sensor component 120 includes but is not limited to: an odometer, a gyroscope, a laser detection component, etc. Optionally, the laser detection component can be a laser radar, a stereo camera, or a time-of-flight camera, etc. This embodiment does not limit the device type of the laser detection component.
[0054] The sensor component 120 is used to collect sensor data and send the sensor data to the control component 110. Accordingly, the control component 110 supports acquiring the sensor data and constructing an environmental map of the current mobile environment of the mobile carrier based on the SLAM algorithm according to the sensor data when the mobile carrier moves on the mobile plane.
[0055] The laser detection component is used to emit a laser beam within a preset spatial range and collect point cloud data of a reflector when there is a reflector. The preset spatial range includes the spatial range in the moving direction of the mobile carrier and the spatial range in the vertical direction perpendicular to the moving direction.
[0056] The traveling direction may be the direction in which the mobile carrier is traveling, for example, if the mobile carrier moves backward, the traveling direction of the mobile carrier is backward; or, the traveling direction may be the direction in which the mobile carrier in a stationary state is about to travel.
[0057] The vertical direction perpendicular to the traveling direction includes: the vertical direction perpendicular to the traveling direction of the front side of the mobile carrier, the vertical direction perpendicular to the traveling direction of the rear side of the mobile carrier, the vertical direction perpendicular to the traveling direction of the left side of the mobile carrier, and the vertical direction perpendicular to the traveling direction of the right side of the mobile carrier.
[0058] A reflector is an object that can reflect the laser beam back to the laser detection component. Taking a vehicle as an example, the reflector may be a road edge, garbage, stone, other vehicles traveling near the vehicle, etc. This embodiment does not limit the type of reflector.
[0059] Point cloud data refers to a data set of points reflected by the surface of a reflector when a laser detection component emits a number of laser beams. In this embodiment, the point cloud data includes the three-dimensional coordinates of the sampling points, the sampling point density, and the reflected signal intensity. The three-dimensional coordinates are used to indicate the three-dimensional position of the corresponding sampling point relative to the laser detection component. Among them, the sampling point is the point reflected by the surface of the reflector.
[0060] The control component 110 supports obtaining point cloud data collected by the laser detection component; and generating a bird's-eye view based on the point cloud data.
[0061] The bird's-eye view refers to a two-dimensional image formed by projecting the sampling points onto a two-dimensional plane according to the three-dimensional coordinates (ie, converting the coordinate values in the height direction indicated by the three-dimensional coordinates to 0) with the height direction perpendicular to the moving plane as the projection direction.
[0062] In this embodiment, the control component 110 is used to: construct an environmental map of the current mobile environment of the mobile carrier based on the real-time positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, the environmental map including the initial positioning information of the mobile carrier in the initial state and the initial orientation information of the mobile carrier; obtain the real-time positioning information of the mobile carrier in real time based on the initial positioning information; obtain the real-time orientation information of the mobile carrier in real time based on the initial orientation information; obtain a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, the bird's-eye view is used to represent the actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, the preset spatial range includes the spatial range in the direction of travel indicated by the real-time orientation information and the spatial range in the vertical direction perpendicular to the direction of travel; for the local map in the environmental map corresponding to the bird's-eye view, delete the environmental information of the non-drivable area in the local map in the bird's-eye view to obtain a processed bird's-eye view.
[0063] Optionally, this embodiment is described by taking the example of the control component 110 being installed in the control system of a mobile carrier (such as a vehicle). In other implementations, the control component 110 may also be implemented in other devices independent of the mobile carrier. This embodiment does not limit the implementation method of the control component 110.
[0064] Since the current mobile environment of the mobile carrier includes static obstacles and dynamic obstacles, the environmental map determined based on the SLAM algorithm includes static obstacles, and the corresponding bird's-eye view includes static obstacles and dynamic obstacles. Therefore, by deleting the environmental information of the non-drivable area, the static obstacles can be filtered out and only dynamic obstacles can be displayed. Dynamic obstacles are usually other mobile carriers near the mobile carrier. In this way, only dynamic obstacles can be displayed without using high-precision maps, which improves the display efficiency of dynamic obstacles.
[0065] In this application, static obstacles refer to stationary objects in a mobile environment, such as green belts, roadblocks, etc. in the vehicle's mobile environment; dynamic obstacles refer to objects in a mobile environment whose positions change over time, such as other vehicles in the vehicle's mobile environment.
[0066] Figure 2 is a flowchart of a method for removing obstacles in a non-travelable area of a mobile carrier provided by an embodiment of the present application. This embodiment uses the method for Figure 1 The device 100 for deleting obstacles in a non-travelable area for a mobile carrier is used as an example for description, and the execution subject of each step is the control component 110 in the device 100 for deleting obstacles in a non-travelable area for a mobile carrier. The method includes at least the following steps:
[0067] Step 201, when the mobile carrier moves on the mobile plane, an environment map of the current mobile environment of the mobile carrier is constructed based on the SLAM algorithm, and the environment map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier.
[0068] The orientation information may be the orientation angle of the front of the mobile carrier.
[0069] Optionally, the mobile carrier determines whether to start the static obstacle removal function; when it is determined that the static obstacle removal function is started, step 201 is executed; when it is determined that the static obstacle removal function is not started, the process ends.
[0070] When constructing an environmental map, the mobile carrier obtains an environmental map by inputting the sensor data collected by the sensor components into the SLAM algorithm.
[0071] Optionally, after obtaining the environment map, the environment map is binarized to obtain a binarized environment map (refer to Figure 3). The binarized environment map includes a first pixel area and a second pixel area, the first pixel area is used to indicate a drivable area, and the second pixel area is used to indicate a non-drivable area. In one example, the pixel value of the drivable area is 0; the pixel value of the non-drivable area is 255.
[0072] Of course, the environment map may also include areas to be explored, and this embodiment does not limit the area division method of the environment map.
[0073] In other examples, the environment map output by the SLAM algorithm may be a binarized environment map. In this case, there is no need to perform the step of binarizing the environment map.
[0074] Step 202: acquiring real-time positioning information of the mobile carrier based on the initial positioning information; acquiring real-time orientation information of the mobile carrier based on the initial orientation information.
[0075] The mobile carrier can obtain the real-time orientation information in real time based on the initial orientation information through the gyroscope. Afterwards, the mobile carrier can calculate the real-time positioning information according to the driving time, driving speed and the real-time orientation information.
[0076] Step 203, obtain a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, and the bird's-eye view is used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information. The preset spatial range includes the spatial range in the direction of travel indicated by the real-time orientation information and the spatial range in the vertical direction perpendicular to the direction of travel.
[0077] In one example, a laser detection component is installed on the mobile carrier, and the laser detection component is used to collect point cloud data of reflective objects within a preset spatial range. At this time, obtaining a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information includes: obtaining point cloud data within the preset spatial range collected by the laser detection component at the position corresponding to the real-time positioning information; the point cloud data includes the three-dimensional coordinates of the sampling points, the sampling point density and the reflection signal intensity; the three-dimensional coordinates are used to indicate the three-dimensional position of the corresponding sampling points relative to the laser detection component; the height direction perpendicular to the moving plane is used as the projection direction, and the sampling points are projected onto the two-dimensional plane according to the three-dimensional coordinates to obtain a bird's-eye view; the two-dimensional plane is parallel to the moving plane; or, the two-dimensional plane is the moving plane.
[0078] Among them, taking the height direction perpendicular to the moving plane as the projection direction, projecting the sampling points onto the two-dimensional plane according to the three-dimensional coordinates to obtain a bird's-eye view, including: obtaining the relative position relationship between the laser detection component and the mobile carrier; based on the relative position relationship, converting the three-dimensional coordinates of the sampling points to a public coordinate system to obtain converted three-dimensional coordinates; the public coordinate system is a coordinate system established based on the position of the mobile carrier; projecting the converted three-dimensional coordinates onto the two-dimensional plane according to the projection direction to obtain a bird's-eye view.
[0079] Optionally, the two-dimensional plane is parallel to the moving plane; or, the two-dimensional plane is the moving plane.
[0080] The bird's-eye view refers to a two-dimensional image formed by projecting the sampling points onto a two-dimensional plane according to the three-dimensional coordinates (ie, converting the coordinate values in the height direction indicated by the three-dimensional coordinates to 0) with the height direction perpendicular to the moving plane as the projection direction.
[0081] The relative position relationship refers to the position relationship of the laser detection component relative to the mobile carrier. In one example, the three-dimensional coordinates are the coordinate values in the coordinate system established with the laser detection component as the coordinate origin, and the public coordinate system is a coordinate system established with the center position of the mobile carrier as the coordinate origin. At this time, the relative position relationship is the coordinate system conversion relationship between the coordinate system where the laser detection component is located and the public coordinate system.
[0082] Since the three-dimensional coordinates of the sampling point are relative to the coordinates of the laser detection component, that is, they are coordinate values in the coordinate system established based on the laser detection component; the coordinate system established based on the laser detection component is not applicable to the three-dimensional coordinates collected by other laser detection components. Therefore, in this embodiment, by converting the three-dimensional coordinates to a common coordinate system, the common coordinate system is applicable to the three-dimensional coordinates collected by each laser detection component after the conversion, so that the three-dimensional coordinates collected by each laser detection component can be combined to obtain an overall three-dimensional image.
[0083] According to the acquisition process of the bird's-eye view, when the mobile environment includes obstacles (including static obstacles and dynamic obstacles), the mobile carrier will obtain the point cloud data of the obstacle and generate a bird's-eye view with the obstacle based on the point cloud data. In this embodiment, the bird's-eye view also includes the position of the mobile carrier.
[0084] Step 204: for the local map in the environmental map corresponding to the bird's-eye view, delete the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain a processed bird's-eye view.
[0085] After the mobile carrier obtains the environment map and the bird's-eye view corresponding to the positioning information and orientation information in the environment map, it intercepts the part corresponding to the bird's-eye view in the environment map to obtain a local map. Figure 4, in the environmental map (a), a portion 41 corresponding to the bird's-eye view is intercepted to obtain a local map (b).
[0086] Optionally, environmental information about non-drivable areas in a local map is deleted from the bird's-eye view to obtain a processed bird's-eye view, including: determining an image intersection between the bird's-eye view and the local map; performing a logical AND operation on the bird's-eye view and the image intersection to obtain a processed bird's-eye view; or performing a logical AND operation on the bird's-eye view and the local map to obtain a processed bird's-eye view.
[0087] The logical AND operation means: the result of 255 and 0 is 0; the result of 255 and 255 is 255; the result of 0 and 0 is 0.
[0088] The environmental information of the non-drivable area in the local map is deleted from the bird's-eye view, and the processed bird's-eye view can be expressed as: bird's-eye view - (bird's-eye view ∩ local map); or, expressed as bird's-eye view - local map.
[0089] For example: Reference Figure 5 , the bird's-eye view 51 includes a mobile carrier 511, a green area 512 and a vehicle 513 (dynamic obstacle) located in front of the mobile carrier 511; the local map 52 includes a green area 521. After deleting the area that is the same as the local map 52 from the bird's-eye view 51, the processed bird's-eye view 53 no longer includes the green area 521, but only includes the vehicle 513.
[0090] Optionally, the mobile carrier may display the processed bird's-eye view.
[0091] Optionally, the mobile carrier may perform obstacle recognition on the processed bird's-eye view to obtain a dynamic obstacle recognition result of the processed bird's-eye view.
[0092] In summary, the method for deleting obstacles in the non-drivable area of a mobile carrier provided in the present embodiment is to construct an environmental map of the current mobile environment of the mobile carrier based on the real-time positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, wherein the environmental map includes the initial positioning information of the mobile carrier in the initial state and the initial orientation information of the mobile carrier; the real-time positioning information of the mobile carrier is obtained in real time based on the initial positioning information; the real-time orientation information of the mobile carrier is obtained in real time based on the initial orientation information; a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information is obtained, and the bird's-eye view is used to represent the actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, and the preset spatial range includes the spatial range in the direction of travel indicated by the real-time orientation information and the spatial range in the vertical direction perpendicular to the direction of travel; for the local map corresponding to the bird's-eye view in the environmental map, the environmental information of the non-drivable area in the local map is deleted from the bird's-eye view to obtain a processed bird's-eye view; the problem of low efficiency in displaying obstacles in the non-drivable area of a mobile carrier based on a high-precision map can be solved; the deployment efficiency of the SLAM map in different scenarios can be improved; and the environmental information in the non-drivable area can be deleted without using a high-precision map.
[0093] Figure 6 is a block diagram of a device for removing obstacles in a non-travelable area of a mobile carrier provided by an embodiment of the present application. In this embodiment, the device is applied to Figure 1 The control components in the device for removing obstacles in the non-travelable area of the mobile carrier are used as an example for explanation. The device comprises at least the following modules: a map construction module 610, a real-time positioning module 620, a bird's-eye view acquisition module 630 and a bird's-eye view processing module 640.
[0094] A map construction module 610 is used to construct an environmental map of the current mobile environment of the mobile carrier based on a simultaneous positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, wherein the environmental map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier;
[0095] A real-time positioning module 620 is used to obtain the real-time positioning information of the mobile carrier in real time based on the initial positioning information; and to obtain the real-time orientation information of the mobile carrier in real time based on the initial orientation information;
[0096] A bird's-eye view acquisition module 630 is used to acquire a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, wherein the bird's-eye view is used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, wherein the preset spatial range includes a spatial range in a direction of travel indicated by the real-time orientation information and a spatial range in a vertical direction perpendicular to the direction of travel;
[0097] The bird's-eye view processing module 640 is used to delete the environmental information of the non-drivable area in the local map corresponding to the bird's-eye view in the environmental map, so as to obtain a processed bird's-eye view.
[0098] For relevant details, refer to the above method embodiment.
[0099] It should be noted that: the device for deleting obstacles in the non-drivable area of the mobile carrier provided in the above embodiment only uses the division of the above functional modules as an example when deleting obstacles in the non-drivable area of the mobile carrier. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device for deleting obstacles in the non-drivable area of the mobile carrier is divided into different functional modules to complete all or part of the functions described above. In addition, the device for deleting obstacles in the non-drivable area of the mobile carrier provided in the above embodiment and the method embodiment for deleting obstacles in the non-drivable area of the mobile carrier belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0100] Figure 7 is a block diagram of a device for removing obstacles in a non-travelable area of a mobile carrier provided by an embodiment of the present application. The device may include Figure 1 The control component 110 in the device 100 for deleting obstacles in a non-drivable area of a mobile carrier is shown. The device at least includes a processor 701 and a memory 702.
[0101] The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 701 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
[0102] The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one instruction, which is used to be executed by the processor 701 to implement the method for deleting obstacles in the non-drivable area of the mobile carrier provided in the method embodiment of the present application.
[0103] In some embodiments, the device for deleting obstacles in the non-travelable area of the mobile carrier may also optionally include: a peripheral device interface and at least one peripheral device. The processor 701, the memory 702 and the peripheral device interface may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface via a bus, a signal line or a circuit board. Schematically, the peripheral devices include but are not limited to: a radio frequency circuit, a touch display screen, an audio circuit, and a power supply.
[0104] Of course, the device for removing obstacles in the non-drivable area of the mobile carrier may also include fewer or more components, which is not limited in this embodiment.
[0105] Optionally, the present application also provides a computer-readable storage medium, in which a program is stored, and the program is loaded and executed by a processor to implement the method of deleting obstacles in a non-drivable area of a mobile carrier in the above method embodiment.
[0106] Optionally, the present application also provides a computer product, which includes a computer-readable storage medium, in which a program is stored, and the program is loaded and executed by a processor to implement the method of deleting obstacles in a non-drivable area of a mobile carrier in the above-mentioned method embodiment.
[0107] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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.
[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for removing obstacles in a non-travelable area of a mobile carrier, characterized in that: The method comprises: During the movement of the mobile carrier on the mobile plane, an environmental map of the current mobile environment of the mobile carrier is constructed based on a simultaneous positioning and mapping SLAM algorithm, wherein the environmental map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier; Binarization is performed on the environment map to obtain a binarized environment map; the binarized environment map includes a first pixel area and a second pixel area, the first pixel area is used to indicate a drivable area, and the second pixel area is used to indicate a non-drivable area; Acquiring real-time positioning information of the mobile carrier based on the initial positioning information in real time; Acquiring real-time orientation information of the mobile carrier based on the initial orientation information in real time; Acquire a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, the bird's-eye view being used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, the preset spatial range comprising a spatial range in a direction of travel indicated by the real-time orientation information and a spatial range in a vertical direction perpendicular to the direction of travel; For the local map in the environmental map corresponding to the bird's-eye view, deleting the environmental information of the non-drivable area in the local map from the bird's-eye view to obtain a processed bird's-eye view, including: determining the image intersection between the bird's-eye view and the local map; performing a logical AND operation on the bird's-eye view and the image intersection to obtain the processed bird's-eye view; or performing a logical AND operation on the bird's-eye view and the local map to obtain the processed bird's-eye view; Obstacle identification is performed on the processed bird's-eye view through a laser detection component to obtain a dynamic obstacle identification result of the processed bird's-eye view, wherein a laser detection component is installed on the mobile carrier, and the laser detection component is used to collect point cloud data of reflectors within the preset spatial range.
2. The method according to claim 1, characterized in that The method further comprises: Determine whether to start the static obstacle removal function; When it is determined to start the static obstacle deletion function, the step of triggering the execution of the local map corresponding to the bird's-eye view in the environmental map, deleting the environmental information of the non-drivable area in the local map in the bird's-eye view, and obtaining a processed bird's-eye view is performed.
3. The method according to claim 1, characterized in that The obtaining of the bird's-eye view corresponding to the real-time positioning information and the real-time orientation information includes: Acquire point cloud data collected by the laser detection component at the position corresponding to the real-time positioning information; the point cloud data includes three-dimensional coordinates of sampling points, sampling point density and reflection signal intensity; the three-dimensional coordinates are used to indicate the three-dimensional position of the corresponding sampling point relative to the laser detection component; The sampling points are projected onto a two-dimensional plane according to the three-dimensional coordinates with a height direction perpendicular to the moving plane as a projection direction to obtain the bird's-eye view; the two-dimensional plane is parallel to the moving plane; or, the two-dimensional plane is the moving plane.
4. The method according to claim 3, characterized in that The step of taking the height direction perpendicular to the moving plane as the projection direction and projecting the sampling points onto a two-dimensional plane according to the three-dimensional coordinates to obtain the bird's-eye view includes: Acquiring a relative position relationship between the laser detection assembly and the mobile carrier; Based on the relative position relationship, the three-dimensional coordinates of the sampling points are converted into a common coordinate system to obtain the converted three-dimensional coordinates; the common coordinate system is a coordinate system established based on the position of the mobile carrier; The converted three-dimensional coordinates are projected onto a two-dimensional plane according to the projection direction to obtain the bird's-eye view.
5. A device for removing obstacles in a non-travelable area of a mobile carrier, characterized in that: The device comprises: A map construction module is used to construct an environmental map of the current mobile environment of the mobile carrier based on a simultaneous positioning and map construction SLAM algorithm during the movement of the mobile carrier on the mobile plane, wherein the environmental map includes initial positioning information of the mobile carrier in an initial state and initial orientation information of the mobile carrier; and is also used to perform binarization processing on the environmental map to obtain a binarized environmental map; the binarized environmental map includes a first pixel area and a second pixel area, wherein the first pixel area is used to indicate a drivable area, and the second pixel area is used to indicate a non-drivable area; A real-time positioning module, configured to obtain the real-time positioning information of the mobile carrier in real time based on the initial positioning information; and obtain the real-time orientation information of the mobile carrier in real time based on the initial orientation information; a bird's-eye view acquisition module, used to acquire a bird's-eye view corresponding to the real-time positioning information and the real-time orientation information, wherein the bird's-eye view is used to represent actual environmental information within a preset spatial range determined based on the real-time positioning information and the real-time orientation information, wherein the preset spatial range includes a spatial range in a direction of travel indicated by the real-time orientation information and a spatial range in a vertical direction perpendicular to the direction of travel; A bird's-eye view processing module is used to delete the environmental information of the non-drivable area in the local map in the bird's-eye view corresponding to the local map in the environmental map, so as to obtain a processed bird's-eye view, including determining the image intersection between the bird's-eye view and the local map; performing a logical AND operation on the bird's-eye view and the image intersection to obtain the processed bird's-eye view; or performing a logical AND operation on the bird's-eye view and the local map to obtain the processed bird's-eye view; and is also used to perform obstacle identification on the processed bird's-eye view through a laser detection component to obtain a dynamic obstacle identification result of the processed bird's-eye view, wherein a laser detection component is installed on the mobile carrier, and the laser detection component is used to collect point cloud data of reflectors within the preset spatial range.
6. A device for removing obstacles in a non-travelable area of a mobile carrier, characterized in that: The device includes a processor and a memory; the memory stores a program, and the program is loaded and executed by the processor to implement the method for deleting obstacles in a non-drivable area of a mobile carrier as described in any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that: The storage medium stores a program, and when the program is executed by the processor, it is used to implement the method for deleting obstacles in a non-drivable area of a mobile carrier as described in any one of claims 1 to 4.
