Vehicle control based on driver behavior

Abstract

The invention provides vehicle control based on driver behavior. A vehicle may, among other things, allocate resources within the vehicle using a predicted vehicle speed change rate based on past driving data of a particular user to reproduce behavior of the particular user in an automated driving system, or accurately predict the ability of the vehicle.

Description

Technical Field

[0001] The present disclosure relates to automotive technology. Background Art

[0002] Vehicles can use energy for propulsion. Summary of the invention

[0003] A vehicle may include a battery thermal management system and a controller. The controller may use data to change a cooling rate of the battery thermal management system. The data may include a specific user operating the vehicle and a predicted rate of change of the vehicle speed from a current speed to a target speed. The predicted rate of change of speed may be derived from data indicating that the specific user is driving the vehicle when the speed changes from the current speed to the target speed. The controller may change the cooling rate such that a greater rate of change results in a greater change.

[0004] A method may generate personalized adaptive cruise control behavior by obtaining data about a user and a predicted speed rate of change, and then applying the user information and the predicted speed rate of change to an adaptive cruise control system. The data about the user may include historical driving data generated by one or more vehicles driven by the user. The predicted vehicle speed rate of change may be generated by a machine learning model using the historical driving data as input. Applying the data and the predicted speed rate of change to an adaptive cruise control system may adjust control operations of the adaptive cruise control system.

[0005] A method may affect the accuracy of a distance to energy prediction by calculating the distance to energy; obtaining data about a user and a predicted rate of change of speed; and then adjusting the distance to energy based on the data and the predicted rate, such that the greater the predicted rate, the greater the adjustment. The data about the user may include historical driving data generated by one or more vehicles driven by the user. The predicted rate of change of speed may be generated by a machine learning model using the historical driving data as input. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 A vehicle is shown that includes a controller that adjusts a battery thermal management system based on the particular user driving the vehicle.

[0007] Figure 2 An approach employed by a controller for generating personalized adaptive cruise control behavior is shown.

[0008] Figure 3 Methods employed by the controller to influence the accuracy of the range-to-empty prediction are shown.

[0009] Figure 4An example speed versus time graph generated for a user based on route information is shown.

[0010] Figure 5 A flow chart illustrating an example method for updating a predicted rate of change of speed for a particular user.

[0011] Figure 6 An example speed versus time graph of data acquired during a particular user's ride is shown.

[0012] Figure 7 An example table for storing predicted speed change rates for a particular user is shown. DETAILED DESCRIPTION

[0013] Embodiments are described herein. However, it should be understood that the disclosed embodiments are merely examples and that other embodiments may take various and alternative forms. The drawings are not necessarily drawn to scale. Some features may be enlarged or minimized to show details of particular components. Therefore, the specific structural details and functional details disclosed herein should not be interpreted as limiting, but merely as a representative basis for teaching those skilled in the art.

[0014] The various features shown and described with reference to any one of the accompanying drawings may be combined with features shown in one or more other drawings to produce embodiments not explicitly shown or described. The combinations of features shown provide representative embodiments for typical applications. However, for specific applications or implementations, various combinations and modifications of features consistent with the teachings of the present disclosure may be desired.

[0015] Depending on the behavior that is unique to a particular user, the same vehicle may use different amounts of energy in an otherwise equivalent use. One aspect of the behavior is the rate of change of speed of the vehicle when the particular user operates the vehicle. Therefore, a vehicle using a predicted rate of change of speed based on past driving data of a particular user and generated via a machine learning model that takes the past driving data as input can effectively allocate resources to subsystems of the vehicle (e.g., a battery cooling system), can accurately predict the capabilities of the vehicle (e.g., the remaining energy range), or can reproduce the behavior of a particular user during operation of an autonomous driving system (e.g., adaptive cruise control). The machine learning model can be trained based on a collection of actual speed change data for a variety of drivers and a variety of initial and final speeds.

[0016] Vehicles may collect various data about the vehicle itself, the environment, or the driver's behavior. For example, a vehicle may periodically collect data about the vehicle's fuel level to output the expected range until the vehicle idles or output the average fuel economy. Some vehicles output information about ambient temperature or generate alerts about potential road icing. Some examples may involve sensors and displays as well as data storage and manipulation. Some examples may also include applying the collected data to optimize the vehicle's systems.

[0017] In many vehicles, some systems may be affected by the driving style of a particular user. For example, consider driver A, who accelerates and decelerates at a greater rate of speed change than other recorded drivers. Further consider driver C, who is a conservative driver who accelerates and decelerates at a lower rate of speed change than the average of all drivers. For example, in some vehicles, driver A may cause the motor to generate more heat than driver C.

[0018] In a battery powered electric vehicle, many systems may be affected by the driving style of a particular user. For example, consider Driver A and Driver C as described above. Under otherwise equivalent usage conditions, Driver A may consume more energy, reduce the vehicle's range by a greater amount, and cause the battery to generate more heat than Driver C.

[0019] The system disclosed herein can collect, analyze, and apply data to accurately predict the remaining energy drivable distance of a vehicle, cool the vehicle's power system, or adjust the vehicle's adaptive cruise control system. For example, consider driver A and driver C as described above. In other equivalent use cases, a vehicle that stores and updates driving data specific to driver A and driver C can apply the data of each driver so that the battery thermal management system can be configured to remove more heat from the battery when driver A is driving, and can be configured to remove less heat from the battery when driver C is driving. In other words, the vehicle can anticipate the demand for the battery thermal management system based on the user's past behavior, and can allocate resources based on the expected demand.

[0020] The vehicle here can collect data about the speed of the vehicle. In instances where the vehicle accelerates so that the speed increases monotonically within the interval created by the initial speed and the final speed, the vehicle can also collect the average acceleration by dividing the interval by the time it takes the vehicle to cross the interval. For example, if the vehicle initially moves at 10mph and accelerates to 25mph in 2 seconds, the interval will be (25mph-10mph)=15mph, the time it takes the vehicle to cross the interval will be 2s, and therefore the average acceleration will be 15mph / 2s=7.5mph / s. Embodiments can use any units.

[0021] In instances where the speed of the vehicle is not increasing monotonically, the collected data may be discarded.The vehicle may use filters other than monotonicity, such as by discarding the current speed rate of change if it is not sufficiently different from the predicted speed rate of change.

[0022] Similarly, in instances where the vehicle decelerates such that the speed decreases monotonically within the interval created by the initial and final speeds, the vehicle can also collect an average deceleration by dividing the interval by the time it takes the vehicle to cross the interval. For example, if the vehicle initially moves at 55 mph and decelerates to 0 mph in 5.5 seconds, the interval would be (0 mph - 55 mph) = -55 mph, the time it takes the vehicle to cross the interval would be 5.5 s, and therefore the average deceleration would be -55 mph / 5.5 seconds = -10 mph / s.

[0023] In instances where the vehicle's speed is not decreasing monotonically, the collected data may be discarded.The vehicle may use filters other than monotonicity, such as by discarding the current speed rate of change if it is not sufficiently different from the predicted speed rate of change.

[0024] Equivalent to storing acceleration or deceleration data, the vehicle can collect a description of how long it takes for the vehicle to accelerate or decelerate monotonically from an initial speed to a final speed when a specific user uses the vehicle. The vehicle can predefine the speed interval between the initial speed and the final speed to store the time data. In an instance where the vehicle accelerates within an actual interval greater than a predefined interval, the vehicle can collect the time for each predefined interval within the actual interval. For example, if the speed of the vehicle increases monotonically from 6mph to 36mph (36mph-6mph=30mph actual interval) and the predefined interval is 3mph (e.g., 0-3mph, 3-6mph, ..., 30-33mph, 33-36mph), the vehicle can record and store the time it takes for the vehicle to accelerate within each of the ten predefined intervals.

[0025] The vehicle here can store predictions (average acceleration values ​​and average deceleration values) and continually update these predictions as a particular user uses the vehicle. For example, consider driver A and driver C as described above. The vehicle may have stored a prediction that driver A will accelerate from 5mph to 10mph in 0.30 seconds and a second prediction that driver C will accelerate from 5mph to 10mph in 1 second. If the vehicle accelerates from 5mph to 10mph in 0.5 seconds while driver A is using the vehicle, the vehicle can update the prediction specific to driver A without changing the second prediction specific to driver C. The predictions after the update can be, for example: driver A will accelerate from 5mph to 10mph in 0.33 seconds, and driver C will accelerate from 5mph to 10mph in 1 second.

[0026] To update the predicted speed, the user can generate the current speed rate by changing from the initial speed to the final speed. The vehicle can record this current speed.

[0027] To update the predicted rate, the vehicle can compare the current rate of change of speed with a threshold value. In an embodiment using this method, if the actual rate is less than the threshold value, the vehicle can prevent the update, but if the actual rate is greater than the threshold value, the vehicle can use the actual rate to update the predicted rate.

[0028] The vehicle may discard the current rate of speed change before updating unless the vehicle accelerates or decelerates monotonically within the speed interval.

[0029] The vehicle herein can use a machine learning algorithm to capture, test, generate and / or update predictions. For example, a machine learning algorithm can be used to collect a subset of actual speed change rates from a larger data set collected while driving. In another example, a machine learning algorithm can be used to verify a set of initialization values ​​or update values. In another embodiment, a machine learning algorithm can be used to update stored values.

[0030] In an example embodiment using a machine learning algorithm to update the predicted rates using the current rates, the current rates can be randomly assigned to the training or test data sets. Then, when a certain condition is met, such as when the training and test sets have grown by 10% since the last time the predicted rates were updated, the machine learning algorithm can be retrained to generate a new set of predicted rates for all speed intervals.

[0031] The vehicle herein may incorporate additional information when changing systems such as the battery thermal management system. For example, assume that the predicted rate will cause the controller to increase cooling by 2% without incorporating additional information. If the controller uses additional information, such as the presence of a congested route or work zone ahead, the controller may only increase cooling by 1.2%.

[0032] The vehicle herein may store the predicted values ​​for later recall. One embodiment may include storing the predicted values ​​in a table. In this embodiment, one axis of the table may include the initial speed, another axis of the table may include the final speed, and the cell at the intersection of the initial speed and the final speed may include a predicted value. The predicted value may correspond to time or a rate of change of the vehicle speed.

[0033] The vehicle herein may store multiple predicted values ​​corresponding to multiple users. One embodiment using a table constructed as above to store predicted values ​​may have one table per user. In this embodiment, the predicted values ​​for a specific user currently using the vehicle may be called, updated, or applied from the storage device without affecting the predicted values ​​for other users.

[0034] Here, the vehicle may apply at least one predicted value to optimize the vehicle's system. For example, consider driver A and driver C as described above. The vehicle may estimate that the vehicle may generate more heat when driver A is using the vehicle than when driver C is using the vehicle based on a predicted value specific to driver A and a second predicted value specific to driver C. Therefore, the vehicle may increase the activity of the cooling system when driver A is using the vehicle and reduce the activity of the cooling system when driver C is using the vehicle.

[0035] The vehicle may combine the additional information with at least one predicted value to optimize the vehicle's systems. For example, if a user enters a route into the vehicle's navigation system, the vehicle may use speed limit data along the route to generate an expected speed over the estimated duration of the route. The vehicle may then apply the predicted acceleration value for the specific user to any change in expected speed to adjust the duration, thereby producing a driving profile personalized for the specific user. This driving profile may then be used to prepare resources in advance of the expected speed change, such as by allocating more power to the cooling system to begin cooling the battery in advance of the expected speed change.

[0036] Here, the vehicle may use at least one predicted value to display personalized information to the user. For example, consider driver A and driver C as described above. One embodiment may include two otherwise equivalent vehicles, where the remaining energy range displayed to driver A is lower than that displayed to driver C because the predicted rate of change for driver A is greater than that for driver C.

[0037] Thus, the vehicle may use information about the user's past rate of speed change from an initial speed to a final speed to generate a predicted rate from the initial speed to the final speed. The predicted rate may be applied to the vehicle's systems to adjust their outputs. For example, the vehicle may use information that driver A accelerated from 10mph to 20mph in 0.5 seconds in the past to predict that driver A will accelerate from 10mph to 20mph in 0.5 seconds in the future. The controller may apply the prediction to the cooling system to adjust the cooling rate based on more efficiently cooling the vehicle. The controller may apply a method to obtain the prediction and then apply it to an adaptive cruise control system to simulate the user's acceleration pattern. The controller may employ a method to calculate the remaining energy range, obtain the prediction, and then adjust the remaining energy range based on the prediction.

[0038] The vehicle may include a system and a controller. The controller may be configured to change the output of the system based on a stored predicted vehicle speed change rate, such that the greater the stored predicted rate, the greater the change. For example, consider driver A and driver C as described above. If the system is a battery thermal management system, the vehicle may be configured to use driver A's predicted vehicle speed change rate from an initial speed to a final speed, the predicted vehicle speed change rate derived from data of driver A's previous transition from an initial speed to a final speed, to change the battery thermal management system to a greater extent (e.g., a greater flow rate, increased power, etc.) for the same initial speed to final speed change compared to driver C because driver A has a greater predicted speed change rate when transitioning from the initial speed to the final speed than driver C. Other systems are contemplated that may include an inverse relationship between the predicted rate of change and the change in the system.

[0039] To generate a personalized cruise control experience, the vehicle can use the user's predicted rate of change of speed to change the control operation of the cruise control system. The cruise control system can autonomously maintain a substantially constant speed, including when traveling on inclined or downhill terrain. Fluctuations in the speed of the vehicle occur in response to changing environmental conditions. For example, if the cruise control system maintains a vehicle speed of 35mph on level ground, and the vehicle begins to climb a hill, the vehicle speed may fluctuate to 30mph. An adaptive cruise control system includes a feedback system in which a fluctuation in reduced speed generates an increased motor input, and in which a fluctuation in increased speed generates a reduced motor input or the activation of another vehicle system. In the previous example, after recognizing that the speed of the vehicle has fluctuated to 30mph, the cruise control system can increase the motor input to restore the vehicle to 35mph when climbing a hill.

[0040] The vehicle can use the current driver's predicted rate of change to cause personalized corrective measures when varying the energy to the motor to maintain a constant speed in response to changing environmental conditions. For example, consider Driver A and Driver C as described above. Driver A's cruise control system can cause more energy to be delivered to the motor in response to changing environmental conditions to cause the vehicle to return to a constant speed in less time than Driver C in an otherwise equivalent situation.

[0041] When the distance between the vehicle and the second vehicle in front of the vehicle decreases, the cruise control system may cause a deceleration. The vehicle may use the predicted rate of change of the current driver to cause a personalized deceleration. For example, consider driver A and driver C as described above. In other equivalent situations, a cruise control system personalized for driver A may cause a greater deceleration than a cruise control system personalized for driver C.

[0042] The cruise control system may cause acceleration from an initial speed to a final speed. The vehicle may use the predicted rate of change of the current driver to cause personalized acceleration. For example, consider driver A and driver C as described above. In other equivalent situations, a cruise control system personalized for driver A may cause a greater acceleration than a cruise control system personalized for driver C.

[0043] The cruise control system may use additional information, such as route information, including directions, speed limits along the route, traffic along the route, weather, ambient temperature, or battery remaining distance to adjust the control operation of the cruise control system. For example, consider driver A as described above. Under otherwise equivalent circumstances, a cruise control system personalized for driver A may result in a greater deceleration on a clear sunny day than on a frozen snowy day. Adjustment factors may be defined for any predetermined criteria in the additional information category.

[0044] Figure 1 A vehicle is shown that includes a controller that adjusts a battery thermal management system based on the particular user driving the vehicle. Figure 1 A vehicle 102 is included. The vehicle 102 includes a controller 104, a battery thermal management system 106, and a battery 110. The controller 104 is connected to the battery thermal management system 106. Typically, the battery thermal management system regulates the temperature of the battery. Here, the battery thermal management system 106 includes at least one cooling device or method 108 to regulate the temperature of the battery 110. Typically, the cooling device or method may or may not enclose the battery. Here, encapsulation is depicted for teaching purposes and is not intended to be limiting.

[0045] The controller 104 can adjust the battery thermal management system 106 based on the specific user and based on the predicted rate of change of speed of the vehicle 102. For example, consider driver A and driver C as described above. If driver A is operating the vehicle 102, the controller 104 can direct the battery thermal management system 106 to increase the cooling effect of the cooling device or method 108 to keep the battery 110 within the predefined operating temperature. Alternatively, if driver C is operating the vehicle 102, the controller 104 can direct the battery thermal management system 106 to maintain the cooling effect of the cooling device or method 108. By distinguishing the driving styles of driver A and driver C, the vehicle 102 therefore more effectively allocates resources to the battery thermal management system 106.

[0046] In one embodiment, once the user enters the vehicle and enters route information, the vehicle can determine the adjustment parameters. By applying the user's past behavior to the speed profile expected by the route information, the controller 104 can adjust the battery thermal management system 106 proactively rather than reactively.

[0047] Figure 2An approach employed by a controller for generating personalized adaptive cruise control behavior is shown. Figure 2 A controller 202 is included that incorporates user information 210 and a predicted rate of speed change 208 to adjust an adaptive cruise control 204. The controller 202 adjusts the adaptive cruise control 204 to generate a personalized adaptive cruise control behavior 206. The predicted rate of speed change 208 is calculated based on at least historical data 212 associated with the user information 210.

[0048] In one embodiment, other information 214 is also used to calculate predicted speed rate 208. Other information 214 may include information related to the proposed route input, information about weather, information about temperature, or information about traffic. Those examples of other information 214 may be combined or included with other examples known to one of ordinary skill in the art to calculate predicted speed rate 208. For example, if the other information includes that the weather is currently raining, predicted speed rate 208 may be reduced.

[0049] Controller 202 is defined herein as any embodiment capable of employing the claimed method of adjusting adaptive cruise control 204 by using user information 210 and predicted speed rate of change 208. In one embodiment, controller 202 and adaptive cruise control 204 may be part of the same system. In another embodiment, the following are all part of a single controller: user information 210, historical data 212, other information 214, predicted speed rate of change 208, controller 202, adaptive cruise control 204, and generated personalized adaptive cruise control behavior 206. In other embodiments, controller 202 may be replaced by an electrical component, other component, multiple components, a different system, or a subsystem that includes adaptive cruise control 204.

[0050] Figure 3 Methods employed by the controller to influence the accuracy of the range-to-empty prediction are shown. Figure 3 A controller 308 is shown that is defined as being capable of any embodiment of the claimed method. The controller 308 calculates the range to empty 302 by, for example, comparing the charge percentage to the estimated range to empty stored in a lookup table, user information 304, and predicted rate of speed change 306, and then outputs an adjusted range to empty 310.

[0051] For example, consider driver A and driver C as described above. Because driver A's user information and predicted rate of speed change indicate that driver A will deplete the battery faster than the average driver, the method may generate an adjusted distance to empty 310 that is less than the calculated distance to empty 302 for driver A. However, for driver C, the method may generate an adjusted distance to empty 310 that is greater than or equal to the calculated distance to empty 302 because driver C's user information and predicted rate of speed change indicate that driver C will deplete the battery at a rate that is less than or equal to the average driver.

[0052] In one embodiment, the controller 308 calculates the calculated distance to empty 302. In one embodiment, one of the user information or the predicted speed rate of change is stored separately from the controller 308.

[0053] Figure 4 An example speed versus time graph generated for a user based on route information is shown. Figure 4 An example relationship between a time 402 that a vehicle has traveled and a speed 404 that depends on the time 402 is shown. At various times, the graph shows a horizontal solid line representing an expected constant speed, such as a first constant speed 406. At other times, the graph shows an inclined dashed line representing an expected speed change, such as a first expected speed change 408 and a second expected speed change 412. Two expected speed changes 410, 414 are also depicted near the second expected speed change rate 412.

[0054] For example, consider Driver A and Driver C as described above. The vehicle can generate a default graph of expected constant speed and expected speed change. The vehicle can then use information derived from historical information and, in some examples, generated via a machine learning model to adjust the expected speed change to produce a driver A-specific expected speed change 410 that is different from the driver C-specific speed change 414. For brevity, this example only discusses adjusting the second expected speed change and is not intended to be limiting. By generating a default graph of expected constant speed and expected speed change, the vehicle can generate a default graph of expected constant speed and expected speed change. Figure 4 When incorporating the past driving behavior of a particular driver into the route information depicted in FIG. 40 , the vehicle may adjust all or any subset of the expected speed changes to better predict the time 402 and the resources that the vehicle is expected to use.

[0055] Figure 5 A flow chart illustrating an example method for updating a predicted rate of change of speed for a particular user. Figure 5A first step 502 is included to collect driving data to obtain the actual speed change rate from the current user's behavior. A second step 504 includes segmenting the actual speed change rate based on a predefined step size (such as 5 mph). For example, using a 5 mph step size, if the actual speed change rate is collected when the driver changes from 55 mph to 75 mph, the actual change rate will be divided into four 5 mph segments: 55 mph to 60 mph, 60 mph to 65 mph, 65 mph to 70 mph, and 70 mph to 75 mph.

[0056] In one embodiment, each segment generated by the second step 504 proceeds individually through the third step 506 and the remainder of the flowchart. For didactic purposes, the following example will discuss the 55mph to 60mph segment ("55 to 60 segment") generated by the second step 504 above. The third step 506 includes testing whether the speed within the segment is monotonically increasing or monotonically decreasing. If the third step 506 results in the speed within the segment monotonically increasing or decreasing, the process moves to the fourth step 508. If the third step 506 results in the speed within the segment not monotonically increasing or decreasing, the process moves to the first management step 520.

[0057] In the fourth step 508, the actual time between the initial speed and the final speed is calculated. The fifth step 510 may occur before the fourth step 508 or simultaneously with the fourth stage, and may occur at a different location than the fourth step 508. The fifth step 510 includes querying whether the vehicle has a stored value assigned to the segment generated by the second step 504. The stored value may be saved in the first storage device online or offline. For example, the fifth step 510 for the 55 to 60 segment may include querying the data storage device to determine whether the vehicle has stored data to move the vehicle from 55 mph to 60 mph.

[0058] If the fifth step 510 results in the vehicle not having a stored value assigned to the segment generated by the second step 504, the process moves to the initial assignment step 518, where the actual time generated by the fourth step 508 becomes the stored value. For example, if the fifth step 510 does not return a stored value for the historical speed change rate from 55mph to 60mph specific to a particular driver, the data recorded for the 55 to 60 segment will be assigned to that stored value. Some intermediate calculations or manipulations, including the application of a machine learning algorithm, may be included before the assignment. If the fifth step 510 results in the vehicle does have a stored value for the segment generated by the second step 504, the process moves to the sixth step 512.

[0059] In a sixth step 512, the difference between the stored value and the actual rate of change of speed generated by the fourth step 508 is calculated, referred to as the "delta". In a seventh step 514, the delta is compared to a predetermined threshold error. If the delta is less than the predetermined threshold error, the process moves to the first management step 520. Otherwise, the process moves to an eighth step 516.

[0060] In an eighth step 516, the actual time generated by the fourth step 504 is used to update the stored value. The update may include calculations involving assigning weights to the stored value and the actual time. The update may include assigning the actual time to a training or test data set used to create or update the machine learning model. The update may include the application of the machine learning model. After the eighth step 516, the process moves to a second management step 524.

[0061] The first management step 520 includes testing whether all data from the first step 502 has been completely processed. If all data has been processed, the process reaches a first termination 522, where the update activity stops. If there is still data to be processed, the process moves to the next iteration 528. The next iteration 528 processes the remaining segments. For example, if the 55 to 60 segment is completed, the next iteration 528 can start the third step 506 with one of the 60mph to 65mph segment, the 65mph to 70mph segment, or the 70mph to 75mph segment.

[0062] The second management step 524 includes testing whether all data from the first step 502 has been completely processed. If all data has been processed, the process reaches a second termination 526, where the vehicle can update the second storage device and then stop the update activity. In one embodiment, the first storage device is an offline storage device and the second storage device is an online storage device. If not all data has been processed, the process moves to the next iteration 528.

[0063] Figure 6 An example speed versus time graph of data acquired during a particular user's ride is shown. Figure 6 An example relationship between a time 602 that a vehicle has traveled and a speed 604 that is dependent on the time 602 is shown. Figure 4 The graph shows the predicted speed and predicted speed change, while Figure 6 The graph shows an example of actual speeds collected during driving.

[0064] Figure 7 An exemplary table for storing predicted speed change rates for a particular user is shown. Figure 7The stored value associated with the predicted rate of change of speed between the initial speed 702 and the final speed 704 is shown. In one embodiment, the stored value is the time taken to move from the initial speed to the final speed. For example, t4 706 is the stored value in the cell at the intersection of the initial speed = 15 mph and the final speed = 20 mph.

[0065] By Figure 6 The curve graph is input into the first step 502 to start Figure 5 The update process is applied to Figure 6 The curve graph and Figure 7 In a second step 504, the data is segmented into 5 mph segments titled t1 606, t2 608, t3 610, t3' 612, t2' 614. For the sake of teaching simplicity, only these segments are discussed, but all potential segments or any subset of potential segments can be evaluated. Segment t1 606 corresponds to a monotonic acceleration from 0 mph to 5 mph. Segment t2 608 corresponds to a monotonic acceleration from 5 mph to 10 mph. Segment t3 610 corresponds to a monotonic acceleration from 10 mph to 15 mph. Segment t3' 612 corresponds to a monotonic deceleration from 15 mph to 10 mph. Segment t2' 614 corresponds to a monotonic deceleration from 10 mph to 5 mph.

[0066] Because all segments are either monotonically increasing or monotonically decreasing, all segments will pass the third step 506, although in some embodiments only one segment will be tested at a time.

[0067] In an embodiment where the stored values ​​are saved in a table format, t1 606, t2 608, t3 610, t3' 612, and t2' 614 will update or initialize the cells at the intersection of the initial speed axis 702 and the final speed axis 704 corresponding to the initial speed and final speed of the segment, respectively. For example, t1 606 will update or initialize the cells at the intersection of initial speed = 0 mph and final speed = 5 mph. Similarly, t3' 612 will update or initialize the cells at the intersection of initial speed = 15 mph and final speed = 10 mph.

[0068] Note the 65-20 cell 708 at the intersection of initial speed = 65 mph and final speed = 20 mph. The example process using a fixed 5 mph step size does not allow the 65-20 cell 708 to carry a value because the deceleration data from 65 mph to 20 mph will be divided into 5-mph segments. Different embodiments may allow the 65-20 cell 708 to carry a value.

[0069] Figure 7The scaling of the table shows that the table only depicts the stored values ​​associated with the increased speed. In such an embodiment, the values ​​associated with the reduced speed will be stored elsewhere. However, in other embodiments, the data associated with both the increased speed and the reduced speed are captured in the same table. In yet other embodiments, the data associated with both the increased speed and the reduced speed may be contained in different data structures.

[0070] The algorithm, method or process disclosed herein may be delivered to or implemented by a computer, a controller or a processing device, which may include any dedicated electronic control unit or a programmable electronic control unit. Similarly, the algorithm, method or process may be stored in various forms as data and instructions that can be executed by a computer or a controller, including but not limited to information permanently stored on a non-writable storage medium such as a read-only memory device and information that can be modified and stored on a writable storage medium such as an optical disk, a random access memory device or other magnetic and optical media. The algorithm, method or process may also be implemented by a software executable object. Alternatively, a suitable hardware component (such as an application-specific integrated circuit, a field programmable gate array, a state machine or other hardware component or device) or a combination of firmware, hardware and software components may be used to embody the algorithm, method or process in whole or in part.

[0071] Although exemplary embodiments are described above, these embodiments are not intended to describe all possible forms covered by the claims. The words used in the specification are descriptive rather than limiting, and it should be understood that various changes can be made without departing from the spirit and scope of these disclosed materials. For example, the terms "controller" and "multiple controllers" can be used interchangeably herein because the functionality of a controller can be distributed across several controllers / modules, which can all communicate via standard technologies.

[0072] As previously described, features of the various embodiments may be combined to form additional embodiments of the invention that may not be explicitly described or shown. Although various embodiments may have been described as providing advantages or being preferred over other embodiments or prior art implementations with respect to one or more desired characteristics, it will be appreciated by those of ordinary skill in the art that one or more features or characteristics may be compromised to achieve desired overall system properties, depending on the specific application and implementation. These properties may include, but are not limited to, strength, durability, marketability, appearance, packaging, size, serviceability, weight, manufacturability, ease of assembly, and the like. For this reason, embodiments that are described as being less desirable than other embodiments or prior art implementations with respect to one or more characteristics are within the scope of the present disclosure and may be desirable for a particular application.

[0073] According to the present invention, a vehicle is provided, which has: a battery thermal management system; and a controller, the controller being programmed to change the cooling rate of the battery thermal management system according to the predicted rate for a specific user and in response to a predicted speed change rate from a current speed to a target speed derived from data indicating that the specific user is driving the vehicle when the speed of the vehicle changes from a current speed to a target speed, such that the greater the predicted rate, the greater the change.

[0074] According to an embodiment, the controller is further programmed to update the predicted rate according to the current rate in response to a difference between the predicted rate and the current rate of change being greater than a predetermined threshold.

[0075] According to an embodiment, the controller is further programmed to use a machine learning algorithm to perform the updating.

[0076] According to an embodiment, the controller is further programmed to update the predicted rate according to the current rate in response to a difference between the predicted rate and the current rate being greater than a predetermined threshold and the current rate being defined by a monotonically increasing or monotonically decreasing value.

[0077] According to an embodiment, the controller is further programmed to, in response to the current rate being defined by a non-monotonically increasing or non-monotonically decreasing value, prevent the updating regardless of the difference value.

[0078] According to an embodiment, the controller is further programmed to vary the cooling rate further in response to at least one of weather, driving conditions, ambient temperature, or a predicted route.

[0079] According to the present invention, a method for generating personalized adaptive cruise control commands includes: obtaining (i) data about a user, including historical driving data generated by one or more vehicles driven by the user, and (ii) a predicted vehicle speed change rate generated by a machine learning model using the historical driving data as input; and applying the data and the predicted rate to an adaptive cruise control system of the vehicle to adjust the control operation of the adaptive cruise control system.

[0080] In one aspect of the present invention, the method includes updating the historical driving data when the user generates an actual speed change rate by changing from an initial speed to a final speed.

[0081] In one aspect of the invention, the updating is in response to a difference between the actual speed change rate and the predicted speed change rate exceeding a threshold.

[0082] In one aspect of the invention, the method comprises preventing said updating when said vehicle moves non-monotonically from said initial speed to said final speed.

[0083] In one aspect of the present invention, the application further includes at least one of route information, weather, ambient temperature, or a driving distance with remaining battery energy.

[0084] In one aspect of the invention, the control operation of the adaptive cruise control system includes deceleration in response to a decrease in distance to a leading vehicle.

[0085] In one aspect of the present invention, the control operation of the adaptive cruise control system includes accelerating from an initial speed to a final speed.

[0086] In one aspect of the invention, the control operation of the adaptive cruise control system includes autonomously maintaining a constant speed.

[0087] In one aspect of the invention, the control operation of the adaptive cruise control system includes maintaining a constant speed when traveling on inclined or downhill terrain.

[0088] According to the present invention, a method for predicting the remaining energy distance includes: obtaining (i) data about a user, including historical driving data generated by one or more vehicles driven by the user, and (ii) a predicted vehicle speed change rate generated by a machine learning model using the historical driving data as input; and changing the remaining energy distance value according to the data and the predicted rate, so that the greater the predicted rate, the greater the change.

[0089] In one aspect of the invention, the method includes updating the predicted rate when a difference between the predicted rate and an actual rate of change collected when the speed changes monotonically between an initial speed and a final speed exceeds a predetermined value.

[0090] In one aspect of the invention, the updating changes the historical driving data of the user.

[0091] In one aspect of the invention, the updating further utilizes a machine learning algorithm to change the predicted rate of change to an updated predicted rate of change.

[0092] In one aspect of the invention, the predetermined value is at least 5 mph.

Claims

1. A vehicle comprising: Battery thermal management system; as well as a controller programmed to, for a specific user and in response to a predicted rate of speed change from a current speed to a target speed derived from data indicating that the specific user is driving the vehicle when the speed of the vehicle changes from a current speed to a target speed, change a cooling rate of the battery thermal management system according to the predicted rate such that the greater the predicted rate, the greater the change.

2. The vehicle of claim 1 wherein the controller is further programmed to update the predicted rate based on the current rate in response to a difference between the predicted rate and the current rate of change being greater than a predetermined threshold.

3. The vehicle of claim 2 wherein the controller is further programmed to use a machine learning algorithm to perform the updating.

4. The vehicle of claim 1 wherein the controller is further programmed to update the predicted rate based on the current rate in response to a difference between the predicted rate and the current rate being greater than a predetermined threshold and the current rate being defined by a monotonically increasing or monotonically decreasing value.

5. The vehicle of claim 4 wherein the controller is further programmed to prevent the updating regardless of the difference in response to the current rate being defined by a non-monotonic increasing or non-monotonic decreasing value.

6. The vehicle of claim 1 wherein the controller is further programmed to vary the cooling rate in further response to at least one of weather, driving conditions, ambient temperature, or a predicted route.

7. A method for generating a personalized adaptive cruise control command, comprising: Obtaining (i) data about a user, including historical driving data generated by one or more vehicles driven by the user, and (ii) a predicted rate of change of vehicle speed generated by a machine learning model using the historical driving data as input; as well as The data and the predicted rate are applied to an adaptive cruise control system of the vehicle to adjust control operation of the adaptive cruise control system. 8 . The method of claim 7 , further comprising updating the historical driving data when the user generates an actual speed change rate by changing from an initial speed to a final speed.

9. The method of claim 8, wherein the updating is in response to a difference between the actual speed rate of change and the predicted speed rate of change exceeding a threshold.

10. The method of claim 8 further comprising preventing said updating when said vehicle moves non-monotonically from said initial speed to said final speed.

11. The method of claim 7, wherein the application further includes at least one of route information, weather, ambient temperature, or battery remaining energy distance.

12. The method of claim 7, wherein the control operation of the adaptive cruise control system includes decelerating in response to a decreasing distance to a leading vehicle.

13. The method of claim 7, wherein the control operation of the adaptive cruise control system includes accelerating from an initial speed to a final speed.

14. The method of claim 7, wherein the control operation of the adaptive cruise control system includes autonomously maintaining a constant speed.

15. The method of claim 7, wherein the control operation of the adaptive cruise control system includes maintaining a constant speed when traveling on inclined or downhill terrain.

Images