Steering control device and method thereof

Abstract

The present disclosure relates to a steering control device and method, wherein steering type information of a driver is generated based on driving data of a vehicle using a steering type classification model, steering pattern information is extracted from driving data using a pattern extraction model, and a steering profile is generated for each driver based on the steering type information and steering pattern information. It includes a configuration for controlling a steering device according to steering control information generated based on the above steering profile and the driver's steering input.

Description

Technology Field

[0001] The present disclosure relates to a steering control device and method, and more specifically, to a steering control device and method that provides a steering response tailored to a driver and driving conditions. Background Technology

[0002] Generally, a steering system refers to a device that changes the driving direction of a vehicle by manipulating the rotational direction of the wheels. In particular, electric power steering systems, which perform steering by generating electrical signals corresponding to steering inputs using electric motors, are widely used these days.

[0003] Furthermore, regarding a specific steering input, the speed and extent to which the vehicle's driving direction changes, and the degree of feedback to the driver, should not be determined uniformly but can vary depending on the driver or driving conditions.

[0004] Considering these factors, there is a need to develop technology that controls the steering system to respond appropriately by comprehensively taking into account the driver's driving style, vehicle condition, and driving situation. The problem to be solved

[0005] The present disclosure aims to provide a steering control device and a method capable of performing steering control such that steering output and feedback in a steering device are provided in accordance with the driver and driving conditions. means of solving the problem

[0006] In one aspect, the present embodiments provide a steering control device comprising at least one memory including computer program instructions and at least one processor for executing computer program instructions, wherein the at least one processor generates steering type information of a driver based on driving data of a vehicle using a steering type classification model, extracts steering pattern information from driving data using a pattern extraction model, generates a steering profile for each driver based on the steering type information and steering pattern information, and controls a steering device according to steering control information generated based on the steering profile and the driver's steering input.

[0007] In another aspect, the present embodiments may provide a steering control method comprising: a driving data analysis step of generating driver steering type information based on vehicle driving data using a steering type classification model and extracting steering pattern information from driving data using a pattern extraction model; a steering profile generation step of generating a steering profile for each driver based on steering type information and steering pattern information; a control information generation step of generating steering control information based on steering profile and steering input; and a steering device control step of controlling a steering device according to steering control information. Effects of the invention

[0008] According to the present disclosure, a steering control device and method can be provided to perform steering control such that steering output and feedback in a steering device are provided in accordance with the driver and driving conditions. Brief explanation of the drawing

[0009] FIG. 1 is a drawing for exemplarily illustrating the configuration of a steering device that can be used in the present disclosure. FIG. 2 is a block diagram of an exemplary computing system that can be used in the present disclosure. FIG. 3 is a block diagram relating to another exemplary configuration of a computing system that can be used in the present disclosure. FIG. 4 is a flowchart relating to a steering control method according to one embodiment. FIG. 5 is a flowchart relating to a steering control method according to another embodiment. FIG. 6 is a flowchart illustrating, in an exemplary manner, a control information correction step according to one embodiment. FIG. 7 is a flowchart illustrating, by way of example, a control information correction step according to another embodiment. FIG. 8 is a flowchart relating to a steering control method according to another embodiment. Specific details for implementing the invention

[0010] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0011] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0012] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0013] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0014] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0015] FIG. 1 is a drawing for exemplarily illustrating the configuration of a steering device that can be used in the present disclosure.

[0016] Referring to FIG. 1, the steering device (100) may include a steering control device (110), a steering motor (120), a steering wheel (130), an upper shaft (140), a lower shaft (150), and a rack device (160). In this case, the steering control device (110) may transmit and receive data with a sensor (170).

[0017] For example, the steering device (100) may include a configuration that performs steering operations using an electric motor. For example, the steering device (100) may include an electric power steering device that uses an electric motor to generate an assist torque to assist the steering force generated by the steering input. For another example, the steering device (100) may include a steer-by-wire device in which the upper and lower stages are mechanically separated and the steering input of the upper stage is transmitted using an electric signal.

[0018] The steering control device (110) may include a configuration for controlling the steering device (100). For example, the steering control device (110) may include a configuration for controlling the steering device (100) using an electric control unit (ECU).

[0019] For example, the steering control device (110) can control an electric motor mounted on the steering device (100). In this case, the steering control device (110) may control the steering device (100) in a different way depending on the location where the electric motor is mounted.

[0020] The specific configuration of such a steering control device (110) will be explained in more detail below in the section describing the steering control device in FIG. 3.

[0021] The steering motor (120) can convert input energy into mechanical motion and output it. For example, the steering motor (120) may include a configuration that receives electrical energy, converts it into rotational motion, and outputs it. Additionally, the steering motor (120) may be electrically connected to the steering control device (110) and become the control target.

[0022] For example, when a steering motor (120) is mounted on an upper unit of a steering device (100), a steering control device (110) can control the steering motor (120) so that the force generated by the steering motor (120) is transmitted to the upper unit shaft (140) and the steering wheel (130), thereby controlling the rotational movement of the upper unit shaft (140) and the steering wheel (130).

[0023] In another example, when the steering motor (120) is mounted on the lower unit of the steering device (100), the steering control device (110) controls the steering motor (120) so that the force generated by the steering motor (120) is transmitted to the lower unit shaft (150) and the rack device (160), thereby controlling the rotational movement of the lower unit shaft (150) and the linear movement of the rack device (160).

[0024] The steering wheel (130) may include a configuration that rotates according to a steering input. In this case, the steering input may include the driver's steering wheel operation, a steering wheel rotation signal from an autonomous driving system, etc.

[0025] For example, the steering wheel (130) may be connected to an upper shaft (140). In this case, the force generated as the steering wheel (130) rotates is transmitted to the upper shaft (140) and can affect the rotational movement of the upper shaft (140).

[0026] The upper shaft (140) can be connected to the steering wheel (130). In this case, the force generated as the upper shaft (140) rotates can affect the rotational movement of the steering wheel (130).

[0027] Additionally, the upper shaft (140) may be connected to the steering motor (120). In this case, the force generated by the steering motor (120) is transmitted to the upper shaft (140) and can affect the rotational movement of the upper shaft (140).

[0028] The lower shaft (150) can be connected to the upper shaft (140) and the rack device (160). For example, the force generated by the rotation of the upper shaft (140) can affect the rotational movement of the lower shaft (150). Also, the force generated by the rotation of the lower shaft (150) can affect the linear movement of the rack device (160).

[0029] For example, the lower shaft (150) may be a configuration that is included in or not included in the steering device (100) depending on the type of steering device (100).

[0030] For example, if the steering device (100) is an electric power steering device, a lower shaft (150) may be included, and in this case, the force generated from the upper shaft (140) may affect the lower unit of the steering device through the lower shaft (150).

[0031] As another example, if the steering device (100) is a steer-by-wire device, the lower shaft (150) may not be included, and in this case, the force generated from the upper shaft (140) may not be mechanically transmitted to the lower end of the steering device. However, in this case, the steering control device (110) can control the lower end of the steering device (110) through an electronic signal.

[0032] The rack device (160) may include a configuration that moves in a linear motion connected to a lower shaft (150). In this case, the rack device (160) may be connected to the lower shaft (150) through a gear, and through this gear, the rotational motion of the lower shaft (150) may be converted into linear motion in the rack device (160).

[0033] For example, the rack device (160) can be connected to the wheel, and the linear motion of the rack device (160) can affect the change in the direction of travel of the wheel.

[0034] For example, the rack device (160) can perform linear motion based on the force transmitted through the steering wheel (130), upper shaft (140), and lower shaft (150) when the steering device (100) is an electric power steering device that does not have a steering motor (120) mounted on its lower end.

[0035] As another example, the rack device (160) can move in a straight line based on the force generated by driving the steering motor (120) through an electrical signal transmitted from the steering control device (110), when the steering device (100) has a steering motor (120) mounted on its lower end.

[0036] The sensor (170) may include a configuration that detects a specific physical phenomenon and converts it into an electrical signal. In this case, the sensor (170) can transmit and receive sensing data, etc., in the form of an electrical signal to and from the steering control device (110).

[0037] For example, the sensor (170) may include both a sensor provided within the steering device (100) and a sensor outside the steering device (100). For example, the sensor (170) may include a motor position sensor, a steering angle sensor, a steering torque sensor, etc., provided within the steering device (100). For another example, the sensor (170) may include a vehicle speed sensor outside the steering device (100), an image sensor including a camera, a radar sensor, a laser sensor including a LiDAR, an inertial measurement unit (IMU), an inclination sensor, or other environmental sensors that sense weather, temperature, road conditions, etc.

[0038] For example, the steering device according to the present disclosure may include a configuration for safety design and handling of emergency situations. For example, key components such as a steering sensor, a motor, and an ECU may be configured with redundancy, and in the event of a failure of one of the redundant components, a backup system may be automatically activated so that steering control is performed using the remaining component. In addition, in the event of a failure of the steering system, the steering wheel may be maintained in a neutral position or controlled to stably stop the driving state in conjunction with an Electronic Stability Control (ESC).

[0039] For example, the steering system may include a configuration that controls according to preset logic to respond to emergency situations such as a failure. For example, by enabling steering control through logic that generates a warning when a failure of the steering system is detected, such as a discrepancy in sensing data (e.g., discrepancy between the steering wheel angle and the wheel direction), and emergency steering wheel locking logic such as an electronic lock, it is possible to prevent the steering wheel from turning abruptly even in emergency situations.

[0040] FIG. 2 is a block diagram relating to an exemplary configuration of a computing system used in the present disclosure. A computing system or computing device may be used to include or implement its components, such as a system or a data processing system.

[0041] A computing system includes a bus or other communication component for transmitting information, and a processor or processing circuit connected to the bus to process information. A computing system may also include one or more processors or processing circuits connected to the bus to process information. A computing system also includes main memory, such as random access memory (RAM) or other dynamic storage devices connected to the bus to store information, and instructions (instructions) to be executed by the processor. The main memory may be or may contain a data store. The main memory may also be used to store location information, temporary variables, or other intermediate information during the execution of instructions by the processor. A computing system may further include ROM or other static storage devices connected to the bus to store static information and instructions for the processor. Storage devices, such as solid-state devices, magnetic disks, or optical disks, may be coupled to the bus to continuously store information and instructions. A storage device may include or be part of a data store.

[0042] For example, a computing system may include at least one computing device. For instance, it may include various computer devices such as smartphones, tablets, laptops, desktops, servers, and clients. In this case, the computing device may be a single stand-alone device, or it may be a configuration including multiple computing devices operating in a distributed environment composed of multiple computing devices that cooperate with each other via a communication network.

[0043] Meanwhile, a computing device can be a classical computing device or a quantum computing device. For example, a quantum computing device can perform operations in units of qubits rather than bits. A qubit can have a state in which 0 and 1 are simultaneously superpositioned, and if there are M qubits, 2^M states can be represented simultaneously.

[0044] A quantum computing device can use various types of quantum gates (e.g., Pauli / Rotation / Hadamard / CNOT / SWAP / Toffoli) that receive one or more qubits to perform quantum operations and perform specified operations, and can combine quantum gates to form a quantum circuit with a special function.

[0045] Quantum computing devices can use quantum artificial neural networks (e.g., QCNN, QGRNN) that can perform functions of conventional artificial neural networks (e.g., CNN, RNN) at a faster speed while using fewer parameters.

[0046] In some cases, the computing system may further include a Graphic Processing Unit (GPU). In this case, the GPU can process image data at high speed and may include a configuration specialized for parallel processing of data, floating-point operations, and matrix-based operations for training and inference of artificial intelligence models.

[0047] Data may be stored in the memory, and at least one of volatile memory (e.g., SRAM, DRAM) or non-volatile memory (e.g., NAND Flash) may be included. For example, the memory may include RAM (Random Access Memory) and ROM (Read-Only Memory). In this case, RAM may include both volatile memory that allows reading and writing of data, and ROM may include both non-volatile memory that allows only reading of data but retains data even when the power of the computing system is turned off.

[0048] For example, data can include text and images, executable programs and code, etc. In some cases, data may be stored not only in memory but also on separate high-capacity storage servers.

[0049] For example, memory may be a medium for storing computer-readable software, applications, program modules, routines, instructions, and / or data, etc., which are coded to perform a specific task when executed by a processor. And the processor may read and execute computer-readable software, applications, program modules, routines, instructions, and / or data, etc., stored in memory.

[0050] In some cases, artificial intelligence models may be stored in memory. In this case, the AI ​​models may include models where supervised learning or unsupervised learning is performed. For example, if supervised learning is performed on an AI model, it may further include annotation-based learning or data labeling.

[0051] For example, when a computing system performs various calculations or data classification and generation tasks using an artificial intelligence model, it may utilize an artificial intelligence model stored in the computing system's memory.

[0052] The processor can extract specific data from data stored in memory or generate new data. For example, the processor can perform the task of classifying at least one preset class from multiple images stored in memory. As an example, the processor can execute an artificial intelligence model stored in memory to perform class classification for each image and output the class classification result to generate new data.

[0053] A computing system can be connected to input devices and displays. For example, a computing system can be connected to a display, such as a liquid crystal display or an active matrix display, to display information to a user via a bus, and an input device, such as a keyboard containing alphanumeric and other keys, can be connected to the bus to transmit information and command selections to the processor.

[0054] For example, the input device may include a touch screen display. The input device may also include cursor controls, such as a mouse, trackball, or cursor direction keys, for transmitting direction information and command selection to a processor and controlling cursor movement on the display.

[0055] For example, an input device may include a configuration that allows a user to input a command to the processor to execute a specific task or to input data necessary for the execution of a specific task. For example, the input device may include a physical or virtual keyboard or keypad, key buttons, a mouse, a joystick, a trackball, a touch-sensitive input means, or a microphone.

[0056] For example, the display may be part of a data processing system, a client computing device, or other components. For example, the display may include a visual display device, a printer, a speaker, or a vibrating device.

[0057] The processes, systems, and methods described herein may be implemented by a computing system in response to a processor executing an array of instructions contained in main memory. These instructions may be read into main memory from other computer-readable media, such as storage devices. The execution of the array of instructions contained in main memory causes the computing system to perform the exemplary processes described herein. In a multiprocessing array, one or more processors may also be used to execute instructions contained in main memory. Hardwired circuits may be used in place of or in conjunction with hardware instructions with the systems and methods described herein. The systems and methods described herein are not limited to any specific combination of hardware circuits and software.

[0058] Although exemplary computing systems have been described above, the essence including the operations described herein may be implemented in other types of digital electronic circuits, or in computer software, firmware, or hardware including structures disclosed herein and structural equivalents thereof or combinations of one or more of these.

[0059] "Data processing system," "computing device," "module," "engine," "component," or "computing device" includes various devices, devices, and machines for processing data, including, for example, a programmable processor, a computer, a system on a chip, or a number of such things, or a combination thereof.

[0060] For example, a processor may include special-purpose logic circuits. For example, it may include a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a digital signal processor (DSP), digital signal processing devices (DSPD), a programmable logic device (PLD), etc.

[0061] In some cases, the processor may further include a separate artificial intelligence semiconductor device for processing tasks using an artificial intelligence model. For example, the artificial intelligence chip may include special-purpose logic circuits such as FPGA, ASIC, DSP, DSPD, PLD, etc., and may be designed to be specialized for learning or inference tasks using an artificial intelligence model.

[0062] For example, the present disclosure may be implemented using an artificial intelligence semiconductor device in which neurons and synapses of a deep neural network are implemented using semiconductor devices. In this case, the semiconductor devices may be currently used semiconductor devices, such as SRAM, DRAM, NAND, etc., or next-generation semiconductor devices, such as RRAM, STT MRAM, PRAM, etc., or a combination thereof. Furthermore, when the present disclosure is implemented using an artificial intelligence semiconductor, the results (weights) of training a deep learning model with software may be transferred to synapse mimic devices arranged in an array, or training may be performed on the artificial intelligence semiconductor device.

[0063] In addition to these hardware configurations, code that creates an execution environment for computer programs may also be included, for example, code that constitutes processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or a combination of one or more of these. The device and execution environment may realize various different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures. For example, a content request module, a content rendering module, or a rendered content delivery module may include or share one or more data processing units, systems, computing units, or processors. Components of the system may include or share one or more data processing units, systems, computing units, or processors.

[0064] A computer program (also known as a program, software, software application, app, script, or code) may be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and may be distributed as a standalone program or in any form including modules, components, subroutines, objects, or other units suitable for use in a computing environment. A computer program may or may not correspond to a file in a file system. A computer program may be stored in a file containing other programs or data (e.g., one or more scripts stored in a markup language document), a single file dedicated to the program, or a portion of a file containing multiple coordinated files (e.g., files storing one or more modules, subprograms, or parts of code). A computer program may be distributed to be executed on a single computer or site, or distributed across multiple sites and interconnected by a communication network.

[0065] The processes and logic flows described herein may be performed by one or more programmable processors that execute one or more computer programs (e.g., components of a data processing system) to perform actions by operating input data and generating outputs. The processes and logic flows may also be performed by special-purpose logic circuits, e.g., FPGAs, ASICs, DSPs, DSPDs, or PLDs, and devices may also be implemented by special-purpose logic circuits. Devices suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices like EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; optomagnetic disks; and CD-ROM and DVD-ROM disks. Processors and memory may be complemented or integrated by special-purpose logic circuits.

[0066] FIG. 3 is a block diagram relating to another exemplary configuration of a computing system used in the present disclosure.

[0067] Referring to FIG. 3, a computing system according to the present disclosure may be connected to a server system. For example, a server system may be connected to the computing system according to the present disclosure via a network via wired or wireless means to transmit and receive data and share computing resources.

[0068] For example, a server system can be built in the form of a cloud system. For instance, the server system may include a configuration that allows individual computing devices to connect to the server system via a network and shares computing resources with the connected devices. In this case, individual computing devices can access the cloud system from anywhere as long as they are connected to a network, such as the Internet.

[0069] For example, a cloud system can provide computing resources by flexibly scaling them up or down as needed, and can share these resources with other computing devices connected via a network. Furthermore, depending on the purpose or scope of use, a cloud system can be built based on various service models such as IaaS (Infrastructure as a Service), PaaS (Platform as a Service), and SaaS (Software as a Service).

[0070] For example, a cloud system may include at least one computing device, a storage device, and a network device. Each computing device included in the cloud system may include a processor and memory to enable processing various computing tasks, the storage device may include configurations related to data storage such as an HDD (Hard Disk Drive), SSD (Solid State Drive), NAS (Network Attached Storage), or SAN (Storage Area Network) for storing large amounts of data, and the network device may include configurations related to networking such as a switch, a router, a load balancer, and a firewall.

[0071] For example, when a computing system performs various calculations or data classification and generation tasks using an artificial intelligence model, it may utilize an artificial intelligence model stored in the computing system's memory.

[0072] Alternatively, in some cases, a computing system may share computing resources from a cloud system and utilize artificial intelligence models stored in the cloud system. In this case, the computing system can process related tasks by using the artificial intelligence models provided by the cloud system, even if it does not directly possess the configurations related to the artificial intelligence models itself.

[0073] For example, a steering control device includes at least one memory containing computer program instructions and at least one processor that executes computer program instructions, wherein the at least one processor generates steering type information of a driver based on driving data of a vehicle using a steering type classification model, extracts steering pattern information from driving data using a pattern extraction model, generates a steering profile for each driver based on the steering type information and steering pattern information, and controls a steering device according to steering control information generated based on the driver's steering profile and steering input.

[0074] And in the present disclosure, the phrase “data, values, conditions, and ranges, etc. are pre-set” may include all methods in which specific data or values, etc. are pre-entered and set during system design or product manufacturing; methods in which data or values, etc. stored in a specific storage space or received from other components are entered and set; and methods in which a user directly enters and sets them through input means such as a prompt.

[0075] For example, driving data may include steering data, vehicle status data, and driving environment data.

[0076] For example, steering data may include data regarding the steering wheel rotation angle and direction, steering wheel rotation speed, force or torque generated by steering wheel operation, feedback torque generated by the steering motor, wheel steering angle and direction, wheel steering angular velocity, force applied to the rack device or wheel, etc.

[0077] For example, vehicle condition data may include all data regarding the condition of the vehicle, such as vehicle speed, acceleration and whether acceleration / deceleration occurs, the yaw / roll / pitch angle of the vehicle, the tilt of the vehicle and lateral acceleration during cornering.

[0078] For example, environmental data may include data regarding the road surface friction coefficient, tire slip ratio, external temperature and weather information, road gradient, etc., related to the road environment around the vehicle.

[0079] For example, a processor can generate driver steering type information based on vehicle driving data. In this case, the driver steering type information can be generated using a steering type classification model.

[0080] For example, a steering type classification model can generate driver steering type information by determining one of the steering types corresponding to each of the multiple clusters generated through clustering of driving data.

[0081] For example, a steering type classification model may include a pre-trained model that clusters multiple data points corresponding to driving data to classify the driver's steering type into one of K steering type groups.

[0082] For example, a steering type classification model may include a configuration that clusters driving data using clustering-based algorithms such as K-Means or DBSCAN (Density-Based Spatial Clustering of Applications with Noise). In this case, the steering type classification model performs initial clustering of data points based on driving data using clustering-based algorithms based on steering speed and turning angle, and can classify each driver to be included in one of the steering type groups (e.g., sensitive steering type group, stable driver type group, etc.) based on the resulting data from the initial clustering performed in conjunction with vehicle speed data.

[0083] For example, a steering type classification model may include a pre-trained model that classifies data by finding the optimal boundary line between steering type groups, taking into account the characteristics of individual drivers, for data points based on clustered driving data.

[0084] For example, a steering type classification model can perform optimal classification of data points based on an optimal classification algorithm such as a Support Vector Machine (SVM). In this case, the steering type classification model utilizes SVM and an optimal classification algorithm to model the non-linear relationship between steering resistance values ​​and vehicle speed, and can perform the task of optimally classifying driving data for each driver into one of the steering type groups by considering the characteristics of the individual driver.

[0085] For example, a processor can extract steering pattern information from a vehicle's driving data. In this case, the steering pattern information can be extracted using a pattern extraction model.

[0086] For example, a pattern extraction model can extract steering pattern information by performing a time-series analysis on the relationship between the driver's steering input and driving data. In this case, the driving data may include data in the form of time-series data containing various data items that can be classified into steering data, vehicle state data, road environment data, etc., according to temporal continuity.

[0087] For example, a pattern extraction model may include a model trained to analyze driving situations and extract steering pattern information by finding parts where data of various items, such as steering angle, angular velocity, and vehicle speed, follow a specific order, arrangement, or rule from driving data containing such time series data.

[0088] For example, the pattern extraction model can perform time series analysis on the driver's driving data, including a Long Short-Term Memory (LSTM) model, and through this, can determine the driving situation in the corresponding time series and extract steering pattern information.

[0089] For example, steering pattern information can be extracted in a form that includes the steering device's response and steering output corresponding to a specific steering input, and based on the correspondence between this steering input and the steering device's response and output, it is possible to analyze which steering response parameters the driver preferred in a given driving situation. Through this, the pattern extraction model can analyze how personalized steering inputs, driving situations, steering response parameters, and steering outputs correspond to each other for each driver.

[0090] For example, the processor can generate a steering profile for each driver based on steering type information and steering pattern information. In this case, the steering profile may include preset parameters to generate information regarding steering outputs corresponding to steering inputs.

[0091] For example, a steering profile may include steering response parameters for generating steering control information by applying them to the driver's steering input. In this case, the processor may generate a steering profile such that the steering response parameters are set according to driving conditions.

[0092] For example, a processor can generate steering control information to produce a steering response and steering output in accordance with the steering type and steering pattern appearing in the driving data of a specific driver, based on the steering type information and steering pattern information of a specific driver.

[0093] To this end, a steering profile is generated based on the steering type information and steering pattern information of a specific driver, and when there is a steering input from the driver, steering response parameters included in the corresponding steering profile are applied to perform steering control so that steering response and steering output reflecting the driver's steering type and steering pattern are achieved.

[0094] For example, steering response parameters may include steering sensitivity for determining the steering angle of the wheel corresponding to the steering angle applied to the steering wheel rotation angle resulting from the steering input, feedback strength for determining the feedback torque corresponding to the steering wheel operation, and neutral restoring force applied when the power supply by the steering wheel operation is interrupted.

[0095] For example, the driving situation may be determined based on at least one of steering data, vehicle state data, and driving environment data included in the driving data. In this case, the processor may determine the driving situation based on the vehicle state or the environment surrounding the vehicle that can be identified from the driving data.

[0096] For example, the processor can determine the driving situation as either a high-speed driving situation or a low-speed driving situation based on vehicle speed data included in the driving data. For example, the processor can determine the driving situation as a high-speed driving situation if the vehicle speed data is greater than or equal to a preset reference vehicle speed, and as a low-speed driving situation if the vehicle speed data is less than the reference vehicle speed.

[0097] In some cases, the reference vehicle speed may be set differently depending on the driver's steering type or the contents of other driving data items other than vehicle speed data. For example, the reference vehicle speed may be set differently for drivers with different steering types. As another example, when the road surface friction coefficient is below the critical friction coefficient, the reference vehicle speed may be set differently from when it is above the critical friction coefficient.

[0098] For example, the processor can determine the driving situation based on road surface friction coefficient data included in the driving data. For example, if the road surface friction coefficient is greater than or equal to a critical friction coefficient, it can be determined as a dry road driving situation, and if it is less than the critical friction coefficient, it can be determined as a slippery road driving situation. Depending on the case, a more detailed determination of the driving situation may be performed, such as determining as a dry road driving situation if the road surface friction coefficient is greater than or equal to a first critical friction coefficient, a wet road driving situation if it is less than the first critical friction coefficient and greater than or equal to a second critical friction coefficient, and an icy road driving situation if it is less than the second critical friction coefficient.

[0099] In addition, the processor can determine the driving situation based on various data included in the driving data, and in some cases, determine that it corresponds to two or more driving situations at a single point in time. For example, the processor can determine the driving situation as corresponding to both "high-speed driving situation" and "slippery road driving situation" for the driving data at a specific point in time.

[0100] For example, the processor can generate steering control information based on the driver's steering profile and steering input. Then, the processor can control the steering device according to the steering control information.

[0101] For example, steering control information may include wheel steering control information regarding at what speed and to what position the wheels will be steered in response to the driver's steering input, feedback torque control information for assisting the steering input at the steering wheel or providing a reaction force, and neutral restoring force control information regarding at what speed and with what strength the steering wheel will be restored to neutral when the steering input is interrupted.

[0102] In some cases, the processor may correct steering control information. In this case, the processor may cause the steering control information to be corrected when specific conditions are satisfied, or it may perform the correction of the steering control information based on an analysis of the driving environment, such as road conditions.

[0103] For example, the processor can determine the driver's steering intention by comparing the driver's steering input with steering pattern information. In this case, the processor can correct steering control information if it determines that steering correction is necessary based on the driving situation determined from the steering intention and driving data.

[0104] For example, the processor may determine that the steering intention is a normal steering intention if the steering input is within the normal steering range according to the steering pattern information. As another example, if the steering input falls outside the normal steering range, the processor may determine whether the steering intention is a danger avoidance intention or a mistake based on the driving situation.

[0105] For example, the processor can determine whether the driver's steering input deviates from the normal steering range based on the steering pattern information in the driver's driving data. In this case, if the driver's steering input is determined to be within the normal steering range, the steering intention can be determined to be a normal steering intention, and if the steering input is determined to be outside the normal steering range, the steering intention can be determined not to be a normal steering intention.

[0106] For example, if the processor determines that the driver's steering input is not a normal steering intention, it can determine, by considering the driving situation, whether the steering input was made with the intention of avoiding danger or by mistake.

[0107] For example, when a sudden steering input is made that deviates from the driver's existing driving pattern by a certain amount, the steering intention resulting from such steering input may be determined differently depending on the driving situation. For example, if the driving situation in which the steering input was made involved the detection of a forward obstacle or required a sharp curve according to road information, the steering intention may be determined to be an intention to avoid danger; however, if the sudden steering input was made even though such circumstances were not visible in the driving situation, it may be determined to be due to a mistake.

[0108] For example, the processor can compare the driver's steering intention with the vehicle's driving state and correct steering control information if it is determined that driving according to the steering intention is not taking place.

[0109] For example, if the steering intention resulting from the driver's steering input is determined to be a normal steering intention, but the resulting vehicle state does not match this normal steering intention and it is determined that normal steering is not taking place, it may be determined that correction of the steering control information is required.

[0110] As another example, if the steering intention resulting from the driver's steering input is determined to be a danger avoidance intention, but the vehicle state is determined to be insufficiently performing steering for danger avoidance, it may be determined that correction of the steering control information is required.

[0111] As another example, if it is determined that the steering intention resulting from the driver's steering input was a mistake, in principle, correction of steering control information may be performed to prevent the risk of an accident caused by the mistake; however, if performing steering control based on the steering input resulting from the mistake does not significantly affect driving safety (e.g., when the vehicle is stationary or driving at a very low speed), correction of steering control information may not be performed.

[0112] The processor can determine whether correction of steering control information is necessary by considering the results of the analysis of steering intentions based on the driver's steering input and the driving situation determined based on driving data, and can set specific conditions for determining whether correction is necessary in some cases.

[0113] For example, the processor may determine that steering correction is required if it satisfies a correction threshold condition that is set differently depending on the steering intention.

[0114] For example, the processor may set several conditions, such as a condition where the vehicle speed is greater than or equal to a critical vehicle speed, a condition where the steering angular velocity is greater than or equal to a critical angular velocity, and a condition where the road surface friction coefficient is greater than or equal to a critical friction coefficient, and may set a correction threshold condition to determine that correction is required when at least x of these conditions are satisfied.

[0115] Furthermore, the processor may set correction threshold conditions by adjusting parameters such as critical vehicle speed, critical angular velocity, and critical friction coefficient according to the driver's steering intention. Additionally, correction threshold conditions can be set differently by considering not only the steering intention but also the driver's steering type or the vehicle's driving situation. Through this, while providing steering response and output tailored to the driver's steering type and pattern during normal driving conditions, steering correction control can be performed more quickly and accurately according to specific conditions in situations where the risk of an accident is relatively high.

[0116] For example, the processor can estimate the road surface friction coefficient based on sensing data. For example, the processor can estimate the road surface friction coefficient information by fusing road sensing data received from at least two sensors.

[0117] For example, the processor can detect the coefficient of friction of the road surface through sensor fusion. For instance, the coefficient of friction of the road surface can be estimated more accurately by fusing sensing data such as road friction sensors inside the tires, cameras mounted on the underside of the vehicle, and LiDAR. In some cases, road conditions, such as whether the road is icy or wet, can be detected using an AI-based road database.

[0118] For example, the processor can correct steering control information based on road surface friction coefficient information.

[0119] For example, the processor can correct steering control information based on a relatively reduced steering sensitivity when the road surface friction coefficient information is less than a first threshold friction coefficient.

[0120] As another example, the processor can correct steering control information based on reduced steering sensitivity but not exceeding a preset maximum steering behavior range when the road surface friction coefficient information is less than a second threshold friction coefficient that is smaller than a first threshold friction coefficient.

[0121] For example, if the road surface friction coefficient information is estimated in the range of 0 to 1, and the first critical friction coefficient is set to 0.7 and the second critical friction coefficient is set to 0.3, the processor can determine whether to correct the steering control information based on the estimated road surface friction coefficient information, and can correct the steering control information by applying a reduction in steering sensitivity and a maximum steering behavior range.

[0122] For example, the processor may determine that correction of steering control information based on road surface friction coefficient information is not necessary, based on the fact that when the road surface friction coefficient information is estimated to be 0.9, the first threshold friction coefficient is 0.7 or higher.

[0123] As another example, the processor can correct steering control information by applying a steering sensitivity that is relatively reduced compared to the steering sensitivity according to the driver's steering profile, based on the fact that when the road surface friction coefficient information is estimated to be 0.6, the first critical friction coefficient is less than 0.7 and the second critical friction coefficient is 0.3 or greater.

[0124] As another example, the processor may apply a steering sensitivity that is relatively reduced compared to the steering sensitivity according to the steering profile based on the fact that when the road surface friction coefficient information is estimated to be 0.2, the first critical friction coefficient is less than 0.7 and the second critical friction coefficient is less than 0.3, and if the result of such application exceeds the maximum steering behavior range, the steering control information may be corrected to a value within the maximum steering behavior range. For example, the steering control information may be corrected to a maximum value within the maximum steering behavior range.

[0125] The processor can control the steering device according to steering control information. For example, if the steering control information is corrected, the steering device can be controlled according to the corrected steering control information, and if the steering control information is not corrected, the steering device can be controlled according to the steering control information as is, which is generated based on the steering profile and steering input.

[0126] Through this, the processor can control the wheels to be steered to a specific position at a specific speed according to the generated steering control information or corrected steering control information when there is steering input from the driver, control the steering motor to generate a feedback torque corresponding to the steering input at the steering wheel, and perform steering control such as controlling the steering wheel to return to neutral at a specific speed and intensity when the steering input is interrupted.

[0127] For example, the present disclosure may be implemented within a vehicle system including a hardware configuration and a software configuration.

[0128] For example, the hardware configuration of a vehicle system may include a control unit (ECU) that performs steering device control, such as processing steering inputs and adjusting the steering sensation (resistance, reaction force) of the wheel in real time; a sensor module including a steering sensor that measures steering angle, speed, resistance, etc., a speed sensor that provides vehicle speed data, an acceleration sensor that detects changes in vehicle movement, and an environment sensor (e.g., camera, radar) that detects road conditions and weather, etc.; a driver identification module that performs user profile identification using biometric recognition (face, fingerprint, voice) or a smart key; and a storage device including local storage within the vehicle and a cloud server (storing and updating driving styles).

[0129] For example, the software configuration of a vehicle system may include a data collection module that collects and records sensor data in real time while driving, a data analysis and learning algorithm that performs machine learning-based driving style analysis and profile generation, a steering device control algorithm that adjusts the response characteristics (resistance, restoring force) of the steering wheel according to the analyzed profile, and a UI and user feedback module that provides an interface for the driver to set the profile or input feedback.

[0130] For example, the processor can perform the operation of generating and applying a steering profile based on personalized steering responses by analyzing the driver's driving style, preferences, driving conditions, etc., based on data. For instance, the processor can generate a personalized steering profile through a process of identifying the driver, collecting data, and analyzing the driving style, and can store, apply, and update the generated steering profile.

[0131] For example, the processor can perform a driver identification process that executes a process for driver recognition upon entry into the vehicle. For instance, the processor can verify the user using a smart key or driver's seat biometric recognition, and if the driver is a new user, start with a default profile and collect driving data based on it, and if the driver is an existing user, load a saved profile.

[0132] The processor can perform a data collection process that collects vehicle and driver behavior data in real time while driving. For example, the processor can perform a data collection process that includes a basic data collection and preprocessing step for collecting and preprocessing driving data (vehicle and driver behavior data) in real time, a real-time filtering and outlier removal step, and a data pattern analysis (Feature Engineering) step.

[0133] For example, regarding the data collection and analysis structure, the processor can go beyond simply generating a profile using only static data such as steering angle and speed, and utilize a multi-layered data analysis structure that reflects the vehicle's dynamic environment and the driver's real-time feedback.

[0134] For example, the basic data collection and preprocessing step may include collecting steering data, vehicle data, and environmental data, and performing certain data processing.

[0135] For example, steering data may include data regarding the driver's steering input, steering angle and steering angle change through a steering angle sensor, steering wheel angular velocity, steering direction (left / right), etc., data regarding the force applied by the driver to the steering wheel and steering intensity through a steering torque sensor, and other data regarding steering restoring force, steering response time, etc.

[0136] For example, the processor can determine whether the driver is turning the steering wheel quickly, moving it slowly, or suddenly releasing the steering wheel through the analysis of steering data. For instance, if steering data is collected showing that the driver turns the steering wheel 30 degrees to the left and the rotation speed is 20 degrees / s, the processor can analyze whether this is an unusual, sudden steering based on this steering data.

[0137] For example, vehicle data may include speed data obtained through a vehicle speed sensor, data regarding whether the speed is low or high, data regarding the vehicle's inclination, yaw / roll / pitch angles, etc. obtained through an IMU (Inertial Measurement Unit) including an accelerometer, gyroscope sensor, etc., and other data regarding acceleration / deceleration patterns, vehicle tilt and lateral acceleration during cornering, etc.

[0138] For example, the processor can determine whether the vehicle is turning a sharp curve or driving at high speed through vehicle data analysis. For instance, the processor can determine that the vehicle is driving at high speed if the vehicle speed data indicates that the vehicle speed is 100 km / h, and based on this, determine that it is necessary to adjust the steering sensitivity sensitively when generating a steering profile or correcting steering control information later.

[0139] For example, environmental data may include data regarding road surface friction force or coefficient of friction (whether it is a wet road, snowy road, or ice), tire slip ratio, etc. through a road surface condition sensor, and data regarding road gradient, weather (rain, snow, etc.) collected using other sensors.

[0140] For example, the processor can determine, through the analysis of environmental data, whether the road is slippery due to a low coefficient of friction or has a high gradient, and based on this, determine that it is necessary to adjust steering response parameters to ensure stable steering when generating a steering profile or correcting steering control information in the future.

[0141] For example, the processor can reflect user feedback, such as changes in steering settings directly adjusted by the driver, and can transmit the collected data to the ECU and cloud server for recording.

[0142] For example, the real-time filtering and outlier removal step may include removing noise by utilizing filtering techniques from vehicle sensors and cloud servers, and removing abnormal data by detecting abnormal and sudden steering changes.

[0143] For example, the processor can perform filtering and outlier removal using Kalman filters, Gaussian smoothing, low-pass filters, etc. For instance, a low-pass filter can be applied to remove noise, and a Kalman filter can be used to correct sensor errors.

[0144] For example, the data pattern analysis step may include analyzing driving patterns over time to classify patterns, adjusting data weights according to driving environments (highways, urban areas, parking lots), and analyzing the correlation between steering patterns and environmental variables.

[0145] The processor can perform a driving style analysis and profiling process that extracts driver characteristics by analyzing collected data using an AI learning model or machine learning algorithm.

[0146] For example, the processor can analyze driving patterns based on driving data. For instance, the processor can identify driving patterns using time-series analysis models, such as LSTM-based neural networks, learn the individual driver's steering style and provide customized steering settings, and analyze the continuous patterns of a specific driver by learning long-term driving data. The results of this driving pattern analysis can then be used to automatically adjust steering accordingly when the driver becomes fatigued or their driving style changes.

[0147] For example, driving patterns or types of driving patterns based on driving pattern analysis can be classified into various categories according to different criteria.

[0148] For example, driving patterns can be extracted and classified into fast steering patterns classified as an agile style, slow steering patterns classified as a stable and cautious style, high-speed steering patterns for styles with low steering sensitivity, and low-speed steering patterns for styles that prefer a sensitive response.

[0149] For example, the processor can perform analysis and learning on driving data using an AI learning model or a machine learning model.

[0150] For example, the processor can perform time series analysis and pattern learning on driving data using an LSTM model.

[0151] As another example, the processor can perform initial clustering based on steering speed and turning angle using a K-means clustering-based model, and by analyzing this in conjunction with vehicle speed, it can distinguish and estimate between sensitive and stable drivers. Furthermore, by using a Support Vector Machine (SVM)-based model to model the non-linear relationship between steering resistance and driving speed, it can perform optimal classification of steering profiles by considering the characteristics of each driver. In addition, clustering models such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN) can also be utilized.

[0152] The processor can perform a personalized profile generation process in which a machine learning model generates a steering profile based on analysis results. For example, the processor can generate a steering profile that includes steering sensitivity to adjust the amount of steering wheel rotation and the ratio of vehicle direction change, feedback intensity to adjust resistance (steering weight) during wheel rotation, neutral restoring force to adjust the magnitude of the force restoring the steering wheel to its original position, and environment-specific responses to dynamic settings for urban, highway, and parking situations.

[0153] For example, the processor can set steering response parameters to suit the driver. For example, the processor can perform personalized adjustments to steering response parameters, including steering sensitivity to adjust the amount of steering wheel rotation and the ratio of wheel direction change, feedback strength to adjust resistance (steering weight) during wheel rotation, and neutral restoring force to adjust the magnitude of the force to restore the steering wheel to its original position.

[0154] For example, the processor can set steering response parameters according to various driving situations, such as high-speed driving, low-speed driving, and sharp curve driving.

[0155] For example, the processor can set steering response parameters in a way that ensures straight-line stability by relatively reducing steering sensitivity and relatively increasing neutral restoring force in high-speed driving situations, such as on a highway.

[0156] For example, in high-speed driving situations, the wheel rotation can be set to respond by only 1 degree for a 5-degree change in steering angle to enhance straight-line stability during highway driving and allow for fine adjustments to be reflected. In this case, a preset algorithm, such as a speed-based steering sensitivity control function, can be applied to enable more stable control.

[0157] For example, the processor can set steering response parameters in a direction that increases steering sensitivity relatively and decreases neutral restoring force relatively in low-speed driving situations such as city driving, thereby ensuring fast responsiveness and reducing the amount of steering wheel operation.

[0158] For example, in low-speed driving situations, the wheel rotation can be set to respond by 3 to 5 degrees for a 5-degree change in steering angle, thereby supporting flexible handling during low-speed driving. In this case, a preset algorithm, such as a steering amplification function at low speeds, can be applied to enable more efficient control.

[0159] In some cases, the processor can set steering response parameters to relatively reduce the steering resistance value during parking situations, even among low-speed driving situations, and enable smoother operation.

[0160] For example, in the case where the user has a driving style that frequently alternates between highways and urban areas, the processor can analyze, during the data collection and analysis process, that the user prefers relatively low steering sensitivity (small steering movement) on highways and prefers fast turning and sensitive responsiveness in urban areas, and during the profile generation process, create a profile based on the above analysis results, for example, setting the vehicle direction to change by 2 degrees for every 10-degree change in the steering wheel angle on highways and by every 10-degree change in the steering wheel angle in urban areas, and during the application process of the generated profile, control can be made so that the steering sensitivity is automatically lowered when the vehicle enters a highway and immediately increased when the vehicle switches to driving in an urban area.

[0161] In this way, the processor can generate and continuously update a dynamic profile that reflects the driver's style while performing a personalized profile generation process, and can generate a steering profile such that customized steering setting parameters for each driver based on machine learning analysis results are applied.

[0162] For example, the processor can perform a profile storage and application process. For instance, the processor can store the generated profile in the vehicle's local memory and on a cloud server, and ensure that the profile is automatically applied when the driver uses the vehicle later. To explain with a more specific example, the processor can provide personalized steering responses according to driving conditions by applying a steering profile, thereby reducing steering sensitivity and increasing stability during highway driving, increasing steering sensitivity and maintaining fast responsiveness during city driving, and enabling smooth steering operation at low speeds during parking.

[0163] For example, the processor can perform a profile update process to improve the steering profile by continuously learning from driving data. For instance, the processor can update the existing steering profile through learning from newly collected driving data. In some cases, the steering profile update may be performed by the driver manually adjusting the settings.

[0164] As such, the present disclosure enables adaptation to driving environments, such as dynamic adjustments based on weather, road conditions, and time of day (night / day), through a configuration that generates a personalized steering profile for each driver based on the collection and analysis of driving data, and applies and updates the profile; supports multi-user, multi-vehicle environments by automatically loading each user profile during vehicle sharing; and provides cloud-based OTA updates to continuously improve algorithms and related processes.

[0165] The processor can perform steering correction control based on the analysis of steering intention. For example, the processor can analyze the driver's steering intention, determine whether steering correction is necessary, and generate a steering correction signal to apply to steering control.

[0166] For example, the processor can analyze the driver's steering intention by analyzing the direction and purpose the driver intends to steer, comparing and analyzing steering speed and angle, and determining whether sudden steering is a risk avoidance or a mistake.

[0167] For example, a processor can analyze the direction and purpose the driver actually intends to steer by recording the driver's steering pattern and comparing the existing steering pattern with the current steering input to determine whether it is sudden steering or normal steering. In this case, the steering pattern can be learned based on artificial intelligence (AI) or machine learning.

[0168] For example, the processor can compare and analyze steering speed and angle by analyzing driving data to determine whether the steering speed and angle resulting from the driver's steering input is abrupt steering (e.g., turning quickly by more than 90°) or continuous fine steering.

[0169] For example, the processor can determine whether sudden steering is a risk avoidance or a mistake by analyzing specific driving situations appearing in the driving data. For instance, if the brakes are applied suddenly along with steering, it can be determined that there is a high probability of risk avoidance; if a driver who usually steers smoothly suddenly steers 90°, it can be determined that there is a high probability of risk avoidance; and if sudden steering wheel movement occurs while driving at high speed, it can be determined that there is a high probability of a mistake and a high risk of an accident, unless there are special circumstances such as detecting a road curve or obstacle ahead.

[0170] For example, the processor can determine whether steering correction is necessary by analyzing the vehicle's steering state and deciding whether to make corrections based on this analysis. In this case, the processor can determine whether steering correction is required by comparing the driver's steering intention with the vehicle state.

[0171] For example, the processor can perform steering control using the initially generated steering control information without steering correction in cases such as when the steering intention and vehicle state are compared and determined to be normal steering, or when the vehicle is reversing at a low speed and steering slowly.

[0172] As another example, the processor may determine that steering correction is necessary in cases where, through the analysis of driving data and steering intentions, it is determined that the vehicle is sliding or that the road is slippery even if it is not, when it is determined that the change in steering angle is abrupt beyond a certain level, or when the driver abruptly rotates the steering wheel while driving at high speed.

[0173] For example, the processor may determine whether steering correction is necessary based on a steering correction necessity determination algorithm. In this case, the steering correction necessity determination algorithm may include logic for determining a risk threshold or risk determination conditions set based on items such as steering speed, vehicle speed, and road surface friction force.

[0174] For example, the risk threshold may include a steering speed threshold for determining whether there is sudden steering, a vehicle speed threshold for determining whether there is high-speed driving, and a road surface friction coefficient threshold for determining whether there is driving on a slippery road. The processor may determine whether steering correction is necessary based on conditions that satisfy at least two or three or more of the above multiple risk thresholds. For example, it may be determined that steering correction is necessary if all of the following conditions are satisfied: a steering speed of 60° / s or more, a vehicle speed of 80 km / h or more, and a road surface friction coefficient of less than 0.4.

[0175] For example, if the processor determines that steering correction is necessary, it can generate a steering correction signal and apply it to steering control. For instance, the processor can generate the steering correction signal by adjusting the electronic steering ratio in a way that relatively reduces steering sensitivity to enhance steering stability during high-speed driving situations, and relatively increases steering sensitivity to enhance the convenience of steering operation during low-speed driving situations.

[0176] In some cases, the processor may perform steering correction control, such as adjusting wheel speed by linking with the ESC (Electronic Stability Control) system along with the generation of a steering correction signal, so that ESC intervention occurs when tire slip is detected. Additionally, separately, if the processor determines that steering correction is necessary, it may generate a strong resistance force on the steering wheel through haptic feedback torque control, or induce steering correction by the driver by causing vibration on the steering wheel, or control the activation of a warning system using a warning light, a warning sound, etc.

[0177] For example, if the processor determines that steering correction is necessary and generates a steering correction signal, it can transmit the corrected steering signal to the steering device. Through this, the steering motor and other components can be controlled according to the corrected steering signal, and the ESC system can be controlled in conjunction. Additionally, depending on the case, the control process based on the corrected steering signal can be monitored in real time to determine whether re-correction is required. For instance, if the wheel rotation angle corresponding to the steering input is re-measured and a difference exceeding a certain threshold occurs despite the control result being based on the corrected steering signal, additional steering correction can be performed.

[0178] The processor can perform adaptive control based on road conditions. For example, the processor can determine the road condition, detect the road surface friction coefficient, and perform adaptive steering control based on real-time driving data.

[0179] For example, the processor can detect the coefficient of friction of the road surface through sensor fusion. For instance, the coefficient of friction of the road surface can be estimated more accurately by fusing sensing data such as road friction sensors inside the tires, cameras mounted on the underside of the vehicle, and LiDAR. In some cases, road conditions, such as whether the road is icy or wet, can be detected using an AI-based road database.

[0180] For example, the processor can correct steering control information based on the road surface friction coefficient. For example, in a dry road driving situation where the road surface friction coefficient is set to 0.7 or higher, the steering of the vehicle can be controlled based on steering control information generated based on basic steering response parameters based on the steering profile. As another example, in a wet road driving situation where the road surface friction coefficient is set to 0.3 or higher and less than 0.7, steering control can be performed to prevent the vehicle from slipping by adjusting the steering sensitivity to be relatively reduced. As yet another example, in an icy road driving situation where the road surface friction coefficient is set to less than 0.3, steering control can be performed to prevent accidents to a higher level by limiting the maximum steering force along with the above steering sensitivity adjustment.

[0181] In this case, a preset algorithm, such as a friction coefficient-based steering correction function, can be applied to enable more accurate and stable control.

[0182] For example, the processor can receive driving data in real time, including speed (V), steering angle (θ), yaw rate, and road surface conditions, and based on this, can perform steering control more precisely by using a feedback-based control algorithm such as PID (Proportional-Integral-Derivative) control. To this end, steering control performance can be improved by optimizing PID parameters based on driving data and the driver's steering type and steering pattern analyzed based on the data.

[0183] For example, the processor can perform adaptive steering control by providing steering assist torque when entering a sharp curve based on road condition data to prevent understeer, and by improving steering stability in high-speed driving situations.

[0184] Below, a steering control method using a steering control device capable of performing all the aforementioned details in the present disclosure is described. Details that overlap with those described above may be omitted depending on the circumstances, but all of them may also be applicable from the perspective of the method below.

[0185] FIG. 4 is a flowchart relating to a steering control method according to one embodiment.

[0186] Referring to FIG. 4, a steering control method (S400) according to one embodiment may include the step of generating a steering profile (S410), the step of generating steering control information (S420), and the step of controlling a steering device (S430).

[0187] For example, a steering control method (S400) may include the steps of generating steering type information of a driver based on driving data of a vehicle using a steering type classification model, extracting steering pattern information from driving data using a pattern extraction model, generating a steering profile for each driver based on the steering type information and steering pattern information, generating steering control information based on the driver's steering profile and steering input, and controlling a steering device according to the steering control information.

[0188] The step of generating a steering profile (S410) may include generating steering type information based on driving data, extracting steering pattern information, and generating a steering profile based on the steering type information and steering pattern information.

[0189] For example, the step of generating a steering profile (S410) may include generating steering type information using a steering type classification model. In this case, the steering type classification model may generate driver's steering type information by determining one of the steering types corresponding to each of a plurality of clusters generated through clustering of driving data.

[0190] For example, the step of generating a steering profile (S410) may include extracting steering pattern information using a pattern extraction model. In this case, the pattern extraction model may extract steering pattern information by performing a time series analysis on the relationship between the driver's steering input and driving data.

[0191] For example, the step of generating a steering profile (S410) may include generating a steering profile for each driver based on steering type information and steering pattern information. In this case, the steering profile may include preset parameters to generate information regarding a steering output corresponding to a steering input.

[0192] For example, the steering profile may include steering response parameters for generating steering control information by applying them to the driver's steering input. In this case, the step of generating the steering profile (S410) may include generating the steering profile such that the steering response parameters are set according to the driving situation.

[0193] For example, the driving situation may be determined based on at least one of steering data, vehicle state data, and driving environment data included in the driving data. In this case, the step of generating a steering profile (S410) may include determining the driving situation based on the vehicle state or the environment around the vehicle that can be identified from the driving data.

[0194] The step of generating steering control information (S420) may include generating steering control information based on a steering profile and a steering input.

[0195] For example, steering control information may include wheel steering control information regarding at what speed and to what position the wheels will be steered, feedback torque control information for assisting steering input at the steering wheel or providing a reaction force, and neutral restoring force control information regarding at what speed and with what strength the steering wheel will be restored to neutral when the steering input is interrupted.

[0196] The step of controlling the steering device (S430) may include controlling the steering device according to steering control information. For example, when there is steering input from the driver, the wheel may be controlled to be steered to a specific position at a specific speed according to steering control information generated based on a steering profile reflecting the driver's steering type and steering pattern; the steering motor may be controlled to generate a feedback torque corresponding to the steering input at the steering wheel; and driver-customized steering control may be performed, such as controlling the steering wheel to return to a neutral position at a specific speed and intensity when the steering input is interrupted.

[0197] In addition, the steering control method according to the present disclosure may control the steering device by using the steering control information generated in the step of generating steering control information as is, but if it is determined that steering correction is necessary in some cases, it may perform correction of the steering control information and control the steering device according to the corrected steering control information.

[0198] Considering these points, Figure 5 below describes a steering control method that includes all the contents of the steering control method (S400) of Figure 4, but further includes a step of correcting the steering control information when it is determined that correction is necessary for the generated steering control information.

[0199] FIG. 5 is a flowchart relating to a steering control method according to another embodiment.

[0200] Referring to FIG. 5, a steering control method (S500) according to another embodiment may include the steps of generating a steering profile (S510), generating steering control information (S520), correcting steering control information (S530), and controlling a steering device (S540).

[0201] In this case, the step of generating a steering profile (S510) and the step of generating steering control information (S520) may include all the contents described in the step of generating a steering profile (S410) and the step of generating steering control information (S420) in the steering control method (S400) described above in FIG. 4.

[0202] In the step of correcting steering control information (S530), it is determined whether correction of steering control information is necessary, and if it is determined that correction is necessary, the steering control information can be corrected.

[0203] To this end, steering control information may be corrected when specific preset conditions are satisfied, or steering control information may be corrected based on an analysis of the driving environment, such as road conditions.

[0204] For example, the step of correcting steering control information (S530) may include comparing the driver's steering input and steering pattern information to determine the driver's steering intention, and correcting the steering control information if it is determined that steering correction is necessary based on the driving situation determined from the steering intention and driving data.

[0205] For example, the step of correcting steering control information (S530) may include determining that the steering intention is a normal steering intention when the steering input is within the normal steering range according to the steering pattern information, and determining whether the steering intention is a danger avoidance intention or a mistake based on the driving situation when the steering input is outside the normal steering range.

[0206] For example, the step of correcting steering control information (S530) may include determining that steering correction is required when a correction threshold condition, which is set differently depending on the steering intention, is satisfied.

[0207] For example, the step of correcting steering control information (S530) may include fusing road sensing data received from at least two sensors to estimate road surface friction coefficient information and correcting steering control information based on road surface friction coefficient information.

[0208] For example, the step of correcting steering control information (S530) may include correcting steering control information based on a relatively reduced steering sensitivity when the road surface friction coefficient information is less than a first threshold friction coefficient, and correcting steering control information based on a reduced steering sensitivity when the road surface friction coefficient information is less than a second threshold friction coefficient which is smaller than the first threshold friction coefficient, but not exceeding a preset maximum steering behavior range.

[0209] The step of controlling the steering device (S540) may include controlling the steering device according to steering control information or corrected steering control information. For example, when there is steering input from the driver, the wheel may be controlled to be steered to a specific position at a specific speed according to the generated steering control information or corrected steering control information, the steering motor may be controlled to generate a feedback torque corresponding to the steering input at the steering wheel, and steering control may be performed such as controlling the steering wheel to return to neutral at a specific speed and intensity when the steering input is interrupted.

[0210] FIG. 6 is a flowchart illustrating, in an exemplary manner, a control information correction step according to one embodiment.

[0211] Referring to FIG. 6, a control information correction step (S530) according to one embodiment may include a friction coefficient estimation step (S610), a first threshold friction coefficient determination step (S620), a steering sensitivity adjustment step (S630), a second threshold friction coefficient determination step (S640), a movement range limiting step (S650), and a steering control information correction step (S660).

[0212] The friction coefficient estimation step (S610) may include estimating the road surface friction coefficient based on sensing data. Additionally, depending on the case, the friction coefficient estimation step (S610) may include estimating road surface friction coefficient information by fusing road sensing data received from at least two sensors.

[0213] For example, the friction coefficient estimation step (S610) can more accurately estimate the road surface friction coefficient by fusing sensing data such as a road surface friction sensor inside the tire, a camera and LiDAR mounted on the underside of the vehicle, and data based on an AI-based road DB.

[0214] The first critical friction coefficient determination step (S620) may include comparing the estimated road surface friction coefficient with the first critical friction coefficient. For example, if the estimated road surface friction coefficient is greater than or equal to the first critical friction coefficient, it is determined that steering correction is not required and the control information correction step (S530) is terminated, and if it is less than the first critical friction coefficient, it is determined that steering correction is required and the steering sensitivity adjustment step (S630) is performed.

[0215] In the steering sensitivity adjustment step (S630), if it is determined that steering correction is required because the estimated friction coefficient is less than the first critical friction coefficient, the steering sensitivity can be adjusted to be relatively reduced.

[0216] For example, if a steering profile is generated for a specific driver and steering control information is generated based on the steering sensitivity in such steering profile, and if it is determined in the first critical friction coefficient determination step (S620) that steering correction is required, the steering sensitivity in the steering profile can be relatively reduced. Then, in the steering control information correction step (S660), the steering control information can be corrected by applying the reduced steering sensitivity to the steering input of the driver.

[0217] The second critical friction coefficient determination step (S640) may include comparing the estimated road surface friction coefficient with the second critical friction coefficient. In this case, the second critical friction coefficient may be set to a value smaller than the first critical friction coefficient.

[0218] For example, if the estimated road surface friction coefficient is greater than or equal to the second critical friction coefficient, it is determined that no additional correction is required except for the correction in the steering sensitivity adjustment step (S630), and the steering control information correction step (S660) is performed immediately; if it is less than the second critical friction coefficient, it is determined that additional steering correction is required, and the movement range limitation step (S650) is performed.

[0219] In the behavior range limiting step (S650), if the estimated friction coefficient is less than the second critical friction coefficient, it may include setting the maximum steering behavior range. By doing so, the behavior range of the steering device can be limited within a certain range, thereby reducing the risk of accidents and improving steering stability.

[0220] It may include correcting steering control information based on reduced steering sensitivity as much as possible, but not exceeding a preset maximum steering behavior range.

[0221] The steering control information correction step (S660) may include performing correction of the steering control information based on the respective comparison results between the estimated road surface friction coefficient and the first critical friction coefficient and the second critical friction coefficient.

[0222] For example, if the estimated road surface friction coefficient is greater than or equal to the first critical friction coefficient, it is determined that correction of the steering control information is not necessary, and thus correction of the steering control information may not be performed.

[0223] As another example, if the estimated road surface friction coefficient is less than the first critical friction coefficient but greater than the second critical friction coefficient, the steering control information can be corrected by applying the steering sensitivity that is relatively reduced in the steering sensitivity adjustment step (S630) instead of the steering sensitivity in the steering profile.

[0224] As another example, if the estimated road surface friction coefficient is less than the second critical friction coefficient which is smaller than the first critical friction coefficient, the steering control information can be corrected by applying a steering sensitivity that is relatively reduced in the steering sensitivity adjustment step (S630) instead of the steering sensitivity in the steering profile, and limiting the result of such application so that it does not exceed the maximum steering behavior range set in the behavior range limiting step (S650).

[0225] FIG. 7 is a flowchart illustrating, by way of example, a control information correction step according to another embodiment.

[0226] Referring to FIG. 7, a control information correction step (S530) according to another embodiment may include a steering intention determination step (S710), a step for determining whether correction is necessary (S720), and a steering control information correction step (S730).

[0227] The steering intention determination step (S710) may include determining the driver's steering intention by comparing the driver's steering input with steering pattern information. For example, if the driver's steering input is determined to be within the normal steering range based on the steering pattern information appearing in the driver's driving data, it may be determined to be a normal steering intention, and if the steering input is determined to be outside the normal steering range, it may be determined not to be a normal steering intention.

[0228] In addition, if the driver's steering input is determined not to be a normal steering intention, it can be determined whether the steering input was made with the intention of avoiding danger or by mistake by considering the driving situation.

[0229] For example, if a sudden steering input is made that deviates from the driver's existing driving pattern beyond a certain level and is judged not to be a normal steering intention, or if a forward obstacle is detected in the driving situation or if the road information indicates a situation requiring a sharp curve, the steering intention may be judged to be an intention to avoid danger, whereas if a sudden steering input is made even though no special circumstances are observed in the driving situation, it may be judged to be due to a mistake.

[0230] In the step of determining whether correction is necessary (S720), the driver's steering intention and the vehicle's driving state are compared, and if it is determined that driving according to the steering intention is not taking place, it can be determined that correction of the steering control information is necessary.

[0231] In addition, depending on the case, in the step of determining whether correction is necessary (S720), it may be determined that steering correction is necessary if the correction threshold condition, which is set differently according to the steering intention, is satisfied.

[0232] In addition, if it is determined in the step for determining whether correction is necessary (S720) that steering correction is not necessary, the control information correction step (S530) can be terminated, and if it is determined that steering correction is necessary, the steering control information correction step (S730) can be performed.

[0233] The steering control information correction step (S730) may include performing correction of the steering control information if it is determined in the correction need determination step (S720) that steering correction is necessary.

[0234] For example, the steering control information correction step (S730) can correct the steering control information regarding the wheel steering angle so that it becomes the wheel steering angle corresponding to the steering input and steering intention when the wheel steering angle corresponding to the driver's steering input and steering intention differs by more than a certain amount.

[0235] As another example, the steering control information correction step (S730) can correct the steering control information regarding the feedback torque so that it becomes the feedback torque corresponding to the steering input and steering intention when there is a difference of more than a certain amount between the feedback torque corresponding to the driver's steering input and steering intention and the feedback torque actually generated.

[0236] FIG. 8 is a flowchart relating to a steering control method according to another embodiment.

[0237] Referring to FIG. 8, a steering control method (S800) according to another embodiment may include a steering input detection step (S810), a vehicle and road condition detection step (S820), a steering intention analysis step (S830), a step for determining whether correction is needed (S840), a steering correction signal generation step (S850), a driver feedback adjustment step (S860), and a steering output step (S870).

[0238] The steering input detection step (S810) may include detecting steering input caused by the driver's steering wheel operation. For example, data such as the steering wheel's rotation angle, rotation speed, and operation intensity may be collected from sensors such as a steering angle sensor and a steering torque sensor.

[0239] The vehicle and road condition detection step (S820) may include collecting and analyzing data regarding the vehicle condition and road condition. For example, data regarding vehicle speed, driving acceleration, road gradient, road surface friction coefficient, tire slip ratio, etc., may be collected using various sensors such as a vehicle speed sensor, IMU, road surface condition sensor, camera, radar, lidar, etc.

[0240] The steering intention analysis step (S830) may include analyzing the driver's steering intention by analyzing the direction and purpose the driver intends to steer, comparing and analyzing the steering speed and angle, and determining whether sudden steering is a risk avoidance or a mistake.

[0241] For example, the steering intention analysis step (S830) may include recording the driver's steering pattern and analyzing the direction and purpose the driver actually intends to steer by comparing the existing steering pattern with the current steering input to determine whether it is sudden steering or normal steering.

[0242] The step of determining whether correction is necessary (S840) can determine whether steering correction is necessary by comparing the driver's steering intention with the vehicle state.

[0243] For example, in cases where the steering intention and the vehicle state are compared and determined to be normal steering, or in cases where the vehicle is reversing at a low speed and steering slowly, the steering output step (S870) can be performed without steering correction.

[0244] For other examples, it may be determined that steering correction is necessary in cases where, through the analysis of driving data and steering intention, it is determined that the vehicle is skidding or that the road is slippery even if it is not, when it is determined that the change in steering angle is abrupt beyond a certain level, or when the driver abruptly rotates the steering wheel while driving at high speed.

[0245] The steering correction signal generation step (S850) may include generating a steering correction signal when it is determined that steering correction is necessary. For example, if it is determined that steering correction is necessary in a high-speed driving situation, the steering correction signal may be generated in a direction that relatively reduces the steering sensitivity, and if it is determined that steering correction is necessary in a low-speed driving situation, the steering sensitivity may be relatively increased.

[0246] The driver feedback adjustment step (S860) can prevent unnecessary steering by generating a relatively higher feedback torque from the steering motor when it is determined that steering correction is necessary.

[0247] In addition, separately, in the driver feedback adjustment step (S860), if it is determined that steering correction is necessary, feedback can be provided to the driver indicating the need for steering correction by causing vibration in the steering wheel to induce steering correction by the driver, or by activating a warning system using a warning light, a warning sound, etc.

[0248] The steering output step (S870) may include applying the initially generated steering signal to the wheel if it is determined in the correction need determination step (S840) that correction is not necessary, and applying the steering correction signal to the wheel if it is determined that correction is necessary, thereby finally performing steering. Through this, the steering actuator moves the wheel, and the vehicle can be steered in the direction intended by the driver.

[0249] As described above, the present disclosure can provide a control device and a method capable of performing steering control such that steering output and feedback in a steering device are provided in accordance with the driver and driving conditions.

[0250] The devices, methods, configurations, glyphs, and operations described herein may be implemented in digital electronic circuits, or computer software, firmware, or hardware comprising structures disclosed herein and structural equivalents, or combinations of one or more of these. The glyphs described herein may be implemented as one or more computer programs, for example, as one or more modules of computer program instructions encoded on a computer storage medium to control execution by a data processing device or operation by a data processing device. Program instructions may be encoded in artificially generated propagated signals, for example, mechanically generated electrical, optical, or electromagnetic signals generated to encode information for transmission to a suitable receiver device for execution by a data processing device. The computer storage medium may be or may include a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of these. Although the computer storage medium is not a propagated signal, the computer storage medium may be a source or destination of computer program instructions encoded in an artificially generated propagated signal. Additionally, a computer storage medium may be one or more individual physical components or media (e.g., multiple CDs, disks, or other storage devices) or may include. The operations described herein may be implemented as operations performed by a data processing device on data stored in one or more computer-readable storage devices or data received from other sources.

[0251] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain rather than limit the technical concept of the present disclosure, the scope of the technical concept is not limited by these embodiments.

Claims

Claim 1 A steering control device comprising: at least one memory including computer program instructions; and at least one processor for executing said computer program instructions, wherein the at least one processor generates steering type information of a driver based on driving data of a vehicle using a steering type classification model, extracts steering pattern information from said driving data using a pattern extraction model, generates a steering profile for each driver based on said steering type information and steering pattern information, and controls a steering device according to steering control information generated based on said steering profile and steering input of said driver. Claim 2 In claim 1, the steering type classification model is determined as one of the steering types corresponding to each of the plurality of clusters generated through clustering of the driving data, thereby generating steering type information of the driver, and is a steering control device. Claim 3 In claim 1, the pattern extraction model is a steering control device that extracts steering pattern information by performing a time series analysis on the relationship between the driver's steering input and the driving data. Claim 4 In claim 1, the steering profile includes steering response parameters for generating steering control information by applying to the steering input of the driver, and the processor is a steering control device that generates the steering profile such that the steering response parameters are set according to driving conditions. Claim 5 In paragraph 4, the driving situation is a steering control device determined based on at least one of steering data, vehicle state data, and driving environment data included in the driving data. Claim 6 A steering control device according to claim 1, wherein the processor determines the steering intention of the driver by comparing the driver's steering input and steering pattern information, and corrects the steering control information when it is determined that steering correction is necessary based on the steering intention and the driving situation determined from the driving data. Claim 7 A steering control device according to claim 6, wherein the processor determines that the steering intention is a normal steering intention when the steering input is within a normal steering range according to the steering pattern information, and determines whether the steering intention is a danger avoidance intention or a mistake based on the driving situation when the steering input is outside the normal steering range. Claim 8 In claim 6, the above processor is a steering control device that determines that steering correction is required when a correction threshold condition, which is set differently according to the steering intention, is satisfied. Claim 9 In claim 1, the processor fuses road sensing data received from at least two sensors to estimate road surface friction coefficient information, and the steering control device corrects the steering control information based on the road surface friction coefficient information. Claim 10 In claim 9, the steering control device wherein the processor corrects the steering control information based on a relatively reduced steering sensitivity when the road surface friction coefficient information is less than a first critical friction coefficient, and corrects the steering control information based on the reduced steering sensitivity when the road surface friction coefficient information is less than a second critical friction coefficient which is smaller than the first critical friction coefficient, so as not to exceed a preset maximum steering behavior range. Claim 11 A steering control method comprising: a step of generating steering type information of a driver based on driving data of a vehicle using a steering type classification model, extracting steering pattern information from the driving data using a pattern extraction model, and generating a steering profile for each driver based on the steering type information and steering pattern information; a step of generating steering control information based on the steering profile and steering input of the driver; and a step of controlling a steering device according to the steering control information. Claim 12 A steering control method according to claim 11, wherein the steering type classification model is determined as one of the steering types corresponding to each of the plurality of clusters generated through clustering of the driving data to generate steering type information of the driver. Claim 13 In claim 11, the pattern extraction model is a steering control method that extracts steering pattern information by performing a time series analysis on the relationship between the driver's steering input and the driving data. Claim 14 In claim 11, the steering profile includes steering response parameters for generating steering control information by applying to the steering input of the driver, and the step of generating the steering profile includes generating the steering profile such that the steering response parameters are set according to driving conditions. Claim 15 In claim 14, the driving situation is a steering control method determined based on at least one of steering data, vehicle state data, and driving environment data included in the driving data. Claim 16 A steering control method according to claim 11, further comprising the step of determining the steering intention of the driver by comparing the driver's steering input and steering pattern information, and correcting the steering control information when it is determined that steering correction is necessary based on the steering intention and the driving situation determined from the driving data. Claim 17 A steering control method according to claim 16, wherein the step of correcting the steering control information comprises determining that the steering intention is a normal steering intention when the steering input is within a normal steering range according to the steering pattern information, and determining whether the steering intention is a danger avoidance intention or a mistake based on the driving situation when the steering input is outside the normal steering range. Claim 18 A steering control method according to claim 16, wherein the step of correcting the steering control information comprises determining that steering correction is required when a correction threshold condition, which is set differently according to the steering intention, is satisfied. Claim 19 A steering control method according to claim 11, further comprising the step of fusing road sensing data received from at least two sensors to estimate road surface friction coefficient information and correcting steering control information based on said road surface friction coefficient information. Claim 20 A steering control method according to claim 19, wherein the step of correcting the steering control information comprises correcting the steering control information based on a relatively reduced steering sensitivity when the road surface friction coefficient information is less than a first critical friction coefficient, and correcting the steering control information based on the reduced steering sensitivity but not exceeding a preset maximum steering behavior range when the road surface friction coefficient information is less than a second critical friction coefficient that is smaller than the first critical friction coefficient.

Images