Vehicle control method, analysis redundancy controller, steer-by-wire system and medium

Abstract

The invention provides a vehicle control method, an analysis redundancy controller, a steer-by-wire system and a medium. The method comprises the steps that first driving data and first steering data of a vehicle are obtained; determining a predicted risk score of the vehicle according to the first driving data and the first steering data; wherein the predicted risk score represents the risk that the vehicle is about to have an accident; and controlling the vehicle according to the predicted risk score.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of vehicle technology, and more specifically, to a vehicle control method, a parsing redundant controller, a steer-by-wire system, and a computer-readable storage medium. Background Art

[0002] In the field of automotive technology, the steer-by-wire system is an important innovation in the steer-by-wire technology and is considered to be able to revolutionize the automotive industry. The steer-by-wire system consists of a controller, a steering motor, a sensor, etc. The driver's intention is interpreted by the sensor, and then an electronic command is sent to the steering actuator by wire. Since electronic devices, such as sensors and microelectronic components, have no mechanical links, the steer-by-wire system is more complex than the mechanical steering system. With the increase in complexity, the susceptibility to failure also increases, especially electronic failures. Mechanical components can be made basically fault-free through proper material selection, strict quality control and over-design. However, the steer-by-wire system is sensitive to various faults caused by electronic devices. Failures in actuators, sensors, controllers, communication buses or any combination may cause the vehicle system to enter a dangerous state, which in turn threatens the safety of the driver, passengers and even people in the surrounding environment. Therefore, it is particularly important to ensure the fault tolerance and safety of the steer-by-wire system. Summary of the invention

[0003] One purpose of the embodiments of the present disclosure is to provide a new technical solution to ensure high safety of a steer-by-wire system.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a vehicle control method, comprising:

[0005] Acquiring first driving data and first turning data of the vehicle;

[0006] Determining a predicted risk score of the vehicle according to the first driving data and the first turning data; wherein the predicted risk score indicates a risk that the vehicle will have an accident;

[0007] The vehicle is controlled based on the predicted risk score.

[0008] Optionally, determining the predicted risk score of the vehicle according to the first driving data and the first turning data includes:

[0009] Acquire second driving data and second steering data of the vehicle;

[0010] The predicted risk score is obtained according to the first driving data, the first turning data, the second driving data and the second turning data.

[0011] Optionally, the driving data includes speed data, attitude angle data and road adhesion coefficient; the steering data includes steering motor power data, steering angle data, and driving status, and the driving status is driving time or mileage.

[0012] Optionally, obtaining the predicted risk score according to the first driving data, the first turning data, the second driving data, and the second turning data includes:

[0013] Based on the set first neural network of the analytical redundancy model and the second driving data, the first driving data is processed to obtain a first kernel density estimation tensor of the first driving data;

[0014] Based on the second neural network of the analytical redundancy model and the second steering data, the first steering data and the first kernel density estimation tensor are processed to obtain the predicted risk score.

[0015] Optionally, the second neural network based on the analytical redundancy model and the second steering data processes the first steering data and the first kernel density estimation tensor to obtain the predicted risk score, including:

[0016] Determining a second kernel density estimation tensor of the first steering data according to the first kernel density estimation tensor;

[0017] Obtaining a first conversion function representing a conversion relationship between the first turning data and the first driving data according to the second turning data, the first turning data and the second kernel density estimation tensor;

[0018] The predicted risk score is obtained according to the first conversion function.

[0019] Optionally, the method further includes:

[0020] In the event of a failure in the steer-by-wire system of the vehicle, the analytical redundant model is updated based on the first driving data.

[0021] Optionally, the method further includes:

[0022] The first driving data is stored as the second driving data; and the first steering data is stored as the second steering data.

[0023] Optionally, controlling the vehicle according to the predicted risk score includes:

[0024] In a case where the predicted risk score is greater than or equal to a score threshold, detecting a target component having a fault in a steer-by-wire system of the vehicle;

[0025] Fault reconfiguration control is performed on the vehicle according to the target device.

[0026] Optionally, the target device includes a steering motor,

[0027] The performing fault reconfiguration control on the vehicle according to the target device includes:

[0028] The differential speeds of the wheel motors of the vehicle are configured to steer the vehicle.

[0029] Optionally, the target device includes a steering motor controller;

[0030] The performing fault reconfiguration control on the vehicle according to the target device includes:

[0031] The analytical redundant controller controlling the vehicle replaces the steering motor controller to drive and control the steering motor of the vehicle.

[0032] According to a second aspect of the present disclosure, a parsing redundant controller is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the method described in the first aspect of the present disclosure under the control of the computer program.

[0033] According to a third aspect of the present disclosure, there is provided a steer-by-wire system, comprising the analytical redundant controller as described in the second aspect of the present disclosure.

[0034] Optionally, the steer-by-wire system further includes an on-board storage unit, and the on-board storage unit is used to store the second driving data and the second steering data of the vehicle;

[0035] The analytical redundant controller is further configured to determine a predicted risk score for the vehicle based on the second driving data and the second steering data.

[0036] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect of the present disclosure is implemented.

[0037] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect of the present disclosure is implemented.

[0038] Through the embodiments of the present disclosure, the predicted risk score of the vehicle is determined based on the first driving data and the first steering data of the vehicle, and the vehicle is controlled based on the predicted risk score, thereby ensuring the high reliability and high safety of the wire-controlled steering system, reducing the redundant hardware of the wire-controlled steering system, and reducing the hardware cost of the vehicle.

[0039] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0041] Figure 1 is a block diagram of a steer-by-wire system according to one embodiment of the present disclosure;

[0042] Figure 2 is a flow chart of a vehicle control method according to an embodiment of the present disclosure;

[0043] Figure 3 is a schematic diagram of the risk field evolution process according to an embodiment of the present disclosure;

[0044] Figure 4 is a block diagram of a parsing redundant controller according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0046] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0047] Technologies, methods and equipment known to persons of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered part of the specification.

[0048] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0049] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0050] <Hardware Configuration>

[0051] Figure 1 is a block diagram of a steer-by-wire system according to one embodiment of the present disclosure.

[0052] like Figure 1 As shown, the wire-controlled steer system 1000 may include a steering motor 1100, a feedback motor 1200, a steering motor controller 1300, a feedback motor controller 1400, a resolution redundant controller 1500, an on-board storage unit 1600, a steering wheel angle sensor 1710, a torque sensor 1720, a motor sensor 1730, and a steering state sensor 1740.

[0053] In this embodiment, the steering motor controller 1300 and the feedback motor controller 1400 can be automotive-grade microprocessors with a safety level of ASIL-D. The steering motor 1100 can use a six-phase motor. The feedback motor 1200 can use a three-phase motor. The analysis redundant controller 1500 can use a processor that meets both the computing load and the safety level (ASIL-D) requirements. The on-board storage unit 1600 must meet the performance requirements such as storage capacity and speed as well as the reliability requirements. The on-board storage unit 1600 can communicate with the cloud to achieve real-time data transmission with the cloud. The communication connection between the analysis redundant controller 1500 and the on-board storage unit 1600 can achieve real-time data transmission of large capacity.

[0054] like Figure 1 As shown, the steer-by-wire system 1000 is also interconnected with other systems of the vehicle through a CAN bus. The other systems include other modules in the chassis domain, such as a braking module and a vibration reduction module, and other modules in the body domain, such as a cockpit module and an environmental perception module.

[0055] <Vehicle Control Method Embodiment>

[0056] The present disclosure provides a vehicle control method, which can be implemented by a vehicle, and specifically by a parsing redundant controller in a steer-by-wire system of the vehicle.

[0057] Figure 2 The figure is a flow chart of a vehicle control method according to an embodiment of the present disclosure.

[0058] like Figure 2 As shown, the vehicle control method may include the following steps S2100 to S2300:

[0059] Step S2100, obtaining first driving data and first turning data of the vehicle.

[0060] In this embodiment, the first driving data is the latest driving data obtained, and the first turning data is the latest turning data obtained.

[0061] The driving data includes speed data, attitude angle data and road adhesion coefficient, wherein the speed data may include longitudinal speed and lateral speed.

[0062] The steering data includes steering motor power data, steering angle data, and driving status, where the driving status is driving time or mileage.

[0063] In this embodiment, the first driving data and the first turning data may be collected by sensors provided in the vehicle.

[0064] Specifically, the speed data can be collected by a speed sensor, or obtained based on the acceleration data collected by an acceleration sensor; the attitude angle data can be collected by an inertial sensor; the road adhesion coefficient can be obtained based on the angular acceleration data collected by the angular acceleration sensor; the steering motor power data can be collected by a motor sensor; the steering angle data can be collected by a steering state sensor; when the driving state is the driving time, the driving state can be obtained by a timer; when the driving state is the mileage, the driving state can be obtained by an odometer.

[0065] Furthermore, the driving time may be the total driving time of the vehicle or the driving time of the vehicle during the current startup. The driving mileage may be the total driving mileage of the vehicle or the driving mileage of the vehicle during the current startup.

[0066] Step S2200: determining a predicted risk score of the vehicle based on the first driving data and the first turning data.

[0067] The predicted risk score indicates the risk of the vehicle having an accident. The larger the predicted risk score, the worse the safety of the steer-by-wire system and the higher the risk of an accident.

[0068] In one embodiment of the present disclosure, the first driving data and the first steering data may be input into a preset analytical redundancy model to obtain a predicted risk score of the vehicle.

[0069] In another embodiment of the present disclosure, determining a predicted risk score of a vehicle based on first driving data and first turning data may include: acquiring second driving data and second turning data of the vehicle, and obtaining a predicted risk score based on the first driving data, the first turning data, the second driving data, and the second turning data.

[0070] In this embodiment, the second driving data is driving data pre-stored in the vehicle-mounted storage unit, and the first turning data is turning data pre-stored in the vehicle-mounted storage unit.

[0071] The data stored in the vehicle storage unit may include experimental simulation data, operation history data and accident statistics data. The experimental simulation data may be data generated by simulation of an experiment, the operation history data may be data acquired during the historical driving process of the vehicle, and the accident statistics data may be data acquired by the vehicle when an accident occurs.

[0072] Furthermore, the operation history data may be data acquired during the historical driving process of the vehicle executing the method of this embodiment, or may be data acquired during the historical driving process of other vehicles and transmitted to the vehicle storage unit via the cloud.

[0073] In this embodiment, a predicted risk score is obtained based on the first driving data, the first turning data, the second driving data and the second turning data, so that the risk of an accident involving the vehicle represented by the obtained predicted risk score can be more accurate, thereby achieving precise control of the vehicle.

[0074] In one embodiment, obtaining the predicted risk score according to the first driving data, the first turning data, the second driving data, and the second turning data may include the following steps S2210 to S2220:

[0075] Step S2210: Based on the first neural network of the set analytical redundancy model and the second driving data, the first driving data is processed to obtain a first kernel density estimation tensor of the first driving data.

[0076] In this embodiment, the risk field kernel function K can be defined based on the concept of risk field. 1 , and combined with the Gaussian kernel function K 2 , construct a multidimensional kernel density estimation tensor Define a multidimensional kernel density estimation tensor based on this The risk analysis model is the first neural network.

[0077] The first neural network adopts the principle of safety cusp mutation and takes into account the emergent characteristics of the steer-by-wire system. The analytical redundancy model can describe the change process of the safety state of the steer-by-wire system and can perform dynamic quantitative evaluation of the safety of the steer-by-wire system.

[0078] In this embodiment, the first kernel density estimation tensor can be determined by the following formula:

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090] in, is the first kernel density estimation tensor; K 1 is the risk field kernel function; K 2 is the Gaussian kernel function; n is the total number of the second driving data; h 1 and h 2 is the bandwidth, i.e., the variance of the kernel function; x represents the speed data in the first driving data; y represents the attitude angle data in the first driving data; z represents the road adhesion coefficient in the first driving data; i represents the speed data in the second driving data of the ith item; y i represents the attitude angle data in the i-th second driving data; z i represents the road adhesion coefficient in the second driving data of the ith item; y p represents the attitude angle data in the second driving data when the vehicle has an accident; p represents the road adhesion coefficient in the second driving data when the vehicle has an accident; η, ω, v represent the network coefficients of the first neural network.

[0091] Step S2220, based on the second neural network and the second steering data of the analytical redundant model, the first steering data and the first kernel density estimation tensor are processed to obtain a predicted risk score.

[0092] In one example, the first steering data, the second steering data, and the first kernel density estimation tensor may be input into a second neural network to obtain a predicted risk score.

[0093] In this embodiment, the second neural network may be As a rule, the second steering data relevant to the safety of the steer-by-wire system is learned.

[0094] In one embodiment of the present disclosure, based on the second neural network and the second steering data of the analytical redundant model, the first steering data and the first kernel density estimation tensor are processed to obtain a predicted risk score, which may include steps S2221 to S2223 as shown below:

[0095] Step S2221, determining a second kernel density estimation tensor of the first steering data based on the first kernel density estimation tensor.

[0096] In this embodiment, the first kernel density function tensor may be Convert from coordinate system xyz to coordinate system αβγ to obtain multidimensional kernel density estimation Wherein, α represents the steering motor power data in the first steering data, β represents the steering angle data in the first steering data, and γ represents the driving state in the first steering data.

[0097] In one example, the first kernel density function tensor can be obtained based on the second conversion function obtained in advance. Processing is performed to obtain the second kernel density estimation tensor

[0098] Step S2222: Obtain a first conversion function representing a conversion relationship between the first turning data and the first driving data according to the second turning data, the first turning data and the second kernel density estimation tensor.

[0099] The first conversion function representing the conversion relationship between the first steering data and the first driving data can be expressed as:

[0100] x=Γ 1 (α)

[0101] y=Γ 2 (β)

[0102] z=Ξ(γ)

[0103] Wherein, α represents the steering motor power data in the first steering data; β represents the steering angle data in the first steering data; γ represents the driving state in the first steering data; Γ 1 , Γ 2 is a continuously differentiable function; Ξ(γ) is the potential function of the folding mutation: Ξ(γ) = γ 3 +τγ. Wherein, τ is the unknown coefficient in the first transfer function.

[0104] The second kernel density estimation tensor can be expressed as:

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116] in, is the second kernel density estimation tensor; K 1 is the risk field kernel function; K 2 is the Gaussian kernel function; n is the total number of the second driving data; h 1 and h 2 is the bandwidth, i.e., the variance of the kernel function; α represents the steering motor power data in the first steering data; β represents the steering angle data in the first steering data; γ represents the driving state in the first steering data; α i represents the steering motor power data in the i-th second steering data; β i represents the steering angle data in the i-th second steering data; γ i represents the driving state in the second turning data of the i-th item; y p represents the attitude angle data in the second driving data when the vehicle has an accident; p represents the road adhesion coefficient in the second driving data when the vehicle has an accident; η, ω, v represent the network coefficients of the first neural network.

[0117] This embodiment utilizes By learning the second turning data, it is possible to observe the change process of the risk field in the driving data.

[0118] Step S2223, obtaining a predicted risk score according to the first conversion function.

[0119] According to the theoretical derivation of the risk field, in the coordinate system αβγ, the radius φ of the risk field (inner field) Θ is a dimension to measure the risk of the wire-controlled steering system. The larger φ is, the greater the system risk is.

[0120] Among them, the radius φ of the risk field (inner field) Θ can be determined by the following formula:

[0121]

[0122] Among them, Γ 1 A first conversion function representing the conversion relationship between the speed data in the first driving data and the steering motor power data in the first steering data, Γ 2 A first conversion function representing a conversion relationship between the posture angle data in the first driving data and the steering angle data in the first steering data.

[0123] The symmetry of the cusp mutation makes the transition of the risk field symmetrical. Therefore, the risk field (internal field) after the transition is Θ J The radius φ J =φ. The degree of folding of the cusp surface (in the coordinate system xyz) corresponding to the risk field is another dimension to measure system risk. The greater the degree of folding, the worse the system security and the higher the system risk. The degree of folding can be expressed as the distance ζ of the risk field Θ transition in the coordinate system αβγ. J to measure equivalently.

[0124] In this embodiment, the predicted risk score can be determined by the following formula:

[0125] Ω J =ζ J φ J

[0126] Among them, Ω J represents the predicted risk score, ζ J represents the distance of the risk field Θ transition in the coordinate system αβγ, φ J Represents the risk field (inner field) after the transition Θ J The radius of .

[0127] In an embodiment in which the driving status is the driving duration, when the predicted risk score is obtained based on the first driving data, the first turning data, the second driving data and the second turning data, the predicted time of the vehicle accident can also be determined.

[0128] In an embodiment where the driving status is mileage, when the predicted risk score is obtained based on the first driving data, the first turning data, the second driving data and the second turning data, the predicted location where the vehicle accident occurs can also be determined, wherein the predicted location can be expressed as the mileage between the vehicle and the current location.

[0129] The predicted time or predicted location of the vehicle accident can be obtained by the risk field (inner field) after the jump Θ J The coordinates of γ J express.

[0130] Step S2300: Control the vehicle according to the predicted risk score.

[0131] In this embodiment, when the predicted risk score is less than the score threshold, it indicates that all components in the steering-by-wire system are normal and the steering-by-wire system can be normally controlled; when the predicted risk score is greater than or equal to the score threshold, it indicates that a fault has occurred in the steering-by-wire system and may cause a vehicle accident, and the steering-by-wire system can be redundantly controlled.

[0132] Through the embodiments of the present disclosure, the predicted risk score of the vehicle is determined based on the first driving data and the first steering data of the vehicle, and the vehicle is controlled based on the predicted risk score, thereby ensuring the high reliability and high safety of the wire-controlled steering system, reducing the redundant hardware of the wire-controlled steering system, and reducing the hardware cost of the vehicle.

[0133] When the predicted time or predicted location of a vehicle accident is obtained, the steer-by-wire system may be redundantly controlled before the predicted time is reached or before the vehicle reaches the predicted location to ensure high reliability and safety of the steer-by-wire system.

[0134] In one embodiment of the present disclosure, controlling a vehicle based on a predicted risk score includes: detecting a target device having a fault in a steer-by-wire system of the vehicle when the predicted risk score is greater than or equal to a score threshold; and performing fault reconfiguration control on the vehicle based on the target device.

[0135] In this embodiment, a fault reconfiguration strategy corresponding to each component in the steer-by-wire system may be pre-configured, and when a target component that fails in the steer-by-wire system is detected, the vehicle is fault reconfigured and controlled according to the fault reconfiguration strategy corresponding to the target component.

[0136] In one example, the target device includes a steering motor, and performing fault reconfiguration control on the vehicle according to the target device includes: configuring the differential speed of wheel motors of the vehicle to steer the vehicle.

[0137] In another example, the target device includes a steering motor controller; fault reconfiguration control of the vehicle is performed according to the target device, including: controlling the analytical redundant controller of the vehicle to replace the steering motor controller to drive and control the steering motor of the vehicle.

[0138] Through this embodiment, when a target device fails and a vehicle accident is predicted, the steer-by-wire system can be redundantly controlled to ensure high reliability and high safety of the steer-by-wire system.

[0139] In one embodiment of the present disclosure, the method may further include: in the event of a failure in the steer-by-wire system of the vehicle, updating the analytical redundancy model according to the first driving data.

[0140] In this embodiment, updating the analytical redundancy model according to the first driving data may be performed by increasing y in the above formula according to the first driving data of the vehicle. p and z p The quantity dimension of .

[0141] Through this embodiment, the accuracy of parsing the redundant model can be improved.

[0142] In one embodiment of the present disclosure, the method also includes: storing the first driving data as the second driving data; storing the first turning data as the second turning data, so that when new first driving data and new first turning data are subsequently acquired, the predicted risk score of the vehicle can be determined based on the previously acquired driving data and turning data, so that the risk of an accident involving the vehicle represented by the obtained predicted risk score is more accurate, thereby achieving precise control of the vehicle.

[0143] Figure 3 FIG. 1 is a schematic diagram of the risk field evolution process according to an embodiment of the present disclosure. Figure 3 As shown in the figure, when the vehicle was driving on the road, the power of the steering motor of the front wheel suddenly decreased, the vehicle understeered and hit the obstacle in front. The key node scenes of the accident evolution process include:

[0144] SN01: The vehicle is driving normally along a straight road;

[0145] SN02: There is a curve in the road ahead and the vehicle starts to turn, but the power of the steering motor suddenly drops.

[0146] SN03: The power of the steering motor decreased, causing the vehicle to understeer, and the vehicle did not slow down, eventually colliding with the obstacle in front.

[0147] The vehicle’s driving data (including vehicle longitudinal and lateral speeds x, attitude angle data y, road adhesion coefficient z) and steering data (including motor sensor power data α, steering angle data β, vehicle driving status γ) before and after the occurrence of node scenes SN01 to SN03.

[0148] By analyzing the driving data and steering data of the redundant model vehicle, the following Figure 4The evolution of the system risk field is shown in Figure 1. From the accident evolution process from SN01 to SN03, it can be seen that in the space composed of the vehicle speed λ (km / h), the odometer Cha (km), and the accident risk RS, the changes in the risk field set are as follows: in scenario SN01, the vehicle is in a normal driving state, and the risk field set, that is, the changes in the accident risk field predicted by the system when the vehicle travels to different odometers, presents a complete, continuous, and undifferentiated form; in scenario SN02, the vehicle's operation presents a safety hazard, and the risk field set begins to differentiate; in scenario SN03, that is, before the accident is about to occur (300ms), the risk field set has differentiated into separate sub-risk fields Θ J , and the product of the maximum diameter of the sub-risk field and the shortest distance from the sub-risk field to the parent risk field set is Ω J Indicates the magnitude of the risk of an impending accident.

[0149] Therefore, the continuous change of the risk field set obtained based on the second kernel density estimation tensor can quantitatively analyze and predict the accident risk faced by the system, and the analysis and prediction results are highly consistent with the actual situation, which shows that the analytical redundancy model proposed in the present invention is reasonable and usable.

[0150] <Analysis of redundant controller implementation example>

[0151] This embodiment also provides a parsing redundant controller, such as Figure 4 As shown, the parsing redundant controller 4000 includes a processor 4100 and a memory 4200, wherein the memory 4200 is used to store a computer program, and the processor 4100 is used to execute the method described in any of the above embodiments under the control of the computer program.

[0152] <Embodiment of steer-by-wire system>

[0153] This embodiment further provides a steer-by-wire system, which may include the analytical redundant controller 4000 described in the above embodiment.

[0154] In one example, the steer-by-wire system may further include an onboard storage unit for storing second driving data and second steering data of the vehicle. The analytical redundant controller is further configured to determine a predicted risk score of the vehicle based on the second driving data and the second steering data.

[0155] In one example, the steer-by-wire system may be the steer-by-wire system 1000 described in the aforementioned embodiment.

[0156] <Readable Storage Medium Embodiment>

[0157] This embodiment provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method described in any method embodiment of the present disclosure is executed.

[0158] <Computer Program Product Embodiment>

[0159] This embodiment provides a computer program product, including a computer program, which implements the method described in any method embodiment of the present disclosure when the computer program is executed by a processor.

[0160] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0161] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0162] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0163] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0164] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0165] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0166] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0167] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0168] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A vehicle control method, characterized in that: include: Acquiring first driving data and first turning data of the vehicle; Determining a predicted risk score of the vehicle according to the first driving data and the first turning data; wherein the predicted risk score indicates a risk that the vehicle will have an accident; The vehicle is controlled based on the predicted risk score.

2. The method according to claim 1, characterized in that The determining, according to the first driving data and the first turning data, a predicted risk score of the vehicle includes: Acquire second driving data and second steering data of the vehicle; The predicted risk score is obtained according to the first driving data, the first turning data, the second driving data and the second turning data.

3. The method according to claim 2, characterized in that The driving data includes speed data, attitude angle data and road adhesion coefficient; the steering data includes steering motor power data, steering angle data and driving status, wherein the driving status is driving time or mileage.

4. The method according to claim 2, characterized in that: The step of obtaining the predicted risk score according to the first driving data, the first turning data, the second driving data, and the second turning data includes: Based on the set first neural network of the analytical redundancy model and the second driving data, the first driving data is processed to obtain a first kernel density estimation tensor of the first driving data; Based on the second neural network of the analytical redundancy model and the second steering data, the first steering data and the first kernel density estimation tensor are processed to obtain the predicted risk score.

5. The method according to claim 4, characterized in that The second neural network based on the analytical redundancy model and the second steering data processes the first steering data and the first kernel density estimation tensor to obtain the predicted risk score, including: Determining a second kernel density estimation tensor of the first steering data according to the first kernel density estimation tensor; Obtaining a first conversion function representing a conversion relationship between the first turning data and the first driving data according to the second turning data, the first turning data and the second kernel density estimation tensor; The predicted risk score is obtained according to the first conversion function.

6. The method according to claim 4, characterized in that The method further comprises: In the event of a failure in the steer-by-wire system of the vehicle, the analytical redundant model is updated based on the first driving data.

7. The method according to claim 2, characterized in that The method further comprises: The first driving data is stored as the second driving data; and the first steering data is stored as the second steering data.

8. The method according to claim 1, characterized in that The controlling the vehicle according to the predicted risk score includes: In a case where the predicted risk score is greater than or equal to a score threshold, detecting a target component having a fault in a steer-by-wire system of the vehicle; Fault reconfiguration control is performed on the vehicle according to the target device.

9. The method according to claim 8, characterized in that The target device includes a steering motor, The performing fault reconfiguration control on the vehicle according to the target device includes: The differential speeds of the wheel motors of the vehicle are configured to steer the vehicle.

10. The method according to claim 8, characterized in that The target device includes a steering motor controller; The performing fault reconfiguration control on the vehicle according to the target device includes: The analytical redundant controller controlling the vehicle replaces the steering motor controller to drive and control the steering motor of the vehicle.

11. A redundant analytical controller, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the method according to any one of claims 1 to 10 under the control of the computer program.

12. A steer-by-wire system, characterized in that: Comprising the analytical redundant controller as claimed in claim 11.

13. The steer-by-wire system according to claim 12, characterized in that: The steer-by-wire system further includes an on-board storage unit, the on-board storage unit being used to store second driving data and second steering data of the vehicle; The analytical redundant controller is further configured to determine a predicted risk score for the vehicle based on the second driving data and the second steering data.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 10 when executed by a processor.

15. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 10 when being executed by a processor.

Images