A vehicle driving control method, device, equipment and storage medium

Abstract

The application provides a vehicle driving control method, device, equipment and storage medium, the method comprises the following steps: target fusion and drivable area fusion are carried out on the sensor signal on the target vehicle, pedestrian target information and drivable area signal are obtained respectively; target cognition and environment cognition are carried out on the target vehicle based on the pedestrian target complete collision avoidance data table and the pedestrian target information, the dangerous pedestrian signal and the dangerous area signal are obtained; longitudinal driving speed planning and / or lateral driving distance planning are carried out on the target vehicle based on the dangerous pedestrian signal, the dangerous area signal and the drivable area signal, so that the target vehicle after planning and the pedestrian target will not contact. The application adopts the control strategy of longitudinal driving speed planning and / or lateral driving distance planning for the vehicle to the pedestrian target outside the vehicle, thereby reducing the possibility of contact between the vehicle and the pedestrian, so as to play a role in identifying and protecting the external pedestrian target during the driving of the vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology for vehicles, specifically to a vehicle driving control method, device, equipment, and storage medium. Background Technology

[0002] The Automatic Parking Assist (APA) system employs multi-sensor (ultrasonic, millimeter-wave, camera, lidar, etc.) fusion detection technology to achieve Level 4 autonomous driving functions within a limited area, including last-mile valet parking, remote valet parking, remote vehicle relocation, and one-click vehicle summoning. The APA system is used in surface or underground parking lots outside public roads, operating at speeds between 0 and 15 km / h. Because the APA system is positioned as Level 4, meaning there is no driver inside the vehicle and no need for remote user supervision, its "observation" capability relies entirely on sensor detection. In parking lot environments, the density of stationary obstacles (vehicles) is high, ambient light is poor, and pedestrians frequently park and retrieve their vehicles, resulting in a very high rate of pedestrian collisions outside the vehicle, making it difficult to effectively guarantee the safety of pedestrians.

[0003] ISO 22737, the first international technical standard specifically for Level 4 autonomous driving systems, primarily regulates and restricts low-speed automated driving (LSAD) on predefined routes with operating speeds below 32 km / h. It explicitly states the need for pedestrian detection and protection, requiring the autonomous driving system to stop before a collision with a pedestrian. However, current solutions based on this standard have the following drawbacks:

[0004] 1. Current solutions for handling pedestrians outside the vehicle in intelligent driving systems partly rely on a site-based intelligent V2X (Vehicle to Everything) approach. This involves the vehicle analyzing pedestrian hazards by communicating with the outside world (the parking lot or other surrounding vehicles) in real time. The V2X method requires auxiliary facilities at the site, the vehicle itself, and other vehicles to detect pedestrian positions and speeds. Furthermore, ensuring effective communication during information exchange is crucial. However, currently, most parking lots struggle to achieve 100% effective network coverage for vehicles. Therefore, this approach places high demands on both the site and the vehicle, significantly limiting its adaptability to various parking scenarios.

[0005] 2. The existing solutions lack a systematic approach to handling pedestrians outside the vehicle, which means that in some extreme scenarios (such as pedestrians suddenly appearing out of the way), pedestrians cannot completely avoid collisions.

[0006] 3. The existing solutions have relatively simple strategies for dealing with pedestrians outside the vehicle, which cannot cover pedestrians in different scenarios, locations, and motion states, and are prone to accidental braking and missed braking of pedestrians outside the vehicle.

[0007] 4. Most existing solutions rely on pedestrian movement speed to control pedestrian targets. However, pedestrian targets outside the vehicle differ from vehicle targets. Pedestrians are highly mobile targets, and sensors such as vision and millimeter-wave sensors have poor accuracy in measuring pedestrian speed. Furthermore, pedestrians' speed changes significantly after observing their environment (pedestrians have strong observation and thinking abilities), making accurate prediction difficult. Therefore, relying primarily on pedestrian movement speed for vehicle control is prone to false braking or missed braking. Summary of the Invention

[0008] In view of the shortcomings of the prior art described above, this application provides a vehicle driving control method, device, equipment and storage medium to solve the above technical problems.

[0009] This application provides a vehicle driving control method, including the following steps:

[0010] Target fusion is performed on sensor signals on the target vehicle to obtain pedestrian target information located in the external space region of the target vehicle; wherein, the target vehicle includes the current vehicle, and the pedestrian target information includes pedestrian targets and pedestrian target attribute information;

[0011] Based on a pre-determined complete collision avoidance data table for pedestrian targets and the pedestrian target information, the target vehicle is subjected to target recognition and environmental recognition to obtain dangerous pedestrian signals and dangerous area signals.

[0012] The sensor signals on the target vehicle are subjected to occlusion pedestrian fusion to obtain occlusion pedestrian fusion results; and the sensor signals on the target vehicle are subjected to drivable area fusion to obtain drivable area signals.

[0013] Based on the pre-generated parking scene hazard level identification results, the occluded pedestrian fusion results, the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, the longitudinal driving speed of the target vehicle is planned; and / or, based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, the lateral driving distance of the target vehicle is planned so that the planned target vehicle will not come into contact with the pedestrian target.

[0014] In one embodiment of this application, the process of obtaining dangerous pedestrian signals and dangerous area signals by performing target recognition and environmental recognition on the target vehicle based on a pre-determined pedestrian target complete collision avoidance data table and the pedestrian target information includes:

[0015] Based on a pre-determined pedestrian target collision avoidance data table, the maximum longitudinal distance at which the front and rear bumpers of the target vehicle can completely avoid collision with the pedestrian target without reducing the current longitudinal driving speed is determined, and the maximum longitudinal distance is taken as the length of the danger zone.

[0016] Based on the current longitudinal driving speed of the target vehicle and the width of the target vehicle, determine the minimum value of the width of the danger zone when the length of the danger zone is not empty, and use the minimum value of the width of the danger zone as the width of the danger zone in the current cycle.

[0017] The length of the danger zone and the width of the danger zone in the current cycle are combined to generate a rectangular region, and this rectangular region is used as the danger zone of the target vehicle to generate the danger zone signal; and...

[0018] Based on the danger zone of the target vehicle and the driving environment of the target vehicle, the risk zone of the target vehicle is determined; wherein, the driving environment of the target vehicle includes: the maximum longitudinal driving speed of the target vehicle;

[0019] The dangerous pedestrian signal is generated based on the movement state of the target pedestrian and whether the pedestrian's location is within the danger zone or the risk zone.

[0020] In one embodiment of this application, the process of planning the longitudinal driving speed of the target vehicle includes:

[0021] The system receives the dangerous pedestrian signal and determines whether a dangerous pedestrian target exists based on the signal. If a pedestrian target exists in the dangerous area or the risk area, then a dangerous pedestrian target exists. If no pedestrian target exists in the dangerous area or the risk area, then no dangerous pedestrian target exists.

[0022] When there are no dangerous pedestrian targets, the first preset speed is used as the longitudinal speed of the target vehicle;

[0023] When a dangerous pedestrian is present, determine whether the pedestrian is located in a dangerous area;

[0024] If the pedestrian target is located in the danger zone and the pedestrian target is stationary, control the target vehicle to maintain its current longitudinal driving speed;

[0025] If the pedestrian target is located in the danger zone and the pedestrian target is in motion, based on the pedestrian target's motion state and the target vehicle's current longitudinal speed, it is determined whether a first ratio is greater than a second ratio; if the first ratio is greater than the second ratio, the target vehicle is controlled to maintain its current longitudinal speed; if the first ratio is less than or equal to the second ratio, the target vehicle's longitudinal speed is planned according to low-speed emergency braking.

[0026] Wherein, the first ratio is the ratio of the lateral distance of the pedestrian target to the moving speed of the pedestrian target, and the second ratio is the ratio of the longitudinal distance of the pedestrian target to the current longitudinal driving speed of the target vehicle.

[0027] In one embodiment of this application, the process of planning the longitudinal driving speed of the target vehicle further includes:

[0028] If the pedestrian target is located in the risk area and the pedestrian target is stationary, determine whether the target vehicle and the pedestrian target have overlapping trajectories; if the target vehicle and the pedestrian target do not have overlapping trajectories, control the target vehicle to travel at a second preset speed; if the target vehicle and the pedestrian target have overlapping trajectories, control the longitudinal speed of the target vehicle according to the distance between the pedestrian target and the target vehicle.

[0029] If the pedestrian target is located in the risk area and the pedestrian target is in motion, then based on the pedestrian target's motion state, it is determined whether the pedestrian target is moving longitudinally; if the pedestrian target is moving longitudinally, it is determined whether the target vehicle and the pedestrian target have overlapping trajectories, and the longitudinal driving speed of the target vehicle is controlled according to the trajectory overlap determination result; if the pedestrian target is moving laterally, the longitudinal driving speed of the target vehicle is controlled according to the distance between the pedestrian target and the target vehicle.

[0030] In one embodiment of this application, the process of planning the longitudinal driving speed of the target vehicle further includes:

[0031] The dangerous area and risk area of ​​the target vehicle are combined to form the unsafe area of ​​the target vehicle; and the space area outside the target vehicle's external space area, excluding the unsafe area, is defined as the safe area of ​​the target vehicle.

[0032] The longitudinal driving speed of the target vehicle relative to each pedestrian target in the unsafe area is obtained and denoted as the expected longitudinal driving speed of each pedestrian target;

[0033] The expected longitudinal driving speed of each pedestrian target is summed and the minimum value is taken to obtain the final expected longitudinal driving speed of all dangerous pedestrian targets in the unsafe area. This speed is used as the longitudinal driving speed of the target vehicle based on the current pedestrian target and is denoted as the first planned longitudinal driving speed.

[0034] The first planned longitudinal driving speed, the third planned longitudinal driving speed, and the longitudinal speed of the obscured pedestrian are combined to obtain the longitudinal driving speed of the target vehicle when there is a pedestrian target in the unsafe area. The longitudinal driving speed is used as the final result of adjusting the driving speed of the target vehicle. The obscured pedestrian fusion result includes the longitudinal speed of the obscured pedestrian, and the third planned longitudinal driving speed is obtained according to the driving environment of the target vehicle.

[0035] In one embodiment of this application, the process of obtaining the third planned longitudinal driving speed includes:

[0036] Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width.

[0037] The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle.

[0038] Based on the minimum lateral distance of the target vehicle and the complete collision avoidance data table for the pedestrian target, the maximum longitudinal driving speed of the target vehicle under the current driving environment is obtained and used as the second planned longitudinal driving speed.

[0039] Based on the second planned longitudinal driving speed, parking scenario hazard coefficient, and parking scenario hazard correction speed, the maximum speed supported by the current scenario is calculated; wherein, the pre-generated parking scenario hazard level identification results include: parking scenario hazard coefficient and parking scenario hazard correction speed.

[0040] The maximum speed supported by the current scenario is compared with the third preset speed, and the larger one is taken as the third planned longitudinal driving speed.

[0041] In one embodiment of this application, the calculation process of the parking scenario hazard coefficient includes:

[0042]

[0043] In the formula, W is the hazard coefficient for the parking scenario, ranging from 0% to 100%; t The level of danger at different times of the day; W p The parking lot is considered dangerous due to its busy location; W d Risk level during holidays.

[0044] In one embodiment of this application, the process of planning the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal includes:

[0045] Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width.

[0046] The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle.

[0047] Calculate the difference between the first minimum width and the second minimum width, and record it as the first difference; then determine whether the absolute value of the first difference is greater than or equal to a first preset value.

[0048] If the absolute value is less than the first preset value, it is determined that the target vehicle has no offset space at the current moment, and no lateral driving distance adjustment is made to the target vehicle;

[0049] If the absolute value is greater than or equal to the first preset value, it is determined that the target vehicle has an offset space at the current moment, and it is determined whether the minimum lateral distance of the target vehicle is less than or equal to the second preset value; if the minimum lateral distance of the target vehicle is greater than the second preset value, it is determined that there is no offset requirement at the current moment, and no lateral driving distance adjustment is made to the target vehicle; if the minimum lateral distance of the target vehicle is less than or equal to the second preset value, it is determined that there is an offset requirement at the current moment, and the dangerous pedestrian signal is received, and it is determined whether there is a dangerous pedestrian target based on the dangerous pedestrian signal; if there is a pedestrian target in the dangerous area or the risk area, then there is a dangerous pedestrian target, and no lateral driving distance adjustment is made to the target vehicle; if there is no pedestrian target in the dangerous area or the risk area, then there is no dangerous pedestrian target, and the lateral driving distance adjustment is made to the target vehicle.

[0050] In one embodiment of this application, if there are no pedestrian targets in the dangerous area and the risk area, the process of adjusting the lateral driving distance of the target vehicle includes:

[0051] Calculate the difference between the preset optimal lateral distance and the minimum lateral distance of the target vehicle, and record it as the second difference;

[0052] Determine whether twice the second difference is less than or equal to the absolute value of the first difference; if twice the second difference is less than or equal to the absolute value of the first difference, then the second difference is taken as the lateral offset distance of the target vehicle; if twice the second difference is greater than the absolute value of the first difference, then half of the absolute value of the first difference is taken as the lateral offset distance of the target vehicle.

[0053] Determine whether the second difference is greater than or equal to zero; if the second difference is greater than or equal to zero, control the target vehicle to shift to the left by the corresponding lateral offset distance; if the second difference is less than zero, control the target vehicle to shift to the right by the corresponding lateral offset distance.

[0054] In one embodiment of this application, the process of planning the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal includes:

[0055] Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width.

[0056] The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle.

[0057] Determine whether the minimum lateral distance to the target vehicle is greater than the width of the danger zone;

[0058] If the minimum lateral distance to the target vehicle is greater than the width of the danger zone, then there is no real-time risk of pedestrian collision.

[0059] If the minimum lateral distance to the target vehicle is less than or equal to the width of the danger zone, there is a real-time risk of pedestrian collision.

[0060] This application also provides a vehicle driving control device, the device comprising:

[0061] The target fusion module is used to fuse sensor signals from the target vehicle to obtain pedestrian target information located in the external space area of ​​the target vehicle; wherein, the target vehicle includes the current vehicle, and the pedestrian target information includes pedestrian targets and pedestrian target attribute information;

[0062] The target recognition and environment recognition module is used to perform target recognition and environment recognition on the target vehicle based on a pre-determined pedestrian target collision avoidance data table and the pedestrian target, and obtain dangerous pedestrian signals and dangerous area signals;

[0063] An occlusion pedestrian fusion module is used to perform occlusion pedestrian fusion on the sensor signals on the target vehicle to obtain the occlusion pedestrian fusion result;

[0064] The drivable area fusion module is used to fuse the sensor signals on the target vehicle to obtain a drivable area signal.

[0065] The vehicle driving planning and control module is used to plan the longitudinal driving speed of the target vehicle based on the pre-generated parking scene hazard level identification result, the occluded pedestrian fusion result, the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal; and / or to plan the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, so that the planned target vehicle will not come into contact with the pedestrian target.

[0066] This application also provides a vehicle driving control device, the device comprising:

[0067] One or more processors;

[0068] A storage device for storing one or more programs, which, when executed by one or more processors, cause the device to implement the vehicle driving control method as described above.

[0069] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer's processor, causes the computer to perform the vehicle driving control method as described in any of the above-described methods.

[0070] As described above, this application provides a vehicle driving control method, apparatus, device, and storage medium, which has the following beneficial effects: This application obtains pedestrian target information located in the external space area of ​​the target vehicle by performing target fusion on sensor signals on the target vehicle; and performs occlusion pedestrian fusion on sensor signals on the target vehicle to obtain occlusion pedestrian fusion results; and performs drivable area fusion on sensor signals on the target vehicle to obtain drivable area signals; simultaneously, based on a pre-determined pedestrian target complete collision avoidance data table and pedestrian target information, the target vehicle performs target recognition and environmental recognition to obtain dangerous pedestrian signals and dangerous area signals; finally, based on pre-generated parking scene hazard level identification results, occlusion pedestrian fusion results, dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs longitudinal driving speed planning; and / or, based on dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs lateral driving distance planning to ensure that the planned target vehicle will not come into contact with the pedestrian target. Wherein, the target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information. Therefore, this application utilizes existing vehicle perception sensors (such as front radar, forward-facing camera, surround-view, and ultrasonic sensors) and employs a multi-sensor fusion method to perceive the external driving environment and pedestrian information. This allows it to determine the location of pedestrians in the external spatial area based on their motion characteristics. Furthermore, this application employs control strategies for longitudinal speed planning and / or lateral distance planning for pedestrians in different spatial areas, thereby reducing the likelihood of vehicle-pedestrian contact and enabling the vehicle to identify and protect external pedestrians during operation. Essentially, this application can assess the risk of a collision between the vehicle and pedestrians based on the driving environment and pedestrian targets, and then adjust the vehicle's driving state to plan the collision avoidance speed for pedestrians.

[0071] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0072] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0073] Figure 1 This is a schematic diagram illustrating an exemplary system architecture that applies the technical solutions in one or more embodiments of this application;

[0074] Figure 2 This is a logical schematic diagram of a vehicle driving control method provided in one embodiment of this application;

[0075] Figure 3 This is a schematic diagram illustrating the division of the external space area of ​​a vehicle according to an embodiment of this application;

[0076] Figure 4 This is a schematic diagram illustrating the process of target recognition and environmental recognition provided in one embodiment of this application;

[0077] Figure 5 This is a schematic diagram illustrating the process of planning the longitudinal driving speed of a vehicle according to an embodiment of this application.

[0078] Figure 6 This is a flowchart illustrating the process of planning the lateral driving distance of a vehicle according to an embodiment of this application.

[0079] Figure 7 This is a schematic diagram of the hardware structure of a vehicle driving control device suitable for implementing one or more embodiments of this application.

[0080] Explanation of parameters in the above figures:

[0081] Parameter symbol Physical meaning of parameters Parameter Units LS Danger zone length rice ZS Danger zone width rice V The longitudinal speed of this vehicle Km / h Vp The target pedestrian speed is set to 5 km / h in this invention. Km / h ZV The width of this vehicle is taken as 1m in this invention. rice Lstop Braking distance of this vehicle rice L1 The longitudinal distance of this vehicle when it comes to a stop rice △Z Lateral offset of this vehicle rice P1 Lateral distance of pedestrian target rice P2 Longitudinal distance of pedestrian target rice V1n The current speed of the vehicle planned for the pedestrian target Km / h V1 The final expected driving speed V1 based on all dangerous pedestrian targets Km / h V2 Based on environmental planning, the vehicle's longitudinal travel speed Km / h V3 Maximum driving speed supported based on the scenario Km / h V4 Obstructing pedestrian longitudinal speed Km / h Z1 Minimum width of the obstacle on the left within the longitudinal range of the drivable area rice Z2 Minimum width of the obstacle on the right within the longitudinal range of the drivable area rice Zmin Minimum lateral distance between the vehicle and obstacles on both sides within the danger zone rice Vs The planned longitudinal speed at the current moment. Km / h Vx Parking scenario danger level correction vehicle speed Km / h Detailed Implementation

[0082] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0083] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0084] In this application, "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0085] The term "multiple" in this application refers to two or more.

[0086] In the description of this application, the terms "first," "second," etc., are used only for the purpose of distinguishing descriptions and should not be construed as indicating or implying relative importance or order.

[0087] Furthermore, in the embodiments of this application, the term "exemplary" is used to indicate that it is an example, illustration, or description. Any embodiment or implementation described as "exemplary" in this application should not be construed as being more preferred or advantageous than other embodiments or implementations. Rather, the use of the term "exemplary" is intended to present the concept in a specific manner.

[0088] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the present application. However, it will be apparent to those skilled in the art that embodiments of the present application may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present application.

[0089] Low-speed emergency braking refers to the ability of a driver to quickly and correctly use the brakes to bring the vehicle to a stop within the shortest possible distance when encountering an emergency while driving.

[0090] Figure 1 A schematic diagram of an exemplary system architecture that can apply the technical solutions of one or more embodiments of this application is shown. Figure 1 As shown, the system architecture 100 may include terminal device 110, network 120, and server 130. Terminal device 110 may include various electronic devices such as smartphones, tablets, laptops, and desktop computers. Server 130 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, such as a wired communication link or a wireless communication link.

[0091] Depending on the implementation requirements, the system architecture in this application embodiment can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group composed of multiple server devices. In addition, the technical solutions provided in this application embodiment can be applied to terminal device 110, or to server 130, or can be implemented jointly by terminal device 110 and server 130. This application does not impose any special limitations on this.

[0092] In one embodiment of this application, the terminal device 110 or server 130 can perform target fusion on sensor signals on the target vehicle to obtain pedestrian target information located in the external space area of ​​the target vehicle; and perform occlusion pedestrian fusion on sensor signals on the target vehicle to obtain occlusion pedestrian fusion results; and perform drivable area fusion on sensor signals on the target vehicle to obtain drivable area signals; simultaneously, based on a pre-determined pedestrian target complete collision avoidance data table and pedestrian target information, the target vehicle performs target recognition and environmental recognition to obtain dangerous pedestrian signals and dangerous area signals; finally, based on pre-generated parking scene hazard level identification results, occlusion pedestrian fusion results, dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs longitudinal driving speed planning; and / or, based on dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs lateral driving distance planning to ensure that the planned target vehicle will not come into contact with the pedestrian target. The target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information. The vehicle driving control method executed by terminal device 110 or server 130 can perceive the external driving environment and pedestrian information based on the vehicle's existing perception sensors (such as front radar, forward-facing camera, surround view, ultrasonic sensors, etc.) using a multi-sensor fusion method. This allows for the determination of the pedestrian's position in the external spatial area based on the pedestrian's motion characteristics. Simultaneously, for pedestrians in different spatial areas, control strategies are applied to the vehicle using longitudinal speed planning and / or lateral distance planning, thereby reducing the possibility of vehicle-pedestrian contact and enabling the vehicle to identify and protect external pedestrians during driving. Essentially, the vehicle driving control method executed by terminal device 110 or server 130 can evaluate the risk of collision between the vehicle and pedestrians from the perspectives of the driving environment and pedestrian targets, and then adjust the vehicle's driving state to complete the collision avoidance speed planning for pedestrians.

[0093] The above section introduced an exemplary system architecture that applies the technical solution of this application. Next, we will continue to introduce the vehicle driving control method of this application.

[0094] Figure 2 A logical schematic diagram of a vehicle driving control method provided in an embodiment of this application is shown. Specifically, in an exemplary embodiment, as... Figure 2 As shown, this embodiment provides a vehicle driving control method, which includes the following steps:

[0095] Target fusion is performed on sensor signals on the target vehicle to obtain pedestrian target information located in the external space region of the target vehicle. The target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information. In some embodiments, the current vehicle may also be referred to as the "this vehicle". The pedestrian target attribute information includes pedestrian target ID, pedestrian target type, pedestrian target lateral and longitudinal distance, pedestrian target lateral and longitudinal relative velocity, pedestrian target position, etc. As an example, this embodiment can divide the external space region in the vehicle's direction of travel into a dangerous area, a risk area, and a safe area. The vehicle's direction of travel includes the forward direction and the backward direction, and the unsafe area includes the dangerous area and the risk area. Specifically, as... Figure 3 As shown, in this embodiment, the hazardous area can be defined as a rectangular area in front of the vehicle's outer contour in the direction of travel, with a lateral distance of ±ZS meters and a longitudinal distance of LS meters. The risk area can be defined as a rectangular area outside the hazardous area in the direction of travel. Since the maximum longitudinal speed limit in a typical parking lot is 15 km / h, the lateral distance of this rectangular area is designed to be ±4 meters, and the longitudinal distance is designed to be 15-LS meters. The safe area can be the space surrounding the vehicle excluding the hazardous and risk areas.

[0096] Based on a pre-defined pedestrian collision avoidance data table and pedestrian target information, the system performs target recognition and environmental recognition on the target vehicle to obtain dangerous pedestrian signals and dangerous area signals. Since pedestrian targets outside the vehicle differ from vehicle targets—pedestrians are highly mobile targets—visual and millimeter-wave sensors have poor accuracy in measuring pedestrian speed, and pedestrians' speed changes significantly after observing their environment, making accurate prediction difficult. Therefore, this embodiment, based on the movement characteristics of pedestrians, utilizes existing vehicle perception sensors—front radar, forward-facing camera, surround-view, and ultrasonic sensors—and employs a multi-sensor fusion method to perceive the external driving environment and pedestrian information. This allows for the determination of the pedestrian's position in the external space based on their movement characteristics, thus enabling the assessment of whether a pedestrian exists in the vehicle's unsafe areas. Figure 4As shown, this embodiment, based on a pre-determined pedestrian target collision avoidance data table and pedestrian target information, performs target recognition and environmental recognition on the target vehicle to obtain dangerous pedestrian signals and dangerous area signals. The process includes: determining the maximum longitudinal distance at which the front and rear bumpers of the target vehicle can completely avoid collision with the pedestrian target without reducing its current longitudinal speed, based on the pre-determined pedestrian target collision avoidance data table; using this maximum longitudinal distance as the dangerous area length; determining the minimum dangerous area width corresponding to a non-empty dangerous area length based on the target vehicle's current longitudinal speed and vehicle width, using this minimum dangerous area width as the dangerous area width for the current period; combining the dangerous area length and the dangerous area width for the current period to generate a rectangular area, using this rectangular area as the target vehicle's dangerous area, and generating a dangerous area signal; and determining the target vehicle's risk area based on the target vehicle's dangerous area and driving environment, where the target vehicle's driving environment includes: the target vehicle's maximum longitudinal speed; and generating a dangerous pedestrian signal based on the pedestrian's motion state and whether the pedestrian's position is within the dangerous area or risk area. This is equivalent to the target vehicle's target recognition and environmental recognition process. The input signals are the longitudinal vehicle speed V, the pedestrian target collision avoidance data table, and the pedestrian target output from the target fusion module. The output signals are the danger zone width ZS, danger zone length LS, pedestrian target position, the area where the pedestrian target is located (risk zone / danger zone), and the pedestrian target's motion state (stationary, longitudinal, lateral). That is, target recognition and environmental recognition involve two processes: danger zone recognition and dangerous pedestrian recognition. In danger zone recognition, based on the vehicle's current speed, the system queries the pedestrian target collision avoidance data table to read the minimum danger zone width ZS corresponding to a non-empty danger zone length LS. This minimum danger zone width ZS is used as the current period's danger zone width value, and the corresponding danger zone length value is read. The current period's danger zone width value is ±4m, and the danger zone length value is (15-LS) meters. In the dangerous pedestrian recognition process, the system receives the pedestrian target output from the target fusion module, determines whether the pedestrian is in the danger zone or risk zone based on the pedestrian target's position coordinates, and selects and outputs all pedestrian targets within the danger zone and risk zone. Output the target location, the area where the target is located (risk area / dangerous area), and the target's motion state (stationary, longitudinal, lateral). In some embodiments or figures, the pedestrian target complete collision avoidance data table may also be referred to as the pedestrian complete collision avoidance table.

[0097] The sensor signals on the target vehicle are subjected to occlusion pedestrian fusion to obtain the occlusion pedestrian fusion result; and the sensor signals on the target vehicle are subjected to drivable area fusion to obtain the drivable area signal.

[0098] Based on the pre-generated parking scene hazard level identification results, occluded pedestrian fusion results, dangerous pedestrian signals, dangerous area signals, and drivable area signals, longitudinal driving speed planning is performed for the target vehicle; and / or, based on dangerous pedestrian signals, dangerous area signals, and drivable area signals, lateral driving distance planning is performed for the target vehicle, so that the planned target vehicle will not come into contact with the pedestrian target.

[0099] Therefore, this embodiment utilizes existing vehicle perception sensors (such as front radar, forward-facing camera, surround-view, and ultrasonic sensors) and employs a multi-sensor fusion method to perceive the external driving environment and pedestrian information. This allows it to determine the pedestrian's location in the external spatial area based on the pedestrian's motion characteristics. Furthermore, this embodiment employs longitudinal speed planning and / or lateral distance planning control strategies for pedestrians in different spatial areas, thereby reducing the possibility of vehicle-pedestrian contact and enabling the vehicle to identify and protect external pedestrians during operation. Essentially, this embodiment can assess the risk of a collision between the vehicle and pedestrians based on the driving environment and pedestrian targets, and then adjust the vehicle's driving state to plan the collision avoidance speed for pedestrians.

[0100] In an exemplary embodiment, the process of dividing the external space area of ​​a target vehicle into a safe zone and an unsafe zone includes: determining, based on a pre-determined pedestrian target complete collision avoidance data table, the maximum longitudinal distance at which the front and rear bumpers of the target vehicle can completely avoid collision with a pedestrian target without reducing the current longitudinal driving speed, and using the maximum longitudinal distance as the danger zone length; determining, based on the current longitudinal driving speed and the width of the target vehicle, the minimum value of the danger zone width corresponding to the danger zone length being non-empty, and using the minimum value of the danger zone width as the danger zone width for the current period; combining the danger zone length and the danger zone width for the current period to generate a rectangular area, and using the rectangular area as the danger zone of the target vehicle; and determining the risk zone of the target vehicle based on the danger zone of the target vehicle and the driving environment of the target vehicle; wherein, the driving environment of the target vehicle includes: the maximum longitudinal driving speed of the target vehicle; combining the danger zone and the risk zone of the target vehicle as the unsafe zone of the target vehicle; and using the space area outside the unsafe zone in the external space area of ​​the target vehicle as the safe zone of the target vehicle.

[0101] Specifically, in this embodiment, the process of dividing the external space of the target vehicle into safe and unsafe zones can be as follows: A pre-determined pedestrian target collision avoidance data table is obtained. This table is calibrated using data simulation and real-vehicle testing. The table contains three dimensions: the horizontal dimension of the table header represents the width of the danger zone ZS; the vertical dimension represents the vehicle's longitudinal speed; and each cell in the table represents the maximum longitudinal distance at which the front and rear bumpers of the vehicle can completely avoid a collision with a pedestrian when the pedestrian crosses the danger zone beyond the horizontal distance ZS, without the vehicle slowing down. This is the length of the danger zone. However, this length only indicates that the vehicle will not collide with a pedestrian within the danger zone's length when the pedestrian crosses it laterally outside the danger zone. Pedestrians within the danger zone may collide with the vehicle because they cannot stop completely. Therefore, to ensure that pedestrians at any position within the danger zone can avoid a collision, the length of the danger zone should be sufficient for the vehicle to stop completely; that is, the length of the danger zone should be greater than the vehicle's stopping distance. The length of the danger zone must meet the following two conditions: (1) Ensure that no collision occurs within the length of the danger zone when a pedestrian crosses it laterally outside the danger zone, i.e., the length of the danger zone LS < (Zs-ZV)*V / Vp; (2) The length of the danger zone is greater than the braking distance of the vehicle, i.e., the length of the danger zone LS > Lstop; where LS is the length of the danger zone; ZS is the width of the danger zone; ZV is the width of the vehicle, which can be taken as 1m here; V is the longitudinal speed of the vehicle, and the longitudinal speed range of the vehicle in the parking lot environment is 0~16km / h; Vp is the target pedestrian speed, and according to the survey, the walking speed of adults is 5km / h. It is assumed that the lateral speed of pedestrians is less than 5km / h when they are not crossing completely, and when children and the elderly are crossing completely. Here, the pedestrian's movement speed is taken as 5km / h; Lstop is the braking distance of the vehicle, and the braking deceleration range of the vehicle in the parking lot environment is: 0m / s 2 ~-9m m / s 2 Here, we take -5m / s 2 The pedestrian target complete collision avoidance data table in this embodiment is shown in Table 1 below.

[0102] Table 1. Pedestrian Target Complete Collision Avoidance Data

[0103]

[0104] In one exemplary embodiment, the method further includes calculating a parking scenario hazard coefficient W based on the hazard level at different times of day, the hazard level during peak parking periods, and the hazard level on holidays. Specifically, the hazard coefficient W is calculated based on the aforementioned hazard levels at different times of day. t Parking lot bustling area danger level W p Holiday risk level W d Analysis yields the hazard coefficient W for the parking scenario, which is:

[0105]

[0106] In the formula, W is the hazard coefficient for the parking scenario, ranging from 0% to 100%; t The level of danger at different times of the day; W p The parking lot is considered dangerous due to its busy location; W d Risk level during holidays.

[0107] Specifically, regarding the risk level at different times of the day, this embodiment summarizes the data from 408 traffic accidents as shown in Table 2. Although the statistics focus on traffic accidents, they reveal the activity levels of people at different times of the day. Furthermore, existing European accident analysis reports show that the number of accidents at different times of the day is almost identical to that in Table 2. Therefore, based on human activity levels, the risk level at different times of the day is divided into three risk levels, as shown in Table 3, with risk levels ranging from low to high as Level 1, Level 2, and Level 3.

[0108] Table 2 Statistical Analysis of Traffic Accidents

[0109]

[0110] Table 3. Risk level W at different times of the day t

[0111]

[0112]

[0113] Regarding the hazard level of a parking lot, this embodiment classifies the hazard level W based on the daily traffic flow (24 hours) of the parking lot, according to the level of its activity. p The risk levels are divided into three categories, as shown in Table 4, with risk level W. p From lightest to heaviest, they are classified as Level 1, Level 2, and Level 3.

[0114] Table 4. Danger Level of Parking Lots Due to High Traffic Congestion (W) p

[0115] Parking lot bustling Level 1 Level 2 Level 3 Traffic volume / day Less than 500 vehicles 500 to 2000 vehicles More than 2,000 vehicles

[0116] Since human activity levels are closely related to holidays, this example uses statistics from Beijing's Xidan Commercial Street to estimate the holiday risk level. Xidan Commercial Street typically sees 145,000 visitors on weekdays, 165,000 on weekends, and 230,000 on statutory holidays. Therefore, the holiday risk level W for various shopping malls, hospitals, and other public places can be inferred. d It can be divided into three hazard levels, as shown in Table 5, with hazard level W. dFrom lightest to heaviest, they are classified as Level 1, Level 2, and Level 3.

[0117] Table 5. Holiday Risk Level W d

[0118] Holidays weekdays Weekend (Saturday and Sunday) statutory holidays Danger level Level 1 Level 2 Level 3

[0119] In an exemplary embodiment, the process of planning the longitudinal driving speed of the target vehicle includes: receiving a dangerous pedestrian signal and determining whether a dangerous pedestrian target exists based on the dangerous pedestrian signal; if a pedestrian target exists in a dangerous area or a risk area, then a dangerous pedestrian target exists; if no pedestrian target exists in a dangerous area or a risk area, then no dangerous pedestrian target exists; when no dangerous pedestrian target exists, a first preset speed is used as the longitudinal driving speed of the target vehicle; when a dangerous pedestrian target exists, it is determined whether the pedestrian target is located in a dangerous area; if the pedestrian target is located in a dangerous area and the pedestrian target is stationary, the target vehicle is controlled to maintain its speed. The vehicle maintains its current longitudinal speed. If the pedestrian is located in a dangerous area and is in motion, based on the pedestrian's motion and the vehicle's current longitudinal speed, it determines whether a first ratio is greater than a second ratio. If the first ratio is greater than the second ratio, the vehicle maintains its current longitudinal speed. If the first ratio is less than or equal to the second ratio, the vehicle's longitudinal speed is planned according to low-speed emergency braking. The first ratio is the ratio of the pedestrian's lateral distance to their speed, and the second ratio is the ratio of the pedestrian's longitudinal distance to the vehicle's current longitudinal speed. For example, the first preset speed can be adjusted according to actual conditions, such as 15 km / h.

[0120] Furthermore, the process of longitudinal speed planning for the target vehicle may also include: if the pedestrian target is located in a risk area and is stationary, determining whether there is trajectory overlap between the target vehicle and the pedestrian target; if there is no trajectory overlap, controlling the target vehicle to travel at a second preset speed; if there is trajectory overlap, controlling the longitudinal speed of the target vehicle based on the distance between the pedestrian target and the target vehicle; if the pedestrian target is located in a risk area and is in motion, determining whether the pedestrian target is moving longitudinally based on its motion state; if the pedestrian target is moving longitudinally, determining whether there is trajectory overlap between the target vehicle and the pedestrian target, and controlling the longitudinal speed of the target vehicle based on the trajectory overlap determination result; if the pedestrian target is moving laterally, controlling the longitudinal speed of the target vehicle based on the distance between the pedestrian target and the target vehicle. As an example, the second preset speed can be adjusted according to the actual situation, for example, 7 km / h.

[0121] Meanwhile, the process of planning the longitudinal driving speed of the target vehicle may also include: obtaining the longitudinal driving speed of the target vehicle relative to each pedestrian target in the unsafe area, denoted as the expected longitudinal driving speed of each pedestrian target; summing the expected longitudinal driving speeds of each pedestrian target and taking the minimum value to obtain the final expected longitudinal driving speed of all dangerous pedestrian targets in the unsafe area, and using it as the longitudinal driving speed of the target vehicle based on the current pedestrian targets, denoted as the first planned longitudinal driving speed; combining the first planned longitudinal driving speed, the third planned longitudinal driving speed, and the occluded pedestrian longitudinal speed to obtain the longitudinal driving speed of the target vehicle when there are pedestrian targets in the unsafe area, and using the longitudinal speed as the final result of adjusting the driving speed of the target vehicle; wherein, the occluded pedestrian fusion result includes the occluded pedestrian longitudinal speed, and the third planned longitudinal speed is obtained according to the driving environment of the target vehicle. As an example, the process of obtaining the third planned longitudinal driving speed in this embodiment includes: based on the lengths of the drivable area and the danger zone corresponding to the drivable area signal, reading the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the normal driving area, and recording it as the first minimum width; and reading the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the normal driving area, and recording it as the second minimum width; comparing the first minimum width, the second minimum width, and the preset optimal lateral distance, and taking the smaller value as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recording it as the minimum lateral distance of the target vehicle. The system calculates the maximum longitudinal speed of the target vehicle under the current driving environment based on the minimum lateral distance to the target vehicle and the pedestrian target collision avoidance data table. This speed is used as the second planned longitudinal speed. Based on the second planned longitudinal speed, the parking scenario hazard coefficient, and the parking scenario hazard correction speed, the maximum speed supported by the current scenario is calculated. The pre-generated parking scenario hazard level identification results include the parking scenario hazard coefficient and the parking scenario hazard correction speed. The maximum speed supported by the current scenario is compared with a third preset speed, and the larger of these is used as the third planned longitudinal speed. For example, the third preset speed can be adjusted according to actual conditions, such as 3 km / h.

[0122] According to the above records, specifically, such as Figure 5 As shown, Figure 5 A flowchart illustrating the process of planning the longitudinal speed of a vehicle is shown. Figure 5 In this process, longitudinal speed planning includes two parts: target-based speed planning and environment-based speed planning. The input signals for longitudinal speed planning are the pedestrian target collision avoidance data table, dangerous pedestrian signals, dangerous area signals, and drivable area signals. After speed planning, the longitudinal speed V of the vehicle in this cycle is obtained.

[0123] Among them, the environment-based speed planning obtains the longitudinal driving speed V2 of the vehicle based on the current degree of danger of the environment. The specific process is as follows:

[0124] Step (1-1): Based on the current cycle's danger zone length LS, read the minimum width Z1 of the drivable area relative to the left obstacle and the minimum width Z2 of the drivable area relative to the right obstacle within the longitudinal range of LS.

[0125] Step (1-2): The minimum lateral distance between the vehicle and the obstacles on both sides within the danger zone is Zmin = min(Z1, Z2, 2.5m);

[0126] Steps (1-3) use the minimum lateral distance Zmin between the two obstacles as the output width ZS of the danger zone. By querying the pedestrian target complete collision avoidance data table, the maximum longitudinal driving speed V2 that can be supported in the current environment is obtained.

[0127] Steps (1-4): Based on the hazard coefficient W of the parking scenario, obtain the maximum vehicle speed V3 that can be supported by the scenario, V3 = V2 - Vx * W;

[0128] Steps (1-5) consider the passability of extremely narrow scenarios and correct the maximum vehicle speed that can be supported in the current environment, V3 = max(V3, 3km / h), to obtain the third longitudinal driving speed.

[0129] The target-based speed planning process involves determining the vehicle's longitudinal speed V1n based on the current pedestrian target's danger level. The specific steps are as follows:

[0130] Step (2-1): Receive a dangerous pedestrian signal and determine if a dangerous pedestrian exists. If not, the vehicle's longitudinal speed V1n = 15 km / h based on the target plan. If a dangerous pedestrian exists, proceed to step (2-2).

[0131] Step (2-2): Determine if the pedestrian is in a danger zone. If yes, proceed to step (2-3). If no, proceed to step (2-5).

[0132] Step (2-3): Determine if the pedestrian is stationary. If yes, based on goal planning, maintain the current speed, V1n = V. If no, proceed to step (2-4).

[0133] Step (2-4): Determine whether the pedestrian or the vehicle reaches the collision point first, and whether P1 / Vp > P2 / V holds true. If true, the vehicle reaches the collision point first, meaning there is no risk of collision with the pedestrian, and the vehicle maintains its current speed, V1n = V. If false, the pedestrian reaches the collision point first, meaning there is a risk of collision with the pedestrian, and the vehicle follows the planned speed V1n for low-speed emergency braking (LAEB).

[0134] Step (2-5): Determine if the pedestrian is stationary. If yes, the pedestrian is stationary, proceed to step (2-6). If no, the pedestrian is not stationary, proceed to step (2-7).

[0135] Steps (2-6) determine whether there is no overlap between the vehicle's and the pedestrian's tracks, i.e., whether the lateral distance between their tracks is greater than 2.1m. If yes, there is no overlap between the pedestrian's and the vehicle's tracks, the pedestrian is safe, and the vehicle should proceed at a limited speed to pass the pedestrian, with a recommended speed of V1n = 7 km / h. If no, there is overlap between the pedestrian's and the vehicle's tracks, the pedestrian is unsafe, and the vehicle should adjust its speed V1n according to the distance to the pedestrian to bring it to a comfortable stop.

[0136] Step (2-7): Determine if the pedestrian is moving longitudinally. If yes, the pedestrian is moving longitudinally with no lateral movement tendency, then proceed to step (2-6). If no, the pedestrian has a lateral movement tendency, and the pedestrian is unsafe. In this case, the vehicle should adjust its speed V1n according to the distance to the pedestrian and brake to a stop as comfortably as possible.

[0137] Step (2-8) In the current cycle, there are N target pedestrians in the danger zone and risk zone. Repeat the speed planning steps based on the current target for each pedestrian target to obtain the expected longitudinal driving speed V1n for each pedestrian target. Add the expected longitudinal driving speeds of each pedestrian target and take the minimum value, V1=min(V1n)n∈[0,N] to obtain the final expected longitudinal driving speed V1 based on all dangerous pedestrian targets.

[0138] Velocity planning based on occluded pedestrians: The longitudinal velocity V4 of the occluded pedestrian is obtained based on the current existence state of the occluded pedestrian. The specific process is as follows:

[0139] 1. When the pedestrian obstruction sign is present, the longitudinal position of the obstructed pedestrian is ≤10m, the confidence level of the obstructed pedestrian is ≥80%, and the pedestrian obstruction detection sensor is R or R+V, then the vehicle will use a comfortable braking stop based on the current longitudinal collision avoidance strategy for the obstructed pedestrian.

[0140] 2. If the pedestrian obstruction sign is present, the longitudinal position of the obstructed pedestrian is greater than 10m, the confidence level of the obstructed pedestrian is greater than 80%, and the pedestrian obstruction detection sensor is R or R+V, then the vehicle's speed limit is 5km / h based on the current longitudinal collision avoidance strategy for the obstructed pedestrian.

[0141] 3. When the pedestrian obstruction sign is present, the pedestrian obstruction confidence level is ≥80%, and the pedestrian obstruction detection sensor is V, then the vehicle's longitudinal collision avoidance strategy based on the current pedestrian obstruction is a speed limit of 4km / h.

[0142] 4. In other cases, there is no current longitudinal collision avoidance strategy for pedestrians who are obstructed.

[0143] Based on the environment, the expected vehicle speed V3 is obtained; based on the target, the expected vehicle speed V1 is obtained; based on the pedestrian obstruction, the expected vehicle speed V4 is obtained; and the planned longitudinal speed Vs = min(V1, V3, V4) at the current moment is obtained.

[0144] In an exemplary embodiment, the process of planning the lateral driving distance of a target vehicle based on a dangerous pedestrian signal, a dangerous area signal, and a drivable area signal includes: reading the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the normal driving area according to the length of the drivable area and the dangerous area corresponding to the drivable area signal, and recording it as the first minimum width; and reading the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the normal driving area, and recording it as the second minimum width; comparing the first minimum width, the second minimum width, and a preset optimal lateral distance, and taking the smaller value as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recording it as the minimum lateral distance of the target vehicle; calculating the difference between the first minimum width and the second minimum width, and recording it as the first difference; and determining whether the absolute value of the first difference is greater than or equal to a first preset value; if the absolute value is less than the first preset value, it is determined that the target vehicle has no offset space at the current moment, and no lateral driving distance adjustment is made to the target vehicle.

[0145] If the absolute value is greater than or equal to the first preset value, it is determined that the target vehicle has offset space at the current moment, and it is determined whether the minimum lateral distance of the target vehicle is less than or equal to the second preset value; if the minimum lateral distance of the target vehicle is greater than the second preset value, it is determined that there is no offset requirement at the current moment, and no lateral driving distance adjustment is made to the target vehicle; if the minimum lateral distance of the target vehicle is less than or equal to the second preset value, it is determined that there is an offset requirement at the current moment, and a dangerous pedestrian signal is received, and it is determined whether there is a dangerous pedestrian target based on the dangerous pedestrian signal; if there is a pedestrian target in the dangerous area or risk area, then there is a dangerous pedestrian target, and no lateral driving distance adjustment is made to the target vehicle; if there is no pedestrian target in the dangerous area or risk area, then there is no dangerous pedestrian target, and the lateral driving distance adjustment is made to the target vehicle.

[0146] Furthermore, if there are no pedestrian targets in the danger zone and risk zone, the process of adjusting the lateral driving distance of the target vehicle includes: calculating the difference between the preset optimal lateral distance and the minimum lateral distance of the target vehicle, and recording it as the second difference; determining whether twice the second difference is less than or equal to the absolute value of the first difference; if twice the second difference is less than or equal to the absolute value of the first difference, then the second difference is used as the lateral offset distance of the target vehicle; if twice the second difference is greater than the absolute value of the first difference, then half of the absolute value of the first difference is used as the lateral offset distance of the target vehicle; determining whether the second difference is greater than or equal to zero; if the second difference is greater than or equal to zero, then controlling the target vehicle to shift to the left according to the corresponding lateral offset distance; if the second difference is less than zero, then controlling the target vehicle to shift to the right according to the corresponding lateral offset distance.

[0147] According to the above records, specifically, such as Figure 6 As shown, Figure 6 A flowchart illustrating the process of planning the lateral travel distance of vehicles is shown. Figure 6 The specific calculation process for the lateral driving distance offset of this vehicle in this cycle is as follows:

[0148] Step (3-1): Receive the danger zone signal and the drivable zone signal. Based on the danger zone length LS of the current cycle, read the minimum left width Z1 and the minimum right width Z2 within the longitudinal LS range of the drivable zone.

[0149] Step (3-2): The minimum lateral distance between the vehicle and the obstacles on both sides within the danger zone is Zmin = min(Z1, Z2, 2.5m).

[0150] Step (3-3): Determine if the vehicle has sufficient offset space, i.e., whether |Z1-Z2|≥0.5m holds true. If true, there is sufficient offset space, proceed to step (3-4); if false, the offset space is insufficient, and the vehicle will not offset.

[0151] Step (3-4): Determine if the vehicle has a shift requirement, i.e., determine if the minimum lateral distance Zmin between the two obstacles is ≤2.1m. If it is true, there is a shift requirement, and proceed to step (3-5). If it is not true, there is sufficient space between the vehicle and the two obstacles, the vehicle has no shift requirement, and the vehicle will not shift.

[0152] Step (3-2): Determine if there is a risk of the vehicle's current deviation, i.e., whether there are dangerous pedestrians in the current danger zone and the danger zone. If true, there are dangerous pedestrians around the vehicle, the deviation poses a collision risk, and the vehicle will not deviate; if false, there are no dangerous pedestrians around the vehicle, the deviation poses no collision risk, and proceed to step (3-6).

[0153] Step (3-3): Determine if the current environment satisfies the optimal lateral distance of 2.5m from the obstacles on both sides, i.e., whether 2.5m - Zmin ≤ |Z1 - Z2| / 2 holds true. If true, the ideal offset requirement is met, and the lateral offset distance of this vehicle is ΔZ = 2.5m - Zmin; if false, the ideal offset requirement is not met, and the currently acceptable lateral offset distance is calculated as ΔZ = |Z1 - Z2| / 2.

[0154] Step (3-7): Determine the current offset direction of the vehicle, that is, determine whether the difference in lateral distance between the vehicle and the obstacles on both sides, 0 ≤ Z1 - Z2, holds true. If it holds true, then the space on the right side of the vehicle is larger, and the vehicle offsets to the right by △Z; if it does not hold true, then the space on the left side of the vehicle is larger, and the vehicle offsets to the left by △Z.

[0155] In an exemplary embodiment, the process of planning the lateral driving distance of a target vehicle based on a dangerous pedestrian signal, a dangerous area signal, and a drivable area signal includes: reading the minimum width between the target vehicle and the obstacle on its left side within the longitudinal range of the drivable area and the length of the dangerous area corresponding to the drivable area signal, and recording it as the first minimum width; and reading the minimum width between the target vehicle and the obstacle on its right side within the longitudinal range of the drivable area, and recording it as the second minimum width; comparing the first minimum width, the second minimum width, and a preset optimal lateral distance, and taking the smaller value as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recording it as the minimum lateral distance of the target vehicle; determining whether the minimum lateral distance of the target vehicle is greater than the width of the dangerous area; if the minimum lateral distance of the target vehicle is greater than the width of the dangerous area, there is no real-time pedestrian collision risk; if the minimum lateral distance of the target vehicle is less than or equal to the width of the dangerous area, there is a real-time pedestrian collision risk. In this case, pedestrians in the dangerous area may not be detected and perceived in time due to obstruction.

[0156] Specifically, such as Figure 6 As shown, the specific process for pedestrian collision risk assessment is as follows:

[0157] Step (4-1): Receive the danger zone signal and the drivable zone signal, and read the minimum width Z1 of the drivable zone relative to the left obstacle and the minimum width Z2 of the drivable zone relative to the right obstacle within the longitudinal LS range.

[0158] Step (4-2): The minimum lateral distance between the vehicle and the obstacles on both sides within the danger zone is Zmin = min(Z1, Z2, 2.5m);

[0159] Step (4-3) determines whether the minimum lateral distance Zmin between the obstacles on both sides is greater than the width ZS of the danger zone. If it is true, there are no obstacles in the danger zone obstructing the sensor's "line of sight," pedestrians in the danger zone will not be obstructed, and the lateral and longitudinal distances of the danger zone meet the pedestrian's complete collision avoidance requirements, so there is no risk of collision for the pedestrian. If it is not true, there are obstacles in the danger zone that may obstruct the sensor's "line of sight," and pedestrians in the danger zone may not be detected and perceived in time due to obstruction, resulting in a risk of collision for the pedestrian.

[0160] Based on the descriptions in the aforementioned exemplary embodiments, this embodiment also provides a scheme for protecting pedestrians outside the vehicle during vehicle driving control. In this embodiment, the pedestrian protection system consists of a target fusion module, an obstructed pedestrian fusion module, a drivable area fusion module, a parking scenario hazard level identification module, a target and environment recognition module, a longitudinal driving speed planning module, and a lateral driving distance planning module. The input sources of the pedestrian protection system include parking lot attribute information, time, holidays, a complete pedestrian collision avoidance data table, and external sensors. The output signals of the pedestrian protection system include the vehicle's longitudinal speed V, the vehicle's lateral offset ΔZ, and the pedestrian collision risk. Specifically, the target fusion module obtains pedestrian targets and their attribute values, including target ID, target type, target lateral and longitudinal distances, and target lateral and longitudinal relative speeds, through multi-sensor information fusion based on the input signals from external sensors. The drivable area fusion module obtains relevant signals of the vehicle's drivable area through multi-sensor information fusion based on the input signals from external sensors. The drivable area signals include the lateral and longitudinal distances of the drivable area boundary points. The target recognition and environment recognition modules are input to the pedestrian target collision avoidance data table and the pedestrian targets and their attribute values ​​output by the target fusion module. After screening for hazardous targets and recognizing environmental hazards, they output hazardous pedestrian signals and hazardous area signals for the current environment. The longitudinal driving speed planning module is input to the pedestrian target collision avoidance data table, hazardous pedestrian signals, hazardous area signals, and drivable area signals. After speed planning, it obtains the longitudinal speed V of the vehicle for this cycle. The lateral driving distance planning module is input to the hazardous pedestrian signals, hazardous area signals, and drivable area signals. After lateral motion planning, it obtains the lateral offset of the vehicle and the pedestrian collision risk for this cycle.

[0161] In summary, this application provides a vehicle driving control method that obtains pedestrian target information located in the external space region of the target vehicle by performing target fusion on sensor signals on the target vehicle; performs occlusion pedestrian fusion on sensor signals on the target vehicle to obtain occlusion pedestrian fusion results; and performs drivable area fusion on sensor signals on the target vehicle to obtain drivable area signals. Simultaneously, based on a pre-determined pedestrian target collision avoidance data table and pedestrian target information, the target vehicle performs target recognition and environmental recognition to obtain dangerous pedestrian signals and dangerous area signals. Finally, based on pre-generated parking scene hazard level identification results, occlusion pedestrian fusion results, dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs longitudinal driving speed planning; and / or, based on dangerous pedestrian signals, dangerous area signals, and drivable area signals, the target vehicle performs lateral driving distance planning to ensure that the planned target vehicle will not come into contact with the pedestrian target. The target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information. Therefore, this method, based on the vehicle's existing perception sensors (such as front radar, forward-facing camera, surround-view, and ultrasonic sensors), employs multi-sensor fusion to perceive the external driving environment and pedestrian information. This allows it to determine the pedestrian's position in the external spatial area based on the pedestrian's motion characteristics. Simultaneously, for pedestrian targets in different spatial areas, this method employs control strategies for longitudinal speed planning and / or lateral distance planning, effectively addressing accidental braking and missed braking by pedestrians outside the vehicle. This reduces the possibility of vehicle-pedestrian contact, enabling the vehicle to identify and protect external pedestrian targets during operation. Essentially, this method can assess the risk of a collision between the vehicle and pedestrians from the perspectives of the driving environment and pedestrian targets, and then adjust the vehicle's driving state to plan the collision avoidance speed for pedestrians.

[0162] Furthermore, this method provides a systematic solution for pedestrian protection outside vehicles, encompassing target fusion, drivable area fusion, target and environmental cognition, longitudinal speed planning, and lateral distance planning modules. It covers pedestrians with varying longitudinal speeds, positions, and motion states, effectively addressing the complete collision avoidance problem for pedestrians in extreme scenarios (such as pedestrians suddenly appearing out of the way). Moreover, through the design and calibration of a complete pedestrian collision avoidance data table, this method provides a systematic solution for pedestrian protection outside vehicles, covering parking scenario hazard level identification, target fusion, occluded pedestrian fusion, drivable area fusion, target and environmental cognition, longitudinal speed planning, and lateral distance planning modules. This covers pedestrians with different speeds, positions, and motion states, fundamentally solving the collision avoidance problem for pedestrians in dangerous and risky areas. Furthermore, this method primarily assesses pedestrian risk based on their position and motion state (stationary / moving), independent of the accuracy of pedestrian speed detection.

[0163] This method essentially divides the area around the vehicle into danger zones, risk zones, and safe zones based on the risk characteristics of pedestrians. Different systematic strategies are applied to pedestrians in different zones, effectively addressing issues of accidental braking and missed braking by pedestrians outside the vehicle. Simultaneously, this method can identify the hazard level of the current parking scenario based on parking lot attribute information, the current time, and holiday information, and then plan the vehicle's longitudinal speed accordingly. Furthermore, the longitudinal speed planning module can evaluate the pedestrian collision risk from three aspects: "environment," "target," and "obstructed pedestrian," thereby completing the pedestrian collision avoidance speed planning. It can also perform lateral offset planning based on the vehicle's driving environment and the perceived results of the target pedestrian.

[0164] In another exemplary embodiment of this application, the embodiment also provides a vehicle driving control device, including:

[0165] The target fusion module is used to fuse sensor signals from the target vehicle to obtain pedestrian target information located in the external space area of ​​the target vehicle; the target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information;

[0166] The target recognition and environment recognition module is used to perform target recognition and environment recognition on the target vehicle based on the pre-determined pedestrian target collision avoidance data table and pedestrian targets, and obtain dangerous pedestrian signals and dangerous area signals;

[0167] An occlusion pedestrian fusion module is used to perform occlusion pedestrian fusion on the sensor signals on the target vehicle to obtain the occlusion pedestrian fusion result;

[0168] The drivable area fusion module is used to fuse sensor signals on the target vehicle to obtain drivable area signals.

[0169] The vehicle driving planning and control module is used to plan the longitudinal driving speed and / or lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal and the drivable area signal, so as to ensure that the planned target vehicle will not come into contact with the pedestrian target.

[0170] It should be noted that the vehicle driving control device provided in the above embodiments and the vehicle driving control method provided in the above embodiments belong to the same concept. The specific operation methods of each module have been described in detail in the above method embodiments and will not be repeated here. In practical applications, the vehicle driving control device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. For example, the vehicle driving planning control module can be divided into a longitudinal driving speed planning module and a lateral driving distance planning module; the input signals of the longitudinal driving speed planning module are the pedestrian target complete collision avoidance data table, dangerous pedestrian signal, dangerous area signal, and drivable area signal, and the longitudinal speed V of the vehicle in this cycle is obtained through speed planning. The input signals of the lateral driving distance planning module are the dangerous pedestrian signal, dangerous area signal, and drivable area signal, and the lateral offset of the vehicle and pedestrian collision risk in this cycle are obtained through lateral motion planning.

[0171] Therefore, this application provides a vehicle driving control device that obtains pedestrian target information located in the external space area of ​​the target vehicle by performing target fusion on sensor signals on the target vehicle; performs occlusion pedestrian fusion on sensor signals on the target vehicle to obtain occlusion pedestrian fusion results; and performs drivable area fusion on sensor signals on the target vehicle to obtain drivable area signals. Simultaneously, based on a pre-determined pedestrian target collision avoidance data table and pedestrian target information, the device performs target recognition and environmental recognition on the target vehicle to obtain dangerous pedestrian signals and dangerous area signals. Finally, based on pre-generated parking scene hazard level identification results, occlusion pedestrian fusion results, dangerous pedestrian signals, dangerous area signals, and drivable area signals, the device performs longitudinal driving speed planning for the target vehicle; and / or, based on dangerous pedestrian signals, dangerous area signals, and drivable area signals, the device performs lateral driving distance planning for the target vehicle to ensure that the planned target vehicle will not come into contact with the pedestrian target. The target vehicle includes the current vehicle, and the pedestrian target information includes the pedestrian target and pedestrian target attribute information. Therefore, this device, based on the vehicle's existing perception sensors (such as front radar, forward-facing camera, surround-view, and ultrasonic sensors), employs a multi-sensor fusion method to perceive the external driving environment and pedestrian information. This allows it to determine the pedestrian's position in the external spatial area based on the pedestrian's motion characteristics. Simultaneously, for pedestrian targets in different spatial areas, this device employs control strategies for longitudinal speed planning and / or lateral distance planning, effectively addressing accidental braking and missed braking by pedestrians outside the vehicle. This reduces the possibility of vehicle-pedestrian contact, enabling the device to identify and protect external pedestrian targets during vehicle operation. Essentially, this device can assess the risk of a collision between the vehicle and pedestrians based on the driving environment and pedestrian targets, and then adjust the vehicle's driving state to plan the collision avoidance speed for pedestrians. Furthermore, this device provides a systematic solution for pedestrian protection outside vehicles, encompassing target fusion, drivable area fusion, target and environmental recognition, longitudinal speed planning, and lateral distance planning modules. It covers pedestrians with varying longitudinal speeds, positions, and movement states, effectively addressing the complete collision avoidance problem for pedestrians in extreme scenarios (such as pedestrians suddenly appearing out of the way). Moreover, through the design and calibration of a complete pedestrian collision avoidance data table, this device provides a systematic solution for pedestrian protection outside vehicles, covering parking scenario hazard level identification, target fusion, occluded pedestrian fusion, drivable area fusion, target and environmental recognition, longitudinal speed planning, and lateral distance planning modules. This solution covers pedestrians with varying speeds, positions, and movement states, fundamentally addressing pedestrian collision avoidance in dangerous and high-risk areas.Furthermore, this device primarily assesses pedestrian risk based on their position and motion state (stationary / moving), without relying on the detection accuracy of pedestrian speed.

[0172] Essentially, this device can divide the area around the vehicle into danger zones, risk zones, and safe zones based on the risk characteristics of pedestrians. Different systematic strategies are applied to pedestrians in different zones, effectively addressing the issues of accidental braking and missed braking by pedestrians outside the vehicle. Simultaneously, this device can identify the hazard level of the current parking scenario based on parking lot attribute information, the current time, and holiday information, and then plan the vehicle's longitudinal speed accordingly. Furthermore, the longitudinal speed planning module can evaluate the pedestrian collision risk from three aspects: "environment," "target," and "obstructed pedestrian," thereby completing the pedestrian collision avoidance speed planning. It can also perform lateral offset planning based on the vehicle's driving environment and the perceived results of the target pedestrian.

[0173] Embodiments of this application also provide a vehicle driving control device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the vehicle driving control device implements the vehicle driving control methods provided in the above embodiments.

[0174] Figure 7 A schematic diagram of a computer device suitable for implementing a vehicle driving control device according to embodiments of this application is shown. It should be noted that... Figure 7 The computer system 1000 of the vehicle driving control device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0175] like Figure 7 As shown, the computer system 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from Storage Unit 1008 into Random Access Memory (RAM) 1003, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1003. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. An Input / Output (I / O) interface 1005 is also connected to bus 1004.

[0176] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.

[0177] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs the various functions defined in the apparatus of this application.

[0178] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0179] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0180] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0181] Another aspect of this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a computer's processor, causes the computer to perform the vehicle driving control method as described above. This computer-readable storage medium may be included in the vehicle driving control device described in the above embodiments, or it may exist independently and not incorporated into the vehicle driving control device.

[0182] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle driving control method provided in the various embodiments described above.

[0183] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A vehicle driving control method, characterized in that, The method includes the following steps: Target fusion is performed on sensor signals on the target vehicle to obtain pedestrian target information located in the external space region of the target vehicle; wherein, the target vehicle includes the current vehicle, and the pedestrian target information includes pedestrian targets and pedestrian target attribute information; Based on a pre-determined complete collision avoidance data table for pedestrian targets and the pedestrian target information, the target vehicle is subjected to target recognition and environmental recognition to obtain dangerous pedestrian signals and dangerous area signals. The sensor signals on the target vehicle are subjected to occlusion pedestrian fusion to obtain occlusion pedestrian fusion results; and the sensor signals on the target vehicle are subjected to drivable area fusion to obtain drivable area signals. Based on the pre-generated parking scene hazard level identification results, the occluded pedestrian fusion results, the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, the longitudinal driving speed of the target vehicle is planned; and / or, based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, the lateral driving distance of the target vehicle is planned so that the planned target vehicle will not come into contact with the pedestrian target; Based on a pre-determined pedestrian target collision avoidance data table and the pedestrian target information, the process of performing target recognition and environmental recognition on the target vehicle to obtain dangerous pedestrian signals and dangerous area signals includes: Based on a pre-determined pedestrian target collision avoidance data table, the maximum longitudinal distance at which the front and rear bumpers of the target vehicle can completely avoid collision with the pedestrian target without reducing the current longitudinal driving speed is determined, and the maximum longitudinal distance is taken as the length of the danger zone. Based on the current longitudinal driving speed of the target vehicle and the width of the target vehicle, determine the minimum value of the width of the danger zone when the length of the danger zone is not empty, and use the minimum value of the width of the danger zone as the width of the danger zone in the current cycle. The length of the danger zone and the width of the danger zone in the current cycle are combined to generate a rectangular region, and this rectangular region is used as the danger zone of the target vehicle to generate the danger zone signal; and... Based on the danger zone of the target vehicle and the driving environment of the target vehicle, the risk zone of the target vehicle is determined; wherein, the driving environment of the target vehicle includes: the maximum longitudinal driving speed of the target vehicle; The dangerous pedestrian signal is generated based on the movement state of the pedestrian target and whether the pedestrian target is located in the dangerous area or the risk area.

2. The vehicle driving control method according to claim 1, characterized in that, The process of longitudinal driving speed planning for the target vehicle includes: The system receives the dangerous pedestrian signal and determines whether a dangerous pedestrian target exists based on the signal. If a pedestrian target exists in the dangerous area or the risk area, then a dangerous pedestrian target exists. If no pedestrian target exists in the dangerous area or the risk area, then no dangerous pedestrian target exists. When there are no dangerous pedestrian targets, the first preset speed is used as the longitudinal speed of the target vehicle; When a dangerous pedestrian is present, determine whether the pedestrian is located in a dangerous area; If the pedestrian target is located in the danger zone and the pedestrian target is stationary, control the target vehicle to maintain its current longitudinal driving speed; If the pedestrian target is located in the danger zone and the pedestrian target is in motion, based on the pedestrian target's motion state and the target vehicle's current longitudinal speed, it is determined whether a first ratio is greater than a second ratio; if the first ratio is greater than the second ratio, the target vehicle is controlled to maintain its current longitudinal speed; if the first ratio is less than or equal to the second ratio, the target vehicle's longitudinal speed is planned according to low-speed emergency braking. Wherein, the first ratio is the ratio of the lateral distance of the pedestrian target to the moving speed of the pedestrian target, and the second ratio is the ratio of the longitudinal distance of the pedestrian target to the current longitudinal driving speed of the target vehicle.

3. The vehicle driving control method according to claim 2, characterized in that, The process of planning the longitudinal driving speed of the target vehicle also includes: If the pedestrian target is located in the risk area and the pedestrian target is stationary, determine whether the target vehicle and the pedestrian target have overlapping trajectories; if the target vehicle and the pedestrian target do not have overlapping trajectories, control the target vehicle to travel at a second preset speed; if the target vehicle and the pedestrian target have overlapping trajectories, control the longitudinal speed of the target vehicle according to the distance between the pedestrian target and the target vehicle. If the pedestrian target is located in the risk area and the pedestrian target is in motion, then based on the pedestrian target's motion state, it is determined whether the pedestrian target is moving longitudinally; if the pedestrian target is moving longitudinally, it is determined whether the target vehicle and the pedestrian target have overlapping trajectories, and the longitudinal driving speed of the target vehicle is controlled according to the trajectory overlap determination result; if the pedestrian target is moving laterally, the longitudinal driving speed of the target vehicle is controlled according to the distance between the pedestrian target and the target vehicle.

4. The vehicle driving control method according to claim 3, characterized in that, The process of planning the longitudinal driving speed of the target vehicle also includes: The dangerous area and risk area of ​​the target vehicle are combined to form the unsafe area of ​​the target vehicle; and the space area outside the target vehicle's external space area, excluding the unsafe area, is defined as the safe area of ​​the target vehicle. The longitudinal driving speed of the target vehicle relative to each pedestrian target in the unsafe area is obtained and denoted as the expected longitudinal driving speed of each pedestrian target; The expected longitudinal driving speed of each pedestrian target is summed and the minimum value is taken to obtain the final expected longitudinal driving speed of all dangerous pedestrian targets in the unsafe area. This speed is used as the longitudinal driving speed of the target vehicle based on the current pedestrian target and is denoted as the first planned longitudinal driving speed. The first planned longitudinal driving speed, the third planned longitudinal driving speed, and the longitudinal speed of the obscured pedestrian are combined to obtain the longitudinal driving speed of the target vehicle when there is a pedestrian target in the unsafe area. The longitudinal driving speed is used as the final result of adjusting the driving speed of the target vehicle. The obscured pedestrian fusion result includes the longitudinal speed of the obscured pedestrian, and the third planned longitudinal driving speed is obtained according to the driving environment of the target vehicle.

5. The vehicle driving control method according to claim 4, characterized in that, The process of obtaining the third planned longitudinal driving speed includes: Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width. The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle. Based on the minimum lateral distance of the target vehicle and the complete collision avoidance data table of the pedestrian target, the maximum longitudinal driving speed of the target vehicle under the current driving environment is obtained as the second planned longitudinal driving speed. Based on the second planned longitudinal driving speed, parking scenario hazard coefficient, and parking scenario hazard correction speed, the maximum speed supported by the current scenario is calculated; wherein, the pre-generated parking scenario hazard level identification results include: parking scenario hazard coefficient and parking scenario hazard correction speed. The maximum speed supported by the current scenario is compared with the third preset speed, and the larger one is taken as the third planned longitudinal driving speed.

6. The vehicle driving control method according to claim 5, characterized in that, The calculation process for the hazard coefficient of the parking scenario includes: ； In the formula, This represents the hazard level coefficient for parking scenarios, ranging from 0% to 100%. The level of danger at different times of the day; The parking lot is considered dangerous due to its busy location; Risk level during holidays.

7. The vehicle driving control method according to claim 1, characterized in that, The process of planning the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal includes: Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width. The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle. Calculate the difference between the first minimum width and the second minimum width, and record it as the first difference; then determine whether the absolute value of the first difference is greater than or equal to a first preset value. If the absolute value is less than the first preset value, it is determined that the target vehicle has no offset space at the current moment, and no lateral driving distance adjustment is made to the target vehicle; If the absolute value is greater than or equal to the first preset value, it is determined that the target vehicle has an offset space at the current moment, and it is determined whether the minimum lateral distance of the target vehicle is less than or equal to the second preset value; if the minimum lateral distance of the target vehicle is greater than the second preset value, it is determined that there is no offset requirement at the current moment, and no lateral driving distance adjustment is made to the target vehicle; if the minimum lateral distance of the target vehicle is less than or equal to the second preset value, it is determined that there is an offset requirement at the current moment, and the dangerous pedestrian signal is received, and it is determined whether there is a dangerous pedestrian target based on the dangerous pedestrian signal; if there is a pedestrian target in the dangerous area or the risk area, then there is a dangerous pedestrian target, and no lateral driving distance adjustment is made to the target vehicle; if there is no pedestrian target in the dangerous area or the risk area, then there is no dangerous pedestrian target, and the lateral driving distance adjustment is made to the target vehicle.

8. The vehicle driving control method according to claim 7, characterized in that, If there are no pedestrian targets in the danger zone and the risk zone, the process of adjusting the lateral driving distance of the target vehicle includes: Calculate the difference between the preset optimal lateral distance and the minimum lateral distance of the target vehicle, and record it as the second difference; Determine whether twice the second difference is less than or equal to the absolute value of the first difference; if twice the second difference is less than or equal to the absolute value of the first difference, then the second difference is taken as the lateral offset distance of the target vehicle; if twice the second difference is greater than the absolute value of the first difference, then half of the absolute value of the first difference is taken as the lateral offset distance of the target vehicle. Determine whether the second difference is greater than or equal to zero; if the second difference is greater than or equal to zero, control the target vehicle to shift to the left by the corresponding lateral offset distance; if the second difference is less than zero, control the target vehicle to shift to the right by the corresponding lateral offset distance.

9. The vehicle driving control method according to claim 1, characterized in that, The process of planning the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal includes: Based on the drivable area signal corresponding to the drivable area and the length of the danger zone, the minimum width of the obstacle to the left of the target vehicle within the longitudinal range of the drivable area is read and recorded as the first minimum width; and the minimum width of the obstacle to the right of the target vehicle within the longitudinal range of the drivable area is read and recorded as the second minimum width. The first minimum width, the second minimum width, and the preset optimal lateral distance are compared, and the smaller value is taken as the minimum lateral distance between the target vehicle and the obstacles on both sides, and recorded as the minimum lateral distance of the target vehicle. Determine whether the minimum lateral distance to the target vehicle is greater than the width of the danger zone; If the minimum lateral distance to the target vehicle is greater than the width of the danger zone, then there is no real-time risk of pedestrian collision. If the minimum lateral distance to the target vehicle is less than or equal to the width of the danger zone, there is a real-time risk of pedestrian collision.

10. A vehicle driving control device, characterized in that, The device includes: The target fusion module is used to fuse sensor signals from the target vehicle to obtain pedestrian target information located in the external space area of ​​the target vehicle; wherein, the target vehicle includes the current vehicle, and the pedestrian target information includes pedestrian targets and pedestrian target attribute information; The target recognition and environment recognition module is used to perform target recognition and environment recognition on the target vehicle based on a pre-determined pedestrian target collision avoidance data table and the pedestrian target, to obtain dangerous pedestrian signals and dangerous area signals. This includes: determining, based on the pre-determined pedestrian target collision avoidance data table, the maximum longitudinal distance at which the front and rear bumpers of the target vehicle can completely avoid collision with the pedestrian target without reducing its current longitudinal speed, and using this maximum longitudinal distance as the dangerous area length; and determining, based on the target vehicle's current longitudinal speed and vehicle width, the minimum value of the dangerous area width corresponding to a non-empty dangerous area length. The minimum width of the danger zone is used as the danger zone width for the current period; the danger zone length and the current period's danger zone width are combined to generate a rectangular area, and this rectangular area is used as the danger zone of the target vehicle to generate the danger zone signal; and, based on the danger zone of the target vehicle and its driving environment, the risk zone of the target vehicle is determined; wherein, the driving environment of the target vehicle includes: the target vehicle's maximum longitudinal speed; and based on the movement state of the pedestrian target and whether the pedestrian target's position is within the danger zone or the risk zone, the dangerous pedestrian signal is generated; An occlusion pedestrian fusion module is used to perform occlusion pedestrian fusion on the sensor signals on the target vehicle to obtain the occlusion pedestrian fusion result; The drivable area fusion module is used to fuse the sensor signals on the target vehicle to obtain a drivable area signal. The vehicle driving planning and control module is used to plan the longitudinal driving speed of the target vehicle based on the pre-generated parking scene hazard level identification result, the occluded pedestrian fusion result, the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal; and / or to plan the lateral driving distance of the target vehicle based on the dangerous pedestrian signal, the dangerous area signal, and the drivable area signal, so that the planned target vehicle will not come into contact with the pedestrian target.

11. A vehicle driving control device, characterized in that, The device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the device to implement the vehicle driving control method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the vehicle driving control method as described in any one of claims 1 to 9.

Images