Method for determining drivable area, vehicle control method, device and chip

Abstract

The embodiment of the invention provides a method for determining a drivable area, a vehicle control method, equipment and a chip, and relates to the field of automatic driving. The method for determining the drivable area comprises the following steps: determining a target area according to environmental perception data; determining at least two boundary extension regions corresponding to the target region according to the environmental perception data and a plurality of region boundary lines of the target region; determining a drivable area corresponding to the target area according to the at least two boundary extension areas; wherein the drivable area is an area for path planning when the vehicle drives into the target area, the environment perception data comprises data detected at multiple moments, and the at least two boundary extension areas comprise a first boundary extension area locked at a first moment and a second boundary extension area locked at a second moment; the first moment and the second moment are different moments.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and more specifically, to a method for determining a drivable area, a vehicle control method, a device, and a chip. Background Art

[0002] In autonomous driving technology, the vehicle can be routed to control the vehicle to enter a specific area such as a parking space. In order to perform route planning, the specific area and the surrounding area can be tested to determine the drivable area, and the route can be planned within the drivable area to control the vehicle to enter the specific area. Therefore, how to determine the accurate and reliable drivable area is of great significance to the route planning and vehicle control of autonomous driving. Summary of the invention

[0003] In view of this, the embodiment of the present disclosure proposes a new technical solution for determining a drivable area.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for determining a drivable area is provided, the method comprising:

[0005] Determine a target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines;

[0006] Determine at least two boundary extension areas corresponding to the target area according to the environment perception data and the multiple area boundary lines of the target area; wherein the environment perception data includes data detected at multiple moments, and the at least two boundary extension areas include a first boundary extension area locked at a first moment and a second boundary extension area locked at a second moment, and the first moment and the second moment are different moments;

[0007] A drivable area corresponding to the target area is determined according to the at least two boundary extension areas; wherein the drivable area is an area where a vehicle performs path planning when entering the target area.

[0008] Optionally, determining at least two boundary extension areas corresponding to the target area according to the environment perception data and a plurality of area boundary lines of the target area includes:

[0009] Determining an initial range of the boundary extension area according to a plurality of area boundary lines of the target area;

[0010] For each boundary extension area, a target range of the boundary extension area is determined according to the environment perception data and the initial range.

[0011] Optionally, determining the target range of the boundary extension area according to the environment perception data and the initial range includes:

[0012] Determine, according to the environmental perception data, a candidate reference point of the boundary extension area at each of a plurality of moments and a confidence level of the candidate reference point; wherein the candidate reference point is located within the initial range, and the confidence levels of the candidate reference points of different boundary extension areas at at least one moment are different;

[0013] Determine, based on the candidate reference points at the multiple moments and the confidences of the candidate reference points, a target reference point of the boundary extension area at the current moment and the confidence of the target reference point;

[0014] A target range of the boundary extension area is determined according to the target reference point and the confidence level.

[0015] Optionally,

[0016] The confidence of the candidate reference points of the first boundary extension area at multiple time moments after the first time moment is less than the confidence of the target reference point of the first boundary extension area at the first time moment;

[0017] The confidence of the candidate reference points of the second boundary extension area at multiple time moments after the second time moment is less than the confidence of the target reference point of the second boundary extension area at the second time moment.

[0018] Optionally, determining, according to the environment perception data, a candidate reference point of the boundary extension area at each of a plurality of moments and a confidence level of the candidate reference point comprises:

[0019] Determine obstacle information within an initial range of the boundary extension area according to the environment perception data;

[0020] Determine candidate reference points of the boundary extension area according to the obstacle information;

[0021] The confidence level of the candidate reference point is determined according to the coordinates of the candidate reference point and the sensor information of the vehicle.

[0022] Optionally, the obstacle information includes coordinates of a plurality of obstacle position points; and determining the candidate reference points of the boundary extension area according to the obstacle information includes:

[0023] The minimum distance among the vertical distances between the plurality of obstacle position points and the target area boundary line is taken as the first distance; wherein the target area boundary line is the area boundary line corresponding to the boundary extension area where the obstacle position point is located;

[0024] The minimum distance between the plurality of obstacle position points and the entry boundary line is used as the second distance; wherein the entry boundary line is a boundary line serving as a vehicle entry entrance among the plurality of area boundary lines, and the area boundary line corresponding to the boundary extension area is perpendicular to the entry boundary line;

[0025] A candidate reference point of the boundary extension area is determined according to the area boundary line, the entry boundary line, the first distance, and the second distance.

[0026] Optionally, determining the confidence of the candidate reference point according to the coordinates of the candidate reference point and the sensor information of the vehicle includes:

[0027] At least one of a distance detection confidence factor, a direction detection confidence factor, a multi-sensor assisted detection confidence factor, and a visibility detection confidence factor of the candidate reference point is calculated according to the coordinates of the candidate reference point and the sensor information of the vehicle;

[0028] The confidence of the candidate reference point is determined according to at least one of the distance detection confidence factor, the direction detection confidence factor, the multi-sensor assisted detection confidence factor, and the visibility detection confidence factor.

[0029] Optionally, the vehicle mounted sensors include a plurality of cameras, wherein:

[0030] The distance detection confidence factor is a detection confidence factor calculated according to the distance from the candidate reference point to the target camera and the maximum perception distance of the target camera; the target camera is a camera that can detect the candidate reference point and is closest to the multiple cameras installed on the vehicle;

[0031] The direction detection confidence factor is a detection confidence factor determined according to the angle between the direction from the candidate reference point to the target camera and the detection center direction of the target camera;

[0032] The multi-sensor assisted detection confidence factor is used to indicate whether the candidate reference point is detected by multiple types of sensors installed on the vehicle;

[0033] The visibility detection confidence factor is used to indicate a proportion of pixels within a specific area centered on the candidate reference point that can be detected by the camera installed on the vehicle.

[0034] Optionally, the multiple moments are multiple moments arranged in order from early to late; and determining the target reference point of the boundary extension area at the current moment and the confidence of the target reference point based on the candidate reference points at the multiple moments and the confidence of the candidate reference points comprises:

[0035] In the case where the current moment is the earliest moment among the multiple moments, the candidate reference point and confidence of the boundary extension area at the earliest moment are used as the target reference point and confidence at the earliest moment; or

[0036] When the current moment is the i-th moment among the multiple moments except the earliest moment, the target reference point and confidence at the i-th moment are determined based on the candidate reference point and confidence at the i-th moment and the target reference point and confidence at the i-1-th moment.

[0037] Optionally, determining the target reference point and the confidence at the i-th moment according to the candidate reference point and the confidence at the i-th moment and the target reference point and the confidence at the i-1-th moment includes:

[0038] If the confidence of the candidate reference point at the i-th moment is greater than or equal to the confidence of the target reference point at the i-1th moment, then adjusting the target reference point and confidence at the i-1th moment according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment; or,

[0039] If the confidence of the specific position point at the i-th moment is greater than or equal to the confidence of the specific position point at the i-1th moment, then the target reference point and confidence at the i-1th moment are adjusted according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment; wherein the specific position point is the target reference point at the i-1th moment; or,

[0040] If the confidence of the candidate reference point at the i-th moment is less than the confidence of the target reference point at the i-1th moment and the confidence of the specific position point at the i-th moment is less than the confidence of the specific position point at the i-1th moment, then the target reference point and confidence at the i-1th moment are used as the target reference point and confidence at the i-1th moment.

[0041] Optionally, determining the initial range of the boundary extension area according to a plurality of area boundary lines of the target area includes:

[0042] Determine an entry boundary line among the plurality of area boundary lines according to the current position of the vehicle; wherein the entry boundary line is an entrance for the vehicle to enter the target area;

[0043] At least two area boundary lines are determined from other area boundary lines except the entry boundary line, and boundary extension areas and initial ranges corresponding to the at least two area boundary lines are determined.

[0044] Optionally, the target area is a target parking space.

[0045] Optionally, the method further includes: displaying the target area and a drivable area corresponding to the target area through a display device.

[0046] According to a second aspect of an embodiment of the present disclosure, a method for determining a drivable area is provided, the method comprising:

[0047] Determine a target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines;

[0048] Determine at least one boundary extension area corresponding to the target area according to the environmental perception data and a plurality of area boundary lines of the target area; wherein the environmental perception data includes data detected at a plurality of moments and used to determine the boundary extension area, each of the boundary extension areas is determined at a specific moment, and the range of the boundary extension area is no longer updated after the specific moment;

[0049] A drivable area corresponding to the target area is determined according to the at least one boundary extension area; wherein the drivable area is an area where a vehicle performs path planning when entering the target area.

[0050] According to a third aspect of an embodiment of the present disclosure, a vehicle control method is provided, the method comprising:

[0051] Determine a target area and a drivable area corresponding to the target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines;

[0052] In the case where the target area is determined as the target area to be entered by the vehicle, path planning is performed within the drivable area, and the vehicle is controlled to enter the target area based on the planned path;

[0053] Among them, the drivable area is an area determined according to at least one boundary extension area for the vehicle to perform path planning when entering the target area; the at least one boundary extension area is at least one boundary extension area corresponding to the target area determined according to the environmental perception data and multiple area boundary lines of the target area; wherein the environmental perception data includes data detected at multiple times, and each of the boundary extension areas is determined at a specific time.

[0054] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute a method as described in any one of the first aspect, the second aspect or the third aspect.

[0055] According to a fourth aspect of an embodiment of the present disclosure, a vehicle is provided, comprising a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute a method as described in any one of the first aspect, the second aspect or the third aspect.

[0056] According to a fifth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method as described in any one of the first aspect, the second aspect or the third aspect is implemented.

[0057] According to a sixth aspect of an embodiment of the present disclosure, a chip is provided, comprising a processing unit, wherein the processing unit is configured to execute a method as described in any one of the first aspect, the second aspect or the third aspect.

[0058] Based on the method for determining the drivable area provided by the embodiment of the present disclosure, the area around the target area is divided into at least one boundary extension area according to the area boundary line of the target area. During the movement of the vehicle, the target range of each boundary extension area can be determined separately, and the target range of each boundary extension area can be obtained more flexibly and accurately, thereby making the drivable area determined according to the boundary extension area more accurate and reliable, thereby improving the safety and reliability of vehicle control.

[0059] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0061] Figure 1 The present invention is a schematic diagram of an intelligent network connection system to which the method provided by the embodiment of the present disclosure can be applied.

[0062] Figure 2 is based on Figure 1 The illustrated embodiment provides a schematic diagram of a vehicle.

[0063] Figure 3 It is a schematic diagram of an obstacle in a parking scene provided by an embodiment of the present disclosure.

[0064] Figure 4 It is a flowchart of a method for determining a drivable area provided in an embodiment of the present disclosure.

[0065] Figure 5 It is a schematic diagram of a boundary extension area of ​​a vertical area provided by an embodiment of the present disclosure.

[0066] Figure 6 It is a schematic diagram of a target area provided by an embodiment of the present disclosure, in which the target area is a boundary extension area of ​​a parallel area.

[0067] Figure 7 It is a schematic diagram of the relative positions of a vehicle and an obstacle provided by an embodiment of the present disclosure.

[0068] Figure 8 It is a flowchart of a method for determining a drivable area provided in an embodiment of the present disclosure.

[0069] Fig. 9 It is a flow chart of a vehicle control method provided by an embodiment of the present disclosure.

[0070] Fig.10 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0071] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0072] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0073] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods, and equipment should be considered as part of the specification.

[0074] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0075] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0076] First, the application scenarios of the embodiments of the present disclosure are described.

[0077] Figure 1 1 is a schematic diagram of an intelligent network system 100 to which the method provided by the embodiment of the present disclosure can be applied. Figure 1 As shown, the intelligent network connection system 100 may include: a vehicle 101, a server 102, and a user terminal 103.

[0078] In some examples, vehicle 101 may be a vehicle with an autonomous driving function. Autonomous driving is also known as unmanned driving or intelligent driving. Vehicles with autonomous driving functions can achieve driving tasks such as environmental perception, decision planning, and control execution. The level of autonomous driving can refer to the automotive intelligence classification standards formulated by the Society of Automotive Engineers (SAE). For example, L0 is manual driving, L1 is assisted driving, L2 is partial autonomous driving, L3 is conditional autonomous driving, L4 is highly autonomous driving, and L5 is fully autonomous driving. The above classification method for autonomous driving levels is only used as an example, and the disclosed embodiments do not limit the classification standards and levels of autonomous driving.

[0079] In some examples, the server 102 may be a single server or a distributed server cluster consisting of multiple servers, and its deployment method may include a local server or a cloud server. The server 102 may communicate with the vehicle 101 and / or the user terminal 103 based on a communication network, and provide various services for the vehicle 101 and / or the user terminal 103. For example, the server may receive the perception data sent by the vehicle, and provide the vehicle with services such as high-precision maps, data analysis, and decision-making planning. For another example, the server may receive query instructions or control instructions sent by the user terminal, and provide corresponding services to the user.

[0080] In some examples, the user terminal 103 may be any form of electronic device that provides services to users, such as a personal computer, a laptop, a smart tablet, a smart phone, a smart wearable device, etc. The user may interact with the vehicle or server through the human-computer interaction terminal configured in the vehicle 101, or may interact with the vehicle or server through the user terminal 103, for example, querying the status and / or parameters of the vehicle through the user terminal, or controlling the vehicle to perform set tasks and / or modify configuration parameters, etc.; wherein the user terminal runs an application based on the intelligent network connection system to achieve interaction with the vehicle or server, and the application may be a local application, a web application, a small program, etc., which is not limited here.

[0081] In some examples, the above-mentioned application running on the user terminal can provide authentication or authorization services for the user. The user who is successfully authenticated and granted the corresponding authority can query and / or control the vehicle within the scope of the granted authority.

[0082] The vehicle 101, the server 102 and the user terminal 103 can communicate with each other through the communication link provided by the communication network 104. The communication network 104 may include one or more networks of any type, for example, the communication network 104 may include the Internet, a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a public switched telephone network (PSTN), a satellite communication network, Wi-Fi, 2G, 3G, 4G, 5G, 6G, NB-IoT, eMTC, infrared, Bluetooth, NFC and other networks providing communication, or a combination of the above multiple networks. The communication networks between the vehicle 101 and the server 102, between the user terminal 103 and the server 102, and between the user terminal 103 and the vehicle 101 may be the same or different.

[0083] It should be noted that Figure 1 The structure of the intelligent network connection system 100 shown in the figure is only illustrative. The intelligent network connection system in the embodiment of the present disclosure is not limited to the above structure, and may include more or fewer devices as needed, and may also combine or split the devices. For example, the intelligent network connection system may not include a user terminal and / or a server; for another example, the user terminal and the server may be deployed together.

[0084] Figure 2 is based on Figure 1 The illustrated embodiment provides a schematic diagram of a vehicle 101. Figure 2 As shown, the vehicle 101 may include a perception component 1011, a computing platform 1012, an execution component 1013, etc. The perception component 1011, the computing platform 1012, and the execution component 1013 may be connected via a bus or other means.

[0085] In some examples, the perception component 1011 can be used to collect information about the vehicle itself or outside. The perception component 1011 may include at least one of a visual sensor unit, a radar, a positioning and navigation unit, an inertial measurement unit (IMU) or other sensing units, wherein the visual sensor unit may include one or more cameras, the radar may include at least one of a laser radar, a millimeter wave radar, an ultrasonic radar or other radars, and the positioning and navigation unit may include at least one of a GPS system, a Beidou system or other global positioning systems.

[0086] In some examples, the computing platform 1012 may include a device with computing capabilities, which is used to process the perception information collected by the perception component 1011 to obtain control information, and send corresponding control instructions to the execution component 1013, so that the execution component 1013 performs corresponding actions, thereby realizing control of the vehicle 101. For example, the computing platform 1012 can perform positioning and mapping (Simultaneous Localization and Mapping, SLAM), path planning, behavior decision-making and other behaviors on the vehicle, thereby realizing autonomous control of the vehicle. The computing platform 1012 may include at least one processor and at least one memory, and each processor may execute instructions stored in the memory individually or collectively to implement the method provided in the embodiment of the present disclosure. The processor in the embodiment of the present disclosure may include a central processing unit (CPU), a graphic processing unit (GPU), a neural-network processing unit (NPU), a tensor processing unit (TPU), a data processing unit (DPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), a microcontroller unit (MCU) or at least one of other processors. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a disk or an optical disk. In addition to storing instructions, the memory can also store data, such as high-precision maps, path information, vehicle location, direction, speed and other data. The data stored in the memory can be retrieved and used by the processor.

[0087] In some examples, the vehicle's computing platform can independently perform computing tasks or communicate with a server to complete computing tasks. For example, the vehicle's computing platform can cooperate with the server to complete corresponding computing tasks.

[0088] The computing platform 1012 may be arranged in the vehicle 101, and part or all of the computing platform 1012 may also be arranged in a server corresponding to the vehicle. For example, some functions of the computing platform 1012 with higher real-time requirements may be arranged in the vehicle, and other functions with lower real-time requirements may be arranged in the server corresponding to the vehicle.

[0089] In some examples, the execution component 1013 is used to execute corresponding actions based on the control of the computing platform 1012, so that the vehicle 101 completes the moving task. The execution component 1013 may include, for example, a power component, a brake component, a transmission component, a steering component, and the like.

[0090] It should be noted that Figure 2 The structure of the vehicle 101 shown in the figure is only illustrative. The vehicle in the embodiment of the present disclosure is not limited to the above structure, and may include more or fewer components as needed, and the devices may be combined or split. For example, the vehicle may not include the above computing platform. For another example, the vehicle may also include a communication component, an interface component, a multimedia component, an input component, an output component, etc.

[0091] In autonomous driving technology, the vehicle can be routed to control the vehicle to enter a specific area such as a parking space. In order to perform route planning, the specific area and the surrounding area can be tested to determine the drivable area, and the route can be planned within the drivable area to control the vehicle to enter the specific area. Therefore, how to determine the accurate and reliable drivable area is of great significance to the route planning and vehicle control of autonomous driving.

[0092] Taking the automatic parking function as an example, the following explanation is given: In the related technology, the target parking space and the surrounding area can be used as a whole for obstacle detection, and the detected obstacle information can be directly used to determine an overall drivable space area. However, due to the large number and complexity of obstacle types in the parking environment, and the obstacle detection accuracy will change with the position and detection angle of the sensor installed on the vehicle during the movement of the vehicle, resulting in low accuracy in directly using obstacle information to determine an overall drivable space area.

[0093] Figure 3 Schematic diagram of a parking scene with obstacles provided by an embodiment of the present disclosure. Figure 3As shown, there are a first obstacle 1 and a second obstacle 2 on the left side of the target area 31 (e.g., the target parking space), and a third obstacle 3 on the right side. When the target vehicle is at the first position 301 near the left side of the target parking space in the figure, since the target vehicle is closer to the first obstacle 1 and the second obstacle 2, the confidence of the relevant information of the first obstacle 1 and the second obstacle 2 detected by the vehicle's sensor is higher, while the confidence of the relevant information of the third obstacle 3 detected is lower; when the target vehicle drives to the second position 302 near the right side of the target parking space, since the target vehicle is away from the first obstacle 1 and the second obstacle 2 and closer to the third obstacle 3, the confidence of the relevant information of the first obstacle 1 and the second obstacle 2 detected by the vehicle's sensor decreases, while the confidence of the relevant information of the third obstacle 3 increases. Therefore, during the movement of the vehicle, the obstacle detection accuracy will change with the position and detection angle of the sensor installed on the vehicle, resulting in low accuracy in directly using obstacle information to determine an overall drivable space area, affecting the safety and reliability of parking. Figure 3 As shown, the target area may include multiple area boundary lines, such as Figure 3 As shown, the target area may include area boundary lines in four directions: front, back, left, and right. The front, back, left, and right directions may be determined by taking the direction of the target area facing the vehicle as the front, and the four directions are front, right, rear, and left in a clockwise direction. It is understandable that the four directions may also be determined by other methods.

[0094] It should be noted that the embodiments of the present disclosure are not only used in automatic parking scenarios, but can also be used in other scenarios where the drivable area needs to be determined, such as how to determine the drivable area when controlling a vehicle to enter a specific area (such as a small area).

[0095] Figure 4 is a flow chart of a method for determining a drivable area provided by an embodiment of the present disclosure. The method for determining a drivable area can be Figure 1 The vehicle and / or server are executed as shown. Figure 4 As shown, the method for determining a drivable area in this embodiment may include the following steps S410 to S430.

[0096] Step S410: determining a target area according to the environmental perception data.

[0097] The target area may include multiple area boundary lines. For example, the target area may include N area boundary lines, where N may be any integer greater than 1. The N area boundary lines may be located in different directions of the target area, for example, if the target area is a quadrilateral, the target area may include area boundary lines located in four directions, front, back, left, and right.

[0098] In some examples, the region boundary line may be an actual existing boundary line, such as a region boundary line actually carved on the ground.

[0099] In other examples, the area boundary line can also be a virtual boundary line. For example, obstacle information existing in the vehicle's surrounding environment is determined based on environmental perception data, an area that the vehicle can enter is determined as the target area based on the obstacle information, and a boundary line between the target area and the obstacle is determined.

[0100] It should be noted that all of the N area boundary lines may be actual boundary lines, all of them may be virtual boundary lines, or some of them may be actual boundary lines and some of them may be virtual boundary lines.

[0101] In some examples, the target area may be a target parking space, and the application scenario of the method may be an automatic parking scenario. For example, the target parking space may include four area boundary lines, that is, N is equal to 4.

[0102] In other examples, the target area may not be limited to parking spaces, but may be any area that a vehicle can enter or can accommodate a vehicle. For example, it may be any quadrilateral area that a vehicle can enter. The target area may include four area boundary lines, that is, N is equal to 4.

[0103] In some examples, the above-mentioned environmental perception data may be data obtained by detecting the surrounding environment of the vehicle through sensors during the driving of the vehicle, for example, it may include image data collected by visual sensors and / or point cloud data collected by radar. The environmental perception data may be input into a pre-generated neural network model to obtain the target area and / or obstacle information output by the neural network model.

[0104] Step S420: determining at least two boundary extension areas corresponding to the target area according to the environment perception data and a plurality of area boundary lines of the target area.

[0105] The environmental perception data may include data detected at multiple moments, and at least two boundary extension areas may include a first boundary extension area locked at a first moment and a second boundary extension area locked at a second moment, and the first moment and the second moment may be different moments.

[0106] For example, the first boundary extension area may be an area determined according to the environmental perception data of the first sampling time window, and the first sampling time window may include a plurality of sampling moments before and including the first moment. The second boundary extension area may be an area determined according to the environmental perception data of the second sampling time, and the second sampling time window may include a plurality of sampling moments before and including the second moment. The sampling moment may be the moment when the vehicle detects the environmental perception data.

[0107] In this way, the first boundary extension area and the second boundary extension area can be locked respectively at different times to improve the flexibility and accuracy of the boundary extension area.

[0108] In some embodiments, M boundary extension areas corresponding to the target area may be determined based on the environmental perception data and N area boundary lines of the target area.

[0109] Wherein, M may be a positive integer less than or equal to N, and M of the N area boundary lines may correspond to M boundary extension areas respectively, that is, the M boundary extension areas correspond one-to-one to the M area boundary lines, and the boundary extension area may be an area located outside the target area and through which the vehicle can drive when entering the target area. For example, the boundary extension area may be an area where the area boundary line extends outside the target area.

[0110] In some embodiments, the N area boundary lines of the target area may include an entry boundary line as a vehicle entry entrance; and the other M area boundary lines among the N-1 area boundary lines except the entry boundary line correspond to the M boundary extension areas respectively.

[0111] In some embodiments, the border extension area may be a quadrilateral area consisting of four corner points, and two corner points of the initial range are located on the area boundary line corresponding to the border extension area or the extension line of the area boundary line. For example, the quadrilateral area may be a rectangular area.

[0112] Step S430: determining a drivable area corresponding to the target area according to at least two boundary extension areas.

[0113] The drivable area may be an area where the vehicle performs path planning when entering the target area. For example, when the target area is determined as the target area to be entered by the vehicle, path planning may be performed in the drivable area, and the vehicle may be controlled to enter the target area based on the planned path.

[0114] In some examples, the drivable area may include an area of ​​a target area and an area of ​​a boundary extension area.

[0115] In some examples, a drivable area for a vehicle to enter a target area through the boundary extension area may be determined based on the at least two boundary extension areas.

[0116] By adopting the method of steps S410 to S430 above, the area around the target area is divided into at least two boundary extension areas. During the movement of the vehicle, each boundary extension area can be determined separately at different times, and the target range of each boundary extension area can be obtained more flexibly and accurately, thereby making the drivable area determined according to the boundary extension area more accurate and reliable, thereby improving the safety and reliability of vehicle control.

[0117] In some embodiments of the present disclosure, the above step S420 may include the following steps S421 and S422:

[0118] Step S421, determining an initial range of the boundary extension area according to a plurality of area boundary lines of the target area.

[0119] In some embodiments, the initial range of the border extension area may be a quadrilateral area consisting of four corner points, and two corner points of the initial range are located on the area boundary line corresponding to the border extension area or the extension line of the area boundary line. For example, the quadrilateral area may be a rectangular area.

[0120] Step S422: for each boundary extension area, determine a target range of the boundary extension area according to the environment perception data and the initial range.

[0121] For example, obstacle information within the initial range can be determined based on the environmental perception data, and a range without obstacles within the initial range can be determined based on the obstacle information as a target range of the boundary extension area. The target range and the initial range can be the same or different.

[0122] In some embodiments, step S421 may include: determining an entry boundary line among multiple area boundary lines based on the current position of the vehicle; determining at least two area boundary lines among other area boundary lines except the entry boundary line, and determining the boundary extension area and initial range corresponding to each of the at least two area boundary lines.

[0123] For example, if there are N area boundary lines in the target area, the entry boundary line among the N area boundary lines can be determined according to the current position of the vehicle; M area boundary lines are determined among the other N-1 area boundary lines except the entry boundary line, and the boundary extension areas corresponding to each of the M area boundary lines and the initial range of the boundary extension areas are determined.

[0124] The entry boundary line is the entrance for the vehicle to enter the target area. For example, the entry boundary line may be the area boundary line closest to the current position of the vehicle, or the entry boundary line may be the area boundary line that the vehicle needs to pass through when entering the target area from the current position.

[0125] In some examples, M may be equal to N-1, that is, all the regional boundary lines except the entry boundary line in the N regional boundary lines are taken as one of the M regional boundary lines. For example, if the target area includes four regional boundary lines, front, back, left, and right, and the entry boundary line is the front boundary line, then the three boundary lines on the left, right, and rear sides of the target area may be taken as the above-mentioned M regional boundary lines. In this way, the boundary extension area corresponding to the regional boundary line can be completely determined, and the range of the drivable area can be expanded as much as possible to increase the probability of the vehicle passing through.

[0126] In other examples, M may be less than N-1. For example, two area boundary lines adjacent to the entry boundary line among the N area boundary lines may be used as the M area boundary lines. For example, if the target area includes four area boundary lines, front, back, left, and right, and the entry boundary line is the front boundary line, the boundary lines on the left and right sides of the entry boundary line of the target area may be used as the M area boundary lines. In this way, the boundary extension area may be determined only for the adjacent area boundary lines, thereby reducing the number of boundary extension areas and improving the computational efficiency.

[0127] In some embodiments of the present disclosure, the initial range of each boundary extension area can be determined according to the area type of the target area. Under different area types, the initial range of each boundary extension area can be the same or different.

[0128] The area type of the target area can be used to indicate the relative relationship between the target driving direction and the current driving direction of the vehicle when the vehicle enters the target area. For example, if the target driving direction is the same as the current driving direction or differs by 180 degrees, the area type of the target area can be defined as a parallel area; for another example, if the target driving direction is different from the current driving direction and the angle difference is not 180 degrees, the area type of the target area can be defined as a non-parallel area. Optionally, the non-parallel area can be further divided into a vertical area and an oblique area. For example, if the target driving direction differs by 90 degrees or 270 degrees from the current driving direction, the area type of the target area can be defined as a vertical area; for another example, if the angle difference between the target driving direction and the current driving direction is an angle other than 0 degrees, 90 degrees, 180 degrees and 270 degrees (for example, 30 degrees, 45 degrees or 60 degrees), the area type of the target area can be defined as an oblique area.

[0129] Taking the target area as a target parking space as an example, the area type of the target area can be the parking space type of the target parking space, and the parking space type can include parallel parking spaces and non-parallel parking spaces, and the non-parallel parking spaces can include vertical parking spaces and diagonal parking spaces. Among them: vertical parking spaces can refer to parking spaces where vehicles are parked vertically to the lane; parallel parking spaces can refer to parking spaces where vehicles are parked parallel to the lane; diagonal parking spaces can refer to parking spaces where the parking spaces form a certain angle with the lane, such as a 45-degree angle or a 60-degree angle, and vehicles can be parked diagonally.

[0130] Figure 5 FIG. 1 is a schematic diagram of a target area provided by an embodiment of the present disclosure, wherein the target area is a boundary extension area of ​​a vertical area. Figure 5 As shown, the target area 51 is a vertical area (such as a vertical parking space), and the target area has four corner points, namely corner point 0, corner point 1, corner point 2, and corner point 3. The target area has four area boundary lines, namely the entry boundary line (the line segment between corner point 0 and corner point 1), the left boundary line located on the left side of the entry boundary line (the line segment between corner point 0 and corner point 3), the right boundary line located on the right side of the entry boundary line (the line segment between corner point 1 and corner point 2), and the lower boundary line located below the entry boundary line (the line segment between corner point 2 and corner point 3), so as to respectively determine the left boundary extension area, the right boundary extension area, and the lower boundary extension area. For example, the left boundary line can be extended to the left by a first distance (such as 1.2 meters) and extended upward by a second distance (such as 1.6 meters) to obtain the left boundary extension area; the right boundary line can be extended to the right by a first distance (such as 1.2 meters) and extended upward by a second distance (such as 1.6 meters) to obtain the right boundary extension area; the lower boundary line can be extended downward by a second distance (such as 1.6 meters) to obtain the lower boundary extension area.

[0131] In some examples, if the regional coordinate system is constructed with corner point 0 of the target area as the coordinate origin, the length direction from corner point 0 to corner point 3 as the x-axis, and the width direction from corner point 0 to corner point 1 as the y-axis, assuming that the length of the target area is x0, the width is y0, the above-mentioned first distance is y1, and the second distance is x1, then the coordinates of the four corner points of the left boundary extension area are (-x1, -y1), (-x1, 0), (x0, 0), and (x0, -y1); the coordinates of the four corner points of the right boundary extension area are (-x1, y0), (-x1, y0+y1), (x0, y0+y1), and (x0, y0); the coordinates of the four corner points of the lower boundary extension area are (x0, 0), (x0, y0), (x0+x1, y0), and (x0+x1, y0).

[0132] In some examples, the target area is a target parking space, and the area coordinate system is a parking space coordinate system.

[0133] In some examples, the specific values ​​of the first distance and the second distance may be any pre-set values.

[0134] In other examples, the first distance and the second distance may be set according to the size of the vehicle and / or the size of the target area. For example, the first distance may be greater than or equal to half of the first preset distance, which may be the width of the vehicle, the width of the target area, or the smaller value of the width of the vehicle and the width of the target area. For another example, the second distance may be greater than or equal to the width of the vehicle.

[0135] Figure 6 FIG. 1 is a schematic diagram of a target area provided by an embodiment of the present disclosure, wherein the target area is a boundary extension area of ​​a parallel area. Figure 6 As shown, the target area 61 is a parallel area (such as a parallel parking space), and the target area has four corner points, namely corner point 0, corner point 1, corner point 2, and corner point 3. The target area has four area boundary lines, namely the entry boundary line (the line segment between corner point 0 and corner point 1), the left boundary line located on the left side of the entry boundary line (the line segment between corner point 0 and corner point 3), the right boundary line located on the right side of the entry boundary line (the line segment between corner point 1 and corner point 2), and the lower boundary line located below the entry boundary line (the line segment between corner point 2 and corner point 3), so as to respectively determine the left boundary extension area, the right boundary extension area, and the lower boundary extension area. For example, the left boundary line can be extended to the left by a third distance (such as 2.6 meters) and extended upward by a fourth distance (such as 1.6 meters) to obtain the left boundary extension area; the right boundary line can be extended to the right by a third distance (such as 2.6 meters) and extended upward by a fourth distance (such as 1.6 meters) to obtain the right boundary extension area; the lower boundary line can be extended downward by a fourth distance (such as 1.6 meters) to obtain the right boundary extension area.

[0136] In some examples, specific values ​​of the third distance and the fourth distance may be any preset values.

[0137] In other examples, the third distance and the fourth distance may be set according to the vehicle body size and / or the area size of the target area. For example, the third distance may be greater than or equal to half of the second preset distance, and the second preset distance may be the vehicle body length, the target area length, or the smaller value of the vehicle body length and the target area length. For another example, the fourth distance may be greater than or equal to the vehicle body width.

[0138] Optionally, the fourth distance may be equal to the second distance, and the third distance may be greater than the first distance.

[0139] It should be noted that for other non-parallel regions, such as oblique regions, reference can also be made to Figure 5The manner in which the vertical regions are shown determines the initial extent of the border extension region.

[0140] In this way, different initial ranges of the boundary extension area can be determined for different types of target areas.

[0141] In some embodiments, the method of determining the target range of the boundary extension area according to the environmental perception data and the initial range in the above step S422 may include the following steps S4221 to S4223:

[0142] Step S4221: Determine the candidate reference points and the confidence levels of the candidate reference points in the boundary extension area at each of multiple moments according to the environmental perception data.

[0143] The candidate reference point is located within the initial range, and the confidence of the candidate reference point in different boundary extension areas at at least one moment is different.

[0144] Step S4222: Based on the candidate reference points and the confidence levels of the candidate reference points at multiple moments, determine the target reference point and the confidence level of the target reference point in the boundary extension area at the current moment.

[0145] Step S4223: Determine the target range of the boundary extension area based on the target reference point and the confidence level.

[0146] In this way, the target reference point and the confidence level of the target reference point at the current moment can be determined based on the environmental perception data detected at multiple moments, and the target range of the boundary extension area can be determined.

[0147] In some examples, the confidence of the candidate reference points in the first boundary extension area at multiple moments after the first moment is less than the confidence of the target reference point of the first boundary extension area at the first moment. In this way, the first boundary extension area can be locked at the first moment to avoid the decrease in the confidence of the candidate reference points after the first moment affecting the reliability of the first boundary extension area.

[0148] In some embodiments, the confidence of the candidate reference points of the second boundary extension area at multiple moments after the second moment is less than the confidence of the target reference point of the second boundary extension area at the second moment. In this way, the second boundary extension area can be locked at the second moment to avoid the decrease in the confidence of the candidate reference points after the second moment affecting the reliability of the second boundary extension area.

[0149] In some examples, if the target area and the drivable area corresponding to the target area can be displayed by a display device, the boundary extension area can also be displayed by a display device.

[0150] In some embodiments, the implementation of step S4221 may include: determining obstacle information within the initial range of the boundary extension area according to the environmental perception data; determining candidate reference points of the boundary extension area according to the obstacle information; and determining the confidence of the candidate reference points according to the coordinates of the candidate reference points and the sensor information of the vehicle. The obstacle information may include static obstacle information and / or dynamic obstacle information.

[0151] In some examples, the obstacle information may include obstacle location points based on freespace representation, such as obstacle freespace points.

[0152] For example, the obstacle information may be the result obtained after parsing the environmental perception data. The obstacle information may be composed of multiple location points (such as freespace points). The attributes of each location point include coordinate X, coordinate Y, obstacle type (vehicle, pedestrian, unknown, etc.), etc. The location and / or other attribute information of the obstacle can be determined through the obstacle information.

[0153] In some examples, if the obstacle information determined based on the environmental perception data does not include obstacle information within the initial range of the boundary extension area, the initial range of the boundary extension area can be used as the target range. At this time, the corner point farthest from the area boundary line among the multiple corner points of the initial range of the boundary extension area can be used as a candidate reference point.

[0154] In some other examples, if the obstacle information determined according to the environmental perception data includes the coordinates of multiple obstacle position points located within the initial range of the boundary extension area; then the method of determining the candidate reference points of the boundary extension area according to the obstacle information may include the following steps S11 to S13:

[0155] Step S11: taking the minimum distance among the vertical distances between the plurality of obstacle positions and the boundary line of the target area as the first distance.

[0156] The target area boundary line is the area boundary line corresponding to the boundary extension area where the obstacle location point is located.

[0157] Step S12: taking the minimum distance among the vertical distances between the plurality of obstacle positions and the driving-in boundary line as the second distance.

[0158] The entry boundary line is a boundary line serving as a vehicle entry entrance among the N area boundary lines, and the area boundary line corresponding to the boundary extension area is perpendicular to the entry boundary line.

[0159] Step S13: determining candidate reference points of the boundary extension area according to the area boundary line, the entry boundary line, the first distance and the second distance.

[0160] For example, the first coordinate of the candidate reference point can be determined based on the area boundary line and the first distance, and the second coordinate of the candidate reference point can be determined based on the entry boundary line and the second distance. In this way, a position point close to the target area and a position point close to the entrance of the target area can be selected from multiple obstacle position points.

[0161] like Figure 5 As shown in FIG. 1 , if the left boundary extension area (left_boundary) of the target area 51 has two obstacle positions (such as freespace points) falling therein, and the parking space coordinates of the two obstacle positions are (1.0, -0.5) and (-0.8, -0.7), then the coordinates of the candidate reference point (left_bound_point) of the left boundary extension area are (-0.8f, -0.5). Figure 6 As shown, if the right boundary extension area (right_boundary) of the target area 61 has two obstacle location points (such as freespace points) falling therein, and the parking space coordinates of the two obstacle location points are (1.2, slot_width+0.5) and (-0.6, slot_width+1.0f), then the available space coordinates of right_boundary right_bound_point are (-0.6f, slot_width+0.5), where slot_width is the horizontal parking space width.

[0162] In this way, candidate reference points of the boundary extension area can be accurately determined.

[0163] In some embodiments of the present disclosure, there may be multiple ways to determine the confidence of a candidate reference point. For example, the confidence of a candidate reference point may be determined based on the coordinates of the candidate reference point and the sensor information of the vehicle, including:

[0164] At least one of the distance detection confidence factor, direction detection confidence factor, multi-sensor assisted detection confidence factor, and visibility detection confidence factor of the candidate reference point is calculated based on the coordinates of the candidate reference point and the sensor information of the vehicle; and the confidence of the candidate reference point is determined based on at least one of the distance detection confidence factor, direction detection confidence factor, multi-sensor assisted detection confidence factor, and visibility detection confidence factor.

[0165] In some embodiments, the vehicle-mounted sensors may include multiple cameras (eg, fisheye cameras).

[0166] In some examples, the distance detection confidence factor may be a detection confidence calculated based on the distance from the candidate reference point to the target camera and the maximum perception distance of the target camera; wherein the target camera is a camera that is closest to the candidate reference point and can detect the candidate reference point among multiple cameras installed on the vehicle.

[0167] Figure 7 Schematic diagram of the relative position of a vehicle and an obstacle provided by an embodiment of the present disclosure. Figure 7 As shown in the figure, the vehicle is equipped with 4 cameras, which are installed in front of the front of the vehicle, behind the rear of the vehicle, on the left side of the vehicle and on the right side of the vehicle. When calculating the confidence, the area around the vehicle is divided into 6 areas, namely the left front area (left_front), the right front area (right_front), the left area (left), the right area (right), the left back area (left_back) and the right back area (right_back). Different camera sensors are used in different areas to calculate the confidence. For example, the candidate reference point with coordinates in the left_front area uses the left-view camera and the front-view camera to calculate its confidence, and the maximum confidence value is taken as the confidence value of the candidate reference point; for example, the candidate reference point in the left area uses the left-view camera to calculate its confidence; for example, the candidate reference point in the right_back area uses the right-view camera and the rear-view camera to calculate its confidence, and the maximum confidence value is taken as the confidence value of the candidate reference point.

[0168] The distance detection confidence factor may include a horizontal distance detection confidence factor and / or a vertical distance detection confidence factor, and the maximum sensing distance of the target camera may include a horizontal maximum sensing distance and / or a vertical maximum sensing distance. Figure 7 They are described as follows:

[0169] Longitudinal distance detection confidence factor: Figure 7 As shown, taking the target camera as a front-view camera as an example, ref_dis_x is the longitudinal distance from the camera's installation position to its detection boundary, that is, the longitudinal maximum perception distance of the target camera, and dis_x is the longitudinal distance from the candidate position point to the camera's installation position. For example, the longitudinal distance detection confidence factor can be calculated based on the following formula (1):

[0170]

[0171] Among them, position_x_conf represents the longitudinal distance detection confidence factor of the candidate reference point, dis_x represents the longitudinal distance from the candidate reference point to the target camera, and ref_dis_x represents the longitudinal maximum perception distance of the target camera.

[0172] Confidence factor of lateral distance detection: Figure 7As shown, taking the target camera as a front-view camera as an example, ref_dis_y is the lateral position from the camera's installation position to its detection boundary, that is, the lateral maximum perception distance of the target camera, and dis_y is the lateral distance from the candidate position point to the camera's installation position. For example, the lateral distance detection confidence factor can be calculated based on the following formula (2):

[0173]

[0174] Among them, position_y_conf represents the lateral distance detection confidence factor of the candidate reference point, dis_y represents the lateral distance from the candidate reference point to the target camera, and ref_dis_y represents the lateral maximum perception distance of the target camera.

[0175] It should be noted that the ref_dis_x of different cameras can have the same or different values, such as the ref_dis_x of the front camera is 25.6 meters, and the ref_dis_x of the left, right and rear cameras is 12.8 meters. The ref_dis_y of different cameras can also have the same or different values, such as the ref_dis_y of the front, rear, left and right cameras is 12.8 meters.

[0176] In this way, an accurate distance detection confidence factor can be calculated.

[0177] The direction detection confidence factor is a detection confidence factor determined according to the angle between the direction from the candidate reference point to the target camera and the detection center direction of the target camera. The direction detection confidence factor may also be referred to as an orientation factor.

[0178] Different cameras have different detection center directions, which can be represented by the unit direction vector ref_vec(x0,y0) of their orientation. For example, the unit direction vector of the front camera is (0,-1), the unit direction vector of the left camera is (-1,0), the unit direction vector of the rear camera is (0,1), and the unit direction vector of the right camera is (1,0). The direction from the candidate reference point to the target camera can also be represented by a vector. For example, the vector connecting the candidate reference point and the target camera installation position is vec(x,y), and the confidence corresponding to the calculated orientation factor is:

[0179] For example, the direction detection confidence factor of the candidate reference point can be calculated by the following formula (3):

[0180]

[0181] Among them, yaw_conf represents the direction detection confidence factor of the candidate reference point, (x, y) represents the vector representation of the candidate reference point, and (x0, y0) represents the vector representation of the detection center direction of the target camera.

[0182] In this way, an accurate direction detection confidence factor can be calculated.

[0183] The multi-sensor assisted detection confidence factor can be used to indicate whether a candidate reference point is detected by multiple types of sensors installed on the vehicle.

[0184] By way of example, the multiple types of sensors may include cameras and ultrasound. If a candidate reference point is detected by both ultrasound and a camera, the coordinates of the candidate reference point may be corrected based on ultrasound. In this case, the multi-sensor assisted detection confidence factor may be a preset maximum value (e.g., 1); otherwise, if the candidate reference point is only detected by the camera but not by ultrasound, the multi-sensor assisted detection confidence factor may be a preset minimum value (e.g., 0).

[0185] The visibility detection confidence factor may be used to indicate the proportion of pixels within a specific area centered at the candidate reference point that can be detected by a vehicle-mounted camera.

[0186] For example, the specific area range may be a 7*7 square range around the candidate reference point as the center. If the proportion of pixels within the specific area range that can be detected by the camera installed on the vehicle is greater than or equal to a preset proportion threshold (e.g., 0.7 or 0.8), the visibility detection confidence factor may be a preset maximum value (e.g., 1); otherwise, if the proportion of pixels within the specific area range that can be detected by the camera installed on the vehicle is less than the preset proportion threshold, the visibility detection confidence factor may be a preset minimum value (e.g., 0).

[0187] In some examples, the confidence of the candidate reference point can be calculated by the following formula (4): final_conf = (A1*pos_x_conf+A2*pos_y_conf+A3*yaw_conf+A4*uss_conf)*vis_conf (4)

[0188] Among them, position_x_conf represents the longitudinal distance detection confidence factor of the candidate reference point, position_y_conf represents the lateral distance detection confidence factor of the candidate reference point, yaw_conf represents the direction detection confidence factor of the candidate reference point, uss_conf represents the multi-sensor assisted detection confidence factor of the candidate reference point, vis_conf represents the visibility detection confidence factor of the candidate reference point, A1 to A4 are weighted coefficients of the confidence factors corresponding to each factor, and the sum of A1 to A4 is 1. The values ​​of A1 to A4 can be set according to simulation or test conditions.

[0189] In some examples, the weighting coefficients of different cameras may be the same. In other examples, the weighting coefficients of different cameras may be different, for example, the weighting coefficients of the longitudinal distance detection confidence factor of the front view camera and the rear view camera are smaller than the weighting coefficient of the lateral distance detection confidence factor; while the weighting coefficients of the longitudinal distance detection confidence factor of the left view camera and the right view camera are larger than the weighting coefficient of the lateral distance detection confidence factor.

[0190] For example, if the target camera of the candidate reference point is a front-view camera or a rear-view camera, the above weighting coefficients may be respectively: A1=0.15, A2=0.35, A3=0.4, A4=0.1; if the target camera of the candidate reference point is a left-view camera or a right-view camera, the above weighting coefficients may be respectively: A1=0.35, A2=0.15, A3=0.4, A4=0.1.

[0191] In some examples, if a candidate reference point is within the visible range of two cameras, the maximum value of the confidences calculated by the two cameras is taken.

[0192] In this way, the confidence of the candidate reference point can be accurately determined based on at least one of the distance detection confidence factor, the direction detection confidence factor, the multi-sensor assisted detection confidence factor, and the visibility detection confidence factor.

[0193] In some embodiments of the present disclosure, the multiple moments are multiple moments arranged in order from early to late; the implementation of the above step S4222 may include:

[0194] When the current moment is the earliest moment among the multiple moments, the candidate reference point and confidence level of the boundary extension area at the earliest moment are used as the target reference point and confidence level at the earliest moment; or,

[0195] When the current moment is the i-th moment among multiple moments except the earliest moment, the target reference point and confidence at the i-th moment are determined based on the candidate reference point and confidence at the i-th moment and the target reference point and confidence at the i-1-th moment.

[0196] Here, i is an integer greater than 1, and the earliest moment among the multiple moments may be the moment when the vehicle records the first frame of environmental perception data.

[0197] In some examples, the implementation of determining the target reference point and the confidence at the i-th moment according to the candidate reference point and the confidence at the i-th moment and the target reference point and the confidence at the i-1-th moment may include at least one of the following:

[0198] Method 1: If the confidence of the candidate reference point at the i-th moment is greater than or equal to the confidence of the target reference point at the i-1th moment, the target reference point and confidence at the i-1th moment are adjusted according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment.

[0199] The method for adjusting the target reference point and the confidence at the i-1th moment may adopt a confidence weighted average method. For example, the coordinates of the candidate reference point at the i-th moment and the coordinates of the target reference point at the i-1th moment may be weighted averaged according to the confidence to obtain the target reference point at the i-th moment; the confidence of the candidate reference point at the i-th moment and the confidence of the target reference point at the i-1th moment may also be weighted averaged to obtain the confidence of the target reference point at the i-th moment.

[0200] Method 2: If the confidence of the specific position point at the i-th moment is greater than or equal to the confidence of the specific position point at the i-1th moment, the target reference point and confidence at the i-1th moment are adjusted according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment.

[0201] The specific position point is the target reference point at the i-1th moment.

[0202] In this way, after the position of the dynamic obstacle in the boundary extension area changes, the specific position point at the historical moment (for example, the i-1th moment) can still be locked, and the confidence of the specific position point at the previous and next moments can be compared to determine whether to adjust the target reference point and the confidence according to the size of the confidence. This can flexibly adapt to complex scenarios where both static obstacles and dynamic obstacles exist.

[0203] Method 3: If the confidence of the candidate reference point at the i-th moment is less than the confidence of the target reference point at the i-1th moment and the confidence of the specific position point at the i-th moment is less than the confidence of the specific position point at the i-1th moment, the target reference point and confidence at the i-1th moment are used as the target reference point and confidence at the i-th moment. That is, the target reference point and confidence are not updated, which is equivalent to locking the boundary extension area.

[0204] Method 4: If the confidence of the candidate reference point at the i-th moment is less than the confidence of the target reference point at the i-1th moment, the target reference point and confidence at the i-1th moment are used as the target reference point and confidence at the i-th moment.

[0205] In this way, since the candidate reference points and confidence levels of different boundary extension areas detected by the vehicle at the same position are different, the candidate reference points and confidence levels detected at different positions of the vehicle for the same boundary extension area are also different. Therefore, the drivable area of ​​the target area is divided into multiple boundary extension areas, and the target reference point of each boundary extension area is locked using the confidence level to maximize the use of available space without collision risk. In addition, the method of calculating the confidence level considers all influencing factors and is easy to expand. The output target reference point and confidence level can be conveniently used downstream to determine the drivable area, thereby improving the safety and reliability of vehicle control.

[0206] Figure 8 is a flow chart of determining a drivable area provided by an embodiment of the present disclosure. The method can be Figure 1 The vehicle and / or server are executed as shown. Figure 8 As shown, the method for determining a drivable area in this embodiment may include:

[0207] Step S810, determining a target area according to the environmental perception data.

[0208] The target area may have multiple area boundary lines, for example, N area boundary lines, where N is an integer greater than 1.

[0209] The target area may have multiple area boundary lines, for example, N area boundary lines, where N is an integer greater than 1.

[0210] In some examples, the implementation of step S810 can refer to Figure 4 The specific implementation method of step S410 in the illustrated embodiment will not be repeated here.

[0211] Step S820: determining at least one boundary extension area corresponding to the target area according to the environment perception data and multiple area boundary lines of the target area.

[0212] In some examples, the environmental perception data may include data detected at multiple times and used to determine the boundary extension area, each boundary extension area is determined at a specific time, and the range of the boundary extension area is no longer updated after the specific time.

[0213] For example, during the driving of the vehicle, the boundary extension area is locked at a specific moment, and after the specific moment, the range of the boundary extension area is no longer updated and remains the range of the boundary extension area locked at the specific moment.

[0214] In one implementation, the above-mentioned after a specific moment may refer to the period between a specific moment and the current moment, the current moment may be the latest moment in the vehicle's driving process, such as the moment when the latest environmental perception data is collected during the vehicle's driving process, and the specific moment may be a historical moment before the current moment. In this way, the range of the boundary extension area is no longer updated between the characteristic moment and the current moment. Optionally, the specific moment may also be the current moment, that is, the boundary extension area may also be determined at the current moment.

[0215] Optionally, the collection moment of the environment perception data used to determine the boundary extension area at a specific moment includes the specific moment and / or a specific historical moment before the specific moment.

[0216] Optionally, different boundary extension areas in the at least one boundary extension area may be determined at different specific moments, for example, based on environmental perception data at different moments.

[0217] In some examples, the above-mentioned specific moment may be the moment when the confidence of the target reference point of the boundary extension area is the highest, for example, the confidence of the candidate reference points of the boundary extension area in multiple moments after the specific moment is less than the confidence of the target reference point of the boundary extension area at the specific moment. In this way, the boundary extension area can be locked at a specific moment based on the confidence, and the boundary extension area is no longer updated after the confidence at the subsequent moment decreases, that is, the boundary extension area at the specific moment can be used as the boundary extension area at the subsequent moment; on the contrary, if the confidence at a certain moment increases, for example, the confidence of the candidate reference point of the boundary extension area at the third moment after the specific moment is greater than or equal to the confidence of the target reference point of the boundary extension area at the specific moment, then the target reference point and confidence can be updated based on the candidate reference point and confidence at the third moment, and the updated target reference point and confidence are used as the new target reference point and confidence at the third moment. The determination method of the candidate reference point, target reference point and confidence of the boundary extension area can refer to the description in the aforementioned embodiment of the present disclosure.

[0218] In some examples, the implementation of step S820 can refer to Figure 4 The specific implementation method of step S420 in the illustrated embodiment will not be repeated here.

[0219] Step S830: determining a drivable area corresponding to the target area according to at least one boundary extension area.

[0220] The drivable area is the area where the vehicle performs path planning when entering the target area.

[0221] In some examples, the implementation of step S830 can refer to Figure 4 The specific implementation method of step S430 in the illustrated embodiment will not be repeated here.

[0222] By adopting the method of steps S810 to S830 above, at least one boundary extension area around the target area is determined at a specific moment, so that the target range of the boundary extension area can be obtained more flexibly and accurately, thereby making the drivable area determined according to the boundary extension area more accurate and reliable, thereby improving the safety and reliability of vehicle control.

[0223] Fig. 9 is a flow chart of a vehicle control method provided by an embodiment of the present disclosure. The vehicle control method may be Figure 1 The vehicle and / or server are executed as shown. Fig. 9 As shown, the method of this embodiment may include:

[0224] Step S910: determining a target area and a drivable area corresponding to the target area according to the environmental perception data.

[0225] The target area may have multiple area boundary lines, for example, N area boundary lines, where N is an integer greater than 1.

[0226] Step S920: When the target area is determined as the target area to be entered by the vehicle, path planning is performed within the drivable area, and the vehicle is controlled to enter the target area based on the planned path.

[0227] Among them, the drivable area is an area determined according to at least one boundary extension area for path planning of the vehicle when entering the target area; at least one boundary extension area is at least one boundary extension area corresponding to the target area determined according to environmental perception data and multiple area boundary lines of the target area; wherein the environmental perception data includes data detected at multiple times, and each boundary extension area is determined at a specific time.

[0228] The method for determining the drivable area can refer to the description in the aforementioned embodiments of the present disclosure, and will not be repeated here.

[0229] In this way, the area around the target area is divided into M boundary extension areas according to the regional boundary line of the target area. During the movement of the vehicle, the target range of each boundary extension area can be determined separately, and the target range of each boundary extension area can be obtained more flexibly and accurately, thereby making the drivable area determined according to the boundary extension area more accurate and reliable, thereby improving the safety and reliability of vehicle control.

[0230] Fig.10 Schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Fig.10As shown, the electronic device 1000 may include a memory 1010 and a processor 1020. The memory 1010 may be used to store computer instructions, and the processor 1020 may be used to call computer instructions from the memory 1010 to execute all or part of the steps of any method in the aforementioned embodiments of the present disclosure. The processor may be one or more, and the one or more processors may execute instructions individually or together. The memory may also be one or more, and the one or more memories may store the above-mentioned computer instructions individually or together. Optionally, the electronic device may be Figure 1 Servers and / or vehicles in.

[0231] The embodiment of the present disclosure also provides a vehicle, which may include a memory and a processor, wherein the memory may be used to store computer instructions, and the processor may be used to call computer instructions from the memory to execute all or part of the steps of any method in the aforementioned embodiment of the present disclosure. The processor may be one or more, and the one or more processors may execute instructions individually or collectively, and the memory may also be one or more, and the one or more memories may store the above-mentioned computer instructions individually or collectively.

[0232] The vehicle in the foregoing embodiments of the present disclosure may be an electric vehicle, a hybrid vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle may be an autonomous vehicle or a non-autonomous vehicle. For example, the vehicle provided in this embodiment may be Figure 1 or Figure 2 Vehicle shown.

[0233] The embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any method in the aforementioned embodiments of the present disclosure is implemented. Optionally, the computer-readable storage medium may be a non-transitory storage medium, but is not limited thereto, and may also be a transient storage medium.

[0234] The present disclosure also provides a chip, which may include a processing unit, which may be used to execute all or part of the steps of any method in the foregoing embodiments of the present disclosure. The chip may be a chip in the form of an application-specific integrated chip ASIC, a system on chip SOC, a field programmable gate array FPGA, etc., which is not limited in the present embodiment. Optionally, the chip may also include a storage unit, which may be used to store computer instructions, and the processing unit may be used to call computer instructions from the storage unit to execute all or part of the steps of any method in the foregoing embodiments of the present disclosure.

[0235] The embodiments of the present disclosure further provide a computer program product, which may include a computer program. When the computer program is executed by a processor, any method in the aforementioned embodiments of the present disclosure may be implemented.

[0236] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement any method in the foregoing embodiments of the present disclosure.

[0237] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0238] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0239] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, which may include object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0240] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0241] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so as to produce a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device for implementing the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions make the computer, programmable data processing device, and / or other equipment work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0242] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0243] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and the module, a program segment or a part of an instruction contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions. It should be noted that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0244] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for determining a drivable area, characterized in that: The method comprises: Determine a target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines; Determine at least two boundary extension areas corresponding to the target area according to the environment perception data and the multiple area boundary lines of the target area; wherein the environment perception data includes data detected at multiple moments, and the at least two boundary extension areas include a first boundary extension area locked at a first moment and a second boundary extension area locked at a second moment, and the first moment and the second moment are different moments; A drivable area corresponding to the target area is determined according to the at least two boundary extension areas; wherein the drivable area is an area where a vehicle performs path planning when entering the target area.

2. The method according to claim 1, characterized in that The step of determining at least two boundary extension areas corresponding to the target area according to the environment perception data and the multiple area boundary lines of the target area includes: Determining an initial range of the boundary extension area according to a plurality of area boundary lines of the target area; For each boundary extension area, a target range of the boundary extension area is determined according to the environment perception data and the initial range.

3. The method according to claim 2, characterized in that The step of determining a target range of the boundary extension area according to the environment perception data and the initial range includes: Determine, according to the environmental perception data, a candidate reference point of the boundary extension area at each of a plurality of moments and a confidence level of the candidate reference point; wherein the candidate reference point is located within the initial range, and the confidence levels of the candidate reference points of different boundary extension areas at at least one moment are different; Determine, based on the candidate reference points at the multiple moments and the confidences of the candidate reference points, a target reference point of the boundary extension area at the current moment and the confidence of the target reference point; A target range of the boundary extension area is determined according to the target reference point and the confidence level.

4. The method according to claim 3, characterized in that The confidence of the candidate reference points of the first boundary extension area at multiple time moments after the first time moment is less than the confidence of the target reference point of the first boundary extension area at the first time moment; The confidence of the candidate reference points of the second boundary extension area at multiple time moments after the second time moment is less than the confidence of the target reference point of the second boundary extension area at the second time moment.

5. The method according to claim 3, characterized in that: The determining, according to the environmental perception data, a candidate reference point of the boundary extension area at each of a plurality of moments and a confidence level of the candidate reference point comprises: Determine obstacle information within an initial range of the boundary extension area according to the environmental perception data; Determine candidate reference points of the boundary extension area according to the obstacle information; The confidence level of the candidate reference point is determined according to the coordinates of the candidate reference point and the sensor information of the vehicle.

6. The method according to claim 5, characterized in that The obstacle information includes coordinates of a plurality of obstacle position points; and determining the candidate reference points of the boundary extension area according to the obstacle information includes: The minimum distance among the vertical distances between the plurality of obstacle position points and the target area boundary line is taken as the first distance; wherein the target area boundary line is the area boundary line corresponding to the boundary extension area where the obstacle position point is located; The minimum distance between the plurality of obstacle position points and the entry boundary line is used as the second distance; wherein the entry boundary line is a boundary line serving as a vehicle entry entrance among the plurality of area boundary lines, and the area boundary line corresponding to the boundary extension area is perpendicular to the entry boundary line; A candidate reference point of the boundary extension area is determined according to the area boundary line, the entry boundary line, the first distance, and the second distance.

7. The method according to claim 5, characterized in that The step of determining the confidence level of the candidate reference point according to the coordinates of the candidate reference point and the sensor information of the vehicle includes: At least one of a distance detection confidence factor, a direction detection confidence factor, a multi-sensor assisted detection confidence factor, and a visibility detection confidence factor of the candidate reference point is calculated according to the coordinates of the candidate reference point and the sensor information of the vehicle; The confidence of the candidate reference point is determined according to at least one of the distance detection confidence factor, the direction detection confidence factor, the multi-sensor assisted detection confidence factor, and the visibility detection confidence factor.

8. The method according to claim 7, characterized in that The vehicle-mounted sensors include a plurality of cameras, wherein: The distance detection confidence factor is a detection confidence factor calculated according to the distance from the candidate reference point to the target camera and the maximum perception distance of the target camera; the target camera is a camera that can detect the candidate reference point and is closest to the multiple cameras installed on the vehicle; The direction detection confidence factor is a detection confidence factor determined according to the angle between the direction from the candidate reference point to the target camera and the detection center direction of the target camera; The multi-sensor assisted detection confidence factor is used to indicate whether the candidate reference point is detected by multiple types of sensors installed on the vehicle; The visibility detection confidence factor is used to indicate a proportion of pixels within a specific area centered on the candidate reference point that can be detected by the camera installed on the vehicle.

9. The method according to claim 3, characterized in that: The multiple moments are multiple moments arranged in order from early to late; the determining, based on the candidate reference points at the multiple moments and the confidences of the candidate reference points, the target reference point of the boundary extension area at the current moment and the confidence of the target reference point comprises: In the case where the current moment is the earliest moment among the multiple moments, the candidate reference point and confidence of the boundary extension area at the earliest moment are used as the target reference point and confidence at the earliest moment; or When the current moment is the i-th moment among the multiple moments except the earliest moment, the target reference point and confidence at the i-th moment are determined based on the candidate reference point and confidence at the i-th moment and the target reference point and confidence at the i-1-th moment.

10. The method according to claim 9, characterized in that The determining the target reference point and the confidence at the i-th moment according to the candidate reference point and the confidence at the i-th moment and the target reference point and the confidence at the i-1-th moment includes: If the confidence of the candidate reference point at the i-th moment is greater than or equal to the confidence of the target reference point at the i-1th moment, then adjusting the target reference point and confidence at the i-1th moment according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment; or, If the confidence of the specific position point at the i-th moment is greater than or equal to the confidence of the specific position point at the i-1th moment, then the target reference point and confidence at the i-1th moment are adjusted according to the candidate reference point and confidence at the i-th moment to obtain the target reference point and confidence at the i-th moment; wherein the specific position point is the target reference point at the i-1th moment; or, If the confidence of the candidate reference point at the i-th moment is less than the confidence of the target reference point at the i-1th moment and the confidence of the specific position point at the i-th moment is less than the confidence of the specific position point at the i-1th moment, then the target reference point and confidence at the i-1th moment are used as the target reference point and confidence at the i-1th moment.

11. The method according to claim 2, characterized in that The step of determining the initial range of the boundary extension area according to the plurality of area boundary lines of the target area includes: Determine an entry boundary line among the plurality of area boundary lines according to the current position of the vehicle; wherein the entry boundary line is an entrance for the vehicle to enter the target area; At least two area boundary lines are determined from other area boundary lines except the entry boundary line, and boundary extension areas and initial ranges corresponding to the at least two area boundary lines are determined.

12. The method according to any one of claims 1 to 11, characterized in that The target area is a target parking space.

13. The method according to any one of claims 1 to 11, characterized in that The method further comprises: The target area and the drivable area corresponding to the target area are displayed by a display device.

14. A method for determining a drivable area, characterized in that: The method comprises: Determine a target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines; Determine at least one boundary extension area corresponding to the target area according to the environmental perception data and a plurality of area boundary lines of the target area; wherein the environmental perception data includes data detected at a plurality of moments and used to determine the boundary extension area, each of the boundary extension areas is determined at a specific moment, and the range of the boundary extension area is no longer updated after the specific moment; A drivable area corresponding to the target area is determined according to the at least one boundary extension area; wherein the drivable area is an area where a vehicle performs path planning when entering the target area.

15. A vehicle control method, characterized in that: The method comprises: Determine a target area and a drivable area corresponding to the target area according to the environmental perception data; wherein the target area includes a plurality of area boundary lines; In the case where the target area is determined as the target area to be entered by the vehicle, path planning is performed within the drivable area, and the vehicle is controlled to enter the target area based on the planned path; Among them, the drivable area is an area determined according to at least one boundary extension area for the vehicle to perform path planning when entering the target area; the at least one boundary extension area is at least one boundary extension area corresponding to the target area determined according to the environmental perception data and multiple area boundary lines of the target area; wherein the environmental perception data includes data detected at multiple times, and each of the boundary extension areas is determined at a specific time.

16. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute: the method according to any one of claims 1 to 15.

17. A vehicle, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute: the method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the computer program implements: the method according to any one of claims 1 to 15.

19. A chip, characterized in that: The chip comprises: the chip comprises a processing unit, and the processing unit is used to execute the method as claimed in any one of claims 1 to 15.

Images