Vehicle control method and related device

Abstract

The invention provides a vehicle control method and a related device, and relates to the technical field of automotive electronics. In the invention, the monitoring model independent of the ADAS main model is arranged in the vehicle, so that the state information of the whole vehicle can be independently judged through the monitoring model, and the initial auxiliary driving control request which is obtained by the ADAS main model and is related to the driving safety of the vehicle is verified and corrected; specifically, the initial auxiliary driving control request is verified and corrected through the whole vehicle state information or the request value in the initial auxiliary driving control request, a target auxiliary driving control request is obtained, an error control instruction output by an ADAS main model is corrected in time, and the vehicle driving safety is improved.

Description

Technical Field

[0001] This application relates to the field of automotive electronics technology, and in particular to a vehicle control method and related devices. Background Technology

[0002] Currently, to enhance the driving experience, an increasing number of vehicles are equipped with Level 2 (L2) driver assistance controllers. These L2 controllers can be similar to ADAS (Advanced Driving Assistance System) controllers. ADAS is an active safety technology that utilizes onboard sensors such as millimeter-wave radar, cameras, and lidar, combined with navigation data, to achieve environmental perception. This system improves driving safety and comfort through functions such as static and dynamic object recognition and hazard warnings, and includes core modules such as adaptive cruise control, lane departure warning, and automatic parking.

[0003] In real-world scenarios, if the control commands output by ADAS are incorrect, it can cause the execution units downstream of ADAS to respond with incorrect commands, resulting in events that could affect vehicle safety.

[0004] Furthermore, existing ADAS technologies suffer from issues such as non-standard and incomplete functional safety mechanism development and design, and incomplete or impossible functional safety testing coverage. Taking the functional safety requirement of "preventing unexpected braking by AEB (Autonomous Emergency Braking) function, causing a speed drop exceeding 60 kph" as an example, there is a risk of systemic failure. Specifically, speed monitoring only occurs when the functional state machine transitions to a specific state; unexpected actions occurring in other functional states cannot be monitored. Moreover, the state machines of different auxiliary functions are interconnected. Eliminating this problem by modifying the ADAS state machine would be an extremely tedious testing task, unable to guarantee 100% testing, and would require modifying other conditions after changing / adding a condition, extending the development cycle and increasing project costs.

[0005] Furthermore, ADAS generally consists of three parts: perception, planning, and control. Functional safety requirements can be achieved by adjusting these three parts of ADAS. If the functional safety standard ISO 26262 is followed, inductive analysis (such as FMEA (Failure Mode and Effects Analysis)) or deductive analysis (such as FTA (Fault Tree Analysis)) can be used to analyze the failure effects of each component of the control system in order to identify each single point of failure that can directly lead to the violation of safety objectives. This allows for the design of corresponding diagnostic mechanisms or the updating of implementation strategies to avoid the existence of single points of failure.

[0006] Therefore, how to ensure that the control commands output by ADAS are accurate is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] In view of the above problems, this application provides a vehicle control method and related apparatus to realize the verification and correction of control commands output by ADAS using a monitoring model, thereby improving vehicle driving safety. The specific solution is as follows:

[0008] The first aspect of this application provides a vehicle control method applied to a vehicle, wherein the vehicle is equipped with an Advanced Driver Assistance System (ADAS) master model and a monitoring model; the ADAS master model and the monitoring model are independent of each other, and the output terminal of the ADAS master model is connected to the input terminal of the monitoring model; the vehicle control method includes:

[0009] Obtain vehicle status information;

[0010] Obtain the initial driver assistance control request related to vehicle driving safety output by the ADAS main model; the initial driver assistance control request is obtained by the ADAS main model processing the vehicle state information;

[0011] Using the vehicle status information or the request value in the initial assisted driving control request, the initial assisted driving control request is verified and corrected to obtain the target assisted driving control request.

[0012] Perform vehicle assisted driving control operations based on the target assisted driving control request.

[0013] In one possible implementation, the initial driver assistance control request is verified and corrected using the vehicle status information or the request value in the initial driver assistance control request to obtain the target driver assistance control request, including:

[0014] If the initial driver assistance control request includes an EBA braking request, the enable validity of the EBA braking request is adjusted using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information to obtain an EBA braking enable result. Alternatively, if the initial driver assistance control request does not include an EBA braking request, the EBA braking enable result is set to disabled.

[0015] If the initial driver assistance control request includes an AEB braking request, the AEB braking verification method corresponding to the AEB braking request and the vehicle status information are used to perform an enable validity adjustment operation on the AEB braking request to obtain an AEB braking enable result. Alternatively, if the initial driver assistance control request does not include an AEB braking request, the AEB braking enable result is set to disabled.

[0016] If the initial driver assistance control request includes an FCTB braking request, the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information are used to perform an enable validity adjustment operation on the FCTB braking request to obtain an FCTB braking enable result. Alternatively, if the initial driver assistance control request does not include an FCTB braking request, the FCTB braking enable result is set to disabled.

[0017] Based on the EBA braking enable result, the AEB braking enable result, and the FCTB braking enable result, a target braking request is obtained, and the target braking request is used as a target assisted driving control request.

[0018] In one possible implementation, the EBA braking request is adjusted using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information to obtain an EBA braking enabling result, including:

[0019] If the brake pedal depth in the vehicle status information is less than the preset pedal depth, the enable state of the EBA brake request is set to disabled, resulting in an EBA brake enable result.

[0020] In one possible implementation, the AEB braking request is adjusted using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information to obtain the AEB braking enabling result, including:

[0021] If the speed drop in the vehicle status information is greater than the first preset speed drop threshold, the yaw rate is invalid, the target system outputs an invalid AEB braking request, or a preset fault exists, the AEB braking request's enable status is set to disabled, thus obtaining an AEB braking enable result.

[0022] In one possible implementation, the FCTB braking request is adjusted using the FCTB braking verification method corresponding to the FCTB braking request and the vehicle state information to obtain the FCTB braking enable result, including:

[0023] If the speed drop in the vehicle status information is greater than the second preset speed drop threshold, the enable state of the FCTB braking request is set to disabled, and the FCTB braking enable result is obtained.

[0024] In one possible implementation, the target braking request is obtained based on the EBA braking enable result, the AEB braking enable result, and the FCTB braking enable result, including:

[0025] If the EBA braking enable result is enabled, the AEB braking request or the FCTB braking request in the initial driver assistance control request will be used as the target braking request.

[0026] If the EBA braking enable result is not enabled, the braking request corresponding to the enabled result in the AEB braking enable result and the FCTB braking enable result is taken as the target braking request.

[0027] In one possible implementation, the initial driver assistance control request is verified and corrected using the vehicle status information or the request value in the initial driver assistance control request to obtain the target driver assistance control request, including:

[0028] If the initial assisted driving control request includes an adaptive cruise control (ACC) function output request, and the ACC function output request is a vehicle start request, if the throttle opening in the vehicle status information is not greater than a preset opening, then the enable state of the vehicle start request is set to disabled, and the target assisted driving control request is obtained.

[0029] And / or, if the ACC function output request is a vehicle acceleration request, and the acceleration in the vehicle status information is greater than a preset acceleration threshold, then the enable state of the vehicle acceleration request is set to disabled, and a target assisted driving control request is obtained.

[0030] In one possible implementation, the initial driver assistance control request is verified and corrected using the vehicle status information or the request value in the initial driver assistance control request to obtain the target driver assistance control request, including:

[0031] If the initial driver assistance control request includes a lane keeping assist (LKA) function output request and the LKA function output request is a torque request, and the torque request value in the torque request is greater than a preset torque threshold, then the torque request value in the torque request is set to the preset torque threshold to obtain the target driver assistance control request.

[0032] A second aspect of this application provides a vehicle control device applied to a vehicle, wherein the vehicle is equipped with an ADAS master model and a monitoring model; the ADAS master model and the monitoring model are independent of each other, and the output terminal of the ADAS master model is connected to the input terminal of the monitoring model; the vehicle control device includes:

[0033] The first acquisition module is used to acquire vehicle status information;

[0034] The second acquisition module is used to acquire the initial assisted driving control request related to vehicle driving safety output by the ADAS main model; the initial assisted driving control request is obtained by the ADAS main model processing the vehicle state information;

[0035] The processing module is used to perform verification and correction operations on the initial assisted driving control request using the vehicle status information or the request value in the initial assisted driving control request, so as to obtain the target assisted driving control request.

[0036] The control module is used to perform vehicle assisted driving control operations based on the target assisted driving control request.

[0037] A third aspect of this application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0038] The memory is used to store computer programs;

[0039] The processor is used to execute the computer program so that the electronic device can implement the vehicle control method described above.

[0040] By employing the above technical solutions, this application provides a vehicle control method and related apparatus. In this application, a monitoring model independent of the ADAS main model is set in the vehicle, thereby enabling the monitoring model to independently judge the overall vehicle status information and to verify and correct the initial assisted driving control requests related to vehicle driving safety obtained by the ADAS main model. Specifically, the initial assisted driving control request is verified and corrected using the overall vehicle status information or the request value in the initial assisted driving control request to obtain the target assisted driving control request. This allows for timely correction of erroneous control commands output by the ADAS main model, thereby improving vehicle driving safety. Attached Figure Description

[0041] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0042] Figure 1 A schematic diagram of the model connection relationship provided in this application;

[0043] Figure 2 A flowchart of a vehicle control method provided in this application;

[0044] Figure 3 A schematic diagram of a communication architecture provided in this application;

[0045] Figure 4 A flowchart of a method for determining a request provided in this application;

[0046] Figure 5 A schematic diagram of another communication architecture provided in this application;

[0047] Figure 6 This is a schematic diagram of the structure of a vehicle control device provided in this application. Detailed Implementation

[0048] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0049] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0050] The terms "first," "second," etc., used 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 terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0051] Currently, driver assistance systems (ADAS) have a significant impact on overall vehicle safety, and the "brain" of an ADAS is the driver assistance controller. To improve the driving experience, an increasing number of vehicles are equipped with Level 2 (L2) driver assistance controllers. L2 ADAS controllers are similar to ADAS controllers. ADAS is an active safety technology that uses onboard sensors such as millimeter-wave radar, cameras, and lidar, combined with navigation data, to achieve environmental perception. This system enhances driving safety and comfort through functions such as static and dynamic object recognition and hazard warnings, and includes core modules such as adaptive cruise control, lane departure warning, and automatic parking. Most automakers' functional safety requirements for ADAS are primarily focused on "avoiding unintended actions by the assistance functions (ASIL B, ASIL: Automotive Safety Integrity Level)."

[0052] In real-world scenarios, if the control commands output by ADAS are incorrect, the execution units downstream of ADAS cannot predict or judge this, which will cause the execution units downstream of ADAS to respond with incorrect commands, resulting in events that affect vehicle safety.

[0053] Furthermore, existing ADAS technologies suffer from issues such as non-standard and incomplete functional safety mechanism development and design, and incomplete or impossible functional safety testing coverage. Taking the functional safety requirement of "preventing unexpected braking by the AEB function, causing a speed drop exceeding 60 kph" as an example, there is a risk of systemic failure. Specifically, speed monitoring only occurs when the functional state machine transitions to a specific state; unexpected actions occurring in other functional states cannot be monitored. Moreover, the state machines of different auxiliary functions are interconnected. Eliminating this problem by modifying the ADAS state machine would be an extremely tedious testing task, unable to guarantee 100% testing, and would require modifying other conditions after changing / adding a condition, extending the development cycle and increasing project costs.

[0054] Furthermore, ADAS generally consists of three parts: perception, planning, and control. Functional safety requirements can be met by adjusting these three parts. Following the functional safety standard ISO 26262, inductive analysis (such as FMEA) or deductive analysis (such as FTA) can be used to analyze the failure effects of each component of the control system, identifying any single point of failure that could directly lead to a breach of safety objectives. This allows for the design of corresponding diagnostic mechanisms or updates to implementation strategies to avoid single points of failure. For ADAS control systems, analyzing the failure effects of each unit separately from the control model is far less convenient and efficient than designing an external monitoring module.

[0055] Therefore, in this embodiment, a monitoring model can be added to monitor the main ADAS model. When setting up the monitoring model, its location needs to be considered to avoid cascading failures. For example, an ADAS driver assistance system can send braking requests to help the driver avoid collision risks. However, collision risks may come from the front, rear, and sides of the vehicle, so there are four corresponding auxiliary functions: AEB (Autonomous Emergency Braking), FCTB (Front Cross Traffic Brake), RCTB (Rear Cross Traffic Braking), and RCW (Rear Collision Warning). Due to the limitations of the vehicle architecture, these functions may share the same braking request signal. The main ADAS model can adjust the activation and deactivation of each function by setting up a functional state machine, but the monitoring model needs to monitor the braking request signal in real time. This can lead to a situation where the AEB suppression condition suppresses the FCTB braking request. If the state machine signals from the ADAS master model are introduced into the monitoring model, causing the monitoring model to only determine the interruption condition of the FCTB function when it is activated, a cascading failure is introduced—incorrect state indications from the state machine will cause the monitoring model to diagnose braking requests with incorrect conditions. The correct approach is as follows: the ADAS master model extracts the internal signals of each function and connects them to the monitoring model. The monitoring model first interrupts the braking request signals of the two functions according to their respective interruption conditions (AEB and FCTB) to achieve differentiated processing. Then, through logical arbitration (ORing the two processed request signals), the internal signal states are mapped to the vehicle signals.

[0056] Based on the above design principles, this application presents a two-level monitoring model scheme using the E-gas three-layer architecture. Specifically, it adds a monitoring model independent of the original ADAS main model around the existing ADAS main model. More specifically, this application provides a vehicle control method and related devices. By setting up a monitoring model independent of the ADAS main model within the vehicle, the monitoring model can independently judge the vehicle's state information and verify and correct the initial driver assistance control requests related to vehicle driving safety obtained from the ADAS main model. Specifically, it uses the vehicle state information or the request value in the initial driver assistance control request to perform verification and correction operations on the initial driver assistance control request, obtaining the target driver assistance control request. This allows for timely correction of erroneous control commands output by the ADAS main model, thereby improving vehicle driving safety.

[0057] Based on the above, one embodiment of this application provides a vehicle control method applied to a vehicle, such as... Figure 1 As shown, the intelligent driving control model of the vehicle includes an ADAS main model and a monitoring model. The ADAS main model and the monitoring model are independent of each other, and the output of the ADAS main model is connected to the input of the monitoring model.

[0058] In this embodiment, the ADAS master model still executes its original functional logic. The input to the ADAS master model is the vehicle signal, and the output includes both "safety-independent requests" and "safety-related requests." "Safety-independent requests" are executed directly, while "safety-related requests" are output to the monitoring model for diagnosis. Specifically, this involves arbitration, interruption, and restriction to ultimately obtain the final vehicle signal. In this embodiment, the monitoring model only diagnoses the results of the ADAS master model and does not interfere with its intermediate processes; that is, the monitoring model performs black-box diagnosis. In this embodiment, safety requirements are assigned to the secondary monitoring model, thus eliminating the need to modify the master model. However, this implementation method relies on ensuring the independence of the master model and the monitoring model, preventing cascading failures and common-cause failures. In other words, from a functional safety perspective, the master model still uses the original algorithm. When designing the monitoring model interface, it is essential to ensure that the monitoring model uses not only the output signal of the master model as a judgment condition.

[0059] In this embodiment, the ADAS algorithm is decoupled from the functional safety monitoring algorithm, which not only avoids the high-cost development of adjusting the ADAS master model, but also makes the functional safety monitoring measures clear and easy to understand, thereby enabling the functional safety test to be carried out completely.

[0060] exist Figure 1 Based on, refer to Figure 2 A vehicle control method includes:

[0061] S11. Obtain vehicle status information.

[0062] Among them, the vehicle status information can refer to Figure 1 For details regarding the vehicle signals, please refer to [link / reference]. Figure 3 .

[0063] Figure 3 The document outlines the monitoring logic for AEB, FCTB, and EBA (Electronic Brake Assist), enabling the differentiation and interruption of these three functions. The ADAS ECU employs a three-layer E-gas architecture, consisting of functional safety software (FuSa Software), functional safety hardware (FuSa Hardware), a monitoring model (used to monitor and judge safety-related requests), and the ADAS main model, from bottom to top. Figure 3 The leftmost part of the image contains external sensors, including a camera and a radar. Figure 3 In this architecture, Level 1 is the ADAS main model architecture, Level 2 is the monitoring model architecture, and Level 3 is the internal diagnostic mechanism of the MCU (Microcontroller Unit) chip. Level 3 is the underlying software configuration, enabling the chip to self-diagnose internal faults. When an internal fault occurs, it can directly trigger a controller reset. The EyeQ subsystem is an independent subsystem. The safety integrity requirement of the ADAS main model is QM (Quality Management) requirement, while the safety integrity requirement of the monitoring model and other modules is ASIL B requirement.

[0064] FuSa Software includes the following software or is capable of performing the following functions:

[0065] 1) Reg_monitor: refers to security software that monitors the chip's registers;

[0066] 2) Configuration: Refers to the security software configured for chip diagnostics;

[0067] 3) BIST: refers to the security software that configures the chip's power-on self-test;

[0068] 4) Memory Protect: Refers to memory protection;

[0069] 5) WDGM: Watchdog Management.

[0070] FuSa Hardware includes the following software or is capable of performing the following functions:

[0071] 1) Voltage Regulator: Refers to the voltage regulator;

[0072] 2) ECC: Refers to error checking and correction technology for data;

[0073] 3) SSH: SRAM hardware support (used for data verification in SRAM);

[0074] 4) SMU: Refers to the chip's security management module;

[0075] 5) Watchdog: refers to a hardware watchdog.

[0076] The EyeQ subsystem takes image data from the camera and diagnostic information from the chip as input. Its outputs include object information, the AEB flag (where TTC (Time To Collision) affects the AEB flag's value), and diagnostic and object information. Object information specifically refers to various target information around the vehicle emitted by the EyeQ subsystem, such as the nearest in-path vehicle, lane markings, and road edges. The AEB flag specifically refers to the AEB braking request output by the EyeQ subsystem. Diagnostic and object information specifically refers to the analysis results, based on safety objectives, determining whether internal circuit faults affect safety goals, such as illegal memory access or internal power rail over / under voltage faults.

[0077] After radar data, vehicle information from CAN Message Protection, and the aforementioned object information are output to the ADAS main model, they undergo perception fusion, object detection, and target identification operations. Following these operations, planning and control operations are performed, including Adaptive Cruise Control (ACC), Automatic Emergency Braking (AEB), and Emergency Lane Keeping (ELK). The planning and control operations output safety-related control requests (such as requests to control vehicle behavior) to the monitoring model, and safety-unrelated control requests (such as requests for entertainment functions) to CAN Message Protection.

[0078] exist Figure 3 In the E-gas three-layer architecture, the data flow is as follows: the camera captures image information, which is then processed by the EyeQ subsystem to obtain target information such as the vehicle ahead and lane markings. The original ADAS main model fuses radar targets and image targets, and combines vehicle information for target recognition and path planning control, finally sending control signals to the monitoring model. The monitoring model combines vehicle signals from the CAN bus and perception & diagnostic signals output from the EyeQ subsystem to monitor the ADAS main model's request signals in real time. The specific monitoring logic of the monitoring model depends on the project's safety requirements.

[0079] The AEB flag, Diagnostic & Object information, and Vehicle information output by the EyeQ subsystem are input into the monitoring model. These three data points constitute the vehicle status information in this embodiment. Based on the vehicle status information, the monitoring model verifies and corrects the "Control request (safety-related)" output by the ADAS main model to obtain the corrected "Control request (safety-related)". The corrected "Control request (safety-related)" is then output to CANMessage Protection for execution.

[0080] S12. Obtain the initial driver assistance control requests related to vehicle driving safety output by the ADAS master model.

[0081] The initial driver assistance control request is obtained by the ADAS main model processing the vehicle status information.

[0082] In this embodiment, the ADAS master model receives vehicle status information via CAN transceiver, radar, camera and other devices. After performing a series of operations such as target matching, trajectory set / fitting and planning control internally, it sends the initial assisted driving control request related to vehicle driving safety, namely "Control request (safety-related)". "Control request (safety-related)" can be such as torque, braking, acceleration request, etc., and will subsequently send the "Control request (safety-related)" to the monitoring model.

[0083] S13. Using the vehicle status information or the request value in the initial assisted driving control request, perform verification and correction operations on the initial assisted driving control request to obtain the target assisted driving control request.

[0084] In this embodiment, the monitoring model also receives vehicle status information and monitors the ADAS main model's output requests according to functional safety requirements. Specifically, during monitoring, it uses the vehicle status information or the request value in the initial driver assistance control request, based on the corresponding verification rules, to perform verification and correction operations on the initial driver assistance control request, thereby obtaining the target driver assistance control request, i.e., the aforementioned corrected "Control request (safety-related)".

[0085] In this embodiment, the functional safety requirements are entirely undertaken by the monitoring model. The functional logic of the monitoring model and the ADAS main model are completely independent. Therefore, the monitoring model can adopt requirements with a lower safety level. For example, the ADAS main model adopts QM (Quality Management) requirements, and the monitoring model adopts ASIL B requirements.

[0086] S14. Perform vehicle assisted driving control operations based on the target assisted driving control request.

[0087] In this embodiment, the modified "Control request (safety-related)" is output to CANMessage Protection for execution.

[0088] In this embodiment, a monitoring model independent of the ADAS main model is set in the vehicle. This allows the monitoring model to independently judge the vehicle status information and verify and correct the initial assisted driving control requests related to vehicle driving safety obtained by the ADAS main model. Specifically, the initial assisted driving control requests are verified and corrected using the vehicle status information or the request value in the initial assisted driving control requests to obtain the target assisted driving control requests. This allows for timely correction of erroneous control commands output by the ADAS main model, thereby improving vehicle driving safety.

[0089] Furthermore, based on the high cohesion of this embodiment, it can be flexibly combined with other monitoring mechanisms, such as the internal diagnostic mechanism of the MCU chip, the internal diagnostic mechanism of the independent subsystem (SEooC, Safety Element out of Context), and the diagnostic mechanism of external sensors, all of which can establish interfaces with the monitoring model to realize closed-loop processing of controller faults and ensure that the ASIL B level of ADAS controller functions is achieved.

[0090] Based on any of the above embodiments, such as Figure 4 As shown, using the vehicle status information or the request value in the initial assisted driving control request, the initial assisted driving control request is verified and corrected to obtain the target assisted driving control request, including:

[0091] S21. If the initial driver assistance control request includes an EBA braking request, the EBA braking verification method corresponding to the EBA braking request and the vehicle status information are used to perform an enable validity adjustment operation on the EBA braking request to obtain an EBA braking enable result. Alternatively, if the initial driver assistance control request does not include an EBA braking request, the EBA braking enable result is set to disabled.

[0092] This embodiment addresses the functional safety issues of implementing Level 2 autonomous driving algorithms by proposing a black-box monitoring scheme and clarifies the model independence design challenges encountered during its implementation. This embodiment emphasizes that the black-box monitoring scheme is not simply about adding redundant judgments to the outer perimeter of the ADAS main model, but rather about analyzing the logical coupling between different functions to avoid limiting vehicle performance. The following example illustrates how to design a monitoring model that ensures independence without affecting vehicle performance in the face of logical coupling within autonomous driving functions. Different vehicle models have different functional couplings; the following is merely one example.

[0093] In real-world scenarios, the three braking functions—AEB, EBA, and FCTB—in the ADAS master model exhibit certain logical coupling: ① AEB and FCTB share the same request signal, SftyDecelGroupSafeAsySftyEnaDecel; ② EBA uses a separate request signal, AsySftyEnaDecelByDBS. When EBA requests braking action, in addition to enabling the AsySftyEnaDecelByDBS signal, the SftyDecelGroupSafeAsySftyEnaDecel signal must also be enabled; otherwise, the actuator will not respond.

[0094] In terms of functional safety, risk analysis will be conducted on each function based on its performance specifications to obtain the safety requirements corresponding to AEB, EBA, and FCTB. For example:

[0095] The security requirements for AEB are:

[0096] 1. The maximum speed is reduced to 60 kph due to the AEB function;

[0097] 2. If the yaw rate information of the vehicle is invalid, an AEB braking request should not be issued;

[0098] 3. An AEB braking request is only allowed if the AEB flag output by the EyeQ subsystem is a valid request and there are no preset faults in Diagnostic & Object information.

[0099] The security requirements for FCTB are:

[0100] The maximum speed is reduced to 20 kph due to the FCTB function.

[0101] EBA's security requirements are:

[0102] When the brake pedal is depressed to less than 15%, an EBA braking request should not be issued.

[0103] Based on the aforementioned security requirements, adding redundant monitoring around the main ADAS model presents the following issues:

[0104] 1. When the monitoring model detects the transition edge of SftyDecelGroupSafeAsySftyEnaDecel, it starts recording the decrease in vehicle speed. When the decrease in vehicle speed reaches a threshold, SftyDecelGroupSafeAsySftyEnaDecel is interrupted. However, it is uncertain whether the interruption threshold should be 60kph or 20kph.

[0105] 2. If the monitoring model detects that the vehicle's Yawrate information is invalid, interrupting SftyDecelGroupSafeAsySftyEnaDecel will prevent both FCTB and EBA functions from requesting braking.

[0106] If the monitoring model is in the ADAS master model, it should make a distinction based on the state machine in the ADAS master model: if the state machine is in the AEB active state, the monitoring model monitors the speed drop of 60 kph and also monitors the Yawrate. Doing so would mistakenly use the state of the ADAS master model as the judgment condition of the monitoring model, which is using a QM model to enable the ASIL model, resulting in cascading failures.

[0107] Therefore, the ADAS master model should integrate the dedicated request signals AsySftyEnaDecelEByDBS for EBA function, AEB_En_internal for AEB function, and FCTB_En_internal for FCTB function into the security model, and use the three pre-configured sub-modules for logical verification.

[0108] like Figure 5 As shown, EBA braking requests are represented by AsySftyEnaDecelEByDBS. AEB braking requests are represented by AEB_En_internal, and FCTB braking requests are represented by FCTB_En_internal. When an EBA braking request exists, both AEB and FCTB braking requests will be automatically generated. When no EBA braking request exists, either an AEB or FCTB braking request can exist.

[0109] In the event of an EBA braking request, there is a corresponding EBA braking verification method, which is as follows: Figure 5 The Condition for EBA. The specific content of the EBA brake calibration method can be the calibration of brake pedal depth.

[0110] The main model will input AsySftyEnaDecelEByDBS into the "Limitation for EBA" submodule in the monitoring model. This submodule can monitor EBA requests based on safety-related functional conditions (usually brake pedal opening).

[0111] In one implementation, when adjusting the enable validity of the EBA braking request using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information, and obtaining the EBA braking enable result, it can be done as follows:

[0112] If the brake pedal depth (also known as brake pedal opening) in the vehicle status information is less than the preset pedal depth (e.g., 15%), the EBA braking request enable status is set to Disabled, resulting in an EBA braking enable result, specifically Disabled. For example... Figure 5 As shown, the EBA braking enable result is specifically AsySftyEnaDecelByDBS, and the value of AsySftyEnaDecelByDBS is specifically Disable.

[0113] If the brake pedal depth (also known as brake pedal opening) in the vehicle status information is not less than the preset pedal depth (e.g., 15%), the EBA braking request enable status is set to Enable, and the EBA braking enable result is obtained. Specifically, the EBA braking enable result is AsySftyEnaDecelByDBS, and the value of AsySftyEnaDecelByDBS is Enable.

[0114] If the initial driver assistance control request does not include an EBA braking request, the EBA braking enable result, i.e., AsySftyEnaDecelByDBS, is set to Disable.

[0115] In this embodiment, the "Limitation for EBA" submodule will select whether to interrupt AsySftyEnaDecelByDBS, i.e. whether to set AsySftyEnaDecelByDBS to Disable, based on whether the brake pedal is depressed by less than 15%.

[0116] S22. If the initial driver assistance control request includes an AEB braking request, the AEB braking validity is adjusted using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information to obtain an AEB braking enable result. Alternatively, if the initial driver assistance control request does not include an AEB braking request, the AEB braking enable result is set to disabled.

[0117] In this embodiment, when an AEB braking request exists, the AEB braking request has a corresponding AEB braking verification method, which is as follows: Figure 5 The Condition for EBA in the document refers to the specific content of the AEB braking verification method, which may include verifying vehicle speed reduction, Yawrate information, the AEB flag output by the EyeQ subsystem, and Diagnostic & Object information, etc.

[0118] The main model will input AEB_En_internal into the "Limitation for AEB" submodule in the monitoring model. This submodule can monitor AEB requests based on security-related functional conditions.

[0119] In one implementation, the AEB braking request is adjusted using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information to obtain the AEB braking enabling result, which may include:

[0120] If the speed drop in the vehicle status information is greater than the first preset speed drop threshold, the yaw rate is invalid, the target system outputs an invalid AEB braking request, or a preset fault exists, the AEB braking request enable status is set to disabled, and the AEB braking enable result is obtained.

[0121] In this embodiment, the first preset speed reduction threshold is set to 60 kph. That is, the "Limitation for AEB" submodule monitors a speed reduction of 60 kph based on the AEB_En_internal transition edge. Specifically, during AEB function monitoring, unexpected braking by the AEB function should be avoided, which could cause a speed reduction exceeding 60 kph. In this embodiment, the monitoring model monitors the vehicle speed reduction caused by AEB braking in real time. When AEB braking causes a speed reduction of 60 kph, the AEB braking request signal is directly set to Disable (i.e., the AEB braking request is interrupted).

[0122] The target system refers to the EyeQ subsystem mentioned above. The target system outputting an invalid AEB braking request specifically means that the AEB flag output by the EyeQ subsystem is invalid. The existence of a preset fault means that there is an illegal memory access or an internal power rail over / under voltage fault in the Diagnostic & Object information output by the EyeQ subsystem.

[0123] In the event of any of the following faults: speed drop greater than 60 kph, invalid yaw rate, invalid AEB braking request output by the EyeQ subsystem, illegal memory access, or over / under voltage on the internal power rail, the AEB braking request enable status is set to Disable, resulting in AEB braking enable. The EBA braking enable result is specifically Disable.

[0124] If the speed drop in the vehicle status information is not greater than the first preset speed drop threshold, the yaw rate is valid, the target system outputs a valid AEB braking request, and there is no preset fault, then the AEB braking request's enabling state is set to Enable, resulting in an AEB braking enable result. The EBA braking enable result is specifically Enable.

[0125] If the initial driver assistance control request does not include an AEB braking request, the AEB braking enable result is set to Disable.

[0126] S23. If the initial driver assistance control request includes an FCTB braking request, the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information are used to perform an enable validity adjustment operation on the FCTB braking request to obtain an FCTB braking enable result. Alternatively, if the initial driver assistance control request does not include an FCTB braking request, the FCTB braking enable result is set to disabled.

[0127] In this embodiment, when an FCTB braking request exists, the FCTB braking request has a corresponding FCTB braking verification method, which is: Figure 5 The Condition for FCTB. Specific details of the FCTB braking verification method include verifying vehicle speed reduction, etc.

[0128] The main model will input FCTB_En_internal into the "Limitation for FCTB" submodule in the monitoring model. This submodule can monitor AEB requests based on security-related functional conditions.

[0129] In one implementation, the FCTB braking request is adjusted using the FCTB braking verification method corresponding to the FCTB braking request and the vehicle state information to obtain the FCTB braking enabling result. This may include:

[0130] If the speed drop in the vehicle status information is greater than the second preset speed drop threshold, the enable state of the FCTB braking request is set to disabled, and the FCTB braking enable result is obtained.

[0131] The second preset speed drop threshold is 20 kph, meaning the "Limitation for FCTB" submodule monitors a speed drop of 20 kph based on the FCTB_En_internal transition edge. If the speed drop exceeds 20 kph, the FCTB braking request is set to Disabled, resulting in FCTB braking being enabled. Specifically, the FCTB braking enabling result is Disabled.

[0132] If the speed drop in the vehicle status information is no greater than 20 kph, the FCTB braking request enable status is set to Enable, resulting in the FCTB braking enable result. Specifically, the FCTB braking enable result is Enable.

[0133] If the initial driver assistance control request does not include an FCTB braking request, the FCTB braking enable result is set to Disable.

[0134] It should be noted that steps S21, S22 and S23 in this embodiment can be executed sequentially or in parallel, and there is no specific limitation.

[0135] S24. Based on the EBA braking enable result, AEB braking enable result and FCTB braking enable result, obtain the target braking request and use the target braking request as the target assisted driving control request.

[0136] In this embodiment, the EBA braking enable result is: Figure 5 In the formula AsySftyEnaDecelByDBS, it can be either Disabled or Enabled. The AEB braking enable result can also be either Disabled or Enabled, and the FCTB braking enable result can also be either Disabled or Enabled.

[0137] In one implementation, "obtaining the target braking request based on the EBA braking enable result, AEB braking enable result, and FCTB braking enable result" may include:

[0138] 1) If the EBA braking enable result is enabled, the AEB braking request or FCTB braking request in the initial driver assistance control request will be used as the target braking request.

[0139] In specific implementation, such as Figure 5As shown, in the monitoring model, the outputs of the "Limitation for AEB" submodule (i.e., the AEB braking enable result) and the "Limitation for FCTB" submodule (i.e., the FCTB braking enable result) pass through an OR gate. The OR gate will output Enable only if at least one of the AEB braking enable result and the FCTB braking enable result is Enabled. If both the AEB braking enable result and the FCTB braking enable result are Disabled, the OR gate will output Disabled.

[0140] The outputs of "Limitation for AEB" and "Limitation for FCTB" are mapped to the common signal SftyDecelGroupSafeAsySftyEnaDecel via an OR gate and a select gate.

[0141] Furthermore, in the ADAS master model, AEB_En_internal and FCTB_En_internal pass through an OR gate. The logic implemented by this OR gate is as follows: since both AEB and FCTB function requests are active high, the two signals are combined into one signal and sent to the public CAN bus via an OR gate. As long as either AEB_En_internal or FCTB_En_internal is a valid braking request, a braking request is considered to exist and is sent to the public CAN bus. In this embodiment, due to the presence of a monitoring model, the output signal of this OR gate is sent to the gating gate of the monitoring model.

[0142] It should be noted that since the actuator side binds the CAN signals output by the two OR gates, a gating gate needs to be set in the monitoring model to ensure that when the EBA braking enable result is Enable, the output signal of the OR gate connecting AEB_En_internal and FCTB_En_internal is also Enable.

[0143] In this embodiment, when the EBA braking enable result is Enable, the AEB braking request or FCTB braking request output by the OR gate connecting AEB_En_internal and FCTB_En_internal is used as the target braking request through a gating gate.

[0144] 2) If the EBA braking enable result is not enabled, the braking request corresponding to the result that is enabled in the AEB braking enable result and the FCTB braking enable result shall be used as the target braking request.

[0145] In this embodiment, when the EBA braking enable result is Disabled, the gating gate will select the braking request corresponding to the braking enable result that is Enabled from the output of the "Limitation for AEB" submodule (i.e., the AEB braking enable result) and the output of the "Limitation for FCTB" submodule (i.e., the FCTB braking enable result), and use it as the target braking request.

[0146] For example, if the AEB braking enable result is Enable and the FCTB braking enable result is Disable, then AEB_En_internal will be used as the target braking request.

[0147] In this embodiment, the gate in the monitoring model is used to map the ADAS main model's requests to SftyDecelGroupSafeAsySftyEnaDecel when AsySftyEnaDecelByDBS is in the Enable state, ensuring that it is also in the Enable state. This allows the monitoring model to monitor whether the ADAS main model's requests can pass through, thereby preventing the FCTB and EBA from being suppressed when the AEB function is not activated.

[0148] Based on any of the above embodiments, the initial driver assistance control request is verified and corrected using vehicle status information or the request value in the initial driver assistance control request to obtain the target driver assistance control request, including:

[0149] If the initial driver assistance control request includes an adaptive cruise control (ACC) function output request, and the ACC function output request is a vehicle start request, if the throttle opening in the vehicle status information is not greater than the preset opening, then the enable status of the vehicle start request is set to disabled, and the target driver assistance control request is obtained.

[0150] And / or, if the ACC function output request is a vehicle acceleration request, and the acceleration in the vehicle status information is greater than a preset acceleration threshold, then the enable status of the vehicle acceleration request is set to disabled, and the target assisted driving control request is obtained.

[0151] In practical implementation, when the ACC function output request in the ADAS main model is a vehicle start request, it is necessary to avoid the ACC function issuing an unexpected vehicle start request, which could lead to a collision with pedestrians ahead. Therefore, in this embodiment, the monitoring model judges the start conditions in real time, ensuring that a start request is issued only when the start conditions are met. In this embodiment, the real-time start condition is generally that the driver has a driving need, such as the throttle opening being greater than a preset opening. The preset opening setting varies slightly for different vehicle models, such as 8%. When the throttle opening in the vehicle status information is not greater than the preset opening, it indicates that the driver does not have a driving need at this time, and the ACC function has unexpectedly issued a vehicle start request. In this case, the enable state of the vehicle start request is set to Disabled, and the target assisted driving control request is obtained. At this time, the target assisted driving control request is that the ACC function output request is Disabled.

[0152] Similarly, when the ACC function output request is a vehicle acceleration request, if the acceleration in the vehicle status information is greater than the preset acceleration threshold, the enable status of the vehicle acceleration request is set to disabled, and the target assisted driving control request is obtained.

[0153] In practical implementation, due to the influence of the vehicle's safety architecture, there is a need to forcibly exit the ACC function when the acceleration value in the vehicle's status information caused by the ACC function exceeds 5g. The logic configured in the monitoring model is as follows: if the acceleration in the vehicle's status information caused by the ACC function exceeds a preset acceleration threshold, such as 5g, then the ACC acceleration request enable signal is set to Disable. Although the signal output by the ADAS main model is used as the judgment signal, it actually interrupts the ADAS main model's request signal. The underlying principle is that in the vehicle's safety architecture, the request enable signal is the interface between various controllers. Therefore, when the monitoring model identifies excessive acceleration in the vehicle's status information, such as exceeding the preset acceleration threshold, it sets the vehicle acceleration request enable state to Disable, thus obtaining the target assisted driving control request. That is, at this point, the ACC request enable signal should be suppressed to achieve the safety goal, rather than setting the request value signal to 0.

[0154] In this embodiment, the ACC function can be monitored to improve the reliability of its operation.

[0155] Based on any of the above embodiments, the initial driver assistance control request is verified and corrected using vehicle status information or the request value in the initial driver assistance control request to obtain the target driver assistance control request, including:

[0156] If the initial driver assistance control request includes an LKA (Lane Keeping Assist) function output request and the LKA function output request is a torque request, and the torque request value in the torque request is greater than the preset torque threshold, then the torque request value in the torque request is set to the preset torque threshold to obtain the target driver assistance control request.

[0157] In this embodiment, the safety requirement for the LKA function is to prevent the LKA function from issuing unexpected torque requests, which could lead to vehicle swaying and loss of control. Therefore, the monitoring model should monitor the torque request value issued by the LKA function in the ADAS main model. When the torque request value issued by the ADAS main model is greater than a preset torque threshold, such as 3 Nm, the monitoring model will modify the torque request value to 3 Nm to obtain the target assisted driving control request.

[0158] In this embodiment, the LKA function can be monitored to improve the reliability of LKA function operation.

[0159] In summary, since ADAS controllers primarily involve algorithm design and fall under the software domain, which only considers systemic failures, imposing ASIL requirements on existing model algorithms would lead to extensive verification work. Alternatively, attempting to decompose complex algorithm models and define safety levels based on inter-module relationships would introduce even more work. Furthermore, due to the reusability of modules, ASIL requirements for multiple modules are often not eliminated. The solution proposed in this embodiment is a black-box monitoring solution, eliminating the need for analysis of the original complex model and enabling efficient and clear allocation of safety requirements during the safety analysis phase. Simultaneously, black-box monitoring should maintain its independence from the main ADAS model to avoid cascading failures.

[0160] Specifically, a monitoring model independent of the main ADAS model is set up in the vehicle intelligent driving control model. This allows for independent judgment of the vehicle's state information (ensuring no cascading failures in the design) and evaluation of initial driver assistance control requests related to vehicle driving safety. Specifically, it verifies and corrects these requests using vehicle state information or request values ​​from the initial driver assistance control requests. The monitoring model promptly corrects erroneous control commands output by the main ADAS model, thereby improving vehicle driving safety.

[0161] Please see Figure 6 , Figure 6 This is a schematic diagram of a vehicle control device provided in an embodiment of this application. It is applied to a vehicle, which includes an ADAS master model and a monitoring model; the ADAS master model and the monitoring model are independent of each other, and the output of the ADAS master model is connected to the input of the monitoring model; the vehicle control device includes:

[0162] The first acquisition module 101 is used to acquire vehicle status information;

[0163] The second acquisition module 102 is used to acquire the initial assisted driving control request related to vehicle driving safety output by the ADAS main model; the initial assisted driving control request is obtained by the ADAS main model processing the vehicle state information;

[0164] Processing module 103 is used to perform verification and correction operations on the initial assisted driving control request using the vehicle status information or the request value in the initial assisted driving control request, so as to obtain the target assisted driving control request.

[0165] The control module 104 is used to perform vehicle assisted driving control operations based on the target assisted driving control request.

[0166] In one possible implementation, the processing module 103 includes:

[0167] The first setting submodule is used to adjust the enable validity of the EBA braking request by using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information when the initial assisted driving control request includes the EBA braking request, so as to obtain the EBA braking enable result; or, when the initial assisted driving control request does not include the EBA braking request, the EBA braking enable result is set to disabled.

[0168] The second setting submodule is used to adjust the AEB braking validity of the initial assisted driving control request by using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information to obtain the AEB braking enabling result, or to set the AEB braking enabling result to be disabled when the initial assisted driving control request does not include the AEB braking request.

[0169] The third setting submodule is used to adjust the enable validity of the FCTB braking request by using the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information when the initial assisted driving control request includes the FCTB braking request, so as to obtain the FCTB braking enable result; or, when the initial assisted driving control request does not include the FCTB braking request, the FCTB braking enable result is set to disabled.

[0170] The request determination submodule is used to obtain the target braking request based on the EBA braking enable result, AEB braking enable result, and FCTB braking enable result, and to use the target braking request as the target assisted driving control request.

[0171] In one possible implementation, the first setting submodule is used to perform an enable validity adjustment operation on the EBA braking request using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information. Specifically, when obtaining the EBA braking enable result, it is used for:

[0172] If the brake pedal depth in the vehicle status information is less than the preset pedal depth, the EBA brake request enable status is set to disabled, resulting in an EBA brake enable result.

[0173] In one possible implementation, when the second setting submodule performs an enable validity adjustment operation on the AEB braking request using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information, and obtains the AEB braking enable result, it is specifically used for:

[0174] If the speed drop in the vehicle status information is greater than the first preset speed drop threshold, the yaw rate is invalid, the target system outputs an invalid AEB braking request, or a preset fault exists, the AEB braking request enable status is set to disabled, and the AEB braking enable result is obtained.

[0175] In one possible implementation, when the third setting submodule uses the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information to perform an enable validity adjustment operation on the FCTB braking request and obtain the FCTB braking enable result, it is specifically used for:

[0176] If the speed drop in the vehicle status information is greater than the second preset speed drop threshold, the enable state of the FCTB braking request is set to disabled, and the FCTB braking enable result is obtained.

[0177] In one possible implementation, the request determines which submodule is specifically used for:

[0178] If the EBA braking enable result is enabled, the AEB braking request or FCTB braking request in the initial driver assistance control request will be used as the target braking request.

[0179] If the EBA braking enable result is not enabled, the braking request corresponding to the enabled result in the AEB braking enable result and the FCTB braking enable result is taken as the target braking request.

[0180] In one possible implementation, the processing module 103 includes:

[0181] The fourth setting submodule is used to set the enable status of the vehicle start request to disabled if the initial assisted driving control request includes an adaptive cruise control (ACC) function output request, and the ACC function output request is a vehicle start request. If the throttle opening in the vehicle status information is not greater than the preset opening, then the target assisted driving control request is obtained.

[0182] The fifth setting submodule is used to set the enable status of the vehicle acceleration request to disabled when the ACC function output request is a vehicle acceleration request and the acceleration in the vehicle status information is greater than a preset acceleration threshold, so as to obtain the target assisted driving control request.

[0183] In one possible implementation, the processing module 103 includes:

[0184] The sixth setting submodule is used to set the torque request value in the initial assisted driving control request to the preset torque threshold if the torque request value in the torque request is greater than the preset torque threshold, and thus obtain the target assisted driving control request, when the initial assisted driving control request includes the lane keeping assist (LKA) function output request and the LKA function output request is a torque request.

[0185] In this embodiment, a monitoring model independent of the ADAS main model is set in the vehicle. This allows the monitoring model to independently judge the vehicle status information and verify and correct the initial assisted driving control requests related to vehicle driving safety obtained by the ADAS main model. Specifically, the initial assisted driving control requests are verified and corrected using the vehicle status information or the request value in the initial assisted driving control requests to obtain the target assisted driving control requests. This allows for timely correction of erroneous control commands output by the ADAS main model, thereby improving vehicle driving safety.

[0186] It should be noted that the working process of each module and sub-module in this embodiment is described in the corresponding descriptions in the above embodiments, and will not be repeated here.

[0187] This application also provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0188] Memory is used to store computer programs;

[0189] The processor is used to execute computer programs so that the electronic equipment can implement the vehicle control method described above.

[0190] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the vehicle control methods provided in this application.

[0191] This application also provides a computer storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the vehicle control methods provided in this application.

[0192] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the accompanying drawings of the device embodiments provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0193] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0194] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0195] The 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 processes or functions described in the embodiments of this application are 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 transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A vehicle control method, characterized in that, The system is applied to vehicles, which are equipped with an Advanced Driver Assistance System (ADAS) master model and a monitoring model; the ADAS master model and the monitoring model are independent of each other, and the output of the ADAS master model is connected to the input of the monitoring model. The vehicle control method includes: Obtain vehicle status information; Obtain the initial driver assistance control request related to vehicle driving safety output by the ADAS main model; the initial driver assistance control request is obtained by the ADAS main model processing the vehicle state information; Using the vehicle status information or the request value in the initial assisted driving control request, the initial assisted driving control request is verified and corrected to obtain the target assisted driving control request. Perform vehicle assisted driving control operations based on the target assisted driving control request.

2. The vehicle control method according to claim 1, characterized in that, Using the vehicle status information or the request value in the initial driver assistance control request, the initial driver assistance control request is verified and corrected to obtain the target driver assistance control request, including: If the initial driver assistance control request includes an EBA braking request, the enable validity of the EBA braking request is adjusted using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information to obtain an EBA braking enable result. Alternatively, if the initial driver assistance control request does not include an EBA braking request, the EBA braking enable result is set to disabled. If the initial driver assistance control request includes an AEB braking request, the AEB braking verification method corresponding to the AEB braking request and the vehicle status information are used to perform an enable validity adjustment operation on the AEB braking request to obtain an AEB braking enable result. Alternatively, if the initial driver assistance control request does not include an AEB braking request, the AEB braking enable result is set to disabled. If the initial driver assistance control request includes an FCTB braking request, the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information are used to perform an enable validity adjustment operation on the FCTB braking request to obtain an FCTB braking enable result. Alternatively, if the initial driver assistance control request does not include an FCTB braking request, the FCTB braking enable result is set to disabled. Based on the EBA braking enable result, the AEB braking enable result, and the FCTB braking enable result, a target braking request is obtained, and the target braking request is used as a target assisted driving control request.

3. The vehicle control method according to claim 2, characterized in that, Using the EBA braking verification method corresponding to the EBA braking request and the vehicle status information, an enable validity adjustment operation is performed on the EBA braking request to obtain the EBA braking enable result, including: If the brake pedal depth in the vehicle status information is less than the preset pedal depth, the enable state of the EBA brake request is set to disabled, resulting in an EBA brake enable result.

4. The vehicle control method according to claim 2, characterized in that, Using the AEB braking verification method corresponding to the AEB braking request and the vehicle status information, an AEB braking validity adjustment operation is performed on the AEB braking request to obtain the AEB braking enabling result, including: If the speed drop in the vehicle status information is greater than the first preset speed drop threshold, the yaw rate is invalid, the target system outputs an invalid AEB braking request, or a preset fault exists, the AEB braking request's enable status is set to disabled, thus obtaining an AEB braking enable result.

5. The vehicle control method according to claim 2, characterized in that, Using the FCTB braking verification method corresponding to the FCTB braking request and the vehicle status information, an enable validity adjustment operation is performed on the FCTB braking request to obtain the FCTB braking enable result, including: If the speed drop in the vehicle status information is greater than the second preset speed drop threshold, the enable state of the FCTB braking request is set to disabled, and the FCTB braking enable result is obtained.

6. The vehicle control method according to claim 2, characterized in that, Based on the EBA braking enable result, the AEB braking enable result, and the FCTB braking enable result, a target braking request is obtained, including: If the EBA braking enable result is enabled, the AEB braking request or the FCTB braking request in the initial driver assistance control request will be used as the target braking request. If the EBA braking enable result is not enabled, the braking request corresponding to the enabled result in the AEB braking enable result and the FCTB braking enable result is taken as the target braking request.

7. The vehicle control method according to claim 1, characterized in that, Using the vehicle status information or the request value in the initial driver assistance control request, the initial driver assistance control request is verified and corrected to obtain the target driver assistance control request, including: If the initial assisted driving control request includes an adaptive cruise control (ACC) function output request, and the ACC function output request is a vehicle start request, if the throttle opening in the vehicle status information is not greater than a preset opening, then the enable state of the vehicle start request is set to disabled, and the target assisted driving control request is obtained. And / or, if the ACC function output request is a vehicle acceleration request, and the acceleration in the vehicle status information is greater than a preset acceleration threshold, then the enable state of the vehicle acceleration request is set to disabled, and a target assisted driving control request is obtained.

8. The vehicle control method according to claim 1, characterized in that, Using the vehicle status information or the request value in the initial driver assistance control request, the initial driver assistance control request is verified and corrected to obtain the target driver assistance control request, including: If the initial driver assistance control request includes a lane keeping assist (LKA) function output request and the LKA function output request is a torque request, and the torque request value in the torque request is greater than a preset torque threshold, then the torque request value in the torque request is set to the preset torque threshold to obtain the target driver assistance control request.

9. A vehicle control device, characterized in that, Applied to vehicles, the vehicles are equipped with an ADAS master model and a monitoring model; the ADAS master model and the monitoring model are independent of each other, and the output of the ADAS master model is connected to the input of the monitoring model; The vehicle control device includes: The first acquisition module is used to acquire vehicle status information; The second acquisition module is used to acquire the initial assisted driving control request related to vehicle driving safety output by the ADAS main model; the initial assisted driving control request is obtained by the ADAS main model processing the vehicle state information; The processing module is used to perform verification and correction operations on the initial assisted driving control request using the vehicle status information or the request value in the initial assisted driving control request, so as to obtain the target assisted driving control request. The control module is used to perform vehicle assisted driving control operations based on the target assisted driving control request.

10. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the vehicle control method as described in any one of claims 1 to 8.

Images