Autonomous driving method, device, vehicle, medium and program product

Abstract

The application applies to the field of artificial intelligence, and provides an automatic driving method, device, vehicle, medium and program product, wherein the method comprises the following steps: determining road information according to environment perception information and vehicle state information, wherein the road information comprises road surface adhesion data; determining a control parameter baseline of a target vehicle based on the road information; acquiring historical preference information of a target user on a road section corresponding to the road information; adjusting the control parameter baseline according to the historical preference information of the target user to obtain a target control parameter, and controlling the target vehicle to drive by using the target control parameter. In this way, drivers with different driving styles can obtain driving experience meeting their own expectations, and thus the acceptance of the automatic driving system by users is improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more particularly to an autonomous driving method, device, vehicle, medium, and program product. Background Technology

[0002] Adaptive cruise control (ACC) is increasingly being used in advanced driver assistance systems. ACC systems can combine the current driving status of the vehicle (such as vehicle speed) and environmental perception data (such as the motion status of a target vehicle ahead) to generate braking or acceleration control commands.

[0003] However, different drivers exhibit significant differences in following distance, braking timing, and acceleration response. For example, some drivers prefer later braking and faster acceleration, while others prefer earlier braking and slower acceleration. The ACC system uses a uniform standard control strategy for all drivers, making it difficult to match the different driving preferences of each driver. This results in some drivers feeling the system response is sluggish, or others feeling that the ACC system intervenes too early. In other words, the ACC system cannot adapt to the personalized needs of different drivers, leading to a poor user experience. Summary of the Invention

[0004] In view of the above, this application provides an autonomous driving method, device, vehicle, medium, and program product.

[0005] In a first aspect, an autonomous driving method is provided, the method comprising: determining road information based on environmental perception information and / or vehicle state information, the road information including road surface attachment data; determining a control parameter baseline for a target vehicle based on the road information; acquiring historical preference information of a target user on the road segment corresponding to the road information; adjusting the control parameter baseline based on the historical preference information of the target user to obtain target control parameters, and controlling the target vehicle to drive with the target control parameters.

[0006] In the above scheme, by acquiring the target user's historical preference information under the current road conditions and adjusting the baseline of the control parameters based on this information, the final target control parameters used to control vehicle driving can match the driver's personalized driving preferences. In this way, the vehicle's infotainment system can dynamically adapt the control parameters according to the driver's actual driving habits. For drivers who prefer later braking and faster acceleration, the system can adaptively delay braking intervention or increase acceleration response based on their historical preferences. Conversely, for drivers who prefer earlier braking and slower acceleration, the system can adaptively advance braking intervention or decrease acceleration response based on their historical preferences. Thus, drivers with different driving styles can obtain a driving experience that meets their expectations, thereby increasing user acceptance of the autonomous driving system.

[0007] Furthermore, the control parameter baseline is determined based on road surface adhesion data. In other words, the adjustment of control parameters is carried out within the physical safety constraints of the road, avoiding the introduction of safety risks due to personalized parameter adjustments on roads with low adhesion coefficients.

[0008] In conjunction with the first aspect, in some implementations, environmental perception information includes weather type identified based on environmental images captured by a camera, and / or rainfall level determined based on rainfall information collected by a rain sensor; vehicle status information includes one or more of the following: tire longitudinal force, vertical load, and slip ratio; control parameter baselines include headway baseline and deceleration baseline; target control parameters include target headway and target deceleration.

[0009] In the above solution, weather recognition via camera images, rainfall level determination via rain sensors, and vehicle status information collection dimensions such as tire longitudinal force, vertical load, and slip ratio ensure high accuracy of the calculated road surface adhesion data. This allows the vehicle's infotainment system to address road surface changes under complex weather conditions using a fusion of vision and sensing, while also accurately sensing adhesion limits based on tire dynamic parameters. This ensures that subsequent personalized adjustments remain within controllable boundaries, balancing personalized experience with driving safety.

[0010] In conjunction with the first aspect, in some implementation methods, the historical preference information is determined based on the comparison results between the historical control parameters of the target vehicle corresponding to the target user and the preset control parameters. Specifically, the historical preference information is greater than the first coefficient when the headway control value in the historical control parameters is less than the first control value, and the historical preference information is greater than the second coefficient when the deceleration control value in the historical control parameters is greater than the second control value.

[0011] In the above scheme, by comparing historical control parameters with preset control parameters and determining historical preference information based on the comparison results, the vehicle-mounted equipment can clearly identify the driver's driving style. For example, when the historical headway control value is small (less than the first control value), it indicates that the driver tends to follow the vehicle in front closely. In this case, the historical preference information is configured to be greater than the first coefficient to indicate a more aggressive following style. When the historical deceleration control value is large (greater than the second control value), it indicates that the driver tends to brake later. In this case, the historical preference information is configured to be greater than the second coefficient to indicate a more sensitive braking style. In this way, the vehicle-mounted equipment does not require complex driving model training; it can efficiently extract driving preference features simply by comparing preset thresholds, reducing computational overhead while ensuring the objectivity and consistency of preference representation, providing a reliable data foundation for subsequent parameter adjustments.

[0012] In conjunction with the first aspect, in some implementations, determining the control parameter baseline of the target vehicle based on the road information includes: corresponding to road surface adhesion data being less than or equal to a first preset threshold, a vehicle headway baseline being greater than a first time distance threshold, and a deceleration baseline being less than a first deceleration threshold; corresponding to road surface adhesion data being greater than or equal to a second preset threshold, a vehicle headway baseline being less than a second time distance threshold, and a deceleration baseline being greater than a second deceleration threshold; wherein, the first preset threshold is less than the second preset threshold, the first time distance threshold is greater than the second time distance threshold, and the first deceleration threshold is less than the second deceleration threshold.

[0013] In the above scheme, when the road surface adhesion data is low, indicating a slippery road surface, the vehicle's headway baseline is increased and the deceleration baseline is decreased to extend the safe following distance and limit braking intensity, preventing excessive braking distance or vehicle loss of control due to insufficient road surface adhesion. When the road surface adhesion data is high, indicating a dry road surface, the vehicle's headway baseline is decreased and the deceleration baseline is increased to allow for more efficient following and more sensitive braking response, improving traffic efficiency. In this way, even with personalized adjustments, the safety baseline will not be compromised, ensuring the safety of autonomous driving.

[0014] In conjunction with the first aspect, in some implementation methods, the control parameter baseline is adjusted according to the target user's historical preference information to obtain the target control parameters, including: determining the time distance adjustment amount of the headway time distance baseline based on the first preference weight and historical preference information corresponding to the headway time distance baseline, and determining the target headway time distance based on the headway time distance baseline and the time distance adjustment amount; determining the deceleration adjustment amount of the deceleration baseline based on the second preference weight and historical preference information corresponding to the deceleration baseline, and determining the target deceleration based on the deceleration baseline and the deceleration adjustment amount.

[0015] In the above solution, the vehicle-mounted equipment can cater to the different needs of drivers in terms of following distance preference and braking timing preference. For example, for drivers who are used to following closely but have a preference for gentle braking, the system can independently increase the headway adjustment amount while decreasing the deceleration adjustment amount, so that the final target control parameters can accurately reproduce their complex driving style, further improving the precision of personalized adaptation and user satisfaction.

[0016] In conjunction with the first aspect, some implementation methods control the driving of the target vehicle using target control parameters, including: obtaining the initial headway of the target vehicle during its driving process; corresponding to an initial headway being less than the target headway, controlling the vehicle to reduce its speed based on the target deceleration until the initial headway of the target vehicle is adjusted to be greater than or equal to the target headway.

[0017] In the above scheme, the initial headway during driving is acquired in real time and compared with the target headway. Deceleration adjustment is triggered only when the initial headway does not meet the target requirement, and the entire deceleration process is guided by the target deceleration until the headway returns to a safe range. In this way, unnecessary frequent acceleration and deceleration avoid the impact on ride comfort, and ensures that the following distance can be smoothly increased when the following distance is insufficient.

[0018] Secondly, this application provides a vehicle infotainment device, including a processor and a memory, wherein the memory is used to store instructions and the processor is used to execute the instructions, and when the processor executes the instructions, it performs the methods described in the first aspect and various implementations of the first aspect.

[0019] Thirdly, this application provides a vehicle including the vehicle-mounted equipment as described in the second aspect.

[0020] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a vehicle-mounted device, perform the methods described in the first aspect and various implementations thereof.

[0021] Fifthly, this application provides a computer program product including computer instructions that, when executed by a computing device, enable the computing device to perform the methods described in the first aspect and various implementations thereof.

[0022] The beneficial effects of the second to fifth aspects mentioned above can be referred to the beneficial effects of the first aspect mentioned above. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0024] Figure 1 This is a flowchart illustrating an autonomous driving method provided in an embodiment of this application;

[0025] Figure 2 This is a flowchart illustrating another autonomous driving method provided in an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the structure of an autonomous driving device provided in an embodiment of this application;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] The illustrative embodiments of this application include, but are not limited to, autonomous driving methods, devices, vehicles, media, and program products.

[0029] As mentioned earlier, some drivers prefer to brake later and accelerate faster, while others prefer to brake earlier and accelerate slowly. The ACC system cannot adapt to the individual needs of different drivers, resulting in some drivers feeling that the system response is slow, or other drivers feeling that the ACC system intervenes too early.

[0030] To address the aforementioned issues, this application provides an autonomous driving method that determines road information, including road surface attachment data, based on environmental perception information and / or vehicle state information; determines a baseline of control parameters for a target vehicle based on the road information; acquires historical preference information of a target user on the corresponding road segment; adjusts the baseline of control parameters based on the target user's historical preference information to obtain target control parameters; and controls the target vehicle's movement using the target control parameters.

[0031] Furthermore, by acquiring the target user's historical preference information under current road conditions and adjusting the baseline of control parameters based on this information, the final target control parameters used to control vehicle movement can match the driver's personalized driving preferences. In this way, the vehicle's infotainment system can dynamically adapt control parameters according to the driver's actual driving habits. For drivers who prefer later braking and faster acceleration, the system can adaptively delay braking intervention or increase acceleration response based on their historical preferences. Conversely, for drivers who prefer earlier braking and slower acceleration, the system can adaptively advance braking intervention or decrease acceleration response based on their historical preferences. Thus, drivers with different driving styles can obtain a driving experience that meets their expectations, thereby increasing user acceptance of the autonomous driving system.

[0032] Furthermore, the baseline of the control parameters in this application is determined based on road surface adhesion data. In other words, the adjustment of the control parameters is carried out within the physical safety constraints of the road, thus avoiding the introduction of safety risks due to personalized parameter adjustments on roads with low adhesion coefficients.

[0033] The method provided in this application can be applied to vehicle-mounted equipment and the like in transportation vehicles. The aforementioned transportation vehicles may include, but are not limited to, road vehicles (e.g., cars), water vehicles (e.g., ships), and air vehicles (e.g., airplanes). The term "vehicle" can be used in a broad sense, including, for example, vehicles (such as commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (such as forklifts, trailers, tractors, etc.), engineering vehicles (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc.

[0034] The following is combined Figure 1 The process of the autonomous driving method provided in this application is described in detail. This autonomous driving method can be applied to the aforementioned vehicle-mounted equipment, such as... Figure 1 As shown, the method includes:

[0035] S110: Determine road information based on environmental perception information and / or vehicle status information, including road surface adhesion data.

[0036] Road surface adhesion data is used to represent the slipperiness of a road. For example, road surface adhesion data is denoted as μ. A value of μ > 0.8 indicates a dry road surface. A value of 0.4 ≤ μ ≤ 0.8 indicates a wet road surface. A value of μ < 0.4 indicates an icy or snowy road surface.

[0037] Vehicle-mounted equipment can determine the current road slipperiness based on environmental perception information and / or vehicle status information, thus obtaining road surface adhesion data.

[0038] In some embodiments, environmental perception information includes weather type identified based on environmental images captured by a camera, and / or rainfall level determined based on rainfall information collected by a rain sensor. For example, environmental perception information may be weather type (e.g., sunny, rain, snow, fog), visibility, and other information collected by a forward-looking camera, rain sensor, or light and humidity sensor.

[0039] In other embodiments, vehicle status information includes one or more of the following: tire longitudinal force, vertical load, and slip ratio.

[0040] For example, the vehicle's infotainment system can acquire signals such as wheel speed, drive torque, braking pressure, and yaw rate from the vehicle's controller area network (CAN), and calculate the road adhesion coefficient (e.g., denoted as slip ratio) in real time using methods such as slip ratio estimation. value).

[0041] For example, vehicle-mounted equipment can utilize the longitudinal force of the tires. and vertical loads The road surface adhesion coefficient was calculated. For example, you can refer to the following formula (1).

[0042] (1)

[0043] Alternatively, vehicle-mounted equipment can also use the slip ratio λ and the road surface adhesion coefficient. The relationship curve is estimated to obtain the current The braking slip ratio λ can be calculated using the following formula (2), where... For vehicle speed, The angular velocity of the wheel. Wheel radius:

[0044] (2)

[0045] Furthermore, the road surface adhesion coefficient under braking conditions You can refer to the following formula (3). Wherein, This indicates the braking torque.

[0046] (3)

[0047] S120: Determine the baseline of control parameters for the target vehicle based on road information.

[0048] In some embodiments, the control parameter baseline includes a headway baseline and a deceleration baseline. The target control parameters include a target headway and a target deceleration. The headway baseline represents the minimum headway threshold value corresponding to the vehicle-mounted equipment triggering braking operation under standard conditions (e.g., preset road adhesion coefficient, weather conditions, etc.), and the deceleration baseline represents the deceleration reference value used by the vehicle-mounted equipment when performing braking operation under standard conditions.

[0049] In other embodiments, the vehicle-mounted equipment determines the corresponding headway baseline and deceleration baseline based on the numerical range of the road surface adhesion data. Specifically, if the road surface adhesion data is less than or equal to a first preset threshold (i.e., low-adhesion road surface, such as μ ≤ 0.4, corresponding to icy or snowy roads), the headway baseline is greater than the first headway threshold, and the deceleration baseline is less than the first deceleration threshold. In other words, a more conservative baseline strategy is adopted, increasing the headway threshold for braking intervention (i.e., advancing the braking intervention timing) and reducing the maximum requested deceleration (e.g., not exceeding 0.2g).

[0050] For road surface adhesion data greater than or equal to the second preset threshold, i.e., a high-adhesion road surface (e.g., μ ≥ 0.8, corresponding to a dry road surface), the vehicle headway baseline is less than the second headway threshold, and the deceleration baseline is greater than the second deceleration threshold. In other words, when returning to the standard or allowing a more aggressive safety baseline, the braking intervention timing is relatively delayed. Specifically, the first preset threshold is less than the second preset threshold, the first headway threshold is greater than the second headway threshold, and the first deceleration threshold is less than the second deceleration threshold.

[0051] For example, for roads with low adhesion coefficients (e.g.) < 0.4: Forces a more conservative baseline strategy, such as earlier braking intervention (increasing the target headway (THW) threshold) and reducing the maximum requested deceleration (e.g., not exceeding 0.2g) to ensure physical safety. High-friction surfaces (e.g., ...) > 0.8): Revert to the standard or allow for a more aggressive safety baseline, with braking intervention time relatively delayed.

[0052] For example, the THW threshold can also be calculated using the following formula (4), where, , , This is the wet slip coefficient (for example, it can be 0.2~0.4). This is the allowable coefficient for drying (e.g., it can be 0.1). The baseline braking intervention threshold under standard dry road conditions (e.g., 1.2 seconds).

[0053] (4)

[0054] S130: Obtain the target user's historical preference information for the road segment corresponding to the road information.

[0055] In some embodiments, historical preference information is determined by comparing the historical control parameters of the target vehicle corresponding to the target user with preset control parameters. Specifically, if the headway control value in the historical control parameters is less than a first control value, it indicates that the driver tends to follow closely and prefers an aggressive driving style; in this case, the historical preference information is greater than the first coefficient. If the deceleration control value in the historical control parameters is greater than a second control value, it indicates that the driver tends to brake later and prefers a more responsive driving style; in this case, the historical preference information is greater than the second coefficient.

[0056] In other embodiments, when the vehicle-mounted equipment detects that the vehicle is in manual driving mode and the road adhesion coefficient tends to stabilize, it will trigger the learning and updating of historical preference information. Specifically, the vehicle-mounted equipment continuously collects the driver's operation data in manual driving mode, including the accelerator pedal opening and its rate of change, the brake pedal opening and its rate of change, and the timing of actions relative to the target ahead, such as how far away from the vehicle in front to start releasing the accelerator to coast, or when to start applying the brakes.

[0057] The vehicle's infotainment system also records the driver's typical operational characteristics under the current road surface adhesion coefficient (μ) scenario. For example, the characteristic of premature or delayed accelerator pedal application can be expressed as: when the vehicle in front moves away or the vehicle's speed is lower than the set speed, does the driver prematurely and deeply press the accelerator to quickly follow, or gently press or delay pressing the accelerator for smooth acceleration? The characteristic of premature or delayed braking can be expressed as: when a vehicle in front slows down or cuts in, does the driver prematurely and lightly apply the brakes for a long coasting deceleration, or apply the brakes heavily after approaching the vehicle in front?

[0058] In some embodiments, the in-vehicle device quantifies the learned operational features into radical coefficients. The value ranges from 0 to 1, where 0 represents an extremely smooth driving style (e.g., early braking, gentle acceleration) and 1 represents an aggressive driving style (e.g., late braking, fast acceleration). The vehicle-mounted equipment divides different road surface adhesion coefficient ranges into scenarios and statistically analyzes the typical braking timing characteristics of drivers in each scenario (e.g., preferred THW threshold, average deceleration).

[0059] For example, the vehicle's infotainment system can also continuously update the radical coefficient. (As an example of historical preference coefficient), a sliding window averaging method can be used, such as the following formula (5).

[0060] (5)

[0061] in, The learning rate ranges from 0.05 to 0.2. This represents the instantaneous aggression extracted from the current manual driving event. Instantaneous Aggression The definition can be found in the following formula (6).

[0062] (6)

[0063] in, This indicates the THW moment when the driver actually begins braking; the earlier the braking, the larger this value. The standard reference braking THW threshold. This indicates the delay time at which the driver begins to accelerate; the shorter the delay time, the more aggressive the driver is. Accelerated latency for standard reference.

[0064] and then, The larger the value, the earlier the braking, which corresponds to a smooth driving style. When the value is close to 1, κ approaches 0 (the actual formula needs to ensure the range).

[0065] S140: Adjust the baseline of control parameters based on the target user's historical preference information to obtain the target control parameters, and control the target vehicle's driving with the target control parameters.

[0066] In some embodiments, the target control parameters include the target headway and the target deceleration. The vehicle-mounted equipment adjusts the headway baseline and deceleration baseline respectively based on historical preference information.

[0067] In other embodiments, the vehicle-mounted equipment determines the time distance adjustment amount of the headway time distance baseline based on a first preference weight and historical preference information corresponding to the headway time distance baseline, and determines the target headway time distance based on the headway time distance baseline and the time distance adjustment amount. The vehicle-mounted equipment determines the deceleration adjustment amount of the deceleration baseline based on a second preference weight and historical preference information corresponding to the deceleration baseline, and determines the target deceleration based on the deceleration baseline and the deceleration adjustment amount.

[0068] For example, the final braking threshold (THW) can also be calculated using the following formula (7).

[0069] (7)

[0070] in, To personalize the intensity weight, the value range is: .when (Smooth style) That is, the braking timing to maintain the baseline. When (In a radical style) The threshold decreases, allowing for later braking intervention. Simultaneously, to ensure safety, a lower limit constraint can be added. , For absolute safety, a lower limit could be set, for example, 0.8 seconds.

[0071] Alternatively, the THW threshold can be calculated using an offset, as shown in the following formula (8).

[0072] (8)

[0073] Among them, deviation amount Based on and The calculation is obtained by referring to the following formula (9), where, This is the maximum allowable lead time, such as the threshold reduction for an aggressive style relative to the baseline, for example, 0.4 seconds. This represents the degree of personalization shift, based on the driver's level of aggression. ( ) Braking threshold for safety baseline.

[0074] (9)

[0075] Alternatively, the THW threshold can be calculated using an offset, as shown in the following formula (10).

[0076] (10)

[0077] in, , This is the maximum allowable lead time (i.e., the threshold reduction for an aggressive style relative to the baseline), for example, 0.4 seconds.

[0078] In other embodiments, the vehicle-mounted device acquires the initial headway of the target vehicle during driving. If the initial headway is less than the target headway, the vehicle-mounted device controls the vehicle to reduce its speed based on the target deceleration until the initial headway of the target vehicle is adjusted to be greater than or equal to the target headway.

[0079] In other embodiments, the vehicle-mounted equipment also... Adjust the slope of the initial deceleration during braking. A smooth braking style uses a gentler slope, while an aggressive style uses a steeper slope. Let the desired deceleration be... The final deceleration of the target is Braking slope The adjustment method for (i.e., the rate of change of deceleration) can be referred to the following formula (11).

[0080] (11)

[0081] in, The baseline slope, This is the slope adjustment coefficient, with a value range of 0 to 0.5.

[0082] In other embodiments, the vehicle's infotainment system also adjusts the throttle response speed when ACC resumes cruise control based on throttle timing preferences. Using the same... Mapping throttle response time You can refer to the following formula (12).

[0083] (12)

[0084] in, This is the maximum throttle response delay time. Minimize throttle response delay. Smoothness style ( (Close to 0) takes a larger response latency, aggressive style ( Approach 1) to achieve a smaller response delay in order to achieve a more aggressive accelerated response.

[0085] Furthermore, the autonomous driving method provided in this application acquires the target user's historical preference information under current road conditions and adjusts the baseline of control parameters based on this information. This ensures that the target control parameters used to control vehicle movement match the driver's personalized driving preferences. In this way, the vehicle's infotainment system can dynamically adapt the control parameters according to the driver's actual driving habits. For drivers who prefer later braking and faster acceleration, the system can adaptively delay braking intervention or increase acceleration response based on their historical preferences. Conversely, for drivers who prefer earlier braking and slower acceleration, the system can adaptively advance braking intervention or decrease acceleration response based on their historical preferences. Thus, drivers with different driving styles can obtain a driving experience that meets their expectations, thereby increasing user acceptance of the autonomous driving system.

[0086] Furthermore, the control parameter baseline is determined based on road surface adhesion data. In other words, the adjustment of control parameters is carried out within the physical safety constraints of the road, avoiding the introduction of safety risks due to personalized parameter adjustments on roads with low adhesion coefficients.

[0087] In some embodiments, the vehicle's infotainment system will also detect whether the Adaptive Cruise Control (ACC) mode is currently activated; the above steps will only be executed if ACC mode is activated. Figure 1 The method shown corresponds to the vehicle's infotainment system being able to collect the user's driving style in manual driving mode even when ACC mode is not enabled, and process the data to obtain the driver's historical preference information.

[0088] For example, refer to Figure 2 The diagram shown is a flowchart of another autonomous driving method provided in this application, which includes:

[0089] S201: Determine road surface adhesion data based on environmental perception information and vehicle status information.

[0090] In some embodiments, environmental perception information may include weather type, visibility, and other information, while vehicle status information may include parameters such as tire longitudinal force, vertical load, and slip ratio. The vehicle-mounted equipment calculates the road surface adhesion coefficient μ using onboard sensors and vehicle bus signals, which characterizes the current road adhesion conditions. Specific implementation details can be found in the aforementioned S110 and S120, and will not be repeated here.

[0091] S202: Check if ACC mode is enabled. If yes, proceed to S203; otherwise, proceed to S208.

[0092] The vehicle's infotainment system checks whether the Adaptive Cruise Control (ACC) function is active. If ACC is enabled, it executes autonomous driving control according to personalized control parameters; if ACC is disabled, it collects the driver's operation data in manual driving mode to update historical preference information.

[0093] S203: Obtain the target user's historical preference information for the road segment corresponding to the road information.

[0094] The vehicle-mounted equipment acquires the target user's historical preference information under the current road surface adhesion coefficient μ value scenario. This historical preference information includes the aggressive coefficient. Characteristic parameters that represent the driver's driving style are used. The vehicle's infotainment system determines historical preference information based on a comparison between historical control parameters and preset control parameters. For example, if the historical headway control value is relatively small, the system indicates a more aggressive following style. The specific implementation method can be found in the aforementioned S130, and will not be repeated here.

[0095] S204: Determine the target control parameters based on the target user's historical preference information.

[0096] In some embodiments, the vehicle-mounted equipment adjusts the control parameter baseline based on historical preference information to obtain target control parameters. The control parameter baseline includes a headway baseline and a deceleration baseline, and the target control parameters include a target headway and a target deceleration. The vehicle-mounted equipment determines the headway adjustment amount based on a first preference weight corresponding to the headway baseline and historical preference information, and determines the deceleration adjustment amount based on a second preference weight corresponding to the deceleration baseline and historical preference information. For a detailed implementation, please refer to the aforementioned S140, which will not be repeated here.

[0097] S205: Based on the current target control parameters and actual road conditions, determine whether braking is required. If yes, proceed to S206; otherwise, proceed to S207.

[0098] In some embodiments, the vehicle-mounted device acquires the initial headway during driving and compares it with the target headway. If the initial headway is less than the target headway, braking is required; if the initial headway is greater than or equal to the target headway, the current driving state is maintained. Specific implementation details can be found in the aforementioned S140, and will not be repeated here.

[0099] S206: Control vehicle braking according to target control parameters.

[0100] The vehicle's infotainment system controls the vehicle to reduce its speed based on the target deceleration. Simultaneously, the system also adjusts the speed based on an aggressiveness factor. Adjust the slope of the initial deceleration during braking; a gentler slope is used for a smooth braking style, and a steeper slope is used for an aggressive braking style, until the initial headway is adjusted to be greater than or equal to the target headway. For specific implementation details, please refer to the aforementioned S140; it will not be repeated here.

[0101] S207: Maintain current driving status.

[0102] When the vehicle's infotainment system detects that the initial headway has met the target headway requirement, the system does not need to perform braking operations. Instead, it continues to maintain the current throttle opening and driving speed to maintain a stable following position.

[0103] S208: Collect driving data of target users and generate historical preference information.

[0104] When ACC mode is not activated, the vehicle's infotainment system continuously collects driver input data in manual driving mode, including accelerator pedal opening and its rate of change, brake pedal opening and its rate of change, and the timing of actions relative to the target ahead, such as advancing or delaying inputs. The system quantifies the collected input characteristics into an aggression coefficient. This data is then stored in the driver's habit model for the corresponding road surface adhesion coefficient scenario, for personalized control during subsequent ACC activation. The specific implementation can be found in the aforementioned S130, and will not be repeated here.

[0105] In this way, by detecting whether ACC mode is activated, when ACC mode is not activated, the system continuously collects the driver's operation data in manual driving mode and generates historical preference information. When ACC mode is activated, the baseline of control parameters is adjusted based on the learned historical preference information, and the vehicle is controlled with the adjusted target control parameters. In this way, the vehicle's equipment can complete style learning without interfering with the driver's normal driving, and automatically transfer the learned preference features to the autonomous driving control after ACC is activated, achieving a smooth transition in driving style from manual driving to autonomous driving.

[0106] In this way, the vehicle's infotainment system can dynamically adapt control parameters based on the driver's actual driving habits. For drivers who prefer later braking and faster acceleration, the system can adaptively delay braking intervention or increase acceleration response based on their historical preferences. Conversely, for drivers who prefer earlier braking and slower acceleration, the system can adaptively advance braking intervention or decrease acceleration response based on their historical preferences. Thus, drivers with different driving styles can obtain a driving experience that meets their expectations, thereby increasing user acceptance of the autonomous driving system.

[0107] Furthermore, the control parameter baseline is determined based on road surface adhesion data. In other words, the adjustment of control parameters is carried out within the physical safety constraints of the road, avoiding the introduction of safety risks due to personalized parameter adjustments on roads with low adhesion coefficients.

[0108] The following is combined Figure 3 This application introduces an autonomous driving device 300, which includes an environmental perception module 310, a vehicle dynamics and road surface perception module 320, a driver operation recording module 330, a driver characteristic learning module 340, and an ACC adaptive control module 350.

[0109] The environmental perception module 310 connects to a forward-facing camera, a rain sensor, and a light and humidity sensor to acquire information such as weather type (e.g., sunny, rainy, snowy, fog) and visibility. The environmental perception information output by this module is used to assist in the subsequent determination of road surface adhesion data and scene segmentation. The specific implementation method can be found in the aforementioned S110, and will not be repeated here.

[0110] The vehicle dynamics and road surface perception module 320 acquires signals such as wheel speed, drive torque, braking pressure, and yaw rate from the CAN bus, and calculates the road surface adhesion coefficient (e.g., denoted as μ) in real time using methods such as slip ratio estimation. The road surface adhesion data output by this module is used to determine the safety baseline of the control parameters. For specific implementation details, please refer to the aforementioned S110 and S120, which will not be elaborated here.

[0111] The driver operation recording module 330 continuously collects the driver's operation data in manual driving mode, including the accelerator pedal opening and its rate of change, the brake pedal opening and its rate of change, and the timing of actions relative to the target ahead, whether advanced or delayed. The data collected by this module provides raw input for the driver characteristic learning module. The specific implementation can be found in the aforementioned S130, and will not be repeated here.

[0112] The driver characteristic learning module 340 internally runs a driver habit model, divides different road surface adhesion coefficient ranges into scenarios, and statistically analyzes the typical braking timing characteristics of drivers in each scenario (such as preferred THW threshold and average deceleration request), outputting an aggressive coefficient representing the driver's driving style. For specific implementation details, please refer to the aforementioned S130 and S140, which will not be elaborated here.

[0113] The ACC adaptive control module 350 receives the outputs from the aforementioned modules, dynamically adjusts the decision threshold and braking curve for braking intervention, and finally outputs a braking request to the vehicle actuators to achieve personalized autonomous driving control that complies with physical safety constraints. The specific implementation method can be found in the aforementioned S140, and will not be repeated here.

[0114] In this way, the autonomous driving device can dynamically adapt control parameters based on the driver's actual driving habits. For drivers who prefer later braking and faster acceleration, the system can adaptively delay braking intervention or increase acceleration response based on their historical preference information. Conversely, for drivers who prefer earlier braking and slower acceleration, the system can adaptively advance braking intervention or decrease acceleration response based on their historical preference information. Thus, drivers with different driving styles can obtain a driving experience that meets their expectations, thereby increasing user acceptance of the autonomous driving system. Furthermore, the control parameter baseline is determined based on road surface adhesion data, meaning that adjustments to the control parameters are made within the constraints of road physical safety, avoiding safety risks introduced by personalized parameter adjustments on low-adhesion surfaces.

[0115] Figure 4 A schematic diagram of the hardware structure of an in-vehicle infotainment device is shown according to an embodiment of this application.

[0116] like Figure 4 As shown, the vehicle infotainment system 400 may include a processor 410, a wireless communication module 420, a mobile communication module 430, a power module 440, an audio module 450, an interface module 460, a main camera 470 and a wide-angle camera 471, a memory 480, a sensor module 490, buttons 402, a motor 403, and an indicator 404, etc. The sensor module 490 may include a seat sensor, an acceleration sensor, a distance sensor, a proximity sensor, a touch sensor, an ambient light sensor, etc.

[0117] It is understood that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on the vehicle infotainment system 400. In other embodiments of this application, the vehicle infotainment system 400 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0118] Processor 410 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0119] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0120] The processor 410 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 410 is a cache memory. This memory can store instructions or data that the processor 410 has just used or that are used repeatedly. If the processor 410 needs to use the instruction or data again, it can retrieve it directly from the aforementioned memory. This avoids repeated accesses, reduces the waiting time of the processor 410, and thus improves the efficiency of the system.

[0121] In this embodiment, the processor 410 of the vehicle infotainment system 400 can perform tasks such as fetching and executing instructions through the controller to implement the above-mentioned functions. Figure 1 The relevant steps performed by the CRRC machine can be found in the descriptions of the above embodiments, and will not be repeated here.

[0122] Interface module 460 may include one or more interfaces. Interfaces may include inter-integrated circuit (I2C) interfaces, inter-integrated circuit sound (I2S) interfaces, pulse code modulation (PCM) interfaces, universal asynchronous receiver / transmitter (UART) interfaces, mobile industry processor interfaces (MIPI), general-purpose input / output (GPIO) interfaces, SIM card interfaces, and / or universal serial bus (USB) interfaces, etc.

[0123] The power module 440 is used to connect the battery, the charging management module, and the processor 410, etc. The power module 440 receives input from the battery and / or the charging management module and supplies power to the processor 410, the memory 480, the main camera 470, the wide-angle camera 471, and the wireless communication module 420, etc.

[0124] The wireless communication module 420 can provide solutions for wireless communication applications on the vehicle infotainment system 400, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0125] The mobile communication module 430 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the vehicle infotainment system 400. The mobile communication module 430 may include at least one filter, switch, power amplifier, low-noise amplifier (LNA), etc.

[0126] The main camera 470 and the wide-angle camera 471 are used to capture still images or videos. An object passes through the lens, generating an optical image that is projected onto a photosensitive element. This photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then passed to the ISP (Image Signal Processor) for conversion into a digital image signal. The ISP outputs the digital image signal to the DSP (Digital Signal Processor) for processing. The DSP converts the digital image signal into standard RGB, YUV, or other image signal formats.

[0127] The memory 480 can be used to store computer executable program code, including instructions. The internal memory 480 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of the vehicle infotainment system 400 (such as audio data, phonebook, etc.). Furthermore, the memory 480 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc. The processor 410 executes various functional applications and data processing of the vehicle infotainment system 400 by running instructions stored in the memory 480 and / or instructions stored in memory located within the processor.

[0128] The vehicle infotainment system 400 can achieve audio functions such as music playback and recording through the audio module 450, speakers, receiver, microphone, and application processor.

[0129] The audio module 450 is used to convert digital audio information into analog audio signal output, and also to convert analog audio input into digital audio signal. The audio module 450 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 450 may be located in the processor 410, or some functional modules of the audio module 450 may be located in the processor 410.

[0130] Buttons 402 include a power button, volume buttons, etc. Buttons 402 can be mechanical buttons or touch-sensitive buttons. The vehicle infotainment system 400 can receive button input and generate key signal inputs related to user settings and function control of the vehicle infotainment system 400.

[0131] Motor 403 can generate vibration alerts. Motor 403 can be used for incoming call vibration alerts or for touch vibration feedback. For example, different vibration feedback effects can be corresponding to touch operations applied to different applications (such as taking photos, playing audio, etc.). Motor 403 can also correspond to different vibration feedback effects for touch operations applied to different areas of the display screen. Different application scenarios (such as time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also be customized.

[0132] Indicator 404 can be an indicator light, used to indicate charging status, power changes, or to indicate messages, missed calls, notifications, etc.

[0133] This application also provides a vehicle, including the aforementioned vehicle infotainment system 400.

[0134] This application also provides a computer-readable storage medium storing instructions that, when executed on a vehicle-mounted device, perform the methods provided in the above embodiments.

[0135] This application also provides a computer program product, including computer program code, which, when run on a computer, causes the computer to execute the autonomous driving methods provided in the above embodiments.

[0136] Various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or combinations of these implementation methods. Embodiments of this application can be implemented as computer program modules or module code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0137] Computer program modules or module code can be applied to input instructions to perform the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor.

[0138] Module code can be implemented using a high-level modular language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used to implement module code when needed. In fact, the mechanisms described in this application are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0139] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored thereon on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, optical discs, magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other forms of propagated signals. Therefore, machine-readable media include any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

Claims

1. An autonomous driving method, characterized in that, The method includes: Road information is determined based on environmental perception information and / or vehicle status information, wherein the road information includes road surface adhesion data; Based on the road information, determine the baseline of control parameters for the target vehicle; Obtain the target user's historical preference information for the road segment corresponding to the road information; Based on the target user's historical preference information, the baseline of the control parameters is adjusted to obtain the target control parameters, and the target vehicle is controlled to drive using the target control parameters.

2. The method according to claim 1, characterized in that, The environmental perception information includes the weather type identified based on environmental images captured by a camera, and / or the rainfall level determined based on rainfall information collected by a rain sensor. The vehicle status information includes one or more of the following: tire longitudinal force, vertical load, and slip ratio; The control parameter baselines include the headway baseline and the deceleration baseline; The target control parameters include the target headway and the target deceleration.

3. The method according to claim 1, characterized in that, The historical preference information is a historical preference coefficient, which is determined based on the comparison results between the historical control parameters of the target vehicle corresponding to the target user and the preset control parameters. Specifically, if the headway control value in the historical control parameters is less than the first control value, the historical preference information is greater than the first coefficient; and if the deceleration control value in the historical control parameters is greater than the second control value, the historical preference information is greater than the second coefficient.

4. The method according to claim 2, characterized in that, The determination of the control parameter baseline for the target vehicle based on the road information includes: The road surface adhesion data is less than or equal to a first preset threshold, the vehicle headway baseline is greater than the first time distance threshold, and the deceleration baseline is less than the first deceleration threshold. The road surface adhesion data is greater than or equal to the second preset threshold, the vehicle headway baseline is less than the second time distance threshold, and the deceleration baseline is greater than the second deceleration threshold. Wherein, the first preset threshold is less than the second preset threshold, the first time interval threshold is greater than the second time interval threshold, and the first deceleration threshold is less than the second deceleration threshold.

5. The method according to claim 4, characterized in that, The step of adjusting the control parameter baseline based on the target user's historical preference information to obtain the target control parameters includes: Based on the first preference weight corresponding to the vehicle head time distance baseline and the historical preference information, the time distance adjustment amount of the vehicle head time distance baseline is determined, and based on the vehicle head time distance baseline and the time distance adjustment amount, the target vehicle head time distance is determined; Based on the second preference weight corresponding to the deceleration baseline and the historical preference information, the deceleration adjustment amount of the deceleration baseline is determined, and based on the deceleration baseline and the deceleration adjustment amount, the target deceleration is determined.

6. The method according to claim 5, characterized in that, Controlling the target vehicle to drive using the target control parameters includes: Obtain the initial headway of the target vehicle during its driving process; If the initial headway is less than the target headway, the vehicle speed is reduced based on the target deceleration until the initial headway of the target vehicle is adjusted to be greater than or equal to the target headway.

7. A vehicle-mounted infotainment system, characterized in that, include: A memory for storing instructions executed by one or more processors of the vehicle infotainment system, and a processor, one of the processors of the vehicle infotainment system, for performing the method of any one of claims 1 to 6.

8. A vehicle, characterized in that, Includes the vehicle-mounted equipment as described in claim 7.

9. A readable medium, characterized in that, The readable medium stores instructions that, when executed on the vehicle-mounted device, cause the vehicle-mounted device to perform the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes: computer program code, which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 6.

Images