Vehicle side control system with adjustable parameters

Abstract

This disclosure relates to a vehicle lateral control system with adjustable parameters. The system includes a controller circuit that receives identity data indicating the driver's identity from a driver monitoring sensor. The controller circuit receives vehicle lateral response data from vehicle sensors based on steering maneuvers performed by the vehicle under driver control. The controller circuit determines lateral steering parameters of the vehicle based on the lateral response data. The controller circuit adjusts lateral control parameters of the vehicle based on the lateral steering parameters. The controller circuit associates the adjusted lateral control parameters of the vehicle with the driver's identity. The controller circuit operates the vehicle according to the lateral control parameters associated with the driver's identity. When the vehicle operates in autonomous driving mode, the system can reproduce the driver's steering behavior.

Description

Background Technology

[0001] The Society of Automotive Engineers (SAE) defines Level 2 automated driving systems as including driver assistance features that provide steering, braking, and acceleration assistance (e.g., lane centering and adaptive cruise control). Vehicles equipped with Level 2 automated driving systems require a human driver to be ready to take over control when the automated system relinquishes control. The factory settings for the lateral control parameters of the automated driving system are calibrated based on the assumption that the driver will find the steering maneuvers performed by the system in automated mode comfortable. However, some drivers may find the factory-set automated steering maneuvers unnatural, too aggressive for traffic conditions, or not aggressive enough for their preferences. Therefore, some drivers may deactivate automated mode, which can lead to reduced vehicle safety. Summary of the Invention

[0002] This document describes one or more aspects of a vehicle lateral control system with adjustable parameters. In one example, the system includes controller circuitry configured to receive identity data indicating the identity of the vehicle's driver from driver monitoring sensors. The controller circuitry receives vehicle lateral response data from one or more vehicle sensors based on steering maneuvers performed by the vehicle under driver control. The controller circuitry determines multiple lateral steering parameters of the vehicle based on the vehicle lateral response data. The controller circuitry adjusts the vehicle's lateral control parameters based on the multiple lateral steering parameters. The controller circuitry associates the adjusted vehicle lateral control parameters with the driver's identity. The controller circuitry operates the vehicle according to the lateral control parameters associated with the driver's identity.

[0003] In another example, a method includes: receiving identity data indicating the identity of a driver of a vehicle from a driver monitoring sensor using controller circuitry. The method includes: receiving vehicle lateral response data based on steering maneuvers performed by the vehicle under the driver's control from one or more vehicle sensors using controller circuitry. The method includes: determining multiple lateral steering parameters of the vehicle based on the vehicle lateral response data using controller circuitry. The method includes: adjusting lateral control parameters of the vehicle based on the multiple lateral steering parameters using controller circuitry. The method includes: associating the adjusted vehicle lateral control parameters with the driver's identity. The method includes: operating the vehicle using controller circuitry according to the lateral control parameters associated with the driver's identity.

[0004] This invention provides a summary of various aspects of a vehicle lateral control system with adjustable parameters, which is further described in the following detailed description and accompanying drawings. For ease of description, this disclosure focuses on vehicle-based or automobile-based systems, such as those integrated into vehicles traveling on roads. However, the techniques and systems described herein are not limited to vehicle or automobile scenarios, but are applicable to other environments in which sensors can be used to determine the dynamics of a moving subject. This summary is not intended to identify essential features of the claimed subject matter, nor is it intended to define the scope of the claimed subject matter. Attached Figure Description

[0005] The following figures illustrate in detail one or more aspects of a vehicle lateral control system with adjustable parameters. The same numbers are used throughout the figures to refer to similar features and components:

[0006] Figure 1 An example of a vehicle lateral control system with adjustable parameters, shown as being installed on a vehicle, is illustrated according to the technology of this disclosure;

[0007] Figure 2 It shows the relationship with Figure 1 An example of an isolated driver monitoring sensor in a vehicle lateral control system with adjustable parameters;

[0008] Figure 3 It shows Figure 1 An example of a vehicle sensor in a vehicle lateral control system with adjustable parameters;

[0009] Figure 4 It shows a camera with the driver facing it. Figure 1 An example of a vehicle lateral control system with adjustable parameters;

[0010] Figure 5 It shows Figure 4 An example of data flow from a vehicle lateral control system with adjustable parameters;

[0011] Figure 6 An example of vehicle lateral response data of a vehicle traveling on a road according to the technology of this disclosure is shown;

[0012] Figure 7 It shows Figure 4 Examples of lateral steering parameters and lateral control parameters of a vehicle lateral control system with adjustable parameters;

[0013] Figure 8 It shows Figure 4An example of a human-machine interface (HMI) for a vehicle lateral control system with adjustable parameters;

[0014] Figure 9 It shows Figure 4 Another example of a human-machine interface (HMI) for a vehicle lateral control system with adjustable parameters;

[0015] Figure 10 It shows Figure 4 Another example of a human-machine interface (HMI) for a vehicle lateral control system with adjustable parameters;

[0016] Figure 11 A flowchart illustrating example lateral control parameters adjusted based on HMI inputs, according to the technology of this disclosure;

[0017] Figure 12 yes Figure 1 An example logic flow for a vehicle lateral control system with adjustable parameters; and

[0018] Figure 13 It is an operation Figure 1 An example method for a vehicle lateral control system with adjustable parameters. Detailed Implementation

[0019] Overview

[0020] This disclosure relates to a vehicle lateral control system with adjustable parameters. When a driver is operating the vehicle in manual driving mode, the controller circuitry receives data from in-cabin sensors indicating the driver's identity. The system learns the driver's steering habits or behaviors that affect the vehicle's lateral response, such as the aggressiveness of the driver's steering into and out of curves, or the degree of aggression in positioning the vehicle relative to lane markings and adjacent vehicles. The system associates or matches the learned steering behaviors with the driver's identity and adjusts the lateral control parameters used to control the vehicle when operating it in autonomous driving mode. The system can store the adjusted lateral control parameters for different drivers in memory and recall the adjusted parameters when the system identifies the driver. The driver can further adjust the aggressiveness of the lateral control parameters by inputting preferences into a human-machine interface (HMI) that can be presented to the driver on the vehicle's console display. The HMI may include preset and adjustable options related to lane bias and corner-cutting in curves. A vehicle lateral control system with adjustable parameters can improve the comfort of the driver and passengers by reproducing the driver's steering behavior when the vehicle is operating in autonomous driving mode, thereby improving the user experience.

[0021] Example System

[0022] Figure 1 An example of a vehicle lateral control system 100 with adjustable parameters is shown, hereinafter referred to as system 100. System 100 includes controller circuitry 102 configured to receive identity data 104 indicating the identity of the driver of vehicle 108 from driver monitoring sensor 106. Driver monitoring sensor 106 may be a component of occupant monitoring system 110 (OMS 110) mounted on vehicle 108, which monitors some or all occupants or passengers within the vehicle cabin. Controller circuitry 102 receives vehicle lateral response data 112 based on steering maneuvers performed when vehicle 108 is operated under the control of the driver (e.g., when the driver steers the vehicle on a road and performs various turns or lane changes). Vehicle lateral response data 112 is received from vehicle sensor 114, which directly or indirectly detects or measures the lateral motion or lateral acceleration of vehicle 108. For example, the difference between the wheel speeds detected by the left wheel speed sensor and the right wheel speed sensor can indirectly indicate that the vehicle 108 is turning, compared to a yaw rate sensor that directly measures the angular rotation of the vehicle 108.

[0023] The controller circuit 102 can determine a lateral steering parameter 116 based on the vehicle's lateral response data 112, which can be used to adjust or modify the lateral control parameters 118 of the vehicle 108. The lateral steering parameter 116 represents the processing of the raw vehicle lateral response data 112 and can be more easily used by the controller circuit 102 to match the driver's steering behavior when the vehicle 108 is operated in autonomous driving mode. The lateral control parameters 118 of the vehicle 108 are calibrable or adjustable parameters that can be interpreted by the vehicle control 120 to control the steering, braking, and acceleration of the vehicle 108.

[0024] The controller circuit 102 can adjust the lateral control parameters 118 of the vehicle 108 and associate the adjusted lateral control parameters 118 with the driver's identity stored in the memory of the controller circuit 102. When the vehicle 108 is operating in autonomous driving mode and the driver is identified or recognized while sitting in the driver's seat, the controller circuit 102 can retrieve the adjusted lateral control parameters 118 for a specific driver from the memory.

[0025] Although vehicle 108 can be any vehicle, for ease of description, vehicle 108 is primarily described as an autonomous vehicle configured to operate in an autonomous driving mode to assist the driver of vehicle 108. Vehicle 108 is capable of SAE Level 2 autonomous operation (as referred to in the background art), which assists the driver in steering, braking, and acceleration, while the driver constantly monitors the operation of vehicle 108 from the driver's seat.

[0026] exist Figure 1 In the example shown, controller circuitry 102 is mounted on vehicle 108 and communicatively coupled to driver monitoring sensor 106, vehicle sensor 114, and vehicle controls 120 via a transmission link. The transmission link can be a wired or wireless interface, for example, Near Field Communication (NFC), Universal Serial Bus (USB), Universal Asynchronous Receiver / Transmitter (UART), or Controller Area Network (CAN). In some examples, controller circuitry 102 receives data from other vehicle systems via a CAN bus (not shown), such as ignition status and transmission gear selection.

[0027] Controller circuit

[0028] The controller circuit 102 may be implemented as a microprocessor or other control circuitry system (such as analog and / or digital control circuitry systems). The control circuitry system may include one or more application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) programmed to execute technology, or one or more general-purpose hardware processors programmed to execute technology according to program instructions in firmware, memory, other storage, or a combination thereof. The controller circuit 102 may also combine custom hardwired logic, ASICs, or FPGAs with custom programming to execute technology. The controller circuit 102 may include memory or storage media (not shown), including non-volatile memory such as electrically erasable programmable read-only memory (EEPROM) for storing one or more routines, thresholds, and captured data. The EEPROM stores data and allows individual bytes to be erased and reprogrammed by applying programming signals. Other examples of non-volatile memory that the controller circuit 102 may include are flash memory, read-only memory (ROM), programmable read-only memory (PROM), and erasable programmable read-only memory (EPROM). Controller circuitry 102 may include volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM)). Controller circuitry 102 may include one or more clocks or timers for synchronizing the control circuitry system or determining the elapsed time of events. One or more routines may be executed by a processor to perform steps for operating vehicle 108 based on signals received by controller circuitry 102 from driver monitoring sensor 106 and vehicle sensor 114, as described herein.

[0029] Driver monitoring sensors

[0030] Figure 2 An example of a driver monitoring sensor 106 located remotely from system 100 is shown. Driver monitoring sensor 106 is configured to monitor the driver of vehicle 108, as will be described in more detail below. Driver monitoring sensor 106 may include one or more sensors that detect various aspects of the driver and may be a component of OMS 110 mounted on vehicle 108. Driver monitoring sensor 106 may include a camera that captures an image of the driver, and OMS 110 determines whether the driver's seat is occupied based on the image. The camera may be a two-dimensional (2D) camera 106-1 or a 3D time-of-flight camera 106-2, the 3D time-of-flight camera 106-2 measuring the time it takes for a light pulse to leave the camera and reflect back onto the camera's imaging array.

[0031] The software executed by OMS 110 can use known image analysis techniques to distinguish between humans, animals, and objects. Objects in the image are detected in regions of interest corresponding to seating positions within the cabin (e.g., the driver's seat position), and the software categorizes the objects as humans and other categories. Processing blocks or models in the software are pre-trained to recognize the shapes of human forms or other objects (e.g., shopping bags, boxes, or animals).

[0032] The driver monitoring sensor 106 may also include a steering wheel torque sensor 106-3, which detects the torque applied to the steering wheel. The torque can be detected when the driver places their hands on the steering wheel, even when the autonomous control system steers the vehicle 108. The steering wheel torque sensor 106-3 may be an electromechanical device integrated into the power steering system of the vehicle 108, determining the torsion bar angle required for steering movement. The steering wheel torque sensor 106-3 may also output the rate of change of the steering angle and the steering wheel angular position.

[0033] The driver monitoring sensor 106 may also include a seat pressure sensor 106-4, which detects pressure or pressure distribution applied to the seat (similarly, a steering wheel pressure sensor may be used to detect pressure or pressure distribution applied to the steering wheel by the driver's hands). The OMS 110 may determine whether the driver is occupying the driver's seat (or gripping the steering wheel) based on a pressure threshold indicating the driver's weight (or the force applied by gripping the steering wheel). For example, if the occupant's weight is greater than 30 kg, the OMS 110 may determine that the driver is an adult. The pressure distribution may indicate whether the object occupying the driver's seat is a person or something other than a person. The pressure distribution may also indicate whether the driver is in the correct position within the driver's seat; for example, when the driver leans to one side of the seat, pressure is concentrated on that side.

[0034] The driver monitoring sensor 106 may also include a capacitive steering wheel sensor 106-5 that detects the driver's hand touching the steering wheel. The capacitive steering wheel sensor 106-5 may be located on the edge of the steering wheel and can detect the point of contact between the hand and the steering wheel. In some examples, touching the steering wheel with a hand distorts the electric field generated by the sensor and changes the sensor's capacitance, thereby indicating the presence of the driver's hand. The capacitive steering wheel sensor 106-5 can detect whether the driver has one or both hands on the steering wheel.

[0035] The driver monitoring sensor 106 may also include a radar sensor 106-6, which detects the presence of objects in the vehicle compartment. The OMS 110 can determine whether the driver's seat is occupied by a driver or an object based on point cloud data received from the radar sensor 106-6, and can monitor whether the driver's hands are on the steering wheel. The OMS 110 compares this point cloud data with a model in the software to determine whether the seat is occupied by a person or an object. In some examples, the radar sensor 106-6 can detect relatively small movements, such as the movement of the chest wall of a breathing driver (e.g., a child in a car seat).

[0036] The driver monitoring sensor 106 may also include a microphone 106-7 for detecting the driver's voice, and the OMS 110 may use voice recognition software to process the voice recording to determine the unique identifying features of the driver's voice. The microphone 106-7 may be a component of the infotainment system of the vehicle 108.

[0037] The driver monitoring sensor 106 may also include a capacitive fingerprint sensor 106-8 for detecting the driver's fingerprint, and the OMS 110 may use fingerprint recognition software to process the fingerprint to determine the unique identifying features of the detected fingerprint of the driver.

[0038] The OMS 110 and controller circuit 102 can use machine learning to detect various driver aspects and steering behaviors. Machine learning is a data analysis technique that teaches computers to learn from experience. Machine learning routines or algorithms use computational methods to learn information from data without relying on predetermined equations as models. As the amount of samples available for learning increases, the routines improve their performance. Machine learning uses two types of techniques: supervised learning, which trains a model on known input and output data so that it can predict future outputs; and unsupervised learning, which discovers hidden patterns or intrinsic structures in the input data.

[0039] Supervised learning uses classification and regression techniques to develop predictive models. Common algorithms used to perform classification include Support Vector Machines (SVM), boosted and bagged decision trees, k-nearest neighbors, and Naive Bayes. Bayesian regression, discriminant analysis, logistic regression, and neural networks are commonly used regression algorithms, including linear models, nonlinear models, regularization, stepwise regression, augmented and bagged decision trees, neural networks, and adaptive neurofuzzy learning. Unsupervised learning discovers hidden patterns or intrinsic structures in data and is used to derive inferences from datasets consisting of input data with unlabeled responses. Clustering is a commonly used unsupervised learning technique. Common algorithms used to perform clustering include k-means and K-centroid methods, hierarchical clustering, Gaussian mixture models, hidden Markov models, self-organizing maps, fuzzy c-means clustering, and subtractive clustering. In the context of autonomous vehicles, the OMS 110 and controller circuitry 102 can specifically utilize machine learning to determine the driver's identity or other aspects of driving behavior based on driver monitoring sensors 106 or the vehicle's lateral response data 112 fed by the vehicle, ensuring that the controller circuitry 102 can accurately determine the lateral steering parameters 116.

[0040] Vehicle sensors

[0041] Figure 3 An example of a vehicle sensor 114 located remotely to system 100 is shown. The vehicle sensor 114 may include an inertial measurement unit (IMU) 114-1, a steering angle sensor 114-2, a vehicle speed sensor 114-3, a positioning sensor 114-4, an externally facing camera 114-5, and a range sensor 114-6.

[0042] IMU 114-1 is an electronic device for detecting the relative motion of vehicle 108 and may include the yaw rate, longitudinal acceleration, lateral acceleration, pitch rate, and roll rate of vehicle 108. IMU 114-1 can use a combination of accelerometers and gyroscopes to detect the relative motion of the vehicle and may be a component of a dynamic control system mounted on vehicle 108.

[0043] As described above, the steering angle sensor 114-2 can be a component of the steering wheel torque sensor 106-3, which outputs the rate of change of steering angle and steering wheel angular position.

[0044] The vehicle speed sensor 114-3 may be a rotation sensor (e.g., a wheel speed sensor), where the signal can also be used to operate the speedometer of the vehicle 108. The vehicle speed sensor 114-3 may also use data from a Global Navigation Satellite System (GNSS), which may be a component of a navigation system (e.g., a Global Positioning System (GPS) that determines speed based on changes in the position of the vehicle 108) installed on the vehicle 108.

[0045] Positioning sensor 114-4 can be GNSS. GNSS refers to a constellation of satellites that transmit signals from space, providing positioning and timing data to a GNSS receiver located on vehicle 108. The receiver then uses this data to determine the location of vehicle 108. GNSS provides positioning, navigation, and timing services on a global or regional basis. GPS, BeiDou, Galileo and GLONASS, IRNSS, and QZSS are examples of GNSS systems operated by the United States, the People's Republic of China, the European Union, India, and Japan, respectively.

[0046] The externally facing camera 114-5 may be a camera that captures images of the road on which the vehicle 108 travels or objects near the vehicle 108. The images may include lane markings defining the road or driving lanes and the boundaries of other vehicles. The controller circuit 102 may use software to classify and identify objects in the images.

[0047] The ranging sensor 114-6 can be a radar sensor, a lidar (LiDAR) sensor, or an ultrasonic sensor that detects objects approaching the vehicle 108. These sensors can be components of an advanced driver assistance system (ADAS) that can be mounted on the vehicle 108. Radar sensors use radio frequency (RF) signals to detect objects and can determine distance based on the time it takes to send and receive reflected RF signals or the travel time of the RF signals. Radar sensors can also detect object motion based on phase changes in reflected RF signals known as the Doppler effect. LiDAR sensors operate similarly to radar sensors but instead use laser pulses to detect objects and distance based on the travel time of the laser pulses and the Doppler effect. Ultrasonic sensors use the travel time of sound waves to detect objects and distance.

[0048] Image-based identification

[0049] Figure 4 An example of a system 100 with a driver-facing 2D camera 106-1 for capturing driver images is shown. The 2D camera 106-1 is configured to detect identifying features of the driver's face in a vehicle 108. For example, the 2D camera 106-1 detects driver-specific features that can be used to distinguish the driver from other passengers in the vehicle 108 or other drivers operating the vehicle 108.

[0050] The 2D camera 106-1 can capture an image of the driver's face, and the OMS 110 can process this image to determine one or more facial features unique to the driver. The OMS 110 can use facial recognition technology, which involves storing a digital image of the driver's face in the OMS 110's memory. Facial recognition technology enables the OMS 110 to accurately pinpoint and measure facial features captured from the image, such as the distance between two features (e.g., the two parts of the mouth, the two ears, the two eyes, the centers of the two pupils), the position of features (e.g., the arrangement of the nose relative to other facial features), or the shape of features (e.g., the face, eyebrows, jawline). These measured facial features can be determined by the OMS 110 and retained in the OMS 110's memory for subsequent use by the system 100, as will be explained in more detail below. OMS 110 can identify and store the identities of multiple drivers, and the identity data 104 from OMS 110 can be periodically updated by OMS 110 to ensure that the controller circuit 102 can accurately associate the driver's identity with the adjusted lateral control parameters 118. For example, OMS 110 can update the identity data 104 at ten-second intervals to take into account changes in the driver during parking.

[0051] Driver steering behavior learning

[0052] Figure 5 This is a flowchart 500 illustrating an example of the type of vehicle lateral response data 112 that can be used by system 100 to learn the driver's steering behavior. Figure 5 The data stream from the vehicle sensor that provides the lateral steering parameter 116 is shown.

[0053] At point 502, when the vehicle is started, the system uses a 2D camera 106-1 to identify the driver, as described above. Figure 4 As shown in the diagram. At 504, controller circuitry 102 determines whether data from vehicle sensor 114 is available. At 506, if data from vehicle sensor 114 is unavailable, system 100 delays the learning process and defaults to the factory-installed lateral control parameters 118. The factory-installed lateral control parameters 118 are initial lateral control parameters 118 that are not associated with driver identity. If data from vehicle sensor 114 is available, system 100 continues the learning process, as will be described in more detail below.

[0054] Figure 6The illustration shows a vehicle 108 traveling in a lane indicated by lane markings on the left and right sides of the vehicle 108. In this example, the centerline of the lane is determined by a forward-facing camera based on an image of the lane markings. Vehicle lateral response data 112 includes a lateral track error 112-1 relative to the lane centerline, a heading error 112-2 relative to a reference point or look-ahead point 122, and road curvature 112-3, which are detected by an outward-facing camera 114-5 or a positioning sensor 114-4. The lateral track error 112-1 indicates the difference between the coordinate center 124 of the vehicle 108 and the nearest point on the centerline of the lane. Figure 6 In the example shown, the coordinate center 124 of vehicle 108 is the point at the center of the front bumper. In this example, a positive lateral trajectory error 112-1 indicates that the coordinate center 124 of vehicle 108 is located to the right of the centerline of the driving lane, and a negative lateral trajectory error 112-1 indicates that the coordinate center 124 is located to the left of the centerline. The lateral trajectory error 112-1 can be measured in units of distance detected by the outward-facing camera 114-5 or by the positioning sensor 114-4. The road curvature 112-3 is defined as the reciprocal of the radius of curvature of the road and can be determined by the position of the forward-facing camera or the position from the positioning sensor 114-4 relative to a digital map including data on the road curvature 112-3.

[0055] exist Figure 6 In the example shown, heading error 112-2 indicates the deviation of the heading 126 or pointing direction of vehicle 108 relative to a reference point or look-ahead point 122 on the centerline of the driving lane ahead of vehicle 108. In some examples, heading error 112-2 indicates the deviation between the orientation of vehicle 108 and the tangent vector of the centerline of the driving lane. Heading error 112-2 can be measured in degrees, and a heading error of zero degrees 112-2 indicates that the driver is turning vehicle 108 directly toward look-ahead point 122. The distance between the vehicle coordinate center 124 and look-ahead point 122 is look-ahead distance 128, and controller circuitry 102 can change look-ahead distance 128 based on road curvature 112-3. For example, as road curvature 112-3 decreases and approaches a straight road, controller circuitry 102 can increase look-ahead distance 128 because the steering correction required to keep vehicle 108 centered is less than on roads with sharper curves or greater road curvature 112-3.

[0056] Return to reference Figure 5The vehicle lateral response data 112 may also include a turning reaction time 112-4, which can be determined based on road curvature 112-3, vehicle speed from vehicle speed sensor 114-3, and yaw rate from IMU 114-1. The turning reaction time 112-4 indicates the driver's steering response when entering a curve from a straight section of road or when encountering a change in road curvature.

[0057] At point 508, controller circuit 102 compares the road curvature rate with the turning rate or yaw rate of vehicle 108 to determine the turning reaction time 112-4. The road curvature rate can be calculated by controller circuit 102 by multiplying the road curvature 112-3 by the speed of vehicle 108. Controller circuit 102 can subtract the yaw rate from the road curvature rate and compare the result with a threshold to determine whether the driver has steered the vehicle in response to the changing road curvature 112-3. For example, a driver steering vehicle 108 traveling at 14 meters per second (m / s) or approximately 50 kilometers per hour (km / h) into a curve with a curvature radius of 100 meters (e.g., a road curvature of 0.01 / m) would need to turn vehicle 108 at a rate of approximately 0.14 radians / s to follow the road. If the yaw rate is close to zero (indicating that the driver has not turned vehicle 108), the difference between the road curvature rate and the yaw rate will be 0.14 radians / s. The controller circuit 102 can determine the turning reaction time 112-4 by recording the time when the vehicle 108 should turn based on the road curvature rate and the actual turning time based on the vehicle 108's yaw rate. The controller circuit 102 can compare the turning reaction time 112-4 to a threshold indicating that the driver has steered the vehicle 108 to follow the curve when the turning reaction time 112-4 falls below the threshold. This threshold can be user-defined and can vary with the vehicle's speed.

[0058] The vehicle lateral response data 112 may also include road curvature 112-5 and lane change time 112-6 during lane change. Road curvature 112-5 during lane change can be used to determine the driver's preference for lane change maneuvers based on road curvature 112-3. For example, one driver may feel comfortable changing lanes on a sharp curve, while another driver may feel uncomfortable changing lanes on any curved road (regardless of curvature). Lane change time 112-6 is the time it takes for the driver to move the vehicle 108 from its current lane to an adjacent lane. Controller circuitry 102 can determine the timing of the lane change using lateral velocity derived from lateral acceleration received from IMU 114-1, and can use a vehicle turn signal as a trigger for the calculation. For example, when the driver activates a turn signal to indicate a future lane change, at 510, controller circuitry 102 can integrate or sum the lateral distance traveled by the vehicle 108 based on the signal received from IMU 114-1. At point 512, controller circuit 102 determines whether the lateral distance traveled by vehicle 108 matches the lane width. If the lateral distance traveled by vehicle 108 does not match the lane width, controller circuit 102 continues to integrate the lateral distance until vehicle 108 has traveled a lateral distance close to the lane width. Controller circuit 102 can use the result of this lateral distance integration to determine the road curvature 112-5 and lane change time 112-6 during a lane change.

[0059] The vehicle lateral response data 112 may also include lateral distances 112-7 to adjacent vehicles. The controller circuitry 102 may use data from the ranging sensor 114-6 or the externally facing camera 114-5 to determine the distances between the vehicle 108 and adjacent vehicles while the driver is traveling on the road. The controller circuitry 102 may use the lateral distances 112-7 to adjacent vehicles to determine lane offset parameters, as will be described below.

[0060] Lateral steering parameters

[0061] Refer again Figure 5The controller circuit 102 processes raw vehicle lateral response data 112 to determine several lateral steering parameters 116, including root mean square (RMS) lane offset 116-1, mean lateral trajectory error 116-2, RMS heading error 116-3, RMS turning reaction time 116-4, tangent percentage 116-5, minimum road curvature for enabling lane change 116-6, and RMS lane change time 116-7. In this example, the controller circuit 102 uses the RMS technique, or the square root of the arithmetic mean of the squares of the individual data values, to process the large amount of vehicle lateral response data 112. The processed vehicle lateral response data 112 reduces the computational load on the controller circuit 102, which could potentially be excessive if only the raw vehicle lateral response data 112 were used instead of the lateral steering parameters 116. Other techniques for processing the raw data, such as the arithmetic mean or moving average of the data points, could be used. RMS is used to process data for certain parameters because it provides a sense of the magnitude of the numbers in the dataset without negative values ​​offsetting positive values, which can happen when using the arithmetic mean. Therefore, RMS can be equal to or slightly greater than the arithmetic mean.

[0062] Return to reference Figure 5 At point 514, controller circuit 102 determines whether the average lateral trajectory error 116-2 is positive or negative, and further determines the overshoot or undershoot percentage 116-5, where a positive value indicates overshoot or the steering path deviates from the outside of the curve, and a negative value indicates undershoot or the steering path deviates from the inside of the curve. Controller circuit 102 can determine the percentage of overshoot or undershoot based on the average lateral trajectory error 116-2 and half the lane width.

[0063] At 516, controller circuit 102 determines whether the driver has performed a sufficient number of steering maneuvers for system 100 to learn the driver's steering behavior, and if so, moves at 518 to adjust the settings of lateral control parameters 118 stored in memory. If the driver has not performed sufficient steering maneuvers, controller circuit 102 continues to collect vehicle lateral response data 112 from vehicle sensors 114 until a data threshold is reached to complete the learning process. The data threshold can be determined experimentally for each lateral steering parameter 116 and can be in the range of thirty to sixty steering events.

[0064] Lateral control parameters

[0065] Figure 7This is a flowchart 700 illustrating an example of how controller circuit 102 determines lateral control parameters 118 based on lateral steering parameters 116. The lateral control parameters 118 include lane offset value 118-1, lateral trajectory error gain 118-2, heading error gain 118-3, look-ahead distance gain 118-4, chamfer value 118-5, and lane change activation threshold and duration 118-6.

[0066] At 702, controller circuit 102 determines whether the lateral steering parameters 116-1 to 116-7 are within or within their respective predetermined factory settings limits established by the vehicle manufacturer, to ensure that system 100 does not use learned values ​​that could cause vehicle handling safety issues. For example, a driver participating in a vehicle racing event may exhibit steering behavior unsuitable for driving vehicle 108 on a traffic road. If any of the lateral steering parameters 116-1 to 116-7 is outside the manufacturer's predetermined limits, controller circuit 102 defaults to the factory setting for the corresponding lateral steering parameter 116. If the lateral steering parameter 116 is within the predetermined limits, controller circuit 102 continues to adjust the lateral control parameter 118 to ensure that the adjusted lateral control parameter 118 remains within the predetermined range.

[0067] The controller circuit 102 can pass through the RMS lane offset parameter 116-1 to become the lane offset value 118-1, which indicates the lateral distance between the driver and other vehicles traveling in the adjacent lane.

[0068] At 704, the controller circuit 102 compares the average lateral trajectory error 116-2 with a lookup table stored in memory. Figure 7 In the example shown, the lookup table is used to reduce the computational load on controller circuitry 102. In other examples, controller circuitry 102 may calculate the gain without a lookup table, or access the gain from a cloud storage facility accessible by controller circuitry 102 via the infotainment system of vehicle 108. Controller circuitry 102 may interpolate the lateral trajectory error gain 118-2 based on values ​​in the lookup table and store the adjusted gain in memory.

[0069] At 706, the controller circuit 102 compares the RMS heading error 116-3 with the heading gain lookup table, interpolates the heading error gain 118-3, and stores the updated gain in memory.

[0070] At 708, the controller circuit 102 compares the RMS turning reaction time 116-4 with the look-ahead gain lookup table, interpolates the look-ahead distance gain 118-4, and stores the updated gain in memory.

[0071] At point 710, controller circuit 102 converts the chamfer percentage 116-5 into a distance based on the current lane width and compares this distance to a threshold. When the chamfer distance is higher than the threshold, controller circuit 102 activates the chamfer. The threshold can be user-defined and can be based on vehicle speed. For example, a threshold of 0.02 meters would allow chamfer activation when the chamfer distance exceeds 0.02 meters. Controller circuit 102 then stores the updated chamfer value 118-5 in memory.

[0072] The controller circuit 102 can pass the minimum road curvature 116-6 and the RMS lane change time 116-7 to generate a lane change activation threshold and a duration 118-6. The controller circuit can set the curvature threshold to a minimum curvature value based on the minimum road curvature 116-6 to enable lane change, and can set the lane change duration based on the RMS lane change time 116-7.

[0073] The controller circuit 102 can store the adjusted lateral control parameters 118 in a memory and associate the adjusted values ​​with the driver's identity, which is also stored in the memory. When the vehicle 108 operates in autonomous driving mode, the controller circuit 102 can identify the driver in the driver's seat and retrieve the adjusted lateral control parameters 118 for the identified driver from the memory. The controller circuit 102 can then use these retrieved values ​​in autonomous driving mode to operate the vehicle 108 to reproduce the driver's steering habits.

[0074] Human-Computer Interface (HMI)

[0075] Figure 8-10 An example of a human-machine interface 130 (HMI 130) is shown. When the vehicle 108 is operating in autonomous driving mode, the HMI 130 can receive input from the driver indicating the driver's preference for aggressive lateral control. Figure 8-10The examples shown are not intended to cover all possible lateral control input scenarios, but are illustrated to explain the concept of receiving input from the driver. The HMI 130 can be presented to the driver on the console display of the vehicle 108 or as an application on a mobile device (e.g., a mobile phone or tablet synchronized with the vehicle 108). The HMI 130 may include inputs for preset selections 132 and adjustable selections 134, which provide the driver with the opportunity to further customize their riding experience when the vehicle 108 is operating in autonomous driving mode.

[0076] exist Figure 8 In the example shown, HMI 130 presents a choice regarding lane change aggression, indicating the driver's preference for the minimum road curvature 116-6 required to enable lane changes. Controller circuitry 102 can further adjust lateral control parameters 118 associated with the driver's identity, stored in memory and used to operate the vehicle 108 in autonomous driving mode. In this example, the driver can choose from two preset options 132 (e.g., Sport or Comfort), or from an adjustable option 134 by moving a slider between positions A and B. In this example, the Sport option could indicate the driver's preference for lane changes on roads with greater curvature, compared to the Comfort option, which suggests the driver prefers lane changes on roads with less curvature. The choice of A or B on the slider provides the driver with a visual understanding of the road curvature, where choosing A is less aggressive than choosing B. Controller circuitry 102 can adjust the lateral control parameters 118 associated with driver input, for example, adjusting previously stored lane change activation thresholds and durations 118-6 determined via a driver learning process.

[0077] Figure 9 An example of HMI 130 presenting a choice for lane centering aggression is shown, indicating the driver's preference for lane centering in curves. In this example, Sport selection may indicate a driver preference for turning closer to the inside of the curve, while Comfort selection may indicate a driver preference for turning closer to the outside of the curve, reducing the driver's perceived centrifugal force at the outside of the curve. A slider provides the driver with additional customization options for lane centering aggression, as shown in positions A, B, and C. Controller circuitry 102 may adjust lateral control parameters 118 related to the driver's selection, such as adjusting the lane offset value 118-1 or the lateral trajectory error gain 118-2.

[0078] Figure 10An example of HMI 130 presenting a choice for lane offset aggression, indicating the driver's preference to position vehicle 108 in the lane adjacent to a parked car, is shown. In this example, a small offset selection might indicate a driver preference to drive closer to the parked car, while a large offset selection might indicate a driver preference to stay further away from the parked car. A slider provides the driver with additional customization options for lane offset aggression, as shown in positions A, B, and C. Controller circuitry 102 can adjust lateral control parameters 118 related to the driver's selection, such as adjusting the lane offset value 118-1.

[0079] like Figure 11 As shown in flowchart 1100, controller circuit 102 can adjust stored lateral control parameters 118 based on values ​​associated with the selection of lateral control aggressiveness from a lookup table. The process of adjusting lateral control parameters 118 based on the lookup table is the same as described above and... Figure 7 The same applies as shown. At 1102, the controller circuit compares the HMI input with factory-set limits to ensure that system 100 does not use learned values ​​that could cause vehicle handling safety issues. From 1104 to 1114, the controller circuit compares the HMI input with a lookup table or predetermined thresholds to further adjust the lateral control parameters 118-1 to 118-4 and 118-6.

[0080] Figure 12 This is a flowchart illustrating an example logic flow 1200 executed by controller circuitry 102. The logic flow begins at 1202 with vehicle ignition and ends at 1216 with driver learning. In this example, at 1202, when the driver actuates the vehicle ignition switch within vehicle 108, controller circuitry 102 receives identity data 104 from OMS 110, as described above. At 1204, controller circuitry 102 determines whether the driver has been identified. If controller circuitry 102 has not identified the driver, then at 1206, controller circuitry 102 adds a new driver based on identity data 104 and changes lateral control parameter 118 to the default factory settings not associated with driver identity.

[0081] If controller circuit 102 identifies a driver, at 1208, controller circuit 102 determines whether the previous lateral control parameters 118 are stored in memory. If no lateral control parameters 118 are stored in memory, at 1206, controller circuit 102 adds a new driver based on identity data 104 and changes the lateral control parameters 118 to the default factory settings. If the lateral control parameters 118 are stored in memory, at 1210, controller circuit 102 retrieves the previous lateral control parameters 118 associated with the identified driver from memory.

[0082] At 1212, controller circuit 102 determines whether input has been received via HMI 130. If input has been received via HMI 130, then at 1214, controller circuit 102 adjusts lateral control parameter 118 based on the HMI input. If input has not yet been received via HMI 130, then at 1216, controller circuit 102 continues as follows... Figure 5 and Figure 7 The driver learning process is shown, and the lateral control parameter 118 is adjusted as described above.

[0083] Other example identification techniques

[0084] The above example relates to a camera that detects an image of a driver's face. In other examples, system 100 may be configured to detect additional identifying features that can be used to determine the driver's identity. The following example describes other sensors that can detect other identifying features of the driver. Apart from the different sensors and corresponding control circuitry for operating the different sensors, the system architecture and logic flow are similar. Figure 4 The example shown.

[0085] Voice-based identification

[0086] In this example, a microphone mounted on vehicle 108 detects the driver's speech. OMS 110 can use speech recognition software to process the speech recording to determine unique identifying features of the detected speech and generate feature vectors based on these features. In some examples, the speech recognition software uses a text-dependent approach, where the driver's spoken command phrases are compared with records of command phrases stored in the memory of OMS 110. In other examples, the speech recognition software uses a text-independent approach, where the driver is free to speak to system 100, and the software learns the driver's speech over time. The identifying features of the feature vectors can include various components extracted from the acoustic speech signal, such as amplitude and frequency from a specific bandwidth, formant frequencies or resonances in the spectrum, pitch contours or variations in the fundamental frequency, and coarticulation of the articulatory organs as they prepare to produce the next sound from the previous one.

[0087] Fingerprint-based identification

[0088] In this example, a capacitive fingerprint sensor installed on vehicle 108 (e.g., on the steering wheel or ignition switch) can detect the driver's fingerprint. OMS 110 can use fingerprint recognition software to process the fingerprint to determine unique identifying features of the detected fingerprint and generate a feature vector based on these features. The identifying features of the feature vector can include various components extracted from the fingerprint, such as ridge endings and ridge bifurcations.

[0089] Eye-based identifiers

[0090] In this example, the camera is an infrared camera (IR camera), and the eye is illuminated with light in the near-infrared spectrum by an IR illuminator located inside the vehicle cabin. In some examples, the OMS 110 may use iris recognition software that processes images of the iris of one or both eyes. In other examples, the OMS 110 may use retinal recognition software that processes images of the retina of one or both eyes. The identifying features of the feature vector may include various components extracted from the pattern of the iris or retina using known feature extraction methods, such as Gabor filters, discrete wavelet transform (DWT), discrete cosine transform (DCT), and Haar wavelet transform (HWT) for extracting frequency content.

[0091] Example Method

[0092] Figure 13 An example method 1300 performed by system 100 is illustrated. For example, controller circuitry 102 configures system 100 to perform operations 1302 to 1312 by executing instructions associated with controller circuitry 102. Operations (or steps) 1302 to 1312 are performed, but are not necessarily limited to the order or combination of operations shown herein. Furthermore, any one or more operations may be repeated, combined, or reorganized to provide other operations.

[0093] Step 1302 includes "receiving identity data". This may include the controller circuitry 102 receiving identity data 104 from the driver monitoring sensor 106, the identity data 104 indicating the identity of the driver of the vehicle 108. As described above, the driver monitoring sensor 106 may be a component of the OMS 110. The identity data 104 may be image-based, voice-based, fingerprint-based, or eye-based data, and the identity data 104 may be stored in the memory of the controller circuitry 102 for multiple drivers.

[0094] Step 1304 includes "receiving vehicle lateral response data". This may include controller circuitry 102 receiving vehicle lateral response data 112 from vehicle sensor 114, the vehicle lateral response data 112 being based on steering maneuvers performed by vehicle 108 under driver control, as described above. Vehicle sensor 114 may directly or indirectly detect lateral movement of vehicle 108. Vehicle lateral response data 112 may be used by system 100 to learn driver steering behavior and may include lateral trajectory error 112-1 relative to lane centerline, heading error 112-2 relative to look-ahead point 122, road curvature 112-3, turning reaction time 112-4, road curvature during lane change 112-5, lane change time 112-6, and lateral distance to adjacent vehicles 112-7, as described above.

[0095] Step 1306 includes “determining lateral steering parameters”. This may include controller circuitry 102 determining lateral steering parameters 116 based on vehicle lateral response data 112, as described above. Controller circuitry 102 processes the raw vehicle lateral response data 112 to determine lateral steering parameters 116. Lateral steering parameters 116 include RMS lane offset 116-1, mean lateral trajectory error 116-2, RMS heading error 116-3, RMS turning reaction time 116-4, tangent percentage 116-5, minimum road curvature for enabling lane change 116-6, and RMS lane change time 116-7, as described above.

[0096] Step 1308 includes “adjusting lateral control parameters”. This may include controller circuitry 102 adjusting lateral control parameters 118 stored in memory based on the identified driver’s lateral steering parameters 116. Lateral control parameters 118 are used to control the vehicle 108 when it is operating in autonomous driving mode and can reproduce the driver’s steering behavior. Lateral control parameters 118 include lane offset value 118-1, lateral trajectory error gain 118-2, heading error gain 118-3, look-ahead distance gain 118-4, chamfer value 118-5, and lane change activation threshold and duration 118-6, as described above. Controller circuitry 102 adjusts lateral control parameters 118 within predetermined ranges established by the vehicle manufacturer to ensure safe vehicle handling. As described above, controller circuitry 102 stores the adjusted lateral control parameters 118 in memory for later retrieval.

[0097] As described above, the controller circuit 102 can further adjust the lateral control parameters 118 stored in the memory via input from the HMI 130. The HMI 130 may include a preset selection 132 and an adjustable selection 134, which further enable the driver to customize their experience when operating the vehicle 108 in autonomous driving mode.

[0098] Step 1310 includes "associating the adjusted parameters with driver identities". This may include: the controller circuit 102 associating or matching adjusted lateral control parameters 118 stored in memory with driver identities also stored in memory, as described above. The controller circuit 102 may associate several driver identities with their corresponding adjusted lateral control parameters 118 in the memory of the controller circuit 102, and recall the adjusted lateral control parameters 118 when the driver of the vehicle 108 is identified.

[0099] Step 1312 includes “operating the vehicle”. This may include: the controller circuit 105 operating the vehicle 108 in autonomous driving mode using lateral control parameters 118 stored in memory and associated with the driver’s identity to reproduce the driver’s steering habits, as described above.

[0100] Example

[0101] Examples are provided in the following sections.

[0102] Example 1. A system comprising: a controller circuit configured to: receive identity data indicating the identity of a driver of a vehicle from a driver monitoring sensor; receive vehicle lateral response data based on steering maneuvers performed by the vehicle under the control of the driver from one or more vehicle sensors; determine a plurality of lateral steering parameters of the vehicle based on the vehicle lateral response data; adjust lateral control parameters of the vehicle based on the plurality of lateral steering parameters; associate the adjusted lateral control parameters of the vehicle with the driver's identity; and operate the vehicle according to the lateral control parameters associated with the driver's identity.

[0103] Example 2. The system of the previous example, wherein the controller circuitry is further configured to: operate the vehicle in response to lateral control parameters associated with the identity of the driver of the vehicle, while avoiding operating the vehicle in response to initial lateral control parameters associated with the vehicle, which are different from the lateral control parameters associated with the driver's identity.

[0104] Example 3. A system of any of the previous examples, wherein the controller circuitry is further configured to: store in the memory of the controller circuitry a plurality of adjusted vehicle lateral control parameters associated with a plurality of driver identities, the plurality of driver identities including the identity of the driver.

[0105] Example 4. A system of any of the preceding examples, wherein the system further includes a human-machine interface (HMI) configured to receive input from the driver indicating lateral control aggression, and wherein controller circuitry is further configured to adjust vehicle lateral control parameters associated with the driver's identity based on the driver input.

[0106] Example 5. A system of any of the previous examples, wherein the HMI includes one or more inputs from preset selections and adjustable selections.

[0107] Example 6. A system of any of the previous examples, wherein the preset selection and adjustable selection include one or more of the following: lane offset relative to stationary vehicles on the road, lane centering on curves, and minimum road curvature to enable lane changing.

[0108] Example 7. A system of any of the previous examples, wherein the controller circuitry is further configured to: adjust stored vehicle lateral control parameters based on values ​​from a lookup table associated with the selection of lateral control aggressiveness.

[0109] Example 8. A system of any of the previous examples, wherein the lateral response data includes one or more of the following: lateral trajectory error relative to the center of the lane, heading error relative to a reference point, turning reaction time, road curvature during lane change, lane change time, and lateral distance to adjacent vehicles.

[0110] Example 9. A system of any of the previous examples, wherein the lateral steering parameters include one or more of the following: root mean square (RMS) lane offset, mean lateral trajectory error, RMS heading error, RMS turning reaction time, cut angle percentage, minimum road curvature for enabling lane change, and RMS lane change time.

[0111] Example 10. A system of any of the previous examples, wherein the lateral control parameters include one or more of the following: lane offset value, lateral trajectory error gain, heading error gain, look-ahead distance gain, chamfer value, and lane change activation threshold and duration.

[0112] Example 11. A system of any of the previous examples, wherein the controller circuitry is further configured to adjust lateral control parameters within a predetermined range.

[0113] Example 12. A system of any of the previous examples, wherein one or more sensors include an inertial measurement unit (IMU), a steering angle sensor, a vehicle speed sensor, a positioning sensor, a camera, and a ranging sensor.

[0114] Example 13. A method comprising: receiving identity data indicating the identity of a driver of a vehicle from a driver monitoring sensor using controller circuitry; receiving vehicle lateral response data based on steering maneuvers performed by the vehicle under the control of a driver from one or more vehicle sensors using controller circuitry; determining a plurality of lateral steering parameters of the vehicle based on the vehicle lateral response data using controller circuitry; adjusting lateral control parameters of the vehicle based on the plurality of lateral steering parameters using controller circuitry; associating the adjusted lateral control parameters of the vehicle with the driver's identity; and operating the vehicle according to the lateral control parameters associated with the driver's identity using controller circuitry.

[0115] Example 14. The method of the previous example further includes: in response to operating the vehicle according to lateral control parameters associated with the identity of the driver of the vehicle, avoiding operating the vehicle according to initial lateral control parameters associated with the vehicle, the initial lateral control parameters being different from the lateral control parameters associated with the identity of the driver.

[0116] Example 15. The method of any of the previous examples further includes: using controller circuitry to store in the memory of the controller circuitry a plurality of adjusted vehicle lateral control parameters associated with a plurality of driver identities.

[0117] Example 16. The method of any of the preceding examples further includes: receiving input from the driver indicating lateral control aggression via a human-machine interface (HMI); and adjusting stored vehicle lateral control parameters based on the driver input using controller circuitry.

[0118] Example 17. A method from any of the previous examples, where the HMI includes inputs from one or more of the preset selections and adjustable selections.

[0119] Example 18. A method of any of the previous examples, wherein the preset selection and adjustable selection include one or more of the following: lane offset relative to stationary vehicles on the road, lane centering on curves, and minimum road curvature to enable lane changing.

[0120] Example 19. The method of any of the previous examples further includes: adjusting the stored vehicle lateral control parameters based on values ​​associated with the selection of lateral control aggressiveness from a lookup table.

[0121] Example 20. A method of any of the previous examples, wherein receiving lateral response data includes receiving one or more of the following: lateral trajectory error relative to the center of the lane, heading error relative to a reference point, turning reaction time, road curvature during lane change, lane change time, and lateral distance to adjacent vehicles.

[0122] Example 21. A system comprising means for performing a method of any of the preceding examples.

[0123] Example 22. A computer-readable storage medium comprising instructions that, when executed, configure a processor to perform a method of any of the preceding examples.

[0124] Conclusion

[0125] While various embodiments of the present disclosure have been described in the foregoing description and illustrated in the accompanying drawings, it should be understood that the present disclosure is not limited thereto, but can be practiced in various ways within the scope of the following claims. It will be apparent from the foregoing description that various modifications can be made without departing from the spirit and scope of the present disclosure as defined by the following claims.

[0126] Unless the context explicitly states otherwise, the use of terms grammatically related to "or" indicates an unrestricted, non-exclusive alternative. As used herein, the phrase referring to "at least one" of a list of items means any combination of those items, including a single member. As an example, "at least one of a, b, or c" is intended to cover: a, b, c, ab, ac, bc, and abc, as well as any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbb, cc, and ccc, or any other ordering of a, b, and c).

Claims

1. A vehicle control system, comprising: A human-machine interface (HMI) configured to receive input from the driver of the vehicle indicating the degree of lateral control aggression; Controller circuit, the controller circuit being configured to: Receive identity data indicating the identity of the driver of the vehicle from the driver monitoring sensor; Vehicle lateral response data is received from one or more vehicle sensors separate from the HMI, the vehicle lateral response data being based on steering maneuvers performed by the vehicle under the control of the driver; Based on the vehicle's lateral response data, multiple lateral steering parameters of the vehicle are determined; The lateral control parameters of the vehicle are adjusted based on the plurality of lateral steering parameters and the input from the driver to the HMI; The adjusted lateral control parameters of the vehicle are associated with the identity of the driver; and The vehicle is operated according to the lateral control parameters associated with the driver's identity.

2. The vehicle control system as described in claim 1, characterized in that, The controller circuit is further configured to: In response to operating the vehicle according to the lateral control parameters associated with the identity of the driver of the vehicle, operation of the vehicle is avoided according to initial lateral control parameters associated with the vehicle, which are different from the lateral control parameters associated with the identity of the driver.

3. The vehicle control system as described in claim 1, characterized in that, The controller circuit is further configured to: store in the memory of the controller circuit a plurality of adjusted vehicle lateral control parameters associated with a plurality of driver identities, the plurality of driver identities including the identity of the driver.

4. The vehicle control system as described in claim 3, characterized in that, The controller circuit is configured to adjust the lateral control parameters by: A first set of lateral control parameters is generated based on the lateral steering parameters; and The first set of lateral control parameters is adjusted based on the input from the driver to the HMI to create a second set of lateral control parameters.

5. The vehicle control system as described in claim 1, characterized in that, The HMI includes preset selections and inputs that can adjust one or more of the selections.

6. The vehicle control system as described in claim 5, characterized in that, The preset and adjustable options include one or more of the following: lane offset relative to stationary vehicles on the road, lane centering on curves, and minimum road curvature for enabling lane changes.

7. The vehicle control system as described in claim 6, characterized in that, The controller circuitry is further configured to adjust stored vehicle lateral control parameters based on values ​​from a lookup table associated with the selection of lateral control aggressiveness.

8. The vehicle control system as described in claim 1, characterized in that, The lateral response data includes one or more of the following: lateral trajectory error relative to the lane center, heading error relative to a reference point, turning reaction time, road curvature during lane change, lane change time, and lateral distance to adjacent vehicles.

9. The vehicle control system as described in claim 1, characterized in that, The lateral steering parameters include one or more of the following: root mean square (RMS) lane offset, mean lateral trajectory error, RMS heading error, RMS turning reaction time, cut angle percentage, minimum road curvature for enabling lane change, and RMS lane change time.

10. The vehicle control system as claimed in claim 1, characterized in that, The lateral control parameters include one or more of the following: lane offset value, lateral trajectory error gain, heading error gain, look-ahead distance gain, chamfer value, and lane change activation threshold and duration.

11. The vehicle control system as described in claim 10, characterized in that, The controller circuit is further configured to adjust the lateral control parameters within a predetermined range.

12. The vehicle control system as claimed in claim 1, characterized in that, The one or more sensors include an inertial measurement unit (IMU), a steering angle sensor, a vehicle speed sensor, a positioning sensor, a camera, and a ranging sensor.

13. A method for controlling a vehicle, comprising: The vehicle receives input from the driver via a human-machine interface (HMI) instructing the driver on the degree of lateral control aggression. The controller circuit receives identity data indicating the identity of the driver of the vehicle from the driver monitoring sensor; The controller circuitry receives vehicle lateral response data from one or more vehicle sensors, which are separate from the HMI, the vehicle lateral response data being based on steering maneuvers performed by the vehicle under the control of the driver; The controller circuit uses the vehicle's lateral response data to determine multiple lateral steering parameters of the vehicle. The controller circuit adjusts the lateral control parameters of the vehicle based on the plurality of lateral steering parameters and the input from the driver to the HMI; The adjusted lateral control parameters of the vehicle are associated with the identity of the driver; as well as The vehicle is operated using the controller circuit based on the lateral control parameters associated with the driver's identity.

14. The vehicle control method as described in claim 13, characterized in that, Further includes: In response to operating the vehicle according to the lateral control parameters associated with the identity of the driver of the vehicle, operation of the vehicle is avoided according to initial lateral control parameters associated with the vehicle, which are different from the lateral control parameters associated with the identity of the driver.

15. The vehicle control method as described in claim 13, characterized in that, Further includes: Using the controller circuit, multiple adjusted vehicle lateral control parameters associated with multiple driver identities are stored in the controller circuit's memory.

16. The vehicle control method as described in claim 15, characterized in that, Adjusting the lateral control parameters of the vehicle includes: A first set of lateral control parameters is generated based on the lateral steering parameters; and The first set of lateral control parameters is adjusted based on the input from the driver to the HMI to create a second set of lateral control parameters.

17. The vehicle control method as described in claim 13, characterized in that, The HMI includes preset selections and inputs that can adjust one or more of the selections.

18. The vehicle control method as described in claim 17, characterized in that, The preset and adjustable options include one or more of the following: lane offset relative to stationary vehicles on the road, lane centering on curves, and minimum road curvature for enabling lane changes.

19. The vehicle control method as described in claim 18, characterized in that, Further includes: The stored vehicle lateral control parameters are adjusted based on the values ​​associated with the selection of lateral control aggressiveness from the lookup table.

20. The vehicle control method as described in claim 13, characterized in that, Receiving the lateral response data includes receiving one or more of the following: lateral trajectory error relative to the center of the lane, heading error relative to a reference point, turning reaction time, road curvature during lane change, lane change time, and lateral distance to adjacent vehicles.

21. A vehicle control system, comprising means for performing any of the vehicle control methods as described in claims 13-20.

22. A computer-readable storage medium comprising instructions that, when executed, configure a processor to perform any of the vehicle control methods as described in claims 13-20.

Images