Method for characterizing the friction coefficient mobilizable by a motor vehicle

Abstract

The invention relates to a method for characterizing the friction coefficient mobilizable by a motor vehicle, and to the vehicle implementing the method. The method comprises: • a step (501) of estimating a cornering stiffness Cy and a step (502) of estimating a pneumatic trail τρ of the tires of one or more driven wheel sets of the motor vehicle, • a step (503) of classifying the friction coefficient mobilizable by the motor vehicle, from among a finite set of classes of friction coefficients, by implementing a machine-learning classification algorithm that has been trained for this purpose and takes as inputs the cornering stiffness Cy and the pneumatic trail τρ, • a step (504) of using the class of friction coefficient mobilizable by the vehicle that was calculated during the preceding step by a driver assistance system of the vehicle.

Description

DESCRIPTION Title: Method for characterizing the coefficient of friction that can be mobilized by a motor vehicle Technical field:

[0001] The invention relates to the field of motor vehicles in the broadest sense (i.e., passenger cars, vans, trucks, sports cars, electric or otherwise, autonomous or not), and more specifically to a method for characterizing the coefficient of friction available to such a motor vehicle, based on information about its lateral dynamics. The estimated coefficient of friction available can then be used by the various driver assistance systems implemented on the vehicle. Previous technique:

[0002] Modern vehicles are equipped with increasingly sophisticated Advanced Driver Assistance Systems (ADAS). These ADAS systems aim to improve safety and driving efficiency by controlling various vehicle actuators.

[0003] Indeed, modern vehicles can be viewed as multi-actuator systems (or "overactuated systems") in which different actuators can be used to perform the same action, with the aim of improving comfort or safety. Each actuator has its operating range, within which it is optimal for achieving the best performance. For example, for lateral vehicle control, differential braking actuators are very effective on low-grip surfaces because the self-alignment of the wheels (which characterizes the tendency of the wheels to return to the vehicle's longitudinal axis on their own) is low. Conversely, steering actuators are more effective on high-grip surfaces because the self-alignment of the wheels is high.

[0004] To use the most appropriate actuators for each situation, ADAS systems need as much information as possible about the vehicle's operation. One such piece of information is the maximum tire-road friction coefficient that the vehicle can mobilize. This represents the maximum longitudinal or lateral force that the tires can generate on the road without exceeding their grip limits. This coefficient is also called the tire friction ellipse. The mobilizable friction coefficient depends on road surface grip and intrinsic vehicle characteristics, such as tire type and condition, as well as other factors like weather conditions, tire pressure, and driving dynamics.

[0005] Knowledge of the mobilizable (or potential, or maximum) tire-road friction coefficient can be used, for example, to select the most suitable actuators for lateral or longitudinal vehicle control, to adjust safety distances, etc.

[0006] In the current state of the art, most work aimed at estimating the friction coefficient uses two main approaches: - the so-called "direct" approaches, which require the use of additional sensors, for example acoustic sensors attached to the chassis near the wheels to measure the noise produced by the contact between the tire and the road, or vision sensors (cameras) that capture images of the road for classification purposes; - the so-called "indirect" approaches, which are based on observing the effects of tire-road adhesion on vehicle dynamics. They mainly use information relating to the longitudinal dynamics of the vehicle and wheel slippage.

[0007] Direct approaches have the drawback of the added cost associated with installing dedicated sensors. It should be noted that today, vehicles are increasingly equipped with sensors that classify road surface grip for noise reduction or ADAS functions. However, these solutions do not take into account vehicle dynamics (i.e., how the vehicle moves on the road and how it responds to the forces and movements acting upon it) or tire condition.

[0008] Indirect approaches mitigate the problem of additional cost by using only the information available on the CAN bus (Controller Area Network, a serial system bus used in modern vehicles to allow the various vehicle controllers and sensors to exchange data). However, their response time is highly dependent on the vehicle's driving dynamics.

[0009] For example, US patent 7751961 B2 is known for estimating the friction coefficient that a vehicle can generate by intentionally accelerating or decelerating it—that is, by sending an additional command to the engine. This acceleration or deceleration provides the longitudinal excitations or dynamics necessary to estimate the friction coefficient. This method is advantageous because the engine is required to generate longitudinal dynamics at a moderate level even in the absence of driver input, particularly in low-dynamic driving conditions. However, the level of such excitation demand, if not properly controlled, can be intrusive or disruptive for the driver and passengers.This method also leads to an increase in the computational load of the control laws used to regulate, for example, the speed to a given reference, particularly in the case where speed regulation (ACC for "Adaptive Cruise Control" >>) is activated, and an increase in energy consumption.

[0010] One aim of the invention is therefore to define a method for characterizing the tire-road friction coefficient that can be mobilized by the motor vehicle, usable for controlling the vehicle's control laws, according to an indirect approach independent of the longitudinal dynamics of the vehicle (i.e., operating in the absence of strong acceleration or braking). Summary of the invention:

[0011] To this end, the present invention describes a method for characterizing the coefficient of friction that can be mobilized by a motor vehicle. The method comprises: - a step of estimating a drift stiffness C y tires from at least one set of steerable wheels of the motor vehicle, - a step of estimating a pneumatic flush T P tires from at least one set of steerable wheels of the motor vehicle, - a classification step of the friction coefficient that can be mobilized by the motor vehicle, among a finite set of classes of mobilizable friction coefficients, by implementing a machine learning classification algorithm trained for this purpose, taking as input the said drift stiffness C y the vehicle's tires and said pneumatic tires T p of the vehicle, - a step of using the class of friction coefficient mobilizable by the motor vehicle calculated during the previous step by a motor vehicle driving assistance system.

[0012] In various embodiments, the classification step of the friction coefficient that can be mobilized by the motor vehicle may further include providing the machine learning classification algorithm with at least one type of data from among: - data on the nature and condition of a road surface, - meteorological data, - data relating to tires, - data relating to vehicle dynamics.

[0013] Advantageously: - the step of estimating a drift stiffness C y may include smoothing of a calculated drift stiffness value and / or - the stage of estimating a pneumatic flush T P may include smoothing of a calculated pneumatic scavenging value.

[0014] According to a particular embodiment, the step of estimating a drift stiffness C yis implemented only when the tires of the steerable wheel assembly of the motor vehicle in question are in a linear operating zone.

[0015] According to a particular embodiment of the invention, the method further comprises a preliminary step of validating the lateral dynamic conditions of the motor vehicle. For example, the lateral dynamic conditions of the motor vehicle are validated when the lateral dynamics of the motor vehicle are greater than its longitudinal dynamics.

[0016] According to one embodiment of the method according to the invention, the finite set of classes of friction coefficients that can be mobilized by the vehicle comprises two classes, and the machine learning classification algorithm is a logistic regression algorithm. According to one embodiment of the method for characterizing the coefficient of friction that can be mobilized by a motor vehicle according to the invention, the step of estimating a drift stiffness C y tires of at least one set of directional wheels of the motor vehicle includes the calculation of C y such that: dF v C v = y dp with: dF y a variation of the lateral force exerted on the tires of the wheel assembly considered, dp the variation of the drift angle of the wheel assembly considered.

[0017] According to one embodiment of the method for characterizing the coefficient of friction that can be mobilized by a motor vehicle according to the invention, the step of estimating a pneumatic slip T P tires of at least one set of directional wheels of the motor vehicle includes the calculation of T P such as : T pp ry with: - T ALthe self-alignment torque of the wheel assembly under consideration, - F y the lateral force exerted on the tires of the wheel assembly in question.

[0018] According to one embodiment of the method for characterizing the coefficient of friction that can be mobilized by a motor vehicle according to the invention, the supervised learning classification algorithm is configured to provide a probability associated with the class of the mobilizable friction coefficient, said probability being taken into account during step (504) of use of the class of mobilizable friction coefficient by a vehicle driving assistance system.

[0019] The invention also relates to a motor vehicle comprising an electronic data processing device configured to implement a method for characterizing the mobilizable friction coefficient according to one of the embodiments of the invention. Brief description of the figures:

[0020] The invention will be better understood and other features, details and advantages will become clearer upon reading the following description, given by way of example, and with the help of the accompanying figures, which are provided by way of example, among which: - Figure 1 represents drift stiffness measurements of a tire on two classes of supports; - Figure 2 represents the evolution of the lateral force exerted on a tire as a function of the vehicle's drift angle for two support classes; - Figure 3 represents the tire-road contact of a tire when a steering angle is applied to the wheel assembly; - Figure 4 represents the distribution of pneumatic caster values ​​obtained during runs carried out on two classes of runs; - Figure 5 schematically represents the steps of a process for characterizing the mobilizable friction coefficient of a motor vehicle according to the invention; - Figure 6 schematically represents steps to carry out the learning of the classification algorithm used in the characterization process according to the invention. Detailed description:

[0021] In the rest of the description, and unless otherwise stated, the term "friction coefficient" will be used to refer to the "friction coefficient that can be mobilized by the vehicle."

[0022] The invention relates to a method for characterizing the coefficient of friction available to a motor vehicle. The purpose of the method is not to precisely estimate this coefficient of friction, but to quickly determine a class representative of its value, possibly associated with a confidence level. Any number of classes can be used, for example, two classes of values ​​(high / low coefficient of friction), or three classes of values ​​(high / medium / low coefficient of friction).

[0023] To achieve this, the method according to the invention relies on processing data relating to the vehicle's lateral dynamics using a supervised machine learning classification algorithm. A classification algorithm is an algorithm that allows elements or data to be classified into predefined categories based on certain common characteristics. These algorithms are commonly used in fields such as image recognition, data analysis, natural language processing, document classification, etc.

[0024] Classification algorithms are used for ADAS, but primarily for identifying contextual elements of the vehicle's environment from camera images. The invention proposes using such a classification algorithm to identify the tire-road friction coefficient from data other than optical flow. One of the challenges lies in selecting the data used as input for these classification algorithms; this data must be relevant to the target classes for the classification results to be meaningful.

[0025] The method according to the invention proposes to use a supervised learning classification algorithm to determine the class of the friction coefficient that can be mobilized by the vehicle using at least two parameters representative of its lateral dynamics: - the rigidity of the fin C ytires of a set of steering wheels of the vehicle, and - the pneumatic hunting T P tires of a set of steering wheels of the vehicle.

[0026] The rigidity of the fin C y A tire's stiffness refers to its ability to generate lateral forces that can be applied during driving. It relates the lateral force exerted on a tire to maintain a given drift angle relative to the vehicle's longitudinal axis to the lateral deformations it undergoes. The higher the drift stiffness, the less the tire deforms laterally in corners, and vice versa.

[0027] Figure 1 shows estimates of the drift stiffness C yof a tire, obtained by driving a vehicle on two classes of surfaces: one class with low grip (such as snow) and one class with high grip (such as dry asphalt). These estimates are made by measuring the forces exerted on the tire and the vehicle's drift angle. The results are represented as a density, with the dispersion along the x-axis representing this density.

[0028] Observations from these measurements lead to the conclusion that, during lateral loading, the more the tire adheres to the road surface, the higher the drift stiffness value C y is high.

[0029] Figure 2 shows the evolution of the lateral force F yexerted on a tire as a function of the vehicle's drift angle, again for both support classes and 12. These curves reach a plateau, respectively and / z2, corresponding to the maximum friction coefficient that the vehicle can mobilize on the corresponding support. The drift stiffness C y corresponds to the absolute value of the slope of the curve relating the force F y at the drift angle Ç> .

[0030] This figure highlights the fact that, for mobilizable adhesion coefficients < / z2, the rigidity of the drift C yl corresponding is less than the rigidity of the fin C y2 corresponding to / z2. There is therefore a link between lateral stiffness C y and the vehicle's mobilizable friction coefficient, which is why the invention uses this information for characterizing the friction coefficient class.

[0031] The pneumatic hunting T P (in English "pneumatic trail") of a tire is a term used in automotive engineering to describe the distance between the center of the tire-road contact area and the point of application of the lateral force.

[0032] Figure 3 represents the contact 301 tire-road surface of a tire when a steering angle is applied to the wheel assembly, being the angle between the longitudinal axis of the vehicle 302 and the steering direction of the directional wheels 303. The tire-road contact has a length 304 and a width 305.

[0033] Point B represents the center of contact between the tire and the road surface. It is also the point of application of the normal force acting on the tire. Applying a steering angle results in the appearance of a lateral force F y to the tire, which deforms the tire-road contact patch. The center of contact of the force F yis represented by point A, positioned slightly ahead of point B in the direction of vehicle travel. The distance between points A and B defines the tire caster T P This pneumatic caster is considered the lever arm of the self-alignment moment T AL of the wheel.

[0034] When T P As the force decreases towards zero, the tire enters the slip zone and loses its self-aligning power: the force F y enters the non-linear operating zone of the tire and the self-aligning torque gradually decreases towards zero.

[0035] The self-aligning torque T AL reaches its maximum value before force F y In other words, the peak of the wheel self-alignment torque occurs before the tires enter their non-linear operating zone. The pneumatic caster T PThe coefficient of friction of a tire is therefore representative of the coefficient of friction that can be mobilized by the vehicle, before the tire enters its non-linear operating zone.

[0036] Figure 4 shows the distribution of tire caster values ​​obtained during runs performed on the two running classes I and I2. It can be observed that the tire caster value T P the wheels of a steering wheel assembly of the vehicle is well representative of the class of the coefficient of friction that can be mobilized by this vehicle.

[0037] The method according to the invention consists of using a classification algorithm to define a class of the friction coefficient that can be mobilized by the vehicle. The inputs to this classification algorithm are values ​​of the vehicle's lateral dynamics that are representative of this friction coefficient, namely at least the drift stiffness C yof a vehicle's directional wheel assembly and pneumatic caster T P the tires of a set of steering wheels of the vehicle (potentially the same set). An advantage of the invention is that these values ​​are available or directly derivable from vehicle data transmitted on the CAN bus. Therefore, implementing the invention does not require the installation of dedicated sensors.

[0038] Figure 5 schematically represents the steps of a process according to the invention for characterizing the coefficient of friction that can be mobilized by a motor vehicle.

[0039] The process includes a first step 501 of estimating a drift stiffness C y tires of a steering wheel assembly of the vehicle, the drift rigidity C y corresponding to the slope relating the lateral force exerted on the tires to the drift angle p. A force F yPositive drift stiffness is induced by a negative drift angle. In order to maintain positive drift stiffness, the slope of F y with respect to the drift angle is considered in absolute value, so that: dF v C v = y dp with: - dF y The variation in lateral force, measured or estimated, for example, from the lateral acceleration, mass, and yaw rate of the vehicle. The force F y can be obtained by a simple method, by multiplying the mass of the vehicle by its lateral acceleration, or by more complex methods, for example by using a Kalman filter; - dp the variation of the wheel set drift angle, measured or estimated for example from the steering wheel angle or yaw rate.

[0040] Advantageously, the estimation of the rudder stiffness C yThe calculated value can be smoothed, for example by a Kalman filter, a recursive least squares algorithm, or any other similar technique. Such smoothing helps to avoid abrupt jumps in C y linked to isolated variations that are not representative of a change adhesion of the tire-road contact, particularly when the adhesion conditions are at the limit of two classes.

[0041] Advantageously, step 501 of estimating the rigidity of the drift C y The vehicle's tires are only activated when the drift angle has a low value, that is, when the tires are in their linear operating zone. As an example, the estimation of C y This can only be achieved when the absolute value of the vehicle's drift angle is less than 5 degrees. When this condition is not met, the drift stiffness value C yused for the implementation of the invention corresponds to the latest estimated value, where appropriate after smoothing of this value.

[0042] The process also includes a second step 502 of estimating the pneumatic flush T P tires of a steering wheel assembly of the vehicle. This step can be performed before, after, or at the same time as step 501. The wheel assembly considered for calculating tire caster can be the same as that considered for drift stiffness, or a different wheel assembly in the case of a four-wheel steering vehicle.

[0043] The pneumatic hunting T P can be estimated in different ways. One example of implementation, which does not require taking into account the mechanical caster (which is a constant related to the chassis), consists of calculating: T pp ry with: - T ALthe self-alignment torque of the wheel assembly, measured or estimated for example from information from a driver torque sensor (which measures the rotational force applied by the driver on the steering wheel of a car), the steering assistance torque (which indicates the rotational force applied by the steering wheel on the entire steering column) and a dry friction torque sensor of the vehicle's front axle (observed on the steering column), - F y the lateral force that is applied to the tires of the wheel set, measured on one or more wheels or estimated for example from the lateral acceleration, mass and yaw rate of the vehicle.

[0044] Advantageously, the pneumatic flush estimate T PThe vehicle's tire performance can be smoothed, for example by a Kalman filter, a recursive least squares algorithm, or any other estimation technique, to avoid abrupt jumps in T P related to occasional variations not representative of a change in adhesion at the contact of the tire-road.

[0045] The method according to the invention includes a third step 503 of classifying the mobilizable friction coefficient of the vehicle from among a finite set of classes of mobilizable friction coefficients, carried out by a machine learning classification algorithm previously trained for this purpose, and taking as inputs the values ​​of the vehicle's lateral dynamics representative of the mobilizable friction coefficient, namely the drift stiffness C y calculated during step 401 and the pneumatic flush T P calculated during step 402.

[0046] The machine learning classification algorithm used can, for example, be a neural network, logistic regression, decision tree, etc. In the case of classifying the mobilizable friction coefficient into only two classes, the machine learning classification algorithm used is advantageously a logistic regression, as it is one of the best methods for binary classification, with a smooth transition approximated by a sigmoid function between the two classes.

[0047] The use of a machine learning classification algorithm allows us to rely on multiple inputs to determine the class of the friction coefficient that can be mobilized by the vehicle. It takes as inputs at least two values ​​of the vehicle's lateral dynamics that are representative of the mobilizable friction coefficient, called primary indicators, namely the drift stiffness Cy and the pneumatic caster Tp of the tires of one or more steerable wheel assemblies of the vehicle. The wheel assembly considered is typically the front wheel assembly of the vehicle, but the invention applies identically considering the drift stiffness C y and / or pneumatic flushing T P rear wheel axle tires when it is a steerable axle, or by supplementing the measurements taken on the front wheel axle with measurements taken on the rear wheel axle.

[0048] The inputs to the classification algorithm can also include secondary indicators as long as they are also representative of this friction coefficient, such as: - data on the nature and condition of the road surface, obtained for example from a camera, - meteorological data, obtained for example by a thermometer, a rain sensor, and / or a weather station, - data relating to tires, such as tire type, pressure, age and / or wear condition, - data relating to vehicle dynamics, such as speed, acceleration, yaw rate and / or slip rate.

[0049] The list of secondary indicators is not exhaustive. These secondary indicators help to improve the accuracy of the classification performed by the supervised learning classification algorithm.

[0050] The method according to the invention finally includes a fourth step 504 of using the class of available friction coefficient calculated in step 503 by a vehicle driver assistance system, for example, for an ADAS system mobilizing the braking, acceleration, or steering actuators for trajectory tracking or lane centering, for adaptive ACC to adjust safety distances from the vehicle ahead, or for collision detection. It could also be an engine control system that adjusts the torque setting or the maximum engine power demand according to the grip class, etc.

[0051] The classification algorithm is trained offline (i.e., outside the vehicle) and in a supervised manner. It consists of providing the classification algorithm with a set of known input and output data, called training data, so that it learns to associate the inputs with the corresponding outputs by creating a model or a mathematical function that can be used during of the inference phase. The training data comes from measurements taken on a test vehicle, or from a driving database.

[0052] Figure 6 schematically represents the steps for training the classification algorithm used in the characterization process according to the invention. The training is performed by considering input / output data of the algorithm of the same type as those of the inference phase of classification step 503.

[0053] The learning process includes the following steps: - collection of 601 input samples, including at least one drift stiffness measurement C y tires of a steering wheel assembly of the vehicle and pneumatic caster T P tires of a steering wheel assembly of the vehicle. The collected samples must be sufficiently numerous and representative of various application cases to allow the classification algorithm to offer satisfactory performance regardless of its implementation conditions. For example, a minimum of one million sets of measurements taken under various conditions of tire-road contact adhesion, weather conditions, tire condition, road surface condition and vehicle dynamics will be used; - association 602 of a class of friction coefficient that can be mobilized by the vehicle to each set of measurements. This association (or labeling) can be done by an operator considering packages of sets of measurements, and consists of assigning a class from among the N output classes sought to each set of measurements; - Training 603 of the supervised machine learning classification algorithm. This step consists of providing it with the datasets collected during step 601 and the corresponding classes associated during step 602, which constitute the training data, so that it learns to associate the datasets with the different classes sought. - Validation 604 of the trained classification algorithm obtained, by introducing new input data into the model and verifying whether the algorithm's outputs correspond to the corresponding classes. A prediction accuracy rate per input class can then be measured. If this accuracy rate is greater than a given threshold for each of the classes considered, for example 95% accuracy, then the trained algorithm can be deployed for implementation. the algorithm's work. Otherwise, the algorithm's accuracy is insufficient, and the learning process must be restarted using new training data.

[0054] The trained classification algorithm can be used to implement the method for characterizing the friction coefficient available to the motor vehicle according to the invention on all vehicles in the range of the vehicle used to collect the training data, as well as on comparable vehicles. Comparable means that the characteristics of the vehicles, in particular their mass, dimensions, and tire size, are of the same order of magnitude.

[0055] According to a particular embodiment of the method according to the invention, the supervised learning classification algorithm implemented in step 503, which classifies the vehicle's available friction coefficient from a finite set of available friction coefficient classes, is configured to provide a probability associated with each classification. This probability provides an indication of the reliability of the determination, which can be taken into account to adapt step 504, which uses the calculated available friction coefficient class from a vehicle driver assistance system.

[0056] According to a particular embodiment of the method for characterizing the coefficient of friction available to the motor vehicle according to the invention, the steps of the method are only carried out when minimum lateral dynamic conditions are met. Indeed, to be accurate, the estimates of the drift stiffness C y and pneumatic hunting T P The tires of one or more steerable wheel sets of the motor vehicle, as carried out during steps 501 and 502, require the presence of a lateral force F y significant. Thus, this particular embodiment of the method according to the invention includes a preliminary step 505 of validating the lateral dynamic conditions of the motor vehicle. This validation can be done in different ways, for example from the longitudinal acceleration signals a x and lateral a y of the vehicle, taking:

[0057] In this embodiment, steps 501 to 504 of the process are performed only when Lateral Dynamics(t) is greater than or equal to a predefined threshold, for example 0.5 or 0.9. Setting the threshold at 0.5 ensures that the drift stiffness C estimates y and pneumatic hunting T P are carried out under conditions where the lateral dynamics of the vehicle are more stressed than the vertical dynamics.

[0058] In another embodiment, steps 501 and 502 are performed only when the vehicle is under conditions where sufficient lateral dynamics are exerted, i.e., when Lateral Dynamics(t) is greater than or equal to the predefined threshold. When this is not the case, the outputs of these two estimation steps correspond to the latest drift stiffness values ​​C y and pneumatic hunting T P calculated under satisfactory lateral dynamic conditions.

[0059] The invention relates to a method for characterizing the coefficient of friction available to a motor vehicle, implementing a supervised machine learning classification algorithm that takes as minimum inputs an estimate of the drift stiffness C y and an estimate of the pneumatic flush T P tires of one or more steerable wheel sets of the motor vehicle. This method is intended to be implemented on board a vehicle to allow it, for example at regular time intervals, to perform an estimation of this mobilizable friction coefficient.

[0060] When steps 501 and 502 include smoothing of the C drift stiffness measurements y and / or pneumatic flushing T P They can be carried out at higher frequencies than the 503 classification step, in order to increase the number of readings to converge towards very precise measurements.

[0061] The rate at which step 504 of using the class of friction coefficient mobilizable by the motor vehicle by a driving assistance system is carried out is independent of the rate of the preceding steps.

[0062] The main advantages of the classification method according to the invention are: - It allows for the rapid detection of intervals of the mobilizable friction coefficient, based on lateral vehicle dynamics data. - It can be implemented using signals available on the vehicle's CAN bus: therefore, there is no need to install specific sensors. - It improves vehicle safety, whether it's an autonomous vehicle or a vehicle equipped with driver assistance systems, - it allows the selection of the most suitable motor vehicle actuators for the context, and better management of the driving power of these actuators, thanks to knowledge of the class of mobilizable friction coefficient.

[0063] The invention also relates to a vehicle comprising an electronic data processing device, for example a computer or a microprocessor, configured to implement the method of characterizing the coefficient of friction that can be mobilized by a motor vehicle described above, from data acquired by sensors of the vehicle.

Claims

DEMANDS 1. A method for characterizing the coefficient of friction that can be mobilized by a motor vehicle, the method comprising: - a step (501) for estimating a drift stiffness C y tires from at least one set of steerable wheels of the motor vehicle, - a step (502) of estimating a pneumatic flush T P tires from at least one set of steerable wheels of the motor vehicle, - a step (503) of classifying the friction coefficient that can be mobilized by the motor vehicle, among a finite set of classes of mobilizable friction coefficients, by implementing a machine learning classification algorithm trained for this purpose taking as input said drift stiffness C y the vehicle's tires and said pneumatic tires T P of the vehicle, - a step (504) of using the class of friction coefficient mobilizable by the motor vehicle calculated during the previous step by a motor vehicle driving assistance system.

2. A method for characterizing the coefficient of friction available to a motor vehicle according to claim 1, wherein the step (503) of classifying the coefficient of friction available to the motor vehicle further comprises providing the machine learning classification algorithm with at least one type of data from among: - data on the nature and condition of a road surface, - meteorological data, - data relating to tires, - data relating to vehicle dynamics.

3. A method for characterizing the coefficient of friction available to a motor vehicle according to any one of the preceding claims, wherein step (501) of estimating a drift stiffness C y includes smoothing of a stiffness value calculated drift and / or step (502) of estimating a pneumatic flush T P includes smoothing of a calculated pneumatic flush value.

4. A method for characterizing the coefficient of friction available to a motor vehicle according to any one of the preceding claims, wherein step (501) of estimating a drift stiffness C y is implemented only when the tires of the steerable wheel assembly of the motor vehicle in question are in a linear operating zone.

5. A method for characterizing the coefficient of friction that can be mobilized by a motor vehicle according to any one of the preceding claims, further comprising a preliminary step (505) for validating the lateral dynamic conditions of the motor vehicle, and steps (501, 502, 503 and 504) for estimating a drift stiffness C y tires, estimation of a pneumatic tire pressure test (T) P tires, classification of the coefficient of friction available to the motor vehicle and use of the class of coefficient of friction available to the motor vehicle are only carried out when the lateral dynamic conditions are validated.

6. Method for characterizing the coefficient of friction that can be mobilized by a motor vehicle according to the preceding claim, wherein the lateral dynamic conditions of the motor vehicle are validated when the lateral dynamics of the motor vehicle are greater than its longitudinal dynamics.

7. Method for characterizing the friction coefficient that can be mobilized by a motor vehicle according to any one of the preceding claims, wherein the finite set of classes of friction coefficients that can be mobilized by the vehicle comprises two classes, and wherein the machine learning classification algorithm is a logistic regression algorithm.

8. A method for characterizing the coefficient of friction available to a motor vehicle according to any one of the preceding claims, wherein step (501) of estimating a drift stiffness C ytires of at least one set of directional wheels of the motor vehicle includes the calculation of C y such that: dF v C v = y dp with: - dF y a variation in the lateral force exerted on the tires of the wheel assembly in question, - dp a variation in the drift angle of the wheel assembly under consideration.

9. A method for characterizing the coefficient of friction available to a motor vehicle according to any one of the preceding claims, wherein step (502) of estimating a pneumatic slip T P tires of at least one set of directional wheels of the motor vehicle includes the calculation of T P such as : T pp ry with: - T AL a self-aligning torque of the considered wheel assembly, - F y a lateral force exerted on the tires of the wheel assembly in question.

10. Method for characterizing the mobilizable friction coefficient of a motor vehicle according to any one of the preceding claims, wherein the supervised learning classification algorithm is configured to provide a probability associated with the class of the mobilizable friction coefficient, said probability being taken into account during step (504) of using the class of mobilizable friction coefficient by a vehicle driving assistance system.

11. Motor vehicle comprising an electronic data processing device configured to implement a method for characterizing the mobilizable friction coefficient according to any one of claims 1 to 10.

Images