Intelligent driving safety control method, device and equipment

Abstract

The invention discloses an intelligent driving safety control method, device and equipment, and relates to the technical field of intelligent driving, and the method comprises the steps: determining the current driving stage of a target vehicle based on the current distance between the target vehicle and a target parking position and the current vehicle speed of the target vehicle; based on the preset driving path, determining a credible state of the current driving path of the target vehicle; when the driving stage is a cruising stage and the credible state is an effective state, performing driving control on the target vehicle based on a first safety constraint parameter corresponding to the cruising stage so as to prolong the fault tolerance time during unexpected steering; and when the driving stage is a parking stage and the credible state is an effective state, performing parking control on the target vehicle based on a second safety constraint parameter corresponding to the parking stage so as to shorten the braking distance during unexpected acceleration.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to an intelligent driving safety control method, device and equipment. Background Technology

[0002] In recent years, Home-Zone Parking Assist (HPA) has been gradually applied to the field of intelligent driving as an extension of automatic parking technology. This function typically includes a cruising phase from the starting point to the target parking space, and a parking phase after arrival at the space. In practical applications, the cruising and parking phases inherently differ in their requirements for vehicle speed, steering, and other dynamic control aspects. However, current methods struggle to adapt safety control constraints based on the vehicle's actual stage throughout the entire journey from cruising to parking. This lack of stage recognition and adaptation to safety control strategies may lead to unexpected control behaviors during driving or transitions, posing a safety risk. Therefore, an intelligent driving safety control method is urgently needed to address the safety risks arising from the lack of accurate stage recognition and dynamic adaptation of corresponding safety constraints. Summary of the Invention

[0003] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solutions, nor is it intended to determine the scope of protection of the claimed technical solutions.

[0004] This application aims to address the control malfunctions and safety hazards in memory-based parking functions caused by the different vehicle control requirements during cruise and parking phases and the lack of path safety verification during switching. The method acquires a pre-recorded preset driving path and dynamically determines the driving phase and path reliability by combining the real-time distance and speed between the vehicle and the target location. Based on this, the vehicle is controlled only when the path is valid, according to safety constraint parameters matched to the cruise or parking phase. This achieves phased, verifiable, and safe collaborative control during fully automatic parking, improving the system's ability to handle unexpected failures and enhancing the safety of the parking process.

[0005] Firstly, this application provides an intelligent driving safety control method, including: Based on the current distance between the target vehicle and the target parking location and the current speed of the target vehicle, the current driving stage of the target vehicle is determined, wherein the driving stage includes a cruising stage or a parking stage. Based on a preset driving path, the credible state of the current driving path of the target vehicle is determined, wherein the preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning phase, and the credible state includes a valid state or an invalid state. When the driving phase is the cruise phase and the trusted state is the valid state, the target vehicle is driven based on the first safety constraint parameter corresponding to the cruise phase in order to extend the fault tolerance time during unexpected steering. When the driving phase is the parking phase and the trusted state is the valid state, parking control is performed on the target vehicle based on the second safety constraint parameter corresponding to the parking phase to shorten the braking distance during unexpected acceleration.

[0006] In some implementations, determining the current driving stage of the target vehicle based on the current distance between the target vehicle and the target parking location and the current speed of the target vehicle includes: When the current distance is greater than or equal to a preset distance threshold, or the current vehicle speed is greater than or equal to a preset vehicle speed threshold, the driving phase is determined to be the cruising phase; When the current distance is less than the preset distance threshold and the current vehicle speed is less than the preset vehicle speed threshold, the driving stage is determined to be the parking stage.

[0007] In some implementations, it also includes: A status flag is set to identify the driving stage, wherein a first preset value is used to identify the cruising stage and a second preset value is used to identify the parking stage; After the target vehicle activates the memory parking function, the value of the status flag bit is initialized to the first preset value; After determining that the driving stage is the cruise stage or the parking stage, the value of the status flag is updated to the first preset value or the second preset value corresponding to the determined driving stage.

[0008] In some implementations, determining the reliable status of the target vehicle's current driving path based on a preset driving path includes: From the preset driving path, obtain preset feature information of at least one path feature point, wherein the path feature point is a key location point recorded in the memory learning stage to characterize the preset driving path; Obtain the actual feature information of the target vehicle after it starts driving from the starting position, which corresponds to the at least one path feature point; The actual feature information is matched and compared with the corresponding preset feature information to obtain the matching result; Based on the matching results, the reliability status of the current driving path is determined.

[0009] In some implementations, the step of controlling the target vehicle based on the first safety constraint parameter corresponding to the cruise phase includes: Based on the first safety constraint parameters, the preset upper limit of acceleration, preset upper limit of steering angle, preset upper limit of vehicle speed and preset upper limit of angular rate allowed in the cruise phase are determined. Obtain request control parameters for controlling the driving of the target vehicle, wherein the request control parameters include request acceleration, request steering angle, request vehicle speed, and request steering angle rate; When the requested acceleration is greater than the preset acceleration limit, or the requested steering angle is greater than the preset steering angle limit, or the requested vehicle speed is greater than the preset vehicle speed limit, or the requested steering angle rate is greater than the preset angle rate limit, the corresponding requested parameters exceeding the preset acceleration limit, the preset steering angle limit, the preset vehicle speed limit, or the preset angle rate limit shall be adjusted to a value no greater than the preset limit value defined by the first safety constraint parameter.

[0010] In some implementations, after determining the reliable state of the target vehicle's current driving path based on a preset driving path, the method further includes: When the trusted state is invalid, the automatic parking function of the target vehicle is turned off.

[0011] In some embodiments, after performing parking control on the target vehicle based on the second safety constraint parameter corresponding to the parking stage when the driving stage is the parking stage and the trusted state is the valid state, the method further includes: Based on the current speed of the target vehicle and the status flag, determine the parameter consistency status; When the parameter consistency status indicates that the current vehicle speed is greater than the preset vehicle speed limit corresponding to the parking stage and the status flag indicates the parking stage, the target vehicle is subjected to fault downgrade processing.

[0012] In some implementations, it also includes: Obtain the brake pedal opening signal; Based on the opening signal, determine the current opening of the brake pedal; When the current opening degree is greater than the preset opening degree threshold, the target vehicle is controlled to perform a braking operation, and the memory parking function is kept active.

[0013] Secondly, this application provides an intelligent driving safety control device, comprising: A driving phase determination unit is used to determine the current driving phase of the target vehicle based on the current distance between the target vehicle and the target parking position and the current speed of the target vehicle, wherein the driving phase includes a cruising phase or a parking phase. A trusted state determination unit is used to determine the trusted state of the current driving path of the target vehicle based on a preset driving path, wherein the preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning phase, and the trusted state includes a valid state or an invalid state. A driving phase control unit is used to control the target vehicle based on a first safety constraint parameter corresponding to the driving phase when the driving phase is the cruise phase and the trusted state is the effective state, so as to extend the fault tolerance time during unexpected steering. A parking phase control unit is used to perform parking control on the target vehicle based on the second safety constraint parameters corresponding to the parking phase when the driving phase is the parking phase and the trusted state is the valid state, so as to shorten the braking distance during unexpected acceleration.

[0014] Thirdly, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the intelligent driving safety control method of any one of the first aspects.

[0015] Fourthly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the intelligent driving safety control method of any one of the first aspects.

[0016] In summary, the intelligent driving safety control method provided by this invention introduces a preset driving path recorded during the memory learning phase, providing a path benchmark and verification basis for the vehicle's automatic driving and parking processes. By acquiring the relative distance between the vehicle and the target parking position and the current vehicle speed in real time, it identifies whether the vehicle is in a cruising phase focused on passage or a parking phase requiring precise control, thus providing an accurate stage judgment basis for implementing differentiated safety control strategies. Based on this, by comparing the vehicle's actual driving situation with the preset driving path in real time, the reliability of the current driving path is judged. Subsequent automated control commands are only executed after the path has been verified as reliable, effectively avoiding the risk of blind control caused by environmental changes, positioning deviations, or memory path failures. When it is confirmed that the vehicle is in a cruising phase and the path is reliable, a first safety constraint parameter matching that phase is applied to control the vehicle. This parameter, while ensuring necessary driving efficiency, reasonably limits key indicators such as maximum speed and steering angle rate, providing more sufficient response time to deal with unexpected steering and other faults, extending the fault tolerance time. Once it is confirmed that the vehicle has entered the parking phase and the path is reliable, the system switches to the second safety constraint parameter, reducing the vehicle speed limit and minimizing the kinetic energy that may accumulate during parking. This shortens the braking distance required in the event of unexpected acceleration, whether through automatic braking or driver intervention, thus increasing the safety margin in parking scenarios. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic flowchart of an intelligent driving safety control method provided in an embodiment of this application; Figure 2 This application provides a schematic diagram of the structure of an intelligent driving safety control device. Figure 3 This is a schematic diagram of an intelligent driving safety control electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0019] The intelligent driving safety control method of this application is mainly applied to intelligent vehicles equipped with Home-Zone Parking Assist (HPA) functionality. HPA allows the vehicle to learn and record its driving path from a fixed starting point (e.g., the entrance to a residential area) to a target parking space (e.g., a private parking space) through a single manual driving experience in familiar closed or semi-closed structured road environments such as residential areas and office parks. In subsequent use, the vehicle can automatically activate the function at the starting point along this learned path, autonomously completing the entire process from the starting point to near the parking space and finally parking. This method aims to solve the key problem of how to intelligently and safely switch control strategies according to different stages of the vehicle's operation (long-range cruise and near-end parking) during fully automated driving and parking, and to continuously verify the reliability of the driving path to ensure safe and smooth operation of the function. In this automated process, the vehicle needs to go through a cruise phase from the starting point to the vicinity of the parking space and a parking phase after arriving at the parking space. The cruise phase focuses on autonomous path tracking and driving efficiency, while the parking phase focuses on low-speed, high-precision positioning and manipulation. This application proposes a control scheme to ensure the connection and switching between the two stages when the function is fully automated.

[0020] To facilitate understanding of this application, the following will explain some key terms and custom-defined terms used in the specification: The memory parking feature described in this application is an intelligent driving function. Its core lies in the vehicle's ability to learn and memorize a user's fixed driving route and target parking space within a familiar area. Upon subsequent recall, the vehicle can then automatically cruise and park along this route from start to finish. This function relies on a priori memory learning phase, during which the vehicle records the complete driving trajectory and environmental information from the set starting position to the target parking position through manual driving or a specific mode, forming a preset driving path that can be referenced for subsequent autonomous driving.

[0021] The preset driving path in this application does not refer to just a geometric line, but rather an ordered set of path feature points. These feature points are key location points captured and stored during the memory learning stage. They may include the vehicle's absolute coordinates, position relative to reference objects, heading angle, and local environmental features of the point, which together constitute the digital representation of the path.

[0022] The driving phase in this application refers to the division of different task objectives throughout the memory parking process, specifically the cruising phase and the parking phase. The cruising phase refers to the stage where the vehicle departs from its starting position and automatically travels along a preset path to near the target parking location; this phase emphasizes stable path tracking and efficient passage. The parking phase refers to the stage where the vehicle has arrived near the target parking location and begins to perform precise parking operations; this phase emphasizes high-precision positioning and control at low speeds.

[0023] The path feature points in this application are key location markers on the preset driving path, serving as the basis for path conformity verification. The reliable state is a binary judgment result used to characterize the degree of consistency between the vehicle's current actual driving path and the preset driving path. A valid state indicates that the two are basically consistent within the allowable error range, the path is reliable, and automatic control can continue; an invalid state indicates that the deviation exceeds the allowable range, the path is unreliable, and a safety response needs to be triggered.

[0024] The "credible state" in this application refers to the determination of whether the vehicle is still on a valid and reliable memory path after comparing and analyzing the actual driving path acquired in real time with the pre-stored preset driving path. It includes two conclusions: a valid state (indicating that the current driving path has not deviated significantly, the expected parking space environment may be valid, and automated control can continue) and an invalid state (indicating that the path has deviated unacceptably, the expected parking space may be invalid, or the environment has changed significantly, and continuing to execute automated control poses a risk). This serves as a safety threshold for deciding whether to continue executing the automated control strategy.

[0025] The first and second safety constraint parameters of this application are two sets of vehicle dynamic control safety limits corresponding to the cruise and parking phases, respectively. These parameters typically include specific values ​​such as the maximum allowed vehicle speed, maximum acceleration, maximum steering angle, and upper limit of steering angle rate for that phase. The first safety constraint parameter aims to ensure cruise efficiency while reserving a safety margin; the second safety constraint parameter aims to maximize the safety of the parking process, and usually imposes stricter restrictions (such as a lower speed limit) to adapt to the higher requirements of precise operation and safety redundancy in parking scenarios.

[0026] The fault tolerance time in this application refers to the maximum time interval allowed from the occurrence of an unexpected fault in the vehicle control system (such as uncommanded steering) to the time during which the system or driver takes effective corrective action and restores the vehicle to a safe state. Extending this time means providing a greater safety margin for fault detection and response.

[0027] The braking distance in this application refers to the distance traveled from the moment the vehicle begins to brake until it comes to a complete stop. In parking scenarios, shortening the braking distance after unexpected acceleration can reduce potential collision risks and improve operational safety in confined spaces.

[0028] Please see Figure 1 This is a schematic flowchart of an intelligent driving safety control method provided in an embodiment of this application, which may specifically include: S110. Based on the current distance between the target vehicle and the target parking position and the current speed of the target vehicle, determine the current driving stage of the target vehicle, which includes the cruising stage or the parking stage. For example, during the operation of the memory parking function, the vehicle needs to go through a cruising phase, moving from the starting point to the target parking space, and a parking phase, where it performs the parking operation after arriving near the parking space. These two phases have different requirements for vehicle motion control, such as speed and steering. To implement control, it is necessary to first determine the specific phase the vehicle is currently in. This determination is achieved by acquiring two parameters: the real-time distance between the vehicle and the preset target parking position, and the vehicle's real-time speed. Continuous monitoring and comparison with internal preset threshold conditions determine whether the vehicle is currently in the cruising phase or the parking phase.

[0029] S120. Based on the preset driving path, determine the credible state of the current driving path of the target vehicle, wherein the preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning stage, and the credible state includes a valid state or an invalid state. For example, during the execution of the memory parking function, the vehicle needs to continuously compare and analyze its current actual driving trajectory with the preset driving path previously recorded during the memory learning phase. This preset driving path contains the expected travel trajectory from the starting position to the target parking position and its key feature information. By acquiring the vehicle's actual position, heading, and other driving information in real time and matching it with the corresponding path feature information in the preset path, a determination is made as to whether the vehicle is still traveling on a valid and reliable memory path.

[0030] S130. When the driving phase is the cruise phase and the trusted state is the effective state, drive the target vehicle based on the first safety constraint parameter corresponding to the cruise phase to extend the fault tolerance time when unexpected steering occurs. For example, when the vehicle is determined to be in the cruise phase and the current driving path is verified to be valid, the first safety constraint parameters configured for this phase will be used to control the vehicle. These parameters, while ensuring path following and necessary traffic efficiency, impose reasonable limits on the vehicle's dynamic parameters such as steering rate and maximum steering angle. By constraining the intensity of steering actions, the rate of change in vehicle attitude caused by unexpected steering malfunctions that may occur during cruise (such as abnormal steering commands due to software errors or signal interference) will be effectively suppressed. This gives the vehicle system or driver more time to detect such anomalies and initiate appropriate safety response mechanisms (such as corrective or braking), thereby extending the time window from the occurrence of a malfunction to the implementation of effective intervention, i.e., the fault tolerance time.

[0031] S140. When the driving phase is the parking phase and the credible state is valid, parking control is performed on the target vehicle based on the second safety constraint parameters corresponding to the parking phase to shorten the braking distance during unexpected acceleration.

[0032] For example, when the vehicle is determined to be in a parking phase and the current driving path is verified as valid, control will switch to a second set of safety constraint parameters designed for this phase. These parameters, tailored to the high precision and low speed requirements of parking scenarios, reduce the maximum permissible vehicle speed and acceleration limits, while imposing more precise restrictions on steering operations. By controlling the vehicle's dynamic response, the accumulation of kinetic energy caused by unexpected acceleration during parking (such as erroneous triggering of the control system or abnormal sensor signals) will be significantly reduced. At this point, the braking distance required, whether by the automatic braking system or manual intervention by the driver, will be shortened, providing greater safety redundancy for the vehicle within a limited operating space and effectively reducing the risk of collision.

[0033] In summary, this embodiment of the application establishes a spatial benchmark for the entire safety control process by acquiring the driving trajectory from the starting position to the target parking position, which is pre-recorded during the memory learning phase, as a preset driving path. This ensures that all subsequent judgments and control actions have a spatial reference. Based on the current distance between the target vehicle and the target parking position, as well as the vehicle's current speed, it determines whether the vehicle is in a cruising phase requiring high traffic efficiency or a parking phase emphasizing precise operation. This mechanism solves the problem of ambiguity in the switching logic between the cruising and parking phases from the perspective of motion state, providing a decision-making premise for implementing differentiated safety strategies. Furthermore, by comparing and analyzing the consistency between the vehicle's actual driving trajectory from the starting position and the aforementioned preset driving path, the reliability of the current driving path is determined. This method embeds a spatial safety decision node into the automated control process, ensuring that subsequent control commands are only executed if the vehicle is verified to be still traveling on a valid memory path. This effectively prevents the risk of blind control caused by drastic environmental changes, positioning drift, or memory path failure. When the vehicle is confirmed to be in the cruising phase and the path is reliable, the first safety constraint parameters adapted for this phase are invoked to control the vehicle's movement. These parameters, while ensuring necessary maneuverability, reduce the severity of the vehicle's dynamic response when unexpected steering failures occur by imposing reasonable limits on key indicators such as steering angle rate. This allows more time for fault detection and the initiation of corrective measures, extending the effective fault tolerance window. When the vehicle is confirmed to be in the parking phase and the path is reliable, the system switches to the more stringent second safety constraint parameters. The significantly reduced speed and acceleration limits greatly reduce the kinetic energy that the vehicle may accumulate during parking. This directly results in a shorter distance required for the vehicle to come to a complete stop from the start of braking, whether automatic braking or driver intervention, in the event of unexpected acceleration. This increases the safety margin and reduces the risk of collision in confined parking spaces. The technical solution of this application not only divides the driving stage from the perspective of motion state and realizes smooth switching, but also meets the safety requirements of different driving scenarios by introducing path verification based on trajectory consistency and differentiated stage parameter control. It realizes phased and verifiable safety control of the entire memory parking process, and improves the overall safety and reliability of function execution.

[0034] In some instances, the current stage of travel of the target vehicle is determined based on the current distance between the target vehicle and the target parking location and the current speed of the target vehicle, including: When the current distance is greater than or equal to a preset distance threshold, or the current vehicle speed is greater than or equal to a preset vehicle speed threshold, the driving phase is determined to be the cruise phase. When the current distance is less than a preset distance threshold and the current vehicle speed is less than a preset vehicle speed threshold, the driving stage is determined to be the parking stage.

[0035] For example, a preset distance threshold (e.g., 3 meters) representing the vehicle's proximity to the target parking position, and a preset speed threshold (e.g., 5 km / h) representing the vehicle entering a low-speed driving state are pre-set. During the operation of the memory parking function, the current distance between the vehicle and the target parking position, as well as the vehicle's current speed, are continuously acquired. Subsequently, the current distance is compared with the preset distance threshold, and the current speed is compared with the preset speed threshold.

[0036] Based on the comparison results, the execution phase judgment logic determines the vehicle's current position. If the current distance is greater than or equal to a preset distance threshold, it indicates that the vehicle is still far from the target parking space and is still in the main part of the path travel. Alternatively, if the current speed is greater than or equal to a preset speed threshold, it indicates that the vehicle is still maintaining a high speed, which does not meet the characteristics of a parking operation. If either of these conditions is met, the target vehicle is determined to be in the cruising phase. Conversely, the target vehicle is determined to be in the parking phase only if both the current distance is less than a preset distance threshold (indicating that the vehicle is very close to the target parking space) and the current speed is less than a preset speed threshold (indicating that the vehicle has reduced to a low speed suitable for parking).

[0037] In summary, this application's embodiments, by introducing a preset distance threshold, provide an objective standard for the spatial concept of approaching a parking space, enabling the perception of the vehicle's positional relationship relative to the target. This forms the spatial basis for distinguishing between the cruising phase, which is primarily for driving, and the parking phase, which is primarily for parking. Simultaneously, by introducing a preset speed threshold, a boundary is provided for low-speed states, effectively distinguishing between high-speed cruising aimed at improving traffic efficiency and low-speed parking operations focused on safety and precision. A conditional judgment strategy combining logical OR and logical AND is employed; that is, the cruising phase only requires either a long distance or high speed, while the parking phase requires both a short distance and low speed, ensuring the rationality of the phase determination. This judgment mechanism accurately captures the actual process of the vehicle transitioning from cruising to parking, triggering a phase switch only when the vehicle simultaneously meets the conditions of spatial proximity and speed reduction. This avoids misjudgments caused by fluctuations in a single parameter (such as a brief stop resulting in zero speed but still a long distance), providing a basis for subsequently applying different first and second safety constraint parameters according to different phases, ensuring that the phased safety control strategy is activated at the correct time.

[0038] In some instances, it also includes: Set a status flag bit to identify the driving stage, wherein the first preset value is used to identify the cruise stage and the second preset value is used to identify the parking stage; After the target vehicle activates the memory parking function, the value of the status flag is initialized to the first preset value; After determining whether the driving stage is a cruise stage or a parking stage, the value of the status flag is updated to the first preset value or the second preset value corresponding to the determined driving stage.

[0039] For example, at the software and hardware collaborative implementation level of the intelligent driving safety control method, a specific storage unit is set as a status flag in the microcontroller (MCU) chip of the intelligent driving domain controller (ADCU). This flag is designed as a software variable with two states: a value of 0 is used as the first preset value, specifically for identifying and representing the cruise phase; a value of 1 is used as the second preset value, specifically for identifying and representing the parking phase. By defining and maintaining this flag in the MCU, the hardware chip responsible for low-level safety monitoring and execution, a global phase status identifier is established, enabling the judgment conclusion of the driving phase to be represented by the data stored in the safety hardware.

[0040] After the target vehicle activates the memory parking function, the status flag bit in the MCU is initialized. At the start of the function, the vehicle is necessarily in the cruising phase from the starting point to the parking space. During initialization, the value of the flag bit is written to the first preset value of 0. This operation establishes the initial state of the system at the hardware level, ensuring that from the very beginning of the control cycle, the phase information recorded inside the MCU corresponds to the starting point of the functional logic.

[0041] During operation, when the driving phase determination unit (located in a chip such as the SOC) determines whether the vehicle is currently in a cruising or parking phase based on real-time distance and vehicle speed, it synchronizes this logical determination result to the status flag in the MCU. Through inter-chip communication, the value of the flag is updated to a preset value corresponding to the current determination result: if the vehicle is determined to be in a cruising phase, it is updated to the first preset value; if it is determined to be in a parking phase, it is updated to the second preset value (e.g., 1). This dynamic synchronization mechanism ensures that the flag state in the MCU is always a true mapping of the latest phase determination result from the decision-making layer, enabling the MCU to make judgments based on this hardware status value when performing all safety logic checks, constraint parameter selections, or fault diagnosis that depend on the current phase.

[0042] In summary, this embodiment of the application improves the reliability and anti-interference capability of status information by setting a status flag bit in the MCU chip of the ADCU to anchor the stage status information to the hardware layer responsible for functional safety. Using 0 and 1 to represent the cruise and parking stages respectively ensures that the status judgment is unambiguous in software logic, facilitating conditional judgments and code execution. Initializing the flag bit to point to the cruise stage during function startup ensures initial consistency between the hardware state and system logic. Furthermore, synchronously updating the flag bit in the MCU based on real-time judgment results guarantees that the safety control unit (MCU) can always execute its safety control tasks based on the latest stage information confirmed by the decision logic, avoiding control errors caused by inconsistencies between the software and hardware states.

[0043] In some instances, the reliable state of the target vehicle's current driving path is determined based on a preset driving path, including: From the preset driving path, obtain the preset feature information of at least one path feature point, wherein the path feature point is a key location point recorded during the memory learning stage to characterize the preset driving path; Obtain the actual feature information of the target vehicle after it starts driving from the starting position, which corresponds to at least one path feature point; The actual feature information is matched and compared with the corresponding preset feature information to obtain the matching result; Based on the matching results, the reliability status of the current driving path is determined.

[0044] For example, during the memory learning phase, the vehicle travels along a planned route from the starting position to the target parking position via manual driving or a specific recording mode, storing a series of key location points characterizing the planned route. These location points are defined as path feature points. Each path feature point is associated with a set of preset feature information, including the point's absolute coordinates, position relative to a fixed reference point, the vehicle's heading angle at that point, and local environmental feature data (such as specific landmarks, lane line geometry, and static obstacle outlines) collected and processed by onboard sensors (such as cameras and LiDAR) at that point. These path feature points, pre-acquired and stored during the memory phase, and their corresponding preset feature information constitute the benchmark for path compliance verification.

[0045] When the target vehicle activates the memory parking function and begins to drive automatically from its starting position, its real-time driving trajectory information is acquired for verification. To this end, the vehicle's actual position and attitude are periodically determined using an onboard positioning system (such as a positioning module integrating GNSS, IMU, and wheel speed signals) and a perception system. When the vehicle's actual position enters the preset spatial proximity range of a pre-stored path feature point, feature acquisition of that point is triggered. At this time, environmental data around the vehicle is collected in real time using current sensors, and features defined for that point during the memory phase are extracted to generate actual feature information corresponding to that path feature point. For example, if the preset feature information of a path feature point includes "5 meters from the building on the right" and "a traffic sign of a specific shape 10 meters ahead," the distance between the vehicle and the building on the right will be measured in real time when the vehicle approaches the point, and the presence of the specific traffic sign ahead will be identified, generating actual feature information containing the measured distance and the sign recognition result.

[0046] After acquiring the actual feature information corresponding to a specific path feature point, a matching and comparison operation is performed. This operation compares each data point in the actual feature information with each data point in the preset feature information corresponding to the same path feature point retrieved from storage. The comparison may involve spatial position error, heading angle deviation, and the matching degree of visual or point cloud features. For example, it calculates the difference between the real-time measured distance between the vehicle and the building and the preset distance, or determines whether the type and spatial relationship of the traffic sign identified in real-time are consistent with the preset sign. The matching result generated by this process characterizes the degree of conformity between the environment actually observed by the vehicle at the current point and the expected environment of the point in memory. If the matching result shows that the actual trajectory of the vehicle is highly consistent with the preset path within the allowable error range, it is judged as a valid state, meaning that the vehicle is still driving on the reliable memory path, the expected target parking space environment may be valid, and automated control continues; conversely, if the matching result exceeds the allowable range, it is judged as an invalid state, indicating that the vehicle may have seriously deviated from the preset path, or the environment has fundamentally changed, causing the memory path to fail, and there is a risk in continuing automated control, requiring the triggering of a safety response mechanism (such as function degradation or exit).

[0047] In summary, this application's embodiments provide a spatial and feature reference system for path conformity verification by introducing predefined path feature points and their preset feature information during the memory phase. During actual driving, when the vehicle approaches these predefined key points, corresponding actual feature information is collected and generated, enabling the reproduction and data capture of key locations on the memorized path. By matching and comparing the actual feature information with the preset feature information, the system assesses whether the vehicle is traveling on the expected memorized route and whether the surrounding environment has undergone any drastic changes, from both spatial geometry and environmental feature dimensions. The reliability status is determined based on rigorous matching results, moving beyond a rough estimate based on a single mileage to a consistency verification based on a series of feature points, thereby improving the accuracy of path verification.

[0048] In some instances, the target vehicle is controlled based on the first safety constraint parameters corresponding to the cruise phase to extend the fault tolerance time during unexpected steering, including: Based on the first safety constraint parameter, the preset upper limit of acceleration, preset upper limit of steering angle, preset upper limit of vehicle speed and preset upper limit of angular rate are determined for the cruise phase. Obtain the requested control parameters for controlling the driving of the target vehicle, wherein the requested control parameters include requested acceleration, requested steering angle, requested vehicle speed, and requested steering angle rate; When the requested acceleration exceeds the preset acceleration limit, or the requested steering angle exceeds the preset steering angle limit, or the requested vehicle speed exceeds the preset vehicle speed limit, or the requested steering angular rate exceeds the preset angular rate limit, the corresponding requested parameters that exceed the preset acceleration limit, preset steering angle limit, preset vehicle speed limit, or preset angular rate limit shall be adjusted to a value no greater than the preset limit value defined by the first safety constraint parameter.

[0049] For example, when performing safety control on a target vehicle during the cruise phase, specific control limits are first set based on a first safety constraint parameter specifically configured for this phase. These limits include, but are not limited to, the maximum speed the vehicle is allowed to reach during this phase, the maximum acceleration that can be applied, the maximum angle the steering wheel can rotate, and the upper limit of the speed at which the steering angle changes. These specific upper limit values ​​collectively constitute the boundary of the vehicle's dynamic behavior during the cruise phase. Their determination is based on a comprehensive consideration of the physical limits of the vehicle platform hardware, control system latency, functional safety objectives (such as fault tolerance time requirements for unexpected steering), and extensive real-vehicle testing and simulation calibration results, aiming to balance traffic efficiency and safety redundancy.

[0050] During actual vehicle operation, decision-making algorithms (such as path planning and decision-making modules running on a system-on-a-chip (SoC)) periodically generate vehicle motion commands. These commands are manifested as requests for control parameters, such as the requested acceleration, the requested steering wheel angle, the requested maintained speed, and the requested rate of change of steering angle. To ensure safety, these upstream request control parameters need to undergo safety verification. The verification process involves comparing each request parameter with its corresponding preset upper limit value defined by the first safety constraint parameter. When the comparison finds that any request parameter value exceeds its corresponding preset upper limit value, such as a requested acceleration greater than the preset acceleration upper limit or a requested steering angle greater than the preset steering angle upper limit, the safety monitoring unit (such as a microcontroller (MCU)) will intervene. The intervention method is not simply to reject the command, but to correct the specific request parameter that exceeds the limit, reducing its value to no greater than the preset upper limit value specified by the first safety constraint parameter. Then, the corrected set of control parameters, conforming to the safety boundary, is issued to the vehicle's actuators (such as the drive motor, steering motor, and braking system), thereby constraining the vehicle's motion.

[0051] In summary, this application's embodiments, based on a first safety constraint parameter defined by multi-dimensional dynamic indicators (acceleration, steering angle, vehicle speed, and steering angular rate), construct a safety boundary for vehicle behavior during the cruise phase, achieving comprehensive constraints on the vehicle's motion state. By acquiring the decision-making layer's requested control parameters in real time and comparing them with preset safety upper limits, safety verification of control commands is achieved, ensuring that the final executed command necessarily falls within the preset safety range. Crucially, by imposing limits on the steering angular rate and maximum steering angle, the severity of yaw motion when unexpected steering failures may occur during cruise is directly reduced. Steering actions become smoother, which extends the time consumed from the occurrence of a failure to its detection and identification by the system, and then to the initiation of safety countermeasures (such as reverse correction or deceleration braking). This provides a greater margin for fault tolerance time, improving the safety performance in handling such steering-related failures during the cruise phase.

[0052] It should be noted that the combination of safety constraints used during the above-mentioned cruise phase includes a maximum speed of no more than 15 km / h and a maximum acceleration of no more than 1.5 m / s². 2The steering angular rate not exceeding 400° / s and the maximum steering angle not exceeding 36.4° are determined through specific engineering methods. The limits for the steering angular rate and maximum steering angle are set based on theoretical calculations and safety analyses of the tolerance time interval for unexpected steering failures. This combination of parameters is not derived from subjective experience, but rather from engineering safety optimization values ​​obtained through extensive real-vehicle testing and simulation under the physical limits of a specific vehicle hardware platform. It ensures the protection of hardware such as the steering mechanism, while reserving necessary safety margins for control algorithm execution redundancy, system latency, and response to sudden obstacles.

[0053] In some instances, parking control of the target vehicle is performed based on the second safety constraint parameters corresponding to the parking phase to shorten the braking distance during unexpected acceleration, including: For example, when performing safety control on the target vehicle during the parking phase, the second safety constraint parameter sets stricter vehicle dynamic boundaries for this phase, which is reflected in a maximum speed not exceeding 5 km / h and an acceleration not exceeding 1 m / s². 2 The specific values ​​are set based on the specific requirements of parking scenarios for low speed, precise control, and safety redundancy. By significantly reducing the upper speed limit to a level far below the cruising speed and combining it with acceleration limits, the vehicle's kinetic energy growth potential and dynamic response intensity within confined parking spaces are constrained. When operating within the safety boundaries defined by these parameters, the vehicle's motion is maintained in a low-speed and smooth controlled mode. If an unexpected acceleration failure occurs during this process, due to the aforementioned preset speed and acceleration upper limits, the increase in vehicle speed and the accumulated kinetic energy caused by the failure will be controlled to a very low level. Therefore, whether the autonomous driving system actively triggers emergency braking or the driver intervenes to take braking measures, the distance required from the start of braking to the vehicle coming to a complete stop—that is, the braking distance—becomes very short due to the small initial kinetic energy. This allows the vehicle to stop safely in extremely limited spaces, effectively reducing the risk of collisions caused by unexpected acceleration during parking and achieving the goal of shortening the braking distance to improve parking safety.

[0054] In some instances, after determining the reliable state of the target vehicle's current driving path based on a preset driving route, the process also includes: When the trusted state is invalid, the automatic parking function of the target vehicle is turned off.

[0055] For example, after determining the credible state of the target vehicle's current driving path based on a preset driving path, if the credible state is determined to be invalid, the automatic parking function of the target vehicle is disabled. This step is based on the previous steps of acquiring the preset driving path and determining the credible state of the current driving path. An invalid state, as a conclusion of the credible state, is characterized by an unacceptable significant deviation found when the actual driving trajectory information of the vehicle from its starting position is compared with the preset driving path information from the starting position to the target parking position, which was recorded in the memory learning phase.

[0056] This deviation may stem from continuous drift of the vehicle positioning system, a fundamental change in the driving environment compared to the memory learning stage (e.g., the path is permanently occupied by obstacles, or the road structure is altered), the vehicle deviating significantly from the preset path due to obstacle avoidance or other reasons, or the actual feature information collected at key path feature points cannot effectively match the preset feature information.

[0057] When the trusted state is deemed invalid, it means that the vehicle may no longer be traveling on a valid memory path, or the target parking environment indicated by the preset path has become invalid. Continuing to execute the automatic parking function that relies on this preset path carries a high risk, such as potentially causing the vehicle to enter the wrong area, fail to recognize a valid parking space, or attempt to park in an unexpected location. Therefore, control commands will be proactively generated and issued to safely and orderly exit or shut down the running automatic parking function.

[0058] The specific steps to disable the automatic parking function may include: terminating the transmission of autonomous control commands generated based on the automatic parking logic to the vehicle's actuators (such as the drive motor, steering motor, and braking system); returning control of the vehicle to the driver, and providing visual, auditory, or tactile prompts through the human-machine interface to inform the driver that the system has exited due to unreliable paths and that the driver must immediately take over the vehicle; simultaneously, the automatic control state machine related to the current memorized parking task can be reset or switched to a standby safety state. This step ensures that the automation process can be interrupted in a timely manner when the prerequisite of path reliability is no longer met, avoiding collisions, driving off the road, or other safety risks that may be caused by blindly executing preset actions. This constitutes a key safety barrier in the entire intelligent driving safety control method, enhancing the overall robustness and safety of the function's operation.

[0059] In some instances, when the driving phase is a parking phase and the trusted state is valid, after performing parking control on the target vehicle based on the second safety constraint parameters corresponding to the parking phase, the following steps are also included: Based on the target vehicle's current speed and status flags, determine the parameter consistency status; When the parameter consistency status indicates that the current vehicle speed is greater than the preset speed limit corresponding to the parking stage and the status flag indicates the parking stage, the target vehicle is subjected to fault downgrade processing.

[0060] For example, the current speed of the target vehicle during the parking process is obtained, and the current value of the status flag bit set in the microcontroller is read simultaneously. The value of the status flag bit is dynamically updated to a second preset value used to identify the parking stage based on the determination result of the driving stage. The current speed is compared with the preset speed limit defined in the second safety constraint parameter set for the parking stage, and it is confirmed whether the current value of the status flag bit is consistent with the second preset value identifying the parking stage. If the current speed is greater than the preset speed limit, and the current value of the status flag bit is indeed the second preset value, the parameter consistency status is determined to be abnormal, indicating that a logical conflict has occurred between the actual operating state of the vehicle (excessive speed) and the recorded and based parking stage identification.

[0061] At this time, a fault degradation process will be triggered. This process includes, but is not limited to, limiting the output of drive torque, applying a preset deceleration rate to bring the vehicle speed back to a safe range, outputting corresponding warning information on the human-machine interface, and switching the vehicle control mode to a degraded safety state that requires close monitoring or intervention by the driver. In this way, when a potential fault with inconsistent status is detected, the risk is prevented from escalating by actively limiting the vehicle's dynamic performance, thus ensuring the safety of the parking process.

[0062] In summary, this application embodiment cross-validates the consistency between real-time vehicle speed and status flags, acquiring vehicle speed in real time to perceive the actual dynamic state, and simultaneously reading flags to confirm the current stage logic. The vehicle speed is compared with the preset speed limit for the parking stage to check if it exceeds the safety boundary; simultaneously, it confirms that the flag still indicates the parking stage to rule out logic jumps. When a contradictory state occurs where the vehicle speed exceeds the limit and the flag indicates parking, it indicates a control, execution, or state management fault. At this time, fault degradation processing is triggered, forcing the vehicle into a safer controlled state by limiting power output and control modes. In addition to traditional parameter constraints, fault detection based on state logic consistency is added, improving the ability to handle complex faults and the overall functional safety level of the system.

[0063] In some instances, it also includes: Obtain the brake pedal opening signal; Based on the opening signal, determine the current opening of the brake pedal; When the current opening degree is greater than the preset opening degree threshold, the target vehicle is controlled to perform a braking operation, and the memory parking function is kept active.

[0064] For example, during the entire operation of the memory parking function, a displacement sensor or angle sensor installed at the brake pedal collects raw analog or digital signals reflecting the degree to which the brake pedal is depressed, i.e., the brake pedal opening signal. This opening signal is transmitted to the vehicle's control unit (such as the Intelligent Driving Domain Controller (ADCU)). Based on the received opening signal, the signal processing module in the control unit parses and calculates it into a specific value characterizing the pedal travel or angle percentage through a built-in calibration mapping relationship, thereby determining the current opening of the brake pedal.

[0065] An internally preset, calibrated opening threshold (e.g., 12%) represents the critical point at which the driver has a clear intention to intervene in braking. The calculated current opening is compared with this preset threshold. When the comparison shows that the current opening is greater than the preset threshold, a highest-priority braking control command is generated and issued to the vehicle's braking actuator, controlling the target vehicle to perform the corresponding braking operation to achieve the driver's expected deceleration or stopping intention. While responding to braking, the logic state machine for maintaining the memory parking function remains active, meaning that the function is neither deactivated nor reset. This means that when the driver releases the brake pedal, if other conditions (such as path reliability and phase validity) are still met, the vehicle can resume and continue the previously interrupted automatic cruise or parking task without requiring the driver to reactivate the function.

[0066] In summary, the braking priority intervention mechanism of this application embodiment refers to the ability to sense the driver's braking operation input by continuously acquiring the brake pedal opening signal and determining the current opening value, thus realizing the basis of human-machine collaborative control. By comparing the current opening with a reasonably calibrated preset opening threshold, it can effectively distinguish between the driver's slight foot movements and braking intentions, avoiding erroneous function deactivation due to minor fluctuations in the pedal signal. When the driver's braking intention is determined to be clear, the braking control operation is executed unconditionally with priority, ensuring the driver's highest level of control over the vehicle, allowing direct intervention in vehicle dynamics at any time by pressing the brake pedal. Crucially, while responding to braking, the memory parking function is kept active rather than directly deactivated. This design treats braking intervention only as a temporary and recoverable interruption event. Once the driver's braking intervention ends, the vehicle can automatically continue the previous automatic driving task without a cumbersome reactivation process, eliminating unexpected function interruptions caused by necessary human intervention, optimizing the smooth experience of human-machine collaborative driving, and maximizing the convenience and continuity of automated functions while ensuring safety.

[0067] Please see Figure 2 This is a schematic diagram of an intelligent driving safety control device provided in an embodiment of this application, applied in the cloud, including: The driving phase determination unit 21 is used to determine the current driving phase of the target vehicle based on the current distance between the target vehicle and the target parking position and the current speed of the target vehicle. The driving phase includes a cruising phase or a parking phase. The trusted state determination unit 22 is used to determine the trusted state of the current driving path of the target vehicle based on the preset driving path. The preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning stage. The trusted state includes a valid state or an invalid state. The driving phase control unit 23 is used to control the target vehicle based on the first safety constraint parameters corresponding to the cruise phase when the driving phase is the cruise phase and the trusted state is the effective state, so as to extend the fault tolerance time when unexpected steering occurs. The parking phase control unit 24 is used to perform parking control on the target vehicle based on the second safety constraint parameters corresponding to the parking phase when the driving phase is the parking phase and the trusted state is valid, so as to shorten the braking distance during unexpected acceleration.

[0068] Please see Figure 3 This application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the intelligent driving safety control method.

[0069] Since the electronic device described in this embodiment is the device used to implement an intelligent driving safety control device in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application is within the scope of protection of this application.

[0070] In practice, when the computer program 311 is executed by the processor, it can implement any of the embodiments corresponding to the first aspect.

[0071] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0072] Those skilled in the art will understand that embodiments of this application can provide methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media containing computer-readable program code.

[0073] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform... Figure 1 The flowchart of an intelligent driving safety control method in the corresponding embodiment.

[0077] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any usable medium that a computer can store or a data storage device such as a server or data center that integrates one or more usable media. The usable medium may be a magnetic medium, an optical medium, or a semiconductor medium, etc.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Furthermore, the mutual couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0081] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in the form of hardware and / or software functional units.

[0082] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, magnetic disks, or optical disks.

[0083] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0084] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications that fall outside the scope of this specification.

[0085] Obviously, those skilled in the art can make various modifications to this specification without departing from its spirit and scope. Therefore, this specification also intends to include any modifications that fall within the scope of the claims and their equivalents.

Claims

1. A method for intelligent driving safety control, characterized in that, include: Based on the current distance between the target vehicle and the target parking location and the current speed of the target vehicle, the current driving stage of the target vehicle is determined, wherein the driving stage includes a cruising stage or a parking stage. Based on a preset driving path, the credible state of the current driving path of the target vehicle is determined, wherein the preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning phase, and the credible state includes a valid state or an invalid state. When the driving phase is the cruise phase and the trusted state is the valid state, the target vehicle is driven based on the first safety constraint parameter corresponding to the cruise phase in order to extend the fault tolerance time during unexpected steering. When the driving phase is the parking phase and the trusted state is the valid state, parking control is performed on the target vehicle based on the second safety constraint parameter corresponding to the parking phase to shorten the braking distance during unexpected acceleration.

2. The method according to claim 1, characterized in that, Determining the current driving stage of the target vehicle based on the current distance between the target vehicle and the target parking location and the current speed of the target vehicle includes: When the current distance is greater than or equal to a preset distance threshold, or the current vehicle speed is greater than or equal to a preset vehicle speed threshold, the driving phase is determined to be the cruising phase; When the current distance is less than the preset distance threshold and the current vehicle speed is less than the preset vehicle speed threshold, the driving stage is determined to be the parking stage.

3. The method according to claim 1 or 2, characterized in that, Also includes: A status flag is set to identify the driving stage, wherein a first preset value is used to identify the cruising stage and a second preset value is used to identify the parking stage; After the target vehicle activates the memory parking function, the value of the status flag bit is initialized to the first preset value; After determining that the driving stage is the cruise stage or the parking stage, the value of the status flag is updated to the first preset value or the second preset value corresponding to the determined driving stage.

4. The method according to claim 1, characterized in that, The step of determining the reliable status of the target vehicle's current driving path based on a preset driving path includes: From the preset driving path, obtain preset feature information of at least one path feature point, wherein the path feature point is a key location point recorded in the memory learning stage to characterize the preset driving path; Obtain the actual feature information of the target vehicle after it starts driving from the starting position, which corresponds to the at least one path feature point; The actual feature information is matched and compared with the corresponding preset feature information to obtain the matching result; Based on the matching results, the reliability status of the current driving path is determined.

5. The method according to claim 1, characterized in that, The driving control of the target vehicle based on the first safety constraint parameters corresponding to the cruise phase includes: Based on the first safety constraint parameters, the preset upper limit of acceleration, preset upper limit of steering angle, preset upper limit of vehicle speed and preset upper limit of angular rate allowed in the cruise phase are determined. Obtain request control parameters for controlling the driving of the target vehicle, wherein the request control parameters include request acceleration, request steering angle, request vehicle speed, and request steering angle rate; When the requested acceleration is greater than the preset acceleration limit, or the requested steering angle is greater than the preset steering angle limit, or the requested vehicle speed is greater than the preset vehicle speed limit, or the requested steering angle rate is greater than the preset angle rate limit, the corresponding requested parameters exceeding the preset acceleration limit, the preset steering angle limit, the preset vehicle speed limit, or the preset angle rate limit shall be adjusted to a value no greater than the preset limit value defined by the first safety constraint parameter.

6. The method according to claim 4, characterized in that, After determining the reliable state of the target vehicle's current driving path based on a preset driving path, the method further includes: When the trusted state is invalid, the automatic parking function of the target vehicle is turned off.

7. The method according to claim 3, characterized in that, After performing parking control on the target vehicle based on the second safety constraint parameter corresponding to the parking stage when the driving stage is the parking stage and the trusted state is the valid state, the method further includes: Based on the current speed of the target vehicle and the status flag, determine the parameter consistency status; When the parameter consistency status indicates that the current vehicle speed is greater than the preset vehicle speed limit corresponding to the parking stage and the status flag indicates the parking stage, the target vehicle is subjected to fault downgrade processing.

8. The method according to claim 1, characterized in that, Also includes: Obtain the brake pedal opening signal; Based on the opening signal, determine the current opening of the brake pedal; When the current opening degree is greater than the preset opening degree threshold, the target vehicle is controlled to perform a braking operation, and the memory parking function is kept active.

9. An intelligent driving safety control device, characterized in that, include: A driving phase determination unit is used to determine the current driving phase of the target vehicle based on the current distance between the target vehicle and the target parking position and the current speed of the target vehicle, wherein the driving phase includes a cruising phase or a parking phase. A trusted state determination unit is used to determine the trusted state of the current driving path of the target vehicle based on a preset driving path, wherein the preset driving path is the driving path from the starting position to the target parking position recorded by the target vehicle during the memory learning phase, and the trusted state includes a valid state or an invalid state. A driving phase control unit is used to control the target vehicle based on a first safety constraint parameter corresponding to the driving phase when the driving phase is the cruise phase and the trusted state is the effective state, so as to extend the fault tolerance time during unexpected steering. A parking phase control unit is used to perform parking control on the target vehicle based on the second safety constraint parameters corresponding to the parking phase when the driving phase is the parking phase and the trusted state is the valid state, so as to shorten the braking distance during unexpected acceleration.

10. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program stored in the memory, implements the steps of the intelligent driving safety control method as described in any one of claims 1 to 8.

Images