Adaptive driver lane keeping assist control

Abstract

The system includes a neural network module, a lane keeping assist (LKA) module, and a control module. The neural network module is configured to receive driver data, identify a driver, receive non-driver data, and generate a lane assist offset value specific to the identified driver based on the non-driver data and the driver data. The LKA module is configured to: receive a lane assist offset value; receiving vehicle data associated with one or more parameters of the vehicle as the vehicle moves, the one or more parameters including a steering angle, a speed, and a position of the vehicle between lane markings; and generating a steering angle control signal based on the received lane assist offset value and the vehicle data. The control module is configured to control steering of the vehicle based on the generated steering angle control signal. Other example systems and methods are also disclosed.

Description

[0001] introduce

[0002] The information provided in this section is for the purpose of generally presenting the context of the present disclosure. The work of the inventors currently listed (to the extent that it is described in this section) and aspects of the description that may not have been prior art at the time of filing are neither explicitly nor implicitly admitted to be prior art against the present disclosure.

[0003] The present disclosure relates to adaptive driver lane keeping assist control.

[0004] The vehicle may include driver assistance systems that rely on sensors for blind spot detection, adaptive cruise control, lane departure warnings, and the like. In some cases, the driver assistance system may be a lane keeping assist (LKA) system. When an LKA system is employed, when vehicle drift is detected, the system attempts to bring the vehicle back to a centered position between lanes using a correction steering angle. This correction is based on a predetermined lane offset value (e.g., a predefined distance that the vehicle should maintain from lane markings), the longitudinal speed of the vehicle, the steering angle of the vehicle, and the vehicle's current lane position between lane markings. Summary of the invention

[0005] A system for controlling adaptive lane keeping assistance in a moving vehicle is disclosed. The system includes a neural network module, a lane keeping assistance (LKA) module in communication with the neural network module, and a control module in communication with the LKA module. The neural network module is configured to: receive driver data from one or more sensors in the vehicle, the driver data being specific to the driver's driving style when controlling the vehicle; identify the driver from a plurality of drivers associated with the vehicle; receive non-driver data, the non-driver data indicating environmental parameters outside the vehicle when the vehicle is moving; and generate a lane assistance offset value specific to the identified driver based on the non-driver data and the driver data. The LKA module is configured to: receive a lane assistance offset value specific to the identified driver; receive vehicle data associated with one or more parameters of the vehicle when the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; and generate a steering angle control signal based on the received lane assistance offset value and the vehicle data. The control module is configured to control the steering of the vehicle based on the generated steering angle control signal.

[0006] In other features, the driver data and the non-driver data are a first data set, and the neural network module is configured to: receive a second data set including driver data, non-driver data, and vehicle data, wherein the driver data is from one or more sensors in the vehicle and is specific to the driving styles of the plurality of drivers associated with the vehicle, the non-driver data indicates environmental parameters external to the vehicle while the vehicle is moving, and the vehicle data is associated with the one or more parameters of the vehicle while the vehicle is moving; and for each of the plurality of drivers associated with the vehicle, train one or more models of the neural network module based on the received second data set.

[0007] In other features, the LKA module is disabled while the one or more models of the neural network module are being trained.

[0008] In other features, the steering angle control signal is a first steering angle control signal, and the control module is configured to receive a second steering angle control signal from a steering wheel angle sensor and control the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0009] In other features, the control module is configured to automatically activate a turn signal of the vehicle if the vehicle position is less than a defined distance from one of the lane markings.

[0010] In other features, the non-driver data includes at least one of perception data, map data, and traffic sign detection data from one or more detection modules of the vehicle.

[0011] In other features, the system further includes one or more sensors configured to detect driver data. The one or more sensors include one or more pressure sensors mounted on a steering wheel of the vehicle and configured to detect applied pressure, and the neural network module is configured to detect a driver engagement level based on the applied pressure and generate a lane assist offset value if the driver engagement level is below a threshold.

[0012] In other features, the neural network module is configured to determine an amount of driver interaction with the vehicle based on driver data received from the one or more sensors in the vehicle, and to reduce an amount of vehicle data provided to the LKA module if the amount of driver interaction is above a threshold.

[0013] In other features, the neural network module is configured to identify the driver from the plurality of drivers associated with the vehicle based on the received driver data specific to the driver's driving style.

[0014] A method for controlling adaptive lane keeping assistance in a moving vehicle is disclosed. The method includes: receiving driver data from one or more sensors in the vehicle, the driver data being specific to the driver's driving style when controlling the vehicle; identifying the driver from a plurality of drivers associated with the vehicle using a neural network module; receiving non-driver data indicating environmental parameters outside the vehicle while the vehicle is moving; generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data; receiving vehicle data associated with one or more parameters of the vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; generating a steering angle control signal based on the lane assist offset value and the vehicle data using a KLA module; and controlling the steering of the vehicle based on the generated steering angle control signal.

[0015] In other features, the driver data and the non-driver data are a first data set, and the method further includes: receiving a second data set including driver data, non-driver data, and vehicle data, the driver data being from one or more sensors in the vehicle and being specific to the driving styles of the plurality of drivers associated with the vehicle, the non-driver data indicating environmental parameters external to the vehicle while the vehicle is moving, the vehicle data being associated with the one or more parameters of the vehicle while the vehicle is moving; and for each of the plurality of drivers associated with the vehicle, training one or more models of the neural network module based on the received second data set.

[0016] In other features, the method further comprises disabling the LKA module while one or more models of the neural network module are being trained.

[0017] In other features, the steering angle control signal is a first steering angle control signal, and the method further includes: receiving a second steering angle control signal from a steering wheel angle sensor and controlling the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0018] In other features, the non-driver data includes at least one of perception data, map data, and traffic sign detection data from one or more detection modules of the vehicle.

[0019] In other features, the method further includes automatically activating a turn signal of the vehicle if the vehicle position is less than a defined distance from one of the lane markings.

[0020] In other features, receiving the driver data from the one or more sensors in the vehicle includes receiving applied pressure from one or more pressure sensors mounted on a steering wheel of the vehicle.

[0021] In other features, the method further includes detecting a driver engagement level based on the applied pressure and generating a lane assist offset value if the driver engagement level is below a threshold.

[0022] In other features, the method further comprises determining an amount of driver interaction with the vehicle based on driver data received from the one or more sensors in the vehicle and reducing an amount of vehicle data provided to the LKA module if the amount of driver interaction is above a threshold.

[0023] In other features, identifying the driver from the plurality of drivers associated with the vehicle using the neural network module includes: identifying the driver based on received driver data specific to the driver's driving style.

[0024] A system for controlling adaptive lane keeping assistance in a moving vehicle is disclosed. The system includes a neural network module and an LKA module in communication with the neural network module. The neural network module is configured to: receive a first data set, the first data set including driver data, non-driver data, and vehicle data, the driver data coming from one or more sensors in the vehicle and being specific to the driving styles of multiple drivers associated with the vehicle, the non-driver data indicating environmental parameters outside the vehicle when the vehicle is moving, and the vehicle data being associated with the one or more parameters of the vehicle when the vehicle is moving; for each of the multiple drivers associated with the vehicle, train one or more models of the neural network module based on the received second data set; after the one or more models of the neural network module are trained, receive a second set, the second set including driver data coming from the one or more sensors and being specific to the driving styles of the drivers among the multiple drivers and non-driver data indicating environmental parameters outside the vehicle when the vehicle is moving; identify a driver from the multiple drivers associated with the vehicle based on the driver's driving style; and generate a lane assist offset value specific to the identified driver based on the non-driver data and the driver data. The LKA module is configured to: receive vehicle data associated with one or more parameters of the vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; and generate a steering angle control signal to control the steering of the vehicle based on the lane assist offset value and the vehicle data.

[0025] In other features, the LKA module is disabled while the one or more models of the neural network module are being trained.

[0026] In other features, the steering angle control signal is a first steering angle control signal, and the system further includes a control module configured to receive a second steering angle control signal from a steering wheel angle sensor and control the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0027] A first aspect of the present disclosure provides a system for controlling adaptive lane keeping assistance in a moving vehicle, the system comprising:

[0028] The neural network module is configured as:

[0029] receiving driver data from one or more sensors in the vehicle, the driver data being specific to the driver's driving style while controlling the vehicle;

[0030] identifying the driver from a plurality of drivers associated with the vehicle;

[0031] receiving non-driver data indicating an environmental parameter external to the vehicle while the vehicle is moving; and

[0032] generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data;

[0033] A lane keeping assist (LKA) module in communication with the neural network module, the LKA module being configured to:

[0034] receiving the lane assist offset value specific to the identified driver;

[0035] receiving vehicle data associated with one or more parameters of the vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; and

[0036] generating a steering angle control signal based on the received lane assist offset value and the vehicle data; and

[0037] A control module is in communication with the LKA module, the control module being configured to control steering of the vehicle based on the generated steering angle control signal.

[0038] According to the system of the first aspect of the present disclosure, wherein:

[0039] The driver data and the non-driver data are a first data set, and

[0040] The neural network module is configured as follows:

[0041] receiving a second data set including driver data, non-driver data, and vehicle data, the driver data being from one or more sensors in the vehicle and being specific to the driving styles of the plurality of drivers associated with the vehicle, the non-driver data being indicative of environmental parameters external to the vehicle while the vehicle is moving, the vehicle data being associated with the one or more parameters of the vehicle while the vehicle is moving; and

[0042] For each of the plurality of drivers associated with the vehicle, one or more models of the neural network module are trained based on the received second data set.

[0043] According to the system of the first aspect of the present disclosure, the LKA module is disabled when the one or more models of the neural network module are being trained.

[0044] According to the system of the first aspect of the present disclosure, wherein:

[0045] The steering angle control signal is a first steering angle control signal; and

[0046] The control module is configured to receive a second steering angle control signal from a steering wheel angle sensor and control the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0047] According to the system of the first aspect of the present disclosure, the control module is configured to automatically activate a turn signal of the vehicle if the vehicle position is less than a defined distance from one of the lane markings.

[0048] According to the system described in the first aspect of the present disclosure, the non-driver data includes at least one of perception data, map data and traffic sign detection data from one or more detection modules of the vehicle.

[0049] The system according to the first aspect of the present disclosure further comprises the one or more sensors configured to detect the driver data, wherein:

[0050] The one or more sensors include one or more pressure sensors mounted on a steering wheel of the vehicle and configured to detect applied pressure; and

[0051] The neural network module is configured to detect a driver engagement level based on the applied pressure and to generate the lane assist offset value if the driver engagement level is below a threshold.

[0052] According to the system described in the first aspect of the present disclosure, the neural network module is configured to: determine the amount of interaction between the driver and the vehicle based on the driver data received from the one or more sensors in the vehicle, and if the driver interaction amount is higher than a threshold, reduce the amount of the vehicle data provided to the LKA module.

[0053] According to the system of the first aspect of the present disclosure, the neural network module is configured to identify the driver from the multiple drivers associated with the vehicle based on received driver data specific to the driver's driving style.

[0054] A second aspect of the present disclosure provides a method for controlling adaptive lane keeping assist in a moving vehicle, the method comprising:

[0055] receiving driver data from one or more sensors in a vehicle, the driver data being specific to a driver's driving style while controlling the vehicle;

[0056] identifying the driver from a plurality of drivers associated with the vehicle using a neural network module;

[0057] receiving non-driver data indicating an environmental parameter external to the vehicle while the vehicle is moving;

[0058] generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data;

[0059] receiving vehicle data associated with one or more parameters of a vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings;

[0060] generating, using a lane keeping assist (KLA) module, a steering angle control signal based on the lane assist offset value and the vehicle data; and

[0061] The steering of the vehicle is controlled based on the generated steering angle control signal.

[0062] The method according to the second aspect of the present disclosure, wherein:

[0063] The driver data and the non-driver data are a first data set; and

[0064] The method also includes: receiving a second data set including driver data, non-driver data, and vehicle data, the driver data being from one or more sensors in the vehicle and being specific to the driving styles of the multiple drivers associated with the vehicle, the non-driver data indicating environmental parameters external to the vehicle while the vehicle is moving, and the vehicle data being associated with the one or more parameters of the vehicle while the vehicle is moving; and for each of the multiple drivers associated with the vehicle, training one or more models of the neural network module based on the received second data set.

[0065] The method according to the second aspect of the present disclosure further includes: disabling the LKA module when the one or more models of the neural network module are being trained.

[0066] The method according to the second aspect of the present disclosure, wherein:

[0067] The steering angle control signal is a first steering angle control signal; and

[0068] The method also includes receiving a second steering angle control signal from a steering wheel angle sensor and controlling the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0069] A method according to the second aspect of the present disclosure, wherein: the non-driver data includes at least one of perception data, map data and traffic sign detection data from one or more detection modules of the vehicle.

[0070] The method according to the second aspect of the present disclosure further includes: automatically activating a turn signal of the vehicle if the vehicle position is less than a defined distance from one of the lane markings.

[0071] The method according to the second aspect of the present disclosure, wherein:

[0072] Receiving the driver data from the one or more sensors in the vehicle includes receiving applied pressure from one or more pressure sensors mounted on a steering wheel of the vehicle; and

[0073] The method further includes detecting a driver engagement level based on the applied pressure and generating the lane assist offset value if the driver engagement level is below a threshold.

[0074] The method according to the second aspect of the present disclosure further includes: determining the amount of interaction between the driver and the vehicle based on the driver data received from the one or more sensors in the vehicle, and if the driver interaction amount is higher than a threshold, reducing the amount of the vehicle data provided to the LKA module.

[0075] According to the method described in the second aspect of the present disclosure, identifying the driver from the multiple drivers associated with the vehicle using the neural network module includes: identifying the driver based on received driver data specific to the driving style of the driver.

[0076] A third aspect of the present disclosure provides a system for controlling adaptive lane keeping assistance in a moving vehicle, the system comprising:

[0077] The neural network module is configured as:

[0078] receiving a first data set, the first data set comprising driver data, non-driver data, and vehicle data, the driver data being derived from one or more sensors in the vehicle and being specific to driving styles of a plurality of drivers associated with the vehicle, the non-driver data being indicative of environmental parameters external to the vehicle while the vehicle is moving, the vehicle data being associated with the one or more parameters of the vehicle while the vehicle is moving;

[0079] for each of the plurality of drivers associated with the vehicle, training one or more models of the neural network module based on the received second data set;

[0080] receiving, after the one or more models of the neural network module are trained, a second set including driver data from the one or more sensors and specific to a driving style of a driver among the plurality of drivers and non-driver data indicative of environmental parameters external to the vehicle while the vehicle is moving;

[0081] identifying the driver from the plurality of drivers associated with the vehicle based on the driving style of the driver; and

[0082] generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data;

[0083] a lane keeping assist (LKA) module in communication with the neural network module, the LKA module being configured to:

[0084] receiving vehicle data associated with one or more parameters of a vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; and

[0085] A steering angle control signal is generated based on the lane assist offset value and the vehicle data to control the steering of the vehicle.

[0086] According to the system described in the third aspect of the present disclosure, wherein:

[0087] disabling the LKA module while the one or more models of the neural network module are being trained;

[0088] The steering angle control signal is a first steering angle control signal; and

[0089] The system also includes a control module configured to receive a second steering angle control signal from a steering wheel angle sensor and to control the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained.

[0090] Further areas of applicability of the present disclosure will become apparent from the detailed description, claims and drawings.The detailed description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] The present disclosure will be more fully understood from the detailed description and accompanying drawings, in which:

[0092] Figure 1 is a block diagram of an example system for controlling adaptive lane keeping assist in a moving vehicle according to the present disclosure;

[0093] Figure 2 is a block diagram of an example system for training a neural network module for generating an adaptive lane assist offset value for a driver according to the present disclosure;

[0094] Figure 3 is a block diagram of an example steering wheel assembly including sensors for collecting driver data according to the present disclosure;

[0095] Figure 4 is a flow chart of an example control process for controlling adaptive lane keeping assist in a moving vehicle according to the present disclosure; and

[0096] Figure 5 is a flow chart of another example control process for controlling adaptive lane keeping assist in a moving vehicle according to the present disclosure.

[0097] Among the drawings, reference numerals may be repeated to identify similar and / or identical elements. DETAILED DESCRIPTION

[0098] A vehicle may employ a lane keeping assist (LKA) system for adaptive driving functionality. The LKA system identifies the vehicle's current position between lane markings and then attempts to center the vehicle between lanes when vehicle drift is detected. The amount of correction used to center the vehicle is proportional to the detected error (e.g., the difference between the vehicle's current position and a threshold value). In such circumstances, the LKA system may typically overcorrect and cause an unpleasant motion sensation to the vehicle's occupants and driver (e.g., a jerky corrective movement of the vehicle) due to the overcorrection feedback. Due to this unpleasant motion sensation, some experienced drivers may choose to override the correction function of the LKA system.

[0099] Additionally, to an experienced driver, the actual correction initiated by the LKA system for a given situation may appear too extreme or too small. This may create a feeling of insecurity in control and concern about the behavior and / or safety of the vehicle for the vehicle driver and passengers. The driver may feel as if they are "fighting" the LKA system rather than having confidence in the vehicle's performance. This may be particularly noticeable on a winding mountain road where elevation changes in addition to turns may drastically change the acceleration and overall performance of the vehicle.

[0100] The systems and methods according to the present disclosure provide a solution for LKA adaptation for a specific driver based on the behavior of that driver and the learned correction techniques. For example, the systems and methods enable training of a neural network module based on collected driver data specific to the driver's driving style, vehicle data from the driver while controlling the vehicle, and non-driver-based environmental related parameters such as road geometry, weather, surrounding traffic, obstacles, etc. Such training can be provided for multiple drivers associated with the same vehicle and when the LKA module is disabled. Once trained for the driver's specific preferences, the neural network module provides an adaptive lane assist offset value to the LKA module for the specific, identified driver, thereby enabling the LKA module to generate a steering angle control signal for controlling the steering of the vehicle while the driver is driving. Thus, a more user-friendly and smoother experience is provided compared to conventional LKA systems, thereby increasing the use of the LKA function in the vehicle.

[0101] Reference now Figure 1 , a block diagram of an example system 100 for controlling an adaptive LKA in a moving vehicle is presented. Figure 1 The system 100 may be used in any suitable vehicle, such as an electric vehicle (eg, a pure electric vehicle, a plug-in hybrid electric vehicle, etc.), an internal combustion engine vehicle, etc. In addition, the system 100 may be applicable to autonomous vehicles, semi-autonomous vehicles, etc.

[0102] like Figure 1As shown in FIG. 1 , system 100 generally includes a neural network module 102, an LKA module 104 in communication with the neural network module 102, and a control module 106 in communication with the LKA module. Figure 1 The system 100 is shown as including a plurality of dedicated modules 102, 104, 106, but it is understood that some or all of the features provided by the modules 102, 104, 106 may be implemented by one or more modules.

[0103] In various embodiments, Figure 1 The neural network module 102 may include various layers. For example, the neural network module (e.g., deep neural network module, etc.) 102 may include one or more input layers, one or more hidden layers, and one or more output layers. The layers may include nodes, each of which is connected to another node and has a weight and a threshold. If the output of a node is above its threshold, the node may be activated and data may be sent to the next layer.

[0104] The neural network module 102 includes trainable LKA correction models (e.g., LKA correction algorithms). In such examples, these models can be trained in a conventional manner by relying on training data, as further explained below, to learn and improve their accuracy over time. Figure 1 In the example of FIG. 1 , the neural network module 102 is shown as a trained module that provides an adaptive lane assist offset value, as further explained below.

[0105] like Figure 1 As shown in , the trained neural network module 102 receives data from multiple sources. For example, the neural network module 102 receives driver data 108 specific to the driver's driving style when the driver controls the vehicle. In such examples, the driver data 108 may be sensed by one or more sensors 110 in the vehicle. For example, in some examples, the one or more sensors 110 may be mounted on (e.g., embedded in, attached to, etc.) one or more components of the steering wheel assembly.

[0106] For example, Figure 3 An example steering wheel assembly 300 is depicted, which includes a steering wheel 302 and a steering wheel shaft 304 connected to the steering wheel 302. Figure 3 As shown in FIG. 1 , a plurality of sensors 306 , 308 are mounted on a steering wheel 302 and a steering wheel shaft 304 .

[0107] exist Figure 3In the example of FIG. 3 , the sensor 306 is a pressure sensor mounted around the circumference of the steering wheel 302. The pressure sensor 306 detects the pressure applied by the driver during the driving process (e.g., when the driver grips the steering wheel 302). In other words, the pressure sensor 306 measures the driver's grip force. The collected pressure data can then be used to determine the driver engagement level, as explained further below. In addition, and as Figure 3 As shown in FIG. 3 , a sensor 308 is mounted on the steering wheel shaft 304. The sensor 308 may include, for example, an accelerometer, a steering wheel angle sensor, a torque sensor, etc., for collecting driver-specific data (e.g., the amount of torque applied, the rotation angle of the steering wheel, etc.) when the driver manipulates the steering wheel 302 (and thus the steering wheel shaft 304). Figure 3 The steering wheel assembly 300 is shown as including eight pressure sensors 306 and one sensor 308, but it should be understood that the steering wheel assembly 300 may include more or fewer sensors and / or sensors with different functions. Regardless, the sensors 306, 308 collect data specific to the driver's driving style (e.g., Figure 1 driver data 108) and provides the data to the neural network module 102.

[0108] Continue to refer Figure 1 , the neural network module 102 additionally receives non-driver data 112, which indicates environmental parameters outside the vehicle when the vehicle is moving. For example, the non-driver data 112 may include perception data from one or more detection modules of the vehicle (e.g., camera, radio radar, lidar, etc.), map data, traffic sign detection data, etc. In various embodiments, the perception data may include, for example, road geometry, weather, surrounding traffic, obstacles, etc., which may be detected by a front camera module and / or another suitable detection module.

[0109] In various embodiments, neural network module 102 identifies a particular driver of a vehicle. In such examples, the driver may be identified from a plurality of drivers associated with the vehicle. For example, and as further explained below, neural network module 102 may be trained for a plurality of drivers associated with the vehicle. In such examples, neural network module 102 may identify a particular driver of the vehicle from a potential database of associated drivers based on, for example, received driver data 108 specific to the driver's driving style. In other examples, neural network module 102 may identify a particular driver based on other data, such as programmed presets (e.g., driver seat placement, side mirror placement, rearview mirror placement, selectable inputs, etc.), selected inputs, etc.

[0110] Additionally, the neural network module 102 generates a lane assist offset value that is specific to the identified driver. In such an example, the lane assist offset value may be generated based on the driver data 108 and the non-driver data 112 received by the neural network module 102. In various embodiments, the lane assist offset value is an adaptive value used to better modulate corrective actions and provide a more pleasant driving experience. For example, the lane assist offset value may vary based on the identified driver, the driver's driving style, and / or how the driver reacts in different geographic locations, conditions, scenarios, etc. (e.g., as detected by one or more detection modules, etc.). Once generated, the neural network module 102 may transmit an output signal 114 including the lane assist offset value or a representation thereof to the LKA module 104.

[0111] In various embodiments, neural network module 102 may additionally receive LKA parameters 116 (e.g., vehicle data) via one or more input signals 118. In such examples, LKA parameters 116 may include, for example, the longitudinal velocity of the vehicle, the steering angle of the vehicle, and the current lane position of the vehicle between lane markings collected by one or more vehicle sensors 120 (such as a steering wheel angle sensor, a front camera module, a speed sensor, etc.). In some examples, an inertial measurement unit (IMU) or module 124 may receive the steering angle of the vehicle (or a representation thereof) and provide data to neural network module 102 based on the steering angle (via input signal 126). In such examples, the data provided by IMU 124 may indicate the direction in which the vehicle is traveling.

[0112] In some examples, LKA parameters 116 or modified LKA parameters may be provided to LKA module 104 via one or more signals 128. For example, trained neural network module 102 may analyze LKA parameters 116 and adjust one or more LKA parameters (if necessary) based on expected forward-looking driving conditions and / or identified specific driving behaviors of the driver. For example, one or more LKA parameters 116 may be adjusted based on real-time detection (e.g., via sensing) of other vehicles, bicycles, sign recognition, road conditions, weather (e.g., crosswind, rain, ice, snow, etc.), based on a map of the area, etc.

[0113] The LKA module 104 may then generate a steering angle control signal 130 based on the lane assist offset value and the LKA parameters from the neural network module 102. In various embodiments, the LKA module 104 may function in a conventional manner based on the received lane assist offset value and the LKA parameters (e.g., modified or unmodified LKA parameters). For example, the LKA module 104 may utilize the adaptive lane assist offset value and the LKA parameters to determine a corrective steering angle.

[0114] Once the corrected steering angle is determined, the LKA module 104 transmits a steering angle control signal 130 having the corrected steering angle (or a representation thereof) to the control module 106 and / or another control module (e.g., a steering control module) in the vehicle. The control module 106 (or the steering control module) then controls the steering of the vehicle based on the generated steering angle control signal 130. For example, the control module 106 may control the steering of the vehicle based on the generated signal 130 via an electronic power steering (EPS) motor and / or via another suitable type of steering system. In such an example, the control module 106 may provide a control signal 132 to the EPS motor and / or another steering system, such as Figure 1 as shown in .

[0115] In various embodiments, a lane turn signal of the vehicle may be automatically triggered when an evasive maneuver is caused by the LKA module 104. For example, if the vehicle position is less than a defined distance from one of the lane markings (e.g., due to an evasive steering maneuver caused by the LKA module 104), the control module 106 may automatically activate a turn signal of the vehicle. In such an example, if the evasive steering maneuver causes the vehicle to turn left and may approach a left lane marking, a left turn signal may be activated, and if the evasive steering maneuver causes the vehicle to turn right and may approach a right lane marking, a right turn signal may be activated. As a result, drivers of neighboring and / or oncoming vehicles may be provided with a warning of the vehicle's movement.

[0116] In various embodiments, the system 100 may take into account driver engagement and / or interaction with respect to the amount of intervention that the LKA module 104 should apply. For example, in some embodiments, the neural network module 102 (and / or another suitable module) may detect or otherwise determine the level of driver engagement based on the pressure applied by the driver while driving (as provided in the driver data 108). In such an example, the pressure applied may be determined by Figure 3 The pressure sensor 306 of the neural network module 102 is detected. Then, if the driver engagement level is below a threshold, the neural network module 102 may generate or adjust the lane assist offset value. For example, the neural network module 102 may associate the engagement value with the detected pressure applied by a specific driver driving under specific conditions (road conditions, vehicle conditions, etc.), and then compare the engagement value to a defined threshold. If the engagement value is below the defined threshold (e.g., indicating a low amount of driver engagement), the neural network module 102 may generate or increase the lane assist offset value. However, if the engagement value is above the defined threshold (e.g., indicating a high amount of driver engagement), the neural network module 102 may not generate or decrease the lane assist offset value.

[0117] Additionally, in some embodiments, the neural network module 102 (and / or another suitable module) may detect or otherwise determine the amount of driver interaction with the vehicle based on the received driver data 108. The neural network module 102 may then adjust the amount of vehicle data (e.g., LKA parameters) provided to the LKA module 104 based on the amount of driver interaction to change the amount of intervention that the LKA module 104 should apply. For example, the neural network module 102 may determine the amount of driver interaction based on the received driver data 108. Figure 3 The amount of driver interaction with the vehicle may be determined based on data from sensors 308 (e.g., applied torque, steering wheel rotation angle, acceleration of turning the steering wheel, etc.). In such an example, the neural network module 102 may determine a driver interaction value based on the received data due to the actions of a specific driver driving under specific conditions (road conditions, vehicle conditions, etc.), and then compare the driver interaction value to a defined threshold. If the driver interaction value is below the defined threshold (e.g., indicating a low amount of interaction), the neural network module 102 may increase the amount of vehicle data (e.g., LKA parameters) provided to the LKA module 104. However, if the driver interaction value is above the defined threshold (e.g., indicating a high amount of interaction), the neural network module 102 may decrease the amount of vehicle data provided to the LKA module 104.

[0118] As this article explains, Figure 1 The neural network module 102 generates an adaptive lane assist offset value for a specific driver driving under specific conditions (road conditions, vehicle conditions, etc.). Before the neural network module 102 can accurately generate the adaptive lane assist offset value and provide it to the LKA module 104, one or more LKA correction algorithms (e.g., machine learning models) in the neural network module 102 are trained.

[0119] For example, Figure 2 Depicted is a block diagram of a system 200 for training a neural network module before the neural network module is used to generate an adaptive lane assist offset value for a driver.

[0120] Figure 2 The system 200 is similar to Figure 1 In some examples, Figure 1-2 Systems 100, 200 may be considered the same system (and may be employed in the same vehicle), where system 200 is used to train a neural network module and system 100 is used to utilize the trained neural network module to generate an adaptive lane assist offset value for a specific driver driving under specific conditions (road conditions, vehicle conditions, etc.).

[0121] like Figure 2As shown in FIG. 1 , the system 200 generally includes a neural network module 202 and a Figure 1 The control module 106. Figure 2 In the example of Figure 1 However, the neural network module 202 is in the training state, while Figure 1 The neural network module 102 is in a training completion state.

[0122] exist Figure 2 In the example of FIG. 1 , the neural network module 202 may be trained based on data received from multiple sources. For example, and as Figure 2 As shown in FIG. 1 , the neural network module 202 receives driver data 108 specific to the driver's driving style when the driver is controlling the vehicle. Such driver data 108 may be obtained by Figure 1 The vehicle sensor(s) 110 and / or Figure 3 In addition, the neural network module 202 receives Figure 1 The non-driver data 112 indicates environmental parameters external to the vehicle while the vehicle is moving, as explained above. In addition, the neural network module 202 receives the LKA parameters 116 (e.g., vehicle data) and data from the IMU 124, as explained above with respect to Figure 1 In such an example, the LKA parameters 116 include, for example, the longitudinal velocity of the vehicle, the steering angle of the vehicle, and the current lane position of the vehicle between lane markings collected by the vehicle sensor(s) 120, as explained above.

[0123] The neural network module 202 then trains one or more LKA correction algorithms (e.g., machine learning models) based on the received data. In such an example, the one or more LKA correction algorithms may be trained individually for multiple drivers associated with the vehicle. For example, a driver may choose to input and / or otherwise notify the system 200 that the driver is currently driving the vehicle. In this way, the neural network module 202 may distinguish between different drivers using the vehicle. Such training may be accomplished in a conventional manner by relying on the received training data. Thus, the neural network module 202 may be trained for each specific driver and according to the driving style of the driver driving under specific conditions (road conditions, vehicle conditions, etc.). This allows the LKA correction algorithm(s) to be trained to recognize driver correction patterns with respect to lane position.

[0124] In various embodiments, neural network module 202 may be trained over a period of time. For example, neural network module 202 may be fully trained within the first few months of vehicle ownership, depending on actual use of the vehicle. Additionally, system 200 may be reset and retrained if necessary. For example, if a vehicle with a trained neural network module is sold and / or a replacement driver is using the vehicle, the driver data may be removed and various values ​​may be reset to default values.

[0125] exist Figure 2 In the example of FIG. 1 , system 200 is shown as not including an LKA module, such as Figure 1 This is because the LKA module is disabled while the LKA correction algorithm(s) of the neural network module 202 are being trained. In other words, the LKA module is not utilized during the training process. Figure 1 The LKA module is not shown, but it is understood that the system 200 may include an LKA module (e.g., a control module 106, etc.) that is disabled and connected to other modules (e.g., Figure 1 In such an example, the LKA module may include an input pin for disabling the module.

[0126] In various embodiments, while the LKA correction algorithm(s) of the neural network module 202 are being trained, the control module 106 and / or another control module (e.g., a steering control module) in the vehicle controls the steering of the vehicle based on the steering angle control signal 230. For example, since the LKA module is disabled during training, the module for controlling the steering of the vehicle cannot generate a steering angle control signal. Therefore, during training, a steering wheel angle sensor (e.g., one of the sensors 110) monitors the rotational position, movement, etc. of the steering wheel and generates the steering angle control signal 230 based on the position, movement, etc. of the steering wheel. The steering wheel angle sensor then transmits the steering angle control signal 230 to the control module 106, which in turn controls the steering of the vehicle based on the steering angle control signal 230.

[0127] Figure 4 The diagram shows the Figure 1 The example control process 400 for controlling an adaptive LKA in a moving vehicle is implemented by the neural network module 102, the LKA module 104, and the control module 106. Figure 1 Although the control process 400 is described with reference to the system 100 of FIG. 1 , it is possible that the control process 400 may be implemented by any suitable system. Figure 4 In the example of FIG. 4 , the control process 400 may be initiated when the system 100 , the vehicle, etc., is powered on and / or at another suitable time.

[0128] like Figure 4 As shown in , control begins at 402, where the trained neural network module 102 receives data from different sources. For example, the trained neural network module 102 receives driver data, non-driver data, LKA parameters, and / or IMU data, as described above with respect to Figure 1 Such data provides information about the driver's driving style, vehicle data from when the driver is controlling the vehicle, and environmental related parameters not based on the driver, such as road geometry, weather, surrounding traffic, obstacles, etc. when the driver is controlling the vehicle. Control then proceeds to 404.

[0129] At 404, control identifies a particular driver of the vehicle. For example, and as explained above, the trained neural network module 102 and / or another suitable module may identify the particular driver from a potential database of associated drivers based on driver data specific to the driver's driving style. In other examples, the trained neural network module 102 and / or another suitable module may identify the particular driver based on a programmed preset, a selected input, etc., as explained above. Control then proceeds to 406.

[0130] At 406, the trained neural network module 102 generates an adaptive lane assist offset value specific to the identified driver. For example, the lane assist offset value may be generated based on the driver data, non-driver data, LKA parameters, and / or IMU data received at 402. In such an example, the adaptive lane assist offset value may vary based on the identified driver, the driver's driving style, and / or how the driver reacts in different geographic locations, conditions, scenarios, etc. (e.g., as detected by one or more detection modules, etc.). Control then proceeds to 408.

[0131] At 408, control determines whether evasive action is required. For example, the LKA module 104 may consider the adaptive lane assist offset value as well as other data, such as the LKA parameters (or adjusted LKA parameters as explained herein). If the LKA module 104 determines based on the LKA parameters (or adjusted LKA parameters) that the vehicle is drifting beyond the adaptive lane assist offset value (e.g., threshold) and evasive action is required, control continues to 410. However, if the LKA module 104 determines based on the LKA parameters (or adjusted LKA parameters) that the vehicle is not drifting beyond the adaptive lane assist offset value and evasive action is not required, control may return to 410. Figure 4 408 or another suitable step, such as 402, as shown in .

[0132] At 410, control generates a steering angle control signal based on the lane assist offset value. For example, and as described above, the LKA module 104 may generate a steering angle control signal based on the adaptive lane assist offset value (e.g., received from the trained neural network module 102) and the LKA parameters (or adjusted LKA parameters as explained herein). The LKA module 104 may then transmit the generated steering angle control signal to the control module 106. Control then proceeds to 412.

[0133] At 412, the control module 106 controls the steering of the vehicle based on the generated steering angle control signal. For example, the control module 106 may control the steering of the vehicle via an EPS motor based on the generated signal and / or in another suitable type of steering system, as explained above. Control may then return to Figure 4 408 or another suitable step, such as 402, as shown in .

[0134] Figure 5 The diagram shows the Figure 1 The example control process 500 for controlling an adaptive LKA in a moving vehicle is implemented by the neural network module 102, the LKA module 104, and the control module 106. Figure 1 Although the control process 500 is described with reference to the system 100 of FIG. 1 , it is possible that the control process 500 may be implemented by any suitable system. Figure 5 In the example of FIG. 5 , control process 500 may be initiated when system 100 , a vehicle, etc., is powered on and / or at another suitable time.

[0135] like Figure 5 As shown in , control begins at 502, where the trained neural network module 102 receives driver data, non-driver data, LKA parameters and / or IMU data, as described above with respect to Figure 1 and 4 Control then proceeds to 504 .

[0136] At 504 , control determines a desired vehicle action based on the received data. For example, the trained neural network module 102 may generate a plan based on sensory inputs such as LKA parameters (or adjusted LKA parameters) and IMU data. Control then proceeds to 506 .

[0137] At 506, control determines whether evasive action is required. For example, and as described above with respect to Figure 4As explained herein, the LKA module 104 may consider the received adaptive lane assist offset value as well as other data, such as LKA parameters (or adjusted LKA parameters), as explained herein. If the LKA module 104 determines that evasive action is required (based on the adaptive lane assist offset value), control continues to 508. If not, control may return to the control module 104 as explained herein. Figure 5 502 shown in .

[0138] At 508, control determines whether the driver is engaged. For example, and as explained above, the neural network module 102 (and / or another suitable module) may determine the level of driver engagement based on the pressure applied to the steering wheel by the driver while driving. In such an example, the neural network module 102 may correlate an engagement value with the detected pressure and then compare the engagement value to a defined threshold. If the engagement value is above the defined threshold (e.g., indicating a high amount of driver engagement), the neural network module 102 may determine that the driver is engaged. In this case, control proceeds to 510.

[0139] However, if the engagement value is below a defined threshold (e.g., indicating a low amount of driver engagement), the neural network module 102 may determine that the driver is not engaged. Control then proceeds to 512 where the LKA module 104 operates based on the adaptive lane assist offset value and other data such as the LKA parameters (or adjusted LKA parameters) as explained herein. Control may then end, as shown in FIG. Figure 5 as shown in, or return to another step, such as 502.

[0140] At 510, control determines whether the driver's action is associated with the desired vehicle action. For example, and as explained above, the neural network module 102 (and / or another suitable module) may determine the driver interaction based on the received driver data. If the driver's action is associated with the desired vehicle action (e.g., indicating that the driver is attempting to manually center the vehicle between lanes), control proceeds to 514, where the LKA module 104 disengages (e.g., at least temporarily). In such an example, the steering of the vehicle may be controlled based on the steering angle control signal generated by the steering wheel angle sensor as explained above. Control then proceeds to 518.

[0141] However, if at 510 the driver's action does not correlate with the desired vehicle action (e.g., indicating that the driver is not attempting to center the vehicle between lanes or is taking an undesirable action), control proceeds to 516. At 516, control determines whether the difference between the driver's action and the desired vehicle action is greater than a threshold. For example, the neural network module 102 and / or the control module 106 may correlate the value of the driver's action with another value of the desired vehicle action. If the difference between the driver's action and the desired vehicle action (e.g., the difference between the values) is less than the threshold, control proceeds to 518. However, if the difference between the driver's action and the desired vehicle action is greater than the threshold, control proceeds to 520, where the data received at 502 is provided to the neural network module 102 for additional training. Control proceeds to 518.

[0142] At 518, control may adjust the magnitude of the LKA parameter (e.g., LKA module feedback) provided to the LKA module 104. For example, the neural network module 102 may decrease the magnitude of the LKA parameter. In turn, the LKA module 104 may adjust corrective actions to provide an improved user experience.

[0143] The foregoing description is essentially merely illustrative and is in no way intended to limit the present disclosure, its application or use. The broad teachings of the present disclosure can be implemented in a variety of forms. Therefore, although the present disclosure includes specific examples, the true scope of the present disclosure should not be so limited, because other modifications will become apparent after studying the drawings, descriptions and appended claims. It should be understood that one or more steps in the method can be performed in different orders (or simultaneously) without changing the principles of the present disclosure. In addition, although each embodiment is described as having specific features above, any one or more of those features described with respect to any embodiment of the present disclosure can be implemented in any other embodiment and / or combined with the features of any other embodiment, even if the combination is not explicitly described. In other words, the described embodiments are not mutually exclusive, and the arrangement of one or more embodiments to each other is still within the scope of the present disclosure.

[0144] The spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.) are described using various terms, including "connected," "engaged," "coupled," "adjacent," "next to," "on top of," "above," "below," and "disposed." Unless explicitly described as "directly," when describing the relationship between a first element and a second element in the above disclosure, the relationship can be a direct relationship, in which there are no other intermediate elements between the first element and the second element, but can also be an indirect relationship, in which there are one or more intermediate elements (spatially or functionally) between the first and second elements. As used herein, the phrase "at least one of A, B, and C" should be interpreted to mean a logical (A or B or C), using a non-exclusive logical "or," and should not be interpreted to mean "at least one of A, at least one of B, and at least one of C."

[0145] In the drawings, the direction of the arrows, as indicated by the arrows, generally demonstrates the flow of information (e.g., data or instructions) of interest to the illustration. For example, when component A and component B exchange various information, but the information transmitted from component A to component B is relevant to the illustration, the arrow may be directed from component A to component B. This unidirectional arrow does not mean that no other information is transmitted from component B to component A. In addition, for information sent from component A to component B, component B may send a request or a receipt confirmation of the information to component A.

[0146] In this application, including the definitions below, the term "module" or the term "controller" may be replaced with the term "circuit". The term "module" may refer to, be part of, or include: an application specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.

[0147] The module may include one or more interface circuits. In some examples, the interface circuit may include a wired or wireless interface connected to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. The functions of any given module of the present disclosure may be distributed between multiple modules connected via the interface circuit. For example, multiple modules may allow load balancing. In a further example, a server (also referred to as a remote or cloud) module may perform some functions on behalf of a client module.

[0148] The term "code" as used above may include software, firmware, and / or microcode, and may refer to a program, a routine, a function, a class, a data structure, and / or an object. The term "shared processor circuit" encompasses a single processor circuit that executes some or all of the code from multiple modules. The term "group processor circuit" encompasses a processor circuit that executes some or all of the code from one or more modules in combination with an additional processor circuit. References to multiple processor circuits encompass multiple processor circuits on discrete dies, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or a combination of the above. The term "shared memory circuit" encompasses a single memory circuit that stores some or all of the code from multiple modules. The term "group memory circuit" encompasses a memory circuit that stores some or all of the code from one or more modules in combination with additional memory.

[0149] The term "memory circuit" is a subset of the term "computer-readable medium". As used herein, the term "computer-readable medium" does not cover transient electrical or electromagnetic signals propagated through a medium (such as on a carrier wave); therefore, the term "computer-readable medium" may be considered to be tangible and non-transitory. Non-limiting examples of non-transitory, tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only memory circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).

[0150] The apparatus and methods described in this application may be implemented in part or in whole by a special purpose computer created by configuring a general purpose computer to perform one or more specific functions embodied in a computer program. The above-mentioned function blocks, flow chart components and other elements serve as software specifications, which can be translated into a computer program by routine work of a skilled technician or programmer.

[0151] The computer program includes processor executable instructions stored on at least one non-transitory tangible computer readable medium. The computer program may also include or rely on stored data. The computer program may include a basic input / output system (BIOS) that interacts with the hardware of the special-purpose computer, device drivers that interact with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.

[0152] A computer program may include: (i) descriptive text to be parsed, such as HTML (Hypertext Markup Language), XML (Extensible Markup Language), or JSON (JavaScript Object Notation), (ii) assembly code, (iii) object code generated by a compiler from source code, (iv) source code for execution by an interpreter, (v) source code for compilation and execution by a just-in-time compiler, etc. By way of example only, the source code may be written using syntax from a language including: C, C++, C#, Objective C, Swift, Haskell, Go, SQL, R, Lisp, Fortran, Perl, Pascal, Curl, OCaml, HTML5 (Hypertext Markup Language Fifth Edition), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Visual Lua, MATLAB, SIMULINK, and

Claims

1. A system for controlling adaptive lane keeping assist in a moving vehicle, the system comprising: The neural network module is configured as: receiving driver data from one or more sensors in the vehicle, the driver data being specific to the driver's driving style while controlling the vehicle; identifying the driver from a plurality of drivers associated with the vehicle; receiving non-driver data indicating an environmental parameter external to the vehicle while the vehicle is moving; as well as generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data; A lane keeping assist (LKA) module in communication with the neural network module, the LKA module being configured to: receiving the lane assist offset value specific to the identified driver; receiving vehicle data associated with one or more parameters of the vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; as well as generating a steering angle control signal based on the received lane assist offset value and the vehicle data; as well as A control module is in communication with the LKA module, the control module being configured to control steering of the vehicle based on the generated steering angle control signal.

2. The system of claim 1, wherein: The driver data and the non-driver data are a first data set, and The neural network module is configured as follows: receiving a second data set including driver data, non-driver data, and vehicle data, the driver data being derived from one or more sensors in the vehicle and being specific to the driving styles of the plurality of drivers associated with the vehicle, the non-driver data being indicative of environmental parameters external to the vehicle while the vehicle is moving, and the vehicle data being associated with the one or more parameters of the vehicle while the vehicle is moving; as well as For each of the plurality of drivers associated with the vehicle, one or more models of the neural network module are trained based on the received second data set.

3. The system of claim 2, wherein the LKA module is disabled while the one or more models of the neural network module are being trained.

4. The system of claim 2, wherein: The steering angle control signal is a first steering angle control signal; and The control module is configured to receive a second steering angle control signal from a steering wheel angle sensor and control the steering of the vehicle based on the received second steering angle control signal while the one or more models of the neural network module are being trained. 5 . The system of claim 1 , wherein the control module is configured to automatically activate a turn signal of the vehicle if the vehicle position is less than a defined distance from one of the lane markings. 6 . The system of claim 1 , wherein the non-driver data comprises at least one of perception data, map data, and traffic sign detection data from one or more detection modules of the vehicle.

7. The system of claim 1 , further comprising the one or more sensors configured to detect the driver data, wherein: The one or more sensors include one or more pressure sensors mounted on a steering wheel of the vehicle and configured to detect applied pressure; and The neural network module is configured to detect a driver engagement level based on the applied pressure and to generate the lane assist offset value if the driver engagement level is below a threshold.

8. The system of claim 1 , wherein the neural network module is configured to determine an amount of driver interaction with the vehicle based on driver data received from the one or more sensors in the vehicle, and to reduce an amount of the vehicle data provided to the LKA module if the amount of driver interaction is above a threshold.

9. The system of claim 1 , wherein the neural network module is configured to identify the driver from among the plurality of drivers associated with the vehicle based on received driver data specific to the driver's driving style.

10. A method for controlling adaptive lane keeping assist in a moving vehicle, the method comprising: receiving driver data from one or more sensors in a vehicle, the driver data being specific to a driver's driving style while controlling the vehicle; identifying the driver from a plurality of drivers associated with the vehicle using a neural network module; receiving non-driver data indicating an environmental parameter external to the vehicle while the vehicle is moving; generating a lane assist offset value specific to the identified driver based on the non-driver data and the driver data; receiving vehicle data associated with one or more parameters of a vehicle while the vehicle is moving, the one or more parameters including steering angle, speed, and vehicle position between lane markings; generating a steering angle control signal based on the lane assist offset value and the vehicle data using a lane keeping assist (KLA) module; as well as The steering of the vehicle is controlled based on the generated steering angle control signal.

Images