Vehicle control method, system, storage medium and electronic device

Abstract

This invention discloses a vehicle control method, system, storage medium, and electronic device. The method includes: in response to receiving a driving scene switching command and the vehicle approaching a target intersection, the vehicle-side control system acquires vehicle-side perception information perceived by the vehicle; the vehicle-side control system sends an information subscription request to a roadside device and receives roadside perception information returned by the roadside device, wherein the roadside device is located at the target intersection, and the roadside perception information includes real-time perception information and predictive perception information, wherein the real-time perception information is perceived in real-time by the roadside device, and the predictive perception information is calculated locally by the roadside device based on the real-time perception information; the vehicle-side control system fuses the vehicle-side perception information and the roadside perception information to obtain fused perception information; and the vehicle-side control system controls the vehicle's driving state based on the fused perception information. This invention solves the technical problem of poor real-time performance in related technologies when controlling vehicles to switch driving scenes.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving, and more specifically, to a vehicle control method, system, storage medium, and electronic device. Background Technology

[0002] Currently, autonomous driving systems for vehicles include multiple modules such as perception, fusion, decision-making, planning, and control. In order for the autonomous driving system to accurately understand the information contained in the vehicle's environment and ensure the safety of the vehicle's driving process, multiple different types of sensors need to be deployed on the vehicle to detect the information contained in the environment. This ensures the reliability of the vehicle's driving process planned based on the information. However, in some specific scenarios, such as when the driving scene changes at a road intersection, there may be large obstacles in the road intersection that cause blind spots in the vehicle's field of vision. The autonomous driving system cannot accurately obtain the environmental information in the blind spot. Therefore, the environmental information can be obtained through the roadside equipment corresponding to the blind spot. However, if the autonomous driving system directly obtains real-time perception information from roadside devices, the large volume and complex data types of this information require the system to spend a significant amount of time filtering and processing it. Conversely, if the system directly obtains predictive perception information from cloud servers, the data transmission delays between the roadside devices and the cloud servers cause the system to wait a considerable amount of time to acquire the environmental information. Both of these factors contribute to poor real-time performance when controlling the vehicle to switch driving scenarios.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a vehicle control method, system, storage medium, and electronic device to at least solve the technical problem of poor real-time performance when controlling a vehicle to switch driving scenarios in related technologies.

[0005] According to one aspect of the present invention, a vehicle control method is provided, comprising: in response to receiving a driving scenario switching command and the vehicle driving to a target intersection, a vehicle-end control system acquires vehicle-end perception information perceived by the vehicle, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; the vehicle-end control system sends an information subscription request to a roadside device and receives roadside perception information returned by the roadside device, wherein the roadside device is located at the target intersection, and the roadside perception information includes: real-time perception information and predictive perception information, wherein the real-time perception information is perceived by the roadside device in real time, and the predictive perception information is calculated locally by the roadside device based on the real-time perception information; the vehicle-end control system fuses the vehicle-end perception information and the roadside perception information to obtain fused perception information; and the vehicle-end control system controls the driving state of the vehicle based on the fused perception information.

[0006] Optionally, the information subscription request carries at least the target driving scenario. The real-time perception information is the perception information corresponding to the target driving scenario selected from the initial perception information perceived by the roadside equipment. The predictive perception information is the information obtained by the roadside equipment based on the real-time perception information to predict the behavior of a preset area of ​​the target intersection. The predictive perception information is used to characterize whether there is any behavior that affects vehicle driving in the preset area.

[0007] Optionally, sending an information subscription request to the roadside device includes: determining the target area of ​​the target intersection based on vehicle-side perception information, wherein the target area is used to characterize the area in the target intersection that is not perceived by the vehicle; sending an information subscription request carrying the target driving scenario and the target area to the roadside device, wherein the predicted perception information is information obtained by the roadside device based on real-time perception information to predict the behavior of the preset area and the target area.

[0008] Optionally, controlling the vehicle's driving state based on fused perception information includes: predicting behavior in a preset area of ​​the target intersection based on fused perception information to obtain a vehicle-side prediction result, wherein the vehicle-side prediction result is used to characterize whether any behavior affecting the vehicle's driving occurs within the preset area; in response to the vehicle-side prediction result indicating that any behavior affecting the vehicle's driving occurs within the preset area, controlling the vehicle's driving state to a stopped state; in response to the vehicle-side prediction result indicating that no behavior affecting the vehicle's driving occurs within the preset area, generating a vehicle-side driving trajectory based on the fused perception information, and controlling the vehicle's driving state based on the vehicle-side driving trajectory.

[0009] Optionally, controlling the vehicle's driving state based on fused perception information includes: receiving a roadside driving trajectory returned by a roadside device, wherein the roadside driving trajectory is a trajectory generated by the roadside device based on roadside perception information; generating a vehicle-side driving trajectory based on fused perception information; and controlling the vehicle's driving state based on the roadside driving trajectory and the vehicle-side driving trajectory.

[0010] Optionally, the driving state of the vehicle is controlled based on the roadside driving trajectory and the vehicle-end driving trajectory, including one of the following: determining a target driving trajectory between the roadside driving trajectory and the vehicle-end driving trajectory based on the confidence level of the roadside driving trajectory and the confidence level of the vehicle-end driving trajectory, and controlling the driving state of the vehicle based on the target driving trajectory; adjusting the vehicle-end driving trajectory based on the roadside driving trajectory to obtain an adjusted driving trajectory, and controlling the driving state of the vehicle based on the adjusted driving trajectory.

[0011] Optionally, the method further includes: the vehicle-side control system receiving target push information corresponding to the target intersection pushed by the roadside equipment, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; and the vehicle-side control system controlling the vehicle to output the target push information.

[0012] Optionally, controlling the vehicle to output target push information includes: prohibiting the vehicle from outputting target push information in response to the vehicle's behavior push function being turned off; and controlling the vehicle to output target push information in response to the vehicle's behavior push function being turned on.

[0013] Optionally, the target push information is the push information with a push level greater than or equal to the vehicle's driving safety level among multiple push information corresponding to the target intersection. The push level is used to characterize the degree of influence of the behavior affecting the vehicle's driving on the vehicle's driving, and the driving safety level is used to characterize the probability of the vehicle driving safely.

[0014] Optionally, the method further includes: the vehicle-side control system sending the vehicle's driving status to the roadside equipment, wherein the driving status is used by the roadside equipment to generate safety warning information, the safety warning information is used to provide safety warnings to objects outside the vehicle, and the safety warning information is output by the roadside equipment.

[0015] According to another aspect of the present invention, a vehicle control method is also provided, comprising: a roadside device receiving an information subscription request sent by a vehicle, wherein the roadside device is located at a target intersection, and the information subscription request is sent by the vehicle when it receives a driving scenario switching instruction and drives to the target intersection, the driving scenario switching instruction being used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; the roadside device sending roadside perception information to the vehicle, wherein the roadside perception information includes: real-time perception information and predictive perception information, the real-time perception information being perceived by the roadside device in real time, and the predictive perception information being calculated locally by the roadside device based on the real-time perception information; wherein the driving state of the vehicle is controlled by fused perception information, the fused perception information being perception information obtained by fusing vehicle-side perception information and roadside perception information, the vehicle-side perception information being used to characterize the perception information perceived by the vehicle.

[0016] Optionally, the information subscription request carries at least the target driving scenario, and the method further includes: the roadside device acquiring the initial perception information perceived in real time by the roadside device; the roadside device filtering out the real-time perception information corresponding to the target driving scenario from the initial perception information; the roadside device performing behavior prediction on a preset area of ​​the target intersection based on the real-time perception information to obtain predicted perception information, wherein the predicted perception information is used to characterize whether any behavior affecting vehicle driving occurs within the preset area.

[0017] Optionally, the information subscription request also carries the target area of ​​the target intersection. The target area is determined by the vehicle-side perception information and is used to characterize the area in the target intersection that is not perceived by the vehicle. Based on the real-time perception information, the behavior of the preset area of ​​the target intersection is predicted to obtain the predicted perception information, including: based on the real-time perception information, the behavior of the preset area and the target area is predicted to obtain the predicted perception information.

[0018] Optionally, the method further includes: the roadside device generating a roadside driving trajectory of the vehicle based on roadside sensing information; the roadside device sending the roadside driving trajectory to the vehicle, wherein the driving state of the vehicle is controlled by the roadside driving trajectory and the vehicle-side driving trajectory, and the vehicle-side driving trajectory is generated based on the vehicle-side sensing information and the roadside sensing information.

[0019] Optionally, the method further includes: the roadside device acquiring target push information corresponding to the target intersection, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; and the roadside device sending the target push information to the vehicle.

[0020] Optionally, obtaining target push information corresponding to the target intersection includes: determining the vehicle's driving safety level based on the information subscription request, wherein the driving safety level is used to characterize the probability of the vehicle driving safely; obtaining the push levels of multiple push information corresponding to the target intersection, wherein the push level is used to characterize the degree of influence of behaviors affecting vehicle driving on vehicle driving; obtaining push information among the multiple push information whose push level is greater than or equal to the driving safety level, thereby obtaining the target push information.

[0021] Optionally, the method further includes: the roadside device receiving the driving status sent by the vehicle; the roadside device generating safety warning information based on the driving status, wherein the safety warning information is used to provide safety warnings to objects outside the vehicle; and the roadside device outputting the safety warning information.

[0022] According to another aspect of the present invention, a vehicle control device is also provided, comprising: an acquisition module, configured to acquire vehicle-side perception information perceived by the vehicle in response to receiving a driving scenario switching command and the vehicle driving to a target intersection, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; a communication module, configured to send an information subscription request to a roadside device and receive roadside perception information returned by the roadside device, wherein the roadside device is located at the target intersection, and the roadside perception information includes: real-time perception information and predictive perception information, wherein the real-time perception information is perceived by the roadside device in real time, and the predictive perception information is calculated locally by the roadside device based on the real-time perception information; a fusion module, configured to fuse the vehicle-side perception information and the roadside perception information to obtain fused perception information; and a control module, configured to control the driving state of the vehicle based on the fused perception information.

[0023] Optionally, the information subscription request carries at least the target driving scenario. The real-time perception information is the perception information corresponding to the target driving scenario selected from the initial perception information perceived by the roadside equipment. The predictive perception information is the information obtained by the roadside equipment based on the real-time perception information to predict the behavior of a preset area of ​​the target intersection. The predictive perception information is used to characterize whether there is any behavior that affects vehicle driving in the preset area.

[0024] Optionally, the communication module includes: a determination unit, used to determine the target area of ​​the target intersection based on vehicle-side perception information, wherein the target area is used to characterize the area in the target intersection that is not perceived by the vehicle; and a communication unit, used to send an information subscription request carrying the target driving scenario and the target area to the roadside device, wherein the predicted perception information is information obtained by the roadside device based on real-time perception information to predict the behavior of the preset area and the target area.

[0025] Optionally, the control module includes: a behavior prediction unit, used to predict the behavior of a preset area of ​​the target intersection based on fused perception information to obtain a vehicle-side prediction result, wherein the vehicle-side prediction result is used to characterize whether any behavior affecting vehicle driving occurs within the preset area; a first control unit, used to control the vehicle's driving state to a stopped state in response to the vehicle-side prediction result indicating that any behavior affecting vehicle driving occurs within the preset area; and a second control unit, used to generate a vehicle-side driving trajectory based on fused perception information in response to the vehicle-side prediction result indicating that no behavior affecting vehicle driving occurs within the preset area, and to control the vehicle's driving state based on the vehicle-side driving trajectory.

[0026] Optionally, the control module includes: a receiving unit for receiving the roadside driving trajectory returned by the roadside equipment, wherein the roadside driving trajectory is a trajectory generated by the roadside equipment based on roadside perception information; a generating unit for generating the vehicle-end driving trajectory based on the fused perception information; and a third control unit for controlling the driving state of the vehicle based on the roadside driving trajectory and the vehicle-end driving trajectory.

[0027] Optionally, the third control unit is further configured to: determine a target driving trajectory between the roadside driving trajectory and the vehicle-end driving trajectory based on the confidence level of the roadside driving trajectory and the confidence level of the vehicle-end driving trajectory, and control the driving state of the vehicle based on the target driving trajectory; and / or adjust the vehicle-end driving trajectory based on the roadside driving trajectory to obtain an adjusted driving trajectory, and control the driving state of the vehicle based on the adjusted driving trajectory.

[0028] Optionally, the communication unit is also used to receive target push information corresponding to the target intersection pushed by the roadside equipment, wherein the target push information is used to characterize the behaviors that have occurred at the target intersection that affect vehicle driving; the control module is also used to control the vehicle to output the target push information.

[0029] Optionally, the control module is also configured to: prevent the vehicle from outputting target push information in response to the vehicle's behavior push function being turned off; and control the vehicle to output target push information in response to the vehicle's behavior push function being turned on.

[0030] Optionally, the target push information is the push information with a push level greater than or equal to the vehicle's driving safety level among multiple push information corresponding to the target intersection. The push level is used to characterize the degree of influence of the behavior affecting the vehicle's driving on the vehicle's driving, and the driving safety level is used to characterize the probability of the vehicle driving safely.

[0031] Optionally, the control module is also used to send the vehicle's driving status to the roadside equipment, wherein the driving status is used by the roadside equipment to generate safety warning information, the safety warning information is used to provide safety warnings to objects outside the vehicle, and the safety warning information is output by the roadside equipment.

[0032] According to another aspect of the present invention, a vehicle control device is also provided, comprising: a receiving module for receiving an information subscription request sent by a vehicle, wherein a roadside device is disposed at a target intersection, and the information subscription request is sent by the vehicle when it receives a driving scenario switching instruction and drives to the target intersection, the driving scenario switching instruction being used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; and a sending module for sending roadside perception information to the vehicle, wherein the roadside perception information includes: real-time perception information and predictive perception information, the real-time perception information being sensed in real time by the roadside device, and the predictive perception information being calculated locally by the roadside device based on the real-time perception information; wherein the driving state of the vehicle is controlled by fused perception information, the fused perception information being perception information obtained by fusing vehicle-side perception information and roadside perception information, the vehicle-side perception information being used to characterize the perception information sensed by the vehicle.

[0033] Optionally, the information subscription request carries at least the target driving scenario, and the device further includes: a first acquisition module, used to acquire initial perception information perceived in real time by the roadside equipment; a filtering module, used to filter out the real-time perception information corresponding to the target driving scenario from the initial perception information; and a prediction module, used to predict the behavior of a preset area of ​​the target intersection based on the real-time perception information to obtain predicted perception information, wherein the predicted perception information is used to characterize whether any behavior affecting vehicle driving occurs within the preset area.

[0034] Optionally, the information subscription request also carries the target area of ​​the target intersection. The target area is determined by the vehicle-side perception information and is used to characterize the area in the target intersection that the vehicle has not perceived. The prediction module includes: a prediction unit, which is used to predict the behavior of the preset area and the target area based on real-time perception information to obtain predicted perception information.

[0035] Optionally, the device further includes: a first generation module for generating a roadside driving trajectory of the vehicle based on roadside perception information; and a transmission module for transmitting the roadside driving trajectory to the vehicle, wherein the driving state of the vehicle is controlled by the roadside driving trajectory and the vehicle-side driving trajectory, and the vehicle-side driving trajectory is generated based on the vehicle-side perception information and the roadside perception information.

[0036] Optionally, the device further includes: a second acquisition module, used to acquire target push information corresponding to the target intersection, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; the sending module is also used to send the target push information to the vehicle.

[0037] Optionally, the second acquisition module includes: a determining unit, configured to determine the driving safety level of a vehicle based on an information subscription request, wherein the driving safety level is used to characterize the probability of safe driving of the vehicle; a first acquisition unit, configured to acquire the push levels of multiple push information corresponding to the target intersection, wherein the push level is used to characterize the degree of influence of behaviors affecting vehicle driving on vehicle driving; and a second acquisition unit, configured to acquire push information among the multiple push information whose push level is greater than or equal to the driving safety level, thereby obtaining the target push information.

[0038] Optionally, the receiving module is also used to receive the driving status sent by the vehicle; the device further includes: a second generating module, used to generate safety prompt information based on the driving status, wherein the safety prompt information is used to provide safety prompts to objects outside the vehicle; and an output module, used to output the safety prompt information.

[0039] According to another aspect of the present invention, a vehicle control system is also provided, comprising: a vehicle-side control system, configured to acquire vehicle-side perception information perceived by the vehicle in response to receiving a driving scenario switching command and the vehicle driving to a target intersection, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; a roadside device, disposed at the target intersection and connected to the vehicle-side control system, configured to acquire real-time perception information, perform local calculations based on the real-time perception information to obtain predicted perception information, and send roadside perception information to the vehicle-side control system after receiving an information subscription request sent by the vehicle-side control system, wherein the roadside perception information includes: real-time perception information and predicted perception information; the vehicle-side control system is further configured to fuse the vehicle-side perception information and the roadside perception information to obtain fused perception information, and control the driving state of the vehicle based on the fused perception information.

[0040] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, the method described above is executed in a processor of the device.

[0041] According to another aspect of the present invention, an electronic device is also provided, comprising: one or more processors; a storage device for storing one or more programs; and a method by which the one or more processors perform any of the above-described methods when the one or more programs are executed by the one or more processors.

[0042] In this embodiment of the invention, in response to receiving a driving scenario switching command and the vehicle reaching the target intersection, the vehicle-end control system acquires vehicle-end perception information perceived by the vehicle; the vehicle-end control system sends an information subscription request to the roadside equipment and receives roadside perception information returned by the roadside equipment; the vehicle-end control system fuses the vehicle-end perception information and the roadside perception information to obtain fused perception information; the vehicle-end control system controls the vehicle's driving state based on the fused perception information. By actively acquiring roadside perception information with high relevance to the command from the roadside equipment when receiving a driving scenario switching command and the vehicle reaching the target intersection, and fusing the roadside perception information with the acquired vehicle-end perception information, the vehicle-end control system obtains fused perception information to assist the vehicle in performing driving scenario switching operations. This enables the vehicle-end control system to fully understand the road conditions at the target intersection based on the fused perception information, improving the vehicle-end control system's control over the current driving scenario and the target driving scenario. Furthermore, the roadside perception information processing includes not only real-time perception information acquired by roadside equipment, but also predictive perception information determined based on this real-time perception information. Through this combined real-time and predictive perception information, the control system can promptly detect potential safety risks in the scenario, thereby improving safety during scenario transitions. Finally, the vehicle-side control system uses this fused perception information to control the vehicle's driving status in real time, enabling the vehicle to safely switch between driving scenarios, significantly improving the safety of the process. It is worth noting that the roadside device that sends roadside perception information to the vehicle in this invention also has local computing capabilities. When it receives an information subscription instruction from the vehicle control system, it can filter the stored information in real time according to the information subscription instruction to obtain the aforementioned roadside perception information. This eliminates the need to interact with the cloud network and filter information through the cloud network, reducing the operating cost of the roadside device and improving the efficiency of obtaining roadside perception information. At the same time, the vehicle control system can directly use the roadside perception information without the need for information filtering, ensuring the timeliness of the roadside perception information during use and reducing the operating cost of the vehicle control system. This solves the technical problem of poor real-time performance when controlling the vehicle to switch driving scenarios in related technologies. Attached Figure Description

[0043] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0044] Figure 1 This is a flowchart illustrating a vehicle control method according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram illustrating a driving scenario at a target intersection according to an embodiment of the present invention;

[0046] Figure 3 This is a schematic diagram of a vehicle and a sensor according to an embodiment of the present invention;

[0047] Figure 4 This is a flowchart illustrating another vehicle control method according to an embodiment of the present invention;

[0048] Figure 5 This is a structural block diagram of a vehicle control device according to an embodiment of the present invention;

[0049] Figure 6 This is a structural block diagram of another vehicle control device according to an embodiment of the present invention;

[0050] Figure 7 This is a system block diagram of a vehicle control system according to an embodiment of the present invention. Detailed Implementation

[0051] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0052] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0053] Example 1

[0054] According to an embodiment of the present invention, a method embodiment for vehicle control is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0055] Figure 1 This is a flowchart illustrating a vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0056] In step S102, in response to receiving a driving scenario switching command and the vehicle driving to the target intersection, the vehicle-side control system acquires the vehicle-side perception information perceived by the vehicle.

[0057] Among them, the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection. This driving scenario switching command can be initiated by the terminal device through the network and sent to the vehicle.

[0058] The aforementioned driving scenario can refer to a scenario comprised of the vehicle's driving area and environmental information within that area. The aforementioned driving scenario switching command can refer to a command used to switch the vehicle's current driving scenario, such as a command to control the vehicle's steering or U-turn at an intersection, a command to control the vehicle to move from a regular road to a highway at a highway intersection, or a command to control the vehicle to find a flat road surface in an area with many obstacles. The aforementioned vehicle-side perception information can refer to information perceived by various sensors on the vehicle, such as the perceived user status inside the vehicle, environmental parameters of the vehicle cabin, driving parameters of pedestrians / other vehicles outside the vehicle, and environmental parameters of the external environment. The aforementioned target intersection can refer to the boundary point between the current driving scenario and the target driving scenario; when the vehicle reaches this target intersection, it indicates that the vehicle's driving scenario is about to switch.

[0059] For ease of understanding, Figure 2 This is a schematic diagram of a driving scenario at a target intersection according to an embodiment of the present invention. Vehicle 01 represents the vehicle itself, vehicles 02 and 03 represent other vehicles, 11, 12, 13, 14, 15, and 16 represent roadside equipment deployed on both sides of the road, the arrows indicate the driving direction of vehicle 1, area A refers to the area where vehicle 2 is currently located, corresponding to the current driving scenario, area B refers to the area that vehicle 1 will enter after switching driving scenarios, corresponding to the target driving scenario, and the intersection O at the junction of area A and area B is the target intersection. Figure 2As shown, if vehicle 01 needs to turn at the target intersection O, the corresponding driving scenario switching command can be the command to control vehicle 01 to turn at the target intersection O. The corresponding current driving scenario can be the scenario consisting of the area A where vehicle 01 is currently located and the environmental information in area A. The corresponding target driving scenario can be the scenario consisting of the area B that vehicle 01 is about to travel to and the environmental information in area B.

[0060] Figure 3 This is a schematic diagram of a vehicle and a sensor according to an embodiment of the present invention, as shown below. Figure 3 As shown, the various sensors deployed on the vehicle may include, but are not limited to: a front-view camera 1, a side camera 2, a 128L (Long band) LiDAR 3, a GPS receiving antenna 4, millimeter-wave radars 5 and 5', a 16L LiDAR 6 and 6', an information processing computer 7, a GPS receiver 8, an inertial measurement unit 9, and a 16L LiDAR 10, etc. Among them, the front-view camera 1, the side camera 2, the 128L (Long band) LiDAR 3, the GPS receiving antenna 4, the millimeter-wave radar 5, and the 16L LiDAR 6 may be sensors deployed outside the vehicle, while the millimeter-wave radar 5', the 16L LiDAR 6', the information processing computer 7, the GPS receiver 8, the inertial measurement unit 9, and the 16L LiDAR 10 may be sensors not belonging to the vehicle interior.

[0061] In one optional embodiment, considering that during vehicle operation, internal or external factors may prevent the vehicle from continuing to drive normally, such as a traffic accident at an intersection, the vehicle control system, while controlling the vehicle to turn at the intersection according to its original trajectory, may be affected by the accident, leading to safety risks during the turning process and making it impossible to safely switch driving scenarios. Therefore, to reduce potential safety risks during driving and ensure normal vehicle operation, the vehicle control system can acquire the aforementioned vehicle-side perception information in real time when it receives a driving scenario switching command and the vehicle's driving scenario is about to switch. For example, if in Figure 2 When a vehicle is about to turn at a road intersection, the vehicle control system may receive a vehicle turning command from the navigation software or the user before the intersection and control the vehicle to turn at the intersection. In order to ensure safety during the turn, the vehicle control system can acquire the aforementioned vehicle perception information when the vehicle is approaching the road intersection. This includes information such as whether the physiological state of the user inside the vehicle is good, whether the user can adapt to a sudden stop, whether there are obstacles in front of the vehicle that will block the vehicle from continuing to move, and whether other vehicles or other users outside the vehicle will affect the vehicle's turning process. This allows the vehicle control system to safely control the vehicle's turn based on the vehicle perception information.

[0062] In step S104, the vehicle-side control system sends an information subscription request to the roadside equipment and receives the roadside perception information returned by the roadside equipment.

[0063] The roadside equipment is installed at the target intersection. The roadside sensing information can include real-time sensing information and predictive sensing information. The real-time sensing information is sensed by the roadside equipment in real time, and the predictive sensing information is calculated locally by the roadside equipment based on the real-time sensing information.

[0064] The aforementioned information subscription request can refer to a request to obtain roadside perception information from roadside equipment. The aforementioned roadside perception information can refer to information perceived by the roadside equipment through multiple sensors that has a high correlation with the aforementioned driving scenario switching command, and can be used to assist the control system in controlling vehicle movement according to the aforementioned driving scenario switching command. The aforementioned real-time perception information can refer to information related to the driving scenario switching command that the roadside equipment perceived in the past period of time at the current moment. The aforementioned predictive perception information can refer to information related to the driving scenario switching command that the roadside equipment predicts locally based on real-time perception information, and that may occur in the future period of time. The aforementioned roadside equipment generally refers to roadside equipment deployed near the vehicle's current location, such as... Figure 2 Roadside equipment deployed in area A, or roadside equipment deployed near the vehicle's location at the next moment, for example... Figure 2 The roadside equipment deployed in area B, generally speaking, considering that the target intersection is the boundary between the current driving scenario and the target driving scenario, can also refer to equipment deployed at the target intersection to improve the efficiency and comprehensiveness of acquiring roadside perception information, for example... Figure 2 The roadside equipment is deployed at the junction of Area A and Area B.

[0065] In one optional embodiment, considering that when a driving scenario changes, the various sensors on the vehicle may not be able to fully perceive the information related to the driving scenario switching command in both the current and target driving scenarios, and if there is information affecting driving safety in the information that the vehicle cannot perceive, it may cause the vehicle to fail to switch from the current driving scenario to the target driving scenario, or a high safety risk may occur during the switching process. For example, if there is a large obstacle at a road intersection, such as a large garden flower bed or a high fence, the area behind the obstacle becomes a blind spot when the vehicle approaches the intersection. At this time, the vehicle control system may not be able to perceive the information in this blind spot through the vehicle's visual sensors, such as whether there are other vehicles driving in the blind spot, or whether there are low stones in the middle of the intersection, and this information may pose a significant safety risk to the vehicle's turning at the road intersection. Therefore, in order to ensure the safety of vehicle operation, the vehicle-side control system can actively acquire the aforementioned roadside perception information from roadside equipment while acquiring the vehicle perception information mentioned above. It is worth noting that the roadside perception information acquired by the vehicle-side control system is highly correlated with the driving scenario switching command. That is, the vehicle-side control system does not need to preprocess the roadside perception information, such as further filtering out more accurate information from the roadside perception information. Instead, it can directly use the roadside perception information, which greatly reduces the operating pressure of the vehicle-side control system and improves the efficiency of the vehicle-side control system in processing roadside perception information.

[0066] In one optional embodiment, considering that the vehicle-side control system may encounter sudden events that affect the switching of driving scenarios during the process of controlling the vehicle to switch driving scenarios, such as other vehicles losing control, obstacles falling from the overpass, or undetected potholes in the road, in order to ensure that the vehicle-side control system can safely control the vehicle to switch driving scenarios, the vehicle-side control system can obtain information sent by the roadside equipment in real time during the switching of driving scenarios, that is, the roadside perception information mentioned above may include the real-time perception information mentioned above.

[0067] Furthermore, considering the inherent lag in information, there may still be safety risks when controlling the vehicle to switch driving scenarios solely based on real-time acquired information. Therefore, to further improve the safety of the driving scenario switching process, the vehicle-side control system also needs to acquire information that may appear in the current and target driving scenarios within a future period. That is, the aforementioned roadside perception information can also include the aforementioned predictive perception information. To ensure that the vehicle-side control system can quickly utilize the roadside perception information sent by the roadside equipment after receiving it, thereby improving information processing efficiency and ensuring safety during driving scenario switching, the aforementioned real-time... The process of sensing information and determining predictive sensing information based on real-time sensing information can be performed locally on the roadside equipment. That is, after receiving an information subscription request, the roadside equipment can directly filter out real-time sensing information from the stored information based on the information subscription request, and determine predictive sensing information based on the real-time sensing information. The roadside equipment does not need to interact with the cloud server, such as sending the filtered real-time sensing information to the cloud server and receiving the predictive sensing information determined by the cloud server based on the real-time sensing information. This greatly reduces information transmission costs, saves data transmission time, and thus reduces the operating costs of the roadside equipment and improves the efficiency of determining roadside sensing information.

[0068] In step S106, the vehicle-side control system fuses the vehicle-side perception information and the roadside perception information to obtain fused perception information.

[0069] In one optional embodiment, after obtaining the aforementioned vehicle-side perception information and roadside perception information, in order to better control vehicle driving based on the vehicle-side perception information and roadside perception information, the vehicle-side control system can first perform fusion processing on the vehicle-side perception information and roadside perception information to obtain the aforementioned fused perception information. For example, the vehicle-side control system can first classify the vehicle-side perception information and roadside perception information, categorizing and organizing different types of information, such as the type of other vehicles, driving direction, and relative position to the target intersection, etc., and remove duplicate information from the organized information, retaining different information to ensure the rationality and completeness of the acquired information. Then, based on a preset information fusion model, the organized information is subjected to multi-level information fusion processing, such as data layer information fusion, feature layer information fusion, and decision layer information fusion, thereby obtaining fused perception information that can assist the vehicle in switching driving scenarios.

[0070] In one optional embodiment, to ensure safety when switching driving scenarios, the process of fusing vehicle-side perception information and roadside perception information can also be performed in real time.

[0071] In step S108, the vehicle-side control system controls the vehicle's driving status based on the fused perception information.

[0072] The aforementioned driving status can refer to whether the control system can normally control the vehicle to execute driving scenario switching commands, such as whether the vehicle can continue to drive, whether the vehicle can turn normally, whether the vehicle needs to stop, and whether the driving trajectory needs to be replanned.

[0073] In one optional embodiment, after obtaining the fused perception information, the vehicle control system can switch driving scenarios based on the fused perception information and control the vehicle's driving state during the execution of the driving scenario switching command. For example, if the fused perception information indicates that the physiological state of the user inside the vehicle is normal, the environmental parameters outside the vehicle are normal, the driving parameters of other vehicles are normal and will not affect the normal driving of the vehicle, and the area in front of the vehicle is safe to drive, then the vehicle control system can control the vehicle's driving state to be able to continue driving and to be able to turn normally; if the vehicle perception information or roadside perception information received during the vehicle's driving process indicates that a sudden accident has occurred in front of the vehicle, for example, during the driving scenario switching process, the fused perception information indicates that another vehicle suddenly loses control and rushes into the area in front of the vehicle, then in order to ensure safety, the vehicle control system can control the vehicle's driving state to switch to a stop and begin to replan the vehicle's driving trajectory.

[0074] In this embodiment of the invention, in response to receiving a driving scenario switching command and the vehicle reaching the target intersection, the vehicle-end control system acquires vehicle-end perception information perceived by the vehicle; the vehicle-end control system sends an information subscription request to the roadside equipment and receives roadside perception information returned by the roadside equipment; the vehicle-end control system fuses the vehicle-end perception information and the roadside perception information to obtain fused perception information; the vehicle-end control system controls the vehicle's driving state based on the fused perception information. By actively acquiring roadside perception information with high relevance to the command from the roadside equipment when receiving a driving scenario switching command and the vehicle reaching the target intersection, and fusing the roadside perception information with the acquired vehicle-end perception information, the vehicle-end control system obtains fused perception information to assist the vehicle in performing driving scenario switching operations. This enables the vehicle-end control system to fully understand the road conditions at the target intersection based on the fused perception information, improving the vehicle-end control system's control over the current driving scenario and the target driving scenario.

[0075] Furthermore, the roadside perception information processing includes not only real-time perception information acquired by roadside equipment, but also predictive perception information determined based on this real-time perception information. Through this combined real-time and predictive perception information, the control system can promptly detect potential safety risks in the scenario, thereby improving safety during scenario transitions. Finally, the vehicle-side control system uses this fused perception information to control the vehicle's driving status in real time, enabling the vehicle to safely switch between driving scenarios, significantly improving the safety of the process.

[0076] It is worth noting that the roadside device that sends roadside perception information to the vehicle in this invention also has local computing capabilities. When it receives an information subscription instruction from the vehicle control system, it can filter the stored information in real time according to the information subscription instruction to obtain the aforementioned roadside perception information. This eliminates the need to interact with the cloud network and filter information through the cloud network, reducing the operating cost of the roadside device and improving the efficiency of obtaining roadside perception information. At the same time, the vehicle control system can directly use the roadside perception information without the need for information filtering, ensuring the timeliness of the roadside perception information during use and reducing the operating cost of the vehicle control system. This solves the technical problem of poor real-time performance when controlling the vehicle to switch driving scenarios in related technologies.

[0077] Optionally, the information subscription request carries at least the target driving scenario. The real-time perception information is the perception information corresponding to the target driving scenario selected from the initial perception information perceived by the roadside equipment. The predictive perception information is the information obtained by the roadside equipment based on the real-time perception information to predict the behavior of a preset area of ​​the target intersection. The predictive perception information is used to characterize whether there is any behavior that affects vehicle driving in the preset area.

[0078] The aforementioned preset area can refer to an area within a specified distance in front of the vehicle, an area within a specified range at the target intersection, or can be set by the user. In one optional embodiment, considering that different vehicles have different efficiencies in responding to emergencies in different environments, for example, if other vehicles suddenly appear in front of the vehicle, the vehicle will generally take emergency evasive action by stopping or making an emergency turn. However, the triggering efficiency of this evasive action may vary under different road conditions, different driving speeds, and different environmental conditions. Therefore, in order to improve vehicle safety, the aforementioned preset area can also be determined based on the vehicle-end perception information obtained in real time by the vehicle-end control system.

[0079] In one optional embodiment, in order to improve the accuracy of the acquired roadside perception information, the information subscription request sent may include at least the target driving scenario that the vehicle is about to enter, so that when the roadside device sends roadside perception information to the vehicle according to the information subscription request, it can send targeted information instead of sending all perceived information.

[0080] In one optional embodiment, considering that the information acquired by the roadside equipment through various sensors may include a variety of information with low relevance to the driving scenario switching command, such as the location of shops in the current driving scenario and the target driving scenario, the equipment model of the roadside equipment, etc., if the roadside equipment directly sends all the perceived information to the vehicle control system, it may cause the vehicle control system to have a large operating pressure, which may lead to a situation where the vehicle cannot be safely controlled. Therefore, in order to reduce the operating pressure on the vehicle control system, the roadside equipment can first perform localization processing on the perceived information, i.e., the aforementioned initial perception information, before sending it, to obtain the aforementioned roadside perception information, and then send the roadside perception information to the control system. The control system can receive the roadside perception information to control the vehicle to safely switch driving scenarios.

[0081] In one optional embodiment, as described above, the roadside perception information may include real-time perception information and predictive perception information. When acquiring real-time perception information, the roadside device can directly filter information matching the information subscription request from the currently stored and real-time perceived initial perception information, i.e., at least information matching the target driving scenario. If further accuracy is required, selectively, after acquiring information matching the target driving scenario, the roadside device can further remove information with low relevance to the driving scenario switching command, such as the type and location of shops in the target driving scenario mentioned above. Considering that some low-relevance information may still be effective for driving scenario switching in special circumstances—for example, if a tire blows out during a driving scenario switch and a repair shop exists in the target driving scenario—the type and location of the shop would also be useful information and does not need to be removed.

[0082] It should be noted that the specific information filtering process can be set by the staff themselves and is not specifically limited here. Furthermore, considering that areas in front of the vehicle or at road intersections where the vehicle exit cannot perceive scene information are areas more prone to accidents affecting normal vehicle operation, when determining predictive perception information based on real-time perception information, it can at least include information predicting behavioral events that may appear in the preset area within a certain period of time. For example, whether pedestrians or other vehicles will enter the preset area and affect the normal operation of the vehicle, and whether pedestrians or other vehicles currently affecting the normal operation of the vehicle in the preset area will leave within a short period of time. In addition to predicting possible behaviors in the preset area, roadside equipment can also predict possible changes in the overall environment within a certain period of time based on real-time perception information, such as whether it will rain in the future, or whether the coefficient of friction between the road surface and vehicle tires will decrease. This further improves the completeness of the predictive perception information, thereby enhancing the safety of the vehicle-side control system when switching driving scenarios based on roadside perception information.

[0083] Optionally, sending an information subscription request to the roadside device includes: determining the target area of ​​the target intersection based on vehicle-side perception information, wherein the target area is used to characterize the area in the target intersection that is not perceived by the vehicle; sending an information subscription request carrying the target driving scenario and the target area to the roadside device, wherein the predicted perception information is information obtained by the roadside device based on real-time perception information to predict the behavior of the preset area and the target area.

[0084] The aforementioned target area can refer to the area that cannot be detected by the various sensors on the vehicle when the vehicle is driving to the target intersection. For example, the area that is blocked by a large garden flower bed or fence in the target driving scenario mentioned above can be understood as a blind spot. This target area can be the same as or different from the aforementioned preset area.

[0085] In one optional embodiment, to improve the correlation between roadside perception information obtained through information subscription requests and driving scene switching instructions, when the vehicle-side control system sends the information subscription request to the roadside device, it can first determine the target area where information cannot be perceived based on the obtained vehicle-side perception information. Then, it adds the target driving scene that the vehicle is about to drive to, and the target area in the target driving scene, to the aforementioned information subscription request. Then, it sends the information subscription request to the roadside device, so that the roadside device can selectively filter out real-time perception information and predict behavioral events that may occur in the target area and preset area in real time based on the real-time perception information to obtain the aforementioned predicted perception information.

[0086] Optionally, controlling the vehicle's driving state based on fused perception information includes: predicting behavior in a preset area of ​​the target intersection based on fused perception information to obtain a vehicle-side prediction result, wherein the vehicle-side prediction result is used to characterize whether any behavior affecting the vehicle's driving occurs within the preset area; in response to the vehicle-side prediction result indicating that any behavior affecting the vehicle's driving occurs within the preset area, controlling the vehicle's driving state to a stopped state; in response to the vehicle-side prediction result indicating that no behavior affecting the vehicle's driving occurs within the preset area, generating a vehicle-side driving trajectory based on the fused perception information, and controlling the vehicle's driving state based on the vehicle-side driving trajectory.

[0087] The aforementioned vehicle-side prediction results can refer to the results of behavioral events that may occur in the target area or preset area, predicted based on fused perception information. These vehicle-side prediction results are related to the process of vehicle driving scene switching and may include at least the following: results that may have a negative impact on the normal driving of the vehicle, such as other vehicles blocking the vehicle from moving forward, or results that may have a positive impact on the normal driving of the vehicle, such as other vehicles blocking the vehicle from moving forward leaving in a short period of time.

[0088] In one optional embodiment, when controlling the vehicle's driving state based on fused perception information, the vehicle-end control system can first predict behavioral events that may appear in a preset area or target area again based on the fused perception information to obtain a more accurate vehicle-end prediction result. Then, the vehicle's driving state is controlled based on the vehicle-end prediction result. For example, if a behavior affecting the vehicle's driving occurs in the preset area, the vehicle's driving state can be controlled to stop; if no behavior affecting the vehicle's driving occurs in the preset area, the vehicle's driving state can be controlled to continue driving. At the same time, a vehicle-end driving trajectory is generated based on the aforementioned fused perception information. The vehicle-end control system can control the vehicle's driving state based on the vehicle-end driving trajectory, such as turning 15° to the left at a specified position, then driving straight for a distance, and then turning 90° to complete the turn.

[0089] In one optional embodiment, to improve the accuracy of controlling the vehicle's behavior, the vehicle-end control system can further control the vehicle's behavior based on the degree of impact of the vehicle-end prediction results on the vehicle's normal driving. For example, if the vehicle-end prediction results show that a behavior that may affect the normal driving of the vehicle might occur in a preset area or a target area, such as a pedestrian walking into the preset area and leaving the area in a short time, thus having a minor impact on the normal driving of the vehicle, then the vehicle can be controlled to remain stationary. However, if the behavior involves a traffic accident occurring in the preset area that cannot be handled in a short time, thus having a significant impact on the normal driving of the vehicle, then the vehicle-end control system can replan the vehicle's driving trajectory to control the vehicle to continue driving.

[0090] Optionally, controlling the vehicle's driving state based on fused perception information includes: receiving a roadside driving trajectory returned by a roadside device, wherein the roadside driving trajectory is a trajectory generated by the roadside device based on roadside perception information; generating a vehicle-side driving trajectory based on fused perception information; and controlling the vehicle's driving state based on the roadside driving trajectory and the vehicle-side driving trajectory.

[0091] In one optional embodiment, if the vehicle's driving state involves planning a driving trajectory and controlling the vehicle's movement based on that trajectory, then to improve the accuracy of the planned driving trajectory and thus enhance driving safety, the vehicle-side control system can further receive the roadside driving trajectory planned by the roadside equipment based on the roadside perception information it has sensed. Simultaneously, it can plan the vehicle-side driving trajectory based on the fused perception information from the aforementioned fusion point. Then, the roadside driving trajectory and the vehicle-side driving trajectory are fused. For example, considering that the roadside driving trajectory generated by the roadside equipment based on the roadside perception information is more consistent with the current road conditions, the vehicle-side driving trajectory can be adjusted using this roadside driving trajectory to obtain a more accurate target driving trajectory. Finally, the vehicle is controlled based on this target driving trajectory, thereby ensuring the safety of the vehicle during driving.

[0092] Optionally, the driving state of the vehicle is controlled based on the roadside driving trajectory and the vehicle-end driving trajectory, including one of the following: determining a target driving trajectory between the roadside driving trajectory and the vehicle-end driving trajectory based on the confidence level of the roadside driving trajectory and the confidence level of the vehicle-end driving trajectory, and controlling the driving state of the vehicle based on the target driving trajectory; adjusting the vehicle-end driving trajectory based on the roadside driving trajectory to obtain an adjusted driving trajectory, and controlling the driving state of the vehicle based on the adjusted driving trajectory.

[0093] In one optional embodiment, the methods for controlling the vehicle's driving state based on the roadside driving trajectory and the vehicle-end driving trajectory may include the following:

[0094] First, the vehicle-mounted control system performs confidence tests on the received roadside driving trajectory and the planned vehicle-mounted driving trajectory to obtain a first confidence level for the roadside driving trajectory and a second confidence level for the vehicle-mounted driving trajectory. For example, it uses fused perception information to perform driving simulations on the roadside driving trajectory and the vehicle-mounted driving trajectory to simulate the frequency of safety accidents that may occur when the vehicle travels along the roadside driving trajectory. The lower the frequency, the higher the confidence level of the roadside driving trajectory. Then, based on the determined first and second confidence levels, it determines the target driving trajectory with a higher confidence level from the roadside driving trajectory and the vehicle-mounted driving trajectory. Finally, the vehicle-mounted control system can control the vehicle's driving state according to the target driving trajectory.

[0095] Second, as mentioned above, the vehicle's driving trajectory is adjusted using the roadside driving trajectory to obtain an adjusted driving trajectory, and then the vehicle's driving state is controlled according to this adjusted driving trajectory.

[0096] Third, the vehicle-side control system can first determine the first confidence level and the second confidence level mentioned above, and then determine a driving trajectory with higher confidence level from the roadside driving trajectory and the vehicle-side driving trajectory. Then, it can use fused perception information or roadside perception information to adjust the driving trajectory, and finally obtain a driving trajectory with higher accuracy. Finally, it can control the driving state of the vehicle based on the driving trajectory.

[0097] Optionally, the method further includes: the vehicle-side control system receiving target push information corresponding to the target intersection pushed by the roadside equipment, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; and the vehicle-side control system controlling the vehicle to output the target push information.

[0098] The aforementioned target push information may refer to information recorded in roadside equipment that has already occurred and will affect the normal driving of vehicles, such as a traffic accident that has occurred at the target intersection and has not yet been resolved, or a pothole that has appeared at the target intersection and has not yet been filled.

[0099] In one optional embodiment, to avoid discomfort to the vehicle occupants due to the vehicle's inability to drive normally, the vehicle control system can also receive information pushed by roadside equipment that affects the normal driving of the vehicle, namely the target push information corresponding to the target intersection, and control the vehicle to output the target push information to remind the vehicle occupants of the reason why the vehicle cannot drive normally, thereby reducing the discomfort of the vehicle occupants.

[0100] Optionally, controlling the vehicle to output target push information includes: prohibiting the vehicle from outputting target push information in response to the vehicle's behavior push function being turned off; and controlling the vehicle to output target push information in response to the vehicle's behavior push function being turned on.

[0101] The aforementioned behavior push function can refer to the function used to push targeted push information to users inside the vehicle.

[0102] In one optional embodiment, considering that some users do not like push notifications, a switch can be installed in the vehicle to control the behavior-based push notification function. Users can choose whether to enable or disable the behavior-based push notification function. When the behavior-based push notification function is disabled, the vehicle control system can prevent the vehicle from outputting the target push notification information; when the behavior-based push notification function is enabled, the vehicle control system can control the vehicle to output the target push notification information.

[0103] In one optional embodiment, the vehicle control system can also acquire a user profile of the user inside the vehicle and select the aforementioned target push message in a targeted manner based on the user profile.

[0104] In one optional embodiment, regardless of whether the behavior push function is turned off or on, the vehicle control system can obtain the target push information pushed by the roadside equipment, so as to ensure that when the user suddenly wants to know the reason why the vehicle cannot drive normally and turns on the behavior push function, the vehicle control system can push the target push information to the user in the vehicle in a timely manner.

[0105] Optionally, the target push information is the push information with a push level greater than or equal to the vehicle's driving safety level among multiple push information corresponding to the target intersection. The push level is used to characterize the degree of influence of the behavior affecting the vehicle's driving on the vehicle's driving, and the driving safety level is used to characterize the probability of the vehicle driving safely.

[0106] In one optional embodiment, considering that there may be many behavioral events affecting the normal operation of a vehicle, and some of these events may have a minor impact, pushing all the target push information corresponding to all behavioral events to the in-vehicle user could potentially annoy them. Therefore, to improve the user experience, a driving safety level can be set that reflects the probability of the vehicle safely switching driving scenarios. The higher the probability, the higher the driving safety level. If the push level of some push information included in the target push information is greater than or equal to the driving safety level, it can be determined that the behavioral event corresponding to the push information has a significant impact on the normal operation of the vehicle, and the vehicle may not be able to safely switch driving scenarios. In this case, the vehicle control system can identify the push information as the target push information and push it to the in-vehicle user. If the push level of some push information included in the target push information is less than the driving safety level, it can be determined that the behavioral event corresponding to the push information has a minor impact on the normal operation of the vehicle, and the vehicle can safely pass the target intersection. In this case, the vehicle control system may not push the push information to the in-vehicle user.

[0107] In one alternative embodiment, the aforementioned driving safety level can also be determined based on the user's profile inside the vehicle.

[0108] Optionally, the method further includes: the vehicle-side control system sending the vehicle's driving status to the roadside equipment, wherein the driving status is used by the roadside equipment to generate safety warning information, the safety warning information is used to provide safety warnings to objects outside the vehicle, and the safety warning information is output by the roadside equipment.

[0109] In one optional embodiment, to ensure the safety of users outside the vehicle during the switching of driving scenarios, the vehicle-side control system can also send the vehicle's behavior status to the roadside equipment. The roadside equipment can generate corresponding safety prompts based on the behavior status and display the safety prompts externally, such as "Vehicle A is about to turn, please be careful," thereby ensuring the driving safety of objects outside the vehicle, such as users outside the vehicle or other vehicles.

[0110] Example 2

[0111] According to another aspect of the embodiments of the present invention, this specification also provides another vehicle control method. Figure 4 This is a flowchart illustrating another vehicle control method according to an embodiment of the present invention, such as... Figure 4 As shown, the steps of this method may include:

[0112] In step S402, the roadside equipment receives an information subscription request sent by the vehicle.

[0113] The roadside equipment is set at the target intersection. The information subscription request is sent by the vehicle when it receives the driving scenario switching instruction and drives to the target intersection. The driving scenario switching instruction is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection.

[0114] The aforementioned information subscription request can refer to a request to obtain roadside perception information from roadside equipment. The aforementioned driving scenario can refer to a scenario comprised of the vehicle's driving area and environmental information within that area. The aforementioned driving scenario switching command can refer to a command used to switch the vehicle's current driving scenario. The aforementioned target intersection can refer to the boundary point between the current driving scenario and the target driving scenario.

[0115] In one optional embodiment, in order to ensure that the vehicle-side control system can safely control the vehicle to execute the driving scene switching command, the vehicle-side control system can actively send the aforementioned information subscription request to the roadside equipment when it receives the driving scene switching command and the vehicle travels to the target intersection, so as to obtain information related to the driving scene switching command. The corresponding roadside equipment can be in an open state, and the vehicle can directly connect to the roadside equipment quickly through a local area network or broadcast, etc. Then the roadside equipment can receive the information subscription request sent by the vehicle in real time, so as to promptly feed back the information corresponding to the information subscription request to the vehicle.

[0116] Step S404: The roadside equipment sends roadside sensing information to the vehicle.

[0117] The roadside perception information includes real-time perception information and predictive perception information. Real-time perception information is perceived by the roadside equipment in real time, while predictive perception information is calculated locally by the roadside equipment based on the real-time perception information.

[0118] Among them, the driving status of the vehicle is controlled by fused perception information, which is the perception information obtained by fusing vehicle-side perception information and roadside perception information. Vehicle-side perception information is used to characterize the perception information perceived by the vehicle.

[0119] The aforementioned roadside perception information refers to information highly correlated with the aforementioned driving scenario switching command, which is perceived by roadside equipment through multiple sensors. The aforementioned real-time perception information refers to information related to the driving scenario switching command that the roadside equipment perceived within a certain period prior to the current moment. The aforementioned predictive perception information refers to information related to the driving scenario switching command that the roadside equipment predicts locally based on real-time perception information, and that may occur within a certain period in the future. The aforementioned vehicle-side perception information refers to information inside and outside the vehicle perceived by various sensors on the vehicle. The aforementioned driving state refers to the state in which the control system can normally control the vehicle to execute the driving scenario switching command.

[0120] In one optional embodiment, after receiving an information subscription request, to ensure the safety of the vehicle-side control system when switching driving scenarios based on roadside perception information, the roadside device can perceive real-time perception information in the environment based on the information subscription request, determine the aforementioned predicted perception information based on the real-time perception information, combine the real-time perception information and the predicted perception information to obtain roadside perception information, and then send the roadside perception information to the vehicle. To improve the efficiency of determining roadside perception information, the roadside device can determine the aforementioned real-time perception information and predicted perception information locally without interacting with the cloud server. For example, it can send the real-time perception information it acquires to the cloud server and then receive the predicted perception information determined by the cloud server based on the real-time perception information. This saves information transmission time, reduces the information transmission cost of the roadside device, and further improves the real-time performance of the determined roadside perception information.

[0121] After receiving roadside perception information, the vehicle-mounted control system can combine it with vehicle-mounted perception information obtained from various sensors on the vehicle to control the vehicle's behavior and switch driving scenarios. To ensure safety during driving scenario switching, the vehicle-mounted control system first fuses the received roadside perception information and the acquired vehicle-mounted perception information to obtain the aforementioned fused perception information. This fused perception information is then used to control the vehicle's behavior during driving scenario switching.

[0122] Optionally, the information subscription request carries at least the target driving scenario, and the method further includes: the roadside device acquiring the initial perception information perceived in real time by the roadside device; the roadside device filtering out the real-time perception information corresponding to the target driving scenario from the initial perception information; the roadside device performing behavior prediction on a preset area of ​​the target intersection based on the real-time perception information to obtain predicted perception information, wherein the predicted perception information is used to characterize whether any behavior affecting vehicle driving occurs within the preset area.

[0123] The aforementioned preset area can refer to the area within a specified distance in front of the vehicle, the area within a specified range at the target intersection, or it can be set by the user.

[0124] In one optional embodiment, considering that the information acquired by the roadside equipment through various sensors or networks may include various types of information with low relevance to the driving scenario switching command, such as the location of shops in the current driving scenario and the model of the roadside equipment, if the roadside equipment directly sends all the perceived information to the vehicle control system, it may cause the vehicle control system to have a large operating pressure, which may lead to a situation where the vehicle cannot be safely controlled. Therefore, in order to reduce the operating pressure on the vehicle control system, before sending roadside perception information to the vehicle, the roadside equipment can first acquire the initial perception information in real time, and then filter out the aforementioned real-time perception information from the initial perception information. Then, based on the real-time perception information, it can predict the behavior of a preset area at the target intersection, such as determining whether there are behavioral events in the preset area that may affect the normal driving of the vehicle, so as to obtain the aforementioned predicted perception information. Finally, the real-time perception information and the predicted perception information are combined to obtain the roadside perception information.

[0125] Optionally, the information subscription request also carries the target area of ​​the target intersection. The target area is determined by the vehicle-side perception information and is used to characterize the area in the target intersection that is not perceived by the vehicle. Based on the real-time perception information, the behavior of the preset area of ​​the target intersection is predicted to obtain the predicted perception information, including: based on the real-time perception information, the behavior of the preset area and the target area is predicted to obtain the predicted perception information.

[0126] The aforementioned target area can refer to the area that cannot be detected by the various sensors on the vehicle when it approaches the target intersection. It can be understood as a blind spot. This target area can be the same as or different from the aforementioned preset area.

[0127] In one optional embodiment, the information subscription request includes information corresponding to the target area of ​​the aforementioned target intersection. In order to improve the correlation between the roadside perception information obtained by the information subscription request and the driving scenario switching command, the currently available area is the area determined by the vehicle-side control system based on the acquired vehicle-side perception information. When determining the predicted perception information, the roadside equipment can perform behavior prediction on the aforementioned preset area and target area based on the acquired real-time perception information, thereby obtaining predicted perception information with richer information content.

[0128] Optionally, the method further includes: the roadside device generating a roadside driving trajectory of the vehicle based on roadside sensing information; the roadside device sending the roadside driving trajectory to the vehicle, wherein the driving state of the vehicle is controlled by the roadside driving trajectory and the vehicle-side driving trajectory, and the vehicle-side driving trajectory is generated based on the vehicle-side sensing information and the roadside sensing information.

[0129] In one optional embodiment, considering that the roadside equipment can perceive information in the target driving scene quickly and can promptly detect behavioral events that may affect the normal driving of the vehicle, if the vehicle-side control system determines that a driving scene switching operation needs to be performed, the roadside equipment can quickly generate a roadside driving trajectory based on the determined roadside perception information and send the roadside driving trajectory to the vehicle. Then, the vehicle-side control system can control the vehicle's behavior state during the driving scene switching process based on the roadside driving trajectory and the vehicle-side driving trajectory generated based on the vehicle-side perception information and the roadside perception information.

[0130] Optionally, the method further includes: the roadside device acquiring target push information corresponding to the target intersection, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; and the roadside device sending the target push information to the vehicle.

[0131] The aforementioned target push information may refer to information recorded in roadside equipment that corresponds to behavioral events that have occurred and will affect the normal driving of vehicles.

[0132] In one optional embodiment, to avoid discomfort for users inside the vehicle due to the vehicle's inability to drive normally, the roadside equipment can also acquire the aforementioned target push information in real time and send the target push information to the vehicle to remind users inside the vehicle of the reason why the vehicle cannot drive normally, thereby reducing the discomfort of users inside the vehicle.

[0133] Optionally, obtaining target push information corresponding to the target intersection includes: determining the vehicle's driving safety level based on the information subscription request, wherein the driving safety level is used to characterize the probability of the vehicle driving safely; obtaining the push levels of multiple push information corresponding to the target intersection, wherein the push level is used to characterize the degree of influence of behaviors affecting vehicle driving on vehicle driving; obtaining push information among the multiple push information whose push level is greater than or equal to the driving safety level, thereby obtaining the target push information.

[0134] In one optional embodiment, considering that there may be many behavioral events affecting the normal driving of a vehicle, and some of these events may have a minor impact, pushing all the target push information corresponding to all behavioral events to the in-vehicle user could potentially annoy them. Therefore, to improve the user experience, the roadside equipment can determine a driving safety level based on the content of the received information subscription request, reflecting the probability of the vehicle safely switching driving scenarios. The higher the probability, the lower the driving safety level. Then, when acquiring multiple push messages corresponding to the target intersection, the push message level is further obtained. Finally, based on the driving safety level, target push information with a push level greater than or equal to the driving safety level is selected from the multiple push messages.

[0135] Optionally, the method further includes: the roadside device receiving the driving status sent by the vehicle; the roadside device generating safety warning information based on the driving status, wherein the safety warning information is used to provide safety warnings to objects outside the vehicle; and the roadside device outputting the safety warning information.

[0136] In one optional embodiment, in order to ensure the safety of users outside the vehicle during the process of controlling the vehicle to switch driving scenarios, the roadside equipment can further receive the behavior status sent by the vehicle in real time, and generate corresponding safety prompt information based on the behavior status, such as "Vehicle A is about to turn, please pay attention to safety", and display the safety prompt information to the outside world, thereby ensuring the driving safety of objects outside the vehicle, such as users outside the vehicle or other vehicles.

[0137] Example 3

[0138] According to another aspect of the embodiments of the present invention, corresponding to the embodiments of the vehicle control method described above, this specification also provides a vehicle control device. Figure 5 This is a structural block diagram of a vehicle control device according to an embodiment of the present invention, such as... Figure 5As shown, the device may include: an acquisition module 502, used to acquire vehicle-side perception information perceived by the vehicle in response to receiving a driving scenario switching command and the vehicle driving to the target intersection, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; a communication module 504, used to send an information subscription request to the roadside device and receive roadside perception information returned by the roadside device, wherein the roadside device is set at the target intersection, and the roadside perception information includes: real-time perception information and predictive perception information, wherein the real-time perception information is perceived by the roadside device in real time, and the predictive perception information is calculated locally by the roadside device based on the real-time perception information; a fusion module 506, used to fuse the vehicle-side perception information and the roadside perception information to obtain fused perception information; and a control module 508, used to control the driving state of the vehicle based on the fused perception information.

[0139] Optionally, the information subscription request carries at least the target driving scenario. The real-time perception information is the perception information corresponding to the target driving scenario selected from the initial perception information perceived by the roadside equipment. The predictive perception information is the information obtained by the roadside equipment based on the real-time perception information to predict the behavior of a preset area of ​​the target intersection. The predictive perception information is used to characterize whether there is any behavior that affects vehicle driving in the preset area.

[0140] Optionally, the communication module includes: a determination unit, used to determine the target area of ​​the target intersection based on vehicle-side perception information, wherein the target area is used to characterize the area in the target intersection that is not perceived by the vehicle; and a communication unit, used to send an information subscription request carrying the target driving scenario and the target area to the roadside device, wherein the predicted perception information is information obtained by the roadside device based on real-time perception information to predict the behavior of the preset area and the target area.

[0141] Optionally, the control module includes: a behavior prediction unit, used to predict the behavior of a preset area of ​​the target intersection based on fused perception information to obtain a vehicle-side prediction result, wherein the vehicle-side prediction result is used to characterize whether any behavior affecting vehicle driving occurs within the preset area; a first control unit, used to control the vehicle's driving state to a stopped state in response to the vehicle-side prediction result indicating that any behavior affecting vehicle driving occurs within the preset area; and a second control unit, used to generate a vehicle-side driving trajectory based on fused perception information in response to the vehicle-side prediction result indicating that no behavior affecting vehicle driving occurs within the preset area, and to control the vehicle's driving state based on the vehicle-side driving trajectory.

[0142] Optionally, the control module includes: a receiving unit for receiving the roadside driving trajectory returned by the roadside equipment, wherein the roadside driving trajectory is a trajectory generated by the roadside equipment based on roadside perception information; a generating unit for generating the vehicle-end driving trajectory based on the fused perception information; and a third control unit for controlling the driving state of the vehicle based on the roadside driving trajectory and the vehicle-end driving trajectory.

[0143] Optionally, the third control unit is further configured to: determine a target driving trajectory between the roadside driving trajectory and the vehicle-end driving trajectory based on the confidence level of the roadside driving trajectory and the confidence level of the vehicle-end driving trajectory, and control the driving state of the vehicle based on the target driving trajectory; and / or adjust the vehicle-end driving trajectory based on the roadside driving trajectory to obtain an adjusted driving trajectory, and control the driving state of the vehicle based on the adjusted driving trajectory.

[0144] Optionally, the communication unit is also used to receive target push information corresponding to the target intersection pushed by the roadside equipment, wherein the target push information is used to characterize the behaviors that have occurred at the target intersection that affect vehicle driving; the control module is also used to control the vehicle to output the target push information.

[0145] Optionally, the control module is also configured to: prevent the vehicle from outputting target push information in response to the vehicle's behavior push function being turned off; and control the vehicle to output target push information in response to the vehicle's behavior push function being turned on.

[0146] Optionally, the target push information is the push information with a push level greater than or equal to the vehicle's driving safety level among multiple push information corresponding to the target intersection. The push level is used to characterize the degree of influence of the behavior affecting the vehicle's driving on the vehicle's driving, and the driving safety level is used to characterize the probability of the vehicle driving safely.

[0147] Optionally, the control module is also used to send the vehicle's driving status to the roadside equipment, wherein the driving status is used by the roadside equipment to generate safety warning information, the safety warning information is used to provide safety warnings to objects outside the vehicle, and the safety warning information is output by the roadside equipment.

[0148] Example 4

[0149] According to another aspect of the embodiments of the present invention, corresponding to the embodiments of the vehicle control method described above, this specification also provides a vehicle control device. Figure 6 This is a structural block diagram of another vehicle control device according to an embodiment of the present invention, such as... Figure 6As shown, the device may include: a receiving module 602, used to receive an information subscription request sent by a vehicle, wherein the roadside equipment is set at the target intersection, and the information subscription request is sent by the vehicle when it receives a driving scenario switching command and drives to the target intersection. The driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; and a sending module 604, used to send roadside perception information to the vehicle, wherein the roadside perception information includes: real-time perception information and predictive perception information. The real-time perception information is perceived by the roadside equipment in real time, and the predictive perception information is calculated locally by the roadside equipment based on the real-time perception information. The driving state of the vehicle is controlled by fused perception information, which is the perception information obtained by fusing vehicle-side perception information and roadside perception information. The vehicle-side perception information is used to characterize the perception information perceived by the vehicle.

[0150] Optionally, the information subscription request carries at least the target driving scenario, and the device further includes: a first acquisition module, used to acquire initial perception information perceived in real time by the roadside equipment; a filtering module, used to filter out the real-time perception information corresponding to the target driving scenario from the initial perception information; and a prediction module, used to predict the behavior of a preset area of ​​the target intersection based on the real-time perception information to obtain predicted perception information, wherein the predicted perception information is used to characterize whether any behavior affecting vehicle driving occurs within the preset area.

[0151] Optionally, the information subscription request also carries the target area of ​​the target intersection. The target area is determined by the vehicle-side perception information and is used to characterize the area in the target intersection that the vehicle has not perceived. The prediction module includes: a prediction unit, which is used to predict the behavior of the preset area and the target area based on real-time perception information to obtain predicted perception information.

[0152] Optionally, the device further includes: a first generation module for generating a roadside driving trajectory of the vehicle based on roadside perception information; and a transmission module for transmitting the roadside driving trajectory to the vehicle, wherein the driving state of the vehicle is controlled by the roadside driving trajectory and the vehicle-side driving trajectory, and the vehicle-side driving trajectory is generated based on the vehicle-side perception information and the roadside perception information.

[0153] Optionally, the device further includes: a second acquisition module, used to acquire target push information corresponding to the target intersection, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that affect vehicle driving; the sending module is also used to send the target push information to the vehicle.

[0154] Optionally, the second acquisition module includes: a determining unit, configured to determine the driving safety level of a vehicle based on an information subscription request, wherein the driving safety level is used to characterize the probability of safe driving of the vehicle; a first acquisition unit, configured to acquire the push levels of multiple push information corresponding to the target intersection, wherein the push level is used to characterize the degree of influence of behaviors affecting vehicle driving on vehicle driving; and a second acquisition unit, configured to acquire push information among the multiple push information whose push level is greater than or equal to the driving safety level, thereby obtaining the target push information.

[0155] Optionally, the receiving module is also used to receive the driving status sent by the vehicle; the device further includes: a second generating module, used to generate safety prompt information based on the driving status, wherein the safety prompt information is used to provide safety prompts to objects outside the vehicle; and an output module, used to output the safety prompt information.

[0156] Example 5

[0157] According to another aspect of the embodiments of the present invention, corresponding to the embodiments of the vehicle control method described above, this specification also provides a vehicle control system. Figure 7 This is a system block diagram of a vehicle control system according to an embodiment of the present invention, such as... Figure 7 As shown, the system may include: a vehicle-side control system 702, used to receive a driving scenario switching command and acquire vehicle-side perception information perceived by the vehicle when the vehicle reaches the target intersection, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; a roadside device 704, set at the target intersection and connected to the vehicle-side control system, used to acquire real-time perception information, perform local calculations based on the real-time perception information to obtain predicted perception information, and send roadside perception information to the vehicle-side control system after receiving an information subscription request sent by the vehicle-side control system, wherein the roadside perception information includes: real-time perception information and predicted perception information; the vehicle-side control system is also used to fuse the vehicle-side perception information and the roadside perception information to obtain fused perception information, and control the driving state of the vehicle based on the fused perception information.

[0158] Example 6

[0159] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, the method described above is executed in a processor of the device.

[0160] Example 7

[0161] According to another aspect of the present invention, an electronic device is also provided, comprising: one or more processors; a storage device for storing one or more programs; and a method by which the one or more processors perform any of the above-described methods when the one or more programs are executed by the one or more processors.

[0162] It should be noted that the sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0163] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0164] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.

[0165] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0166] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0167] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0168] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that, include: In response to receiving a driving scenario switching command and the vehicle driving to the target intersection, the vehicle-side control system acquires the vehicle-side perception information perceived by the vehicle, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; The vehicle-side control system sends an information subscription request to the roadside device and receives roadside perception information returned by the roadside device. The roadside device is set at the target intersection. The roadside perception information includes real-time perception information and predictive perception information. The real-time perception information is perceived by the roadside device in real time, and the predictive perception information is calculated locally by the roadside device based on the real-time perception information. The vehicle-mounted control system fuses the vehicle-mounted sensing information and the roadside sensing information to obtain fused sensing information; The vehicle-mounted control system controls the vehicle's driving status based on the fused perception information.

2. The vehicle control method according to claim 1, characterized in that, The information subscription request carries at least the target driving scenario. The real-time perception information is the perception information corresponding to the target driving scenario selected from the initial perception information perceived by the roadside equipment. The predictive perception information is the information obtained by the roadside equipment based on the real-time perception information to predict the behavior of a preset area of ​​the target intersection. The predictive perception information is used to characterize whether any behavior affecting the vehicle's driving occurs within the preset area.

3. The vehicle control method according to claim 2, characterized in that, Sending information subscription requests to roadside equipment includes: The target area of ​​the target intersection is determined based on the vehicle-side perception information, wherein the target area is used to characterize the area in the target intersection that is not perceived by the vehicle; Send an information subscription request carrying the target driving scenario and the target area to the roadside device, wherein the predicted perception information is information obtained by the roadside device based on the target perception information to predict the behavior of the preset area and the target area.

4. The vehicle control method according to claim 1, characterized in that, Based on the fused perception information, the driving state of the vehicle is controlled, including: Based on the fused perception information, behavior prediction is performed on a preset area of ​​the target intersection to obtain vehicle-side prediction results, wherein the vehicle-side prediction results are used to characterize whether any behavior affecting the vehicle's driving occurs within the preset area; In response to the vehicle-side prediction result indicating that a behavior affecting the vehicle's driving occurs within the preset area, the vehicle's driving state is controlled to be stopped. In response to the vehicle-side prediction result indicating that no behavior affecting the vehicle's driving occurs within the preset area, a vehicle-side driving trajectory is generated based on the fused perception information, and the vehicle's driving state is controlled based on the vehicle-side driving trajectory.

5. The vehicle control method according to claim 1, characterized in that, Based on the fused perception information, the driving state of the vehicle is controlled, including: Receive the roadside driving trajectory returned by the roadside device, wherein the roadside driving trajectory is a trajectory generated by the roadside device based on the roadside sensing information; Based on the fused sensing information, the vehicle's driving trajectory is generated; The driving state of the vehicle is controlled based on the roadside driving trajectory and the vehicle end driving trajectory.

6. The vehicle control method according to claim 1, characterized in that, The method further includes: The vehicle-side control system receives target push information corresponding to the target intersection pushed by the roadside equipment, wherein the target push information is used to characterize behaviors that have occurred at the target intersection that have affected the vehicle's driving. The vehicle-mounted control system controls the vehicle to output the target push information.

7. A vehicle control method, characterized in that, include: The roadside equipment receives an information subscription request sent by a vehicle. The roadside equipment is located at the target intersection. The information subscription request is sent by the vehicle when it receives a driving scenario switching instruction and drives to the target intersection. The driving scenario switching instruction is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection. The roadside equipment sends roadside sensing information to the vehicle, wherein the roadside sensing information includes: Real-time sensing information and predictive sensing information, wherein the real-time sensing information is sensed in real time by the roadside equipment, and the predictive sensing information is calculated locally by the roadside equipment based on the real-time sensing information; The vehicle's driving state is controlled by fused perception information, which is obtained by fusing vehicle-side perception information and roadside perception information. The vehicle-side perception information is used to characterize the perception information perceived by the vehicle.

8. A vehicle control system, characterized in that, include: The vehicle-side control system is used to respond to receiving a driving scenario switching command and the vehicle driving to the target intersection to obtain the vehicle-side perception information perceived by the vehicle, wherein the driving scenario switching command is used to control the vehicle to switch from the current driving scenario to the target driving scenario at the target intersection; A roadside device, installed at the target intersection and connected to the vehicle-mounted control system, is used to acquire real-time perception information, perform local calculations based on the real-time perception information to obtain predicted perception information, and send roadside perception information to the vehicle-mounted control system after receiving an information subscription request from the vehicle-mounted control system. The roadside perception information includes the real-time perception information and the predicted perception information. The vehicle-side control system is also used to fuse the vehicle-side perception information and the roadside perception information to obtain fused perception information, and to control the driving state of the vehicle based on the fused perception information.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the execution of the method according to any one of claims 1 to 7 in the processor of the device.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the method of any one of claims 1 to 7.

Images