Vehicle automatic driving control method and device, electronic equipment and storage medium
Through the evaluation of data of multiple monitoring categories and risk weight configuration of autonomous driving vehicles, accurate downgrade processing is achieved when the risk of autonomous driving increases, the problem of vehicles adapting to changes in traffic environment in complex scenarios is solved, and the driver's takeover is improved Timeliness and safety.
Patent Information
- Application Number
- CN202411148095.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
AI Technical Summary
How to accurately implement driving level downgrade treatment for autonomous vehicles, especially in complex scenarios to ensure that vehicles can adapt to changes in the traffic environment.
By obtaining monitoring data for multiple monitoring categories associated with the vehicle at the driving level, assessing the risk of autonomous driving, and performing downgrades at the driving level when the risk is greater than the preset threshold, including environmental, vehicle and driver monitoring categories, Use risk weights to rationally configure, collect and update monitoring data for accurate risk assessment and downgrade processing.
The accuracy of the risk assessment of vehicles at different levels of autonomous driving is achieved, ensuring timely downgrading when the risk of autonomous driving increases, improving the timeliness and safety of driver takeovers, and avoiding potential accidents caused by a single prompt method.
Smart Images

Figure CN118928466A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle automatic driving control, and in particular to a control method, device, electronic device and storage medium for vehicle automatic driving. Background Art
[0002] Currently, autonomous driving vehicles are divided into L0~L5, with a total of 6 driving levels, namely no autonomous driving assistance, driver assistance, partial autonomous driving assistance, combined autonomous driving assistance, highly autonomous driving and fully autonomous driving. Due to technical, regulatory and economic constraints, autonomous driving cannot reach L5 level fully autonomous driving in the short term. Highly autonomous driving L4 is defined as when an emergency occurs, the driver will not take over, but the autonomous driving system will solve the problem itself, which means that in the driving of vehicles at L3 and below the L3 driving level, the driver becomes an indispensable part. When encountering some complex scenarios, the autonomous driving system should switch the vehicle's autonomous driving level to the next level in time so that the target level autonomous driving system can withstand and handle the current traffic environment.
[0003] Therefore, how to accurately implement driving level downgrade processing for autonomous driving vehicles is a technical problem that needs to be solved urgently. Summary of the invention
[0004] In view of the above-mentioned technical problems, the present invention provides a control method, device, electronic device and storage medium for vehicle autonomous driving, which accurately evaluate the autonomous driving risk of the vehicle at its driving level and can accurately downgrade the driving level of the autonomous driving vehicle.
[0005] The embodiment of the present invention provides the following solution:
[0006] In a first aspect, an embodiment of the present invention provides a method for controlling automatic driving of a vehicle, the method comprising:
[0007] After the vehicle turns on the autonomous driving function, monitoring data of various monitoring categories of driving risks associated with the vehicle at the driving level, where the driving level is the different levels of the vehicle based on the degree of autonomous driving control;
[0008] According to the monitoring data of each monitoring category, the category monitoring risk of each monitoring category is obtained, wherein each monitoring category includes at least one monitoring data of the category to which it belongs;
[0009] Based on the monitoring risk and corresponding risk weight of each category, the autonomous driving risk of the vehicle at the driving level is obtained;
[0010] When the risk of autonomous driving is greater than the preset risk threshold, the vehicle's driving level will be downgraded.
[0011] In an optional embodiment, monitoring data of multiple monitoring categories of driving risks associated with the vehicle at the driving level are obtained, including:
[0012] Determine the target monitoring item of each monitoring category of the driving level according to the driving level of the vehicle and the first corresponding relationship, wherein the first corresponding relationship is the relationship between different driving levels and the corresponding monitoring items of each monitoring category;
[0013] Data collection is performed according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories at the driving level of the vehicle.
[0014] In an optional embodiment, the driving level is L3 driving level; data collection is performed according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories of the vehicle at the driving level, including:
[0015] Data collection is implemented according to multiple target monitoring items in the environmental monitoring category, and monitoring data of the environmental monitoring category including rainfall, driving road type, driving weather, driving lighting and driving position are obtained;
[0016] Implement data collection according to multiple target monitoring items of vehicle monitoring categories, and obtain monitoring data of vehicle monitoring types including the perception status of environmental sensors, the running speed of control software, the running status of controllers and the execution status of vehicle actuators;
[0017] Data collection is implemented according to multiple target monitoring items of the driver monitoring category, and the monitoring data of the driver monitoring category obtained includes the driver's sleepiness state and driving concentration score.
[0018] In an optional embodiment, before obtaining the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight, the method further includes:
[0019] According to the driving level of the vehicle and the second corresponding relationship, the current risk weight of each category of monitoring risk at the driving level is determined, wherein the second corresponding relationship is the relationship between different driving levels and the corresponding risk weights of each monitoring category.
[0020] In an optional embodiment, the multiple monitoring categories include an environment monitoring category, a vehicle monitoring category, and a driver monitoring category; after determining the current risk weight of each category of monitoring risk at the driving level, the method further includes:
[0021] Update the first risk weight of the environmental monitoring category based on the vehicle's driving location;
[0022] Update the second risk weight of the vehicle monitoring category based on the vehicle’s accumulated mileage;
[0023] Update the third risk weight of the driver monitoring category based on the driver's single cumulative driving time.
[0024] In an optional embodiment, before obtaining the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight, the method further includes:
[0025] According to the driver's cumulative task time for executing driving tasks and the third corresponding relationship, the current risk weight of each category of monitoring risk at the driving level is determined, wherein the third corresponding relationship is the relationship between the cumulative time of different tasks and the corresponding risk weight of each monitoring category.
[0026] In an optional embodiment, the driving level of the vehicle is downgraded, including:
[0027] Outputting a first prompt instruction for implementing a driving level downgrade process, wherein the first prompt instruction is a takeover prompt instruction of a first intensity level to the driver in an audio and visual manner;
[0028] If the driver's takeover feedback signal is received within the preset time, the takeover prompt to the driver will be stopped;
[0029] If no takeover feedback signal from the driver is received within the preset time, a second prompt instruction is output, wherein the second prompt instruction is a takeover prompt instruction of a second intensity level to the driver including tactile, sound and visual methods, and the prompt intensity of the second intensity level is greater than the prompt intensity of the first intensity level.
[0030] In a second aspect, an embodiment of the present invention further provides a control device for automatic driving of a vehicle, the device comprising:
[0031] An acquisition module, used to acquire monitoring data of multiple monitoring categories of driving risks associated with the vehicle at the driving level after the vehicle turns on the automatic driving function, wherein the driving level is the different levels divided by the vehicle based on the degree of automatic driving control;
[0032] A first obtaining module is used to obtain the category monitoring risk of each monitoring category according to the monitoring data of each monitoring category, wherein each monitoring category includes at least one monitoring data of the category to which it belongs;
[0033] The second acquisition module is used to obtain the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight;
[0034] The processing module is used to downgrade the driving level of the vehicle when the risk of autonomous driving is greater than a preset risk threshold.
[0035] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of any one of the methods in the first aspect.
[0036] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.
[0037] Compared with the prior art, the control method, device, electronic device and storage medium of the present invention for automatic vehicle driving have the following advantages:
[0038] The technical solution of the present invention is to obtain monitoring data of multiple monitoring categories of driving risks associated with the driving level of the vehicle after the vehicle turns on the automatic driving function. The driving level is the different levels of the vehicle divided based on the degree of automatic driving control; according to the monitoring data of each monitoring category, the category monitoring risk of each monitoring category is obtained, and according to each category monitoring risk and the corresponding risk weight, the automatic driving risk of the vehicle at the driving level is obtained; when the automatic driving risk is greater than the preset risk threshold, the driving level of the vehicle is downgraded. The solution implements automatic driving monitoring from multiple monitoring categories, and reasonably configures the risk of each category monitoring through risk weights, so that the vehicle can select an applicable risk assessment strategy at different automatic driving levels, and realizes the accurate assessment of the automatic driving risk of the vehicle at the driving level, and then can accurately downgrade the driving level of the automatic driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0040] Figure 1 A flow chart of a method for controlling automatic driving of a vehicle provided by an embodiment of the present invention;
[0041] Figure 2 A logical schematic diagram of a method for controlling an automatic driving vehicle provided by an embodiment of the present invention;
[0042] Figure 3This is a schematic diagram of the overall logic of a vehicle after the automatic driving function is turned on according to an embodiment of the present invention;
[0043] Figure 4 A schematic diagram of the structure of a control device for automatic driving of a vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention belong to the scope of protection of the embodiments of the present invention.
[0045] See also Figure 1 , Figure 1 The flowchart of a vehicle automatic driving control method provided in an embodiment of the present invention can be applied to the vehicle controller (ECU, Electronic Control Unit) of the vehicle, or the automatic driving controller to implement the automatic driving control of the vehicle. The terminal device of the application can run the control method, and no specific limitation is made here. The control method includes:
[0046] S11. After the vehicle turns on the automatic driving function, monitoring data of various monitoring categories of driving risks associated with the vehicle at the driving level is obtained, wherein the driving level is the different levels of the vehicle based on the degree of automatic driving control.
[0047] Specifically, the autonomous driving function is a function that the vehicle implements at the L0 to L5 driving levels, and can be activated based on the vehicle driver's command trigger. For example, based on the environmental data collected by the sensors on the vehicle, a prompt to confirm the activation of the autonomous driving function is output after comprehensive analysis. After the driver confirms, the vehicle's autonomous driving function is activated. The vehicle's driving level can be either the L3 driving level or the L2 driving level, and there is no specific restriction here. For different driving levels, corresponding types of monitoring categories and monitoring items for each monitoring category can be set; the same types of monitoring categories can also be set for all driving levels, and there are differences in the monitoring items of each monitoring category in different driving levels.
[0048] Exemplarily, step S11 includes sub-steps S11-1 to S11-2, which are specifically described as follows:
[0049] S11-1. Determine the target monitoring items of each monitoring category at the driving level according to the driving level of the vehicle and the first corresponding relationship, wherein the first corresponding relationship is the relationship between different driving levels and the corresponding monitoring items of each monitoring category. The first corresponding relationship can be constructed based on the experience of technicians or calibration experiments, and different monitoring items are set for each monitoring category at different driving levels. The first corresponding relationship can be represented as a corresponding relationship table, and the target monitoring items that need to be monitored at the driving level of the vehicle are obtained by searching in the first corresponding relationship through the current driving level of the vehicle.
[0050] S11-2, data collection is performed according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories of the vehicle at the driving level. The target monitoring items of each monitoring category represent the monitoring data that needs to be collected under the monitoring category, such as temperature, humidity, wind speed, etc. of the environmental monitoring category, and the operating status of the controller of the vehicle monitoring category to determine whether the controller is in normal operation.
[0051] The following will take the driving level of the vehicle being L3 as an example to specifically describe the specific execution steps of sub-step S11-2, which specifically include:
[0052] The first step is to implement data collection according to multiple target monitoring items in the environmental monitoring category, and obtain monitoring data of the environmental monitoring category including rainfall, driving road type, driving weather, driving lighting and driving position. Each monitoring item in the environmental monitoring category can be set to a value between 0-1. For example, when there is no rainfall, the monitoring data of the monitoring item is 0; when the rainfall is characterized by light rain, the monitoring data is 0.1; when the rainfall is characterized by moderate rain, the monitoring data is 0.5; when the rainfall is characterized by heavy rain, the monitoring data is 1. Similarly, the driving road type is the type of road on which the vehicle is driving at the current driving level. It can be determined through image recognition or map positioning. The driving road types include expressways, urban elevated roads, provincial roads, urban roads, country roads, etc. Each type of road is set with a corresponding monitoring value for quantitative distinction to facilitate subsequent identification. It should be noted that when outputting the monitoring data of the driving road type, certain road conditions, including whether there are signs prohibiting pedestrians and cyclists, whether the road has physical isolation facilities, whether there are markings to divide the direction of traffic flow to prevent vehicles from crossing, and whether the lane lines are regular and clear can all be used as data monitoring. In addition, the lane curvature radius, road slope, water accumulation, and snow accumulation on the road can also be monitored as monitoring items. Driving lighting monitoring can include ambient light that is too dark, too bright, facing the light, backlighting, drastic changes in light and dark (for example, the brightness change rate is greater than the change rate threshold), flashing, etc. Driving weather monitoring can include rain, snow, fog, sandstorms, hail, etc. Driving position monitoring can include positioning accuracy, positioning terrain (such as canyons, tunnels), etc.
[0053] In the second step, data collection is implemented according to multiple target monitoring items of the vehicle monitoring category, and the monitoring data of the vehicle monitoring type obtained includes the perception state of the environmental sensor, the running speed of the control software, the running state of the controller, and the execution state of the vehicle actuator. The perception state of the environmental sensor can be characterized by whether the environmental sensor is blocked. If it is blocked, the monitoring data can be 1; if it is not blocked, the monitoring data is 0; the running speed of the control software can also be monitored and quantified, and the running speed of the software can be determined by setting test variables and test functions. The running state of the controller includes whether there is a fault code; the execution state of the vehicle actuator includes the state of the vehicle's acceleration, braking and steering actuators.
[0054] The third step is to implement data collection according to multiple target monitoring items in the driver monitoring category, and obtain monitoring data of the driver monitoring category including the driver's drowsiness state and driving concentration score. The drowsiness state can also be set to a value between 0 and 1. For example, the driver's facial image is captured by a camera to identify whether the driver has drowsiness characteristics. Similarly, by identifying whether the driver turns his head to chat with people around him, and whether he operates his mobile phone, his driving concentration score is determined. The driving concentration score is set to a value between 0 and 1, 1 is completely focused, without any distraction, and can respond quickly and accurately to the surrounding environment; 0 is completely inattentive, and may completely ignore the driving task and have no response to the surrounding environment, which is a very dangerous situation in actual driving.
[0055] So far, monitoring data of various monitoring categories of driving risks associated with the vehicle at the driving level have been obtained.
[0056] S12. Obtain the category monitoring risk of each monitoring category according to the monitoring data of each monitoring category, wherein each monitoring category includes at least one piece of monitoring data of the corresponding category.
[0057] Specifically, a risk calculation model can be set for each monitoring category, and the monitoring data of each monitoring category can be input into the corresponding risk calculation model to obtain the category monitoring risk of the monitoring category. For example, a convolutional neural network model can be set as a risk calculation model, and the monitoring data of environmental monitoring categories such as rainfall, road type, driving weather, driving lighting and driving position can be input into the risk calculation model to obtain the first category monitoring risk of the environmental monitoring category, which is recorded as Ei. Similarly, based on the same processing method as above, the second category monitoring risk of the vehicle monitoring category can be obtained, which is recorded as Vi; and the third category monitoring risk of the driver monitoring category can be recorded as Hi.
[0058] S13. Obtain the autonomous driving risk of the vehicle at the current driving level based on each category of monitoring risk and the corresponding risk weight.
[0059] Specifically, taking the monitoring categories including environment monitoring category, vehicle monitoring category and driver monitoring category as an example, the first category monitoring risk of the environment monitoring category is recorded as Ei, the second category monitoring risk of the vehicle monitoring category is recorded as Vi, and the third category monitoring risk of the driver monitoring category is recorded as Hi. The risk weights corresponding to the environment monitoring category, vehicle monitoring category and driver monitoring category are the first risk weights. Second risk weight and the third risk weight The formula can be:
[0060]
[0061] Obtain the autonomous driving risk R of the vehicle at the driving level. It can be understood that each risk weight can be configured based on actual needs.
[0062] In practical applications, due to the differences in the degree of autonomous driving of vehicles at different driving levels, if the same risk weight is set for each driving level, the accuracy of the driving level control processing for the autonomous driving vehicle will also be insufficient. Based on this, in a specific implementation, before obtaining the autonomous driving risk of the vehicle at the driving level, the control method also includes:
[0063] According to the driving level of the vehicle and the second corresponding relationship, the current risk weight of each category of monitoring risk at the driving level is determined, where the second corresponding relationship is the relationship between different driving levels and the corresponding risk weights of each monitoring category. The second corresponding relationship can be set based on the characteristics of each driving level. For example, the main difference between driving level L3 and driving level L2 is that in automatic driving at driving level L3, the driver does not need to participate in driving control tasks, but only needs to supervise the vehicle and driving environment when the vehicle reminds him. At this time, the third risk weight It can be set to a smaller value. However, in L2 autonomous driving, the driver is the driving responsible party and needs to continue to complete the driving task through autonomous control. Need to be set to a larger value.
[0064] Furthermore, in different driving scenarios, the risk of autonomous driving of vehicles varies. If the risk weight is set based on a unified standard, the calculation result of the risk of autonomous driving may be inaccurate in special scenarios. Still taking multiple monitoring categories including environmental monitoring category, vehicle monitoring category and driver monitoring category as an example; after determining the current risk weight of each category of monitoring risk at the driving level, the control method also includes:
[0065] The first step is to update the first risk weight of the environmental monitoring category based on the vehicle's driving position. The first risk weight can be updated based on big data. For example, based on big data analysis of traffic accidents, it can be determined that certain sections of road are more prone to traffic accidents. The driving map of the autonomous driving system will store which sections of road are prone to traffic accidents. At this time, when the vehicle enters a section prone to traffic accidents based on its driving position, the first risk weight of the environmental monitoring category will be appropriately increased. According to climate data, when the outdoor temperature is below minus 5 degrees, the road is prone to ice, causing the vehicle to slip. The first risk weight can also be appropriately increased.
[0066] The second step is to update the second risk weight of the vehicle monitoring category based on the vehicle's accumulated mileage. As the vehicle's age or accumulated mileage increases, the vehicle's condition deteriorates and the probability of failure of various parts increases. For example, in the first year of vehicle use or when the mileage is 15,000 kilometers, 0.4, after the vehicle is in use for the tenth year or the cumulative mileage reaches 150,000 kilometers, is 0.55, and the intermediate years or accumulated mileage can be calculated by interpolation.
[0067] The third step is to update the third risk weight of the driver monitoring category based on the driver’s single cumulative driving time.
[0068] The driver's reaction to the vehicle's control will deteriorate as the driving time increases. The third risk weight can be adjusted according to the driver's driving time. Make dynamic adjustments. For example, within the first hour of driving, After the driver drove for 1 hour, After the driver drove for 2 hours, Third risk weight Other intermediate values of can be calculated by interpolation.
[0069] The safety of vehicle driving is closely related to the driver's experience. Generally, experienced drivers have faster reaction times and can make correct decisions quickly in emergency situations. Based on this, the current risk weight of each category of monitoring risk at the driving level can also be determined based on the driver's cumulative task time for performing driving tasks and the third corresponding relationship, where the third corresponding relationship is the relationship between the cumulative time of different tasks and the corresponding risk weight of each monitoring category. In the third corresponding relationship, the greater the driver's cumulative task time for performing driving tasks, the higher the third risk weight. The larger the risk, the smaller the third risk weight. The smaller.
[0070] After the risk weight of each category of monitoring risk is derived based on the above method, the autonomous driving risk of the vehicle at the current driving level is calculated through each risk weight and each category of monitoring risk, and step S14 is entered after the autonomous driving risk is obtained.
[0071] S14. When the risk of autonomous driving is greater than a preset risk threshold, the driving level of the vehicle is downgraded.
[0072] Specifically, the risk threshold can be set freely, and the vehicle can be controlled to remind the driver of the downgrade in time. For example, the corresponding risk threshold is set based on different driving levels. When the driving level is downgraded from L3 to L2, the risk threshold for implementing the downgrade process is set as the first threshold; when the driving level is downgraded from L2 to L1, the risk threshold for implementing the downgrade process is set as the second threshold. It should be noted that the downgrade process can first remind the driver of the downgrade, and the downgrade can be carried out after the driver confirms the takeover within the preset time; if the driver's confirmation of takeover is not received within the preset time, the vehicle can be controlled to pull over to ensure the safety of the downgrade process.
[0073] In practical applications, since the downgrade prompt directly affects the safety of driving, if the prompt method is single, a vehicle accident may occur due to failure to alert the driver. Based on this, in a specific implementation, step S14 includes sub-steps S14-1 to S14-3, which are specifically described as follows:
[0074] S14-1, outputting a first prompt instruction for implementing a driving level downgrade process, wherein the first prompt instruction is a takeover prompt instruction of the first intensity level to the driver in a voice mode and a visual mode. The voice mode includes implementing a "Beep sound" prompt, which is an electronic signal sound, which is a short, single-tone sound used to remind the driver to take over in time. The visual mode includes displaying a takeover icon on the central control screen or instrument.
[0075] S14-2: If the takeover feedback signal from the driver is received within the preset time, it means that the safety of the vehicle driving can be guaranteed through the driver's control, and then the takeover prompt to the driver is stopped, that is, the output of the first prompt instruction is stopped.
[0076] S14-3. If the takeover feedback signal from the driver is not received within the preset time, it means that the first prompt instruction did not allow the driver to take over, and then a second prompt instruction is output, wherein the second prompt instruction is a takeover prompt instruction of a second intensity level including tactile, audio and visual methods to the driver, and the prompt intensity of the second intensity level is greater than the prompt intensity of the first intensity level. In the second prompt instruction, the audio method also includes audio reminders, such as audio prompts to the driver through human voice prompts and warning sounds. The tactile method includes one or more of steering wheel vibration, seat vibration, and Bluetooth watch vibration. The visual method also includes flashing of the takeover icon, flashing of the ambient light inside the vehicle, etc.
[0077] Of course, when there is an emergency takeover, all available strong interaction methods can be used together to provide the driver with a concise takeover signal, and at the same time express the urgency of the takeover through the signal. It can be understood that when the driver takes over, it includes the lateral driving control and longitudinal driving control of the vehicle. The determination of lateral driving control can be determined by the steering wheel capacitive sensor to identify whether the driver is holding the steering wheel; the steering wheel torque sensor can be used to identify whether the driver applies torque to the steering wheel. The determination of longitudinal driving control can identify the driver's pressing of the accelerator pedal and the brake pedal.
[0078] Activities that affect driving tasks are generally divided into two types: 1) The physiological state does not support normal driving. Common categories include driver fatigue, road rage, and acute disease. 2) Distracted behavior affects normal driving. Common factors include drivers making phone calls, sending text messages, frequently chatting with passengers, and not paying attention to the road in front for a long time. The driver's ability to take over can be identified through the on-board DMS (Driver Monitoring System).
[0079] See also Figure 2 , Figure 2 The following is a logic diagram of the control method for automatic vehicle driving. The state monitoring module includes driver state monitoring, vehicle state monitoring, and driving environment monitoring. The driver state mainly focuses on the driver's distraction, fatigue, and control information; the vehicle state needs to obtain information such as the vehicle's motion state and stability; and the driving environment includes weather conditions, road conditions, and the motion state of surrounding vehicles.
[0080] Based on the status information output by the status monitoring module, the risk assessment module predicts and evaluates the risks in the three aspects of "driver-vehicle-environment" for the current autonomous driving functions and working scenarios, and provides reference information for the downgrade decision module.
[0081] When making a downgrade decision, the output data of the driver monitoring module, the vehicle status monitoring module and the traffic environment monitoring module are received to predict the highest autonomous driving level that can be achieved due to the risk, and compare it with the current driving level ADAS to determine whether to issue a downgrade signal; secondly, it is necessary to decide on the downgrade path based on the actual situation. Under non-emergency downgrade conditions, a continuous downgrade method should be adopted. If emergency downgrade conditions occur and the target autonomous driving level is discontinuous with the current level, a skip-level downgrade should be adopted; based on actual requirements, the level of the downgrade signal is decided, which is divided into two categories, including a level one normal takeover signal and a level two emergency takeover signal.
[0082] The human-computer interaction interface is responsible for designing the form of degradation signals, which may include multi-modal prompt signals such as sound, light, touch, and watches. Under the premise of ensuring safe takeover, the driver's comfort is taken into consideration, allowing the driver to take over the vehicle quickly and smoothly, allowing the ADAS to be downgraded smoothly.
[0083] After the downgrade process begins, the external takeover control system starts working, and the control of the vehicle will gradually be transferred from the vehicle to the driver. At this time, the status monitoring and risk assessment module should continue to work, assess the risks in the three aspects of "driver-vehicle-environment", and prepare countermeasures for possible changes in downgrade signals until the downgrade is successful and the control of the vehicle is completely returned to the driver.
[0084] The following is an overall description of the vehicle automatic driving control method provided by the embodiment of the present invention. Figure 3 , Figure 3 The overall logic diagram of the control method includes:
[0085] S301. Control the vehicle to perform autonomous driving at driving level L3.
[0086] S302: Determine whether the driver performs lateral control of the vehicle.
[0087] S303: When it is determined that the driver performs lateral control of the vehicle, determine whether the driver performs longitudinal control of the vehicle.
[0088] S304: When it is determined that the driver does not perform lateral control of the vehicle, determine whether the driver performs longitudinal control of the vehicle.
[0089] S305: When the driver performs longitudinal control of the vehicle, a secondary takeover reminder is output externally.
[0090] S306: Determine whether the driver is holding the steering wheel.
[0091] S307: When the driver holds the steering wheel, determine whether the driver has the ability to take over.
[0092] S308: When the driver does not hold the steering wheel, control the vehicle to pull over and park.
[0093] S309: When the driver fails to exercise longitudinal control, determine whether the vehicle is urgently downgraded from driving level L3 to driving level L2.
[0094] S310. When the result of the judgment in step S309 is yes, a secondary takeover reminder is output externally.
[0095] S311. When the judgment in step S309 is No, a first-level takeover reminder is output externally.
[0096] S312: Determine whether the driver is holding the steering wheel.
[0097] S313. When it is determined in step S312 that the driver does not hold the steering wheel, a secondary takeover reminder is outputted externally.
[0098] S314: Determine whether the driver is holding the steering wheel.
[0099] S315: Control the vehicle to pull over when the driver does not hold the steering wheel.
[0100] S316. When it is determined in step S312 that the driver is holding the steering wheel, the vehicle is controlled to execute automatic driving control of driving level L2.
[0101] S317: Determine whether the driver performs lateral control of the vehicle.
[0102] S318: When it is determined that the driver performs lateral control of the vehicle, determine whether the driver performs longitudinal control of the vehicle.
[0103] S319: When it is determined that the driver does not perform lateral control of the vehicle, determine whether the driver performs longitudinal control of the vehicle.
[0104] S320: When the driver performs longitudinal control of the vehicle, a secondary takeover reminder is output externally.
[0105] S321. Determine whether the driver is holding the steering wheel.
[0106] S322. When the driver holds the steering wheel, determine whether the driver has the ability to take over.
[0107] S323: Determine whether the conditions for downgrading the driving level from L2 to L1 are met.
[0108] S324. When step S323 is judged as No, the vehicle is controlled to implement L2 level autonomous driving.
[0109] S325. When the judgment in step S323 is yes, a secondary takeover reminder is output externally.
[0110] S326: Determine whether the driver is holding the steering wheel.
[0111] S327. Pull the vehicle over to the side of the road when the driver does not hold the steering wheel.
[0112] S328. When the driver holds the steering wheel, determine whether the driver has the ability to take over.
[0113] S329: When the driver is capable of taking over, control the vehicle to enter L1 driving level autonomous driving.
[0114] S330: Determine whether the driver performs lateral control of the vehicle.
[0115] S331: When the driver does not perform lateral control of the vehicle, determine whether the condition for downgrading from L1 to L0 is met.
[0116] S332: When the conditions for downgrading from L1 to L0 are not met, the vehicle is controlled to perform L1 driving level autonomous driving.
[0117] S333: When the conditions for downgrading from L1 to L0 are met, a secondary takeover reminder is output externally.
[0118] S334: Determine whether the driver performs longitudinal control of the vehicle.
[0119] S335: When the driver fails to perform longitudinal control of the vehicle, control the vehicle to pull over to the side of the road.
[0120] S336. Determine whether the driver has the ability to take over.
[0121] S337: When the driver is capable of taking over, the system enters driving level L0 autonomous driving.
[0122] Based on the same technical concept as the control method, the embodiment of the present invention also provides a control device for automatic driving of a vehicle, see Figure 4 , Figure 4 The schematic diagram of the structure of the control device is as follows:
[0123] The acquisition module 401 is used to acquire monitoring data of multiple monitoring categories of driving risks associated with the vehicle at the driving level after the vehicle turns on the automatic driving function, wherein the driving level is a different level divided by the vehicle based on the degree of automatic driving control;
[0124] A first obtaining module 402 is used to obtain the category monitoring risk of each monitoring category according to the monitoring data of each monitoring category, wherein each monitoring category includes at least one monitoring data of the category to which it belongs;
[0125] The second obtaining module 403 is used to obtain the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight;
[0126] The processing module 404 is used to downgrade the driving level of the vehicle when the autonomous driving risk is greater than a preset risk threshold.
[0127] In an optional embodiment, the acquisition module includes:
[0128] A determination submodule, configured to determine a target monitoring item of each monitoring category at the driving level according to the driving level at which the vehicle is located and the first corresponding relationship, wherein the first corresponding relationship is a relationship between different driving levels and corresponding monitoring items of each monitoring category;
[0129] The acquisition submodule is used to implement data collection according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories of the vehicle at the driving level.
[0130] In an optional embodiment, the driving level is L3 driving level; the obtaining submodule includes:
[0131] A first acquisition unit is used to collect data according to multiple target monitoring items of the environmental monitoring category, and obtain monitoring data of the environmental monitoring category including rainfall, driving road type, driving weather, driving lighting and driving position;
[0132] The second acquisition unit is used to implement data collection according to multiple target monitoring items of the vehicle monitoring category, and obtain monitoring data of the vehicle monitoring type including the perception state of the environmental sensor, the running speed of the control software, the running state of the controller and the execution state of the vehicle actuator;
[0133] The third acquisition unit is used to implement data collection according to multiple target monitoring items of the driver monitoring category, and obtain monitoring data of the driver monitoring category including the driver's sleepiness state and driving concentration score.
[0134] In an optional embodiment, the control device further includes:
[0135] The first determination module is used to determine the current risk weight of each category of monitoring risk at the driving level according to the driving level of the vehicle and the second corresponding relationship, wherein the second corresponding relationship is the relationship between different driving levels and the corresponding risk weights of each monitoring category.
[0136] In an optional embodiment, the multiple monitoring categories include an environment monitoring category, a vehicle monitoring category, and a driver monitoring category; and the control device further includes:
[0137] A first updating module, used for updating a first risk weight of an environmental monitoring category according to a driving position of the vehicle;
[0138] A second updating module, used for updating a second risk weight of the vehicle monitoring category according to the accumulated mileage of the vehicle;
[0139] The third updating module is used to update the third risk weight of the driver monitoring category according to the driver's single cumulative driving time.
[0140] In an optional embodiment, the control device further includes:
[0141] The second determination module is used to determine the current risk weight of each category of monitoring risk at the driving level according to the driver's cumulative task time for executing the driving task and the third corresponding relationship, wherein the third corresponding relationship is the relationship between the cumulative time of different tasks and the corresponding risk weight of each monitoring category.
[0142] In an optional embodiment, the processing module includes:
[0143] A first output submodule is used to output a first prompt instruction for implementing a downgrade process of the driving level, wherein the first prompt instruction is a takeover prompt instruction of a first intensity level to the driver in an audio manner and a visual manner;
[0144] The control submodule is used to stop prompting the driver to take over when receiving a takeover feedback signal from the driver within a preset time;
[0145] The second output submodule is used to output a second prompt instruction if no takeover feedback signal from the driver is received within a preset time, wherein the second prompt instruction is a takeover prompt instruction of a second intensity level to the driver including tactile, sound and visual methods, and the prompt intensity of the second intensity level is greater than the prompt intensity of the first intensity level.
[0146] Based on the same technical concept as the control method, an embodiment of the present invention also provides an electronic device, including a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of any one of the control methods.
[0147] Based on the same technical concept as the control method, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the control methods are implemented.
[0148] The technical solution provided in the embodiments of the present invention has at least the following technical effects or advantages:
[0149] After the vehicle turns on the automatic driving function, the monitoring data of multiple monitoring categories of driving risks associated with the vehicle's driving level are obtained. The driving level is the different levels of the vehicle based on the degree of automatic driving control; the category monitoring risk of each monitoring category is obtained according to the monitoring data of each monitoring category, and the automatic driving risk of the vehicle at the driving level is obtained according to each category monitoring risk and the corresponding risk weight; when the automatic driving risk is greater than the preset risk threshold, the driving level of the vehicle is downgraded. This solution implements automatic driving monitoring from multiple monitoring categories, and reasonably configures the risk of each category monitoring through risk weights, so that the vehicle can select the appropriate risk assessment strategy at different automatic driving levels, and realizes the accurate assessment of the automatic driving risk of the vehicle at the driving level, and then can accurately downgrade the driving level of the automatic driving vehicle.
[0150] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0151] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (modules, systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0152] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0154] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for controlling automatic driving of a vehicle, characterized in that: The method comprises: After the vehicle starts the automatic driving function, monitoring data of multiple monitoring categories of driving risks associated with the vehicle at the driving level, wherein the driving level is different levels of the vehicle divided based on the degree of automatic driving control; According to the monitoring data of each monitoring category, the category monitoring risk of each monitoring category is obtained, wherein each monitoring category includes at least one monitoring data of the category to which it belongs; Obtaining the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight; When the autonomous driving risk is greater than a preset risk threshold, the driving level of the vehicle is downgraded.
2. The method for controlling automatic vehicle driving according to claim 1, characterized in that: The obtaining of monitoring data of multiple monitoring categories of driving risks associated with the vehicle at the driving level includes: Determining a target monitoring item of each monitoring category of the driving level according to the driving level of the vehicle and the first corresponding relationship, wherein the first corresponding relationship is a relationship between different driving levels and corresponding monitoring items of each monitoring category; Data collection is performed according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories of the vehicle at the driving level.
3. The method for controlling the automatic driving of a vehicle according to claim 2, characterized in that: The driving level is L3 driving level; the data collection is performed according to the target monitoring items of each monitoring category to obtain monitoring data of multiple monitoring categories of the vehicle at the driving level, including: Implement data collection according to multiple target monitoring items of the environmental monitoring category, and obtain monitoring data of the environmental monitoring category including rainfall, driving road type, driving weather, driving lighting and driving position; Implementing data collection according to multiple target monitoring items of the vehicle monitoring category, obtaining monitoring data of the vehicle monitoring type including the sensing state of the environmental sensor, the running speed of the control software, the running state of the controller and the execution state of the vehicle actuator; Data collection is performed according to multiple target monitoring items of the driver monitoring category, and the monitoring data of the driver monitoring category obtained includes the driver's sleepiness state and driving concentration score.
4. The method for controlling automatic vehicle driving according to claim 1, characterized in that: Before obtaining the autonomous driving risk of the vehicle at the driving level according to each category of monitoring risk and the corresponding risk weight, the method further includes: According to the driving level of the vehicle and the second corresponding relationship, the current risk weight of each category of monitoring risk at the driving level is determined, wherein the second corresponding relationship is the relationship between different driving levels and the corresponding risk weights of each monitoring category.
5. The method for controlling the automatic driving of a vehicle according to claim 4, characterized in that: The multiple monitoring categories include an environment monitoring category, a vehicle monitoring category, and a driver monitoring category; after determining the current risk weight of each category of monitoring risk at the driving level, the method further includes: updating the first risk weight of the environmental monitoring category according to the driving position of the vehicle; updating the second risk weight of the vehicle monitoring category according to the accumulated mileage of the vehicle; The third risk weight of the driver monitoring category is updated according to the driver's single cumulative driving time.
6. The method for controlling the automatic driving of a vehicle according to claim 1, characterized in that: Before obtaining the autonomous driving risk of the vehicle at the driving level according to each category of monitoring risk and the corresponding risk weight, the method further includes: According to the driver's cumulative task time for executing the driving task and the third corresponding relationship, the current risk weight of each category of monitoring risk at the driving level is determined, wherein the third corresponding relationship is the relationship between the cumulative time of different tasks and the corresponding risk weight of each monitoring category.
7. The method for controlling automatic vehicle driving according to claim 1, characterized in that: The step of downgrading the driving level of the vehicle includes: Outputting a first prompt instruction for implementing a driving level downgrade process, wherein the first prompt instruction is a takeover prompt instruction of a first intensity level to the driver in an audio and visual manner; If a takeover feedback signal from the driver is received within a preset time, then the takeover prompt to the driver is stopped; If no takeover feedback signal from the driver is received within the preset time, a second prompt instruction is output, wherein the second prompt instruction is a takeover prompt instruction of a second intensity level to the driver including tactile, sound and visual methods, and the prompt intensity of the second intensity level is greater than the prompt intensity of the first intensity level.
8. A control device for automatic vehicle driving, characterized in that: The device comprises: an acquisition module, configured to acquire monitoring data of multiple monitoring categories of driving risks associated with the vehicle at a driving level after the vehicle turns on the automatic driving function, wherein the driving level is a different level divided by the vehicle based on the degree of automatic driving control; A first obtaining module is used to obtain the category monitoring risk of each monitoring category according to the monitoring data of each monitoring category, wherein each monitoring category includes at least one monitoring data of the category to which it belongs; A second obtaining module is used to obtain the autonomous driving risk of the vehicle at the driving level according to each category monitoring risk and the corresponding risk weight; A processing module is used to downgrade the driving level of the vehicle when the autonomous driving risk is greater than a preset risk threshold.
9. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is coupled to the processor and stores instructions, and when the instructions are executed by the processor, the electronic device executes the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Intelligent auxiliary driving vehicle-mounted terminal for large vehicle
CN120482052A
Autonomous-driving intervention determination method and system based on multi-point tactile sensing
WO2026223079A1
