Travelable area identification method and device for pedestrian-vehicle mixed road section, electronic equipment and storage medium

Abstract

The invention discloses a drivable area identification method and device for a pedestrian-vehicle mixed road section, electronic equipment and a storage medium, and the method comprises the steps: determining initial drivable area information according to map grid information in the pedestrian-vehicle mixed road section; acquiring a detection result of the obstacle, wherein the detection result at least comprises position information of the obstacle, speed information of the obstacle and type information of the obstacle; classifying the moving ability of the obstacle based on the speed information of the obstacle and the type information of the obstacle; and obtaining final drivable area information in response to the preliminary drivable area information, the position information of the obstacle and the obstacle moving ability classification. According to the invention, the obstacles are classified to identify the future driving area, the vehicle is helped to leave the congested road section, and the traffic efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, device, electronic device, and storage medium for identifying drivable areas in mixed pedestrian and vehicle traffic sections. Background Technology

[0002] Navigating congested roads is one of the challenges of autonomous driving. Autonomous vehicles already in operation on public roads often get stuck in congested areas, causing traffic jams.

[0003] One of the core issues in managing congested roads is how to identify drivable areas for the future from the perspective of current congestion. Summary of the Invention

[0004] This application provides a method, device, electronic device, and storage medium for identifying drivable areas in mixed pedestrian and vehicle traffic sections. By classifying obstacles, it identifies "future" drivable areas, helping vehicles escape congested sections and improving traffic efficiency.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a method for identifying drivable areas in mixed pedestrian and vehicle traffic sections, wherein the identification method includes:

[0007] Based on the map grid information in the pedestrian and vehicle mixed traffic sections, preliminary drivable area information is determined;

[0008] Obtain the detection results of obstacles, wherein the detection results include at least the obstacle's position information, obstacle's speed information, and obstacle's type information;

[0009] Based on the speed information and type information of the obstacles, the movement capabilities of the obstacles are classified.

[0010] In response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities, the final drivable area information is obtained.

[0011] In some embodiments, classifying the obstacle's mobility based on the obstacle's speed information and type information includes:

[0012] Based on the speed information of multiple obstacles obtained from multiple frames, as well as the position and type information of each obstacle, each obstacle is classified into at least four types according to its mobility: zombie obstacle, fixed obstacle, crawling obstacle, and normal obstacle.

[0013] In some embodiments, the method further includes:

[0014] Determine whether each of the obstacles has a historical velocity;

[0015] If an obstacle does not have a historical speed and the detection results for the obstacle do not include people, it is considered a zombie obstacle.

[0016] If an obstacle does not have a historical speed and the detection results for the obstacle include a person, it is considered a stationary obstacle.

[0017] If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle does not exceed a preset threshold speed, it is considered a creeping obstacle.

[0018] If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle is not less than the preset threshold speed, it is considered a normal obstacle.

[0019] In some embodiments, obtaining the final drivable area information in response to the preliminary drivable area information, the location information of the obstacle, and the obstacle mobility classification includes:

[0020] Based on the capability classification results of the zombie obstacles, the fixed obstacles, the crawling obstacles, and the normal obstacles, the spatiotemporal passability probability P is assigned to the map grid of the preliminary drivable area. (i，j) Wherein P (i，j) This represents the spatiotemporal accessibility probability value of the i-th row and j-th column raster in the raster map;

[0021] Wherein, the grid P occupied by the zombie obstacle (i，j) =0, the grid P occupied by the fixed obstacle (i，j) =0.1, the grid P occupied by the creeping obstacle (i，j) =0.5, the grid P occupied by the normal obstacle (i，j) =1.0.

[0022] In some embodiments, before obtaining the final drivable area in response to the preliminary drivable area, the location information of the obstacles, and the obstacle mobility classification, the method further includes:

[0023] Receive road event information sent by roadside equipment to determine the road restricted area; wherein the road restricted area occupies the grid P. (i，j) =0.

[0024] In some embodiments, the spatiotemporal passability probability value in the map grid information is updated based on road event information sent by the roadside equipment;

[0025] The higher the spatiotemporal passability probability value, the lower the passability cost.

[0026] In some embodiments, the method further includes using the final drivable area information as input for vehicle route planning.

[0027] Secondly, embodiments of this application also provide a drivable area identification device for mixed pedestrian and vehicle traffic sections, wherein the identification device includes:

[0028] The initial module is used to determine preliminary drivable area information based on map grid information in pedestrian and vehicular mixed traffic sections;

[0029] The acquisition module is used to acquire the detection results of obstacles, and the detection results include at least the location information, speed information and type information of the obstacles;

[0030] The capability classification module is used to classify the movement capability of the obstacle based on its speed information;

[0031] The reprocessing module is used to obtain the final drivable area information in response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities.

[0032] Thirdly, embodiments of this application also provide an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to perform the above-described method.

[0033] Fourthly, embodiments of this application also provide a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform the above-described method.

[0034] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: Preliminary drivable area information is determined based on map grid information in a mixed pedestrian and vehicle road section; then, the location information of obstacles is obtained, and the mobility of the obstacles is classified based on their speed information. In response to the preliminary drivable area information, the location information of the obstacles, and the classification of their mobility capabilities, final drivable area information is obtained. By using the determined preliminary drivable area information, the current location information of the obstacles, and the classification of their mobility capabilities, the final drivable area information for future times is obtained. Attached Figure Description

[0035] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0036] Figure 1 This is a schematic diagram illustrating the application scenario of the method for identifying drivable areas in mixed pedestrian and vehicle traffic sections according to embodiments of this application;

[0037] Figure 2 This is a flowchart illustrating the method for identifying drivable areas in mixed pedestrian and vehicle traffic sections according to an embodiment of this application.

[0038] Figure 3 This is a schematic diagram of the spatiotemporal drivable area in the method for identifying drivable areas in mixed pedestrian and vehicle traffic sections in the embodiments of this application;

[0039] Figure 4 This is a schematic diagram illustrating the implementation principle of the method for identifying drivable areas in mixed pedestrian and vehicle traffic sections in this application embodiment;

[0040] Figure 5 This is a schematic diagram of the drivable area identification device for mixed pedestrian and vehicle traffic sections in this application embodiment;

[0041] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0044] like Figure 1 The diagram shows the obstacles divided in the grid map, where the left and right sides represent lane boundaries, respectively. The grid is divided into the same mesh and the J and I directions. It can be understood that the J and I directions represent lateral and longitudinal directions, respectively. Obstacle types are categorized as zombie obstacles, fixed obstacles, creeping obstacles, and normal obstacles. Additionally, the diagram includes scenarios where the obstacle type is an accident zone, such as temporary road construction.

[0045] This application provides a method for identifying drivable areas in mixed pedestrian and vehicle traffic sections, such as... Figure 2 The diagram shows a flowchart of a method for identifying drivable areas in mixed pedestrian and vehicle traffic sections according to an embodiment of this application. The method includes at least the following steps S210 to S240:

[0046] Step S210: Determine preliminary drivable area information based on map grid information in the mixed pedestrian and vehicle road section.

[0047] For autonomous vehicles, the perception module can generate grid map data and obstacle information within the drivable area, and based on the grid map information, preliminarily determine the drivable area and its grid.

[0048] "Pedestrian-vehicle mixed traffic sections" can be "congested sections" that can be determined in advance based on historical information or based on perception results. It is understood that "pedestrian-vehicle mixed traffic sections" in this application embodiment can also refer to "congested sections" or other sections with the same road conditions.

[0049] Step S220: Obtain the detection results of the obstacle. The detection results include at least the obstacle's position information, the obstacle's speed information, and the obstacle's type information.

[0050] The obstacle detection results include at least the obstacle's location information, speed information, and type information. The obstacle's location information can be obtained through the perception module of the autonomous vehicle. In addition to location information, it also includes, but is not limited to, obstacle speed information and heading angle information. The obstacle type information refers to whether the obstacle is a person, bicycle, motor vehicle, truck, etc.

[0051] Based on the perceived obstacle information, and according to its historical speed information (including multiple frames of perception results, each frame needs to be processed) and detection results, a mobility capability label is added to the obstacle.

[0052] Step S230: Classify the obstacle's mobility based on the obstacle's speed information and the obstacle's type information.

[0053] When classifying the mobility of the obstacles, the mobility of the obstacles can be classified by determining whether the speed information of the obstacles is greater than or less than a preset threshold. This classification includes, but is not limited to, being a zombie obstacle, a fixed obstacle, a crawling obstacle, and a normal obstacle.

[0054] Step S240: In response to the preliminary drivable area information, the location information of the obstacles, and the obstacle mobility classification, the final drivable area information is obtained.

[0055] Based on the preliminary drivable area information, combined with the location information of the obstacles and the classification of the obstacles' mobility, the drivable area of ​​the congested road section ahead is identified and confirmed, thus the spatiotemporal drivable area is deduced.

[0056] By taking into account both obstacle and road information, the above method can identify the drivable road area in the future under the condition of "current congestion".

[0057] Using the above method, preliminary drivable area information is determined based on map grid information in mixed pedestrian and vehicular traffic sections; obstacle location information is obtained; and obstacle mobility is classified based on obstacle speed information. Responding to the preliminary drivable area information, the obstacle location information, and the obstacle mobility classification, final drivable area information is obtained. By classifying obstacle mobility, drivable areas in the future can be identified in advance even under current congestion conditions.

[0058] In one embodiment of this application, classifying the mobility of obstacles based on their speed information and type information includes: classifying each obstacle into at least four types according to its mobility, based on the speed information of multiple obstacles acquired from multiple frames, as well as the position and type information of each obstacle: zombie obstacle, fixed obstacle, crawling obstacle, and normal obstacle.

[0059] Specifically, when classifying the mobility of obstacles, the first step is to determine if historical speed information exists. If historical speed information exists, it is necessary to further determine whether the speed exceeds a preset threshold. If historical speed information does not exist, it is necessary to determine whether there are pedestrians in the initially drivable area. The type of obstacle will affect the classification result of the specific obstacle according to its mobility. For example, bicycles and motor vehicles may be classified as zombie obstacles or stationary obstacles, so the classification also depends on the obstacle's speed.

[0060] Based on the speed information of multiple obstacles acquired through multi-frame acquisition and the position information of each obstacle, each obstacle is classified into at least four types according to its mobility: zombie obstacles, stationary obstacles, crawling obstacles, and normal obstacles. Zombie obstacles include obstacles that are not controlled by anyone and do not move for a long time. Stationary obstacles include obstacles with a speed of 0. Crawling obstacles include obstacles with a low speed or idling state. Normal obstacles include pedestrians or vehicles that pass normally.

[0061] In one embodiment of this application, the method further includes: determining whether each obstacle has a historical speed; if an obstacle does not have a historical speed and the detection result of the obstacle does not include a person, it is considered a zombie obstacle; if an obstacle does not have a historical speed and the detection result of the obstacle includes a person, it is considered a stationary obstacle; if an obstacle has a historical speed and the historical highest vehicle speed in the detection result of the obstacle does not exceed a preset threshold speed, it is considered a crawling obstacle; if an obstacle has a historical speed and the historical highest vehicle speed in the detection result of the obstacle is not less than the preset threshold speed, it is considered a normal obstacle.

[0062] like Figure 4 As shown, obstacles are categorized by their mobility. It's important to note that when distinguishing between zombie obstacles and stationary obstacles, it's necessary to determine if there is a person (referring to a person driving a motor vehicle, bicycle, or truck, which is different from the person listed in the obstacle type information). When determining whether an obstacle is a crawling obstacle or a normal obstacle, speed information needs to be considered.

[0063] If an obstacle lacks historical speed information and the detection results do not include people (such as empty cars or bicycles), it is considered a zombie obstacle and does not possess the ability to move. In this case, the corresponding passable probability is 0.

[0064] If there is no historical speed information and the detection results show a person, it is considered a fixed obstacle with weak mobility.

[0065] If historical speed information is available, and the historical maximum speed does not exceed [a certain value], then [the speed is likely related to speed or speed]. v ( v (≥0 is a constant), it is considered to be a creeping obstacle with a certain ability to move.

[0066] If historical speed information is available, and the maximum speed is greater than or equal to... v If it is considered a normal obstacle and can be moved normally, then the corresponding passability probability is 1.0.

[0067] In one embodiment of this application, obtaining the final drivable area information in response to the preliminary drivable area information, the location information of the obstacles, and the obstacle mobility classification includes: assigning a spatiotemporal passability probability P to the map grid of the preliminary drivable area based on the capability classification results of the zombie obstacles, the fixed obstacles, the crawling obstacles, and the normal obstacles. (i，j) Wherein P (i，j) The spatiotemporal passability probability value of the i-th row and j-th column grid cell in the grid map; where the grid cell P occupied by the zombie obstacle is... (i，j) =0, the grid P occupied by the fixed obstacle (i，j)=0.1, the grid P occupied by the creeping obstacle (i，j) =0.5, the grid P occupied by the normal obstacle (i，j) =1.0.

[0068] like Figure 3 As shown, based on the classification of obstacle mobility, a "spatiotemporal drivability probability" P is calculated for the obtained drivable area and its grid on the map. (i，j) Assignment (where P) (i，j) The spatiotemporal accessibility probability of the i-th row and j-th column of the raster map is:

[0069] The grid P occupied by zombie obstacles (i，j) =0; The number of grid cells P occupied by a fixed obstacle. (i，j) =0.1; the grid P occupied by the crawling obstacle (i，j) =0.5; the grid P occupied by normal obstacles (i，j) =1.0.

[0070] It is important to note that the higher the "spacetime travel probability," the lower the travel cost. Conversely, the lower the travel probability, the higher the travel cost.

[0071] Therefore, for the total cost of passage = other costs - the sum of the passability probabilities of each grid node on the path, the method for identifying the drivable area of ​​the mixed pedestrian and vehicle road segment in this application aims to minimize the total cost of passage of the path, so it can select those grid points with higher passability probabilities as the drivable area for planning.

[0072] It is understood that the above "spatiotemporal passability probability" is only an example and is not intended to limit the specific value of the "spatiotemporal passability probability" in the embodiments of this application, but the probability ratio is basically consistent with the actual situation.

[0073] Unlike related technologies that use grid maps for judgment, which have limitations, the above method introduces a "spatiotemporal passability probability value" to better determine the drivable area based on preliminary drivable area information.

[0074] In one embodiment of this application, before obtaining the final drivable area in response to the preliminary drivable area, the location information of the obstacle, and the obstacle mobility classification, the method further includes: receiving road event information sent by a roadside device to determine a road no-entry zone; wherein the road no-entry zone occupies a grid P. (i，j) =0.

[0075] like Figure 3 As shown, the system receives road event information from roadside equipment and determines the restricted road zone. The restricted road zone occupies grid P. (i，j)=0. Preferably, by receiving road event information sent by roadside equipment, the road prohibition zone can be further determined, and the spatiotemporal passability probability P of the grid of the prohibition zone can be determined. (i，j) =0. For the total cost of passage = other costs - the sum of the passability probabilities of each grid node on the path, when calculating the cost of each grid, the grid node with the higher probability value is selected first.

[0076] In one embodiment of this application, the spatiotemporal passability probability value in the map grid information is updated; wherein, the larger the spatiotemporal passability probability value, the smaller the passability cost.

[0077] The spatiotemporal accessibility probability value in a portion of the map grid information is updated by the new "road event information".

[0078] Unlike related technologies that lack consideration of road event information, the above method infers the spatiotemporal drivable area based on the map's drivable area, obstacle location and mobility classification, and roadside events.

[0079] In one embodiment of this application, the method further includes using the final drivable area information as input for vehicle route planning.

[0080] The final result is as follows Figure 3 The spatiotemporal drivable area is shown and used as input for path planning of autonomous vehicles.

[0081] This application embodiment also provides a drivable area identification device 500 for mixed pedestrian and vehicle traffic sections, such as... Figure 5 The diagram shows a schematic representation of a drivable area identification device for mixed pedestrian and vehicle traffic sections in this application. The drivable area identification device 500 for mixed pedestrian and vehicle traffic sections includes at least: an initialization module 510, an acquisition module 520, a capability classification module 530, and a reprocessing module 540, wherein:

[0082] In one embodiment of this application, the initial module 510 is specifically used to: determine preliminary drivable area information according to the map grid information in the mixed pedestrian and vehicle road section.

[0083] For autonomous vehicles, the map engine module can generate grid map data within the drivable area, the perception module can acquire obstacle information, and based on the grid map information, the drivable area and its grids can be preliminarily determined.

[0084] "Pedestrian-vehicle mixed traffic sections" can be "congested sections" that can be determined in advance based on historical information or based on perception results. It is understood that "pedestrian-vehicle mixed traffic sections" in this application embodiment can also refer to "congested sections" or other sections with the same road conditions.

[0085] In one embodiment of this application, the acquisition module 520 is specifically used to: acquire the detection results of the obstacle, the detection results including at least the obstacle's position information, the obstacle's speed information, and the obstacle's type information.

[0086] The obstacle detection results include at least the obstacle's location information, speed information, and type information. The obstacle's location information can be obtained through the autonomous vehicle's perception module. In addition to location information, it also includes, but is not limited to, obstacle speed information and heading angle information.

[0087] Based on the perceived obstacle information, and according to its historical speed information (including multiple frames of perception results, each frame needs to be processed) and detection results, a mobility capability label is added to the obstacle.

[0088] In one embodiment of this application, the capability classification module 530 is specifically used to classify the obstacle's mobility capability based on the obstacle's speed information and the obstacle's type information.

[0089] When classifying the movement ability of the obstacle, the obstacle's ability can be classified by determining whether the speed information of the obstacle is greater than or less than a preset threshold. This classification includes, but is not limited to, being a zombie obstacle, a fixed obstacle, a crawling obstacle, and a normal obstacle.

[0090] In one embodiment of this application, the reprocessing module 540 is specifically used to: obtain final drivable area information in response to the preliminary drivable area information, the location information of the obstacle, and the obstacle mobility classification.

[0091] Based on the preliminary drivable area information, combined with the location information of the obstacles and the classification of the obstacles' mobility, the drivable area of ​​the congested road section ahead is identified and confirmed, thus the spatiotemporal drivable area is deduced.

[0092] In one embodiment of this application, the capability classification module 530 is further configured to:

[0093] Based on the speed information of multiple obstacles obtained from multiple frames, as well as the position and type information of each obstacle, each obstacle is classified into at least four types according to its mobility: zombie obstacle, fixed obstacle, crawling obstacle, and normal obstacle.

[0094] The capability classification module 530 in one embodiment of this application is further used for:

[0095] Determine whether each of the obstacles has a historical velocity;

[0096] If an obstacle does not have a historical speed and the detection results for the obstacle do not include people, it is considered a zombie obstacle.

[0097] If an obstacle does not have a historical speed and the detection results for the obstacle include a person, it is considered a stationary obstacle.

[0098] If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle does not exceed a preset threshold speed, it is considered a creeping obstacle.

[0099] If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle is not less than the preset threshold speed, it is considered a normal obstacle.

[0100] In one embodiment of this application, the reprocessing module 540 is further configured to:

[0101] Based on the capability classification results of the zombie obstacles, the fixed obstacles, the crawling obstacles, and the normal obstacles, the spatiotemporal passability probability P is assigned to the map grid of the preliminary drivable area. (i，j) Wherein P (i，j) This represents the spatiotemporal accessibility probability value of the i-th row and j-th column raster in the raster map;

[0102] Wherein, the grid P occupied by the zombie obstacle (i，j) =0, the grid P occupied by the fixed obstacle (i，j) =0.1, the grid P occupied by the creeping obstacle (i，j) =0.5, the grid P occupied by the normal obstacle (i，j) =1.0.

[0103] In one embodiment of this application, it further includes: a roadside module, used for:

[0104] Receive road event information sent by roadside equipment to determine the road restricted area; wherein the road restricted area occupies the grid P. (i，j) =0.

[0105] In one embodiment of this application, the roadside module is further configured to: update the spatiotemporal passability probability value of a portion of the map grid information based on road event information sent by the roadside device;

[0106] The higher the spatiotemporal passability probability value, the lower the passability cost.

[0107] In one embodiment of this application, it further includes: a planning input module, which is also used for:

[0108] The final drivable area information is used as input for vehicle route planning.

[0109] It is understood that the aforementioned drivable area identification device for mixed pedestrian and vehicle traffic sections can implement each step of the drivable area identification method for mixed pedestrian and vehicle traffic sections provided in the foregoing embodiments. The relevant explanations regarding the drivable area identification method for mixed pedestrian and vehicle traffic sections are applicable to the drivable area identification device for mixed pedestrian and vehicle traffic sections, and will not be repeated here.

[0110] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0111] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0112] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0113] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a drivable area identification device for mixed pedestrian and vehicle traffic sections at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0114] Based on the map grid information in the pedestrian and vehicle mixed traffic sections, preliminary drivable area information is determined;

[0115] Obtain the location information of the obstacles;

[0116] Based on the speed information of the obstacles, the movement capabilities of the obstacles are classified.

[0117] In response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities, the final drivable area information is obtained.

[0118] The above is as stated in this application. Figure 2 The method executed by the drivable area identification device for mixed pedestrian and vehicle traffic sections disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0119] The electronic device can also perform Figure 2 A method for implementing a drivable area identification device in a mixed pedestrian and vehicle traffic section, and realizing the drivable area identification device in such a section. Figure 2 The functions of the embodiments shown are not described in detail here.

[0120] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 2The method executed by the drivable area identification device in the pedestrian-vehicle mixed-traffic section shown in the embodiment is specifically used to perform the following:

[0121] Based on the map grid information in the pedestrian and vehicle mixed traffic sections, preliminary drivable area information is determined;

[0122] Obtain the location information of the obstacles;

[0123] Based on the speed information of the obstacles, the movement capabilities of the obstacles are classified.

[0124] In response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities, the final drivable area information is obtained.

[0125] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0131] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0132] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0133] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for identifying drivable areas in mixed pedestrian and vehicular traffic sections, wherein, The identification method includes: Based on the map grid information in the pedestrian and vehicle mixed traffic sections, preliminary drivable area information is determined; Obtain the detection results of obstacles, wherein the detection results include at least the obstacle's position information, obstacle's speed information, and obstacle's type information; Based on the speed information and type information of the obstacles, the movement capabilities of the obstacles are classified. In response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities, the final drivable area information is obtained.

2. The method as described in claim 1, wherein, The classification of obstacle mobility based on the obstacle's speed information and obstacle type information includes: Based on the speed information of multiple obstacles obtained from multiple frames, as well as the position and type information of each obstacle, each obstacle is classified into at least four types according to its mobility: zombie obstacle, fixed obstacle, crawling obstacle, and normal obstacle.

3. The method of claim 2, further comprising: Determine whether each of the obstacles has a historical velocity; If an obstacle does not have a historical speed and the detection results for the obstacle do not include people, it is considered a zombie obstacle. If an obstacle does not have a historical speed and the detection results for the obstacle include a person, it is considered a stationary obstacle. If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle does not exceed a preset threshold speed, it is considered a creeping obstacle. If an obstacle has a historical speed and the highest historical vehicle speed in the detection results of the obstacle is not less than the preset threshold speed, it is considered a normal obstacle.

4. The method as described in claim 3, wherein, The process of obtaining final drivable area information in response to the preliminary drivable area information, the location information of the obstacles, and the obstacle mobility classification includes: Based on the capability classification results of the zombie obstacles, the fixed obstacles, the crawling obstacles, and the normal obstacles, the spatiotemporal passability probability P is assigned to the map grid of the preliminary drivable area. (i，j) Wherein, P (i，j) This represents the spatiotemporal accessibility probability value of the i-th row and j-th column raster in the raster map; Wherein, the grid P occupied by the zombie obstacle (i，j) =0, the grid P occupied by the fixed obstacle (i，j) =0.1, the grid P occupied by the creeping obstacle (i，j) =0.5, the grid P occupied by the normal obstacle (i，j) =1.

0.

5. The method as described in claim 4, wherein, Before obtaining the final drivable area in response to the preliminary drivable area, the location information of the obstacles, and the obstacle mobility classification, the method further includes: Receive road event information sent by roadside equipment to determine the road restricted area; wherein the road restricted area occupies the grid P. (i，j) =0.

6. The method of claim 5, wherein, Update the spatiotemporal passability probability value in the map grid information based on the road event information sent by the roadside equipment; The higher the spatiotemporal passability probability value, the lower the passability cost.

7. The method of claim 1, wherein, Also includes: The final drivable area information is used as input for vehicle route planning.

8. A device for identifying drivable areas in a mixed pedestrian and vehicle traffic section, wherein, The identification device includes: The initial module is used to determine preliminary drivable area information based on map grid information in pedestrian and vehicular mixed traffic sections; The acquisition module is used to acquire the detection results of obstacles, and the detection results include at least the location information, speed information and type information of the obstacles; The capability classification module classifies the obstacle's mobility capability based on the obstacle's speed information and the obstacle's type information; The reprocessing module is used to obtain the final drivable area information in response to the preliminary drivable area information, the location information of the obstacles, and the classification of the obstacles' mobility capabilities.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the method of any one of claims 1 to 7.

Images