Vehicle starting control method and device, vehicle and medium

Abstract

The invention relates to the technical field of vehicle control, and discloses a vehicle starting control method and device, a vehicle and a medium, and the method comprises the following steps: in response to starting operation of the vehicle in an automatic parking state, adjusting parking release control parameters according to current road surface information and vehicle parameters; and releasing the automatic parking state according to the adjusted parking release control parameter. The parking release control parameters are dynamically adjusted according to real-time road surface information and vehicle parameters through a dynamic and self-adaptive parameter adjusting mechanism, the limitation of traditional fixed calibration is eliminated, different road conditions and vehicle states can be adapted, the vehicle starting quality in the automatic parking state is remarkably improved, and the vehicle starting speed is increased. And fixed parameters under the automatic parking function can be continuously optimized, so that the method adapts to individual manufacturing differences of different vehicles, starting abnormities such as slope sliding, dragging and vehicle channeling of the vehicles can be effectively avoided, the safety and smoothness of vehicle starting are improved, and meanwhile the user driving experience and the vehicle intelligent control level are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, specifically to vehicle start-up control methods, devices, vehicles, and media. Background Technology

[0002] The Auto Hold function, a core convenience feature in modern vehicles, is widely used in various models. This function automatically maintains braking pressure to keep the vehicle stationary when the driver releases the brake pedal, such as when the vehicle is temporarily stopped, waiting at a traffic light, thus reducing the driver's workload. When the driver needs to start again, simply pressing the accelerator pedal will cause the system to automatically release the parking brake once a certain level of driving torque is reached, resulting in a smooth start.

[0003] Currently, the performance experience of automatic parking is mainly a subjective feeling during vehicle start-up, primarily manifested in the subjective smoothness of releasing the automatic parking function during start-up; the performance of this function is particularly critical under incline conditions. For incline conditions, the release condition of this function is that the power torque reaches a calibrated value, and the magnitude of the calibrated value directly affects the start-up smoothness. Specifically, current automatic parking control strategies typically rely on a set of pre-calibrated fixed parameters, such as a theoretical start-up torque threshold related to the slope and a pressure relief coefficient. The release condition is usually that the actual driving torque reaches the product of the two values. This set of parameters is calibrated and solidified during the vehicle development phase through limited prototype testing, aiming to balance the anti-rollback capability and start-up responsiveness during incline starts.

[0004] However, due to unavoidable inconsistencies in vehicle manufacturing processes, such as micro-level differences in braking system friction coefficients, vehicle weight, and powertrain output characteristics, control methods based on fixed calibration parameters are difficult to adapt to the actual conditions of all vehicles. For example, in actual use, using fixed calibration parameters may result in a lower pressure relief coefficient for some vehicles, causing the automatic parking function to release too early, and insufficient driving torque to overcome slope resistance, easily leading to the vehicle "rolling back" and posing a safety hazard. For other vehicles, the fixed pressure relief coefficient may be too high, causing the automatic parking function to release too late or abruptly, resulting in a noticeable jerk or delay when starting the vehicle, i.e., a "dragging" phenomenon, which seriously affects driving smoothness, comfort, and safety.

[0005] In addition, some existing technologies have control schemes aimed at optimizing the start-up process, such as adjusting the braking execution process through real-time feedback or applying additional power compensation after an anomaly is detected. However, most of these methods focus on fine-tuning the execution links under the given control commands or taking remedial measures after a problem occurs. They fail to fundamentally perform dynamic and adaptive correction and learning of the core control parameters that determine the timing of automatic parking release.

[0006] In summary, there is an urgent need to design a system that can sense the vehicle's own characteristics and real-time status, and continuously optimize the fixed calibration parameters under the vehicle's automatic parking function, thereby proactively adapting to the individual manufacturing differences of different vehicles, and eliminating abnormal phenomena such as slippage, dragging, and sudden acceleration when the vehicle starts, so as to improve the user's driving experience and the level of vehicle intelligent control. Summary of the Invention

[0007] This invention provides a vehicle start-up control method, device, vehicle, and medium to solve the problem mentioned in the above-mentioned technical background that the existing technology is unable to overcome the mismatch of fixed calibration parameters caused by differences in vehicle manufacturing consistency, which easily leads to frequent abnormal vehicle start-up phenomena and seriously affects the smoothness of start-up and the user's driving experience.

[0008] In a first aspect, the present invention provides a vehicle start-up control method, the method comprising: In response to the vehicle's starting operation in automatic parking mode, the parking release control parameters are adjusted based on the current road information and vehicle parameters. Release the automatic parking status according to the adjusted parking release control parameters; Among them, road surface information includes longitudinal slope angle, vehicle parameters include drive shaft torque and braking pressure, and parking release control parameters include pressure relief coefficient; Based on the current road conditions and vehicle parameters, adjust the parking release control parameters, including any one of the following: In response to a longitudinal slope angle greater than zero and a drive shaft torque less than the critical slip torque threshold, the pressure relief coefficient is increased. The critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle. In response to a longitudinal slope angle greater than zero and a braking pressure greater than the dwell braking pressure threshold, the pressure relief coefficient is reduced. The dwell braking pressure threshold is proportional to the absolute value of the longitudinal slope angle. In response to a longitudinal slope angle less than zero and an estimated net acceleration force greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, vehicle weight, and throttle opening degree.

[0009] This invention focuses on the starting operation of a vehicle in automatic parking mode. It dynamically adjusts the parking release control parameters based on real-time road information and vehicle parameters, and releases the automatic parking state based on these adjusted parameters. This continuously optimizes the fixed parameters under the automatic parking function, adapting to individual manufacturing differences in different vehicles. It effectively avoids starting anomalies such as vehicle rollback, dragging, and sudden acceleration, improving the safety and smoothness of starting on slopes while enhancing the user's driving experience and the vehicle's intelligent control level, thus significantly improving the starting quality of the vehicle in automatic parking mode. Furthermore, this invention uses longitudinal slope angle to identify slope conditions and combines vehicle operating parameters such as driveshaft torque and braking pressure to dynamically adjust the pressure relief coefficient. This ensures that the automatic parking release process accurately matches the actual starting state and road conditions, effectively avoiding problems such as rollback, dragging, and excessive impact during starting. Furthermore, this invention adjusts the pressure relief coefficient in different scenarios based on the longitudinal slope angle and parameters such as drive shaft torque, braking pressure, throttle opening and closing degree, and vehicle weight. It also uses the critical slip torque threshold, the stall braking pressure threshold, and the weighted estimated net acceleration force associated with the longitudinal slope angle to determine various starting anomalies. This enables the automatic parking release control to more accurately adapt to starting conditions on different slopes, effectively avoiding problems such as slipping on uphill slopes, dragging on uphill slopes, and lurching caused by excessive acceleration on downhill slopes. This greatly improves the safety, smoothness, and handling stability of the vehicle when starting on a slope.

[0010] In one optional implementation, releasing the automatic parking state according to the adjusted parking release control parameters includes: Release the automatic parking status using the adjusted parking release control parameters.

[0011] This invention uses the adjusted parking release control parameters directly for the release of the current automatic parking state, which can correct the control deviation in the current start-up process in real time and immediately, thereby quickly suppressing abnormal situations such as slippage, dragging, and sudden acceleration that may occur during the start-up process, and improving the response speed, smoothness and safety of the start-up. At the same time, the control process does not need to wait for the next working condition to be triggered, and the adjustment is more direct and timely, which is conducive to improving the driver's driving experience and the real-time performance of the vehicle control.

[0012] In one optional implementation, the vehicle parameters also include the vehicle type and current load; increasing the pressure relief coefficient includes: The amplification factor of the pressure relief coefficient is determined based on the vehicle model and the current load. The pressure relief coefficient is then amplified based on the amplification factor, which is inversely proportional to the current load.

[0013] In one alternative implementation, reducing the pressure relief coefficient includes: The reduction factor of the pressure relief coefficient is determined based on the vehicle model and the current load. The pressure relief coefficient is then reduced based on the reduction factor, which is proportional to the current load.

[0014] This invention, when adjusting the pressure relief coefficient, further incorporates vehicle parameters such as vehicle model and current load as adjustment criteria. It sets an increasing coefficient in the reverse direction and a decreasing coefficient in the forward direction based on different loads. This allows the adjustment range of the pressure relief coefficient to precisely match the actual load state of the vehicle, preventing the vehicle's parking release from being too fast or too slow due to load changes. This effectively improves the stability, safety, and smoothness of vehicle starting under different load conditions. Simultaneously, by associating the adjustment coefficient with the load, the vehicle starting control strategy becomes more adaptable, more precise, and has a wider range of applications, thereby greatly enhancing the user's driving experience and the level of intelligent vehicle control.

[0015] In one optional implementation, adjusting the parking release control parameters further includes: The pressure relief coefficient is adjusted using calculation rules to keep it within a preset threshold range; the calculation rules include at least one of addition and subtraction operations, mapping operations based on simulation curves, exponential operations, and logarithmic operations.

[0016] In one optional implementation, the vehicle start-up control method further includes: storing the current adjustment record in a start-up parameter learning library, periodically calling the record samples in the start-up parameter learning library to train the AI ​​decision-making model; and using the AI ​​decision-making model to output release control reference parameters based on the road surface information and vehicle parameters collected each time the vehicle starts.

[0017] In one optional implementation, releasing the automatic parking state according to the adjusted parking release control parameters includes: If the difference between the adjusted parking release control parameter and the release control reference parameter is less than the error threshold, the automatic parking state is released using the release control reference parameter, and an AI positive result is accumulated once.

[0018] In one optional implementation, the vehicle start-up control method further includes: If the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is not less than the safety ratio, then the automatic parking state is released using the release control reference parameter, and one negative AI result is accumulated.

[0019] In one optional implementation, the vehicle start-up control method further includes: if the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is less than the safety ratio value, then the adjusted parking release control parameter is used to release the automatic parking state, and an AI negative result is accumulated once.

[0020] This invention achieves intelligent learning and iterative optimization of automatic parking release parameters by storing vehicle start-up adjustment records, constructing a learning library, and training an AI decision-making model to output AI reference parameters for automatic parking release control. When the automatic parking state is released, it performs hierarchical judgment and adaptive selection based on the difference between the adjusted parameters and the AI ​​reference parameters, and the ratio of positive AI results. This ensures safe and reliable start-up while gradually improving the accuracy and applicability of AI decisions, upgrading parking release control from traditional rule-based control to intelligent decision-making control. It not only avoids the limitations of a single control logic but also provides a safety margin through error thresholds and safety ratios. While improving the smoothness and intelligence of hill starts, it ensures the safety and stability of the entire vehicle start-up process. The control strategy possesses self-learning, self-adaptive, and self-optimizing capabilities, making it applicable to a wider range of scenarios and with higher engineering application value.

[0021] In a second aspect, the present invention provides a vehicle start-up control device, the device comprising: The adjustment module is used to respond to the vehicle's starting operation in automatic parking mode. Based on the current road information and vehicle parameters, it adjusts the parking release control parameters, including the pressure relief coefficient. The control module is used to release the automatic parking state according to the adjusted parking release control parameters; Among them, road surface information includes longitudinal slope angle, vehicle parameters include drive shaft torque and braking pressure, and parking release control parameters include pressure relief coefficient; Based on the current road conditions and vehicle parameters, adjust the parking release control parameters, including any one of the following: In response to a longitudinal slope angle greater than zero and a drive shaft torque less than the critical slip torque threshold, the pressure relief coefficient is increased. The critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle. In response to a longitudinal slope angle greater than zero and a braking pressure greater than the dwell braking pressure threshold, the pressure relief coefficient is reduced. The dwell braking pressure threshold is proportional to the absolute value of the longitudinal slope angle. In response to a longitudinal slope angle less than zero and an estimated net acceleration force greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, vehicle weight, and throttle opening degree.

[0022] The vehicle start control device of the present invention focuses on the starting operation of the vehicle in automatic parking mode. Specifically, it dynamically adjusts the parking release control parameters through real-time road information and vehicle parameters, and releases the automatic parking state based on the adjusted parking release control parameters. It can continuously optimize the fixed parameters under the automatic parking function, thereby adapting to the individual manufacturing differences of different vehicles. It not only effectively avoids abnormal starting situations such as vehicle rollback, dragging, and sudden acceleration, but also improves the safety and smoothness of starting the vehicle on a slope. At the same time, it greatly enhances the user driving experience and the level of intelligent vehicle control.

[0023] Thirdly, the present invention provides a vehicle, the vehicle including a controller, the controller including a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the vehicle starting control method of the first aspect or any corresponding embodiment described above.

[0024] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle start-up control method of the first aspect or any corresponding embodiment thereof.

[0025] The vehicle start-up control method and device provided by this invention only initiate the subsequent parameter acquisition and anomaly judgment process when the automatic parking function is activated and the vehicle is in a slope condition. This reduces the computing power consumption of the vehicle controller and allows control resources to focus on core problem scenarios such as vehicle rollback, dragging, and sudden acceleration, greatly improving control efficiency and targeting. Furthermore, in response to vehicle start-up, the parking release control parameters are dynamically adjusted through real-time road information and vehicle parameters. This can accurately identify various slope start-up anomalies and adopt adaptive parameter adjustment schemes for each anomaly, realizing dynamic adaptation of the control strategy to individual vehicle characteristics. This solves the technical problem that the fixed calibration parameters under the traditional automatic parking function cannot adapt to the differences in vehicle manufacturing and slope conditions. It not only avoids the occurrence of vehicle rollback, dragging, and sudden acceleration during start-up, improving the smoothness of vehicle start-up, but also effectively enhances the user driving experience and the level of vehicle intelligent control. Attached Figure Description

[0026] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0027] Figure 1This is a schematic flowchart of a first embodiment of a vehicle start-up control method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a second process for a vehicle start-up control method according to an embodiment of the present invention; Figure 3 This is a flowchart illustrating the adaptive control process of the automatic parking function; Figure 4 This is a schematic diagram of the adaptive control process for another automatic parking function; Figure 5 This is a schematic diagram of the third process of the vehicle start-up control method according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a vehicle starting control device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the vehicle structure according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the basic module for the storage medium of the automatic parking function. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] According to an embodiment of the present invention, a vehicle start-up control method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a vehicle start-up control method. Figure 1 This is a schematic flowchart of a first embodiment of a vehicle start-up control method according to the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: In response to the vehicle's start-up operation in automatic parking mode, adjust the parking release control parameters based on the current road information and vehicle parameters.

[0031] In this embodiment, this step means that when the vehicle is in a state where automatic parking is activated and the vehicle remains stationary, when the driver performs a starting operation (such as pressing the accelerator pedal), the current road surface information and vehicle status parameters are immediately collected in real time, and the parking release control parameters are dynamically and adaptively adjusted based on the collected real-time information. Specifically, this embodiment uses the starting operation as the control trigger time, which can ensure that the adjustment action responds synchronously with the driver's starting intention; at the same time, the current real-time road surface information and vehicle parameters are used as the basis for adjustment, so that the parking release control parameters are no longer fixed calibration values, but are precisely matched with the actual slope, load, and vehicle status; thus, parameter optimization is completed in the initial stage of starting, laying the control foundation for the subsequent smooth release of automatic parking and avoiding abnormalities such as dragging, rolling backward, and sudden acceleration, improving the real-time performance, accuracy, and adaptability of the entire starting process.

[0032] It should be noted that in this embodiment, "automatic parking activated" means that the automatic parking function is currently activated in the vehicle. The specific activation method of this function can be adapted by referring to relevant content in this field. For example, the activation methods of the automatic parking function are mainly divided into manual active activation (such as operating a dedicated physical button on the vehicle) and automatic trigger activation (some models will automatically activate this function according to the driving scenario, such as in a vehicle start-stop scenario: after the driver presses the brake pedal to bring the vehicle to a complete stop, the system automatically activates automatic parking, and the vehicle remains stationary after the brake pedal is released). In this embodiment, "responding to vehicle start-up" refers to recognizing the driver's intention to start, which can be recognized by the driver releasing the brake pedal or pressing the accelerator pedal.

[0033] It should be explained that the specific content of the road surface information in this embodiment can be adaptively adjusted based on actual needs. For example, the road surface information is slope information used to characterize the tilt angle and tilt direction of the road surface where the vehicle is currently located, such as the longitudinal slope angle; in some scenarios, it can be extended to include auxiliary information such as the road surface friction coefficient, such as icy / waterlogged roads, which can be obtained by relying on the vehicle's existing sensors, such as the Inertial Measurement Unit (IMU), and is only used as an example.

[0034] To further explain, the vehicle status parameters in this embodiment can reflect the vehicle's starting state and are used to determine relevant data for starting abnormalities. For example, before the automatic parking function is released, the parameters are static / pre-start parameters, such as basic status parameters: slope information (already acquired in advance to confirm whether adaptive operation is activated), initial pressure relief coefficient (system-preset calibration parameter), and indirect signals related to the vehicle's current load (such as suspension sensor signals); and power preparation parameters: initial torque of the drive motor (initial torque increase value), initial throttle opening value (signal of the driver's throttle input), etc.; the parameters during the release process are dynamic / execution parameters, such as wheel speed signals, IMU acceleration signals, real-time changes in drive torque, and brake pressure changes, etc. This is only an example, and the specific content of the vehicle status parameters can be adaptively adjusted according to actual needs.

[0035] To further clarify, the parking release control parameter in this embodiment specifically refers to the core control parameter that determines the timing and rate of automatic parking function release. The specific content of this parameter can be adaptively adjusted according to actual needs. Note that the parking release control parameter in this embodiment is directly related to the hydraulic pressure relief speed of the braking system; that is, the larger the parameter value, the slower the brake pressure relief and the later the automatic parking release; the smaller the value, the faster the brake pressure relief and the earlier the automatic parking release.

[0036] Step S102: Release the automatic parking state according to the adjusted parking release control parameters.

[0037] It should be noted that this step includes two implementation methods: using the adjusted parking release control parameters for the current automatic parking state release, and using the adjusted parking release control parameters for the next automatic parking state release under the same operating conditions. In this embodiment, using the adjusted parking release control parameters for the current automatic parking state release means that after identifying the current starting condition and adjusting the parking release control parameters, the adjusted parameters are directly used to execute the current automatic parking release process. This design takes into account that "the vehicle has experienced or is about to experience starting abnormalities such as rolling backwards, dragging, or sudden acceleration during the current starting process, requiring immediate correction and intervention." Therefore, this type of automatic parking state release implementation method can correct the control deviation of the current start in real time, quickly suppress problems such as impact, sudden acceleration, and rolling backwards during the current starting process, improve the response speed, smoothness, and safety of the current start, and provide a more direct and timely control method, which can quickly improve the driver's driving experience.

[0038] To further explain, in this embodiment, the adjusted parking release control parameters are used to release the automatic parking state under the same working conditions. This means that the parking release control parameters adjusted during this start are stored. When the vehicle starts under the same working conditions in subsequent starts (such as when the vehicle is on the same slope, with the same load, and on the same road surface), the adjusted parameters are directly reused to execute the automatic parking release. (That is, the control parameters for the release of the automatic parking function are continuously optimized, and the currently adjusted control parameters are applied to the next vehicle hill start control.) This design takes into account that "the vehicle's force characteristics and starting requirements are consistent under the same working conditions, and the optimal adjustment parameters can be directly adapted to subsequent starts under the same working conditions, avoiding repeated trials and anomalies." Therefore, this type of automatic parking state release implementation method can achieve self-learning and adaptive optimization of the control parameters under the same working conditions, making the vehicle's starting process smoother and more stable in the same scenario, avoiding repeated starting anomalies; at the same time, it does not require readjustment for each start, reducing control fluctuations, improving the consistency, reliability, and intelligence level of the control strategy, and does not require additional hardware, making it easy to implement in engineering.

[0039] The vehicle start control method provided in this embodiment focuses on the start operation of the vehicle in automatic parking mode. It dynamically adjusts the parking release control parameters based on real-time road information and vehicle parameters, and releases the automatic parking state based on the adjusted parking release control parameters. It can continuously optimize the fixed parameters under the automatic parking function, thereby adapting to the individual manufacturing differences of different vehicles. It can effectively avoid abnormal starting of the vehicle such as rolling back, dragging, and sudden acceleration, improve the safety and smoothness of starting the vehicle on the slope, and greatly improve the user driving experience and the level of intelligent vehicle control, thus significantly improving the starting quality of the vehicle in automatic parking mode.

[0040] It should be noted that the method designed in this embodiment, which uses adjusted parking release control parameters to release the automatic parking state under the same operating conditions, provides users with a continuous and stable improvement in the starting experience, avoiding repeated problems. It not only achieves a qualitative leap in vehicle starting from "adaptive control" to "self-learning," laying the foundation for lifelong learning and performance evolution, but also extends safety and comfort guarantees from a "single process" to the "entire vehicle lifecycle," achieving long-term optimization of the overall experience. Based on this, this embodiment provides a vehicle starting control method. Figure 2 This is a schematic diagram of a second process for a vehicle start-up control method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: In response to the vehicle's start-up operation in automatic parking mode, adjust the parking release control parameters based on the current road information and vehicle parameters.

[0041] In this embodiment, vehicle parameters include vehicle wheel speed and vehicle acceleration; road surface information includes longitudinal slope angle; and parking release control parameters include pressure relief coefficient.

[0042] In practical applications, vehicle start-up smoothness issues may stem from various underlying causes, such as insufficient drive system output (leading to rollback) or improper brake system release (leading to dragging / lurching). In this embodiment, vehicle parameters are wheel speed and acceleration. These parameters directly reflect the vehicle's motion state and allow for intuitive perception of the actual performance during the start-up process. For example, the direction of wheel speed directly reflects whether the vehicle is rolling back, and the rate of change of acceleration directly reflects the start-up smoothness. This approach judges the problem from the "result" level and uses the vehicle's motion results for feedback control (with a slightly slower response time, requiring waiting for motion to occur). This ensures that the system can accurately identify abnormal phenomena that have occurred or are occurring, and then uses the adjusted parking release control parameters for the next automatic parking release under the same operating conditions (aiming to accumulate experience to form personalized adaptation, avoid the recurrence of the same problem, and make the vehicle's start-up performance better with each use).

[0043] It should be noted that this embodiment uses the longitudinal slope angle to determine whether the vehicle is in a slope condition; where slope condition refers to whether the road surface where the vehicle is currently located is uphill or downhill. Note that this embodiment can also determine whether the vehicle is currently in a slope condition based on multiple road surface information such as slope angle and inclination direction, so as to improve the accuracy of slope condition determination.

[0044] Furthermore, this embodiment utilizes vehicle wheel speed and vehicle acceleration to determine abnormal vehicle starting conditions (i.e., abnormal hill start, specifically referring to abnormal phenomena / situations caused by the mismatch between the timing of automatic parking release and power output when the vehicle is starting on a slope), such as vehicle rollback, dragging, and jerking. Among these, rollback refers to the wheels sliding in the opposite direction to the expected direction of travel during the starting phase, such as the vehicle rolling backward in drive gear; dragging refers to the automatic parking release not being timely, causing the power system and braking system to clash, resulting in jerky starting and abnormally slow acceleration; jerking refers to the phenomenon where, during the starting process, due to excessively rapid brake release, insufficient braking force, and the superposition of factors such as road slope and vehicle power, the vehicle's speed suddenly increases and acceleration changes drastically in a short period of time, manifested as abnormally rapid forward lurching, jerking, and lurching.

[0045] In this embodiment of the invention, the longitudinal slope angle is used to identify the slope condition, and the wheel speed and acceleration are combined to accurately perceive the real-time status of the vehicle. The automatic parking release is achieved through the pressure relief coefficient, which can overcome the limitations of traditional fixed calibration. It not only accurately matches the slope start control requirements, but also effectively avoids abnormal starting conditions such as vehicle slippage, dragging, and sudden acceleration. It greatly improves the safety and smoothness of vehicle starting, while also significantly enhancing the user driving experience and the level of vehicle intelligent control.

[0046] In this embodiment, step S201 above adjusts the parking release control parameters based on the current road surface information and vehicle parameters, including any one of the following: 1. In response to a longitudinal slope angle greater than zero and a vehicle wheel speed less than zero, the pressure relief coefficient is increased.

[0047] It should be noted that in this embodiment, "responding to a longitudinal slope angle greater than zero and a vehicle wheel speed less than zero" indicates that the vehicle is sliding backward on an uphill slope. That is, during the process of starting on an uphill slope, due to excessively rapid brake release, insufficient braking force, or failure of the driving force to keep up in time, the vehicle overcomes the braking effect and slides backward along the slope, which is manifested as a sudden reverse speed change and backward slip of the vehicle body when starting, which poses a safety hazard.

[0048] In one specific embodiment, whether a vehicle has rolled backwards can be determined based on the vehicle wheel speed signal (i.e., vehicle wheel speed). Specifically, if the wheel speed signal indicates that the direction of wheel rotation is opposite to the vehicle's expected direction of travel, it is determined that the vehicle has rolled backwards. For example, the expected direction of travel is directly determined by the vehicle's current gear position. If the gear is a forward gear (e.g., D), the expected direction of travel is forward; if the gear is a reverse gear (e.g., R), the expected direction of travel is backwards. This direction is used as a reference and compared with the actual direction of wheel rotation identified by the wheel speed sensor to determine whether the vehicle has rolled backwards. Note that the vehicle wheel speed signal in this embodiment has positive and negative values. These values ​​are essentially digital representations of the wheel speed direction, determined by a preset judgment standard set by the vehicle controller, specifically including: (1) Positive wheel speed (ν>0): This corresponds to the vehicle rotating in the direction the driver intends to drive. For example, the wheels rotate forward when in forward gear and backward when in reverse gear. Both are considered positive wheel speeds.

[0049] (2) Negative wheel speed (ν < 0): This corresponds to the vehicle turning in the opposite direction to the driver's intended direction of travel. For example, when the vehicle is in forward gear, the wheels turn backward (rolling uphill when starting), and when the vehicle is in reverse gear, the wheels turn forward (rolling downhill when reversing). Both are considered negative wheel speeds.

[0050] In summary, this embodiment of the invention directly uses the matching relationship between wheel speed direction and the vehicle's expected driving direction as the criterion for judgment, defining slippage as the wheels rotating in the opposite direction to the driving intention. This aligns with the user's actual perception of slippage, avoiding the risk of misjudging the magnitude of wheel speed and accurately anchoring the core abnormal feature of unexpected reverse sliding, thus greatly improving the accuracy of vehicle slippage identification.

[0051] 2. In response to the longitudinal slope angle being greater than zero and the rate of change of vehicle acceleration within the first preset time period after starting being greater than the first preset threshold, the pressure relief coefficient is reduced, and the starting time of the first preset time period is greater than the first time value.

[0052] It should be noted that in this embodiment, "responding to a longitudinal slope angle greater than zero and the rate of change of vehicle acceleration within a first preset time period after starting being greater than a first preset threshold" indicates that the vehicle is experiencing uphill drag. That is, during the uphill start-up process, due to slow brake release and excessive braking force, the driving force cannot overcome the braking resistance in time, and the vehicle is first stalled and stationary. After the driving force is greater than the braking resistance and the slope resistance, it suddenly surges forward and produces a jerking and impact abnormal phenomenon, which manifests as delayed start-up, jerking, and sudden and violent changes in vehicle speed.

[0053] In one specific embodiment, whether a vehicle is dragging can be determined based on the vehicle acceleration signal (i.e., vehicle acceleration). Specifically, the rate of change of the vehicle acceleration signal within a first preset time period is calculated (note that the rate of change of the acceleration signal refers to the instantaneous change in the vehicle's longitudinal acceleration within the preset time period after automatic parking is released, reflecting the dynamic fluctuation of acceleration over time. The specific value of the first preset time period can be adaptively determined according to actual needs and is not limited in detail here). If the rate of change is greater than a first preset threshold (note that the specific value of the first preset threshold can be personalized based on differences in vehicle manufacturing consistency and subjective experience of smooth start-up, to adapt to the power requirements of different vehicle models and individual vehicles), it is determined that the vehicle is dragging. Specifically, by using the rate of change of the acceleration signal as a criterion, the essence of dragging can be accurately captured, namely, the conflict between power and braking when the brakes are not fully released, leading to sudden acceleration changes or abnormal gradual increases. Compared to a single acceleration value, using the rate of change of acceleration can more sensitively distinguish between normal start-up acceleration and dragging / jerked acceleration, thereby significantly reducing the probability of misjudgment and improving the accuracy of identifying vehicle dragging.

[0054] In this embodiment, the first time value represents the moment of sudden speed change during uphill start, i.e., the moment when the vehicle suddenly accelerates from a stationary, halted state. The timing design in this embodiment, where the start time of the first preset time period is greater than the first time value, means that the rate of change of vehicle acceleration is only detected and judged after the sudden speed change occurs during uphill start. It should be noted that this timing design takes into account that during actual uphill start, the vehicle is in a stationary, stalled state before the speed change, with a small change in acceleration that cannot effectively reflect drag characteristics. After the speed change, the vehicle will experience a significant acceleration change due to drag, and detecting the rate of change of acceleration at this time can more accurately and reliably identify uphill drag conditions. Through the above practical considerations, the invalid detection interval before the speed change can be effectively avoided, interference signals during the stationary phase can be eliminated, the accuracy and robustness of drag judgment can be improved, and misjudgments and omissions can be avoided. This ensures the timeliness and accuracy of subsequent pressure relief coefficient adjustment, and improves the smoothness and safety of uphill start.

[0055] 3. In response to the longitudinal slope angle being less than zero and the rate of change of vehicle acceleration within the second preset time period after starting being greater than the second preset threshold, the pressure relief coefficient is increased, the starting time of the second preset time period is less than the second time value, and the first time value is greater than the second time value.

[0056] It should be noted that in this embodiment, "responding to a longitudinal slope angle greater than zero and a vehicle wheel speed less than zero" represents a vehicle lurching forward on a downhill slope. This refers to an abnormal phenomenon where, during a downhill start, the vehicle suddenly accelerates abnormally forward due to excessively rapid brake release and insufficient braking force, under the combined influence of gravity and driving force. This manifests as a sharp increase in vehicle speed, a significant change in acceleration, and body lurching, resulting in decreased ride comfort and driving stability. Note that the specific values ​​of the second preset time period and the second preset threshold in this embodiment can be adaptively determined according to actual needs. For a more detailed understanding, please refer to the relevant content on the first preset time period and the first preset threshold mentioned above; no detailed limitations are provided here.

[0057] In this embodiment, the second time value represents the moment of sudden speed change during downhill start-up, i.e., the moment when the vehicle suddenly accelerates from a stationary state. The timing design in this embodiment, where the start time of the second preset time period is less than the second time value, means that the detection and judgment of the vehicle's acceleration change rate begins before the sudden speed change occurs during downhill start-up. It should be noted that this timing design takes into account that in actual downhill start-up, the vehicle already has a tendency to surge forward before the speed change, and the acceleration will change significantly in advance. If detection is only performed after the speed change, the delayed judgment will result in the surge already occurring and being unable to be suppressed in time. By starting to detect the acceleration change rate before the speed change, the tendency for downhill surge can be identified in advance, enabling earlier and more timely prediction and intervention, effectively preventing surge, improving the real-time, forward-looking, and accurate nature of downhill surge judgment, ensuring the timeliness and effectiveness of subsequent pressure relief coefficient adjustment, and improving the smoothness and safety of the vehicle's downhill start-up.

[0058] It should be noted that in this embodiment, the first time value refers to the moment of sudden speed change during uphill dragging; where the speed change point during uphill dragging occurs late, the vehicle can only move after the driving force has accumulated enough to "push open" the braking pressure, that is, the vehicle speed suddenly jumps from 0 to a clearly positive value, resulting in a jerking / impact; the second time value refers to the moment of sudden speed change during downhill lurching; where the speed change point during downhill lurching occurs early, the vehicle moves immediately the moment the braking pressure drops below the "downhill holding force", that is, the vehicle speed suddenly and rapidly increases from a standstill, resulting in lurching. Therefore, in this embodiment, considering that the braking release is too slow during uphill dragging, and the power is accumulated enough to break through the brakes, the speed change point is the moment when the driving force overcomes the brakes (later); while the braking release is too fast during downhill lurching, and gravity suddenly propels the vehicle forward, the speed change point is the moment when the brakes are insufficient to resist the downward force (earlier), therefore, the speed change point during uphill dragging is designed to be greater than the speed change point during downhill lurching.

[0059] It should be noted that a larger pressure relief coefficient results in slower brake pressure relief and later automatic parking release; conversely, a smaller pressure relief coefficient results in faster brake pressure relief and earlier automatic parking release. In this embodiment, when the vehicle rolls downhill, the pressure relief coefficient is increased to delay the brake release timing and counteract the vehicle's reverse sliding tendency; when the vehicle is dragging, the pressure relief coefficient is decreased to advance the brake release timing and alleviate the conflict between power and braking; when the vehicle lurches forward, the pressure relief coefficient is increased to slow down the brake pressure relief speed, delay the automatic parking release timing, and prolong the braking force holding time, counteracting the tendency of the vehicle to lurch forward too quickly due to the gravity component on the downhill slope, thereby suppressing lurching forward on the downhill slope.

[0060] Note that in this embodiment, the pressure relief coefficient can be increased or decreased by multiplying the current pressure relief coefficient by a preset correction coefficient. For example, increasing the pressure relief coefficient is achieved by multiplying the current pressure relief coefficient by a preset correction coefficient greater than 1; decreasing the pressure relief coefficient is achieved by multiplying the current pressure relief coefficient by a preset correction coefficient less than 1.

[0061] It should be noted that since the pressure relief coefficient is a constant, other calculation rules can also be used to adjust the data to meet the personalized parameter adjustment needs of different vehicle models and different starting states. Therefore, the adjustment of the pressure relief coefficient in this embodiment also includes: adjusting the pressure relief coefficient using calculation rules to keep the adjusted pressure relief coefficient within a preset threshold range; wherein, the calculation rules include at least one of addition and subtraction operations, mapping operations based on simulation curves, exponential operations, and logarithmic operations.

[0062] In this embodiment, addition and subtraction operations can directly increase or decrease a fixed offset. Using the initial pressure relief coefficient k0 as a benchmark, a fixed value is directly added or subtracted based on phenomena such as vehicle slippage, dragging, or sudden acceleration. The formula can be simplified to: k = k0 ± Δk, where Δk is a preset fixed offset. If the vehicle slips / accelerates, the pressure relief coefficient needs to be increased; therefore, Δk = 0.05. If k0 = 1.0, the corrected pressure relief coefficient is: k 修正 =1.0 + 0.05 = 1.05 (equivalent to 105% percentage correction); When the vehicle is towed, the pressure relief coefficient needs to be reduced. Similarly, assuming Δk = 0.05, the corrected pressure relief coefficient is: k 修正 =1.0 - 0.05 = 0.95 (equivalent to 95% percentage correction). Specifically, this type of operation is simple to calculate and has a direct response, making it suitable for scenarios where the correction accuracy requirement is not high and rapid adjustment is needed.

[0063] In this embodiment, the mapping operation based on the simulated curve is dynamically adapted according to a preset curve. This means a continuous curve, such as a linear curve or a quadratic curve, is preset and related to vehicle conditions, such as the degree of slippage and the duration of drag. The corresponding correction value is matched from the curve based on the actual degree of anomaly, rather than a fixed offset. For example, a linear curve is set for the slippage distance and the correction coefficient, where the longer the slippage distance, the greater the increase in the correction coefficient (e.g., the pressure relief coefficient is 1.05 after correction for a 5cm slippage, and 1.10 after correction for a 10cm slippage). When the vehicle is dragging, a quadratic curve is set based on the acceleration gradient exceeding the limit, where the greater the exceedance, the gentler the decrease in the correction coefficient, to avoid over-correction leading to slippage. Specifically, this type of operation provides finer correction, can adapt to different degrees of abnormal operating conditions, and improves smoothness.

[0064] Note that the specific selection of the operation rules in this embodiment can be adaptively adjusted according to actual needs. Specifically, by setting diverse operation rules and flexibly selecting them according to actual scenarios, such as addition and subtraction suitable for rapid linear adjustment, simulation curve mapping adapted to fine correction of different degrees of anomalies, and exponential or logarithmic operations to achieve non-linear precise control, the personalized parameter adjustment needs of different vehicle models and different starting states can be met. This improves the accuracy of parameter adjustment and further enhances the smoothness of starting on slopes, greatly optimizing the driving experience. Specifically, this embodiment adopts a reverse adaptation adjustment strategy for different causes of vehicle slippage, dragging, and jerking. That is, when the vehicle slips, the pressure relief coefficient is increased to delay brake release and counteract the reverse slipping trend; when the vehicle drags, the pressure relief coefficient is decreased to release brake earlier and alleviate the conflict between power and braking. This can achieve a precise correspondence between the anomaly type and the adjustment direction, and quickly improve the smoothness of vehicle starting.

[0065] In this embodiment, by using wheel speed and acceleration signals to determine when a vehicle experiences rollback, dragging, or sudden acceleration, an abnormal hill start can be identified. This necessitates adjusting the pressure relief coefficient of the vehicle's automatic parking function release and using the adjusted coefficient to control the subsequent release of the automatic parking function under incline conditions. By using wheel speed and acceleration signals to determine typical types of abnormal vehicle starts, redundant parameters are eliminated, achieving a direct correspondence between phenomena and parameters. This simplifies the judgment logic and improves the real-time performance and accuracy of anomaly identification.

[0066] In summary, this invention addresses different starting scenarios such as uphill and downhill, and combines the vehicle's wheel speed and acceleration change rate to accurately identify starting anomalies such as slippage, dragging, and sudden acceleration, making the vehicle's control logic more closely match actual hill start conditions. Furthermore, it designs a corresponding adjustment scheme for the pressure relief coefficient, effectively suppressing slippage and alleviating starting drag on uphill sections, while increasing the pressure relief coefficient to suppress unexpected acceleration on downhill sections, thereby optimizing starting smoothness and significantly improving the safety and driving experience of hill starts. Simultaneously, it accurately identifies various starting anomalies based on a preset time period, making the adjustment strategy precise and controllable, thus greatly enhancing the accuracy and anti-interference capability of vehicle starting control.

[0067] Step S202: Release the automatic parking state according to the adjusted parking release control parameters.

[0068] Specifically, step S202 includes: Step S2021: Use the adjusted parking release control parameters to release the automatic parking state under the same working conditions for the next time.

[0069] It should be noted that in this embodiment, if the vehicle is not in a slope condition, or if the vehicle does not have an abnormal start on a slope, the pressure relief coefficient of the vehicle's automatic parking function is maintained. Specifically, by keeping the pressure relief coefficient unchanged when the vehicle is in a non-slope condition with no risk of slipping or when starting normally on a slope, unnecessary parameter fluctuations that could lead to a decrease in start-up smoothness can be avoided. For example, misadjusting the pressure relief coefficient on a flat road could cause jerking or hesitation, thus ensuring the consistency and stability of the driving experience in normal scenarios.

[0070] In this embodiment of the invention, by designing and using the adjusted parking release control parameters to release the automatic parking state under the same working conditions, the automatic parking release parameters under the same working conditions can be self-learned and adaptively optimized to form continuously optimized control logic. This avoids repeated starting abnormalities such as rolling back, dragging, and sudden acceleration under the same road conditions, and greatly improves the stability, smoothness, and safety of vehicle starting on slopes.

[0071] In one specific embodiment, considering that once calibration is completed, the relevant parameters will be fixed; however, for different vehicles of the same model, there are often abnormal phenomena such as rolling backward, dragging, and jerking when starting on an incline due to differences in manufacturing consistency, resulting in varying degrees of complaints about the smoothness of the start. Based on this, this embodiment provides an adaptive control scheme for the automatic parking function to address the rolling backward and dragging phenomena only when starting on an uphill slope. According to the actual situation of the vehicle, the rolling backward and dragging phenomena when starting on an incline are identified, and the pressure relief coefficient of the automatic parking function is adaptively adjusted to solve the driving experience problems caused by the fixed calibration parameters in the prior art. Figure 3 This is a flowchart illustrating the adaptive control process of the automatic parking function; as shown in the diagram, the process includes the following steps: Step S1: First, determine whether the vehicle is in the automatic parking function working state. This can be determined by the vehicle's own functional modules.

[0072] In this embodiment, determining whether the automatic parking function is in operation can be done simply by the function itself.

[0073] Step S2: If the vehicle is in the automatic parking function working state, obtain the current road condition of the vehicle.

[0074] In this embodiment, the road surface status, i.e., road surface information, can be represented by objective data such as slope α. If slope α > 0%, proceed to the next step; if slope α ≤ 0%, the adaptive adjustment function is not activated.

[0075] Step S3: When the vehicle starts moving, obtain the relevant parameters of the automatic parking function before and after it is released.

[0076] In this embodiment, when the automatic parking function is working, the vehicle is stationary. During the start-up process, the vehicle wheel speed signal, IMU acceleration signal, drive torque signal, and throttle opening signal are acquired. The function is released under the following conditions: ① the throttle is in the working state, ② the gear signal is forward gear, and ③ the drive torque reaches the set value.

[0077] It should be noted that during the initial calibration process, the torque setting value is k0×T0; where T0 is the theoretical torque required for vehicle start-up, a linear fixed value corresponding to the slope α, calculated and determined in the calibration model; when the system detects that the throttle opening signal and torque value have reached the set state, the automatic parking function is released. Based on the subjective experience of the actual vehicle during the automatic parking function calibration, T0 is usually corrected by a coefficient of k0, which is the initial pressure relief coefficient. Generally, this value ranges from 0.7 to 1.4, and this value is obtained from experimental calibration; the initial value of the automatic parking function pressure relief coefficient has been determined during the vehicle design calibration stage (its specific value is related to factors such as slope, load, and vehicle type); this embodiment aims to automatically adjust the pressure relief coefficient based on the vehicle's performance during use to avoid abnormal vehicle start-up on slopes.

[0078] Step S4: Based on the vehicle's starting situation, automatically determine whether there is any slippage or dragging, automatically correct the pressure relief coefficient, and apply it to the next working process.

[0079] In this embodiment, the logic for adjusting the automatic parking function pressure relief coefficient value based on the current vehicle movement is determined by Table 1, as follows.

[0080] Table 1

[0081] It should be noted that in this step, during the automatic parking release process, the vehicle's rolling speed and acceleration are monitored to determine whether it is slipping or dragging. Specifically, the forward wheel speed can be set to positive and the reverse wheel speed to negative. If the vehicle's wheel speed signal ν < 0, it is determined to be slipping. Furthermore, if ν ≥ 0, the IMU acceleration signal is monitored. When the acceleration change gradient Δa is greater than a first preset threshold (denoted as λ), it is determined to be dragging. The specific value of λ can be given based on subjective performance during calibration. When the vehicle slips or drags, k0 is corrected by a percentage constant N, and the pressure relief coefficient after correction is k. 修正 =N×k0; If the vehicle rolls off the slope (i.e., ν < 0), the value of N is set to 105%; if it is dragged (i.e., ν ≥ 0 and Δa > λ), The N value is set to 95%.

[0082] In this embodiment, Figure 4 This is a flowchart illustrating the adaptive control process for another automatic parking function. As shown in the diagram, the detailed implementation process of the adaptive control for the automatic parking function includes: Step 401: Determine whether the vehicle's automatic parking function is in operation.

[0083] In this embodiment, if the system is in a working state, the next step 402 is performed; otherwise, no operation is performed and the system waits for the next cycle.

[0084] Step 402: Obtain the current road surface status of the vehicle.

[0085] In this embodiment, the objective data is the slope α, and step 403 is executed.

[0086] Step 403: Determine whether the obtained slope is greater than 0%.

[0087] In this embodiment, if the slope α > 0%, then step 404 is executed; otherwise, step 409 is executed.

[0088] Step 404: Obtain relevant parameters before and after the automatic parking function is released, including wheel speed signal, IMU acceleration signal, drive torque signal, and throttle opening signal.

[0089] In this embodiment, this step is performed when the vehicle starts moving.

[0090] Step 405: Determine if the vehicle is rolling backwards.

[0091] In this embodiment, the vehicle is judged to have rolled backwards based on the signal in step 404. Specifically, the forward wheel speed is set to be positive and the reverse wheel speed is set to be negative. If the vehicle wheel speed signal ν < 0, it is judged to have rolled backwards. If rolling backwards occurs, proceed to the next step 406. If rolling backwards does not occur, proceed to step 407.

[0092] Step 406, the pressure relief coefficient k value increases.

[0093] In this embodiment, if the vehicle rolls backward, the pressure relief coefficient k is automatically adjusted. Specifically, the correction factor is set to 105% to increase the pressure relief coefficient. Therefore, the increased pressure relief coefficient k... 增大 =105%×k0, stop the process after completing this adjustment, and apply this data to the next work cycle.

[0094] Step 407: Determine if there is any vehicle towing.

[0095] In this embodiment, this step is to further confirm whether there is a drag phenomenon, and it is determined by monitoring the IMU acceleration signal. When the acceleration changes gradient... a (For the time t from the start to the end of the automatic parking function release, if the acceleration at the start of the start is a0 and the acceleration at the end of the start is a1, then...) If a = (a1 - a0) / t) is greater than λ, it is determined to be a dragging condition. The specific value can be given based on subjective performance during calibration. If dragging is determined, proceed to the next step 408; otherwise, proceed to step 409.

[0096] It should be noted that in this embodiment, the order of judging the vehicle's rollback phenomenon in step 405 and the vehicle's dragging phenomenon in step 407 is not limited. If they can be judged simultaneously, the order of judgment can be adjusted adaptively according to actual needs. For example, in practical applications, the safety risks of rollback are more direct and the consequences are more serious. Rollback can lead to collisions between the current vehicle and other vehicles, or a fall off the slope, which are hard safety accidents that directly threaten the safety of the driver, passengers, and surrounding vehicles and pedestrians. On the other hand, dragging mainly affects the driving experience and has no direct safety risks. For example, dragging may only manifest as a jerky start or abnormal acceleration, at most causing a decline in the driving experience and minor wear and tear on vehicle parts, without causing a direct traffic accident. Therefore, this embodiment is based on the design principle of "safety first, experience second" for vehicle control. That is, considering that the danger level of actual vehicle rollover is higher than that of dragging, rollover is taken as the priority judgment item. High safety risks can be identified and adjustments (such as increasing the pressure relief coefficient) can be triggered as soon as possible. Compared with judging both types of anomalies at the same time, the response time of high-risk anomalies can be greatly shortened. Drag is taken as the second priority judgment item and judged when rollover has not occurred. This does not affect safety control and can also take into account the optimization of start-up smoothness.

[0097] Note that the above process based on the abnormal hazard level setting in this embodiment is only an example and is not intended to limit the scope. The order of judging slope abnormalities can be adaptively adjusted according to actual needs.

[0098] Step 408, the pressure relief coefficient k value decreases.

[0099] In this embodiment, when the vehicle experiences dragging, the pressure relief coefficient k is automatically adjusted. The specific correction factor can be set to 95%, thus reducing the pressure relief coefficient k. 减小 =95%×k0.

[0100] Step 409, the pressure relief coefficient k remains unchanged.

[0101] In this embodiment, if the vehicle does not slip or drag, the system parameters remain unchanged, the process stops, and the next cycle begins.

[0102] In summary, this embodiment, based on vehicle driving conditions, uses relevant data collection and analysis to determine the slippage and dragging phenomena during the release of the automatic parking function, and automatically adjusts the pressure relief coefficient to ultimately solve the driving experience problem. Specifically, this embodiment only responds to the vehicle's start-up by collecting vehicle operating parameters before and after the release of the automatic parking function, accurately identifying abnormal slope starts, and adjusting control parameters accordingly. This achieves dynamic adaptation of the control strategy to the individual characteristics of the vehicle, thus solving the technical problem that the fixed calibration parameters under the traditional automatic parking function cannot adapt to the differences in vehicle manufacturing and slope conditions. This not only avoids the slippage and dragging phenomena during slope starts but also effectively improves the smoothness of slope starts and the user's driving experience.

[0103] It should be noted that the adjusted parking release control parameters designed in this embodiment are directly used for the release of the current automatic parking state. This allows for real-time and immediate correction of control deviations during the current start-up process, thereby quickly suppressing abnormal situations such as rollback, dragging, and sudden acceleration that may occur during the start-up, improving the response speed, smoothness, and safety of the start-up. Simultaneously, the control process does not require waiting for the next operating condition trigger, making the adjustment more direct and timely, which is beneficial for improving the driver's driving experience and the real-time performance of the vehicle control. Based on this, this embodiment provides a vehicle start-up control method. Figure 5 This is a schematic diagram of a third process for a vehicle start-up control method according to an embodiment of the present invention, as shown below. Figure 5 As shown, the process includes the following steps: Step S501: In response to the vehicle's start-up operation in automatic parking mode, adjust the parking release control parameters based on the current road information and vehicle parameters.

[0104] In this embodiment, vehicle parameters include driveshaft torque and braking pressure; road surface information includes longitudinal slope angle; and parking release control parameters include pressure relief coefficient.

[0105] Note that the vehicle parameters in this embodiment include driveshaft torque and braking pressure. These parameters, as core internal parameters of the drive and braking system, can deeply predict the root cause of problems within the power and braking system. For example, driveshaft torque reflects whether the driving force is sufficient, and braking pressure reflects whether the braking force is fully released. This diagnoses problems from the "cause" level and solves problems that are "about to happen." For example, insufficient torque and brake drag are problems that are currently occurring. Such anomalies are directly related to the safety and smoothness of this start-up and must be intervened immediately during the process. Specifically, this is achieved through feedforward control and status monitoring (which has a faster response speed and can intervene before movement). The adjusted parking release control parameters are then used for the automatic parking release in this situation (aimed at providing immediate intervention for real-time risks to ensure the safety of this start-up process).

[0106] It should be noted that this embodiment uses driveshaft torque and braking pressure to determine abnormal vehicle starting conditions. Driveshaft torque represents the vehicle's power output (i.e., directly reflects the driving force transmitted from the engine / motor to the wheels); braking pressure represents the parking braking force (i.e., directly reflects the parking resistance applied by the brakes). By judging the real-time matching relationship between power and braking force, abnormal conditions such as rolling backward, dragging, and lurching during the starting process can be identified. The specific identification process is as follows: 1. When a vehicle starts smoothly and normally, the driving force and braking force will transition smoothly and synchronously: the driving force gradually increases and the braking force gradually decreases, with the two being smoothly matched. Once there is a serious mismatch or imbalance between the driving force and braking force, it can be determined as an abnormal start.

[0107] 2. Uphill drag: The torque of the drive shaft continues to increase, but the braking pressure is still too high. The driving force cannot overcome the braking force for a long time, and the two form a rigid resistance.

[0108] 3. Rolling backwards on an uphill slope: The braking pressure drops too quickly, the braking force is insufficient, and the torque of the drive shaft has not yet built up enough driving force, causing the vehicle to roll backwards.

[0109] 4. Spurring forward on a downhill slope: The braking pressure drops too quickly, and the braking force is insufficient to counteract the combined force of gravity and the torque of the drive shaft, causing the vehicle to suddenly lurch forward.

[0110] In summary, since both driveshaft torque and braking pressure are real-time, directly collectable state quantities of the vehicle, they have fast signal response and high accuracy. They can identify starting abnormalities from the essence of power and braking matching. Using driveshaft torque and braking pressure to determine vehicle starting abnormalities has significant advantages such as direct judgment logic, strong robustness, no need for additional sensors, and ease of engineering implementation.

[0111] In this embodiment, the specific methods for obtaining the driveshaft torque and braking pressure can be determined according to conventional methods in the art. For example, the driveshaft torque can be directly calculated by the vehicle controller / motor controller and output through the CAN bus (Controller Area Network). This can be achieved by calculating the actual output torque of the drive motor / engine in real time, combined with parameters such as the gearbox ratio, final drive ratio, and transmission efficiency; or by directly acquiring the torque through the vehicle's integrated driveshaft torque sensor and sending the detection signal to the vehicle controller. The braking pressure originates from the pressure detection signal built into the vehicle's braking system. It can be directly acquired by the pressure sensor on the ESP (Electronic Stability Program), ESC (Electronic Stability Control), EPB (Electronic Park Brake), or the brake master cylinder / wheel cylinder, directly acquiring the current brake hydraulic pressure / parking execution pressure. The braking pressure value is then sent to the vehicle controller via the CAN bus as a direct basis for determining abnormal starting conditions.

[0112] In this embodiment of the invention, by designing a longitudinal slope angle to identify slope conditions and combining vehicle operating parameters such as drive shaft torque and braking pressure, the pressure relief coefficient is dynamically adjusted. This enables the automatic parking release process to be precisely matched with the vehicle's actual starting state and road conditions, effectively avoiding problems such as slippage, dragging, and excessive impact during starting, thereby greatly improving the safety, smoothness, and stability of vehicle starting.

[0113] In this embodiment, step S501 above adjusts the parking release control parameters based on the current road surface information and vehicle parameters, including any one of the following: 1. In response to the longitudinal slope angle being greater than zero and the drive shaft torque being less than the critical slip torque threshold, the pressure relief coefficient is increased. The critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle.

[0114] It should be noted that a longitudinal slope angle greater than zero indicates an uphill condition. If the driveshaft torque is less than the critical slippage torque threshold, it means the current power output is insufficient to resist the downhill force, and the vehicle is at risk of rolling backward. Therefore, it is necessary to increase the pressure relief coefficient to slow down brake pressure relief and delay the release of automatic parking, relying on braking force to counteract the slippage trend and ensure safe uphill start. Therefore, in this embodiment, "responding to a longitudinal slope angle greater than zero and a driveshaft torque less than the critical slippage torque threshold" indicates that the vehicle has slipped uphill. The relevant content on uphill slippage can be found in the previous text and will not be repeated here.

[0115] It should be noted that, in this embodiment, the critical rollback torque threshold refers to the minimum driveshaft torque required for the vehicle to just resist the gravitational force of the slope and prevent it from rolling backwards when going uphill. Furthermore, as the vehicle goes uphill, the downward gravitational force along the slope increases with the slope gradient; that is, the gentler the slope (the smaller the absolute value of the longitudinal slope angle), the smaller the downward force, and the smaller the minimum torque required to resist rollback; conversely, the steeper the slope (the larger the absolute value of the longitudinal slope angle), the greater the downward force, and the greater the minimum torque required to resist rollback. Therefore, the critical rollback torque threshold increases with the increase of the absolute value of the longitudinal slope angle and decreases with the decrease of the absolute value, showing a direct proportional relationship. This ensures the accuracy and rationality of rollback determination under different slope gradients.

[0116] 2. In response to the longitudinal slope angle being greater than zero and the braking pressure being greater than the retention braking pressure threshold, the pressure relief coefficient is reduced. The retention braking pressure threshold is proportional to the absolute value of the longitudinal slope angle.

[0117] It should be noted that a longitudinal slope angle greater than zero indicates an uphill driving condition. If the braking pressure is greater than the parking brake pressure threshold at this time, it means that the current braking pressure is too high and the braking force is too strong. This will cause the driving force to be unable to overcome the braking resistance in time, and the vehicle is prone to abnormalities such as starting sluggishness and sudden impact after stalling. Therefore, by reducing the pressure relief coefficient, the brake pressure is released faster and the automatic parking is released earlier, reducing the resistance of the braking force to the power output and alleviating uphill sluggishness. Therefore, in this embodiment, "responding to a longitudinal slope angle greater than zero and braking pressure greater than the parking brake pressure threshold" indicates that the vehicle is experiencing uphill sluggishness. The relevant content on uphill sluggishness can be found in the previous text and will not be repeated here.

[0118] It should be noted that the dragging brake pressure threshold in this embodiment refers to the maximum permissible braking pressure that will not cause the vehicle to stall or become stuck due to excessive braking force during uphill starting. Furthermore, when starting uphill, the steeper the slope, the greater the gravitational component of the vehicle's downward force along the slope, requiring a greater parking braking force to prevent rolling back, and consequently, a higher permissible maximum non-drag braking pressure. Conversely, the gentler the slope, the smaller the gravitational component, requiring less parking braking force, and a lower permissible maximum non-drag braking pressure. Therefore, the dragging brake pressure threshold increases with the increase of the absolute value of the longitudinal slope angle and decreases with the decrease of the angle, exhibiting a direct proportional relationship. This ensures the accuracy and rationality of drag determination under different slopes.

[0119] 3. In response to a longitudinal slope angle less than zero and an estimated net acceleration force greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, vehicle weight, and throttle opening degree. It should be noted that a longitudinal slope angle less than zero indicates a downhill condition. If the calculated estimated net acceleration force is greater than the acceleration force threshold, it means the vehicle's forward acceleration tendency is too strong under the combined effect of gravity and driving force, and a lurching motion is imminent. Therefore, by increasing the pressure relief coefficient, the brake pressure relief is slowed down, and the automatic parking release is delayed, using braking force to suppress the excessive forward acceleration tendency and avoid lurching. Therefore, in this embodiment, "in response to a longitudinal slope angle greater than zero and vehicle wheel speed less than zero" indicates that the vehicle is lurching downhill. For details on lurching downhill, please refer to the previous text; it will not be repeated here.

[0120] It should be noted that the estimated net acceleration force in this embodiment refers to the net force that propels the vehicle forward rapidly at the moment of starting downhill, which is formed by the superposition of the downhill gravity component, the vehicle's own weight, and the driver's throttle input. The greater this force, the more likely the vehicle is to suddenly lurch forward. The acceleration force threshold refers to the maximum permissible net acceleration force that will prevent the vehicle from lurching forward when starting downhill, and its specific value can be determined adaptively according to actual needs.

[0121] It should be noted that the estimated net acceleration force in this embodiment is determined by three core factors that most directly affect vehicle acceleration during downhill driving. Specifically, a larger absolute value of the longitudinal slope angle indicates a steeper downhill slope, a greater downward gravitational force on the vehicle, and a stronger forward acceleration tendency. Greater vehicle weight results in a greater downward sliding force and a stronger acceleration tendency. A greater throttle opening leads to greater power output, which, combined with the downhill gravitational force, further strengthens the acceleration tendency. By weighted summing of these three factors, the actual forward acceleration tendency of the vehicle can be comprehensively and accurately quantified, thereby accurately predicting whether a vehicle acceleration during downhill driving is imminent, ensuring the reliability and adaptability of the acceleration prediction. Note that the specific method of weighted summation is not limited here and can be adjusted adaptively according to actual needs. In this embodiment of the invention, the pressure relief coefficient is adjusted in different scenarios based on the longitudinal slope angle and parameters such as drive shaft torque, braking pressure, throttle opening degree, and vehicle weight. Various starting anomalies are judged by using the critical slip torque threshold, the stall braking pressure threshold and the weighted estimated net acceleration force associated with the longitudinal slope angle. This enables the automatic parking release control to more accurately adapt to starting conditions on different slopes, effectively avoiding problems such as slipping on uphill slopes, dragging on uphill slopes and lurching caused by excessive acceleration on downhill slopes. This greatly improves the safety, smoothness and handling stability of the vehicle when starting on a slope.

[0122] Step S502: Release the automatic parking state according to the adjusted parking release control parameters.

[0123] Specifically, step S502 above includes: Step S5021: Release the automatic parking state using the adjusted parking release control parameters.

[0124] In this embodiment of the invention, the adjusted parking release control parameters are directly used to release the automatic parking state in this instance. This can correct the control deviation in the current start-up process in real time and immediately, thereby quickly suppressing abnormal situations such as slippage, dragging, and sudden acceleration that may occur during the start-up process, and improving the response speed, smoothness, and safety of the start-up. At the same time, the control process does not need to wait for the next working condition to be triggered, making the adjustment more direct and timely, which is conducive to improving the driver's driving experience and the real-time performance of the vehicle control.

[0125] In practical applications, vehicle type determines inherent characteristics such as overall vehicle weight and braking performance. Therefore, the current load directly affects the magnitude of the force on the slope and the starting inertia. Furthermore, different vehicle types and loads present different risks and control requirements for vehicle slippage, dragging, and lurching. For example, sedans have a low center of gravity and low mass, resulting in rapid power and braking response, making them more sensitive to the depressurization speed; SUVs (Sport Utility Vehicles) have a high center of gravity and high inertia, making them more prone to lurching downhill and slipping uphill; trucks / commercial vehicles have high mass and large load space, requiring a more conservative and gradual depressurization rhythm. Therefore, the depressurization coefficient needs to be adjusted to suit the vehicle type and current load to ensure a smooth and reliable start. Thus, the vehicle parameters in this embodiment also include the vehicle type and current load. It should be noted that the vehicle model refers to the inherent type of the vehicle at the factory, such as sedan, SUV, etc., which represents fixed parameters such as overall vehicle weight and braking system characteristics. These parameters can be obtained through factory-stored parameters of the vehicle controller or by identification of the vehicle identification number. The current load refers to the total mass of passengers, cargo, etc., carried by the vehicle in real time, which can be obtained through detection by suspension height sensors, axle load sensors, or indirectly estimated by the vehicle controller.

[0126] In this embodiment, increasing the pressure relief coefficient as described above includes: determining an increase factor for the pressure relief coefficient based on the vehicle model and the current load, amplifying the pressure relief coefficient based on the increase factor, and the increase factor being inversely proportional to the current load.

[0127] It should be noted that if a downhill tendency to surge forward is detected and the pressure relief coefficient needs to be increased, a fixed amplification is not used. Instead, the basic amplification ratio is first determined based on the vehicle model, then the final amplification coefficient is calculated based on the current load, and finally, the basic pressure relief coefficient is proportionally amplified using this amplification coefficient to obtain the actual pressure relief coefficient used for this start.

[0128] It's important to explain that the amplification factor is a correction factor used to proportionally amplify the base pressure relief coefficient. Its function is to precisely adjust the amplification of the pressure relief coefficient according to the characteristics of different vehicle models and loads, ensuring a balance between the effect of suppressing lurching and the smoothness of starting. The inverse relationship between the current design, where the larger the load, the smaller the value of the amplification factor, is designed because when the load is large, the total mass of the vehicle is large, and the gravity component and inertia on the downhill slope are large. To suppress lurching, the base pressure relief coefficient itself is already calibrated to a large value, and only a small amplification is needed to achieve the ideal braking effect. If the amplification factor is too large, it will lead to slow pressure relief, sluggish starting, and sluggish power. Conversely, when the load is small, the total mass of the vehicle is small, and the downhill acceleration trend is weak. The calibrated value of the base pressure relief coefficient is too small, and a larger amplification factor is needed to amplify the pressure relief coefficient to obtain sufficient braking force to suppress lurching. Therefore, in this embodiment, by designing an increase coefficient that is inversely proportional to the current load, the pressure relief coefficient under different loads can be in the optimal range, which avoids both sluggish starting of heavy-load vehicles and sudden acceleration of light-load vehicles, thereby improving the smoothness of starting and control robustness under full load conditions.

[0129] In this embodiment, reducing the pressure relief coefficient as described above includes: determining a reduction factor for the pressure relief coefficient based on the vehicle model and the current load, reducing the pressure relief coefficient based on the reduction factor, and the reduction factor being proportional to the current load.

[0130] It should be noted that this embodiment is applicable to control scenarios that alleviate drag on uphill. If it is necessary to reduce the pressure relief coefficient and accelerate braking to relieve drag, the reduction is not done by a fixed amount. Instead, the basic reduction ratio is first determined based on the vehicle model; then the final reduction coefficient is calculated based on the current load; finally, the pressure relief coefficient is reduced proportionally using this reduction coefficient to obtain the actual pressure relief coefficient used.

[0131] It's important to explain that the reduction coefficient is a correction factor that proportionally reduces the pressure relief coefficient. Its function is to precisely control the reduction range of the pressure relief coefficient when mitigating uphill drag, achieving a balance between "eliminating drag" and "preventing rollback." The design of a proportional relationship where the reduction coefficient increases with the current load is based on the consideration that a heavier load on an uphill slope results in a greater downward gravitational force on the vehicle and a higher risk of rollback. In this case, the pressure relief coefficient cannot be reduced too much, otherwise the pressure relief would be too rapid, and the braking force would be lost too early. Therefore, a larger reduction coefficient is used to ensure that the pressure relief coefficient decreases only slightly, alleviating drag without causing rollback. Conversely, a lighter load on an uphill slope results in a lower risk of rollback, allowing for a larger reduction in the pressure relief coefficient, enabling faster brake pressure relief and quickly resolving the conflict between power and braking, thus completely eliminating drag. Therefore, a smaller reduction coefficient is used to achieve a larger reduction. Thus, in this embodiment, by designing the reduction coefficient to be proportional to the current load, drag can be alleviated and rollback can be prevented across all load ranges, making vehicle start-up control safer, smoother, and more robust.

[0132] In this embodiment of the invention, when adjusting the pressure relief coefficient, vehicle parameters such as vehicle model and current load are further introduced as adjustment basis. An increasing coefficient is set in the reverse direction and a decreasing coefficient is set in the forward direction according to different loads. This allows the adjustment range of the pressure relief coefficient to accurately match the actual load state of the vehicle, avoiding excessively fast or slow release of the vehicle's parking brake due to load changes. This effectively improves the stability, safety, and smoothness of vehicle starting under different load conditions. Simultaneously, associating the adjustment coefficient with the load makes the vehicle starting control strategy more adaptable, more precise, and more applicable, thereby greatly improving the user's driving experience and the level of intelligent vehicle control.

[0133] In practical applications, through iterative model learning, the model can continuously absorb real-world starting condition data, correct decision-making biases, and continuously improve the output accuracy of parking release control parameters. Simultaneously, it enhances the model's adaptability to complex conditions such as different slopes and loads, suppresses starting anomalies, achieves self-optimization and intelligence in vehicle starting control, and improves control stability, reliability, and ride comfort. Therefore, the vehicle starting control method in this embodiment further includes: storing the current adjustment record in a starting parameter learning library, periodically calling the recorded samples in the starting parameter learning library to train the AI ​​decision model; and using the AI ​​decision model to output release control reference parameters based on the road information and vehicle parameters collected for each start.

[0134] It should be noted that in this embodiment, after each vehicle starts and the pressure relief coefficient is adjusted, the operating conditions, adjustment process, and control results of this start are saved to form a continuously accumulating learning library of starting parameters. These real starting samples are then used periodically to train an AI decision-making model, allowing the model to learn "what kind of road surface and what kind of vehicle state correspond to the optimal parking release parameters". In subsequent vehicle starts under the same operating conditions, this trained model can directly output the most suitable release control reference parameters for this start based on the current road surface information and vehicle parameters, thereby achieving more accurate, smoother, and more intelligent automatic parking release control.

[0135] It needs to be explained that the starting parameter learning library contains multiple parameter adjustment records for various vehicles. Each adjustment record contains at least the following information: road surface information, such as longitudinal slope angle and uphill / downhill conditions; vehicle parameters, such as vehicle type, current load, driveshaft torque, braking pressure, and throttle opening degree; control actions, such as the original value of the pressure relief coefficient, adjustment direction (e.g., increase / decrease), increase / decrease coefficient, and final pressure relief coefficient; and control effects, such as whether there is slippage / dragging / jerking, and starting smoothness. The AI ​​decision model in this embodiment refers to a data-driven model based on machine learning or deep learning, specifically designed for intelligent decision-making during automatic parking and starting. It does not rely on fixed manually calibrated formulas but autonomously learns control patterns from real starting data (such as input longitudinal slope angle, vehicle type, current load, driveshaft torque, braking pressure, and throttle opening degree, etc., collected in real time) to achieve intelligent and adaptive parking release parameter decision-making (outputting the optimal parking release control reference parameters for this start, such as the pressure relief coefficient or the adjustment amount of the pressure relief coefficient). Note that AI is an abbreviation for Artificial Intelligence.

[0136] In this embodiment, releasing the automatic parking state according to the adjusted parking release control parameters includes: 1. If the difference between the adjusted parking release control parameter and the release control reference parameter is less than the error threshold, the automatic parking state is released using the release control reference parameter, and an AI positive result is accumulated once.

[0137] In this embodiment, the adjusted parking release control parameters are the actual adjustment parameters calculated by traditional control logic such as slope, wheel speed, acceleration, or drive shaft torque and braking pressure, i.e., the adjusted pressure relief coefficient; the release control reference parameters are the intelligent optimization parameters output by the AI ​​decision model based on historical learning samples; the error threshold is the engineering calibration value used to determine whether two sets of parameters are close, i.e., the pre-set judgment value; a positive AI result indicates that the output parameters of the AI ​​decision model are consistent with the actual adjustment parameters, indicating that the AI ​​decision is accurate; a negative AI result indicates that the deviation between the AI ​​decision model and the actual adjustment parameters is large, indicating that the AI ​​decision is inaccurate.

[0138] It should be noted that "if the difference between the adjusted parking release control parameters and the release control reference parameters is less than the error threshold," meaning that when the difference between the two sets of parameters is less than the error threshold, it indicates that the AI ​​decision-making result is highly consistent with traditional safety rules, proving that the AI ​​output is reliable and reasonable. In this case, the AI ​​release control reference parameters are used to release the automatic parking brake, and a positive AI result is recorded for positive reinforcement training of the AI ​​model.

[0139] 2. If the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is not less than the safety ratio value, then the automatic parking state is released using the release control reference parameter, and one negative AI result is accumulated.

[0140] In this embodiment, the positive AI result ratio represents the proportion of positive AI results to the total number of starts, reflecting the reliability of AI decision-making; the safety ratio is a preset reliability threshold, used to determine whether AI decision-making is trustworthy; negative AI results indicate that the AI ​​decision-making model deviates significantly from the actual adjusted parameters, indicating that the AI ​​decision-making is inaccurate.

[0141] It should be noted that "if the difference between the adjusted parking release control parameters and the release control reference parameters is greater than the error threshold and the ratio of positive AI results is not less than the safety ratio value," meaning that when the difference between the two sets of parameters is greater than the error threshold, but the ratio of positive AI results is greater than or equal to the safety ratio value, it indicates that the AI ​​model has been validated by a large number of samples, and its overall accuracy and reliability are up to standard. Even if there are deviations from traditional rules, the smoother AI optimization decision is still prioritized. In this case, the automatic parking is still released using the AI ​​release control reference parameters, and one negative AI result is recorded for subsequent correction of model deviations.

[0142] 3. If the difference between the adjusted parking release control parameters and the release control reference parameters is greater than the error threshold and the ratio of positive AI results is less than the safety ratio, then the adjusted parking release control parameters will be used to release the automatic parking state, and one negative AI result will be accumulated.

[0143] It should be noted that "if the difference between the adjusted parking release control parameters and the release control reference parameters is greater than the error threshold and the ratio of positive AI results is less than the safety ratio," meaning that when the difference between the two sets of parameters is greater than the error threshold and the ratio of positive AI results is less than the safety ratio, it indicates that the AI ​​model is undertrained and its reliability is not up to standard. To avoid starting risks, a safety fallback strategy is implemented, and the AI ​​decision is abandoned. At this time, the system switches to automatic parking with the parameters adjusted according to traditional rules to ensure starting safety and records one negative AI result, indicating that the model needs further training and optimization.

[0144] In this embodiment of the invention, by storing vehicle start-up adjustment records, constructing a learning library, and training an AI decision-making model, AI reference parameters for automatic parking release control are output, realizing intelligent learning and iterative optimization of automatic parking release parameters. When the automatic parking state is released, hierarchical judgment and adaptive selection are performed based on the difference between the adjusted parameters and the AI ​​reference parameters, and the ratio of positive AI results. This can gradually improve the accuracy and applicability of AI decision-making while ensuring safe and reliable start-up, upgrading parking release control from traditional rule control to intelligent decision-making control. This not only avoids the limitations of single control logic but also provides a safety net through error thresholds and safety ratios. While improving the smoothness and intelligence of hill starts, it ensures the safety and stability of the entire vehicle start-up process. The control strategy has self-learning, self-adaptive, and self-optimizing capabilities, making it applicable to a wider range of scenarios and with higher engineering application value.

[0145] This embodiment also provides a vehicle starting control device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0146] This embodiment provides a vehicle start control device, such as... Figure 6 As shown, the device includes: The adjustment module 601 is used to respond to the vehicle's starting operation in automatic parking mode by adjusting the parking release control parameters, including the pressure relief coefficient, based on the current road information and vehicle parameters.

[0147] The control module 602 is used to release the automatic parking state according to the adjusted parking release control parameters.

[0148] In some alternative implementations, the adjustment module 601 includes: The next operating condition adjustment submodule is used to increase the pressure relief coefficient in response to a longitudinal slope angle greater than zero and a vehicle wheel speed less than zero; decrease the pressure relief coefficient in response to a longitudinal slope angle greater than zero and a rate of change of vehicle acceleration within a first preset time period after starting greater than a first preset threshold, wherein the start time of the first preset time period is greater than the first time value; and increase the pressure relief coefficient in response to a longitudinal slope angle less than zero and a rate of change of vehicle acceleration within a second preset time period after starting greater than a second preset threshold, wherein the start time of the second preset time period is less than the second time value, and the first time value is greater than the second time value.

[0149] This operating condition adjustment submodule is used to increase the pressure relief coefficient in response to situations where the longitudinal slope angle is greater than zero and the drive shaft torque is less than the critical slip torque threshold. The critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle. In response to situations where the longitudinal slope angle is greater than zero and the braking pressure is greater than the holding braking pressure threshold, the pressure relief coefficient is decreased. The holding braking pressure threshold is proportional to the absolute value of the longitudinal slope angle. In response to situations where the longitudinal slope angle is less than zero and the estimated net acceleration force is greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, the vehicle's weight, and the degree of throttle opening.

[0150] In some alternative implementations, the control module 602 includes: The next operating condition control submodule is used to release the automatic parking state under the same operating condition next time using the adjusted parking release control parameters.

[0151] The current operating condition control submodule is used to release the current automatic parking state using the adjusted parking release control parameters.

[0152] In some optional implementations, the next operating condition adjustment submodule or the current operating condition adjustment submodule may further include: The pressure relief coefficient adjustment unit is used to determine the amplification factor of the pressure relief coefficient based on the vehicle model and the current load. The pressure relief coefficient is amplified according to the amplification factor, which is inversely proportional to the current load.

[0153] The pressure relief coefficient reduction unit is used to determine the reduction factor of the pressure relief coefficient based on the vehicle model and the current load, and then reduce the pressure relief coefficient according to the reduction factor. The reduction factor is proportional to the current load.

[0154] In some optional implementations, the adjustment module 601 further includes: The pressure relief coefficient adjustment submodule is used to adjust the pressure relief coefficient using calculation rules so that the adjusted pressure relief coefficient remains within a preset threshold range; wherein, the calculation rules include at least one of addition and subtraction operations, mapping operations based on simulation curves, exponential operations, and logarithmic operations.

[0155] In some alternative embodiments, the apparatus further includes: The iterative learning module stores the current adjustment record in the starting parameter learning library, periodically calls the recorded samples in the starting parameter learning library to train the AI ​​decision model, and uses the AI ​​decision model to output release control reference parameters based on the road information and vehicle parameters collected each time the vehicle starts.

[0156] The parameter verification module is used to: if the difference between the adjusted parking release control parameter and the release control reference parameter is less than the error threshold, then release the automatic parking state using the release control reference parameter and accumulate one positive AI result; if the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is not less than the safety ratio value, then release the automatic parking state using the release control reference parameter and accumulate one negative AI result; if the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is less than the safety ratio value, then release the automatic parking state using the adjusted parking release control parameter and accumulate one negative AI result.

[0157] The vehicle starting control device provided in this embodiment of the invention can execute the vehicle starting control method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0158] The vehicle starting control device in this embodiment of the invention focuses on the starting operation of the vehicle in automatic parking mode. Specifically, it dynamically adjusts the parking release control parameters through real-time road information and vehicle parameters, and releases the automatic parking state based on the adjusted parking release control parameters. It can continuously optimize the fixed parameters under the automatic parking function, thereby adapting to the individual manufacturing differences of different vehicles. This not only effectively avoids abnormal starting situations such as vehicle rollback, dragging, and sudden acceleration, but also improves the safety and smoothness of starting the vehicle on a slope. At the same time, it greatly enhances the user driving experience and the level of intelligent vehicle control.

[0159] In this embodiment, Figure 7 This is a schematic diagram of a vehicle structure provided in an embodiment of the present invention. See below for details. Figure 7 The diagram illustrates a structural schematic suitable for implementing a vehicle according to an embodiment of the present invention. The vehicle includes a controller, which may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 702 or a program loaded from memory 708 into a random access memory RAM 703. The RAM 703 also stores various programs and data required for vehicle operation. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0160] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows the vehicle to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 Vehicles with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0161] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the vehicle start-up control method of the embodiments of the present invention.

[0162] Figure 7 The vehicle shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0163] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the vehicle start-up control method shown in the above embodiments is implemented.

[0164] In one specific embodiment, a storage medium is proposed for implementing the adaptive control of the above-described automatic parking function. Figure 8This is a schematic diagram of the basic module for the storage medium of the automatic parking function. For example... Figure 8 As shown, it includes: Functional module 801 provides automatic parking function and can automatically determine whether it is in working state.

[0165] The data acquisition module 802 is capable of acquiring relevant signals inside the vehicle in real time.

[0166] The judgment module 803 processes the data based on the actual situation of the vehicle and determines whether the pressure relief coefficient of the automatic parking function needs to be adjusted.

[0167] The adjustment module 804 can adjust the pressure relief coefficient of the automatic parking function according to the aforementioned input.

[0168] The storage module 805 can store and utilize relevant parameters.

[0169] In this embodiment, the pressure relief coefficient of the automatic parking function is adaptively adjusted according to the vehicle's starting situation. This solves the problem of abnormal phenomena such as vehicle slippage, dragging, and sudden acceleration when starting on a slope due to manufacturing inconsistencies in the prior art, and effectively improves the driving experience of the automatic parking function.

[0170] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A vehicle starting control method, characterized in that, The method includes: In response to the vehicle's starting operation in automatic parking mode, the parking release control parameters are adjusted based on the current road information and vehicle parameters. The automatic parking state is released according to the adjusted parking release control parameters; The road surface information includes the longitudinal slope angle, the vehicle parameters include the drive shaft torque and braking pressure, and the parking release control parameters include the pressure relief coefficient. The adjustment of the parking release control parameters based on the current road information and vehicle parameters includes any one of the following: In response to the longitudinal slope angle being greater than zero and the drive shaft torque being less than the critical slip torque threshold, the pressure relief coefficient is increased, wherein the critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle; In response to the longitudinal slope angle being greater than zero and the braking pressure being greater than the retention braking pressure threshold, the pressure relief coefficient is reduced, wherein the retention braking pressure threshold is proportional to the absolute value of the longitudinal slope angle; In response to the longitudinal slope angle being less than zero and the estimated net acceleration force being greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, the vehicle weight, and the degree of throttle opening.

2. The vehicle starting control method according to claim 1, characterized in that, Releasing the automatic parking state according to the adjusted parking release control parameters includes: Release the automatic parking state using the adjusted parking release control parameters.

3. The vehicle starting control method according to claim 1, characterized in that, The vehicle parameters also include the vehicle model and current load; increasing the pressure relief coefficient includes: The amplification factor of the pressure relief coefficient is determined based on the vehicle model and the current load, and the pressure relief coefficient is amplified based on the amplification factor, wherein the amplification factor is inversely proportional to the current load.

4. The vehicle starting control method according to claim 3, characterized in that, The reduction of the pressure relief coefficient includes: The reduction factor of the pressure relief coefficient is determined based on the vehicle model and the current load, and the pressure relief coefficient is reduced based on the reduction factor, wherein the reduction factor is proportional to the current load.

5. The vehicle starting control method according to claim 1, characterized in that, The adjustment of the parking release control parameters also includes: The pressure relief coefficient is adjusted using calculation rules to keep it within a preset threshold range; wherein the calculation rules include at least one of addition and subtraction operations, mapping operations based on simulated curves, exponential operations, and logarithmic operations.

6. The vehicle starting control method according to any one of claims 1 to 5, characterized in that, The method further includes: storing the current adjustment record to a starting parameter learning library, periodically calling the record samples in the starting parameter learning library to train the AI ​​decision model; and using the AI ​​decision model to output release control reference parameters based on the road information and vehicle parameters collected each time a start is initiated.

7. The vehicle starting control method according to claim 6, characterized in that, The step of releasing the automatic parking state according to the adjusted parking release control parameters further includes: If the difference between the adjusted parking release control parameter and the release control reference parameter is less than the error threshold, the automatic parking state is released using the release control reference parameter, and an AI positive result is accumulated once.

8. The vehicle starting control method according to claim 7, characterized in that, The method further includes: If the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is not less than the safety ratio, then the automatic parking state is released using the release control reference parameter, and one negative AI result is accumulated.

9. The vehicle starting control method according to claim 7, characterized in that, The method further includes: If the difference between the adjusted parking release control parameter and the release control reference parameter is greater than the error threshold and the ratio of positive AI results is less than the safety ratio, then the automatic parking state is released using the adjusted parking release control parameter, and one negative AI result is accumulated.

10. A vehicle starting control device, characterized in that, The device includes: The adjustment module is used to respond to the vehicle's starting operation in automatic parking mode by adjusting the parking release control parameters based on the current road information and vehicle parameters. The control module is used to release the automatic parking state according to the adjusted parking release control parameters; The road surface information includes the longitudinal slope angle, the vehicle parameters include the drive shaft torque and braking pressure, and the parking release control parameters include the pressure relief coefficient. The adjustment of the parking release control parameters based on the current road information and vehicle parameters includes any one of the following: In response to the longitudinal slope angle being greater than zero and the drive shaft torque being less than the critical slip torque threshold, the pressure relief coefficient is increased, wherein the critical slip torque threshold is proportional to the absolute value of the longitudinal slope angle; In response to the longitudinal slope angle being greater than zero and the braking pressure being greater than the retention braking pressure threshold, the pressure relief coefficient is reduced, wherein the retention braking pressure threshold is proportional to the absolute value of the longitudinal slope angle; In response to the longitudinal slope angle being less than zero and the estimated net acceleration force being greater than the acceleration force threshold, the pressure relief coefficient is increased. The estimated net acceleration force is determined by a weighted sum of the absolute value of the longitudinal slope angle, the vehicle weight, and the degree of throttle opening.

11. A vehicle, characterized in that, The vehicle includes a controller, which includes a memory and a processor. The memory and the processor are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle start-up control method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the vehicle start-up control method according to any one of claims 1 to 9.

Images