Control method, device and equipment of auxiliary driving system and storage medium

Abstract

The present disclosure provides a control method and device of an assisted driving system, equipment and a storage medium, and belongs to the field of vehicle control. The method comprises: obtaining target data of a target device in a vehicle, the target data being data affecting the remaining service life of the target device; predicting the remaining service life of the target device according to the target data; and in response to the remaining service life of the target device being less than or equal to a first threshold, closing the control authority of the assisted driving system on the target device. This is conducive to improving the safety factor of the assisted driving system and thus improving the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of vehicles, and in particular to a control method, apparatus, device, and storage medium for an assisted driving system. Background Technology

[0002] Advanced driver assistance systems (ADAS) can take over the control of relevant vehicle components and perform automatic control based on environmental information such as traffic lights and the distance between the vehicle and surrounding vehicles. For example, when the system detects that the vehicle is too close to an obstacle, it can take over the braking function and automatically apply the brakes. However, current ADAS systems still have many safety hazards and are not highly trusted by users. Therefore, it is necessary to properly control ADAS systems to reduce safety hazards and increase user trust in them.

[0003] In related technologies, methods for controlling assisted driving systems include: collecting external environmental data; evaluating whether the behavior of the assisted driving system is inconsistent with the actual situation based on the external environmental data; and disabling the corresponding functions of the assisted driving system if the behavior of the assisted driving system is inconsistent with the actual situation.

[0004] However, the above methods can only reduce safety hazards caused by the behavior of the driver assistance system not conforming to the actual situation. Even when the behavior of the driver assistance system conforms to the actual situation, safety hazards may still exist. Summary of the Invention

[0005] This disclosure provides a control method, apparatus, device, and storage medium for a driver assistance system, which can reduce safety hazards in driver assistance systems. The technical solution includes at least the following:

[0006] In a first aspect, a control method for an assisted driving system is provided, comprising: acquiring target data of a target device in a vehicle, the target data being data affecting the remaining service life of the target device; predicting the remaining service life of the target device based on the target data; and, in response to the remaining service life of the target device being less than or equal to a first threshold, disabling the assisted driving system's control authority over the target device.

[0007] Optionally, the target device includes brake pads, and the target data includes braking pressure, brake pad thickness, braking temperature, braking time, braking deceleration, the distance between the vehicle seat and the road surface during the braking time, the brake pedal depth, and braking torque. Predicting the remaining service life of the target device based on the target data includes: inputting the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration into a brake pad prediction model to obtain a first prediction result. The brake pad prediction model characterizes the correspondence between the remaining service life of the brake pad and the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration; determining a correction coefficient based on the distance between the vehicle seat and the road surface during the braking time, the brake pedal depth, and the braking torque; and correcting the first prediction result using the correction coefficient to obtain a second prediction result, where the second prediction result is the predicted remaining service life of the brake pad.

[0008] Optionally, determining the correction coefficient based on the distance between the vehicle base and the road surface during the braking time, the brake pedal depth, and the braking torque includes: obtaining a road surface bumpiness coefficient based on the change in the distance between the vehicle base and the road surface during the braking time; and determining the correction coefficient based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque.

[0009] Optionally, determining the correction coefficient based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque includes: determining a first correction coefficient based on the brake pedal depth, wherein the first correction coefficient is less than 1 when the brake pedal depth is greater than a third threshold; determining a second correction coefficient based on the braking torque, wherein the second correction coefficient is less than 1 when the braking torque is greater than a fourth threshold; and multiplying the first correction coefficient, the second correction coefficient, and the road surface bumpiness coefficient to obtain the correction coefficient.

[0010] Optionally, the method further includes: optimizing the initial model using an optimization algorithm to obtain the brake pad prediction model, wherein the initial model is as follows:

[0011]

[0012] Wherein, S is the predicted remaining service life of the brake pad, W0 is the brake pad thickness, W1 is the brake pad thickness threshold, the brake pad thickness threshold is used to indicate the brake pad thickness when the brake pad is damaged, t is the braking time, and ΔW is the thickness of the brake pad worn within time t.

[0013] Optionally, the target device includes an exhaust fan, and the target data includes exhaust fan temperature, exhaust fan speed, and exhaust fan operating current. Predicting the remaining service life of the target device based on the target data includes: obtaining an exhaust fan correspondence, which indicates the relationship between the exhaust fan temperature, operating current, and speed; determining the expected speed based on the exhaust fan correspondence, the exhaust fan operating current, and the exhaust fan temperature; and determining the remaining service life of the exhaust fan based on the exhaust fan speed and the expected speed.

[0014] Optionally, after disabling the control authority of the driver assistance system over the target device in response to the remaining service life of the target device being less than or equal to a first threshold, the method further includes: outputting a prompt message, the prompt message being used to indicate that the control authority of the driver assistance system over the target device is in a disabled state and that the remaining service life of the target device is also disabled.

[0015] Secondly, a control device for an assisted driving system is also provided, including: a data acquisition module, a prediction module, and a control module.

[0016] The data acquisition module acquires target data of a target device in the vehicle, wherein the target data is data affecting the remaining service life of the target device. The prediction module predicts the remaining service life of the target device based on the target data. The control module disables the control authority of the driver assistance system over the target device in response to the remaining service life of the target device being less than or equal to a first threshold.

[0017] Optionally, the target device includes brake pads, and the target data includes braking pressure, brake pad thickness, braking temperature, braking time, braking deceleration, the distance between the vehicle seat and the road surface during the braking time, the brake pedal depth, and braking torque. The prediction module is further configured to input the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration into a brake pad prediction model to obtain a first prediction result. The brake pad prediction model is used to characterize the correspondence between the remaining service life of the brake pad and the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration. Based on the distance between the vehicle seat and the road surface during the braking time, the brake pedal depth, and the braking torque, a correction coefficient is determined. The first prediction result is corrected using the correction coefficient to obtain a second prediction result, which is the predicted remaining service life of the brake pad.

[0018] Optionally, the prediction module is further configured to determine the road surface bumpiness coefficient based on the change in distance between the vehicle base and the road surface during the braking time; and to determine the correction coefficient based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque.

[0019] Optionally, the prediction module is further configured to determine a first correction coefficient based on the brake pedal depth, wherein the first correction coefficient is less than 1 when the brake pedal depth is greater than a third threshold; determine a second correction coefficient based on the braking torque, wherein the second correction coefficient is less than 1 when the braking torque is greater than a fourth threshold; and multiply the first correction coefficient, the second correction coefficient, and the road surface bumpiness coefficient to obtain the correction coefficient.

[0020] Optionally, the device further includes: a prediction model determination module, used to optimize an initial model using an optimization algorithm to obtain the brake pad prediction model, wherein the initial model is as follows:

[0021]

[0022] Wherein, S is the predicted remaining service life of the brake pad, W0 is the brake pad thickness, W1 is the brake pad thickness threshold, the brake pad thickness threshold is used to indicate the brake pad thickness when the brake pad is damaged, t is the braking time, and ΔW is the thickness of the brake pad worn within time t.

[0023] Optionally, the target device includes an exhaust fan, and the target data includes exhaust fan temperature, exhaust fan speed, and exhaust fan operating current. The prediction module is further configured to: obtain an exhaust fan correspondence, which indicates the relationship between the exhaust fan temperature, operating current, and speed; determine the expected speed based on the exhaust fan correspondence, the exhaust fan operating current, and the exhaust fan temperature; and determine the remaining service life of the exhaust fan based on the exhaust fan speed and the expected speed.

[0024] Optionally, the device further includes: a prompting module for outputting prompting information, the prompting information being used to indicate that the driver assistance system's control over the target device is in a closed state and that the target device has at least one of the following: the remaining service life of the target device.

[0025] Thirdly, a computer device is also provided, comprising: a memory and a processor, wherein the memory stores at least one computer program, the at least one computer program being loaded and executed by the processor to perform the control method of the assisted driving system described in the above embodiments.

[0026] Fourthly, a computer-readable storage medium is also provided, wherein at least one computer program is stored in the computer-readable storage medium, the at least one computer program being loaded and executed by a processor to perform the control method of the assisted driving system described in the above embodiments.

[0027] The beneficial effects of the technical solutions provided in this disclosure include at least the following:

[0028] By acquiring target data of the target device in the vehicle, and predicting the remaining lifespan of the target device based on this data, the driver assistance system (ADAS) disables its control over the target device when the remaining lifespan is less than or equal to a first threshold. This approach prevents the ADAS from taking over the aging target device (remaining lifespan less than or equal to the first threshold), thus avoiding potential safety hazards. Furthermore, while the ADAS's takeover of the target device may be realistic, continued control by the aging device would pose a safety risk. Disabling the ADAS at this point reduces these potential safety risks, improving its overall safety. This increased safety also enhances user satisfaction with the ADAS and the vehicle, ultimately improving the user experience. Attached Figure Description

[0029] Figure 1 A flowchart illustrating a control method for an assisted driving system provided in an exemplary embodiment of this disclosure is shown.

[0030] Figure 2 A flowchart is shown for a control method of an assisted driving system provided in another exemplary embodiment of this disclosure;

[0031] Figure 3 A flowchart is shown for a control method of an assisted driving system provided in another exemplary embodiment of this disclosure;

[0032] Figure 4 This illustration shows a schematic diagram of the structure of a control device for an assisted driving system provided in an exemplary embodiment of the present disclosure;

[0033] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation

[0034] Unless otherwise defined, the technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure pertains. The terms “first,” “second,” “third,” and similar terms used in this patent application specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms “an” or “a” and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms “comprising” or “including” and similar terms mean that the elements or objects preceding “comprising” or “including” encompass the elements or objects listed following “comprising” or “including” and their equivalents, but do not exclude other elements or objects.

[0035] To make the objectives, technical solutions, and advantages of this disclosure clearer, the embodiments of this disclosure will be described in further detail below with reference to the accompanying drawings.

[0036] Advanced driver assistance systems (ADAS) utilize various sensors installed in the vehicle to collect environmental data both inside and outside the vehicle. This allows for the identification of static and dynamic objects, enabling the driver to detect potential hazards as quickly as possible. In some situations, ADAS can even take over control of in-vehicle devices, improving driving safety. For example, using sensors, ADAS can collect external environmental data and, when it detects the vehicle is close to an obstacle, take over the braking system and apply the brakes actively. Furthermore, ADAS can adjust the exhaust fan speed based on the vehicle's speed; for instance, increasing the exhaust fan speed at higher speeds improves emissions efficiency and vehicle performance.

[0037] Figure 1 A flowchart illustrating a control method for an assisted driving system provided in an exemplary embodiment of this disclosure is shown. This method can be executed by an onboard device of the vehicle, which can be an onboard computer, a main control unit (MCU), or a functional module integrated on the system motherboard, etc. See also... Figure 1 The method includes the following steps:

[0038] In step 101, target data of the target device in the vehicle is acquired.

[0039] Optionally, the target device refers to a device that the driver assistance system has control over, such as brake pads or an exhaust fan; this disclosure does not limit this. Target data refers to data affecting the remaining service life of the target device.

[0040] In step 102, the remaining service life of the target device is predicted based on the target data.

[0041] In step 103, in response to the remaining useful life of the target device being less than or equal to a first threshold, the control authority of the driver assistance system over the target device is disabled.

[0042] In this embodiment, by acquiring target data of a target device in the vehicle and predicting the remaining lifespan of the target device based on the target data, the driver assistance system (ADAS) disables its control over the target device when the remaining lifespan of the target device is less than or equal to a first threshold. This addresses two issues: firstly, it prevents the ADAS from taking over the aging target device (when its remaining lifespan is less than or equal to the first threshold), thus avoiding potential safety hazards. Secondly, while the ADAS's behavior of taking over the target device still aligns with reality, the target device is already aging, and continued control would pose a safety risk. Disabling the ADAS at this point reduces the safety risks associated with its behavior aligning with reality, thereby improving the safety coefficient of the ADAS. Improved safety also increases user satisfaction with the ADAS and the vehicle, ultimately enhancing the user experience.

[0043] Figure 2 A flowchart of a control method for an assisted driving system provided in another exemplary embodiment of the present disclosure is shown. This method can be executed by an onboard device of a vehicle, which can be an onboard computer, a main control unit (MCU), or a functional module integrated on a system motherboard, etc. Figure 2 In this paper, the method of the present disclosure will be illustrated by taking the target device as a brake pad as an example.

[0044] See Figure 2 The method includes the following steps:

[0045] In step 201, the status of the control authority of the driver assistance system over the target device is obtained.

[0046] The status of the driver assistance system's control authority over the target device includes on and off.

[0047] For details regarding the target device, please refer to step 101 above, which will not be elaborated here.

[0048] If the driver assistance system's control permission over the target device is enabled, it means that the driver assistance system can control the target device, and step 202 is executed. If the driver assistance system's control permission over the target device is disabled, it means that the driver assistance system cannot control the target device, and the current process is exited.

[0049] In some embodiments, steps 202-205 continue to be executed regardless of whether the driver assistance system's control over the target device is enabled or disabled. In this case, if the driver assistance system's control over the target device is disabled, it is not necessary to disable the driver assistance system's control over the target device again when executing step 204; step 205 can be executed directly. This allows for the prediction of the target device's remaining lifespan and the notification of the user when the predicted remaining lifespan is insufficient, enabling the user to promptly understand the remaining lifespan of the target device and replace it in a timely manner, thus improving the user experience.

[0050] In step 202, target data of the target device in the vehicle is acquired.

[0051] In this embodiment, the driver assistance system has the function of taking over the braking from the brake pads based on the distance between the vehicle and an obstacle. If the driver assistance system detects that the vehicle is close to an obstacle, it will take over the braking from the brake pads and actively apply the brakes. In such cases, the behavior of the driver assistance system is correct. However, if the brake pads are about to fail, and the driver assistance system continues to control the damaged brake pads, brake failure may occur, resulting in slippage between the brake pads and the brake disc, leading to serious safety problems. In this situation, it is necessary to control the control authority of the driver assistance system over the brake pads, preventing the driver assistance system from continuing to actively control the brake pads and returning control of the brake pads to the driver. Upon being aware of the situation, the driver can control the braking intensity (e.g., increasing the depth of the brake pedal) to avoid safety problems. Furthermore, if the driver is aware that the brake pads are about to fail, they can replace the brake pads in time, further reducing safety issues. Therefore, in this embodiment, the target device is the brake pads.

[0052] Target data indicates information that affects the remaining service life of a target device. For brake pads, target data includes brake pressure, brake pad thickness, brake temperature, braking time, braking deceleration, the distance between the vehicle seat and the road surface during braking, brake pedal depth, and braking torque. In other words, these target data can affect the remaining service life of brake pads in various ways, causing brake pad wear.

[0053] Braking pressure refers to the pressure of the brake pump during hydraulic braking, which is also the pressure of the hydraulic oil. This pressure can be obtained through a pressure sensor in the hydraulic system. When a vehicle brakes, braking pressure is a crucial factor affecting the frictional force applied to the brake pads. Higher braking pressure results in greater braking force, which in turn increases the frictional force on the brake pads. Greater friction leads to easier wear of the brake pads and a faster reduction in their lifespan.

[0054] Brake pad thickness can be obtained using a thickness sensor located near the brake pads. Braking temperature, the temperature between the brake pads and the brake disc during braking, can be obtained using a temperature sensor located near the brake pads. For each of the four wheels of a vehicle, there is at least one temperature sensor around the brake pads of each wheel. Braking temperature affects the remaining lifespan of the brake pads. On one hand, during braking, the friction between the brake pads and the brake disc generates a large amount of heat. Therefore, braking temperature can also reflect the magnitude of the frictional force on the brake pads; the higher the braking temperature, the greater the frictional force, and the shorter the remaining lifespan of the brake pads. On the other hand, since brake pads are made of composite chemical materials, if the temperature of the brake pads increases, the high temperature will affect the performance of the composite chemical materials, leading to oxidation and softening of the material surface. Therefore, under the same frictional force, the remaining lifespan of brake pads at high temperatures will be shorter than that at low temperatures. Thus, the higher the temperature of the brake pads during braking (compared to the temperature of the brake pads when not braking), the shorter the remaining lifespan of the brake pads.

[0055] In some embodiments, since the vehicle has four wheels, each with a brake pad, each wheel may have a different brake pad thickness and braking temperature. Therefore, steps 203-205 are performed once for each wheel's brake pad thickness and braking temperature, thereby improving the accuracy of the prediction results and further reducing safety hazards of the driver assistance system.

[0056] In other embodiments, the brake pad thickness is the average thickness of the brake pads of the four wheels, and the braking temperature is the average temperature between the brake pads and the brake discs of the four wheels during braking. Thus, when predicting the remaining service life of the brake pads, steps 203-205 only need to be performed once based on the average thickness of the brake pads of the four wheels and the average temperature between the brake pads and the brake discs of the four wheels during braking, thereby improving the prediction efficiency. Furthermore, the average thickness of the brake pads of the four wheels and the average temperature between the brake pads and the brake discs of the four wheels during braking can also reflect the current thickness of the vehicle's brake pads well without excessive deviation.

[0057] In some embodiments, the brake pad thickness includes the thickness of the front wheel brake pads and the thickness of the rear wheel brake pads, wherein the front wheel brake pad thickness is the average of the thicknesses of the two front wheel brake pads of the vehicle, and the rear wheel brake pad thickness is the average of the thicknesses of the two rear wheel brake pads of the vehicle. Since braking of the vehicle actually involves both rear wheel braking (handbrake braking) and four-wheel braking (brake pedal braking), the brake pad thicknesses of the two front wheels and the two rear wheels may differ. For the same reason, the braking temperature also includes the front wheel braking temperature and the rear wheel braking temperature, where the front wheel braking temperature is the average temperature between the brake pads and brake discs when the two front wheels are braking, and the rear wheel braking temperature is the average temperature between the brake pads and brake discs when the two rear wheels are braking.

[0058] In this case, steps 203-205 are performed once for the front wheel brake pad thickness and front wheel brake temperature; steps 203-205 are performed once for the rear wheel brake pad thickness and rear wheel brake temperature, thereby improving prediction efficiency and accuracy.

[0059] Braking time, or the duration of a single braking action, is calculated by the difference between the start and end times of a single braking operation. When the braking system is in operation, the onboard equipment records the start and end times of each braking action and stores them in memory. By querying the memory for the start and end times of a single braking operation, the braking time can be calculated.

[0060] Braking time reflects the duration of a single braking action, that is, the length of time the brake pads are subjected to frictional force during a single braking event. A longer braking time indicates a longer period of frictional force on the brake pads. For the same frictional force, if the total time the brake pads are subjected to frictional force is the same (e.g., 30 seconds), then the remaining lifespan of the brake pads will obviously differ depending on whether the braking is performed 10 times, each time for 3 seconds, or a single braking event lasting 30 seconds. A longer single braking time results in the brake pads being under frictional force for an extended period, causing the brake pad temperature to rise and thus reducing its remaining lifespan. Conversely, multiple short braking events, due to their shorter duration, result in a brief temperature increase followed by cooling down as subsequent braking is not continuous, thus having a smaller impact on the brake pad's lifespan.

[0061] Braking deceleration reflects the rate at which a vehicle's speed decreases during braking. In some examples, engine speed can be obtained using a speed sensor and converted into vehicle speed. The braking deceleration can then be calculated based on the vehicle speed at two adjacent moments during braking and the time interval between those moments. For instance, braking deceleration can be calculated based on the vehicle speed at the start and end of braking.

[0062] When a vehicle brakes from the same speed to a stop, the greater the braking deceleration, the greater the frictional force on the brake pads; conversely, the smaller the braking deceleration, the smaller the frictional force. Greater friction leads to easier wear of the brake pads and a faster reduction in their lifespan. Therefore, greater braking deceleration has a greater impact on the lifespan of the brake pads.

[0063] The distance between the vehicle base and the road surface is obtained in real time by a distance sensor mounted on the vehicle base.

[0064] Brake pedal depth, or brake pedal travel, is obtained through a potentiometer mounted on the brake pedal.

[0065] The braking torque is calculated using the following formula (2.1):

[0066] M-2FiηuR(2.1)

[0067] Where M is the braking torque, F is the air chamber thrust, i is the vehicle lever ratio, η is the vehicle working efficiency, μ is the friction coefficient of the brake pad, and R is the braking radius of the brake pad.

[0068] F can be obtained through a pressure sensor in the vehicle cylinder. i, η, and μ are all vehicle-specific parameters, which can be obtained from the vehicle's instruction manual. This disclosure does not limit the method of obtaining i, η, and μ. In this disclosure, R is the outer radius of the sector-shaped brake pad. In other embodiments, R is the inner radius of the sector-shaped brake pad, or R is the average of the sum of the inner and outer radii of the sector-shaped brake pad; this disclosure does not limit this.

[0069] Optionally, step 202 can be performed periodically. In this embodiment, the period ranges from 0.5 to 5 seconds, for example, it can be 0.5s, 1s, 3s, or 5s. The period interval for acquiring the target data should not be too long; if the period is too long, the data acquisition interval will be too long, resulting in low accuracy.

[0070] Optionally, the acquired target data is stored in the on-board device's memory, and the memory stores the acquisition time of each target data. When storing the target data in the memory, the target data is stored in chronological order, thus facilitating the acquisition of target data at different times as needed.

[0071] In step 203, the remaining service life of the target device is predicted based on the target data.

[0072] In some embodiments, step 203 is performed after each vehicle braking, thereby accurately predicting the remaining service life of the target device.

[0073] In other embodiments, step 203 can be performed periodically. In the embodiments of this disclosure, the period ranges from 0.5 to 3 days, for example, it can be 0.5 days (12 hours), 1 day, 2 days, or 3 days. The period for executing step 203 should not be too long or too short. Since the probability of a sudden change in the remaining service life of the target device in the short term is small, the period for executing step 203 should not be less than 0.5 days, otherwise it will lead to excessive repetitive calculations and waste of computing resources. At the same time, if the period for executing step 203 is too long, for example, longer than 3 days, it will lead to the inability to predict the remaining service life of the target device in a timely manner, which may easily cause safety hazards.

[0074] Optionally, in some embodiments, there are multiple target devices in the vehicle. For each target device, before performing step 203, the method further includes: determining a target prediction model based on the target device and target data.

[0075] The target prediction model is a prediction model corresponding to the target device and target data. Different target devices and target data have different target prediction models, which can accurately predict the remaining service life of different target devices.

[0076] In this embodiment of the disclosure, the target device is a brake pad, so the prediction model is a brake pad prediction model.

[0077] In this case, the method includes the following three steps:

[0078] The first step is to input the braking pressure, brake pad thickness, braking temperature, braking time, and braking deceleration into the brake pad prediction model to obtain the first prediction result.

[0079] The brake pad prediction model is used to characterize the relationship between the remaining service life of the brake pad and the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration.

[0080] The second step is to determine the correction coefficient based on the distance between the vehicle base and the road surface, the brake pedal depth, and the braking torque during the braking time.

[0081] The second step may include: obtaining a road surface bumpiness coefficient based on the change in distance between the vehicle base and the road surface during the braking time; and determining a correction coefficient based on the road surface bumpiness coefficient, brake pedal depth, and braking torque.

[0082] Optionally, the road surface bumpiness coefficient is obtained based on the change in distance between the vehicle base and the road surface during the braking time, including: if the difference between the distance between the vehicle base and the road surface in two unit time intervals during the braking time is greater than a second threshold, then the road surface bumpiness coefficient is less than 1; or, if the difference between the distance between the vehicle base and the road surface in two unit time intervals during the braking time is less than or equal to the second threshold, then the road surface bumpiness coefficient is 1. The two unit time intervals during the braking time can be any two non-overlapping unit time intervals within the braking time, such as two adjacent unit time intervals, or two unit time intervals separated by a certain duration (e.g., 1 second).

[0083] If the difference is greater than the second threshold, it indicates that the road surface is relatively bumpy. Braking on a bumpy road may reduce the remaining service life of the target device. Therefore, when the difference is greater than the second threshold, the road surface bumpiness coefficient is set to less than 1.

[0084] Optionally, the length of a unit time can be 0.5 to 2 seconds, for example, 0.5 seconds, 1 second, or 2 seconds. Two unit times within the braking time can be two adjacent unit times. When using the distance between the vehicle's chassis and the road surface between two adjacent unit times to characterize the degree of road bumps, the length of the two adjacent unit times should not be too long. Since road bumps may be instantaneous during vehicle movement, if the time is too long, the difference between the distances between the vehicle's chassis and the road surface between two adjacent unit times may not accurately reflect the degree of road bumps.

[0085] Optionally, the value range of the second threshold is 3cm to 6cm, for example, it can be 3cm, 4cm, 5cm or 6cm.

[0086] Optionally, when the difference is greater than the second threshold, the road surface bumpiness coefficient decreases as the difference increases.

[0087] For example, in the initial state, the road surface bumpiness coefficient is 1. For every 1cm increase in the difference greater than the second threshold, the road surface bumpiness coefficient is reduced by X (X can be equal to 0.01 or 0.02, etc.). If the difference greater than the second threshold is not an integer, the decimal part is rounded off before calculating the road surface bumpiness coefficient.

[0088] For example, the braking time is 1 second, the second threshold is 3 cm, and X equals 0.01. Two adjacent time intervals within the braking time can be 0.5 seconds before and 0.5 seconds after this 1 second. In the first 0.5 seconds, the distance between the vehicle's base and the road surface is 25 cm, and in the last 0.5 seconds, the distance is 30 cm. Therefore, it can be determined that the difference in distance between the vehicle's base and the road surface between two adjacent time intervals within the braking time is 5 cm, which is greater than the second threshold. Thus, the road bumpiness coefficient is less than 1, and is 0.98.

[0089] The road surface bumpiness coefficient can effectively reflect the degree of road surface bumpiness during braking, and the first prediction result can be corrected based on the road surface bumpiness coefficient, thereby improving the accuracy of the prediction result.

[0090] Optionally, a correction coefficient is determined based on the road surface roughness coefficient, brake pedal depth, and braking torque, including: determining a first correction coefficient based on the brake pedal depth, wherein the first correction coefficient is less than 1 when the brake pedal depth is greater than a third threshold, and equal to 1 when the brake pedal depth is less than or equal to the third threshold; determining a second correction coefficient based on the braking torque, wherein the second correction coefficient is less than 1 when the braking torque is greater than a fourth threshold, and equal to 1 when the braking torque is less than or equal to the fourth threshold; and multiplying the first correction coefficient, the second correction coefficient, and the road surface roughness coefficient to obtain the correction coefficient.

[0091] Brake pedal depth and braking torque also affect the remaining lifespan of brake pads. For example, when the brake pedal depth is greater than the third threshold, it means that the brake pedal depth is too deep, exceeding the normal braking depth, which falls within the range of emergency braking. Emergency braking may affect the remaining lifespan of brake pads (e.g., reduce the remaining lifespan of brake pads).

[0092] The same principle applies when the braking torque exceeds the fourth threshold. Excessive braking torque means excessive braking force, which in turn means the brake pads will experience excessive friction. Therefore, the braking torque will also affect the remaining service life of the brake pads (i.e., reduce their remaining service life). Thus, when the brake pedal depth exceeds the third threshold, the first correction coefficient will be less than 1, and when the braking torque exceeds the fourth threshold, the second correction coefficient will also be less than 1. This corrects the first prediction result from the brake pad model (i.e., reduces the predicted remaining service life in the first prediction result), making the predicted remaining service life of the brake pads more accurate.

[0093] Optionally, when the brake pedal depth is greater than the third threshold, the first correction coefficient starts from 1 and decreases as the difference between the brake pedal depth and the third threshold increases. When the brake pedal depth is less than or equal to the third threshold, the first correction coefficient is 1.

[0094] Optionally, the value of the third threshold is in the range of 9 to 12 cm, for example, it can be 9 cm, 10 cm, 11 cm or 12 cm.

[0095] For example, for every 1cm increase in the brake pedal depth beyond the third threshold, the first correction coefficient is reduced by Y (Y can be equal to 0.02 or 0.03, etc., and Y is greater than X and Z). If the portion of the brake pedal depth beyond the third threshold is not an integer, the decimal part is rounded off before calculating the second correction coefficient.

[0096] Optionally, when the braking torque is greater than the fourth threshold, the second correction coefficient decreases from 1 as the difference increases.

[0097] Optionally, the value of the fourth threshold is in the range of 2500 to 3000 N*m, for example, it can be 2500 N*m, 2750 N*m or 3000 N*m.

[0098] For example, for every 100 N*m increase in the portion of the braking torque that is greater than the fourth threshold, the second correction coefficient is reduced by Z (Z can be equal to 0.01 or 0.02, etc.). If the portion of the difference that is greater than the fourth threshold is not an integer multiple of 100, the remainder is rounded off before the third correction coefficient is calculated.

[0099] For example, if the first correction factor is Y equal to 0.9, the second correction factor is Z equal to 0.99, and the road surface bumpiness factor is X equal to 1, then the correction factor for the first prediction result is 0.9 * 0.99 * 1 = 0.891.

[0100] The degree of road bumps, brake pedal depth, and braking torque are not affected by the vehicle's own performance, but rather reflect the external environment or different user habits. Therefore, using these three factors as correction coefficients to correct the first prediction result can make the predicted remaining service life of the brake pads more accurate.

[0101] The third step is to correct the first prediction result using a correction factor to obtain the second prediction result, which is the predicted remaining service life of the brake pad.

[0102] Optionally, a correction factor is used to correct the first prediction result, that is, the correction factor is multiplied by the first prediction result, and the resulting second prediction result is the predicted remaining service life of the brake pad.

[0103] In actual vehicle operation, the remaining service life of brake pads is also related to the degree of road bumps, brake pedal depth, and braking torque. When the degree of road bumps, brake pedal depth, and braking torque are too high, the remaining service life of the brake pads will be reduced. Therefore, correction coefficients for the first prediction result can be determined based on the degree of road bumps, brake pedal depth, and braking torque. Among these, since brake pedal depth has the greatest impact on the remaining service life of brake pads, the corresponding first correction coefficient decreases the most as the difference between the brake pedal depth and the third threshold increases, thereby improving the reliability of the correction coefficient.

[0104] In this embodiment, steps one through three are all performed in the vehicle. In some embodiments, steps one through three are performed on a cloud server, thereby reducing the computational burden on the in-vehicle equipment.

[0105] When steps one through three are executed on the cloud server, before step 203, the method further includes sending target data to the cloud server. This allows the server to predict the remaining lifespan of the target device based on the target data. Furthermore, after the server predicts the remaining lifespan of the target device, it also needs to send the predicted remaining lifespan of the target device to the vehicle. Accordingly, the vehicle receives the remaining lifespan of the target device.

[0106] When predicting the remaining lifespan of a target device using a server, the computational requirements of the vehicle terminal can be reduced because the server is capable of performing a greater amount of calculations.

[0107] In one possible implementation, before inputting braking pressure, brake pad thickness, braking temperature, braking time, and braking deceleration into the brake pad prediction model, a brake pad prediction model also needs to be obtained. Therefore, the method includes the following two steps:

[0108] The first step is to determine the initial model based on the brake pad wear formula.

[0109] The initial model is shown below:

[0110]

[0111]

[0112] Formula (2.3) is the brake pad wear formula, where P is the braking pressure, V is the braking deceleration, t is the braking time, T is the braking temperature, T0 is the temperature of the brake pad before braking, A, a, b, c and n are all constants, E is the brake pad activation energy constant, R is the gas molar constant, and ΔW is the thickness of the brake pad worn in time t.

[0113] For details regarding P, V, t, and T, please refer to step 202 above; further details are omitted here.

[0114] The temperature T0 of the brake pads before braking is similar to T, and is obtained by a temperature sensor located around the brake pads.

[0115] The brake pad activation energy constant E and the gas molar constant R are vehicle-specific parameters and can be obtained from the vehicle's instruction manual.

[0116] e is the base of the logarithmic function, approximately 2.718281828459045.

[0117] A, a, b, c, and n can be solved using five different sets of training data. Each set of training data needs to include: the thickness ΔW of the brake pad wear in time t, the braking pressure P, the braking deceleration V, the braking time t, the braking temperature T, and the temperature of the brake pad before braking T0. The values ​​of the constants A, a, b, c, and n in the initial model can be solved using six different sets of the above training data.

[0118] Optionally, the first step includes: determining the initial model based on the brake pad thickness, the brake pad wear formula, and the braking time t.

[0119] Since the brake pad wear formula provides the relationship between braking time t and brake pad wear thickness ΔW, that is, it gives the amount of wear ΔW of the brake pad after each time t, we only need to determine the difference between the brake pad thickness and the thickness at which the brake pad will fail. Dividing this difference by the amount of wear ΔW will determine how many more time intervals t are needed for the brake pad to fail. Multiplying this number by time t will determine the remaining service life of the brake pad. Therefore, based on this, the initial model in formula (2.2) can be determined.

[0120] Where S represents the predicted remaining service life of the brake pad, W0 represents the brake pad thickness, and W1 represents the brake pad thickness threshold, which indicates the brake pad thickness at which the brake pad is damaged. In this embodiment, the brake pad thickness threshold ranges from 2 to 5 mm, for example, it can be 2 mm, 3 mm, or 5 mm.

[0121] For details regarding W0 and t, please refer to step 202 above. For details regarding △W, please refer to the brake pad wear formula (2.3) above. Details are omitted here.

[0122] The second step is to use an optimization algorithm to optimize A, a, b, c, and n in the initial model to obtain the brake pad prediction model.

[0123] Optionally, the optimization algorithm can be a common optimization algorithm such as the least squares algorithm or the linear regression algorithm, and the embodiments disclosed herein are not limited to this.

[0124] When optimizing A, a, b, c, and n in the initial model using an optimization algorithm, multiple sets of the aforementioned training data are input into the initial model. The optimization goal is to make the predicted remaining service life S of the brake pads consistent in two adjacent time periods, which can improve the accuracy of the brake pad prediction model.

[0125] In some embodiments, the target data in the memory of each vehicle can be used as training data for the brake pad prediction model, where ΔW is determined by the difference in brake pad thickness before and after a single braking action. In this way, a corresponding brake pad prediction model exists for each vehicle, thereby further improving the accuracy of the brake pad prediction model.

[0126] In another possible implementation, the method for obtaining the brake pad prediction model includes: taking the brake pressure P, brake deceleration V, brake time t, and brake temperature T as inputs, and taking the wear thickness ΔW of the brake pad within time t as the output, which is a set of training data; and constructing a brake pad prediction model based on multiple sets of training data and an extreme gradient boosting algorithm.

[0127] Extreme gradient boosting is a common machine learning algorithm. It constructs a tree-like objective function model that minimizes structural risk using input and output. The objective function model includes a loss function and a regularization term representing model complexity. The loss function is a function that can be expanded using a second-order Taylor series. By iteratively training the objective function using training data, a brake pad prediction model can be obtained. There are many related technologies involved in extreme gradient boosting, which will not be detailed here.

[0128] It should be noted that the implementation method of the brake pad prediction model in this disclosure is not limited. Any brake pad prediction model in the related technology can be used, such as using a machine learning algorithm such as a neural network algorithm to construct the brake pad prediction model.

[0129] In this embodiment of the disclosure, step 203 enables the prediction of the remaining service life of the target device based on the target data, and the prediction method in this embodiment of the disclosure can effectively improve the accuracy of the prediction results.

[0130] In step 204, in response to the remaining useful life of the target device being less than or equal to a first threshold, the control authority of the driver assistance system over the target device is disabled.

[0131] In this embodiment of the disclosure, the first threshold is 1 to 5 days, for example, it can be 1 day, 2 days, 3 days or 5 days.

[0132] If the remaining service life of the target device is less than or equal to the first threshold, it means that the target device is about to be damaged. At this time, the target device cannot continue to be controlled by the driver assistance system. Therefore, the target driver assistance system's control authority over the target device can be closed, so that the target device cannot continue to control the driver assistance system, thereby reducing the safety hazards of the driver assistance system.

[0133] For example, if the target device is a brake pad, the driver assistance system can be deactivated when it is predicted that the remaining service life of at least one brake pad in the vehicle is less than or equal to a first threshold, thereby reducing the safety hazards of the driver assistance system.

[0134] Optionally, the method further includes: exiting the current process in response to the remaining useful life of the target device being greater than a first threshold.

[0135] If the remaining service life of the target device is greater than the first threshold, it means that the remaining service life of the target device is sufficient. Therefore, there is no need to disable the control authority of the assisted driving system over the target device, and you can directly exit the current process.

[0136] In step 205, a prompt message is output.

[0137] This message is used to inform the user that the driver assistance system's control over the target device is off, or that the target device has at least one of the following remaining lifespans:

[0138] In one possible implementation, a pop-up window can be displayed on the vehicle's screen to provide a notification that the driver assistance system's control over the target device is disabled, and to inform the user of the remaining lifespan of the target device. The content of the pop-up window can be preset before the vehicle leaves the factory and stored in the vehicle's memory.

[0139] For example, if the remaining service life of the brake pads is 3 days, which is less than the first threshold, then the driver assistance system's control over the braking function is disabled. Therefore, the pop-up message will include: "The remaining service life of the brake pads is 3 days; the braking control of the driver assistance system is disabled."

[0140] In another possible implementation, prompts can be output via voice announcement. The voice announcement informs the user that the driver assistance system's control over the target device is disabled, and also informs the user of the remaining lifespan of the target device. The voice announcement content can be preset before the vehicle leaves the factory and stored in the vehicle's memory. For example, if the brake pads have a remaining lifespan of 3 days, after disabling the driver assistance system's control over the brake pads, the voice announcement might say, "Brake pads have a remaining lifespan of 3 days; driver assistance system brake control is disabled."

[0141] In practice, the two implementation methods of displaying pop-up windows on the screen and voice broadcasting can also be combined.

[0142] In this embodiment, by acquiring the control status of the assisted driving system's control authority over the target device, obtaining the target data of the target device in the vehicle, and predicting the remaining lifespan of the target device based on the target data, the assisted driving system closes its control authority over the target device when the remaining lifespan of the target device is less than or equal to a first threshold, and outputs corresponding prompt information. This achieves two goals: firstly, it prevents the assisted driving system from taking over the aging target device (remaining lifespan less than or equal to the first threshold), thus avoiding safety hazards caused by the aging target device still being controlled by the assisted driving system. Secondly, while the assisted driving system's behavior of taking over the target device still aligns with reality, the target device is already aging, and continued control by the assisted driving system would pose a safety hazard. Closing the assisted driving system at this time reduces the safety hazards present when the assisted driving system's behavior aligns with reality, thus improving the safety factor of the assisted driving system. Improved safety factor also increases user satisfaction with the assisted driving system and the vehicle, thereby enhancing the user experience. Furthermore, the prompt information informs the user of the remaining lifespan of the target device in the vehicle, thereby improving the vehicle's intelligence level and further enhancing the user experience.

[0143] Some driver assistance systems (ADAS) also have the function of controlling the exhaust fan speed in the exhaust system. For example, ADAS might increase the exhaust fan speed at higher vehicle speeds to expel exhaust gases more quickly and reduce the temperature of the exhaust system. When the ADAS is not in operation, the exhaust fan usually maintains a constant speed. However, if the exhaust fan is about to fail, and the ADAS still controls its speed (e.g., by increasing the speed), it will lead to increased exhaust system noise and a degraded user experience. In severe cases, if the exhaust fan is already old (or about to age) but the ADAS continues to supply operating current to speed it up, it may cause the exhaust fan wiring to burn out, potentially leading to exhaust system malfunctions and safety hazards. Therefore, the target device could also be the exhaust fan itself.

[0144] Figure 3 A flowchart of a control method for an assisted driving system provided in another exemplary embodiment of the present disclosure is shown. This method can be executed by an onboard device of a vehicle, which can be an onboard computer, a main control unit (MCU), or a functional module integrated on a system motherboard, etc. Figure 3 In this paper, the method of the present disclosure will be illustrated by taking the exhaust fan in the exhaust pipe of an automobile as an example.

[0145] See Figure 3The method includes the following steps:

[0146] In step 301, the status of the control authority of the driver assistance system over the target device is obtained.

[0147] For details regarding the status of the driver assistance system's control authority over the target device, please refer to step 201 above, which will not be elaborated here.

[0148] In this embodiment of the disclosure, since the target device is the exhaust fan in the exhaust pipe of a car (hereinafter referred to as the exhaust fan), step 301 is to obtain the control status of the assisted driving system's control authority over the exhaust fan.

[0149] In step 302, target data of the target device in the vehicle is acquired.

[0150] Target data is used to indicate data that affects the remaining service life of the target device. For exhaust fans, target data includes: exhaust fan temperature, exhaust fan speed, and exhaust fan operating current.

[0151] The exhaust fan temperature is obtained through a temperature sensor located around the exhaust fan. Since the car's exhaust system is in a high-temperature environment for a long time, the temperature sensor located around the exhaust fan needs to be a high-temperature resistant sensor.

[0152] The exhaust fan speed can be obtained by a speed sensor located on the exhaust fan, and the exhaust fan operating current can be calculated by inputting the exhaust fan's operating voltage into the vehicle equipment.

[0153] In step 303, the remaining service life of the target device is predicted based on the target data.

[0154] In this embodiment of the disclosure, step 303 is executed periodically, thereby enabling accurate prediction of the remaining service life of the exhaust fan. The details of periodically executing step 303 are consistent with those of periodically executing step 203 in the aforementioned step 203, and are omitted here.

[0155] Optionally, step 303 includes the following three steps:

[0156] Step 1: Obtain the corresponding relationship of the exhaust fans.

[0157] The exhaust fan correspondence is used to indicate the relationship between the temperature, operating current, and speed of the exhaust fan.

[0158] For example, the corresponding relationship between exhaust fans can be obtained by measuring the relationship curves of the operating current and speed of multiple normally operating exhaust fans under different temperature environments.

[0159] The second step is to determine the expected speed based on the corresponding relationship of the exhaust fans, the operating current of the exhaust fans, and the temperature of the exhaust fans.

[0160] The expected speed is the speed that an exhaust fan should have under normal operating current and temperature.

[0161] Optionally, the exhaust fan correspondence is stored in the memory of the vehicle device, and the expected speed of the exhaust fan under normal conditions can be determined by querying the correspondence.

[0162] The third step is to determine the remaining service life of the exhaust fan based on its speed and the expected speed.

[0163] If the expected rotational speed is greater than the exhaust fan speed, it means that the exhaust fan speed is less than the exhaust fan speed under normal conditions, indicating that the exhaust fan performance has deteriorated, which means that the remaining service life of the exhaust fan is less than the remaining service life of the exhaust fan under normal conditions.

[0164] If the expected speed is less than or equal to the current speed, it indicates that the exhaust fan is performing well, confirming that the exhaust fan is normal and has sufficient remaining service life.

[0165] Step 303 enables the prediction of the remaining lifespan of the exhaust fan, thereby controlling the driver assistance system when the remaining lifespan of the exhaust fan is insufficient, disabling the driver assistance system's control over the exhaust fan, and thus improving the user experience.

[0166] In step 304, in response to a decrease in the performance of the target device, the driver assistance system's control over the target device is disabled.

[0167] For devices like exhaust fans, performance degradation alone can significantly reduce the user experience (e.g., by generating noise). Therefore, the control of the target device by the driver assistance system should not be turned off only when the remaining service life is less than or equal to the first threshold. Instead, the control of the target device by the driver assistance system should be turned off as soon as the performance of the target device is determined to be degraded. This will improve the user experience while reducing the safety hazards of the driver assistance system.

[0168] In step 305, a prompt message is output.

[0169] The relevant content of the output prompt message is described in step 205 above, and will not be detailed here.

[0170] In practical applications, the specific content of the prompt message can be modified according to different target devices. This embodiment does not limit the specific content of the prompt message.

[0171] In this embodiment, by acquiring the control status of the assisted driving system's control authority over the target device, obtaining the target data of the target device in the vehicle, predicting the remaining lifespan of the target device based on the target data, and responding to the performance degradation of the target device, closing the assisted driving system's control authority over the target device and outputting corresponding prompt information, this approach avoids safety hazards caused by the assisted driving system still taking over an aging target device (performance degradation, insufficient remaining lifespan). Furthermore, while the assisted driving system's takeover of the target device may still be consistent with reality, the target device is already aged, and continued control by the assisted driving system would pose a safety hazard. Closing the assisted driving system at this point reduces the safety hazards present when its behavior is consistent with reality, thus improving the safety factor of the assisted driving system. Improved safety also increases user satisfaction with the assisted driving system and the vehicle, thereby enhancing the user experience. In addition, the prompt information informs the user of the remaining lifespan of the target device in the vehicle, thereby improving the vehicle's intelligence and further enhancing the user experience.

[0172] The following are device embodiments of this application. For details not described in detail in the device embodiments, please refer to the above method embodiments.

[0173] Figure 4 A schematic diagram of the structure of a control device for an assisted driving system provided in an exemplary embodiment of this disclosure is shown. See also: Figure 4 The control device 400 of the driver assistance system includes: a data acquisition module 401, a prediction module 402, and a control module 403.

[0174] The data acquisition module 401 is used to acquire target data of a target device in the vehicle, wherein the target data is data affecting the remaining service life of the target device. The prediction module 402 is used to predict the remaining service life of the target device based on the target data. The control module 403 is used to disable the control authority of the driver assistance system over the target device in response to the remaining service life of the target device being less than or equal to a first threshold.

[0175] Optionally, the target device includes brake pads, and the target data includes braking pressure, brake pad thickness, braking temperature, braking time, braking deceleration, the distance between the vehicle seat and the road surface during the braking time, brake pedal depth, and braking torque. The prediction module 402 is further configured to input the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration into a brake pad prediction model to obtain a first prediction result. The brake pad prediction model is used to characterize the correspondence between the remaining service life of the brake pad and the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration. Based on the distance between the vehicle seat and the road surface during the braking time, a road surface bumpiness coefficient is obtained. Based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque, a correction coefficient is determined. The first prediction result is corrected using the correction coefficient to obtain a second prediction result, which is the predicted remaining service life of the brake pad.

[0176] Optionally, the prediction module 402 is further configured to determine the road surface bumpiness coefficient based on the change in distance between the vehicle base and the road surface during the braking time; and to determine the correction coefficient based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque.

[0177] Optionally, the prediction module 402 is further configured to determine a first correction coefficient based on the brake pedal depth, wherein the first correction coefficient is less than 1 when the brake pedal depth is greater than a third threshold; determine a second correction coefficient based on the braking torque, wherein the second correction coefficient is less than 1 when the braking torque is greater than a fourth threshold; and multiply the first correction coefficient, the second correction coefficient, and the road surface bumpiness coefficient to obtain the correction coefficient.

[0178] Optionally, the device further includes: a prediction model determination module 404, used to optimize the initial model using an optimization algorithm to obtain the brake pad prediction model, wherein the initial model is as follows:

[0179]

[0180] Wherein, S is the predicted remaining service life of the brake pad, W0 is the brake pad thickness, W1 is the brake pad thickness threshold, the brake pad thickness threshold is used to indicate the brake pad thickness when the brake pad is damaged, t is the braking time, and ΔW is the thickness of the brake pad worn within time t.

[0181] Optionally, the target device includes an exhaust fan, and the target data includes exhaust fan temperature, exhaust fan speed, and exhaust fan operating current. The prediction module 402 is further configured to: obtain an exhaust fan correspondence, which indicates the relationship between the exhaust fan temperature, operating current, and speed; determine the expected speed based on the exhaust fan correspondence, the exhaust fan operating current, and the exhaust fan temperature; and determine the remaining service life of the exhaust fan based on the exhaust fan speed and the expected speed.

[0182] Optionally, the device further includes: a prompting module 405 for outputting prompting information, the prompting information being used to indicate that the driver assistance system's control authority over the target device is in a closed state and that the target device has at least one of the following: the remaining service life of the target device.

[0183] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. For example... Figure 5 As shown, the computer device 500 includes a processor 501 and a memory 502.

[0184] Processor 501 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 501 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 501 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 501 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 501 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0185] The memory 502 may include one or more computer-readable storage media, which may be non-transitory. The memory 502 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 502 is used to store at least one instruction, which is executed by the processor 501 to implement the driver assistance system anti-control method provided in this disclosure embodiment.

[0186] Those skilled in the art will understand that Figure 5 The structure shown does not constitute a limitation on the computer device 500, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0187] This disclosure also provides a non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of a computer device, the computer device is able to execute the control method of the driver assistance system provided in this disclosure.

[0188] This disclosure also provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the control method of the assisted driving system provided in this disclosure.

[0189] The above description is merely an optional embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A control method for an assisted driving system, characterized in that, The method includes: Acquire target data of a target device in a vehicle, wherein the target data is data that affects the remaining service life of the target device; Based on the target data, predict the remaining service life of the target device; In response to the remaining service life of the target device being less than or equal to a first threshold, the control authority of the driver assistance system over the target device is disabled.

2. The method according to claim 1, characterized in that, The target device includes brake pads, and the target data includes braking pressure, brake pad thickness, braking temperature, braking time, braking deceleration, distance between the vehicle base and the road surface during the braking time, brake pedal depth, and braking torque. The step of predicting the remaining service life of the target device based on the target data includes: The brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration are input into the brake pad prediction model to obtain a first prediction result. The brake pad prediction model is used to characterize the correspondence between the remaining service life of the brake pad and the brake pad thickness, braking pressure, braking temperature, braking time, and braking deceleration. A correction factor is determined based on at least one of the following: the distance between the vehicle base and the road surface during the braking time, the brake pedal depth, and the braking torque; The first prediction result is corrected using the correction coefficient to obtain a second prediction result, which is the predicted remaining service life of the brake pad.

3. The method according to claim 2, characterized in that, The step of determining a correction coefficient based on at least one of the following: the distance between the vehicle base and the road surface during the braking time, the brake pedal depth, and the braking torque, includes: The road surface bumpiness coefficient is determined based on the change in distance between the vehicle base and the road surface during the braking time. The correction coefficient is determined based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque.

4. The method according to claim 3, characterized in that, The step of determining the correction coefficient based on the road surface bumpiness coefficient, the brake pedal depth, and the braking torque includes: A first correction coefficient is determined based on the brake pedal depth. When the brake pedal depth is greater than a third threshold, the first correction coefficient is less than 1. A second correction coefficient is determined based on the braking torque. When the braking torque is greater than a fourth threshold, the second correction coefficient is less than 1. The correction coefficient is obtained by multiplying the first correction coefficient, the second correction coefficient, and the road surface bumpiness coefficient.

5. The method according to claim 2, characterized in that, The method further includes: The initial model is optimized using an optimization algorithm to obtain the brake pad prediction model, which is as follows: Wherein, S is the predicted remaining service life of the brake pad, W0 is the brake pad thickness, W1 is the brake pad thickness threshold, the brake pad thickness threshold is used to indicate the brake pad thickness when the brake pad is damaged, t is the braking time, and ΔW is the thickness of the brake pad worn within time t.

6. The method according to claim 1, characterized in that, The target device includes an exhaust fan, and the target data includes exhaust fan temperature, exhaust fan speed, and exhaust fan operating current. The step of predicting the remaining service life of the target device based on the target data includes: Obtain the exhaust fan correspondence, which is used to indicate the relationship between the temperature, operating current and speed of the exhaust fan; The expected speed is determined based on the exhaust fan correspondence, the exhaust fan operating current, and the exhaust fan temperature; The remaining service life of the exhaust fan is determined based on the exhaust fan speed and the expected speed.

7. The method according to any one of claims 1 to 6, characterized in that, After the method further includes disabling the control authority of the driver assistance system over the target device in response to the remaining service life of the target device being less than or equal to a first threshold, the method also includes: Output a prompt message, which is used to indicate that the driver assistance system's control over the target device is in a closed state and that the target device has at least one of the following: the remaining service life of the target device.

8. A control device for a driver assistance system, characterized in that, The control device includes: The data acquisition module is used to acquire target data of the target device in the vehicle, wherein the target data is data that affects the remaining service life of the target device; A prediction module is used to predict the remaining service life of the target device based on the target data; The control module is configured to disable the driver assistance system's control over the target device in response to the target device's remaining service life being less than or equal to a first threshold.

9. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to implement the method according to any one of claims 1 to 7.

Images