METHOD FOR ESTIMATING A ROAD SURFACE COEFFICIENT USING A REBEAT TORQUE

Abstract

A method for determining road surface information in a vehicle (100), comprising: Receiving control data sampled by sensors (130); Determining at least one condition assessment value based on the received control data, wherein the at least one condition assessment value is a SAT mode associated with a linearity of the restoring torque, SAT; Determining a set of features that includes at least one of the SAT, slip angle, SAT variance, steering rate, and lateral acceleration, based on the state appraisal value; Processing the tax data obtained during a tax maneuver and associated with the feature set, using a pattern classification technique; Determining a surface type based on processing; Determining a tax maneuver type, and wherein determining the feature set and processing the tax data is based on the tax maneuver type; and Controlling one or more vehicle systems (100) based on the specific surface type.

Description

TECHNICAL AREA

[0001] The technical field generally concerns vehicles, and in particular methods for estimating road surface information for use in vehicle control. BACKGROUND

[0002] It is desirable to know the road surface friction coefficient during vehicle operation. For example, a control system can use this information to control one or more vehicle components, thereby assisting the driver in operating the vehicle safely. Currently, there is no method to directly measure the road surface friction coefficient. Therefore, the road surface friction coefficient must be estimated using sensor information available in the vehicle. Conventional techniques for estimating the road surface friction coefficient may be unreliable because they are sensitive to various dynamic vehicle behavior patterns, such as steering behavior.

[0003] DE 601 00 399 T2 relates to a device for estimating the coefficient of friction of a roadway for a vehicle, comprising a first section for estimating the coefficient of friction of a roadway in order to calculate a first coefficient of friction of a roadway based on the vehicle's lateral behavior, a second section for estimating the coefficient of friction of a roadway in order to calculate a second coefficient of friction of a roadway based on the vehicle's longitudinal behavior, a third section for estimating the coefficient of friction of a roadway in order to calculate a third coefficient of friction of a roadway based on the roadway conditions, and a section for selecting an estimate value in order to select either the first, second or third road friction coefficient as the final road friction coefficient estimate value.

[0004] DE 199 35 805 A1 relates to a system comprising a unit for determining a state variable related to vehicle motion. A memory stores nonlinear tire properties for a range of road surfaces. A unit estimates the vehicle skid angle for each road surface based on the state variable and the tire properties. An evaluation unit determines the instantaneous state of the road surface based on the vehicle skid angle, which is compensated by a feedback compensation unit. The feedback compensation unit compensates the skid angles for each road surface driven on based on an instantaneous state variable and a previous skid angle determined for each road surface.

[0005] US 2011 / 0 130 974 A1 relates to a method and apparatus for estimating the friction between a road surface and a vehicle tire. The method includes, but is not limited to, calculating a slope estimate k_sl for a slope of a linear range of a self-aligning torque function defined by a self-aligning torque as a function of a slip angle, in a slope estimation step. The method further includes, but is not limited to, deriving a first estimate u_sl of a road friction coefficient from the slope estimate k_sl and deciding, in a linearity estimation step, whether a current slope k_op lies within the linear range of the self-aligning torque function.If, in the linearity estimation step, it is decided that the current slope k_op lies within the linear range of the self-aligning torque function, the first estimate µ_sl of the road friction coefficient is output as the second estimate µ_cont of the road friction coefficient.

[0006] Accordingly, it is desirable to provide improved methods for determining the type of road surface. Furthermore, other desirable features and characteristics of the present invention will become apparent from the following detailed description and the attached claims, together with the attached drawings and the technical field and background described above. SUMMARY

[0007] Methods for determining road surface information in a vehicle are provided. In one embodiment, the method includes the features of claim 1.

[0008] In an exemplary system, this includes the following: A condition assessment module that determines at least one condition assessment value based on control data. A feature set determination module determines a feature set, including at least one of the state adjustment torque (SAT), slip angle, SAT variance, steering rate, and lateral acceleration based on the condition assessment value. A surface classification module processes the control data obtained during a steering maneuver and associated with the feature set, using a pattern classification technique to determine a surface type. DESCRIPTION OF THE DRAWINGS

[0009] The exemplary embodiments are now described together with the following figures, where identical reference numerals denote identical elements, and where Fig. 1 is a functional block diagram of an exemplary vehicle according to various embodiments; Fig. 2 is a data flow diagram illustrating a vehicle control module according to various embodiments; and Fig. 3 and Fig. Four flowcharts illustrate the procedures for determining road surface information according to various examples. DETAILED DESCRIPTION

[0010] The following detailed description is merely exemplary and is not intended to limit applications and uses. Furthermore, it is not intended to be bound by any express or implied theory set forth in the preceding technical section, background, summary, or subsequent detailed description. It should be assumed that throughout the drawings, corresponding reference numbers indicate similar or corresponding parts and features.As used herein, the term module refers to any hardware, software, firmware, all electronic control components, any processing logic and / or all processing devices, individually or in combination, including, without limitation: an application-specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated or as a group), and memory executing one or more software and / or firmware programs, a combinational logic circuit and / or other suitable components providing the described function.

[0011] Embodiments of the invention can be described here as functional and / or logical block components and various processing steps. It should be noted that such block components can be implemented by any number of hardware, software, and / or firmware components configured to perform specific functions. For example, an embodiment of the invention may employ various integrated switching components, such as memory elements, digital signal processing elements, logic elements, lookup tables, or the like, which can perform a variety of functions under the control of one or more microprocessors or other control devices.Furthermore, experts will recognize that the embodiments of the present invention can be implemented together with any number of control systems, and that the vehicle system described here is merely an exemplary embodiment of the invention.

[0012] Due to brevity, conventional techniques relating to signal processing, data transmission, signaling, control, and other functional aspects of the system (and the individual operating components of the system) may not be described in detail here. Furthermore, the connecting lines shown in the various figures included herein are designed to represent exemplary functional relationships and / or physical couplings between the various elements. It should be noted that many alternative or additional functional relationships or physical connections may exist in an embodiment of the present invention.

[0013] With reference to Fig. Figure 1 shows an exemplary vehicle 100, which includes a control system 110, according to exemplary embodiments. As can be seen, the vehicle 100 can be of any type of vehicle that travels over a road surface. Although the figures shown here represent an example with certain arrangements of elements, additional elements, devices, features, or components may be present in actual embodiments. It should also be assumed that Fig. Figure 1 is for illustrative purposes only and may not be drawn to scale.

[0014] The control system 110 includes a control module 120, which receives input from one or more sensors 130 of the vehicle. The sensors 130 detect observable states of the vehicle 100 and generate sensor signals based on these. For example, the sensors 130 can detect states of an electric power steering system 140 of the vehicle 100, an inertial measurement unit 150 of the vehicle 100, and / or other systems of the vehicle 100 and generate sensor signals based on these. In various embodiments, the sensors 130 communicate the signals directly to the control module 120 and / or can communicate the signals 130 to other control modules (not shown), which in turn communicate the data from the signals to the control module 120 via a communication bus (not shown) or other communication means.

[0015] The control module 120 receives the signals and / or data acquired by the sensor and, based on this, estimates a surface type and a surface value (which correlates with the road surface friction coefficient). In various embodiments, as discussed in more detail below, the control module 120 determines the surface type based on a classification technique with numerous classification patterns that evaluate data obtained during a steering maneuver. The surface can be, for example, ice, compacted snow, dry, or of another type. The control module 120 determines the surface value based on the determined surface type. The surface value can be a nominal value, for example, between 0 and 1, associated with the determined surface type. Typical values ​​are 0.1 for ice, 0.35 for snow, and 1.0 for dry.The control module 120 generates signals to control one or more components of the vehicle 100 based on the surface value and / or surface type, and / or makes the surface value and / or surface type available to other control systems (not shown) of the vehicle 100 for further processing and control of components of the vehicle 100.

[0016] Now, with reference to Fig. 2 and with further reference to Fig. Figure 1 illustrates a data flow diagram of the control module 120 according to various exemplary embodiments. As can be seen, various exemplary embodiments of the control module 120 according to the present invention can contain any number of submodules. In various exemplary embodiments, the submodules shown in Figure 1 can be... Fig. 2, combined and / or further subdivided to similarly estimate road surface information and one or more vehicle components 100 ( Fig. 1) to control based on this. In various exemplary embodiments, the control module 120 includes a preprocessing module 160, a condition assessment module 170, a surface classification module 180, and a decision-making module 190.

[0017] The preprocessing module 160 receives control data 200 as input, which is processed by the sensors 130 ( Fig. 1) sampled and / or determined by the control module 120 or other control modules (not shown) during a specific period of time. The control data 200 includes, but is not limited to, control angle data, yaw rate data, longitudinal velocity data, pinion angle data, motor torque data, torsion bar torque data, and lateral acceleration data. The preprocessing module preprocesses the control data 200 to eliminate noise and other inaccuracies. The preprocessing module 160 then uses the preprocessed data 280 to determine self-centering torque (SAT) data, slip angle data, lateral acceleration data, and control rate data. For example, the SAT data represents the torque produced by a tire when driven along a surface that tends to align the tire with the vehicle's direction of travel.The preprocessing module 160 determines the SAT data and other data using methods that are generally known in the prior art.

[0018] The condition assessment module 170 receives preprocessed data 280 as input, including steering rate data, steering angle data, SAT data, slip angle data, and lateral acceleration data. Based on this input, the condition assessment module 170 determines the condition assessment values ​​310. In various embodiments, the condition assessment values ​​310 include a steering mode 320, a SAT mode 330, and a steering maneuver mode 340.

[0019] In various embodiments, the state assessment module 170 evaluates the control rate data to determine the control mode 320. The state assessment module 170 sets the control mode 320 to indicate a control speed, such as fast control or normal control. For example, if the value of the control rate data is large (e.g., greater than a threshold), then the state assessment module 170 sets the control mode 320 to indicate fast control. In another example, if the value of the control rate data is small (e.g., less than a threshold), the state assessment module 170 sets the control mode 320 to indicate normal control.As can be seen, in various embodiments the condition assessment module 170 can set the control mode 320 to display other control speeds, and is not limited to the examples shown.

[0020] In various embodiments, the condition assessment module 170 evaluates the SAT data and the side acceleration data to determine the SAT mode 330. The condition assessment module 170 sets the SAT mode 330 to indicate linearity of the SAT data, such as linear or non-linear. For example, if the magnitudes of the SAT data and the side acceleration data increase, the condition assessment module 170 sets the SAT mode 330 to indicate linearity. In another example, if the magnitudes of the SAT data decrease and the magnitudes of the side acceleration data increase, the condition assessment module 170 sets the SAT mode 330 to indicate non-linearity. As can be seen, in various embodiments, the condition assessment module 170 can set the SAT mode 330 to indicate other forms of linearity and is not limited to the examples presented here.

[0021] In various embodiments, the condition assessment module 170 evaluates the control angle data to determine the control maneuver mode 340. The condition assessment module 170 sets the control maneuver mode 340 to indicate a control maneuver type, such as a control maneuver or a non-control maneuver. For example, the condition assessment module 170 tracks the control angle data based on two (or more) time-moving windows of different sizes. If increases are present in both windows and the increases exceed a threshold, then the condition assessment module 170 determines that the data is associated with a control maneuver and sets the control maneuver mode 340 to indicate a control maneuver.However, if there is no increase in either window, or if an increase does not exceed a threshold, then the condition assessment module 170 determines that the data is not associated with a control maneuver and sets the control maneuver mode 340 to indicate a non-control maneuver. As can be seen, in various embodiments, the condition assessment module 170 can set the control maneuver mode 340 to indicate further control maneuvers and is not limited to the examples presented here.

[0022] The surface classification module 180 receives preprocessed data 280 as input, including steering rate data, steering angle data, slip angle data, SAT data, and lateral acceleration data. The surface classification module 180 also receives condition assessment values ​​310, including steering mode 320, SAT mode 330, and steering maneuver mode 340. Based on these inputs, the surface classification module 180 determines a surface type 350 and a surface value 360. For example, the surface classification module 180 first evaluates the condition assessment values ​​310 together with the slip angle data to select a feature set from a number of feature sets. The feature set defines the data to be used in further evaluations.

[0023] In various embodiments, the feature set may include, but is not limited to: Set 1, comprising SAT and slip angle; Set 2, comprising SAT, SAT variance, and slip angle; Set 3, comprising lateral acceleration, steering rate, and slip angle; Set 4, comprising lateral acceleration; and Set 5 as a default set. The Surface Classification Module 180 selects Feature Set 1 when the slip angle is greater than a threshold, the SAT mode indicates linear, and the steering mode indicates normal steering. The Surface Classification Module 180 selects Feature Set 2 when the slip angle is within a range, the SAT mode indicates linear, and the steering mode indicates normal steering.The Surface Classification Module 180 selects feature set 3 if the slip angle is greater than a threshold, the SAT mode indicates linear behavior, and the control mode indicates fast control. The Surface Classification Module 180 selects feature set 4 if the SAT mode indicates non-linear behavior. The Surface Classification Module 180 selects feature set 5 if the control maneuver mode indicates non-steering.

[0024] The Surface Classification Module 180 then uses the data associated with the feature set to identify the surface type 350. For example, if the feature set is set to one of Set 1, Set 2, or Set 3, the Surface Classification Module 180 evaluates the data associated with the feature set based on a statistical pattern classification procedure. In another example, if the feature set is set to one of Set 4 or Set 5, no statistical analysis is performed. However, if the feature set is set to Set 4, the SAT mode is non-linear, and the surface type 350 and surface value 360 ​​can be easily determined based on the lateral acceleration value. If the feature set is set to Set 5, default values ​​for surface type 350 and surface value 360 ​​are used.

[0025] In various embodiments, the statistical pattern classification method compares real-time data associated with the feature set with pre-stored data associated with the same feature set, comprising typical patterns of different road surfaces. The pre-stored data may be stored in a pattern data store 370. The method for statistical pattern classification and surface type identification 350 may be, but is not limited to, linear discriminant analysis (LDA) (e.g., Batch Perception, Fisher Linear Discriminant, etc.), a support vector machine (SVM), or another classification method.

[0026] The surface classification module 180 then determines that the surface value 360 ​​is the nominal value associated with the specific surface type 350. The nominal values ​​and their associations with surface type 350 can be predefined and stored in the pattern data store 370.

[0027] The decision-making module 190 receives preprocessed data 280 as input, including the control angle data, the lateral acceleration data, and the surface type 350 and surface value 360. Based on this input, the decision-making module determines a final surface type 380 and a final surface value 390. For example, if the control angle indicates that the data corresponds to a steering maneuver, the lateral acceleration data is tracked and evaluated to see if it corresponds to surface type 350. If the lateral acceleration is large (for example, greater than a threshold) and surface type 350 is a high-friction type (for example, a dry surface), then surface type 350 is confirmed as valid, and the final surface type 380 is determined to be a high-friction type.If the lateral acceleration is large (for example, greater than a threshold), and the surface type 350 is a low-friction type (for example, an icy surface), then the result indicating that surface type 350 is a low-friction surface is a false detection result (i.e., since it is unlikely that a low-friction surface type would have a large lateral acceleration). In this case, the decision module 190 sets the final surface type 380 and the final surface value 390 to a high-friction surface type (for example, a dry surface).

[0028] In various embodiments, the decision-making module 190 determines the final surface type 380 based on an analysis of a sequence of individual decision points within a time-moving window frame. For example, the decision-making module 190 determines the final surface type 380 by tracking the specified surface value 360 ​​during a time window. In various embodiments, the time window can have different sizes and can be reset at different points.

[0029] With reference to Fig. 3 and Fig. 4 and with further reference to Fig. Figures 1 and 2 show flowcharts of methods 400 and 600 for determining the surface type and surface value and for inspecting a vehicle based on the surface type and surface value according to various embodiments. Methods 400 and 600 can be used in conjunction with vehicle 100. Fig. 1 can be implemented and can be used by the control module 120 of Fig. 1 according to various exemplary embodiments. As can be seen in light of this disclosure, the order of operation within the method is not limited to sequential execution, as described in Fig. 3 and Fig. 4 illustrates, but can be carried out in one or more varying sequences, as applicable and according to the present disclosure. As will be seen further, the procedures of Fig. 3 and Fig. 4. They may be planned to function at predetermined time intervals during the operation of vehicle 100, and / or they may be planned to function based on predetermined events.

[0030] Fig. Figure 3 is a flowchart of a procedure for determining the final surface type 380 and the final surface value 390 and, based on this, for controlling the vehicle 100. As in Fig. As shown in Figure 3, the procedure can begin at 405. The control data 200 is collected and preprocessed at 410. The SAT data and slip angle data are determined at 420 based on the collected control data 200. Subsequently, the condition assessment values ​​310 are determined at 430 based on the preprocessed data 280. Specifically, the steering maneuver mode 340 is determined at 440 based on the steering angle. The steering mode 320 is determined at 450 based on the steering rate, and the SAT mode 330 is determined at 460 based on the SAT data and the lateral acceleration data.

[0031] The feature set is then determined based on the condition assessment values ​​310 and 370. The data associated with the feature set are processed using a classification procedure (for example, linear discriminatory analysis or other methods) and the stored patterns to identify surface type 350 at 480. Surface value 360 ​​is determined based on surface type 350 at 490. Surface type 350 is confirmed based on a lateral acceleration assessment at 500. If surface type 350 is confirmed at 510, surface value 360 ​​and surface type 350 are processed to determine the final surface type 380 and final surface value 390 at 520. Subsequently, one or more vehicle systems are checked based on the final surface type 380 and / or the final surface value 390 at 530, and the process may end at 540.However, if surface type 350 is not confirmed at 530, the procedure may end at 540.

[0032] Fig. Figure 4 is a flowchart of a procedure 600 to determine the feature set, as in Figure 470 of Fig. Figure 3 shows that the procedure can begin at 605. The steering maneuver mode 340 is evaluated at 610. If the steering maneuver mode 340 does not indicate a steering maneuver at 610, the procedure proceeds to 620, where the surface type 350 and the surface value 360 ​​are set to default values ​​(for example, a previous value or another predetermined default value), and the procedure can end at 630.

[0033] However, if the steering maneuver mode 340 indicates a steering maneuver at 610, the SAT mode 330 is evaluated at 640. If the SAT mode 330 indicates a non-linear SAT, set 4 is selected as the feature set containing the lateral acceleration at 650. The procedure can then end at 630.

[0034] However, if SAT mode 330 indicates a linear SAT at 640, steering maneuver mode 320 is evaluated at 660. If steering mode 320 indicates fast steering at 660, the slip angle data is evaluated at 670. If the slip angle at 670 is less than a threshold, the procedure proceeds to 620, where surface type 350 and surface value 360 ​​are set to default values ​​(for example, a previous value or another predetermined default), and the procedure may end at 630.

[0035] However, if the slip angle is greater than the threshold at 670, then at 675 set 4 is selected as the feature set containing the lateral acceleration, the steering rate, and the slip angle. The procedure can then end at 630.

[0036] If the control mode at 660 does not indicate fast control but normal control, the slip angle data is evaluated at 680. For example, if at 680 the slip angle is greater than a first threshold (where, for example, a high threshold indicates a large strip), at 690 set 1 is selected as the feature set containing the SAT and the slip angle. The procedure can then end at 630.

[0037] However, if the slip angle at 680 is smaller than the first threshold, at 700 the slip angle is compared to a second threshold (for example, a lower threshold indicates a small stripe). If at 700 the slip angle is larger than the second threshold, set 2 is selected as the feature set, which at 710 contains the SAT, the SAT variance, and the slip angle. The procedure can then end at 630. However, if at 700 the slip angle is smaller than the second threshold, the procedure proceeds to 620, the surface type 350 and the surface value 360 ​​are set to default values ​​(for example, a previous value or another predetermined default), and the procedure can end at 630. Examples

[0038] Example 1. A method for determining road surface information in a vehicle, comprising: Determining at least one condition assessment value based on tax data; Determining a set of features that includes at least one of the restoring torque (SAT), slip angle, SAT variance, steering rate, and lateral acceleration based on the state appraisal value; Processing tax data obtained during a tax maneuver and associated with the feature set using a pattern classification technique; and Determining a surface type based on processing.

[0039] Example 2. The procedure of Example 1, wherein the at least one value of the state assessment is a control mode associated with a control rate.

[0040] Example 3: The procedure of Example 1, wherein at least one value of the state assessment is a SAT mode associated with a linearity of the SAT.

[0041] Example 4. The procedure of one of Examples 1 to 3, further comprising determining a tax maneuver type, and wherein determining the feature set and processing the tax data is based on the tax maneuver type.

[0042] Example 5. The procedure of Example 4, wherein the steering maneuver type is at least one of a steering maneuver or a non-steering maneuver.

[0043] Example 6. The procedure of Example 5, further comprising determining a steering maneuver type, and wherein determining the surface type is based on a default value when it is determined that the steering maneuver type is a non-steering maneuver.

[0044] Example 7. The procedure of one of Examples 1 to 6, wherein determining the feature set includes determining the feature set that includes SAT and hideout.

[0045] Example 8. The procedure from Example 7, further expanded: Determine that a slip angle is greater than a threshold, and where determining the state evaluation value includes determining that a SAT mode is linear and determining that the control mode is a normal control and where determining that the feature set contains SAT and slip angle is based on the slip angle being greater than a threshold, the SAT mode being linear, and the control mode being normal control.

[0046] Example 9. The procedure of one of Examples 1 to 6, wherein determining the feature set includes determining the feature set including SAT, SAT variance and slack angle.

[0047] Example 10. The procedure from Example 9, further expanded: Determine that the hiding place lies within a certain range, where determining the state evaluation value includes determining that a SAT mode is linear and determining that the control mode is a normal control, where determining that the feature set contains SAT, SAT variance, and slip angle is based on the assumption that the slip angle is within the range, the SAT mode is linear, and the control mode is a normal control.

[0048] Example 11. The procedure according to one of Examples 1 to 6, wherein determining the feature set includes determining the feature set that includes the lateral acceleration, the steering rate and the slip angle.

[0049] Example 12. The procedure from Example 11, further expanded: Determine that a slip angle is greater than a threshold, and where determining the state evaluation value includes determining that a SAT mode is linear and determining that the control mode is fast control, and where determining that the feature set includes the lateral acceleration, the steering rate and the slip angle is based on the slip angle being greater than a threshold, the SAT mode being linear and the steering mode being fast steering.

[0050] Example 13. The procedure of one of Examples 1 to 6, wherein determining the feature set includes determining the feature set that includes lateral acceleration.

[0051] Example 14. The procedure from Example 13, further expanded: Determining the state assessment value includes determining that a SAT mode is non-linear, and where the determination that the feature set includes lateral acceleration is based on the fact that the SAT mode is non-linear.

[0052] Example 15. The procedure of one of Examples 1 to 14, further comprising determining a surface value based on the surface type.

[0053] Example 16. The procedure of one of Examples 1 to 15, wherein the pattern classification technique includes at least one linear discriminant analysis and one support vector machine analysis.

[0054] Example 17. The procedure of one of Examples 1 to 16, further comprising confirming the surface type based on an assessment of lateral acceleration.

[0055] Example 18. The method of one of Examples 1 to 17, further comprising determining a final surface type based on a multitude of specific surface types within a time-moving window.

[0056] Example 19. A system for determining road surface information in a vehicle, comprising: A condition assessment module that determines at least one condition assessment value based on control data, a module for determining a feature set that specifies that a feature set contains at least one of the restoring torque (SAT), slip angle, SAT variance, steering rate and lateral acceleration based on the state appraisal value, and A module for classifying surfaces that processes the control data obtained during a control maneuver and associated with the feature set, using a pattern classification technique to determine the surface type.

[0057] Example 20. The system of Example 19, further comprising a decision-making module that determines a final surface type based on a multitude of specific surface types within a time-moving window.

[0058] While the preceding detailed description presented at least one exemplary embodiment, it should be noted that a very large number of variations exist. It should also be noted that the exemplary embodiment or embodiments are merely examples and are not intended to limit the scope of protection, applicability, or configuration of the disclosure in any way. Rather, the detailed description above provides those skilled in the art with a suitable roadmap for implementing the exemplary embodiment or embodiments. It should be assumed that various modifications to the function and arrangement of elements can be made without deviating from the scope of protection of the invention as specified in the appended claims and their legal equivalents.

Claims

[1] A method for determining road surface information in a vehicle (100), comprising: Receiving control data sampled by sensors (130); Determining at least one condition assessment value based on the received control data, wherein the at least one condition assessment value is a SAT mode associated with a linearity of the restoring torque, SAT; Determining a set of features that includes at least one of the SAT, slip angle, SAT variance, steering rate, and lateral acceleration, based on the state appraisal value; Processing the tax data obtained during a tax maneuver and associated with the feature set, using a pattern classification technique; Determining a surface type based on processing; Determining a tax maneuver type, and wherein determining the feature set and processing the tax data is based on the tax maneuver type; and Controlling one or more vehicle systems (100) based on the specific surface type. [2] The method according to claim 1, wherein the at least one state assessment value is a control mode associated with a control rate. [3] The method according to claim 1, wherein the steering maneuver type is at least one of a steering maneuver or a non-steering maneuver. [4] The method according to claim 3, further comprising determining a steering maneuver type, and wherein the determination of the surface type is based on a default value when it is determined that the steering maneuver type is the non-steering maneuver. [5] The method according to any one of claims 1 to 4, wherein determining the feature set includes determining that the feature set contains SAT and slip angle. [6] The method according to claim 5, further comprising: Determine that a slip angle is greater than a threshold, and where determining the state evaluation value includes determining that the SAT mode is linear and determining that the control mode is normal control, where determining that the feature set includes SAT and slip angle is based on the fact that the slip angle is greater than a threshold, the SAT mode is linear, and the control mode is normal control. [7] The method according to any one of claims 1 to 4, wherein determining the feature set comprises determining the feature set including the feature set SAT, SAT variance and slip angle. [8] The method according to claim 7, further comprising: Determine that the hiding place lies within a certain range, and where determining the state evaluation value includes determining that the SAT mode is linear and determining that the control mode is normal control, where determining that the feature set includes SAT, SAT variance and slip angle is based on the assumption that the slip angle is within the range, the SAT mode is linear and the control mode is normal control.

Images