Automatic driving splash filtering method and device, electronic equipment and storage medium

Abstract

The invention discloses an automatic driving splash filtering method and device, electronic equipment and a storage medium, which are used for solving the technical problem of abnormal braking caused by incapability of effectively judging and filtering a splash condition in a driving process of an automatic driving vehicle. The method comprises the following steps: constructing a distance grid model of the autonomous vehicle by taking the center between two rear wheels of the autonomous vehicle as an original point; the distance grid model comprises a head grid, a tail grid and filtering grids corresponding to four wheels of the autonomous vehicle; the advancing direction of the autonomous vehicle during advancing is judged, a target wheel is determined from the four wheels based on the advancing direction, and a key trigger grid is selected from the vehicle head grid and the vehicle tail grid; the target wheel corresponds to the target filtering grid; and based on the target filtering grid and the key triggering grid, carrying out splashing judgment on the target wheel based on the obstacle distance measurement point cloud, and determining whether to execute a splashing filtering action or not based on a judgment result.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an autonomous driving water splash filtering method, device, electronic device and storage medium. Background Art

[0002] Autonomous driving technology is the product of a highly integrated approach to modern artificial intelligence, computer vision, sensor technology, and vehicle engineering. Its core goal is to enable vehicles to safely and efficiently complete driving tasks without human intervention through onboard sensors, computing platforms, and algorithms. In recent years, with breakthroughs in deep learning algorithms, advances in high-performance computing capabilities, and the widespread use of multiple sensor types such as lidar, cameras, and radar, autonomous driving technology has made significant progress and has achieved relatively mature application in specific scenarios (such as highways and restricted areas).

[0003] Perception technology is a core element of autonomous driving systems. It primarily involves real-time perception and understanding of the surrounding environment. LiDAR, a key sensor in autonomous driving systems, offers the advantage of direct physical measurement, providing real-world feedback and unaffected by environmental factors. Therefore, LiDAR is often considered the last line of defense for the safe operation of autonomous driving systems.

[0004] During actual driving, the road may be flooded due to various circumstances. The splashing water may create a virtual obstacle for the autonomous vehicle, causing unnecessary abnormal braking. Summary of the Invention

[0005] The present invention provides an autonomous driving water splash filtering method, device, electronic device and storage medium, which are used to solve or partially solve the technical problem of abnormal braking caused by the inability to effectively judge and filter water splashing during driving of autonomous driving vehicles.

[0006] The present invention provides a method for filtering water splashes in an autonomous driving system, the method comprising:

[0007] Constructing a distance grid model of the autonomous vehicle with the center between the two rear wheels of the autonomous vehicle as the origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous vehicle;

[0008] determining a direction of travel of the autonomous driving vehicle, determining a target wheel from the four wheels based on the direction of travel, and selecting a key trigger grid from the front grid and the rear grid; the target wheel corresponds to a target filter grid;

[0009] Based on the target filtering grid and the key triggering grid, a water splash judgment based on the obstacle ranging point cloud is performed on the target wheel, and based on the judgment result, it is determined whether to perform a water splash filtering action.

[0010] Optionally, constructing a distance grid model of the autonomous driving vehicle with the center between the two rear wheels of the autonomous driving vehicle as the origin includes:

[0011] Taking the center between the two rear wheels of the autonomous vehicle as the origin, using multiple distance grids of preset sizes, a distance grid model is established with a first preset distance forward, a second preset distance backward, a third preset distance left and right, and a fourth preset distance in height;

[0012] The first distance grid triggered by the front of the vehicle when moving forward is used as the front grid of the autonomous vehicle, and the first distance grid triggered by the rear of the vehicle when moving backward is used as the rear grid of the autonomous vehicle;

[0013] When the autonomous driving vehicle is moving forward, a preset number of distance grids in front of the left front wheel are used as left front wheel filtering grids, and a preset number of distance grids in front of the right front wheel are used as right front wheel filtering grids;

[0014] When the autonomous driving vehicle moves backward, a preset number of distance grids in front of the left rear wheel are used as left rear wheel filtering grids, and a preset number of distance grids in front of the right rear wheel are used as right rear wheel filtering grids.

[0015] Optionally, determining a direction of travel of the autonomous driving vehicle and determining a target wheel from among the four wheels based on the direction of travel includes:

[0016] Determining a direction of travel of the autonomous driving vehicle;

[0017] When the traveling direction is forward, the left front wheel and / or the right front wheel are used as target wheels;

[0018] When the traveling direction is backward, the left rear wheel and / or the right rear wheel are used as target wheels.

[0019] Optionally, the selecting a key trigger grid from the front grid and the rear grid includes:

[0020] When the target wheel is the left front wheel and / or the right front wheel, the front grid is used as the key trigger grid;

[0021] When the target wheel is the left rear wheel and / or the right rear wheel, the rear grid is used as the key trigger grid.

[0022] Optionally, performing water splash judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key triggering grid, and determining whether to perform the water splash filtering action based on the judgment result, includes:

[0023] Determining the first triggered grid in the moving direction among the target filtering grids as the filtering triggering grid;

[0024] Determining whether the key trigger grid is currently in an empty state;

[0025] If so, when the previous frame of the filter trigger grid is empty and the obstacle ranging point cloud appears in the current frame, it is determined that water splashing occurs, and all obstacle ranging point clouds appearing in the target filter grid are filtered.

[0026] Optionally, the method further includes:

[0027] When the key trigger grid is not currently in an empty state, or when all grids in the target filtering grid are restored to an empty state after performing the splash filtering, the current splash judgment process is exited.

[0028] Optionally, the top-view area of ​​the distance grid model is larger than the top-view area of ​​the autonomous driving vehicle; the height of the distance grid model is greater than or equal to the height of the center point of the wheels of the autonomous driving vehicle off the ground; the other distance grids in the distance grid model except the front grid, the rear grid, the left front wheel filter grid, the right front wheel filter grid, the left rear wheel filter grid, and the right rear wheel filter grid are used to obtain timing information when the vehicle is moving.

[0029] The present invention also provides an automatic driving water splash filtering device, comprising:

[0030] a model building unit, configured to build a distance grid model of the autonomous driving vehicle with the center between the two rear wheels of the autonomous driving vehicle as an origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous driving vehicle;

[0031] a target wheel determination unit, configured to determine a direction of travel of the autonomous vehicle, determine a target wheel from the four wheels based on the direction of travel, and select a key trigger grid from the front grid and the rear grid; the target wheel corresponds to a target filter grid;

[0032] The water splash judgment unit is used to perform water splash judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key trigger grid, and determine whether to perform a water splash filtering action based on the judgment result.

[0033] The present invention further provides an electronic device, comprising a processor and a memory:

[0034] The memory is used to store program code and transmit the program code to the processor;

[0035] The processor is used to execute the automatic driving water splash filtering method as described in any one of the above items according to the instructions in the program code.

[0036] The present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the automatic driving splash filtering method as described in any one of the above items.

[0037] It can be seen from the above technical solutions that the present invention has the following advantages:

[0038] A method for filtering water splashes in autonomous driving is proposed. First, a distance grid model of the autonomous driving vehicle is constructed with the center between the two rear wheels of the autonomous driving vehicle as the origin. The distance grid model includes the front grid, the rear grid, and the filter grids corresponding to each of the four wheels. Thus, a model for water splash judgment based on the modeling method can be constructed, which can simplify the subsequent water splash judgment and filtering process and provide a simple and effective judgment method. The direction of travel of the autonomous driving vehicle is determined, and the target wheel is determined from the four wheels based on the direction of travel. The key trigger grid is selected from the front grid and the rear grid. The target wheel corresponds to the target filter grid. Therefore, by determining the direction of travel of the vehicle, the area where water splashing may occur and the relevant judgment calculation needs to be performed can be quickly identified, reducing the relevant calculation amount and improving the calculation efficiency. Finally, based on the target filtering grid and the key triggering grid, the target wheel is judged for splashing water based on the obstacle ranging point cloud, and whether to execute the splashing water filtering action is determined based on the judgment result; thus, by setting up the splashing water judgment process, it can be determined whether the splashing water filtering action needs to be executed. When the splashing water occurs, the filtering action is executed, which can avoid the accidental braking behavior of the autonomous driving vehicle due to splashing water on the road during driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A flowchart of the steps of a method for filtering splash water for autonomous driving;

[0041] Figure 2 A schematic diagram of the overall process of an autonomous driving splash water filtering method;

[0042] Figure 3 This is a structural block diagram of an autonomous driving splash water filtering device. DETAILED DESCRIPTION

[0043] Embodiments of the present invention provide an autonomous driving water splash filtering method, device, electronic device, and storage medium, which are used to solve or partially solve the technical problem of abnormal braking caused by the inability to effectively judge and filter water splashing during driving of autonomous driving vehicles.

[0044] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] For example, in autonomous driving systems, perception technology is one of the core technologies. This primarily involves real-time perception and understanding of the surrounding environment. LiDAR, a key sensor in autonomous driving systems, excels in that its ranging is based on direct physical measurements, providing real-world feedback and unaffected by environmental factors. Therefore, LiDAR is often considered the last line of defense for the safe operation of autonomous driving systems.

[0046] During actual driving, the road may be flooded due to various circumstances. The splashing water may create a virtual obstacle for the autonomous vehicle, causing unnecessary abnormal braking.

[0047] Therefore, one of the core inventive points of the embodiment of the present invention is to propose a method for filtering splash water for automatic driving. First, a model for water splash judgment is constructed based on a modeling method, which can simplify the subsequent water splash judgment and filtering process, and provide a simple and effective judgment means. Secondly, by judging the direction of travel of the vehicle, the area where the vehicle may be splashed and the relevant judgment calculation needs to be performed can be quickly locked, thereby reducing the relevant calculation amount and improving the calculation efficiency. Finally, by setting the water splash judgment process, it can be determined whether it is necessary to perform a water splash filtering action. When a water splash occurs, a filtering action is performed, which can avoid the incorrect braking behavior of the automatic driving vehicle due to water splashing on the road during driving.

[0048] Reference Figure 1 , shows a flowchart of a method for filtering water splashes in an autonomous driving system provided by an embodiment of the present invention, which may specifically include the following steps:

[0049] Step 101: constructing a distance grid model of the autonomous vehicle with the center between the two rear wheels of the autonomous vehicle as the origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous vehicle;

[0050] In some embodiments, a distance grid model of the autonomous driving vehicle is constructed with the center between the two rear wheels of the autonomous driving vehicle as the origin. Specifically, it can be:

[0051] Taking the center between the two rear wheels of the autonomous driving vehicle as the origin, a distance grid model with multiple preset sizes is established, with a first preset distance forward, a second preset distance backward, a third preset distance left and right, and a fourth preset distance in height.

[0052] The distance grid first triggered by the front of the vehicle when moving forward is used as the front grid of the autonomous vehicle, and the distance grid first triggered by the rear of the vehicle when moving backward is used as the rear grid of the autonomous vehicle.

[0053] When the autonomous driving vehicle is moving forward, a preset number of distance grids in front of the left front wheel are used as left front wheel filtering grids, and a preset number of distance grids in front of the right front wheel are used as right front wheel filtering grids.

[0054] When the autonomous driving vehicle moves backward, a preset number of distance grids in front of the left rear wheel are used as left rear wheel filtering grids, and a preset number of distance grids in front of the right rear wheel are used as right rear wheel filtering grids.

[0055] Among them, the bird's-eye view area of ​​the distance grid model is larger than the bird's-eye view area of ​​the autonomous driving vehicle; the height of the distance grid model is greater than or equal to the height of the center point of the wheels off the ground in the autonomous driving vehicle; other distance grids in the distance grid model except the front grid, rear grid, left front wheel filter grid, right front wheel filter grid, left rear wheel filter grid, and right rear wheel filter grid are used to obtain timing information when the vehicle is moving.

[0056] Specifically, during driving, a distance grid model is established with the center between the rear wheels as the origin. Starting from the origin, the forward distance is front_span meters, and the backward distance is behind_span meters (since the model is based on the center between the rear wheels, the backward extension distance can be set to be smaller than the forward extension distance), totaling front_behind_span meters, and front_behind_num distance grids. The left distance is right_span meters, and the right distance is left_span meters, totaling right_left_span meters, and right_left_num distance grids. The height is set to high_span meters (for practical purposes, the height can be set to be greater than or equal to the height of the wheel center point above the ground, but not exceeding or slightly exceeding the overall wheel height), totaling high_num distance grids. The constructed distance grid model then consists of front_behind_num * right_left_num * high_num distance grids.

[0057] The first distance grid triggered by the front of the vehicle when moving forward is used as the front grid of the autonomous vehicle. In actual application, when the vehicle is moving forward, if the wheel currently selected for water splash detection is the left front wheel, the index of the front grid can be set to front_left_start_carbody_index; if the wheel currently selected for water splash detection is the right front wheel, the index of the front grid can be set to front_right_start_carbody_index.

[0058] The first distance grid triggered by the rear of the vehicle during backward travel is used as the rear grid of the autonomous vehicle. In actual applications, when the vehicle is traveling backward, if the wheel currently selected for water splash detection is the left rear wheel, the index of the rear grid can be set to back_left_start_carbody_index; if the wheel currently selected for water splash detection is the right rear wheel, the index of the rear grid can be set to back_right_start_carbody_index.

[0059] When the vehicle is moving forward, the filter_num distance grids in front of the left front wheel are used as the left front wheel filter grid, and the filter_num distance grids in front of the right front wheel are used as the right front wheel filter grid.

[0060] When the vehicle is moving backward, the filter_num distance grids in front of the left rear wheel are used as the left rear wheel filter grid, and the filter_num distance grids in front of the right rear wheel are used as the right rear wheel filter grid.

[0061] Aside from the aforementioned front and rear grids, and the individual wheel filter grids, the remaining distance grids primarily serve to capture timing information. In practical applications, a timing model can be established based on the position changes corresponding to frame-to-frame timing variations using these other distance grids. This model can then be used to determine the vehicle's current trajectory and direction. Based on this direction, the target wheel for water splash determination calculations is determined, and the relevant determination calculations for the target index grids (key trigger grids, target filter grids, and their filter trigger grids) are initiated.

[0062] Step 102: determining a direction of travel of the autonomous vehicle, determining a target wheel from the four wheels based on the direction of travel, and selecting a key trigger grid from the front grid and the rear grid; the target wheel corresponds to a target filter grid;

[0063] In some embodiments, the direction of travel of the autonomous vehicle is determined, and a target wheel is determined from the four wheels based on the direction of travel. Specifically, the direction of travel of the autonomous vehicle is determined; when the direction of travel is forward, the left front wheel and / or the right front wheel is used as the target wheel; when the direction of travel is backward, the left rear wheel and / or the right rear wheel is used as the target wheel.

[0064] When traveling forward, both the left and right front wheels may trigger a splash detection during forward movement. Depending on the situation, this may occur on only the left front wheel, only the right front wheel, or both wheels. Regardless of which wheel meets the splash detection criteria, the relevant action can be triggered. Similarly, when traveling backward, both the left and right rear wheels may trigger a splash detection during backward movement.

[0065] The key trigger grid is selected from the front grid and the rear grid. Specifically, when the target wheel is the left front wheel and / or the right front wheel, the front grid is used as the key trigger grid, and its index is front_left_start_carbody_index (corresponding to the left front wheel) or front_right_start_carbody_index (corresponding to the right front wheel); when the target wheel is the left rear wheel and / or the right rear wheel, the rear grid is used as the key trigger grid, and its index is back_left_start_carbody_index (corresponding to the left rear wheel) or back_right_start_carbody_index (corresponding to the right rear wheel).

[0066] Step 103 : performing a water splashing judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key triggering grid, and determining whether to perform a water splashing filtering action based on the judgment result.

[0067] In some embodiments, a splash judgment based on the obstacle ranging point cloud is performed on the target wheel based on the target filtering grid and the key triggering grid, and whether to perform the splash filtering action is determined based on the judgment result. Specifically, it can be:

[0068] The first triggered grid in the target filter grid in the direction of travel is determined as the filter trigger grid; among them, the grid first triggered by the left front wheel is recorded as front_left_start_index, the right front wheel is recorded as front_right_start_index, the first triggered grid by the left rear wheel is recorded as back_left_start_index, and the right rear wheel is recorded as back_right_start_index;

[0069] Determine whether the key trigger grid is currently empty;

[0070] If so, when the previous frame of the filter trigger grid is empty and the obstacle ranging point cloud appears in the current frame, it is determined that water splashing occurs, and all obstacle ranging point clouds appearing in the target filter grid are filtered.

[0071] In another case, when the key trigger grid is not currently in an empty state, or when all grids in the target filtering grid are restored to an empty state after performing the splash filtering, the current splash judgment process is exited.

[0072] For example, assuming that the current vehicle is moving forward and the left front wheel is determined to be the target wheel, the left front of the vehicle must first determine whether the key trigger grid front_left_start_carbody_index is currently empty (based on the eight connected domains of the key trigger grid (that is, the distance grids in the eight directions of the key trigger grid, namely, the up, down, left, right, and four diagonal directions around it are regarded as connected areas) and are determined by a certain weight). When it is determined that the key trigger grid front_left_start_carbody_index is currently in an empty state, if the filter trigger grid front_left_start_index of the left front wheel was freespace (empty) in the previous frame, and an obstacle ranging point cloud appears in the current frame, it can be considered that a water splash has occurred, and all obstacle point clouds that appear in the target filter grid in this direction will be filtered out. When front_left_start_carbody_index is no longer marked as empty (that is, it is not currently in an empty state), or the entire left side is empty (all grids in the target filter grid are restored to an empty state), the water splash judgment process is exited. The water splashing judgment process for other wheels is similar to this process and will not be described here in detail.

[0073] In an embodiment of the present invention, a method for filtering water splashes in an autonomous driving system is proposed. First, a distance grid model of the autonomous driving vehicle is constructed with the center between the two rear wheels of the autonomous driving vehicle as the origin; wherein, the distance grid model includes the front grid, the rear grid and the filter grids corresponding to the four wheels of the autonomous driving vehicle; thus, a model for water splash judgment is constructed based on the modeling method, which can simplify the subsequent water splash judgment and filtering process and provide a simple and effective judgment method. The direction of travel of the autonomous driving vehicle is determined, the target wheel is determined from the four wheels based on the direction of travel, and the key trigger grid is selected from the front grid and the rear grid; wherein, the target wheel corresponds to the target filter grid; thus, by judging the direction of travel of the vehicle, the area where the vehicle may splash and the relevant judgment calculation needs to be performed can be quickly locked, thereby reducing the relevant calculation amount and improving the calculation efficiency. Finally, based on the target filtering grid and the key triggering grid, the target wheel is judged for splashing water based on the obstacle ranging point cloud, and whether to execute the splashing water filtering action is determined based on the judgment result; thus, by setting up the splashing water judgment process, it can be determined whether the splashing water filtering action needs to be executed. When the splashing water occurs, the filtering action is executed, which can avoid the accidental braking behavior of the autonomous driving vehicle due to splashing water on the road during driving.

[0074] For better explanation, refer to Figure 2 , which shows a schematic diagram of the overall process of an autonomous driving water splash filtering method provided by an embodiment of the present invention. It should be noted that this embodiment only briefly describes the general process of autonomous driving water splash filtering. The specific implementation process of each step can be understood by referring to the relevant content in the aforementioned embodiments. It will not be described here in detail. It is understood that the present invention is not limited to this.

[0075] Step 201: Construct a distance grid model of the autonomous vehicle with the center between the two rear wheels of the autonomous vehicle as the origin; the distance grid model includes the front grid, the rear grid, and the filter grids corresponding to each of the four wheels of the autonomous vehicle; jump to step 202;

[0076] Step 202: Determine the direction of travel of the autonomous vehicle, determine the target wheel from the four wheels based on the direction of travel, and select a key trigger grid from the front grid and the rear grid; the target wheel corresponds to the target filter grid; jump to step 203;

[0077] Step 203: Determine the first triggered grid in the target filtering grid in the traveling direction as the filtering trigger grid; jump to step 204;

[0078] Step 204: Determine whether the key trigger grid is currently empty; if so, jump to step 205-1; if not, jump to step 206;

[0079] Step 205-1: When the previous frame of the filter trigger grid is empty and the current frame has an obstacle ranging point cloud, it is determined that water splashing occurs, and all obstacle ranging point clouds appearing in the target filter grid are filtered; then jump to step 205-2;

[0080] Step 205-2: Determine whether all cells in the target filter grid have returned to an empty state after the splash filtering is performed; if not, continue to perform the splash filtering until all cells in the target filter grid have returned to an empty state, and then jump to step 206; if so, directly jump to step 206;

[0081] Step 206: Exit the current water splashing judgment process; jump to step 204 and enter the next water splashing judgment process.

[0082] Reference Figure 3 , shows a structural block diagram of an automatic driving water splash filtering device provided by an embodiment of the present invention, which may specifically include:

[0083] A model building unit 301 is configured to build a distance grid model of the autonomous driving vehicle with the center between the two rear wheels of the autonomous driving vehicle as the origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous driving vehicle;

[0084] a target wheel determination unit 302 for determining a direction of travel of the autonomous vehicle, determining a target wheel from the four wheels based on the direction of travel, and selecting a key trigger grid from the front grid and the rear grid; the target wheel corresponds to a target filter grid;

[0085] The water splashing judgment unit 303 is used to perform water splashing judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key triggering grid, and determine whether to perform a water splashing filtering action based on the judgment result.

[0086] In an optional embodiment, the model building unit 301 includes:

[0087] a distance grid model construction subunit, configured to establish a distance grid model with a center between the two rear wheels of the autonomous vehicle as the origin, using a plurality of distance grids of preset sizes, with a first preset distance forward, a second preset distance rearward, a third preset distance leftward and a third preset distance rightward, and a fourth preset distance in height;

[0088] a front and rear grid determining unit, configured to use the distance grid first triggered by the front of the vehicle when traveling forward as the front grid of the autonomous vehicle, and use the distance grid first triggered by the rear of the vehicle when traveling backward as the rear grid of the autonomous vehicle;

[0089] a front wheel filter grid determination unit, configured to use a preset number of distance grids in front of the left front wheel as the left front wheel filter grid, and a preset number of distance grids in front of the right front wheel as the right front wheel filter grid when the autonomous driving vehicle is moving forward;

[0090] The rear wheel grid determination unit is used to use a preset number of distance grids in front of the left rear wheel as the left rear wheel filtering grid, and a preset number of distance grids in front of the right rear wheel as the right rear wheel filtering grid when the autonomous driving vehicle moves backward.

[0091] In an optional embodiment, the target wheel determination unit 302 includes:

[0092] a traveling direction determination unit, configured to determine the traveling direction of the autonomous driving vehicle;

[0093] a first target wheel determination unit, configured to use the left front wheel and / or the right front wheel as a target wheel when the traveling direction is forward;

[0094] The second target wheel determination unit is used to use the left rear wheel and / or the right rear wheel as the target wheel when the traveling direction is backward.

[0095] In an optional embodiment, the target wheel determination unit 302 includes:

[0096] a first key trigger grid determining unit, configured to use the front grid as a key trigger grid when the target wheel is the left front wheel and / or the right front wheel;

[0097] The second key trigger grid determination unit is used to use the rear grid as the key trigger grid when the target wheel is the left rear wheel and / or the right rear wheel.

[0098] In an optional embodiment, the water splashing judgment unit 303 includes:

[0099] A filter triggering grid unit, configured to determine the first triggered grid in the moving direction among the target filter grids as a filter triggering grid;

[0100] an empty state judgment unit, configured to judge whether the key trigger grid is currently in an empty state;

[0101] The water splashing determination unit is configured to determine the occurrence of water splashing when the previous frame of the filtering trigger grid is empty and an obstacle ranging point cloud appears in the current frame, and filter all obstacle ranging point clouds appearing in the target filtering grid.

[0102] In an optional embodiment, the empty state determination unit is further configured to:

[0103] When the key trigger grid is not currently in an empty state, or when all grids in the target filtering grid are restored to an empty state after performing the splash filtering, the current splash judgment process is exited.

[0104] In an optional embodiment, the top-view area of ​​the distance grid model is larger than the top-view area of ​​the autonomous driving vehicle; the height of the distance grid model is greater than or equal to the height of the center point of the wheels of the autonomous driving vehicle off the ground; and the other distance grids in the distance grid model except the front grid, the rear grid, the left front wheel filter grid, the right front wheel filter grid, the left rear wheel filter grid, and the right rear wheel filter grid are used to obtain timing information when the vehicle is moving.

[0105] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the aforementioned method embodiment.

[0106] It should be noted that, in order to enable those skilled in the art to better distinguish data of the same type but with different actual meanings, some technical features are distinguished and described using terms such as first and second in the embodiments of the present invention. Terms such as first and second are only used to distinguish data and have no other special meanings. It can be understood that the present invention does not impose any restrictions on this.

[0107] An embodiment of the present invention further provides an electronic device, the device including a processor and a memory:

[0108] The memory is used to store program codes and transmit the program codes to the processor;

[0109] The processor is used to execute the automatic driving water splash filtering method of any embodiment of the present invention according to the instructions in the program code.

[0110] An embodiment of the present invention also provides a computer-readable storage medium, which is used to store program code, and the program code is used to execute the automatic driving water splash filtering method of any embodiment of the present invention.

[0111] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0114] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for filtering splash water of an autonomous driving vehicle, characterized in that: include: Constructing a distance grid model of the autonomous vehicle with the center between the two rear wheels of the autonomous vehicle as the origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous vehicle; determining a direction of travel of the autonomous driving vehicle, determining a target wheel from the four wheels based on the direction of travel, and selecting a key trigger grid from the front grid and the rear grid; The target wheel corresponds to the target filter grid; Based on the target filtering grid and the key triggering grid, a water splash judgment based on the obstacle ranging point cloud is performed on the target wheel, and based on the judgment result, it is determined whether to perform a water splash filtering action.

2. The automatic driving water splash filtering method according to claim 1, characterized in that: The distance grid model of the autonomous driving vehicle is constructed with the center between the two rear wheels of the autonomous driving vehicle as the origin, including: Taking the center between the two rear wheels of the autonomous vehicle as the origin, using multiple distance grids of preset sizes, a distance grid model is established with a first preset distance forward, a second preset distance backward, a third preset distance left and right, and a fourth preset distance in height; The first distance grid triggered by the front of the vehicle when moving forward is used as the front grid of the autonomous vehicle, and the first distance grid triggered by the rear of the vehicle when moving backward is used as the rear grid of the autonomous vehicle; When the autonomous driving vehicle is moving forward, a preset number of distance grids in front of the left front wheel are used as left front wheel filtering grids, and a preset number of distance grids in front of the right front wheel are used as right front wheel filtering grids; When the autonomous driving vehicle moves backward, a preset number of distance grids in front of the left rear wheel are used as left rear wheel filtering grids, and a preset number of distance grids in front of the right rear wheel are used as right rear wheel filtering grids.

3. The automatic driving water splash filtering method according to claim 2, characterized in that: The determining the direction of travel of the autonomous driving vehicle and determining a target wheel from the four wheels based on the direction of travel includes: Determining a direction of travel of the autonomous driving vehicle; When the traveling direction is forward, the left front wheel and / or the right front wheel are used as target wheels; When the traveling direction is backward, the left rear wheel and / or the right rear wheel are used as target wheels.

4. The automatic driving water splash filtering method according to claim 3, characterized in that: The selecting of a key triggering grid from the front grid and the rear grid includes: When the target wheel is the left front wheel and / or the right front wheel, the front grid is used as the key trigger grid; When the target wheel is the left rear wheel and / or the right rear wheel, the rear grid is used as the key trigger grid.

5. The automatic driving water splash filtering method according to claim 4, characterized in that: The step of performing water splashing judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key triggering grid, and determining whether to perform the water splashing filtering action based on the judgment result, includes: Determining the first triggered grid in the moving direction among the target filtering grids as the filtering triggering grid; Determining whether the key trigger grid is currently in an empty state; If so, when the previous frame of the filter trigger grid is empty and the obstacle ranging point cloud appears in the current frame, it is determined that water splashing occurs, and all obstacle ranging point clouds appearing in the target filter grid are filtered.

6. The automatic driving water splash filtering method according to claim 5, characterized in that: Also includes: When the key trigger grid is not currently in an empty state, or when all grids in the target filtering grid are restored to an empty state after performing the splash filtering, the current splash judgment process is exited.

7. The automatic driving water splash filtering method according to any one of claims 2 to 6, characterized in that: The top-view area of ​​the distance grid model is larger than the top-view area of ​​the autonomous driving vehicle; the height of the distance grid model is greater than or equal to the height of the center point of the wheels of the autonomous driving vehicle off the ground; the other distance grids in the distance grid model except the front grid, the rear grid, the left front wheel filter grid, the right front wheel filter grid, the left rear wheel filter grid, and the right rear wheel filter grid are used to obtain timing information when the vehicle is moving.

8. An automatic driving splash water filtering device, characterized in that: include: a model building unit, configured to build a distance grid model of the autonomous driving vehicle with the center between the two rear wheels of the autonomous driving vehicle as an origin; the distance grid model includes a front grid, a rear grid, and filter grids corresponding to each of the four wheels of the autonomous driving vehicle; a target wheel determination unit, configured to determine a direction of travel of the autonomous driving vehicle, determine a target wheel from the four wheels based on the direction of travel, and select a key trigger grid from the front grid and the rear grid; The target wheel corresponds to the target filter grid; The water splash judgment unit is used to perform water splash judgment on the target wheel based on the obstacle ranging point cloud based on the target filtering grid and the key trigger grid, and determine whether to perform a water splash filtering action based on the judgment result.

9. An electronic device, characterized in that: The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the automatic driving water splash filtering method described in any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program code, and the program code is used to execute the automatic driving water splash filtering method described in any one of claims 1-7.

Images