Method, system, device and storage medium for suppressing accelerated assist driving control

Abstract

The application relates to an accelerated auxiliary driving control method, system, device and storage medium. Through real-time collection of vehicle surrounding environment information by an intelligent driving control unit, combination of vehicle state information monitored by a kinetic energy control unit, and driver state information obtained by an in-vehicle monitor, dynamic comparison of a pre-constructed user driving habit database by a central processor, multi-dimensional unexpected acceleration judgment is realized. When the driving behavior deviation exceeds the threshold value, the environment risk level reaches the high risk, and the driver state is abnormal, the system triggers the power limitation or cut-off instruction in stages, and cooperates with the brake system to perform safe deceleration. Through the cooperative decision of environment perception, personalized driving mode matching and real-time state monitoring, the problems of high false rejection rate and response lag in the prior art are effectively solved, and the driving safety is significantly improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent assisted driving technology, specifically to an assisted driving control method, system, device, and storage medium for suppressing acceleration. Background Technology

[0002] As the acceleration performance of electric vehicles continues to improve and the number of existing new energy vehicles continues to increase, users are paying more and more attention to vehicle safety. Vehicle safety is not only reflected in collision safety and information security, but also in various unexpected acceleration scenarios. Unexpected acceleration is a major concern for users, leading to the emergence of a large number of speed limit control methods.

[0003] Currently, acceleration suppression devices in automobiles require users to react automatically to accident scenarios and suppress acceleration based on their own judgment.

[0004] However, in the moments when many accidents occur, users are often in a state of heightened tension or incorrect driving, which can lead to significant errors in judgment and serious safety issues. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, device, and storage medium for suppressing acceleration in assisted driving control, in order to solve a series of safe driving accidents caused by unexpected acceleration in new energy vehicles.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] An assisted driving control method for suppressing acceleration, applied to the central processing unit in an assisted driving control system.

[0008] The method includes:

[0009] When the mode to suppress unexpected acceleration is activated, the system performs scene matching based on the real-time captured current environmental information of the vehicle and a pre-built user driving habit database to obtain the target scene. The user driving habit database includes various road condition scenes and driving behavior data corresponding to each scene.

[0010] Based on the target scenario, the current environmental information, the pre-acquired driver status information, vehicle status information, and the user driving habit database, determine whether to perform acceleration suppression;

[0011] If acceleration suppression is determined, a suppression command is sent to the kinetic energy control unit so that the kinetic energy control unit performs acceleration suppression on the vehicle based on the suppression command.

[0012] In one possible implementation, determining whether to perform acceleration suppression based on the target scenario, the current environmental information, pre-acquired driver state information, vehicle state information, and the user driving habit database includes:

[0013] Based on the target scenario, extract driving behavior data corresponding to the target scenario from the user driving habit database;

[0014] Based on the driver status information, determine the driver status abnormality indicators;

[0015] Based on the vehicle status information and the driving behavior data, the driving behavior deviation is calculated;

[0016] Based on the current environmental information, assess the environmental hazard level;

[0017] If the driver's abnormal state index, the driving behavior deviation, and the environmental hazard level all meet the preset unexpected acceleration conditions, then acceleration suppression is determined to be executed.

[0018] In one possible implementation, the method further includes:

[0019] Receive driver identification information sent by the in-vehicle monitoring device;

[0020] The driver's identity information is compared with the preset vehicle owner information;

[0021] If the driver's identity information is the same as the preset vehicle owner information, then the mode to suppress unexpected acceleration will be activated.

[0022] If the driver's identity information is different from the preset vehicle owner information, the system will switch to the default driving mode and prompt the user.

[0023] In one possible implementation, the unintended acceleration conditions include abnormal driving behavior conditions, hazardous environmental conditions, and consequently, abnormal driver state conditions.

[0024] The abnormal driving behavior conditions include the driving behavior deviation exceeding a preset deviation threshold;

[0025] The environmental hazard conditions are classified as high-level.

[0026] The abnormal driver status condition includes any two of the following conditions:

[0027] If the gaze is off the road for more than a first preset time, the heart rate exceeds the baseline range by a preset percentage, or the hands are off the steering wheel for more than a second preset time.

[0028] In one possible implementation, the suppression command includes a primary suppression command or a secondary suppression command. Before sending the suppression command to the kinetic energy control unit, the method further includes:

[0029] Calculate the forward collision time and the avoidable space index based on the current environmental information;

[0030] If the forward collision time is greater than a third preset time and the avoidable space index is greater than a preset threshold, then the first-level suppression command is generated. The first-level suppression command includes maintaining the current power output and activating the braking system to decelerate smoothly.

[0031] If the forward collision time is less than the third preset time and / or the avoidable space index is less than the preset threshold, then the secondary suppression command is generated. The secondary suppression command includes immediately cutting off the motor power output, activating the electronic stability system for steering assistance, and performing maximum braking.

[0032] In one possible implementation, the multiple road condition scenarios include any one or more of urban road conditions, mountain road conditions, rural road conditions, daily driving conditions, and highway driving conditions.

[0033] In one possible implementation, the method further includes:

[0034] Record the data information after suppressing acceleration;

[0035] Based on the data information, the user driving habit database is updated.

[0036] An assisted driving control system for suppressing acceleration, characterized in that it comprises: an intelligent driving control unit, a kinetic energy control unit, a central processing unit, and an in-vehicle monitor, wherein the intelligent driving control unit is connected to the central processing unit via Ethernet communication, and the kinetic energy control unit and the in-vehicle monitor are respectively connected to the central processing unit via CAN bus communication.

[0037] The intelligent driving control unit includes millimeter-wave radar, lidar, and a camera, which are used to perceive the vehicle's surrounding environment in real time, generate environmental information, and send it to the central processing unit.

[0038] The kinetic energy control unit includes wheel speed sensors, acceleration sensors, and braking sensors, which are used to monitor the vehicle status in real time and generate vehicle status information to be sent to the central processing unit.

[0039] The in-vehicle monitor includes an in-vehicle camera and a heartbeat detector, used to monitor the driver's status information in real time and send the driver's status information to the central processing unit;

[0040] The central processing unit is used to execute the acceleration suppression assisted driving control method as described in any of the preceding methods.

[0041] A central processing unit includes: a storage unit and a processing unit;

[0042] The storage unit stores computer-executed instructions;

[0043] The processing unit executes the computer execution instructions stored in the storage unit, causing the processing unit to perform the method described above.

[0044] A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described above.

[0045] A computer program product includes a computer program that, when executed by a processor, implements the method described above.

[0046] The beneficial effects of this invention are:

[0047] By collecting real-time environmental information about the vehicle's surroundings through the intelligent driving control unit, combining it with vehicle status information monitored by the kinetic energy control unit, and driver status information obtained from in-vehicle monitors, the central processor dynamically compares this information with a pre-built user driving habit database to achieve multi-dimensional judgment of unexpected acceleration. When the deviation of driving behavior exceeds a threshold, the environmental hazard level reaches a high risk, and the driver's state is abnormal, the system triggers power limiting or cut-off commands in stages, and coordinates with the braking system to perform safe deceleration. This solution effectively solves the problems of high misjudgment rate and slow response in existing technologies through the coordinated decision-making of environmental perception, personalized driving mode matching, and real-time status monitoring, significantly improving driving safety. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the architecture of an assisted driving control system.

[0049] Figure 2 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 1 ;

[0050] Figure 3 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 2 ;

[0051] Figure 4 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 3 ;

[0052] Figure 5Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 4 ;

[0053] Figure 6 A schematic diagram of the structure of a central processing unit provided in an embodiment of this application.

[0054] Explanation of reference numerals in the attached diagram: 1-Millimeter-wave radar; 2-LiDAR; 3-Camera; 4-Wheel speed sensor; 5-Acceleration sensor; 6-Brake sensor; 7-Intelligent driving control unit; 8-Kinematic energy control unit; 9-Central processing unit; 10-Central control screen; 11-In-vehicle camera; 12-Heartbeat detector; 13-Ethernet cable; 14-CAN cable; 15-LVDS cable. Detailed Implementation

[0055] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0056] Currently, car acceleration suppression devices require users to react automatically to accident scenarios and suppress acceleration based on their own judgment. However, in many accidents, users are often in a state of emotional tension or incorrect driving, which can lead to significant errors in judgment and pose serious safety risks.

[0057] With the rise of AI and big data, to better identify safety risks and provide a more intelligent acceleration suppression method for users, AI big data is used to continuously record users' driving habits, forming a database of users' acceleration habits. When the mode to suppress unexpected acceleration is activated, LiDAR, millimeter-wave radar, and cameras are used to identify risks around the vehicle and match them with the driver's daily driving habits. For unsafe scenarios, AI makes a judgment and directly interrupts power to change the vehicle's state, protecting the driver's safety. For unexpected acceleration situations that occur during normal driving, the system will match the user's driving habits with the user's seat status, heart rate status, and other personal status to determine whether to execute an acceleration command, thereby protecting the user's driving safety.

[0058] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0059] Figure 1 This is a schematic diagram of the architecture of an assisted driving control system, such as... Figure 1 As shown, the system includes an intelligent driving control unit, a kinetic energy control unit, a central processing unit, and an in-vehicle monitor. The intelligent driving control unit is connected to the central processing unit via Ethernet, and the kinetic energy control unit and the in-vehicle monitor are connected to the central processing unit via CAN bus.

[0060] Optionally, the system may also include a central control screen, through which users can interact intelligently with the central processor.

[0061] The intelligent driving control unit mainly includes millimeter-wave radar, lidar and cameras. Through combined application, it enables the vehicle to perceive the surrounding environment in an all-round and high-precision manner and provide feedback on changes in the user's driving environment.

[0062] The kinetic energy control unit mainly includes wheel speed sensors, acceleration sensors, and braking sensors. During vehicle operation, its speed, acceleration, and braking signals are output to the central processing unit in real time.

[0063] After receiving the mode settings from the central control screen, the central processing unit will collect and process images and data from the intelligent driving control unit in real time, as well as the vehicle status from the intelligent driving control unit, and store the analysis results in the central processing unit's file library to form a personalized user driving style record; the central processing unit will also receive information from the vehicle's cameras and heartbeat detection device in real time to detect the user's status and ensure driving safety.

[0064] Specifically, users can enable or disable the unexpected acceleration suppression mode on the central control screen. If the screen receives an enable signal, it will transmit the relevant signal to the central processor via the LVDS line. Millimeter-wave radar, lidar, and cameras form an intelligent driving control unit via Ethernet cables, capturing the surrounding environment in real time. The intelligent driving control unit will classify and process the collected environmental scenes and transmit the processed information to the central processor. Wheel speed sensors, acceleration sensors, braking sensors, kinetic energy control units, and the central processor work together, transmitting information via CAN cables. After receiving the instruction from the central processor to enable the unexpected acceleration suppression mode, the kinetic energy control unit will transmit vehicle status signals to the central processor in real time. The in-vehicle camera and heart rate detector will monitor the driver's status in real time. Once the driver is detected to be in a non-driving state or in other unexpected situations, the relevant information will be transmitted to the central processor via CAN cables. The central processor, based on its internal processing logic, will notify the kinetic energy control unit to take appropriate action via CAN cables. The central processing unit receives scene classifications from the intelligent driving control unit and, together with the kinetic energy control unit, establishes a database to record the driver's driving speed, accelerator pedal, and braking behavior in different environments, forming an AI user database. When it receives dangerous situations such as the driver being in a non-driving position or the driver's heart stopping, it can promptly issue instructions to the kinetic energy control unit and, based on the real-time driving situation, perform emergency handling.

[0065] Figure 2 This is a schematic flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application. Figure 1 ,like Figure 2 As shown, this method is applied to the above Figure 1 The central processing unit in the driver assistance control system, specifically includes the following methods:

[0066] S201: When the mode to suppress unexpected acceleration is activated, the target scenario is obtained by matching the current environmental information of the vehicle captured in real time with the pre-built user driving habit database.

[0067] Currently, unintended acceleration threshold solutions typically use a uniform accelerator pedal travel threshold, which cannot adapt to the individual operating habits of different drivers, resulting in a high misjudgment rate. Furthermore, relying solely on the braking system for abrupt intervention lacks coordinated control with the power system, making it prone to causing vehicle instability.

[0068] In this step, existing technologies typically classify scenes using GPS positioning or simple vehicle speed, which cannot identify complex road conditions, such as similar scenes on urban expressways and highways. Furthermore, static scene classification cannot adapt to dynamic changes such as temporary construction and congestion. Therefore, accurate dynamic scene determination can be achieved based on multi-dimensional data.

[0069] Specifically, the system captures real-time information about the vehicle's current environment and performs scene matching based on a pre-built database of user driving habits to determine the target scene.

[0070] The current environmental information is composed of data collected by millimeter-wave radar, lidar, and external vehicle cameras. This allows for comprehensive and high-precision perception of the vehicle's surroundings. It should be noted that the millimeter-wave radar, lidar, and external vehicle cameras are connected via Ethernet in the aforementioned embodiment. Figure 1 The intelligent driving control unit in the system can collect data on the vehicle's surrounding environment in real time.

[0071] The user driving habit database includes various road condition scenarios and corresponding driving behavior data for each scenario. These various road conditions include, but are not limited to, any one or more of the following: urban road conditions, mountain road conditions, rural road conditions, daily driving conditions, and highway driving conditions.

[0072] It should be noted that the user driving habit database is built based on drivers' historical driving behavior data under different road conditions.

[0073] The system compares the current environmental information collected with different road conditions in the user's driving habit database to determine the scenario with the highest matching degree as the target scenario.

[0074] Optionally, the scene matching probability can be calculated based on a pre-trained random forest classifier to determine the scene with the highest probability. This implementation is merely an example, and the embodiments of this application do not specifically limit the specific matching implementation method.

[0075] S202: Based on the target scenario, current environmental information, pre-acquired driver status information, vehicle status information, and user driving habit database, determine whether to perform acceleration suppression.

[0076] In this step, existing technologies, which only monitor pedal travel, cannot distinguish between sudden acceleration and pedal sticking, thus ignoring the correlation between environmental risks and driver state. This new technology, however, comprehensively judges whether unexpected acceleration has occurred by considering the target scenario, current environmental information, pre-acquired driver state information, vehicle state information, and a user driving habit database, avoiding misjudgments from a single sensor. This addresses the high false alarm rate caused by existing systems relying on a single indicator (such as pedal opening).

[0077] Specifically, based on the target scenario, driving behavior data corresponding to the target scenario is extracted from the user driving habit database. Based on the driver's state information, abnormal driver state indicators are determined. Based on the vehicle state information and driving behavior data, the driving behavior deviation is calculated. Based on the current environmental information, the environmental hazard level is assessed. If the abnormal driver state indicators, driving behavior deviation, and environmental hazard level all meet the preset unexpected acceleration conditions, then acceleration suppression is determined to be executed.

[0078] S203: If it is determined that acceleration suppression should be performed, a suppression command is sent to the kinetic energy control unit so that the kinetic energy control unit performs acceleration suppression on the vehicle based on the suppression command.

[0079] Current technologies typically trigger maximum braking force directly during acceleration suppression, which can easily lead to rear-end collisions. Furthermore, the lack of coordination with the powertrain means the electric motor continues to output power even when ESP intervenes. Therefore, implementing tiered braking measures can balance safety and driving experience, avoiding the vehicle instability issues caused by a one-size-fits-all braking approach.

[0080] Specifically, when it is determined that the acceleration is unexpected and acceleration suppression needs to be performed, a suppression command is sent to the vehicle's kinetic energy control unit, which then executes the acceleration suppression command according to the suppression command.

[0081] For example, the execution process can be carried out in emergency mode, where the power system will reduce the motor torque from 100% to 0% within 20ms and activate regenerative braking, which can provide an additional -0.2g deceleration, for example.

[0082] The brake-by-wire module of the braking system establishes hydraulic pressure, for example, the pressure build-up time from 0 to 100 bar is 120 ms, and the four-wheel braking force distribution ratio can be 65% in the front and 35% in the rear.

[0083] The steering assist can calculate the density of obstacles in each 30-degree sector based on the point cloud data collected by the lidar, thereby applying a unilateral braking force difference to the left.

[0084] Optionally, the method further includes:

[0085] S204: Records data information after acceleration is suppressed.

[0086] S205: Update the user driving habit database based on data information.

[0087] Existing technologies typically rely on manual calibration and updates of databases at regular intervals, which fails to automatically filter out abnormal data. Therefore, automatic database updates can enable system self-optimization, continuously adapt to changes in user driving habits, and resolve the performance degradation issues caused by the rigidity of existing technical parameters.

[0088] Specifically, during the acceleration suppression process, the central processing unit records and stores the data information after the acceleration is suppressed in real time, providing a complete record of all dimensions of data before and after the unexpected acceleration event. This data can be used for accident retrospective analysis, liability determination, and system optimization. This solves the problems of liability disputes and optimization difficulties caused by incomplete data recording in existing technologies.

[0089] For example, the data information may include environmental information, such as the distance to the vehicle in front, relative speed and acceleration of the vehicle in front collected by millimeter-wave radar, point cloud data collected by lidar and the boundary coordinates of the drivable area, lane curvature and traffic light status collected by the vehicle's external camera, etc.

[0090] It can also include vehicle status, such as the motor output torque and battery SOC of the drive system, the master cylinder pressure and brake force distribution ratio of the braking system, and the steering wheel angle and yaw rate of the steering system.

[0091] It can also include driver status information, such as visual behavior, driver's gaze direction and blink frequency, operational behavior, driver's hand grip position, pedal pressure, physiological indicators, real-time heart rate, skin conductance, etc.

[0092] To ensure the system continuously adapts to changes in user driving habits and road conditions, and to prevent performance degradation due to data aging, the problem of static databases in existing technologies being unable to adapt to evolving driver behavior can be addressed. This allows for the updating of the user driving habit database based on the recorded data.

[0093] Specifically, the data needs to be cleaned first. For example, invalid data, such as sensor failure periods and extreme weather data, and abnormal operation annotations, such as automatically marking emergency obstacle avoidance operations, can be filtered out. Suspicious data can also be manually composited. Then, feature extraction and weighting are performed. For example, updating driving behavior features, where features can include the average pedal opening and braking response time. The average pedal opening can be updated using a sliding window weighted average, and the braking response time can be updated by recalculating after removing the maximum and minimum values.

[0094] It should be noted that the above are merely examples for understanding the implementation of the solution, and the embodiments of this application do not specifically limit the specific implementation process.

[0095] The acceleration suppression assisted driving control method provided in this application, when activating the unexpected acceleration suppression mode, performs scene matching based on real-time captured vehicle current environmental information and a pre-built user driving habit database to obtain a target scene. Based on the target scene, current environmental information, pre-acquired driver state information, vehicle state information, and user driving habit database, it determines whether to execute acceleration suppression. If acceleration suppression is determined, a suppression command is sent to the kinetic energy control unit, causing the kinetic energy control unit to execute acceleration suppression on the vehicle based on the suppression command. This method effectively solves the problems of high misjudgment rate and slow response in existing technologies, significantly improving driving safety.

[0096] Figure 3 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 2 ,like Figure 3 As shown, based on the above embodiment, step S202 specifically includes:

[0097] S301: Based on the target scenario, extract driving behavior data corresponding to the target scenario from the user driving habit database.

[0098] Traditional methods for analyzing driver behavior data after determining the driving scenario typically use fixed thresholds, which cannot adapt to different driver operating habits. However, accurately extracting historical driving behavior data matching the current driving scenario from a user driving habit database provides a personalized benchmark for subsequent unexpected acceleration judgments and can also solve the aforementioned problems.

[0099] Specifically, as described in the above embodiments, determining the target scene can be achieved in another possible way. This involves using millimeter-wave radar to detect the distance and relative speed to the vehicle ahead, lidar to generate road curvature and lane width data, and camera-recognized traffic sign information to construct a complete feature vector for the current scene. The similarity between the current scene features and the feature vectors of five predefined scene categories (urban, highway, mountain, rural, and everyday) in the database is calculated using an Euclidean distance algorithm. The scene with the highest similarity is selected as the target scene; for example, a similarity threshold of 85% or higher is set.

[0100] For example, based on a defined target scenario, the driver's historical driving data for that scenario can be retrieved from the database. This data may include accelerator pedal travel statistics (mean, standard deviation, maximum value), typical speed ranges and their probability distribution, braking operation characteristics (accelerator pedal release rate before braking, braking force distribution), etc.

[0101] It should be noted that the data time range can be the most recent 3 months to ensure timeliness.

[0102] S302: Determine abnormal driver status indicators based on driver status information.

[0103] In this step, multimodal sensor data is used to comprehensively determine whether the driver is in a state where he is unable to operate the vehicle normally, providing a key basis for suppression decisions.

[0104] Specifically, the driver's visual behavior is monitored, for example, by using an infrared camera to continuously track: gaze direction (calculated from the corneal reflection point) and head posture (pitch and yaw angles) at a sampling rate of 30fps. When the gaze is detected to deviate from the center of the road ahead for more than a preset time, it is marked as inattentiveness.

[0105] Physiological state monitoring: Capacitive sensors are used to monitor the steering wheel grip status in real time, such as hand contact area, grip force, and time of release. Heart rate variability (HRV) can also be detected by photoplethysmography (PPG). Abnormalities are defined as follows: heart rate below 50 bpm or above 120 bpm, and HRV standard deviation exceeding 30% of baseline.

[0106] Seated posture analysis: Seat pressure distribution sensors detect, for example, weight distribution deviation (left-right difference >15kg) and seat tilt angle (forward-backward >10° or left-right >8°). A warning is triggered if the abnormality persists for more than a preset time.

[0107] S303: Calculate the deviation of driving behavior based on vehicle status information and driving behavior data.

[0108] In this step, the degree of difference between the current driving operation and historical behavioral benchmarks is precisely quantified to identify potential unintended acceleration behaviors.

[0109] Specifically, vehicle status information can include accelerator pedal opening (0-100%), pedal change rate (% / s), and vehicle speed change acceleration. The standard deviation multiple of the current pedal opening compared to the historical mean is calculated, and the dynamic characteristics of pedal operation, such as emergency pedal detection and abnormal holding time, are analyzed.

[0110] A deviation index is constructed, which includes opening deviation value, abnormal rate of change and vehicle speed matching degree. Weights are assigned to each item, and then a fuzzy logic algorithm is used to obtain the behavior deviation degree.

[0111] S304: Assess the environmental hazard level based on current environmental information.

[0112] In this step, by comprehensively assessing the level of safety risks in the vehicle's surrounding environment, it can be ensured that the suppression operation will not cause secondary danger.

[0113] Specifically, based on relative distance measurements and relative velocity calculations from millimeter-wave radar data, the precise collision time is calculated for a graded assessment to obtain the forward collision risk level. Then, through lidar point cloud processing, ground plane fitting and obstacle clustering analysis are performed to calculate the passable area, obtaining the effective width (remaining lane width) and length (visibility distance), thereby analyzing the lateral avoidance space. Weights are then assigned to these two indicators to obtain the environmental hazard level.

[0114] S305: If the driver's abnormal state indicators, driving behavior deviation, and environmental hazard level all meet the preset unexpected acceleration conditions, then acceleration suppression will be implemented.

[0115] In this step, based on the analysis results of the previous four steps, a final decision is made on whether to suppress acceleration, ensuring the accuracy and safety of the judgment.

[0116] Specifically, an unexpected acceleration condition is pre-set. If the analysis results of the above four parts all meet the condition, it is judged as an unexpected acceleration behavior, and acceleration suppression needs to be performed.

[0117] Unexpected acceleration conditions include abnormal driving behavior conditions, hazardous environmental conditions, and abnormal driver status conditions. Abnormal driving behavior conditions include driving behavior deviation exceeding a preset deviation threshold; hazardous environmental conditions are at a high level; abnormal driver status conditions include any two of the following conditions: the driver's gaze is off the road for more than a first preset time, the heart rate exceeds the baseline range by a preset percentage, and the driver's hands are off the steering wheel for more than a second preset time.

[0118] Optionally, after determining that acceleration suppression needs to be performed, haptic feedback and visual prompts can be provided to the user, such as vibration of the accelerator pedal and flashing of a red warning box. A manual cancellation window can also be retained for a certain period of time. If the user cancels the acceleration suppression within the preset time, the acceleration suppression will not be performed. If the preset time is exceeded, the acceleration suppression will be performed automatically.

[0119] The acceleration suppression assisted driving control method provided in this application extracts driving behavior data corresponding to the target scenario from a user driving habit database based on the target scenario. Based on driver state information, it determines abnormal driver state indicators. Based on vehicle state information and driving behavior data, it calculates the driving behavior deviation. Based on current environmental information, it assesses the environmental hazard level. If the abnormal driver state indicators, driving behavior deviation, and environmental hazard level all meet preset unexpected acceleration conditions, it determines to execute acceleration suppression. This method, by establishing a refined scenario classification system, a multi-dimensional real-time monitoring network, and an intelligent decision-making mechanism, maximizes the preservation of driving autonomy while ensuring safety.

[0120] Figure 4 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 3 ,like Figure 4 As shown, based on the above embodiments, the method further includes:

[0121] S401: Receives driver identification information sent by the in-vehicle monitor.

[0122] S402: Compare driver identity information with preset vehicle owner information.

[0123] S403: If the driver's identity information is the same as the preset vehicle owner information, then activate the mode to suppress unexpected acceleration.

[0124] S404: If the driver's identity information does not match the preset vehicle owner information, switch to the default driving mode and prompt the user.

[0125] Accurately acquiring the current driver's biometric information provides a data foundation for subsequent identity verification. This solves the problem of personalized settings failing to distinguish between different drivers, a problem inherent in traditional solutions. It also verifies whether the current driver is an authorized user, ensuring that personalized security policies are accurately loaded. After successful verification, it loads the verified vehicle owner's exclusive driving safety configuration, achieving personalized protection. For unregistered drivers, a universal security policy is used, ensuring basic protection while preventing false alarms.

[0126] Specifically, the vehicle is equipped with a camera that can identify the driver and obtain their identity information. It can also capture the driver's facial information and perform data preprocessing on the captured facial information, such as facial image normalization. Then, the processed facial data is compared with pre-stored personnel information. If the comparison is successful, the mode to suppress unexpected acceleration is activated. If the comparison fails, the mode to suppress unexpected acceleration is not activated, and the vehicle switches to the default driving mode and prompts the current user.

[0127] Optionally, the above steps are triggered in response to the user's operation of enabling the suppression of unexpected acceleration mode. The user can send a request to the central processing unit to enable the suppression of unexpected acceleration mode through the central control screen, and the central processing unit performs the above steps based on the request.

[0128] Optionally, voiceprint verification can be used to improve the accuracy of identity recognition. It should be noted that the collection of user information in this embodiment is authorized by the user.

[0129] The acceleration suppression assisted driving control method provided in this application embodiment receives driver identity information sent by an in-vehicle monitor, compares the driver identity information with preset vehicle owner information, and if the driver identity information and the preset vehicle owner information are the same, activates the unexpected acceleration suppression mode; if the driver identity information and the preset vehicle owner information are different, switches to the default driving mode and prompts the user. This solution improves the safety of vehicle use.

[0130] Figure 5 Flowchart of the assisted driving control method for suppressing acceleration provided in the embodiments of this application Figure 4 ,like Figure 5 As shown, based on the above embodiments, if the suppression command includes a first-level suppression command or a second-level suppression command, then before sending the suppression command to the kinetic energy control unit, the method further includes:

[0131] S501: Calculates forward collision time and avoidable space index based on current environmental information.

[0132] S502: If the forward collision time is greater than the third preset time and the avoidable space index is greater than the preset threshold, then generate a first-level suppression command.

[0133] S503: If the forward collision time is less than the third preset time and / or the avoidable space index is less than the preset threshold, a secondary suppression command is generated.

[0134] Minimize driving intervention while ensuring safety and maintaining driving smoothness. Address the comfort issues arising from the traditional "one-size-fits-all" braking approach. Furthermore, implement maximum safety intervention in emergencies to prevent collisions. Overcome the shortcomings of traditional approaches, such as slow braking response and insufficient hazard avoidance capabilities. Intelligent mitigation strategies can be employed.

[0135] Specifically, after determining that acceleration suppression is necessary, the forward collision time and the avoidable space index are calculated based on the current environmental information. The specific calculation method is the same as in the previous embodiment and will not be repeated here. After calculating the forward collision time and the avoidable space index, it is determined whether there is a risk of collision with the vehicle in front. If there is no risk, automatic braking can be performed directly, generating a first-level suppression command. If there is a risk of collision with the vehicle in front, a safe path selection needs to be formulated, generating a second-level suppression command.

[0136] If the forward collision time is greater than the third preset time and the avoidable space index is greater than the preset threshold, a first-level suppression command is generated; if the forward collision time is less than the third preset time and / or the avoidable space index is less than the preset threshold, a second-level suppression command is generated.

[0137] The first-level suppression command includes maintaining the current power output and activating the braking system to decelerate smoothly. The second-level suppression command includes immediately cutting off the motor power output, activating the electronic stability system for steering assistance, and performing maximum braking.

[0138] It should be noted that in the Level 2 suppression command, the steering assist driving needs to determine the safe steering and obstacle avoidance direction based on radar data.

[0139] The acceleration suppression assisted driving control method provided in this application calculates the forward collision time and the avoidable space index based on current environmental information. If the forward collision time is greater than a third preset time and the avoidable space index is greater than a preset threshold, a first-level suppression command is generated. If the forward collision time is less than the third preset time and / or the avoidable space index is less than the preset threshold, a second-level suppression command is generated. This method, through precise environmental risk assessment, differentiated control strategies, and multi-system collaborative intervention, optimizes the driving experience while ensuring safety and reducing the accident rate.

[0140] Figure 6 A schematic diagram of the structure of the central processing unit provided in the embodiments of this application is shown below. Figure 6 As shown, the central processing unit 600 includes: a storage unit 601 and a processing unit 602;

[0141] Storage unit 601 stores computer-executed instructions;

[0142] The processing unit 602 executes the computer execution instructions stored in the storage unit 601, causing the processing unit 602 to execute the above-mentioned acceleration suppression assisted driving control method.

[0143] Optionally, the central processing unit also includes a communication component 603. The processing unit 602, the storage unit 601, and the communication component 603 are connected via a bus 604.

[0144] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processing unit can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0145] The storage unit may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0146] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0147] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0148] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0149] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0150] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0151] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0152] 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.

[0153] In addition, the functional units in the various embodiments of the present invention 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.

[0154] If a function 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 invention, or the part that contributes to the prior art, or a 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 (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0156] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for assisted driving control that suppresses acceleration, characterized in that, The method, applied to a central processing unit in an assisted driving control system, includes: When the mode to suppress unexpected acceleration is activated, the system performs scene matching based on the real-time captured current environmental information of the vehicle and a pre-built user driving habit database to obtain the target scene. The user driving habit database includes various road condition scenes and driving behavior data corresponding to each scene. Based on the target scenario, the current environmental information, the pre-acquired driver status information, vehicle status information, and the user driving habit database, determine whether to perform acceleration suppression; If acceleration suppression is determined, a suppression command is sent to the kinetic energy control unit so that the kinetic energy control unit performs acceleration suppression on the vehicle based on the suppression command; The step of determining whether to perform acceleration suppression based on the target scenario, the current environmental information, pre-acquired driver state information, vehicle state information, and the user driving habit database includes: Based on the target scenario, extract driving behavior data corresponding to the target scenario from the user driving habit database; Based on the driver status information, determine the driver status abnormality indicators; Based on the vehicle status information and the driving behavior data, the driving behavior deviation is calculated; Based on the current environmental information, assess the environmental hazard level; If the driver's abnormal state index, the driving behavior deviation, and the environmental hazard level all meet the preset unexpected acceleration conditions, then acceleration suppression is determined to be executed. If the suppression command includes a primary suppression command or a secondary suppression command, then before sending the suppression command to the kinetic energy control unit, the method further includes: Calculate the forward collision time and the avoidable space index based on the current environmental information; If the forward collision time is greater than a third preset time and the avoidable space index is greater than a preset threshold, then the first-level suppression command is generated. The first-level suppression command includes maintaining the current power output and activating the braking system to decelerate smoothly. If the forward collision time is less than the third preset time and / or the avoidable space index is less than the preset threshold, then the secondary suppression command is generated. The secondary suppression command includes immediately cutting off the motor power output, activating the electronic stability system for steering assistance, and performing maximum braking.

2. The method according to claim 1, characterized in that, The method further includes: Receive driver identification information sent by the in-vehicle monitoring device; The driver's identity information is compared with the preset vehicle owner information; If the driver's identity information is the same as the preset vehicle owner information, then the mode to suppress unexpected acceleration will be activated. If the driver's identity information is different from the preset vehicle owner information, the system will switch to the default driving mode and prompt the user.

3. The method according to claim 1, characterized in that, The unintended acceleration conditions include abnormal driving behavior conditions, hazardous environmental conditions, and abnormal driver state conditions. The abnormal driving behavior conditions include the driving behavior deviation exceeding a preset deviation threshold; The environmental hazard conditions are classified as high-level. The abnormal driver status condition includes any two of the following conditions: If the gaze is off the road for more than a first preset time, the heart rate exceeds the baseline range by a preset percentage, or the hands are off the steering wheel for more than a second preset time.

4. The method according to claim 1, characterized in that, The various road condition scenarios include any one or more of the following: urban road conditions, mountain road conditions, rural road conditions, daily working conditions, and highway working conditions.

5. The method according to claim 1, characterized in that, The method further includes: Record the data information after suppressing acceleration; Based on the data information, the user driving habit database is updated.

6. A driver assistance control system for suppressing acceleration, characterized in that, include: The system includes an intelligent driving control unit, a kinetic energy control unit, a central processing unit, and an in-vehicle monitor. The intelligent driving control unit is connected to the central processing unit via Ethernet, and the kinetic energy control unit and the in-vehicle monitor are respectively connected to the central processing unit via CAN bus. The intelligent driving control unit includes millimeter-wave radar, lidar, and a camera, which are used to perceive the vehicle's surrounding environment in real time, generate environmental information, and send it to the central processing unit. The kinetic energy control unit includes wheel speed sensors, acceleration sensors, and braking sensors, which are used to monitor the vehicle status in real time and generate vehicle status information to be sent to the central processing unit. The in-vehicle monitor includes an in-vehicle camera and a heartbeat detector, used to monitor the driver's status information in real time and send the driver's status information to the central processing unit; The central processing unit is used to execute the assisted driving control method for suppressing acceleration as described in any one of claims 1 to 5.

7. A central processing unit, characterized in that, include: Storage unit, processing unit; The storage unit stores computer-executed instructions; The processing unit executes the computer execution instructions stored in the storage unit, causing the processing unit to perform the acceleration suppression assisted driving control method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the assisted driving control method for suppressing acceleration as described in any one of claims 1-5.

Images