Regional perception information generation method and device, electronic equipment and storage medium

Abstract

The invention provides a region perception information generation method and device, electronic equipment and a storage medium, and relates to the technical field of road side perception, and the method comprises the steps: carrying out the grid division of an obtained region map, and determining the grid state corresponding to each grid obtained through division based on the region map; dividing the regional map into a plurality of target regions, and determining a region state corresponding to each target region according to grid states corresponding to grids in the target regions; based on the region state corresponding to each target region, generating region sensing information corresponding to the region map; and when the area state is the partial driving state, changing the area state corresponding to the target area based on the reference area state set. According to the method, the region state of the target region is determined based on the grid state, the target region is processed based on the reference region state set in the process of generating the region sensing information, and the information generation efficiency is improved while the accuracy of the region sensing information is ensured.

Description

Technical Field

[0001] The present invention relates to the field of roadside perception technology, and in particular to a method, device, electronic device and storage medium for generating area perception information. Background Art

[0002] With the rapid development of autonomous driving related technologies, the field of intelligent transportation has also ushered in many key technological breakthroughs. Among them, roadside perception technology that can provide information such as regional perception has shown a pivotal position in the field of intelligent transportation. Nowadays, regional perception and other information have long become an indispensable reference for making intelligent decisions in the field of autonomous driving (such as guiding path planning based on regional perception information).

[0003] However, the methods currently used by roadside perception technology to generate regional perception information have obvious limitations, and often require sacrificing efficiency to ensure the accuracy of regional perception information, which restricts the further development of related technology fields such as autonomous driving. Summary of the invention

[0004] The problem solved by the present invention is how to balance efficiency and accuracy when generating regional perception information.

[0005] In order to solve the above problems, the present invention provides a method for generating region awareness information, comprising:

[0006] Divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state;

[0007] The regional map is divided into a plurality of target regions, and the regional state corresponding to each of the target regions is determined according to the grid state corresponding to the grid located in the target region; wherein the area of ​​each of the target regions is larger than the area of ​​each of the grids; and the regional state includes the drivable state, the non-drivable state and the partially drivable state;

[0008] Based on the area state corresponding to each of the target areas, area perception information corresponding to the area map is generated; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

[0009] Optionally, the determining the area state corresponding to each target area according to the grid state corresponding to the grid located in the target area includes:

[0010] Performing a state judgment operation on each of the target areas respectively to obtain a judgment result; wherein the state judgment operation includes judging whether the grid states corresponding to each of the grids in the target area are consistent;

[0011] When the judgment result is consistent, obtaining the area state corresponding to the target area according to the grid state;

[0012] When the judgment result is inconsistent, a segmentation operation is performed on the target area to obtain multiple new target areas, and for the new target areas, the process returns to the step of performing a state judgment operation on each of the target areas.

[0013] Optionally, before performing a segmentation operation on the target area to obtain a plurality of new target areas, the method further includes:

[0014] Determine a region segmentation level corresponding to the target region; wherein each time the segmentation operation is performed on the target region, the region segmentation level corresponding to each new target region obtained based on the target region increases by one level;

[0015] When the area segmentation level is greater than a preset level, the area state corresponding to the target area is set to the partially drivable state.

[0016] Optionally, the preset level is determined based on the acquired current environment information and a preset adjustment strategy, and the preset adjustment strategy includes:

[0017] When the current traffic flow determined according to the current environmental information is greater than a first preset threshold and shows an increasing trend, increasing the preset level;

[0018] When the current traffic flow is less than a second preset threshold and shows a decreasing trend, the preset level is reduced; wherein the first preset threshold is greater than the second preset threshold.

[0019] Optionally, the changing the region state corresponding to the target region based on a reference region state set includes:

[0020] Obtaining a target ratio corresponding to the non-drivable state in the reference area state set;

[0021] When the target proportion is greater than or equal to a preset proportion, the area state corresponding to the target area is changed to the non-drivable state;

[0022] When the target proportion is less than the preset proportion, a reference area is screened out from all candidate areas based on preset boundary conditions, and the target area is merged into the reference area; wherein the candidate area includes each of the target areas adjacent to the target area.

[0023] Optionally, the step of selecting a reference area from all candidate areas based on a preset boundary condition includes:

[0024] Respectively obtain the overlapping length of the boundary between each candidate area and the target area;

[0025] For each of the boundary overlap lengths, when the boundary overlap length is greater than a reference length, the candidate area corresponding to the boundary overlap length is used as the reference area; wherein the reference length is determined based on the contour information of the target area.

[0026] Optionally, the area map includes a road area and a non-driving area; and the determining, based on the area map, a grid state corresponding to each grid obtained by division includes:

[0027] Extracting a current drivable area from the area map according to the road area and the non-drivable area;

[0028] When the center of the grid corresponding to the grid is within the current drivable area, the grid state corresponding to the grid is the drivable state;

[0029] When the grid center corresponding to the grid is not within the current drivable area, the grid state corresponding to the grid is the non-drivable state.

[0030] In the present invention, the regional map is divided into grids, and the grid state corresponding to each grid is determined based on the regional map. Compared with the method of processing the regional map as a whole at the same time to generate regional perception information, it is beneficial to reduce the computing power consumption and the difficulty of data processing while providing a high-precision reference basis for regional perception information. Since the area of ​​the target area in the present invention is larger than the area of ​​the grid, each target area in the present invention can contain multiple grids. On the one hand, the grid state corresponding to the grid located in the target area can provide a reliable data basis for determining the regional state corresponding to the target area, ensuring the accuracy of regional perception information. On the other hand, when determining the regional state corresponding to the target area based on the grid state corresponding to the grid in the target area, the target area with a larger area can refine the information such as the grid state corresponding to the smaller area of ​​the grid, which can effectively reduce the data volume and is conducive to improving the efficiency of subsequent generation of regional perception information. Due to the complexity of the actual road conditions corresponding to the regional map, it is likely that the distribution of grid states corresponding to different grids will be more complicated. Accordingly, when extracting perception information such as grid status based on the regional status corresponding to the target area, it is easy to cause a decrease in perception accuracy (i.e., causing the regional status corresponding to some target areas to be partially drivable), affecting the accuracy and reliability of regional perception information. In the process of generating regional perception information based on the regional status corresponding to each target area, when the regional status corresponding to a certain target area is detected to be partially drivable, the reference state information corresponding to the target area (such as a reference regional status set) can be determined based on the regional status corresponding to the target area adjacent to it, thereby mining the correlation of different regional states based on the spatial continuity of different target areas. In this way, when the present invention performs regional status changes and other processing on such target areas based on the reference regional status set, it can effectively compensate for the uncertainty of the regional status corresponding to some target areas caused by the decrease in perception accuracy, ensure the accuracy of the final generated regional perception information, and then when generating perception information corresponding to the regional map, it can take into account both efficiency and accuracy.

[0031] The present invention also provides a region perception information generating device, comprising:

[0032] A division module, which is used to divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state;

[0033] A determination module, which is used to divide the area map into multiple target areas, and determine the area state corresponding to each of the target areas according to the grid state corresponding to the grid located in the target area; wherein the area of ​​each of the target areas is larger than the area of ​​each of the grids; and the area state includes the drivable state, the non-drivable state and the partially drivable state;

[0034] A generation module, which is used to generate area perception information corresponding to the area map based on the area state corresponding to each of the target areas; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

[0035] The advantages of the region awareness information generating device provided by the present invention and the region awareness information generating method compared with the prior art are basically the same, and will not be described in detail here.

[0036] The present invention also provides an electronic device, comprising a memory and a processor;

[0037] The memory is used to store computer programs;

[0038] The processor is used to implement the above-mentioned method for generating area awareness information when executing the computer program.

[0039] The advantages of the electronic device provided by the present invention and the method for generating area perception information are basically the same as those of the prior art, and will not be elaborated here.

[0040] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating area perception information as described above is implemented.

[0041] The advantages of the computer-readable storage medium provided by the present invention and the method for generating region perception information are substantially the same as those of the prior art and will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of a flow chart of a method for generating region awareness information according to an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of a flow chart of a method for generating region awareness information according to another embodiment of the present invention;

[0044] Figure 3 A schematic diagram of a process of dividing a regional map into grids in an embodiment of the present invention;

[0045] Figure 4 A schematic diagram of a process of dividing a regional map into multiple target regions in an embodiment of the present invention;

[0046] Figure 5 A schematic diagram of a process of performing a segmentation operation on a target region to obtain multiple new target regions in an embodiment of the present invention;

[0047] Figure 6 A schematic diagram of a process of generating region perception information based on the region state corresponding to each target region in an embodiment of the present invention;

[0048] Figure 7 A schematic diagram of the structure of a device for generating region awareness information according to an embodiment of the present invention;

[0049] Figure 8 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0051] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0052] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". Relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0053] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0054] At present, a single method such as geometric calculation is usually used to generate regional perception information, which determines the drivability of each area through real-time geometric calculation. However, this method often needs to process a large number of complex geometric operations in a short time. Especially in dynamic scenes, this method requires extremely high computing resources and has obvious limitations, which directly leads to low efficiency in generating regional perception information.

[0055] In view of the problems existing in the above-mentioned related technologies, this embodiment provides a region perception information method, device, electronic device and storage medium.

[0056] like Figure 1 As shown, a method for generating region awareness information provided by an embodiment of the present invention includes the following steps:

[0057] S1: dividing the acquired regional map into grids, and determining a grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state.

[0058] In the field of roadside information perception, regional perception information can serve aspects such as autonomous driving decision-making (such as path planning and false detection object filtering) and intelligent traffic management. For ease of understanding and description, this embodiment takes the regional perception requirements in the field of autonomous driving as an example to introduce the method for generating regional perception information.

[0059] Specifically, the regional map referred to in this embodiment represents a map corresponding to the area where information perception is required, which may include a local area in an acquired high-precision map. Assuming that a vehicle in the field of autonomous driving needs to perceive an area within its preset perception range (such as a 200-meter area around the vehicle), the regional map can be obtained by obtaining the current vehicle position (such as position coordinates) and a high-precision map, and extracting the area corresponding to the preset perception range from the high-precision map based on the current vehicle position. On this basis, the regional map can be grid-divided to obtain multiple grids (such as dividing the regional map into multiple grids of equal size based on preset division parameters).

[0060] In one embodiment, the grid state may reflect the vehicle's ability to pass through the area corresponding to the grid. For example, the drivable state in this embodiment may indicate that the vehicle can pass through the area corresponding to the grid, and the non-drivable state referred to in this embodiment may indicate that the vehicle cannot pass through the area corresponding to the grid (such as the area corresponding to the grid is a separation zone in the road surface, etc.). After the regional map is divided into grids, the grid state corresponding to each grid may be determined based on the regional map. For example, the road surface area in the regional map may be extracted (such as extraction based on image recognition) to determine whether the overlapping area corresponding to the grid and the road surface area exceeds a preset threshold (such as 90%). If so, the grid state is set to a drivable state. If not, the grid state is set to a non-drivable state.

[0061] In this embodiment, the regional map is divided into grids, and the grid state corresponding to each grid obtained by the division is determined based on the regional map. Compared with the method of processing the entire regional map at the same time to generate regional perception information, it is beneficial to reduce computing power consumption and data processing difficulty while providing high-precision information reference for regional perception information.

[0062] S2: Divide the regional map into multiple target areas, and determine the regional state corresponding to each target area according to the grid state corresponding to the grid located in the target area; wherein the area of ​​each target area is larger than the area of ​​each grid; the regional state includes a drivable state, a non-drivable state and a partially drivable state.

[0063] Specifically, after obtaining the regional map, the present embodiment can also divide the regional map into regions to obtain multiple target regions. In this embodiment, the area of ​​each target region is greater than the area of ​​each grid. For example, assuming that the shapes of the regions corresponding to the grid and the target region are both rectangular, when the regional map is divided into grids, the regional map can be divided into multiple grids of the same size according to the preset first reference size. On this basis, the regional map can be divided according to the preset second reference size to obtain multiple target regions of the same size. In this embodiment, the area corresponding to each target region can be greater than the area of ​​each grid by constraining the first reference size (such as the side length of the rectangle corresponding to the grid) to be less than the second reference size (such as the side length of the rectangle corresponding to the target region). In this embodiment, the regional state includes a drivable state, a non-drivable state, and a partially drivable state. In this embodiment, when the regional state is a drivable state (or a non-drivable state), the vehicle's traffic capacity in the corresponding area is similar to that when the above-mentioned grid state is a drivable state (or a non-drivable state), and will not be repeated here. The partially drivable state referred to in this embodiment may mean that the target area contains grids in both drivable and non-drivable states, and the vehicle's traffic capacity in the target area is uncertain.

[0064] In one embodiment, since the area of ​​the target area is larger than the area of ​​the grid, the area state of the target area can be determined according to the grid states corresponding to the grids located in the target area. For example, assuming that the target area contains three grids, the grid state corresponding to each grid can be obtained respectively. If the grid states of the three grids are all drivable or non-drivable, it can be determined that the area state corresponding to the target area can be the corresponding drivable or non-drivable state. If the grid states corresponding to the three grids are inconsistent (such as including one drivable state and two non-drivable states), it can be considered that the area state corresponding to the target area is a partially drivable state.

[0065] Optionally, in this embodiment, when determining the grid state corresponding to each grid and determining the area state corresponding to each target area, a GPU (graphics processing unit) may be used to implement parallel processing of information, which is beneficial to further improve the efficiency of generating area perception information.

[0066] Optionally, in this embodiment, if the entire area map obtained is a drivable area or a non-drivable area, there is no need to further divide the area map, which is conducive to avoiding waste of computing power. That is, before dividing the area map into multiple target areas, this embodiment also includes:

[0067] Determine whether the grid status corresponding to each grid in the regional map is consistent;

[0068] If so, the region perception information corresponding to the region map is obtained according to the grid state;

[0069] If not, the area map is divided into a plurality of target areas.

[0070] In this embodiment, since the area of ​​each target area is larger than the area of ​​each grid, each target area may contain multiple grids. On the one hand, the grid state corresponding to the grid in the target area can provide a high-precision reference basis for determining the regional state corresponding to the target area, which is conducive to improving the accuracy of regional perception information. On the other hand, when determining the regional state corresponding to the target area based on the grid state corresponding to the grid in the target area, the target area with a larger area can condense the perception information corresponding to the grid with a smaller area, which can effectively reduce the data volume and is conducive to improving the generation efficiency of subsequent regional perception information.

[0071] S3: Based on the area status corresponding to each target area, generate area perception information corresponding to the area map; wherein, when the area status corresponding to the target area is a partially drivable state, change the area status corresponding to the target area based on a reference area status set; wherein the reference area status set includes area status corresponding to target areas adjacent to the target area.

[0072] Specifically, the reference area state set referred to in this embodiment may include a set of area states corresponding to other target areas adjacent to the target area corresponding to the partially drivable state. When the area state corresponding to the target area is a partially drivable state, the reference area state set corresponding to the target area can be obtained. For example, assuming that the area state corresponding to target area A is a partially drivable state, other target areas adjacent to target area A (such as eight neighborhood areas or four neighborhood areas of target area A, etc.) can be obtained, and for ease of understanding and expression, they can be recorded as target area B. Then the area state corresponding to each target area B can be obtained to obtain a reference area state set, and the target area can be processed based on the reference area state set. For example, assuming that there are four target areas B, and their respective corresponding area states are non-drivable state, non-drivable state, non-drivable state and drivable state, respectively, then the area state with the highest proportion in the reference area state set (assuming it is a non-drivable state) can be selected, and the area state corresponding to target area A can be changed from a partially drivable state to a non-drivable state.

[0073] In one embodiment, after obtaining the regional status corresponding to each target area, it can be determined whether there is a target area whose regional status is a partially drivable state. If so, the regional status corresponding to the target area can be changed based on the reference regional status set (such as changing it to a drivable state or a non-drivable state), thereby clarifying whether the vehicle can pass in different target areas. The regional perception information corresponding to the regional map referred to in this embodiment can reflect the vehicle's passability in different areas of the regional map, and regional perception information can be generated based on the regional status corresponding to each target area. After the target area corresponding to the partially drivable state is subjected to regional status changes and other processing based on the reference regional status set, the regional status corresponding to each target area in the regional map is deterministic. On this basis, each target area can be associated with the corresponding regional status respectively, thereby generating regional perception information corresponding to the regional map.

[0074] Optionally, to reduce data storage pressure, after determining the area status corresponding to each target area, the grids and their corresponding grid states within the target area corresponding to the drivable state and the non-drivable state may be deleted, leaving only accurate and representative target areas and their corresponding area statuses.

[0075] In this embodiment, the regional map is divided into grids, and the grid state corresponding to each grid is determined based on the regional map. Compared with the method of processing the regional map as a whole to generate regional perception information at the same time, it is beneficial to reduce the computing power consumption and the difficulty of data processing while providing a high-precision reference basis for regional perception information. Since the area of ​​the target area in this embodiment is larger than the area of ​​the grid, each target area in this embodiment can contain multiple grids. On the one hand, the grid state corresponding to the grid located in the target area can provide a reliable data basis for determining the regional state corresponding to the target area, ensuring the accuracy of regional perception information. On the other hand, when determining the regional state corresponding to the target area based on the grid state corresponding to the grid in the target area, the target area with a larger area can refine the information such as the grid state corresponding to the smaller area of ​​the grid, which can effectively reduce the data volume and is conducive to improving the efficiency of subsequent generation of regional perception information. Due to the complexity of the actual road conditions corresponding to the regional map, it is likely that the distribution of grid states corresponding to different grids will be more complicated. Accordingly, when extracting perception information such as grid status based on the regional status corresponding to the target area, it is easy to cause a decrease in perception accuracy (i.e., causing the regional status corresponding to some target areas to be partially drivable), affecting the accuracy and reliability of regional perception information. In the process of generating regional perception information based on the regional status corresponding to each target area, when the regional status corresponding to a certain target area is detected to be partially drivable, the reference state information corresponding to the target area (such as a reference regional status set) can be determined based on the regional status corresponding to the target area adjacent to it, thereby mining the correlation of different regional states based on the spatial continuity of different target areas. In this way, when the present embodiment performs regional status changes and other processing on such target areas based on the reference regional status set, it can effectively compensate for the uncertainty of the regional status corresponding to some target areas caused by the decrease in perception accuracy, ensure the accuracy of the final generated regional perception information, and then when generating perception information corresponding to the regional map, it can take into account both efficiency and accuracy.

[0076] Optionally, determining the region state corresponding to each target region according to the grid state corresponding to the grid located in the target region includes:

[0077] Performing a state judgment operation on each target area respectively to obtain a judgment result; wherein the state judgment operation includes judging whether the grid states corresponding to each grid in the target area are consistent;

[0078] When the judgment result is consistent, the area state corresponding to the target area is obtained according to the grid state;

[0079] When the judgment result is inconsistent, a segmentation operation is performed on the target area to obtain multiple new target areas, and for the new target areas, the step of performing a state judgment operation on each target area is returned.

[0080] Specifically, in this embodiment, after determining the grid state corresponding to each grid, the grid state corresponding to each grid in the target area can be obtained respectively, and it is determined whether the corresponding grid states are consistent to obtain a determination result. When the determination result is consistent, the region state corresponding to the target area can be obtained according to the grid state. For example, assuming that the grid state corresponding to each grid in a target area is a drivable state, the drivable state can be used as the region state corresponding to the target area.

[0081] In one embodiment, when the judgment result is inconsistent, it means that there are differences in the grid states corresponding to different grids in the target area. At this time, a segmentation operation can be performed on the target area to obtain multiple new target areas. For example, when the grid states corresponding to the grids in the target area A are inconsistent, the target area A can be divided, such as being divided into four areas of equal area, to obtain four new target areas and respectively recorded as: target area A1, target area A2, target area A3 and target area A4. On this basis, the area state corresponding to each new target area can be determined according to the grid state, that is, for each new target area, the step of performing the state judgment operation on each target area is returned, and the area state corresponding to the target area is determined according to the obtained judgment result, or the new target area is further divided. For example, assuming that the grid states corresponding to the grids in the divided target area A1, target area A2 and target area A3 are consistent, the area states corresponding to the target area A1, target area A2 and target area A3 can be obtained according to the corresponding grid states. Assuming that the grid states corresponding to the grids in the target area A4 are still inconsistent, the target area A4 can be further divided to obtain new target areas which are respectively recorded as: target area A41, target area A42, target area A43 and target area A44, and then the process returns to the step of performing the state judgment operation on each target area until the area state corresponding to each target area is obtained.

[0082] In this embodiment, the judgment operation is performed for the consistency of the grid state corresponding to each grid in the target area, which is conducive to identifying whether the traffic capacity of the vehicle in the target area is deterministic, and then determining whether the dispersion state of different areas inside it (i.e., the grid state corresponding to different grids) can be accurately reflected according to the overall state of the target area (i.e., the regional state). When the judgment result is consistent, the regional state corresponding to the target area is obtained according to the grid state, which is conducive to accurately refining information such as multiple grid states contained in the target area. When the judgment result is inconsistent, the segmentation operation is performed on the target area to obtain multiple new target areas, which is conducive to improving the local perception accuracy of complex areas in the regional map (such as the probability of inconsistent grid states of grids in the target area near the road boundary position) and is conducive to improving the representativeness of the regional state to the grid states corresponding to different grids inside it. In this way, this embodiment only further divides the target area when necessary, and different target areas in the regional map can correspond to different perception accuracies, which is conducive to reducing computing power consumption and data storage pressure while improving the accuracy of regional perception information.

[0083] Optionally, before performing a segmentation operation on the target region to obtain a plurality of new target regions, the method further includes the following steps:

[0084] Determine a region segmentation level corresponding to the target region; wherein each time a segmentation operation is performed on the target region, the region segmentation level corresponding to each new target region obtained based on the target region increases by one level;

[0085] When the area segmentation level is greater than a preset level, the area state corresponding to the target area is set to a partially drivable state.

[0086] Specifically, the regional segmentation level referred to in this embodiment can reflect the perception accuracy corresponding to the target area to a certain extent. The larger the regional segmentation level corresponding to the target area, the more segmentation times it has experienced, the smaller the target area, and the higher the corresponding perception accuracy. It can be determined according to the number of segmentation operations experienced by the target area. After each segmentation operation is performed on a target area, the regional segmentation level corresponding to each new target area obtained after the target area is segmented can be increased by one level. For example, assuming that the above-mentioned target area A is the initial target area obtained based on the regional map division, its corresponding regional segmentation level can be set to level one. On this basis, after performing a segmentation operation on the target area, the target area A is divided into four new target areas, namely, target area A1, target area A2, target area A3 and target area A4. It is necessary to increase one level on the basis of the regional segmentation level corresponding to the target area A, and obtain the regional segmentation levels corresponding to the four new target areas, that is, the regional segmentation level corresponding to the target areas A1 to A4 is level two. By analogy, the regional segmentation level corresponding to the above-mentioned target areas A41, target area A42, target area A43 and target area A44 is level three.

[0087] In one embodiment, after determining the region segmentation level corresponding to the target region, it can be determined whether the region segmentation level is greater than a preset level (such as level 4). If so, the segmentation operation is no longer performed on the target region, and the region state corresponding to the target region is directly set to a partially drivable state. If not, the segmentation operation is performed on the target region to obtain multiple new target regions.

[0088] In this embodiment, in the process of determining the regional state corresponding to the target area according to the grid state, when the judgment result corresponding to the judgment operation is inconsistent, it means that the perception accuracy of the target area may not meet the actual complex road conditions, and the vehicle's traffic capacity in the target area is uncertain. At this time, it is necessary to continue to divide the target area to further improve the perception accuracy of the target area. On this basis, this embodiment ensures the rationality of the perception accuracy by judging whether the regional segmentation level is greater than the preset level. When the regional segmentation level is greater than the preset level, the regional state corresponding to the target area is set to a partially drivable state, which is conducive to avoiding excessive computing power consumption and further improving the efficiency of generating regional perception information.

[0089] Optionally, the preset level is determined based on the acquired current environment information and a preset adjustment strategy, and the preset adjustment strategy includes:

[0090] When the current traffic flow determined according to the current environmental information is greater than the first preset threshold and shows an increasing trend, increasing the preset level;

[0091] When the current traffic flow is less than the second preset threshold and shows a decreasing trend, the preset level is reduced; wherein the first preset threshold is greater than the second preset threshold.

[0092] Specifically, the current environmental information referred to in this embodiment can reflect the current environmental conditions of the vehicle. The current traffic flow referred to in this embodiment may include the vehicle flow and / or pedestrian flow corresponding to the location of the vehicle, which can reflect the current operating scenario of the vehicle to a certain extent. In this embodiment, the current environmental information may include the number of vehicles within a preset perception range obtained by the vehicle (such as obtained by a radar device, etc.). On this basis, the current traffic flow (such as 5psc / min) can be obtained based on the average value of the number of vehicles within a preset time length.

[0093] In one embodiment, after determining the current traffic flow, it can be determined whether the current traffic flow is greater than the first preset threshold, and whether the current traffic flow is less than the second preset threshold. Among them, in this embodiment, the first preset threshold and the second preset threshold can be set in advance, and the first preset threshold is greater than the second preset threshold. Taking the current traffic flow including the current vehicle flow as an example, when the current vehicle flow is greater than the first preset threshold (such as 10psc / min), or less than the second preset threshold (such as 2psc / min), it means that the vehicle operation scene may have changed. On this basis, the change trend of the current vehicle flow can be determined. For example, the current vehicle flow within three consecutive preset cycles can be obtained, which is recorded as the first flow, the second flow and the third flow. When the first flow is less than the second flow, and the second flow is less than the third flow, it can be considered that the current traffic flow presents an increasing trend. Correspondingly, when the first flow is greater than the second flow, and the second flow is greater than the third flow, it can be considered that the current traffic flow presents a decreasing trend.

[0094] In this embodiment, the larger the current traffic flow, the more congested the traffic is, and the vehicle may be in a scene such as an urban road. On the contrary, the larger the current traffic flow, the looser the traffic is, and the vehicle may be in a scene such as a highway. On this basis, this embodiment can accurately predict the changes in the corresponding operating environment of the vehicle based on the change trend of the current traffic flow, and then dynamically adjust the perception accuracy of the regional perception information by increasing or decreasing the preset level. In this embodiment, when the current traffic flow is greater than the first preset threshold (or less than the second preset threshold), continuing to judge whether the current traffic flow shows an increasing trend (or a decreasing trend) is conducive to ensuring the reliability of scene prediction and avoiding the contingency of a single data. In this embodiment, when it is predicted that the traffic is becoming more and more congested (that is, when the current traffic flow determined by the current environmental information is greater than the first preset threshold and shows an increasing trend), increasing the preset level is conducive to improving the perception accuracy of complex areas in the regional perception information (such as areas near the road surface boundary), which is conducive to improving the reliability of the regional perception information, thereby ensuring the safety of vehicle operation. When the present embodiment predicts that traffic is becoming increasingly relaxed (i.e., the current traffic flow determined by the current environmental information is less than the second preset threshold and is showing a decreasing trend), reducing the preset level is beneficial to appropriately reduce the perception accuracy corresponding to the regional perception information, while taking into account the safety of vehicle operation, and is also beneficial to further improve the generation efficiency of regional perception information.

[0095] Optionally, changing the region state corresponding to the target region based on the reference region state set includes:

[0096] Obtain the target ratio corresponding to the non-drivable state in the reference area state set;

[0097] When the target proportion is greater than or equal to the preset proportion, the area state corresponding to the target area is changed to a non-drivable state;

[0098] When the target proportion is less than the preset proportion, a reference area is screened out from all candidate areas based on preset boundary conditions, and the target area is merged into the reference area; wherein the candidate area includes each target area adjacent to the target area.

[0099] Specifically, in this embodiment, the reference area state set may include the area state corresponding to each target area adjacent to the target area corresponding to the partially drivable state. After obtaining the reference area state set, the number of non-drivable states in the reference area state set can be obtained as the target number, and the target proportion can be obtained according to the ratio of the target number to the total number corresponding to the reference area state set. On this basis, it can be determined whether the target proportion is greater than or equal to the preset proportion; if so, it means that the similarity of the corresponding area states between the target areas adjacent to the target area is high, and the area state corresponding to the target area can be changed to a non-drivable state. If not, it means that the similarity of the corresponding area states between the target areas adjacent to the target area is low, and appropriate fusion processing is required.

[0100] In one embodiment, when the target proportion is less than the preset proportion, each target area adjacent to the target area can be obtained to obtain each candidate area. And based on the preset boundary conditions, a reference area is screened out from all the candidate areas, and the target area is merged into the reference area. For example, the candidate areas with overlapping boundaries with the target area can be first screened out from all the candidate areas. On this basis, the regional status corresponding to each candidate area can be obtained, and the candidate areas corresponding to the regional status of a drivable state or a non-drivable state can be selected to obtain the reference area. On this basis, the target area can be merged into the reference area. Correspondingly, within the corresponding regional range of the target area, the corresponding regional status is changed from a partially drivable state to a regional status corresponding to the reference area. Optionally, after the reference area is screened out from all the candidate areas based on the preset boundary conditions, when the number corresponding to the reference area is greater than 1, the reference area with a regional status of a non-drivable state can be preferentially selected for fusion.

[0101] In this embodiment, the target proportion corresponding to the non-drivable state in the reference area state set can reflect the similarity between different area states in the reference area state set. When the target proportion is greater than or equal to the preset proportion, it means that the similarity of the corresponding area states between the target areas adjacent to the target area is high, which is conducive to ensuring the accuracy of state propagation. The area state corresponding to the target area can be changed to the non-drivable state (that is, the non-drivable state with a larger proportion is propagated to the area state corresponding to the target area). While further improving the efficiency of generating regional perception information, the rationality of the area state corresponding to the target area can also be ensured. When the target proportion is less than the preset proportion, it means that the similarity of the corresponding area states between the target areas adjacent to the target area is low, and it is not suitable to directly select the area state in the reference area state set to change the area state corresponding to the target area. The target area adjacent to the target area can be used as a reference area, and the reference area can be screened out from all candidate areas based on the preset boundary conditions, and the target area can be merged into the reference area. In this way, when the target proportion corresponding to the non-passable state is greater than or equal to the preset proportion, the area state is propagated based on the state similarity between adjacent target areas, and the target state corresponding to the target area is changed. When the target ratio corresponding to the impassable state is less than the preset ratio, the spatial continuity between adjacent target areas can be used to merge the target areas, realize indirect regional state change, and comprehensively improve the accuracy of regional perception information.

[0102] Optionally, the reference area is selected from all candidate areas based on preset boundary conditions, including:

[0103] Obtain the boundary overlap lengths of each candidate area and the target area respectively;

[0104] For each boundary overlap length, when the boundary overlap length is greater than a reference length, the candidate area corresponding to the boundary overlap length is used as a reference area; wherein the reference length is determined based on the contour information of the target area.

[0105] Specifically, in this embodiment, the preset boundary conditions can be used to constrain the boundary overlap length corresponding to the reference area to be greater than the reference length. In the process of determining the reference area, the contour information corresponding to the target area corresponding to the partially drivable state can be obtained, the reference length can be determined based on the contour information, and the reference area can be screened out from all the alternative areas. For example, assuming that the target area is a rectangle with four equal sides, the contour information may include a single side length of the target area (such as 1m), and the reference length can be determined to be 0.75m based on the single side length and the preset minimum overlap coefficient (such as 0.75). On this basis, the boundary overlap length corresponding to the target area and each alternative area can be obtained respectively, and the alternative area with a boundary overlap length greater than 0.75m can be used as the reference area.

[0106] In this embodiment, based on the boundary conditions, candidate regions whose boundary overlap length is greater than the reference length are selected from all candidate regions to obtain the reference region, which is conducive to ensuring the spatial correlation between the target region and the reference region and improving the reliability of regional fusion. Among them, the contour information of the target region can provide an accurate reference basis for determining the reference length. The corresponding reference lengths can be different for different target regions, which is conducive to adapting to the actual conditions corresponding to different target regions in the regional map, thereby realizing flexible adaptive fusion.

[0107] Optionally, the area map includes a road area and a non-driving area; and determining a grid state corresponding to each grid obtained by division based on the area map includes:

[0108] Extract the current drivable area from the area map according to the road area and the non-drivable area;

[0109] When the grid center corresponding to the grid is within the current drivable area, the grid state corresponding to the grid is a drivable state;

[0110] When the grid center corresponding to the grid is not within the current drivable area, the grid state corresponding to the grid is a non-drivable state.

[0111] Specifically, in this embodiment, the regional map may include road areas and non-driving areas (such as green belt areas), and the geometric outlines of different types of areas may be directly extracted (such as different geometric outlines in the regional map are pre-associated with corresponding regional types), or the regional types and regional outlines may be extracted based on methods such as image recognition. On this basis, the current drivable area may be extracted from the regional map based on the road area and the non-driving area. For example, the difference between the road area and the non-driving area may be obtained in the road area to obtain the current drivable area (which may be represented by a geometric outline).

[0112] In this embodiment, after the regional map is divided into grids, the grid center (such as the center coordinates) corresponding to each grid can be obtained respectively, and it is determined whether the grid center corresponding to the grid is in the current drivable area. If so, the grid state corresponding to the grid is a drivable state. If not, the grid state corresponding to the grid is a non-drivable state, which is beneficial to ensure the reliability of the grid state while quickly determining the grid state. For example, this embodiment can obtain the maximum coordinates and minimum coordinates of the geometric contour corresponding to the current drivable area in different directions to obtain the coordinate range. By determining whether the center coordinates corresponding to the grid center are within the above coordinate range, it is possible to quickly determine whether the grid center is in the current drivable area.

[0113] like Figure 2As shown, a specific embodiment of the method for generating region perception information of the present invention is now exemplarily described, and the method includes:

[0114] Divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map;

[0115] The regional map is divided into a plurality of target regions, and a state judgment operation is performed on each target region to obtain a judgment result; the state judgment operation includes judging whether the grid states corresponding to each grid in the target region are consistent;

[0116] When the judgment result is consistent, the region state corresponding to the target region is obtained according to the grid state corresponding to the grid located in the target region;

[0117] When the judgment result is inconsistent, determining the region segmentation level corresponding to the target region;

[0118] Determine whether the region segmentation level is greater than a preset level;

[0119] If yes, the area state corresponding to the target area is a partially drivable state;

[0120] If not, a segmentation operation is performed on the target area to obtain multiple new target areas, and for the new target areas, the step of performing a state determination operation on each target area is returned;

[0121] When the area state corresponding to the target area is a partially drivable state, obtaining a reference area state set corresponding to the target area, wherein the reference area state set includes area states corresponding to target areas adjacent to the target area;

[0122] Determine whether the target proportion corresponding to the non-drivable state in the reference area state concentration is greater than a preset proportion;

[0123] If yes, the area status corresponding to the target area is changed to a non-drivable state;

[0124] If not, a reference area is selected from all candidate areas based on a preset boundary condition, and the target area is merged into the reference area; wherein the candidate area includes each target area adjacent to the target area;

[0125] The regional perception information corresponding to the regional map is obtained according to the regional status corresponding to each target area.

[0126] The schematic diagram of the process of rasterizing the regional map in this embodiment is as follows: Figure 3 shown. Figure 3P1 is a schematic diagram corresponding to the initial regional map (the white area in P1 represents the road area, and the gray area represents the non-driving area), and P2 is a schematic diagram corresponding to the regional map after grid division.

[0127] The schematic diagram of the process of dividing the area map into multiple target areas in this embodiment is as follows Figure 4 shown. Figure 4 P3 in FIG. 3 is a schematic diagram corresponding to the regional map after the grid state corresponding to each grid is determined. In P3, G represents the grid, G=1 represents the grid state is a drivable state, and G=0 represents the grid state is a non-drivable state. Figure 4 P4 in the figure is a schematic diagram corresponding to the regional map after dividing the regional map into regions and obtaining the target region.

[0128] The schematic diagram of the process of performing a segmentation operation on the target region to obtain multiple new target regions in this embodiment is as follows Figure 5 shown. Figure 5 P5 in the figure represents a schematic diagram corresponding to the regional map when the regional state corresponding to the target region is determined based on the grid state corresponding to the grid in the target region. In P5, R represents the target region, R=1 represents the regional state is a drivable state, R=0 represents the regional state is a non-drivable state, and R=n represents the target region whose regional state has not yet been confirmed. Figure 5 P6 in the figure shows the schematic diagram corresponding to the regional map after dividing the target area with inconsistent grid states corresponding to the grids in the target area to obtain new target areas and determining the regional states corresponding to each new target area. R=0.5 in P6 means that the regional state corresponding to the target area is a partially drivable state.

[0129] The schematic diagram of the process of generating regional perception information based on the regional status corresponding to each target region in this embodiment is as follows: Figure 6 shown. Figure 6 P7 is a schematic diagram of the regional map after the target area of ​​R=0.5 in P6 is fused into the reference area based on the preset boundary conditions. In this implementation, after generating regional status information according to the regional status corresponding to each target area, the grid and its corresponding grid status information can be deleted, which is conducive to reducing the data volume and reducing storage pressure.

[0130] In this way, in the process of generating regional perception information in this embodiment, the perception accuracy of the local area is improved only when necessary (such as near the boundary of the road area in P6, the target area is divided into smaller areas), and for continuous road areas or other continuous non-driving areas, the area of ​​the corresponding target area is also correspondingly larger (such as the target areas of R=0 and R=1 in P5). When the vehicle makes relevant decisions for autonomous driving based on the regional perception information generated in this embodiment (such as path planning), it can directly identify the area in the regional map where the vehicle is allowed to pass based on the current boundary coordinates of the vehicle (such as the boundary coordinates corresponding to the projection contour of the vehicle on the road surface), thereby achieving efficient and accurate perception of the regional status, and can better adapt to the regional perception needs of the vehicle in dynamic scenes such as autonomous driving.

[0131] like Figure 7 As shown, an embodiment of the present invention provides a region awareness information generating device 700, including:

[0132] A division module 710 is used to divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state;

[0133] A determination module 720, which is used to divide the regional map into multiple target regions, and determine the regional state corresponding to each of the target regions according to the grid state corresponding to the grid located in the target region; wherein the area of ​​each of the target regions is larger than the area of ​​each of the grids; and the regional state includes the drivable state, the non-drivable state and the partially drivable state;

[0134] A generation module 730 is used to generate area perception information corresponding to the area map based on the area status corresponding to each of the target areas; wherein, when the area status corresponding to the target area is the partially drivable state, the area status corresponding to the target area is changed based on a reference area status set; wherein the reference area status set includes the area status corresponding to the target area adjacent to the target area.

[0135] The technical effects that can be produced by the region awareness information generating device and the region awareness information generating method provided in this embodiment are basically the same, and will not be described in detail here.

[0136] like Figure 8 As shown, an electronic device 800 provided by an embodiment of the present invention includes a memory 810 and a processor 820; the memory 810 is used to store a computer program; the processor 820 is used to implement the above-mentioned method for generating area perception information when executing the computer program.

[0137] In other words, an electronic device 800 includes a memory 810 and a processor 820 coupled to the memory 810; the memory 810 is configured to store a computer program; and the processor 820 is configured to perform the following operations when executing the computer program:

[0138] Divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state;

[0139] The regional map is divided into a plurality of target regions, and the regional state corresponding to each of the target regions is determined according to the grid state corresponding to the grid located in the target region; wherein the area of ​​each of the target regions is larger than the area of ​​each of the grids; and the regional state includes the drivable state, the non-drivable state and the partially drivable state;

[0140] Based on the area state corresponding to each of the target areas, area perception information corresponding to the area map is generated; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

[0141] The technical effects that can be produced by the electronic device and the method for generating area perception information provided in this embodiment are basically the same, and will not be repeated here.

[0142] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating region awareness information as described above is implemented.

[0143] In other words, a non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following operations:

[0144] Divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state;

[0145] The regional map is divided into a plurality of target regions, and the regional state corresponding to each of the target regions is determined according to the grid state corresponding to the grid located in the target region; wherein the area of ​​each of the target regions is larger than the area of ​​each of the grids; and the regional state includes the drivable state, the non-drivable state and the partially drivable state;

[0146] Based on the area state corresponding to each of the target areas, area perception information corresponding to the area map is generated; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

[0147] The computer-readable storage medium provided in this embodiment and the method for generating region awareness information can produce substantially the same technical effects, which will not be described in detail herein.

[0148] An electronic device 800 that can be used as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device 800 is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device 800 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present invention described herein and / or required.

[0149] The electronic device 800 includes a computing unit, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for the operation of the device can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0150] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0151] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A method for generating region perception information, characterized in that: include: Divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state; The regional map is divided into a plurality of target regions, and the regional state corresponding to each of the target regions is determined according to the grid state corresponding to the grid located in the target region; wherein the area of ​​each of the target regions is larger than the area of ​​each of the grids; and the regional state includes the drivable state, the non-drivable state and the partially drivable state; Based on the area state corresponding to each of the target areas, area perception information corresponding to the area map is generated; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

2. The method for generating region awareness information according to claim 1, characterized in that: The determining the area state corresponding to each target area according to the grid state corresponding to the grid located in the target area respectively includes: Performing a state judgment operation on each of the target areas respectively to obtain a judgment result; wherein the state judgment operation includes judging whether the grid states corresponding to each of the grids in the target area are consistent; When the judgment result is consistent, obtaining the area state corresponding to the target area according to the grid state; When the judgment result is inconsistent, a segmentation operation is performed on the target area to obtain multiple new target areas, and for the new target areas, the process returns to the step of performing a state judgment operation on each of the target areas.

3. The method for generating region awareness information according to claim 2, characterized in that: Before performing a segmentation operation on the target area to obtain a plurality of new target areas, the method further includes: Determine a region segmentation level corresponding to the target region; wherein each time the segmentation operation is performed on the target region, the region segmentation level corresponding to each new target region obtained based on the target region increases by one level; When the area segmentation level is greater than a preset level, the area state corresponding to the target area is set to the partially drivable state.

4. The method for generating region awareness information according to claim 3, characterized in that: The preset level is determined based on the acquired current environment information and the preset adjustment strategy, and the preset adjustment strategy includes: When the current traffic flow determined according to the current environmental information is greater than a first preset threshold and shows an increasing trend, increasing the preset level; When the current traffic flow is less than a second preset threshold and shows a decreasing trend, the preset level is reduced; wherein the first preset threshold is greater than the second preset threshold.

5. The method for generating region awareness information according to claim 1, characterized in that: The changing the area state corresponding to the target area based on the reference area state set includes: Obtaining a target ratio corresponding to the non-drivable state in the reference area state set; When the target proportion is greater than or equal to a preset proportion, the area state corresponding to the target area is changed to the non-drivable state; When the target proportion is less than the preset proportion, a reference area is screened out from all candidate areas based on preset boundary conditions, and the target area is merged into the reference area; wherein the candidate area includes each of the target areas adjacent to the target area.

6. The method for generating region awareness information according to claim 5, characterized in that: The step of selecting a reference area from all candidate areas based on a preset boundary condition includes: Respectively obtain the overlapping length of the boundary between each candidate area and the target area; For each of the boundary overlap lengths, when the boundary overlap length is greater than a reference length, the candidate area corresponding to the boundary overlap length is used as the reference area; wherein the reference length is determined based on the contour information of the target area.

7. The method for generating region awareness information according to any one of claims 1 to 6, characterized in that: The regional map includes a road area and a non-driving area; the grid state corresponding to each grid obtained by dividing based on the regional map includes: Extracting a current drivable area from the area map according to the road area and the non-drivable area; When the center of the grid corresponding to the grid is within the current drivable area, the grid state corresponding to the grid is the drivable state; When the grid center corresponding to the grid is not within the current drivable area, the grid state corresponding to the grid is the non-drivable state.

8. A device for generating region awareness information, characterized in that: include: A division module, which is used to divide the acquired regional map into grids, and determine the grid state corresponding to each grid obtained by the division based on the regional map; wherein the grid state includes a drivable state and a non-drivable state; A determination module, which is used to divide the area map into multiple target areas, and determine the area state corresponding to each of the target areas according to the grid state corresponding to the grid located in the target area; wherein the area of ​​each of the target areas is larger than the area of ​​each of the grids; and the area state includes the drivable state, the non-drivable state and the partially drivable state; A generation module, which is used to generate area perception information corresponding to the area map based on the area state corresponding to each of the target areas; wherein, when the area state corresponding to the target area is the partially drivable state, the area state corresponding to the target area is changed based on a reference area state set; wherein the reference area state set includes the area states corresponding to the target areas adjacent to the target area.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the region awareness information generating method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the method for generating area awareness information according to any one of claims 1 to 7 is implemented.

Images