Personalized driver-to-vehicle distance for adaptive cruise control

Abstract

The vehicle includes at least one sensor in communication with the controller. The controller includes a ranging module configured to determine an inter-vehicle distance between the vehicle and a leading vehicle traveling in front of the vehicle. The controller further comprises an inter-vehicle distance learning module and an adaptive cruise control module. The inter-vehicle distance learning module is configured to learn a personalized inter-vehicle distance set when the adaptive cruise control module is not engaged. The adaptive cruise control module is configured to maintain the vehicle at a personalized inter-vehicle distance from the leading vehicle when the active cruise control module is engaged.

Description

Technical Field

[0001] This disclosure relates to vehicles, and more particularly to cruise control systems for vehicles. Background Technology

[0002] Traditional cruise control systems for vehicles set a desired speed and maintain it regardless of traffic flow, road conditions, or other factors. Adaptive cruise control (ACC) is an advanced driver assistance system for road vehicles that automatically adjusts the vehicle's speed to maintain a predetermined distance from the vehicle ahead, rather than maintaining a set speed. ACC can also be referred to as dynamic cruise control, among several other similar terms.

[0003] Current adaptive cruise control systems allow the operator to select a distance from a predetermined set of distances, and the ACC system will keep the vehicle at any distance selected by any vehicle in front of the vehicle operating the ACC system. Such systems do not take into account operator preferences and / or driving style, driver reaction time and / or braking distance, exceeding the operator's ability to manually select a distance from a predetermined set of distances to be maintained.

[0004] Therefore, it is desirable to provide an adaptive cruise control system that can take into account driver preferences and driving style as well as current conditions. Summary of the Invention

[0005] In one exemplary embodiment, the vehicle includes at least one sensor in communication with a controller. The controller includes a ranging module configured to determine a vehicle-to-vehicle distance between the vehicle and a lead vehicle traveling ahead of it. The controller also includes a vehicle-to-vehicle distance learning module and an adaptive cruise control module. The vehicle-to-vehicle distance learning module is configured to learn a personalized set of vehicle-to-vehicle distances when the adaptive cruise control module is not engaged. The adaptive cruise control module is configured to maintain the vehicle at a personalized vehicle-to-vehicle distance from the lead vehicle within the personalized set of vehicle-to-vehicle distances when the adaptive cruise control module is engaged.

[0006] In addition to one or more of the features described in this paper, each personalized workshop distance in the personalized workshop distance set corresponds to a unique set of conditions.

[0007] In addition to one or more features described herein, the unique set of conditions includes at least one of speed conditions, traffic conditions, road conditions, and weather conditions.

[0008] In addition to one or more features described in this article, the unique set of conditions includes at least two distinct conditions.

[0009] In addition to one or more features described herein, the shop-to-shop distance learning module includes a neural network trained using a training set of training shop-to-shop distances, wherein each training shop-to-shop distance has a corresponding set of conditions.

[0010] In addition to one or more features described herein, the shop floor distance learning module includes a statistical model configured to estimate shop floor distances that vary over time.

[0011] In addition to one or more of the features described in this paper, the statistical model is a Kalman filter.

[0012] In addition to one or more features described in this paper, the estimated time-varying workshop distance is determined according to the following equation: HdwyEstMeas = (LeadVehDistance / (max(Vx,1))) + uncertainty, where HdwyEstMeas is the estimated personalized workshop distance, LeadVehDistance is the measured physical distance between the vehicle and the lead vehicle, Vx is the current speed of the vehicle, and uncertainty is the uncertainty value of the Kalman filter.

[0013] In addition to one or more of the features described in this article, the personalized vehicle distance set is a driver-specific vehicle distance.

[0014] In addition to one or more features described herein, the set of personalized workshop distances associated with the driver is stored in a matrix with multiple cells, wherein each cell in the matrix corresponds to a different set of unique conditions.

[0015] In another exemplary embodiment, a process for generating a personalized adaptive cruise control vehicle distance includes: monitoring vehicle vehicle distances during a learning operating mode and storing the monitored vehicle vehicle distances as learned vehicle distances. The monitoring includes identifying at least one current condition and associating the at least one current condition with the learned vehicle distance. The method accumulates a sample set of learned vehicle distances having the same at least one current condition until the sample set of learned vehicle distances has a sample size greater than a predefined minimum sample size. The method combines the sample set of learned vehicle distances into a single personalized vehicle distance and provides this single personalized vehicle distance to the adaptive cruise control unit.

[0016] In addition to one or more features described herein, the sample set of ensemble-learned shop floor distances includes statistical analysis of the sample set of shop floor distances performed on the learning process.

[0017] In addition to one or more of the features described in this paper, the statistical analysis includes estimating time-varying shop distances by applying a Kalman filter to a sample set of learned shop distances.

[0018] In addition to one or more features described in this paper, the estimated time-varying workshop distance is determined according to the following equation: HdwyEstMeas = (LeadVehDistance / (max(Vx,1))) + uncertainty, where HdwyEstMeas is the individualized workshop distance, LeadVehDistance is the measured physical distance between the vehicle and the lead vehicle, Vx is the current speed of the vehicle, and uncertainty is the uncertainty value of the Kalman filter.

[0019] In addition to one or more features described herein, the sample set of the combined learned shop distances includes providing the sample set of learned shop distances and at least one corresponding condition as a training set for training shop distances to the neural network.

[0020] In addition to one or more features described in this paper, combining a sample set of learned shop floor distances into a single personalized shop floor distance also includes storing the single personalized shop floor distance in a cell of a matrix.

[0021] In addition to one or more features described in this paper, the matrix defines multiple cells, and each cell corresponds to a different set of unique conditions related to the workshop distance stored in the cell.

[0022] In addition to one or more features described herein, providing a single personalized vehicle distance to the adaptive cruise control unit includes identifying at least one vehicle condition and identifying cells of a matrix, wherein the unique set of conditions of the identified cells matches at least one vehicle condition, and the single personalized vehicle distance provided is a personalized vehicle distance stored in the cells of the matrix.

[0023] In addition to one or more features described herein, the process includes operating adaptive cruise control using a single personalized vehicle distance.

[0024] Apart from one or more features described in this article, the matrix is ​​a driver-specific matrix.

[0025] The above-described features and advantages, as well as other features and advantages, of this disclosure will become apparent when taken in conjunction with the accompanying drawings and the following detailed description. Attached Figure Description

[0026] Other features, advantages, and details appear by way of example only in the following detailed description, which is described in detail with reference to the accompanying drawings, wherein:

[0027] Figure 1 The vehicle is according to the embodiment;

[0028] Figure 2 This is a high-level process for operating an adaptive cruise control system according to an embodiment;

[0029] Figure 3 The illustration shows the operation of a vehicle without the adaptive cruise control system engaged, according to an embodiment.

[0030] Figure 4 The illustration depicts the operation of a vehicle with an engaged adaptive cruise control system according to an embodiment; and

[0031] Figure 5 The illustration depicts the process of operating a driver-specific adaptive cruise control system for a vehicle according to an embodiment. Detailed Implementation

[0032] The following description is exemplary in nature only and is not intended to limit this disclosure, its application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features. As used herein, the term "module" refers to processing circuitry that may include application-specific integrated circuits (ASICs), electronic circuitry, processor (shared, dedicated, or group) and memory executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components that provide the described functionality.

[0033] As used herein, the term controller refers to a dedicated controller including a processor and memory, a general-purpose controller including control modules configured to perform control processes using the dedicated controller, a network of multiple different controllers that communicate with each other and each includes a processor and memory and is configured to cooperate in implementing control processes, and any similar configuration for implementing control processes.

[0034] As used herein, the “inter-vehicle distance” between a first vehicle (leading vehicle) and a second vehicle (following vehicle) traveling along the same trajectory is the amount of time it takes for the second vehicle to reach the position held by the first vehicle. For example, if the leading vehicle passes a marker along the trajectory, the inter-vehicle distance is the amount of time it takes for the following vehicle to pass the same marker along the same trajectory. As can be understood, knowing the current speed of the following vehicle and the inter-vehicle distance allows for the simple calculation of the instantaneous distance between the following and leading vehicles by multiplying the inter-vehicle distance time by the current speed. By defining the inter-vehicle distance in units of time, a process or operator can accurately adapt reaction and braking times by using a baseline inter-vehicle distance and adding reaction and / or braking times to it. This adjustment can be performed using a relatively simple calculation independent of the vehicle's current speed.

[0035] Adaptive cruise control systems typically use the clearance distance between the leading and following vehicles as a representative of the inter-vehicle distance and allow users to adjust the clearance distance to one of a limited number of preset clearance distances (e.g., 20 feet, 30 feet, 40 feet). The adaptive cruise control then uses the speed of the following vehicle to calculate the corresponding inter-vehicle distance and maintains that distance throughout the entire operation of the adaptive cruise control. In existing adaptive cruise control systems, the preset clearance distance cannot be customized for the preferred driving characteristics of a particular driver.

[0036] One or more embodiments described herein utilize two modes. A first "learning mode" monitors inter-vehicle distances during driver vehicle operation and stores the monitored inter-vehicle distances as learned inter-vehicle distances. Furthermore, the learning mode tracks a set of current conditions (e.g., road conditions, weather conditions, traffic conditions, speed limits, and road types) and associates each monitored inter-vehicle distance with a corresponding current condition in the learned set of inter-vehicle distances. The learning mode operates when the adaptive cruise control system is not activated.

[0037] Using the learned set of vehicle distances, the vehicle will adjust the adaptive cruise control vehicle distance stored in the adaptive cruise control from the initial preset value to a value corresponding to the vehicle distance in the learned set of vehicle distances.

[0038] The method and process continuously monitor the driver's driving style under different environmental conditions and situations, and learn the driver's preferred inter-vehicle distance (multiple monitored inter-vehicle distances) for a given set of conditions.

[0039] In one implementation of the control system described herein, the vehicle includes a controller that monitors the vehicle's inter-vehicle distances when the vehicle is in a learning mode. During the learning mode, the controller associates the determined inter-vehicle distances with one or more available corresponding conditions for the driver (e.g., weather type, road conditions, road type, speed limit, etc.) and stores the monitored inter-vehicle distances and associated conditions in the learned set of inter-vehicle distances. After accumulating a sufficient sample size of the monitored inter-vehicle distances (e.g., greater than a threshold amount), the controller determines personalized inter-vehicle distances that match the driver's individual driving style and implements the determined personalized inter-vehicle distances in a personalized adaptive cruise control system.

[0040] In one instance of the implementation, statistical modeling techniques, such as Kalman filtering, are used to correlate the monitored shop-to-shop distances with personalized shop-to-shop distances.

[0041] In another instance of the implementation, the learned driving intervals, along with the corresponding conditions, are processed as a training set for a neural network, and the training set is used to train the neural network to allow adaptive cruise control to generate the determined inter-vehicle distances based on the vehicle's current conditions.

[0042] According to an embodiment, Figure 1 A vehicle 10 including a cruise control controller (controller 20) is shown. Controller 20 includes a vehicle-to-vehicle distance learning module 22 and a personal adaptive cruise control module 24. Controller 20 is also connected to at least one imaging and / or ranging sensor (sensor 30) (e.g., camera, radar device, lidar device, etc., including combinations thereof and / or multiple thereof), wherein sensor 30 is configured to provide controller 20 with sufficient information to detect a second vehicle 11 (leading vehicle, such as a following vehicle) ahead of vehicle 10. Figures 2 to 4 The workshop distance between (as shown).

[0043] In some examples, controller 20 is configured to detect the current inter-vehicle distance of vehicle 10 based solely on image data. In another example, controller 20 is configured to detect the current inter-vehicle distance of vehicle 10 based on ranging data. In yet another example, controller 20 may also include a communication module 28 having at least one of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2X) communication capabilities, thereby allowing vehicle 10 to receive current inter-vehicle distance information transmitted from another vehicle or system. Furthermore, controller 20 is connected to speed sensor 40, which provides vehicle speed feedback data to controller 20.

[0044] Condition input 50 provides controller 20 with one or more data points regarding the conditions under which vehicle 10 is currently operating. As used herein, vehicle conditions refer to any operational or environmental parameters in which the vehicle is currently operating and which may affect reaction time and / or braking time, and therefore require adjustments to the individual inter-vehicle distance for adaptive cruise control. Conditions may be received from other controllers on vehicle 10, including but not limited to vehicle sensors of sensor 30, Global Navigation Satellite System (GNSS), and online data sources such as national meteorological services, internet-based map services, etc.

[0045] The adaptive cruise control module 24 provides control outputs to one or more vehicle systems, such as the drive motor 60. These control outputs enable vehicle operation control, which operates the vehicle 10 using any adaptive cruise control method combined with a personalized inter-vehicle distance.

[0046] about Figure 2 , Figure 3 and Figure 4 Further description Figure 1 The vehicle 10 has the following aspects. Figure 2 The illustration shows an example advanced procedure 200 for operating an adaptive cruise control system. Figure 3 The illustration shows the operation of vehicle 10 without the adaptive cruise control system engaged (referred to as adaptive cruise control system inactive). Figure 4 The illustration shows an example operation of vehicle 10 with the adaptive cruise control system engaged (referred to as the adaptive cruise control system being active).

[0047] Initially, during the operation of vehicle 10, when adaptive cruise control is not activated ( Figure 3 The learning mode is activated. During the learning mode, the controller 20 uses sensors to monitor the inter-vehicle distance 310 in the initial inter-vehicle distance determination step 210. During the first instance of operating the learning mode, the driver calibrates the controller by manually selecting an inter-vehicle distance from a preset set of inter-vehicle distances corresponding to the current inter-vehicle distance of the vehicle 10. The controller then calibrates the learning vector to set the current inter-vehicle distance of the vehicle 10 to the manually selected inter-vehicle distance. The calibration of the learning vector ensures that subsequent operations in the learning mode are provided with a single calibration value, thereby normalizing the operation.

[0048] As the monitored shop-to-shop distances are accumulated in the learned shop-to-shop distance set, this set is stored in memory 26 within controller 20, or at another location accessible to controller 20. Once sufficient shop-to-shop distances have been accumulated in the learned set, the shop-to-shop distance learning module 22 estimates the personalized shop-to-shop distance based on the complete set of learned shop-to-shop distances in the personalized shop-to-shop distance estimation step 220 using a statistical modeling system. In one instance, the statistical model used is a Kalman filter. In alternative examples, alternative statistical modeling may be used.

[0049] As the process continues, in the refinement estimation step 230, the additional learned vehicle distances are accumulated, and the personalized vehicle distances are refined into individual personalized vehicle distances for adaptive cruise control. In a system where road conditions (such as weather, road type, location, time of day, etc.) are associated with the monitored vehicle distances determined in the vehicle distance determination step 210, the statistical modeling and refinement estimation step 230 of step 220 are performed for each available condition or set of conditions, and a single personalized vehicle distance corresponding to each condition or set of conditions is generated. As an example, if the available set of conditions includes paved or unpaved road types and time of day (daytime or nighttime), different personalized vehicle distances are generated for each of paved / daytime, paved / nighttime, unpaved / daytime, and unpaved / nighttime, resulting in four different personalized vehicle distances, where the controller 20 utilizes any personalized vehicle distance corresponding to the current conditions of the vehicle 10.

[0050] In such an example, personalized shop-to-shop distances are stored in a matrix, where each cell corresponds to a unique set of conditions associated with the specific shop-to-shop distance stored in that cell. Below is an example matrix (Matrix I) with traffic conditions (leftmost column) and vehicle speeds closest to 10 miles per hour (top row):

[0051] Speed / Traffic 0 10 20 30 Stop and go 2.25 2.1 1 1 busy 1.5 1 0.8 0.8 normal 2 1.25 1 0.8

[0052] Matrix I

[0053] Although two simple condition matrices are shown for illustrative purposes, it should be understood that the matrix can be multidimensional and can hold any number of conditions and any number of values ​​for those conditions. The limitation on the size of the matrix is ​​a practical limitation of computer processing.

[0054] In a specific example, when adaptive cruise control is not activated and the driver has full control of vehicle 10, controller 20 uses a Kalman / adaptive filter learning process to generate a personalized set of vehicle-to-vehicle distances from the learned set of vehicle-to-vehicle distances. As vehicle 10 continues to operate, controller 20 uses a Kalman filter to estimate continuous vehicle-to-vehicle distances (vehicle-to-vehicle distances that vary over time). For example, the personalized vehicle-to-vehicle distances can be determined using the following equation:

[0055] HdwyEstMeas = (LeadVehDistance / (max(Vx,1))) + Uncertainty

[0056] Where HdwyEstMeas is the personalized workshop distance, LeadVehDistance is the measured physical distance between vehicle 10 and the leading vehicle 11, Vx is the current speed of vehicle 10, and uncertainty is the uncertainty value of the Kalman filter.

[0057] When the HdwyEstMeas value (personalized workshop distance) converges within a specific speed range and / or other condition range (remaining at a single value within tolerance or error range), the value is stored as the final value. In some examples, covariance is used to ensure that the final value is not lower than or higher than the minimum or maximum (respectively) permissible value. Once stored as the final value, in step 250, process 200 records that the matrix cells corresponding to the set of conditions for the final value have been learned and can be implemented in adaptive cruise control.

[0058] After learning the units of the matrix, process 200 verifies the final values ​​in the matrix by incrementing a "valid count" for each unit of the matrix containing the learned values. When the valid count is greater than a predefined constant value (Kcnt), the personalization is considered conditionally valid, and process 200 performs a final validity confirmation check.

[0059] The final validity verification check identifies the differences between each cell of the matrix and every other cell in the matrix, and verifies that all differences are less than a predetermined acceptable value. When all differences are less than the predetermined acceptable value, the final validity verification check is passed, and the learned shop floor distance is considered fully valid.

[0060] Once a sufficient set of fully valid vehicle distances has been determined, process 200 proceeds to the combined estimation step 230, in which the personalized vehicle distances are combined into a final set of personalized vehicle distances that can be used by adaptive cruise control.

[0061] In step 240, the final personalized set of vehicle distances is provided to the adaptive cruise control module 24. Using the adaptive cruise control module 24, the vehicle 10 maintains a vehicle distance 410 that matches the vehicle distance provided corresponding to the current conditions of the vehicle 10.

[0062] Continue to refer to Figures 1 to 4 , Figure 5 A more detailed example process 500 for learning a specific inter-vehicle distance for a given driver is shown. Initially, process 500 begins at start step 502. Start step 502 can be initiated automatically when the driver is identified and the vehicle 10 is engaged in a mode different from the adaptive cruise control mode. In an alternative example, start step 502 can be manually initiated by the driver or other vehicle operator using any manual process initiation.

[0063] After process 500 has been initiated, controller 20 monitors the second vehicle 11 in front of the driver in lead vehicle check 504. If lead vehicle 11 is not detected at step 504, process 500 returns to start step 502. As long as the driver or other vehicle operator does not force a stop to the learning mode, process 500 cycles through start step 502 and lead vehicle check 504 until the second vehicle (lead vehicle 11) in front of vehicle 10 is detected.

[0064] When a lead vehicle 11 is detected ahead of vehicle 10 at step 504, process 500 proceeds to step 506, where process 506 determines a vehicle stability value indicating how stable the current inter-vehicle distance is. At step 508, process 500 determines whether the vehicle is stable in the stability check (i.e., the inter-vehicle distance changes over time within an error tolerance) by comparing the vehicle stability value determined at step 506 with a threshold. When it is determined at step 508 that vehicle 10 is unstable (i.e., the determined vehicle stability value is less than the threshold), process 500 returns to the start step 502.

[0065] When it is determined at step 508 that the vehicle 10 is stable (i.e., the determined vehicle stability value is greater than or equal to a threshold), process 500 proceeds to step 510 and determines whether the driver has engaged the adaptive cruise control system.

[0066] When the adaptive cruise control system is activated, process 500 proceeds to step 512 and extracts the learned vehicle distance corresponding to the current conditions from matrix 524 of learned vehicle distances. Matrix I above provides a simplified example matrix illustration of matrix 524. Then, process 500 proceeds to step 514 and passes the vehicle distance value to controller 20. Process 500 ends at closing step 530.

[0067] When the adaptive cruise control system is not activated at step 510, process 500 begins at step 516 to store the monitored inter-vehicle distances in a learned set of inter-vehicle distances. Step 516 includes performing a sequence of checks 518, where each check corresponds to a potential vehicle condition. In the illustrated example, the sequence of checks 518 includes checks 520 for determining whether vehicle 10 is in stop-and-go traffic conditions and checks 522 for determining whether vehicle 10 is in heavy traffic conditions. In other examples, the sequence of checks 518 may include any number and / or type of conditions, including weather, road type, vehicle location, or any other available conditions.

[0068] The results of each check 520, 522 are provided to matrix 524, where the combined results identify the cell in matrix 524 corresponding to the current set of conditions. Once a matching cell is identified, process 500 calculates the shop floor distance and validity in step 526. This can be based on... Figure 2-4 The described process 200 executes step 526. Then, the process ends in the closing step 530.

[0069] The terms “a” and “an” do not indicate a limitation of quantity, but rather that at least one of the referenced items is present. Unless the context clearly indicates otherwise, the term “or” means “and / or”. Throughout the specification, the reference to “aspect” means that a particular element described in connection with that aspect (e.g., a feature, structure, step, or characteristic) is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in the aspects.

[0070] When an element, such as a layer, film, region, or substrate, is referred to as being “on” another element, it can be directly on the other element, or there may be intermediate elements present. Conversely, when an element is referred to as being “directly” on another element, there are no intermediate elements present.

[0071] Unless otherwise specified herein, all test standards are the most recent standards in effect up to the filing date of this application, or, if priority is claimed, the filing date of the earliest priority application in which a test standard appears.

[0072] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0073] While the foregoing disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from its scope. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this disclosure without departing from the basic scope of this disclosure. Therefore, this disclosure is intended to be limited to the specific embodiments disclosed, but will include all embodiments falling within its scope.

Claims

1. A vehicle comprising: At least one sensor communicating with a controller, wherein the controller includes a ranging module configured to determine a vehicle-to-vehicle distance between the vehicle and a lead vehicle traveling in front of the vehicle; and The controller includes a vehicle distance learning module and an adaptive cruise control module, wherein the vehicle distance learning module is configured to learn a personalized set of vehicle distances when the adaptive cruise control module is not engaged, and wherein the adaptive cruise control module is configured to maintain the vehicle at a personalized vehicle distance from the lead vehicle within the personalized set of vehicle distances when the adaptive cruise control module is engaged.

2. The vehicle according to claim 1, wherein, Each personalized workshop distance in the personalized workshop distance set corresponds to a unique set of conditions.

3. The vehicle according to claim 2, wherein, The unique set of conditions includes at least one of speed conditions, traffic conditions, road conditions, and weather conditions.

4. The vehicle according to claim 3, wherein, The unique set of conditions includes at least two distinct conditions.

5. The vehicle of claim 1, wherein the vehicle-to-vehicle distance learning module comprises a neural network trained using a training set of training vehicle-to-vehicle distances, wherein each training vehicle-to-vehicle distance has a corresponding set of conditions.

6. The vehicle of claim 1, wherein the vehicle-to-vehicle distance learning module includes a statistical model configured to estimate the vehicle-to-vehicle distance as it changes over time.

7. The vehicle according to claim 6, wherein, The statistical model is a Kalman filter.

8. The vehicle according to claim 7, wherein, The estimated time-varying shop distance is determined using the following equation: HdwyEstMeas = (LeadVehDistance / (max(Vx,1))) + uncertainty; Where HdwyEstMeas is the estimated personalized workshop distance, LeadVehDistance is the measured physical distance between the vehicle and the lead vehicle, Vx is the current speed of the vehicle, and uncertainty is the uncertainty value of the Kalman filter.

9. The vehicle according to claim 1, wherein, The personalized workshop distance set is the workshop distance specific to the driver.

10. The vehicle according to claim 1, wherein, The set of personalized workshop distances associated with the driver is stored in a matrix with multiple cells, wherein each cell in the matrix corresponds to a different set of unique conditions.

Images