Vehicle control method, device, electronic device, storage medium and vehicle

Abstract

The present invention provides a vehicle control method, device, electronic device, storage medium, and vehicle. The method includes: presetting different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level; obtaining the vehicle's driving mode and occlusion alarm level; if the vehicle is in driver driving mode and the occlusion alarm level is severe, controlling the intelligent driving mode to be in a disabled mode and sending a first warning prompt; if the vehicle is in intelligent driving mode and the occlusion alarm level is moderate, sending a second warning prompt; if the vehicle is in intelligent driving mode and the occlusion alarm level is severe, using the target sensor's perception information as supplementary information for supplementary identification and simultaneously sending a driver takeover prompt. The embodiments of the present invention ensure vehicle driving safety by determining the occlusion alarm level in different driving modes and selecting different operations.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle control method, device, electronic equipment, storage medium and vehicle. Background Art

[0002] Currently, advanced intelligent driving assistance features based on navigation settings have been implemented on highways and in urban areas. These features are used in multiple scenarios, including lane changes, on- and off-ramps, merging, overtaking, and left and right turns in urban areas. This poses significant challenges to the accuracy and usability of the perception system's object detection and road topology recognition. Sensors in the perception system include lasers that provide point cloud data, millimeter-wave radars that excel at tracking dynamic targets, and cameras for vision.

[0003] As the main sensing component in the multi-sensor perception system, lidar may have its external window interface blocked due to deployment area restrictions or interference from the external climate environment (for example, when covered with mud or dirt, or when the internal window encounters cold air in high temperature and high humidity, condensation and fog will form in the air). When encountering these scenarios, the accuracy and completeness of the output targets of the intelligent driving perception system will be affected, increasing the risk of vehicle accidents. Summary of the Invention

[0004] In view of this, the present invention aims to provide a vehicle control method, device, electronic device, storage medium, and vehicle to solve the problem that the obstruction of the external window interface of the lidar affects the accuracy and integrity of the output target of the intelligent driving perception system, thereby increasing the risk of vehicle accidents. The specific technical solution is as follows:

[0005] According to a first aspect of the present invention, a vehicle control method is provided, the method comprising:

[0006] Pre-setting different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a mild occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level;

[0007] Get the vehicle's driving mode and occlusion warning level;

[0008] If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, controlling the intelligent driving mode to be in a disabled mode and sending a first warning prompt;

[0009] If the driving mode is the intelligent driving mode and the obstruction warning level is the moderate obstruction warning level, sending a second warning prompt;

[0010] If the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, the perception information of the target sensor is used as supplementary information for supplementary identification to ensure the normal operation of the intelligent driving mode, and a driver takeover prompt is sent at the same time.

[0011] Optionally, the step of pre-setting different degrees of occlusion alarm levels for point cloud quantities in different ranges includes:

[0012] Get the number of first point clouds monitored by the target lidar without obstruction;

[0013] Obtaining a first target quantity corresponding to a first percentage and a second target quantity corresponding to a second percentage of the first point cloud quantity, wherein the second percentage is less than the first percentage;

[0014] Determine a first target range by using the first target quantity and the first point cloud quantity;

[0015] determining a second target range by using the first target quantity and the second target quantity;

[0016] determining a range smaller than or equal to the second target number as a third target range;

[0017] If the number of monitored point clouds is within the first target range, it is determined to be a light occlusion alarm level. If the number of monitored point clouds is within the second target range, it is determined to be a moderate occlusion alarm level. If the number of monitored point clouds is within the third target range, it is determined to be a heavy occlusion alarm level.

[0018] Optionally, if the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, controlling the intelligent driving mode to be in a disabled mode and sending a first warning prompt includes:

[0019] If the driving mode is the driver driving mode and the obstruction warning level is the mild / moderate obstruction warning level, the vehicle's active safety functions and intelligent navigation functions are allowed to be activated normally;

[0020] If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, the intelligent driving mode is controlled to be in the disabled mode, the fault light of the active safety function is lit on the vehicle instrument, the intelligent navigation function is placed in the disabled mode, and the first warning prompt is sent.

[0021] Optionally, if the driving mode is the intelligent driving mode and the obstruction alarm level is the moderate obstruction alarm level, sending a second warning prompt further includes:

[0022] If the driving mode is the intelligent driving mode, obtaining the temperature difference and the air humidity difference inside and outside the target lidar window;

[0023] If the temperature difference is greater than a first preset value and the air humidity difference is greater than a second preset value, triggering a window heating mechanism inside the target lidar;

[0024] Real-time monitoring of the second point cloud quantity of the target laser radar under the window heating mechanism;

[0025] If the second point cloud quantity is at a moderate occlusion warning level, a second early warning prompt is sent on the vehicle instrument panel.

[0026] Optionally, after sending a second warning prompt on the vehicle instrument panel if the second point cloud quantity is at a moderate occlusion alarm level, the method further includes:

[0027] Continue to monitor the number of third point clouds of the target lidar in real time;

[0028] Comparing the third point cloud quantity with the second point cloud quantity;

[0029] If the number of the third point cloud is less than the number of the second point cloud, the vehicle speed is controlled to be reduced to prompt the user.

[0030] Optionally, if the driving mode is the intelligent driving mode and the obstruction alarm level is the severe obstruction alarm level, the perception information of the target sensor is used as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode. After sending the driver takeover prompt, the following is also included:

[0031] Get the vehicle's current target speed;

[0032] If the target vehicle speed is greater than a third preset value, controlling the vehicle to decelerate to a speed lower than the third preset value;

[0033] If the target vehicle speed is less than a third preset value, the vehicle is controlled to decelerate and exit the smart driving mode.

[0034] According to a second aspect of the present invention, there is provided a vehicle control device, the device comprising:

[0035] A first setting module is used to pre-set different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a heavy occlusion alarm level;

[0036] A first acquisition module is used to obtain the driving mode and occlusion warning level of the vehicle;

[0037] a first control module, configured to control the intelligent driving mode to be in a disabled mode and send a first warning prompt if the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level;

[0038] A first sending module is configured to send a second warning prompt if the driving mode is the intelligent driving mode and the obstruction alarm level is the moderate obstruction alarm level;

[0039] The second sending module is used to use the perception information of the target sensor as supplementary information for supplementary identification if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, so as to ensure the normal operation of the intelligent driving mode and send a driver takeover prompt at the same time.

[0040] According to another aspect of the present invention, there is also provided an electronic device, comprising:

[0041] processor;

[0042] a memory for storing instructions executable by the processor;

[0043] The processor is configured to execute the instructions to implement the vehicle control method as described above.

[0044] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle control method described above are implemented.

[0045] According to yet another aspect of the present invention, a vehicle is provided, comprising: the above-mentioned vehicle control device.

[0046] The vehicle control method provided by an embodiment of the present invention pre-sets different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level, so as to facilitate the subsequent targeted adoption of different measures based on different occlusion alarm levels; obtains the vehicle's driving mode and occlusion alarm level; if the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, controls the intelligent driving mode to be in a disabled mode, and sends a first warning prompt to ensure the safety of vehicle driving; if the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level, sends a second warning prompt to prompt the user to deal with the problem in a timely manner to avoid increasing the severity of the occlusion problem; if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, uses the perception information of the target sensor as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode, and simultaneously sends a driver takeover prompt, using other sensors for redundant perception, further ensuring the safety of current driving. The embodiment of the present invention determines the occlusion alarm level under different driving modes of the vehicle and selects different operations, so that when the accuracy and integrity of the output target of the laser radar are impaired, the vehicle driving safety is guaranteed as much as possible. At the same time, the target sensor is relied upon to supplement the perception information, thereby ensuring the driving safety of the vehicle.

[0047] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0049] Figure 1 is a flowchart of the steps of a vehicle control method provided by an embodiment of the present invention;

[0050] Figure 2 yes Figure 1 Flowchart of step 101 in the vehicle control method provided by an embodiment of the present invention;

[0051] Figure 3 yes Figure 1 Flowchart of step 104 in the vehicle control method provided by an embodiment of the present invention;

[0052] Figure 4 1 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present invention;

[0053] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, each embodiment of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be understood by those skilled in the art that in each embodiment of the present invention, many technical details are provided to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in this application can be implemented. The division of the following embodiments is for convenience of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with each other and referenced to each other under the premise that there is no contradiction.

[0055] Reference Figure 1 , shows a flowchart of the steps of a vehicle control method provided by an embodiment of the present invention, the method may include:

[0056] In step 101 , different degrees of occlusion alarm levels are pre-set for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a medium occlusion alarm level, and a heavy occlusion alarm level.

[0057] In the embodiments of the present invention, the point cloud data is obtained from LiDAR (Lidar), a key sensor in autonomous vehicles. LiDAR is used to perceive the surrounding environment in real time, identifying roads, vehicles, pedestrians, obstacles, and more, and assisting with vehicle navigation and obstacle avoidance. However, due to deployment restrictions or external climatic interference, the LiDAR's external window interface may be obscured, resulting in partial loss of environmental perception and impacting vehicle operation.

[0058] Therefore, the embodiment of the present invention sets three different degrees of occlusion alarm levels internally according to the number of point clouds actually input by the laser radar, including a light occlusion alarm level, a moderate occlusion alarm level and a heavy occlusion alarm level.

[0059] Step 102: Obtain the driving mode and occlusion warning level of the vehicle.

[0060] In the embodiment of the present invention, the driving mode of the vehicle is mainly based on whether it is currently controlled by a person. If the current driving is controlled by the driver, then the driving mode at this time is the driver driving mode. If the current driving is not controlled by a person but is controlled by the vehicle itself, then the driving mode at this time is the intelligent driving mode.

[0061] In Driver mode, the driver has full control over the vehicle's acceleration, braking, and steering, with no or limited assistance features. Intelligent Driving mode typically refers to a vehicle equipped with a range of advanced driver assistance systems that can partially take over driving tasks, improving safety and comfort. Intelligent Driving mode includes the following features: Adaptive Cruise Control (ACC): Automatically adjusts the vehicle's speed based on the speed of the vehicle ahead to maintain a safe distance; Lane Keeping Assist (LKA): Helps the driver stay within their lane, issuing warnings or automatically adjusting the lane if the vehicle deviates; Automatic Emergency Braking (AEB): Automatically applies the brakes when the system detects an impending collision; Traffic Jam Assist (TJA): Automatically follows the vehicle ahead in low-speed traffic jams and keeps it within its lane; and Highway Driving Assist (HDA): On highways, the vehicle can automatically change lanes, overtake, and maintain distance under the driver's supervision. While intelligent driving modes are becoming standard features in modern vehicles, Driver mode remains essential, as drivers must be ready to take over control when necessary to ensure safe driving.

[0062] Step 103: If the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, the intelligent driving mode is controlled to be in the disabled mode and a first warning prompt is sent.

[0063] In the driver driving mode of the embodiment of the present invention, there are three possible obstruction alarm levels. If it is a mild obstruction alarm level or a moderate obstruction alarm level, the activation and operation of the active safety function and the intelligent navigation function will not be affected. If it is a severe obstruction alarm level, the intelligent driving function will not be activated. At the same time, the active safety function fault light will be lit on the instrument panel, and a prompt will be given that the active safety function is restricted. At the same time, the intelligent navigation function will be set to be inactivated and a prompt will be sent. The specific steps include:

[0064] If the driving mode is driver driving mode and the occlusion warning level is mild / moderate occlusion warning level, the vehicle's active safety functions and intelligent navigation functions are allowed to be activated normally;

[0065] If the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, the intelligent driving mode is controlled to be in the disabled mode, the fault light of the active safety function is lit on the vehicle instrument, the intelligent navigation function is in the disabled mode, and the first warning prompt is sent.

[0066] Among them, the above-mentioned prompts of limited active safety functions and the first warning prompts can be given through pictures, text, sound, etc. The content of the prompts can be "The sensor is severely blocked and the active safety function is limited", "The current vehicle's lidar is severely blocked and needs to be processed", "The sensor is severely blocked and the intelligent navigation function cannot be activated", etc.

[0067] Step 104: If the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level, a second warning prompt is sent.

[0068] In the intelligent driving mode of the embodiment of the present invention, there may also be three levels of obstruction alarms. If there is a mild obstruction alarm level, it is considered that the impact on intelligent driving is not significant, and no action will be taken at this time. If there is a moderate obstruction alarm level, due to the heavy reliance on point cloud information by intelligent driving, a text pop-up prompt will be added to the instrument panel or large screen interface, i.e., the second warning prompt. The text content of the second warning prompt may be "The current vehicle LiDAR has reached a moderate obstruction level and requires timely treatment" or "The current vehicle LiDAR has reached a moderate obstruction level. Please drive carefully."

[0069] Obstruction of the LiDAR's viewport can be caused by a variety of factors, including the external environment or the LiDAR's installation location and design. The present invention primarily addresses obstruction caused by the external environment, which can occur due to a variety of factors. For example, severe weather conditions such as heavy rain, snow, fog, or sandstorms can cause the LiDAR's viewport to become covered with dust, dirt, snow, ice, mist, water droplets, or other contaminants. In hot weather, a large temperature difference between the inner and outer surfaces of the LiDAR window can cause condensation to obstruct the inner window.

[0070] In step 105 , if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, the perception information of the target sensor is used as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode, and a driver takeover prompt is sent at the same time.

[0071] In an embodiment of the present invention, if the vehicle itself is in intelligent driving mode, but it is subsequently detected that the number of laser point clouds is seriously missing and reaches a severe occlusion level, the perception system will first rely on other target sensors (such as vision and millimeter-wave radar) as perception input sources to complete target tracking, obstacle judgment, and lane line fitting supplementary identification to avoid vehicle failure during intelligent driving and ensure the normal operation of the intelligent driving mode. At the same time, a downgrade prompt will be issued, that is, the driver will be prompted to take over through pictures, sounds, seat belt vibrations, etc.

[0072] It should be noted that there is a handover delay when the driver takes over, usually 1 to 3 seconds (the actual time depends on the performance and design of the vehicle). During this time, the vehicle is in an uncontrolled state, that is, it is neither under driver control nor vehicle intelligent control. If the car is driving at high speed when the handover occurs, then even if the handover time is short, a vehicle accident may occur. Therefore, when setting the vehicle's driving control transfer, it is necessary to limit the vehicle's speed and slow down the vehicle when taking over. The specific steps include:

[0073] Get the vehicle's current target speed;

[0074] If the target vehicle speed is greater than a third preset value, controlling the vehicle to decelerate to a value lower than the third preset value;

[0075] If the target vehicle speed is less than the third preset value, the vehicle is controlled to decelerate and exit the intelligent driving mode.

[0076] For example, the third preset value is set to 50 km / h. If the current target speed of the vehicle is 70 km / h, since 70 km / h>50 km / h, the vehicle needs to be controlled to decelerate first until it is reduced to less than 50 km / h (for example, 49 km / h). Since 49 km / h<50 km / h, the vehicle can be controlled to exit the smart driving mode while continuing to decelerate until the driver takes over. It should be noted that if the current target speed is 40 km / h, since 40 km / h<50 km / h, the vehicle can be controlled to maintain 40 km / h when taking over, or it can be decelerated to take over, but it cannot be accelerated to take over, that is, the vehicle is only allowed to decelerate and not accelerate when taking over.

[0077] The vehicle control method provided by an embodiment of the present invention pre-sets different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level, so as to facilitate the subsequent targeted adoption of different measures based on different occlusion alarm levels; obtains the vehicle's driving mode and occlusion alarm level; if the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, controls the intelligent driving mode to be in a disabled mode, and sends a first warning prompt to ensure the safety of vehicle driving; if the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level, sends a second warning prompt to prompt the user to deal with the problem in a timely manner to avoid increasing the severity of the occlusion problem; if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, uses the perception information of the target sensor as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode, and simultaneously sends a driver takeover prompt, using other sensors for redundant perception, further ensuring the safety of current driving. The embodiment of the present invention determines the occlusion alarm level under different driving modes of the vehicle and selects different operations, so that when the accuracy and integrity of the output target of the laser radar are impaired, the vehicle driving safety is guaranteed as much as possible. At the same time, the target sensor is relied upon to supplement the perception information, thereby ensuring the driving safety of the vehicle.

[0078] Further, refer to Figure 2 , showing Figure 1 A flowchart of step 101 in a vehicle control method is provided, which may include:

[0079] Step 1011: Obtain the number of first point clouds monitored by the target laser radar without obstruction.

[0080] When setting different degrees of occlusion alarm levels in an embodiment of the present invention, it is necessary to first determine the number of first point clouds under an ideal state (unobstructed state), and then use this number as a benchmark to determine different degrees of occlusion levels. Different types of laser radars with different performances monitor different numbers of first point clouds without obstruction, so this data can be determined based on the design parameters of the target laser radar, or based on the best data of the target laser radar during the factory testing phase. The present invention does not make specific limitations here. Among them, the types of target laser radars include but are not limited to solid-state laser radars, MEMS laser radars, Flash laser radars, multi-line laser radars, frequency modulated continuous wave (FMCW) laser radars, etc.

[0081] Step 1012: Obtain a first target quantity corresponding to a first percentage and a second target quantity corresponding to a second percentage of the first point cloud quantity, wherein the second percentage is smaller than the first percentage.

[0082] In this embodiment of the present invention, two percentage thresholds are set, corresponding to the first target number and the second target number. For example, if the first percentage is 90% and the second percentage is 70%, then if the number of point clouds under unobstructed conditions is 1000, then the first target number is 900 and the second target number is 700.

[0083] Step 1013: Determine a first target range based on the first target quantity and the first point cloud quantity.

[0084] In the embodiment of the present invention, the range between the first target number (such as 900 point clouds) and the number of point clouds without occlusion (such as 1000 point clouds) is defined as the first target range (900-1000).

[0085] Step 1014: Determine a second target range based on the first target quantity and the second target quantity.

[0086] In the embodiment of the present invention, the range between the first target number (e.g., 900 point clouds) and the second target number (e.g., 700 point clouds) is defined as the second target range (700-900), wherein 900 point clouds do not belong to the first target range, and 700 point clouds do not belong to the second target range, to avoid data overlap between different target ranges.

[0087] Step 1015: Determine a range that is less than or equal to the second target number as a third target range.

[0088] In the embodiment of the present invention, the range that is less than or equal to the second target number is defined as the third target range (such as [0-700]). However, if it is completely blocked, or the blockage is very serious, it is in the range of [0-300]. At this time, an error message can also be sent to prompt the user to detect the working status of the target lidar. And if it is in intelligent driving, it will quickly slow down and control the driver to take over, and can stop when necessary. It should be noted that the setting of the above numerical values ​​is only used as a reference example for explanation. The actual number of point clouds and the percentage setting need to be determined according to the actual situation. The present invention does not make specific limitations here.

[0089] Step 1016: If the number of monitored point clouds is within the first target range, it is determined to be a light occlusion alarm level; if the number of monitored point clouds is within the second target range, it is determined to be a moderate occlusion alarm level; if the number of monitored point clouds is within the third target range, it is determined to be a heavy occlusion alarm level.

[0090] In the embodiment of the present invention, if the number of point clouds actually monitored is within the first target range, for example, 965 point clouds, the system will determine that there is light occlusion in the laser radar window and trigger a light occlusion alarm. If the number of point clouds actually monitored is within the second target range, for example, 830 point clouds, the system will determine that there is moderate occlusion in the laser radar window and trigger a moderate occlusion alarm. If the number of point clouds actually monitored is within the third target range, for example, 530 point clouds, the system will determine that there is heavy occlusion in the laser radar window and trigger a heavy occlusion alarm.

[0091] In the above process, the degree of occlusion of the lidar is evaluated by comparing the actual number of monitored point clouds with the preset target range, and different levels of alarms are triggered according to the degree of occlusion so that corresponding measures can be taken.

[0092] Further, refer to Figure 3 , showing Figure 1 A flowchart of step 104 in a vehicle control method is provided, which may include:

[0093] Step 1041: If the driving mode is the intelligent driving mode, obtain the temperature difference and air humidity difference inside and outside the target lidar window.

[0094] In hot and humid weather, when the temperature difference between the inside and outside surfaces of the LiDAR window is large and the air humidity is high, condensation may form on the inner window, obstructing the LiDAR. To mitigate this obstruction, the vehicle has an internal window heating mechanism built into the LiDAR to mitigate the increased obstruction. Therefore, it is necessary to first obtain the temperature and humidity difference between the inside and outside of the target LiDAR window to determine whether to activate the window heating mechanism.

[0095] Step 1042: If the temperature difference is greater than the first preset value and the air humidity difference is greater than the second preset value, the window heating mechanism inside the target lidar is triggered.

[0096] In the embodiment of the present invention, when the temperature difference and the air humidity difference simultaneously meet certain conditions, the window heating mechanism inside the target lidar will be triggered. It should be noted that air humidity usually refers to relative humidity (RH), which is the ratio of the actual water vapor pressure in the air to the saturated water vapor pressure at that temperature, usually expressed as a percentage. For example, the first preset value is set to 20°C and the second preset value is 40%. At this time, it is determined that condensation may occur, so the window heating mechanism inside the target lidar is triggered to reduce the formation of condensation.

[0097] Step 1043 , monitor the second point cloud quantity of the target laser radar in real time under the window heating mechanism.

[0098] In the embodiment of the present invention, under the window heating mechanism, the condensation phenomenon may be alleviated, which will reduce condensation and reduce the obstruction of the target lidar. However, it is also possible that the condensation relief rate is lower than the condensation generation rate, which will cause condensation to increase and aggravate the obstruction of the target lidar. Therefore, it is also necessary to determine whether the window heating mechanism can solve the condensation problem by monitoring the number of second point clouds in real time under the window heating mechanism.

[0099] Step 1044: If the number of the second point cloud is at a moderate occlusion alarm level, a second warning prompt is sent on the vehicle instrument panel.

[0100] As long as the temperature difference exceeds the first preset value and the humidity difference exceeds the second preset value, condensation is considered to be occurring and the window heating mechanism is triggered. However, the amount of condensation may not be large at first. However, if the rate of condensation reduction is lower than the rate of condensation generation, the degree of obstruction will increase over time. If the second point cloud count reaches the moderate obstruction alarm level and the driving mode is Intelligent Driving, a text pop-up notification will be added to the instrument panel or large screen interface, and the number of laser point clouds and window heating status will continue to be monitored.

[0101] It should be noted that after sending the second warning prompt, it is necessary to continue to monitor the number of point clouds of the target lidar (the number of point clouds monitored at this time is named the third point cloud number) to observe the effect of the heating mechanism on the disappearance of condensation. If condensation continues to form and the rate of formation is greater than the rate of disappearance (the number of third point clouds continues to decrease compared to the second point cloud number), it indicates that the degree of occlusion is gradually deepening and the point cloud monitoring situation is continuously deteriorating. At this time, the control end needs to make a corresponding small deceleration to remind the user again. Among them, in autonomous driving or intelligent driving systems, "control end" usually refers to the electronic control unit (ECU) or central processing unit (CPU) responsible for vehicle control and decision-making. "Small deceleration to remind the user" means that the control end will slightly reduce the speed of the vehicle and issue a prompt to the driver through the vehicle's user interface (such as the instrument panel display, head-up display or sound warning). This deceleration is usually gradual, with the purpose of reminding the driver to pay attention to the current driving environment or system status, rather than sudden emergency braking. The specific steps include:

[0102] Continue to monitor the number of third point clouds of the target lidar in real time;

[0103] Comparing the third point cloud quantity with the second point cloud quantity;

[0104] If the number of the third point cloud is less than the number of the second point cloud, the vehicle speed is controlled to be reduced to prompt the user.

[0105] This strategy is designed to ensure the driver remains alert to the vehicle's status and ready to take control when necessary, without compromising driving comfort. In Intelligent Driving Mode, this small deceleration and prompt can help the driver understand the system's status and take action when necessary, thereby improving overall safety.

[0106] In summary, in the above process, the vehicle takes different measures under different functions and different degrees of obstruction. Refer to Table 1, which is a table of the availability range of smart driving function activation under different functions and different degrees of obstruction:

[0107] Table 1: Availability range of smart driving function activation under different functions and different degrees of occlusion

[0108]

[0109]

[0110] The above settings increase the availability range of intelligent driving function activation, while ensuring the safety of intelligent driving operation and degradation optimization strategy.

[0111] Reference Figure 4 , shows a schematic structural diagram of a vehicle control device provided by an embodiment of the present invention, the device comprising:

[0112] The first setting module 201 is used to pre-set different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a medium occlusion alarm level and a heavy occlusion alarm level.

[0113] The first acquisition module 202 is used to acquire the driving mode and the occlusion warning level of the vehicle.

[0114] The first control module 203 is configured to control the intelligent driving mode to be in a disabled mode and send a first warning prompt if the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level.

[0115] The first sending module 204 is configured to send a second warning prompt if the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level.

[0116] The second sending module 205 is used to use the perception information of the target sensor as supplementary information for supplementary recognition if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, so as to ensure the normal operation of the intelligent driving mode and send a driver takeover prompt at the same time.

[0117] Optionally, the first setting module 201 specifically includes:

[0118] The first acquisition submodule is used to obtain the first point cloud quantity monitored by the target laser radar without obstruction.

[0119] The second acquisition submodule is configured to acquire a first target quantity corresponding to a first percentage and a second target quantity corresponding to a second percentage of the first point cloud quantity, wherein the second percentage is smaller than the first percentage.

[0120] The first determination submodule is configured to determine a first target range according to the first target quantity and the first point cloud quantity.

[0121] The second determining submodule is configured to determine a second target range according to the first target quantity and the second target quantity.

[0122] The third determining submodule is configured to determine a range that is less than or equal to the second target number as a third target range.

[0123] The fourth determination submodule is used to determine that if the number of monitored point clouds is within the first target range, it belongs to the light occlusion alarm level; if the number of monitored point clouds is within the second target range, it belongs to the moderate occlusion alarm level; if the number of monitored point clouds is within the third target range, it belongs to the heavy occlusion alarm level.

[0124] Optionally, the first control module 203 specifically includes:

[0125] The function setting submodule is used to allow the vehicle's active safety functions and intelligent navigation functions to be activated normally if the driving mode is the driver driving mode and the occlusion alarm level is the mild / moderate occlusion alarm level.

[0126] The mode setting submodule is used to control the intelligent driving mode to be in the disabled mode if the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, and at the same time light up the fault light of the active safety function on the vehicle instrument, and put the intelligent navigation function in the disabled mode, and send the first warning prompt.

[0127] Optionally, the first sending module 204 specifically includes:

[0128] The third acquisition submodule is used to obtain the temperature difference and air humidity difference inside and outside the target lidar window if the driving mode is the intelligent driving mode.

[0129] The trigger submodule is used to trigger the window heating mechanism inside the target lidar if the temperature difference is greater than a first preset value and the air humidity difference is greater than a second preset value.

[0130] The monitoring submodule is used to monitor the number of second point clouds of the target lidar in real time under the window heating mechanism.

[0131] The prompt submodule is used to send a second early warning prompt on the vehicle instrument if the second point cloud quantity is at a moderate occlusion alarm level.

[0132] Optionally, the vehicle control device further includes:

[0133] The monitoring module is used to continue to monitor the number of third point clouds of the target lidar in real time.

[0134] The comparison module is used to compare the third point cloud quantity with the second point cloud quantity.

[0135] The second control module is configured to control the vehicle to reduce its speed to prompt the user if the number of the third point cloud is less than the number of the second point cloud.

[0136] The second acquisition module is used to obtain the current target speed of the vehicle.

[0137] The third control module is configured to control the vehicle to decelerate to a speed lower than the third preset value if the target vehicle speed is greater than the third preset value.

[0138] The fourth control module is used to control the vehicle to decelerate and exit the intelligent driving mode if the target vehicle speed is less than a third preset value.

[0139] The vehicle control method provided by an embodiment of the present invention pre-sets different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level, so as to facilitate the subsequent targeted adoption of different measures based on different occlusion alarm levels; obtains the vehicle's driving mode and occlusion alarm level; if the driving mode is the driver driving mode and the occlusion alarm level is the severe occlusion alarm level, controls the intelligent driving mode to be in a disabled mode, and sends a first warning prompt to ensure the safety of vehicle driving; if the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level, sends a second warning prompt to prompt the user to deal with the problem in a timely manner to avoid increasing the severity of the occlusion problem; if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, uses the perception information of the target sensor as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode, and simultaneously sends a driver takeover prompt, using other sensors for redundant perception, further ensuring the safety of current driving. The embodiment of the present invention determines the occlusion alarm level under different driving modes of the vehicle and selects different operations, so that when the accuracy and integrity of the output target of the laser radar are impaired, the vehicle driving safety is guaranteed as much as possible. At the same time, the target sensor is relied upon to supplement the perception information, thereby ensuring the driving safety of the vehicle.

[0140] Reference Figure 5 , an embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0141] Processor 301, memory 303 for storing processor-executable instructions;

[0142] The processor 301 is configured to execute the instructions to implement the vehicle control method as described above:

[0143] Pre-setting different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a mild occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level;

[0144] Get the vehicle's driving mode and occlusion warning level;

[0145] If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, controlling the intelligent driving mode to be in a disabled mode and sending a first warning prompt;

[0146] If the driving mode is the intelligent driving mode and the obstruction warning level is the moderate obstruction warning level, sending a second warning prompt;

[0147] If the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, the perception information of the target sensor is used as supplementary information for supplementary identification to ensure the normal operation of the intelligent driving mode, and a driver takeover prompt is sent at the same time.

[0148] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0149] The communication interface is used for communication between the above terminal and other devices.

[0150] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0151] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0152] In another embodiment provided by the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the vehicle control method described in any one of the above embodiments is implemented.

[0153] In another embodiment provided by the present invention, a vehicle is further provided, which may specifically include: the above-mentioned vehicle control device.

[0154] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0155] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0156] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0157] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A vehicle control method, characterized in that: The method comprises: Pre-setting different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a mild occlusion alarm level, a moderate occlusion alarm level, and a severe occlusion alarm level; Get the vehicle's driving mode and occlusion warning level; If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, controlling the intelligent driving mode to be in a disabled mode and sending a first warning prompt; If the driving mode is the intelligent driving mode and the obstruction warning level is the moderate obstruction warning level, sending a second warning prompt; If the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, the perception information of the target sensor is used as supplementary information for supplementary identification to ensure the normal operation of the intelligent driving mode, and a driver takeover prompt is sent at the same time.

2. The method according to claim 1, characterized in that The method of pre-setting different degrees of occlusion alarm levels for point cloud quantities in different ranges includes: Get the number of first point clouds monitored by the target lidar without obstruction; Obtaining a first target quantity corresponding to a first percentage and a second target quantity corresponding to a second percentage of the first point cloud quantity, wherein the second percentage is less than the first percentage; Determine a first target range by using the first target quantity and the first point cloud quantity; determining a second target range by using the first target quantity and the second target quantity; determining a range smaller than or equal to the second target number as a third target range; If the number of monitored point clouds is within the first target range, it is determined to be a light occlusion alarm level. If the number of monitored point clouds is within the second target range, it is determined to be a moderate occlusion alarm level. If the number of monitored point clouds is within the third target range, it is determined to be a heavy occlusion alarm level.

3. The method according to claim 1, characterized in that If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, controlling the intelligent driving mode to be in the disabled mode and sending a first warning prompt includes: If the driving mode is the driver driving mode and the obstruction warning level is the mild / moderate obstruction warning level, the vehicle's active safety functions and intelligent navigation functions are allowed to be activated normally; If the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level, the intelligent driving mode is controlled to be in the disabled mode, the fault light of the active safety function is lit on the vehicle instrument, the intelligent navigation function is placed in the disabled mode, and the first warning prompt is sent.

4. The method according to claim 1, wherein If the driving mode is the intelligent driving mode and the occlusion alarm level is the moderate occlusion alarm level, sending a second warning prompt further includes: If the driving mode is the intelligent driving mode, obtaining the temperature difference and the air humidity difference inside and outside the target lidar window; If the temperature difference is greater than a first preset value and the air humidity difference is greater than a second preset value, triggering a window heating mechanism inside the target laser radar; Real-time monitoring of the second point cloud quantity of the target laser radar under the window heating mechanism; If the second point cloud quantity is at a moderate occlusion warning level, a second early warning prompt is sent on the vehicle instrument panel.

5. The method according to claim 4, characterized in that After sending a second warning prompt on the vehicle instrument panel if the second point cloud quantity is at a moderate occlusion alarm level, the method further includes: Continue to monitor the number of third point clouds of the target lidar in real time; Comparing the third point cloud quantity with the second point cloud quantity; If the number of the third point cloud is less than the number of the second point cloud, the vehicle speed is controlled to be reduced to prompt the user.

6. The method according to claim 1, wherein If the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, the sensing information of the target sensor is used as supplementary information for supplementary recognition to ensure the normal operation of the intelligent driving mode. After sending the driver takeover prompt, the following is also included: Get the vehicle's current target speed; If the target vehicle speed is greater than a third preset value, controlling the vehicle to decelerate to a speed lower than the third preset value; If the target vehicle speed is less than a third preset value, the vehicle is controlled to decelerate and exit the smart driving mode.

7. A vehicle control device, characterized in that: The device comprises: A first setting module is used to pre-set different degrees of occlusion alarm levels for point cloud quantities in different ranges, wherein the occlusion alarm levels include a light occlusion alarm level, a moderate occlusion alarm level, and a heavy occlusion alarm level; A first acquisition module is used to obtain the driving mode and occlusion warning level of the vehicle; a first control module, configured to control the intelligent driving mode to be in a disabled mode and send a first warning prompt if the driving mode is the driver driving mode and the obstruction alarm level is the severe obstruction alarm level; A first sending module is configured to send a second warning prompt if the driving mode is the intelligent driving mode and the obstruction alarm level is the moderate obstruction alarm level; The second sending module is used to use the perception information of the target sensor as supplementary information for supplementary identification if the driving mode is the intelligent driving mode and the occlusion alarm level is the severe occlusion alarm level, so as to ensure the normal operation of the intelligent driving mode and send a driver takeover prompt at the same time.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the vehicle control method according to any one of claims 1 to 6.

9. A readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: include: The vehicle control device according to claim 7.

Images