Method for automated management of the longitudinal speed of a motor vehicle.

Abstract

Method for managing the longitudinal speed of a first motor vehicle.Method for managing the longitudinal speed of a first motor vehicle, characterized in that it comprises an alternation between the following steps: - a learning step comprising an iteration of the following sub-steps: • a determination of a current driving mode of the first motor vehicle as being of a first type if a longitudinal speed of the first motor vehicle is controlled by a human driver, otherwise as being of a second type then • if the current driving mode is of the first type, a sub-step of recording observation data, • otherwise, an end-of-observation sub-step comprising a calculation of a model of a personalized tracking time from the observation data collected at different observation times, - an iteration of a step of automatic application of a personalized tracking time calculated from the personalized tracking time model. Figure for the abstract: 3.

Description

Title of the invention: Method for automated management of the longitudinal speed of a motor vehicle.

[0001] The invention relates to a method for automated management of the longitudinal speed of a motor vehicle. The invention also relates to a device for automated management of the longitudinal speed of a motor vehicle. The invention also relates to a computer program implementing the mentioned method. The invention finally relates to a recording medium on which such a program is recorded.

[0002] The longitudinal speed control of a motor vehicle can be automated, whether by a cruise control or by an autonomous driving system. Such automatic longitudinal speed management systems make it possible in particular to adapt the speed of the equipped vehicle to the presence of vehicles in its environment. Thus, when they are active, they act on the behavior of the vehicle like a virtual driver taking over part of the driving task.

[0003] Existing automatic longitudinal speed management systems can be configured according to predefined settings, but these do not necessarily correspond to the driver's driving habits.

[0004] Alternatively, some vehicles offer the possibility of configuring settings for these systems via a human-machine interface. But the increasing complexity of the systems makes their configuration too complex for users, and they may ultimately turn away from such driver assistance systems.

[0005] The aim of the invention is to provide a device and a method for automated longitudinal speed management which overcomes the above drawbacks and improves the devices and methods for automated longitudinal speed management known from the prior art. In particular, the invention makes it possible to produce a device and a method which are simple and reliable and which adapt to the driving habits of a user.

[0006] To this end, the invention relates to a method for managing the longitudinal speed of a first motor vehicle comprising a means for perceiving the environment located at the front of the motor vehicle and a first means for determining the speed and acceleration of the motor vehicle. The process involves alternating between the following steps: - a learning step comprising an iteration, at different observation times, of the following sub-steps: • a determination, at an observation time, of a current driving mode of the first motor vehicle as being of a first kind if a longi speed tudinal of the first motor vehicle is controlled by a human driver, if not as being of a second kind, then • if the current driving mode is of the first type, a sub-step of recording observation data comprising a measurement at the instant of observation of a longitudinal speed of the first motor vehicle and a calculation at the instant of observation of a driver following time separating the first motor vehicle from a second motor vehicle preceding the first motor vehicle on its traffic lane, the driver following time being calculated as a function of the data from the perception means and the first determination means, or • otherwise, an end-of-observation sub-step comprising a calculation of a model of a personalized monitoring time from the observation data collected during the different observation times, the calculation of the model comprising a calculation according to the least squares method, - an iteration of a step of automatic application of a personalized tracking time between the first motor vehicle and the second motor vehicle 200, the personalized tracking time being calculated from the personalized tracking time model and as a function of a longitudinal speed of the first motor vehicle measured by the first determination means at an iteration time of the application step.

[0007] In one embodiment, the motor vehicle further comprising a second means for determining a nature of weather conditions from among a predefined set of weather conditions, and - the observation data recording sub-step further comprises determining and recording weather conditions at the observation time from among the predefined set of weather conditions, - the end of observation sub-step includes an update of a sub-model of the consolidated model by meteorological condition of the predefined ensemble, and - the application step comprises a sub-step of determining, from the predefined set, the weather conditions at the iteration time, and the sub-model used to calculate the personalized tracking time is determined by the weather conditions determined at the iteration time.

[0008] In one embodiment, a custom tracking time model is a piecewise affine function that associates a driver tracking time with any longitudinal velocity within a given value interval, the given value interval being decomposed into subintervals delimiting pieces of the piecewise affine function.

[0009] In one embodiment, each given sub-interval is associated with a subset of the set of observations grouping the observations made when the longitudinal speed applied by the motor vehicle was within the range of speeds defined by the given subinterval, and in that the origin and the slope of the piecewise affine function delimited by the subinterval are calculated by applying the least squares method to the observations of the subset.

[0010] In one embodiment, the sub-intervals determine speed ranges of a fixed amplitude, for example speed ranges whose amplitude is equal to 10 kilometers per hour.

[0011] In one embodiment, the iterations of steps E2 and / or E3 are carried out at a frequency of a computer on which the method is executed, for example at a frequency of 100 Hertz.

[0012] In one embodiment, the method comprises a driving phase delimited by - a moment at the start of a driving phase, where a motor vehicle engine is started by means of a key or an ignition button by a driver, and - a moment at the end of a driving phase, where a motor vehicle engine is stopped by means of a key or an ignition button by a driver. In addition, between the driving phase start time and the driving phase end time, a personalized tracking time model is recorded in a volatile memory of the motor vehicle, and, at the driving phase end time, a personalized tracking time model is recorded in a non-volatile memory of the motor vehicle.

[0013] The invention further relates to a device for managing the longitudinal speed of a first motor vehicle, the motor vehicle being equipped with a longitudinal speed control module, an engine and a braking system, the device comprising hardware and / or software elements implementing the method according to the invention, in particular hardware and / or software elements designed to implement the method according to the invention, and / or the device comprising means for implementing the steps of the method according to the invention.

[0014] The invention further relates to a computer program product comprising program code instructions recorded on a computer-readable medium for implementing the steps of the method according to the invention when said program operates on a computer, or to a computer program product downloadable from a communication network and / or recorded on a data medium readable by a computer and / or executable by a computer, comprising instructions which, when the program is executed by the computer, cause the latter to implement the steps of the method according to the invention.

[0015] The invention also relates to a data recording medium, readable by a computer, on which is recorded a computer program comprising program code instructions for implementing the method according to the invention, or on a computer-readable recording medium comprising instructions which, when executed by a computer, cause the latter to implement the steps of the method according to the invention.

[0016] The invention also relates to a signal of a data medium, carrying the computer program product according to the invention.

[0017] The attached drawings represent, by way of example, an embodiment of a device for automated longitudinal speed management according to the invention and an embodiment of a method for automated longitudinal speed management according to the invention.

[0018] [Fig.l] represents a motor vehicle equipped with an automated longitudinal speed management device according to the invention.

[0019] [Fig.2] defines longitudinal and lateral speeds of the motor vehicle and of a vehicle targeting the preceding one on its traffic lane.

[0020] [Fig.3] describes the principle of the invention.

[0021] [Fig.4] is a first flowchart of an automated management method according to the invention.

[0022] [Fig.5] illustrates a method of updating a custom tracking time model.

[0023] [Fig.6] illustrates a method of applying a custom tracking time model.

[0024] [Fig.7] is a second flowchart of an automated management method according to the invention.

[0025] [Fig.8] is a flowchart of a learning step of a driver tracking time.

[0026] [Fig.9] is a flowchart of a step of automatically applying a personalized tracking time.

[0027] An embodiment of a vehicle equipped with a means for implementing an automated longitudinal speed management method is described below with reference to [Fig.l].

[0028] The first motor vehicle 100, or motor vehicle 100 may be a motor vehicle of any type, in particular a passenger vehicle, a utility vehicle, a truck or even a public transport vehicle such as a bus or a shuttle. According to the embodiment described, the motor vehicle 100 is an autonomous vehicle and will be referred to as an "autonomous vehicle" in the remainder of the description.

[0029] This illustration is therefore made without limitation. In particular the vehicle au- tomobile could be a non-autonomous vehicle, equipped with a driving assistance system, in particular a driving assistance system corresponding to a level greater than or equal to level 2 of autonomy, that is to say corresponding to partial autonomy of the vehicle.

[0030] The motor vehicle 100 comprises a system 10 for automated management of the longitudinal speed of a motor vehicle, also referred to in the remainder of the document as “management system 10”.

[0031] The management system 10 may be part of a more global driving assistance system 50, comprising a longitudinal speed control module 5 capable of transmitting control commands to an engine 6 or to a braking system 7 of the vehicle.

[0032] As a note, for its movement, the motor vehicle 100 may be equipped with several engines, for example a thermal engine and an electric motor. In the remainder of the document, stopping the motor vehicle 100 corresponds to stopping all of the engines used for the movement of the motor vehicle 100.

[0033] With reference to [Fig.2], it is assumed that the motor vehicle 10 is traveling on a traffic lane 40 of a road, and the terminology used in the remainder of the document is defined: - The axis called longitudinal axis 101 of the motor vehicle 100 is defined as an axis of symmetry of the motor vehicle 100 parallel to the axis along which the vehicle moves in a straight line, oriented towards the front of the vehicle. - The axis called the lateral axis 102 of the motor vehicle intersects the longitudinal axis 101 perpendicularly at a point located at the center of gravity of the motor vehicle 100, and it is oriented towards the left of the motor vehicle, the left and the right being defined according to the driver's point of view. - The speed vector 103 of the motor vehicle 100 in projection on the longitudinal axis 101 defines the longitudinal component 104 of the speed vector, called longitudinal speed. - The speed vector 103 of the motor vehicle 100 in projection on the lateral axis 102 defines the lateral component 105 of the speed vector, called lateral speed. - Similarly, a distance between two vehicles can be projected onto the longitudinal and lateral axes, thus defining a longitudinal distance -or following distance DS- and a lateral distance.

[0034] The same terminology is applied to define the position and speed parameters of a second vehicle 200, shown in [Fig.2]. The second vehicle 200 is characterized by the fact that it travels on the same lane 40 as the motor vehicle 100 and is located directly in front of it. In the remainder of the document, the second vehicle 200 may be referred to interchangeably as the target vehicle 200.

[0035] A target vehicle 200 may be a motor vehicle of any type, including a passenger vehicle or a utility vehicle or even a motorcycle.

[0036] In the remainder of the document, the term “following time” refers to the time that it would take, at a given instant, for the motor vehicle 100 to reach the position of a target vehicle 200. In this context, the motor vehicle 100 may also be designated by the term “following vehicle”.

[0037] [Fig. 3] makes it possible to compare automatic management and manual management of the tracking time applied between a following vehicle and a target vehicle, the automatic management being carried out without implementing the invention.

[0038] Graphs G30, G40 and G50 illustrate the evolution of the tracking time as a function of the longitudinal speed of the following vehicle. The tracking time is expressed in seconds on the ordinate axis 400 and the longitudinal speed of the following vehicle is expressed in kilometers per hour on the abscissa axis 300.

[0039] The TS_min and TS_max markers respectively represent a minimum tracking time and a maximum tracking time. The minimum tracking time TS_min corresponds to a lower limit of the tracking time below which the following vehicle presents a significant risk of accident, for example 0.5 seconds. The maximum tracking time TS_max corresponds to a detection limit of the target vehicle, for example 3 seconds.

[0040] Graph G30 illustrates an implementation of a conventional automatic following time management system - without implementing the invention - which allows a driver to choose between several predefined automatic following time profiles. In the case represented by [Fig.3], the conventional system applies a mapping of several profiles PI, P2, Pi, Pj of the evolution of the following time as a function of the longitudinal speed of the following vehicle. The profiles PI, P2, Pi, Pj determine a substantially linear and increasing variation of the automatic following time as a function of the longitudinal speed of the following vehicle. If the driver selects the PI profile, the conventional system will implement a reduced automatic following time, whereas if he chooses the Pj profile, the conventional system will implement a high automatic following time. Other profiles, such as P2 to Pi, allow intermediate settings between the PI and Pj profiles.

[0041] Graph G40 makes it possible to compare a manual TSM tracking time profile implemented by a driver with automatic PI, Pj profiles. In the illustrated case, the TSM tracking time does not evolve linearly as a function of the longitudinal speed of the following vehicle. Whatever the PI to Pj profile chosen, the operation of the conventional automatic tracking time management system will differ from the driver's tracking habits.

[0042] Graph G50 illustrates the principle of the invention in which a personalized profile automatic follow-up time profile TSP is obtained by decomposing a manual follow-up time profile TSM into a succession of linear segments (corresponding to segments SI to S6). Thus the application of the personalized automatic follow-up time profile TSP will be consistent with the driver's following habits.

[0043] For this, the management system 10 alternates between phases of learning a personalized tracking time profile and phases of implementing a personalized tracking time profile.

[0044] In other words: - In an operating mode of the first type M_MANUAL, the control of the longitudinal speed of the motor vehicle 100 can be manual. In this case, the longitudinal speed of the motor vehicle 100 is determined by the driver. In this operating mode, the management system 10 performs a learning process of the driver's driving habits, relating in particular to the following time TSC applied by the driver between a target vehicle 200 and the motor vehicle 100. The learning process comprises the construction of a personalized following time model MOD_TSP which will be described later in this document. - In an operating mode of the second type M_AUTO, the control of the longitudinal speed of the motor vehicle 100 can be automatic, that is to say determined by the management system 10 from the personalized tracking time model MOD_TSP. Thus, in the second operating mode, the longitudinal speed is preferentially determined so as to apply a tracking time TSP reproducing the driving habits of the driver of the motor vehicle 100.

[0045] The system 10 for automated management of the longitudinal speed of a motor vehicle mainly comprises the following elements: - a means of perception 1 of the environment located in front of the motor vehicle 100, of the radar, camera or lidar type, - a means of determining 2 the speed and acceleration of the motor vehicle 100, - a human-machine interface 3 allowing the driver to manage the activation and deactivation of the automatic longitudinal speed management, and to determine whether the automatic longitudinal speed management is carried out by applying predefined tracking times, or by applying learned tracking times, - a processing unit 4 comprising a microprocessor 41, a memory 42 and communication interfaces 43.

[0046] The management system 10, and particularly the microprocessor 41, mainly comprises the following modules which cooperate with each other: - a 411 mission start module, this module being able to cooperate with the interface man-machine 3 and / or memory 42, - a module 412 for learning a driver tracking time, this module being able to cooperate with the perception means 1, the determination means 2, the human-machine interface 3 and / or the memory 42, - a module 413 for automatically applying a personalized tracking time, this module being able to cooperate with the perception means 1 and the determination means 2, the human-machine interface 3, the longitudinal speed control module 5 and / or the memory 42, - an end-of-mission module 414, this module being able to cooperate with the human-machine interface 3 and / or the memory 42,

[0047] The motor vehicle 100, in particular the management system 10, preferably comprises all the hardware and / or software elements configured so as to implement the method defined in the subject of the invention or the method described below.

[0048] The detection means 1 may comprise for example a radar, and / or a lidar, and / or a camera and / or any other type of sensor suitable for detecting targets in front of the motor vehicle 100.

[0049] The detection means 1 can provide measurements to the microprocessor 3, including: - the longitudinal distance DS between the motor vehicle 100 and the target vehicle 200, - the longitudinal speed 204 of the target vehicle 200, and - the longitudinal acceleration of the target vehicle 200.

[0050] Preferably, the analysis of the images provided by the detection means 1 can also provide data concerning the weather conditions which may influence the driving of the motor vehicle 100. In particular, the detection means 1 makes it possible to detect the presence of rain or snow.

[0051] Thus, in one embodiment, the detection means 1 makes it possible to determine at each instant the meteorological conditions in which the motor vehicle 100 is operating as being rainy conditions M_RAIN, snowy conditions M_SNOW or otherwise normal conditions M_NORMAL.

[0052] A meteorological criterion can thus be taken into account in the construction and application of the personalized tracking time model MOD_TSP.

[0053] In one embodiment, the MOD_TSP model could comprise several sub-models MOD_TSP_NO, MOD_TSP_P, MOD_TSP_NE each corresponding respectively to each of the weather conditions, NORMAL, M_RAIN, M_SNOW.

[0054] In an alternative embodiment not developed in this document, weather data and / or other environmental conditions that may modify the vi sibility could be inferred from, for example, a wiper operation indicator and / or a lighting status.

[0055] The means 2 for determining the speed and acceleration of the motor vehicle 100 can be carried out by computers using data relating to the chassis of the motor vehicle 100, data from the wheel rotation speed sensors.

[0056] The human-machine interface 3 allows the driver in particular to alternate between a driving mode of a first type M_MANUAL, in which he manually controls the longitudinal speed of the motor vehicle 100, and a driving mode of the second type M_AUTO in which the control of the longitudinal speed is automatic. Different embodiments are conceivable for the human-machine interface 3, for example buttons and / or a touch screen and / or voice control.

[0057] The human-machine interface 3 allows the driver to specify whether the automatic longitudinal speed control should apply predefined tracking times or learned tracking times.

[0058] The predefined tracking times may correspond to tracking time values defined during vehicle calibration. Alternatively, the predefined tracking times may be values defined by the driver via the human-machine interface 3.

[0059] In contrast to the predefined tracking times, the learned tracking times - referred to in the remainder of the document as "personalized tracking times TSP" - are calculated automatically by the management system 10 during the manual driving phases, so as to reproduce the driver's habits during the automatic driving phases. The learned tracking times are recorded in one or more MOD_TSP models.

[0060] In an embodiment not shown in [Fig.l], the management system 10 could receive information from a user management system of the motor vehicle 100. Thus, the longitudinal speed management system 10 could construct a MOD_TSP model per user. In other words, if the motor vehicle 100 is equipped with a user management system, then a personalized tracking time can be managed for each of the users of the motor vehicle 100, so as to adapt the behavior of the vehicle to each of the users.

[0061] The module 413 for applying a personalized tracking time is capable of transmitting, via communication interfaces 43, a tracking time to the longitudinal speed control module 5. The module 5 transmits control orders to the engine 6 or to the braking system 7 so as to apply the tracking time determined by the management system 10.

[0062] The memory 42 constitutes a recording medium readable by a computer or by the calculator comprising instructions which, when executed by the computer or the calculator, lead it to implement a management method 10 according to an embodiment of the invention.

[0063] The memory 42 also makes it possible to record the personalized tracking time model MOD_TSP. Advantageously, the memory 42 comprises a volatile memory 421, the contents of which are erased regularly, in particular when the memory is no longer supplied with electric current, and a non-volatile memory 422 the contents of which persist over time even when it is no longer supplied with electric current.

[0064] The personalized tracking time model MOD_TSP will advantageously be constructed over the course of the missions (or drives) of the motor vehicle 100, a mission being a driving phase delimited by - a start of mission, where the motor vehicle 100 is stationary and the driver starts the vehicle using, for example, a key or an ignition button, - an end of mission, corresponding to a stopping of the vehicle by the driver using, for example, a key or an ignition button.

[0065] As a note, during the same mission several phases of automatic engine shutdown (in particular, those generated by a “stop and start” system) may occur.

[0066] In a preferred embodiment, the memory 42 makes it possible to record at the end of an Nth mission of the motor vehicle 100 a MOD_TSPN model, corresponding to an update of a MOD_TSPN model i recorded during the previous mission. The update of the MOD_TSPN model takes into account the learning carried out during the Nth mission.

[0067] In a preferred embodiment, the memory 42 comprises a volatile memory 421 and a non-volatile memory 422. Such an architecture allows, - on the one hand, during the course of an Nth mission, to record in volatile memory 421 the temporary data necessary for the construction of the MOD_TSPn model, and - on the other hand, to record in non-volatile memory 422 the MOD_TSPN model generated at the end of an Nth mission, and to keep it until the end of the N+1th mission.

[0068] The motor vehicle 100, in particular the management system 10, preferably comprises all the hardware and / or software elements configured so as to implement the method defined in the subject of the invention or the method described below.

[0069] A mode of execution of the method for managing the longitudinal speed of a motor vehicle is described below with reference to [Fig.4]. The method comprises four steps E1 to E4 which take place over the duration of an Nth mission of the motor vehicle 100: - steps E1 and E4 are executed respectively at the beginning of the Nth mission, and at the end of the Nth mission, and - during the progress of the Nth mission, the method comprises an alternation of iterations on one or other of the steps E2 or E3.

[0070] In a mission start step El, the method is initialized for the Nth mission of the vehicle.

[0071] The initialization of the method comprises a recovery in non-volatile memory 422 of a personalized tracking time model MOD_TSPN i, which was saved in the non-volatile memory 422 at the end of the N-th mission. At the start of the Nth mission, the MOD_TSPN model is therefore equal to the MOD TSPX model ।

[0072] Under certain conditions, the MOD_TSPN i model may contain a default value of the MOD_TSP0 model. This is the case, for example, - if N=1, that is to say if it is the very first mission of the motor vehicle 100, or - if the motor vehicle 100 has always been used by applying the automatic mode M_AUTO for tracking time management.

[0073] For example, the default value of the MOD_TSP0 model may correspond to a model which associates, with any value of the longitudinal speed, a default tracking time, for example a tracking time of 2 seconds.

[0074] Furthermore, in step E1, an initial driving mode of the first motor vehicle 100 is determined. - as being of a first kind M_MANUEL if the longitudinal speed of the motor vehicle 100 is controlled at the initialization time by a human driver, - as being of a second kind M_AUTO if the longitudinal speed of the motor vehicle 100 is controlled at the initialization time by the longitudinal speed control module 5.

[0075] In one embodiment, the initial driving mode of the motor vehicle 100 can be determined by the value of a variable MODE_V stored in memory, in particular in the volatile memory 421. The variable MODE_V could take the values M_MANUEL and M_AUTO. For example, the value of the variable MODE_V could be updated in memory as a function of an action by the driver of the motor vehicle 100 on the human-machine interface 3.

[0076] In one embodiment, the variable MODE_V could further take a third value M_STOP when the driver ends the current mission.

[0077] If the initial driving mode is determined as being of the first type M_MANUAL, then we continue with the second learning step E2; if the initial driving mode is determined as being of the second type M_AUTO, then continues with the third step E3 of applying a personalized tracking time.

[0078] The learning step E2 includes an iteration, at different times observation T_OBSP, of the following sub-steps:

[0079] - a determination, at the observation time T_OBSP, of a driving mode current of the first motor vehicle 100 as being of a first kind M_MANUEL if a longitudinal speed of the first motor vehicle 100 is controlled by a human driver, otherwise as being of a second kind M_AUTO, then - if the current driving mode is of the first type M_MANUAL, a sub-step E21 of recording observation data D_OBSP comprising a measurement at the observation time T_OBSP of a longitudinal speed of the first motor vehicle 100 and a calculation at the observation time T_OBSP of a driver following time TSCP separating the first motor vehicle 100 from a second motor vehicle 200 preceding the first motor vehicle on its traffic lane 40, the driver following time TSCP being calculated as a function of the data from the perception means 1 and the determination means 2, or - if the current driving mode is the second mode M_AUTO, an end-of-observation sub-step E22 comprising an update of a model of a personalized tracking time MOD_TSP from the observation data D_OBS collected at the different observation times T_OBSP, the update comprising a calculation according to the least squares method.

[0080] As a side note, - for p=l, that is to say during the first iteration of step E2, the determination of a current driving mode of the first motor vehicle 100 is carried out in step El, then - as explained below, for p>l the determination at the observation time T_OBSP of a current driving mode of the first motor vehicle 100 is carried out in a sub-step E22 of the p-lth iteration of step E2.

[0081] Thus, at the start of an Nth mission of the vehicle, if the initial driving mode calculated in step E1 is manual, we continue with step E2 which iterates over sub-step E21 followed by sub-step E22.

[0082] In a first sub-step E21, a driver following time TSCP separating the motor vehicle 100 from a target vehicle 200 preceding the motor vehicle 100 on its traffic lane 40 is calculated, the driver following time being calculated as a function of the data from the perception means 1 and the determination means 2.

[0083] The following measurements are received from the detection means 1: - a longitudinal distance DSP measured between the motor vehicle 100 and the target vehicle 200, - a longitudinal speed 204 of the target vehicle 200, and - a longitudinal acceleration Ac of the target vehicle 200.

[0084] In addition, the determination means 2 provides a longitudinal speed VLP and an acceleration Ap of the motor vehicle 100.

[0085] The driver tracking time can thus be calculated from the longitudinal distance DSP, the speeds 204, VLP and the longitudinal accelerations Ac and Ap.

[0086] In a preferred embodiment, sub-step E21 begins with a processing of verification of conditions required for recording an observation. For example, the required conditions preferably include: - detection of a target vehicle 200, - the stabilization of the longitudinal speed of the motor vehicle 100 and of the longitudinal speed of the target vehicle 200, the variations of which must be less than a first given threshold, - the stabilization of a longitudinal distance measured between the motor vehicle 100 and the target vehicle 200, the variations of which must be less than a second given threshold.

[0087] The first given threshold may correspond to a percentage of the current speed of the motor vehicle 100, for example 2% of the current speed. In this case, the first threshold is approximately 2 km / h for a current speed of 110 km / h. This percentage may be calibrated to other percentage values.

[0088] The second given threshold may correspond to a percentage of the current distance between the motor vehicle 100 and the target vehicle 200, for example 1% of the current distance between the motor vehicle 100 and the target vehicle 200. In one embodiment, the second threshold may be, for example, approximately 6 meters for a current speed of 110 km / h.

[0089] Preferably, the required conditions must be satisfied for a minimum duration of 2 seconds.

[0090] The current tracking time can then be determined from the tracking distance DS p and a relative longitudinal speed VLRP calculated between the target vehicle 200 and the motor vehicle 100.

[0091] Thus, in sub-step E21, a pth observation D_OBSPp is recorded comprising a driver tracking time TSCP and a speed VLP applied at an instant T_OBSP.

[0092] Advantageously, sub-step E21 can further comprise a determination and recording of meteorological conditions METEO_MP at the observation time T_OBSP from a predefined set ENS_METEO of meteorological conditions.

[0093] For example, from data from the perception means 1, in sub-step E21 the presence of rain or snow is detected, then the value of the meteorological conditions METEO_MP at the observation time T_OBSP is defined as being one of the conditions defined in the predefined set ENS_METEO, that is to say as being equal to M_NORMAL, M_RAIN, M_SNOW. The data METEO_MP is then integrated into the pth observation D_OBSP.

[0094] In an embodiment where the MOD_TSP model comprises several sub-models MOD_TSP_NO, MOD_TSP_P, MOD_TSP_NE each corresponding respectively to the meteorological conditions, M_NORMAL, M_RAIN, M_SNOW, the pth observation D_OBSP will be integrated into the sub-model determined by the METEO_MP data.

[0095] We then continue with sub-step E22 in which a time delay is started with a duration equal to an iteration period P_ITER_MAN. In one embodiment, the iteration period of sub-steps E21 and E22 is determined by the processing frequency of the computer, i.e. 100 Hertz.

[0096] The timer expires at a time T_OBSp+i,=T_OBSp+P_ITER_MAN.

[0097] At time T_OBSp+i, we check - on the one hand if the Nth mission of the vehicle continues and - on the other hand if the manual driving phase continues.

[0098] To do this, we check that the value of the variable M0DE_V is indeed M_MANUEL. If so, we loop back to recording step E21.

[0099] If the value of the variable MODE_V is different from M_MANUEL, then an end of learning phase is detected, that is to say the end of a continuous phase of iterations of sub-steps E21 and E22.

[0100] In this case, sub-step E22 comprises an update of the MOD_TSPN model by integrating the observation data D_OBSP acquired during the learning phase which ends.

[0101] In one embodiment, a custom tracking time model MOD_TSPN is a piecewise affine function that associates a driver tracking time TSCP with any longitudinal velocity VLP included in a given value interval [VLmin, VLmax], the given value interval [VLmin, VLmax] being decomposed into a set of sub-intervals II, I2, Ij delimiting the pieces of the affine function.

[0102] In one embodiment, sub-intervals II, I2, Ij are of the same amplitude, for example they determine speed ranges whose amplitude is 10 kilometers per hour.

[0103] In one embodiment, a first processing consists of constructing an evolution curve C5 of the driver tracking time TSC as a function of the longitudinal speed of the motor vehicle 100 as represented by [Fig.5]. The time of followed is expressed in seconds on the 400 y-axis and the longitudinal speed of the following vehicle is expressed in kilometers per hour on the 300 x-axis.

[0104] The abscissa axis 300 is segmented into intervals or speed ranges Ij of the same amplitude, for example into intervals or ranges of 10 km / h. Alternatively, the intervals or ranges could be of variable length, to refine the model over certain speed ranges.

[0105] The curve C5 is discretized into segments Sj, each representing - over a given range of longitudinal speeds Ij - a linear evolution of the driver tracking time as a function of the longitudinal speed. Each segment Sj is characterized by a triplet (aj, bj, nj) which is calculated in the manner described below.

[0106] The segment Sj is determined from a subset of observation data D_OBSj, relating to observations made when the longitudinal speed of the motor vehicle 100 was within the speed range Ij.

[0107] Each observation data of the subset D_OBSj can be represented by a point My with coordinates (xy, yy), - xy being the longitudinal speed of the motor vehicle 100 determined in sub-step E21, and - yy being the tracking time determined in sub-step E21.

[0108] We note nj the number of observations of the subset D_OBSj, that is to say the number of points Myused to determine the segment Sj.

[0109] The slope aj and the origin bj of the segment Sj are calculated according to the Mathl formula applying the least squares method:

[0110] [Math.l] ~ v"' 7 [YES] where - is the average of the nj xy, - ÿj is the average of the nj yy,

[0112] The segments Sj being each characterized by a triplet (aj, bj, nj), they together constitute a model of the driver tracking time resulting from the last learning phase.

[0113] Advantageously, the model obtained is consolidated in order to also take into account the data observed during the previous learning phases, that is to say a prev_MOD_TSPN model defined at the end of the previous learning phase.

[0114] In one embodiment, the new model new_MOD_TSPN is determined by calculating a weighted average between the model prev_MOD_TSPN and the resulting model D_OBS data collected in the last learning phase (represented by curve C5).

[0115] The prev_MOD_TSPN model consists of a series of prev_MOD_TSPNj sub-models or prev_SNj segments characterized by a triplet (prev_aNj, prev_bNj, prev_nNj), - the line segment prev_SNj having origin prev_bNj and slope prev_aNj, - a number prev_nNj of measurement points having been used to determine the segment prev_SNj.

[0116] Similarly, the new_MOD_TSPN model consists of a series of new_MOD_TSPNj sub-models or new_SNj segments characterized by a triplet (new_aNj, new_bNj, new_nNj), - the straight line segment new_SNj having origin new_bNj and slope new_aNj, - a number new_nNj of measurement points having been used to determine the segment new_SNj.

[0117] In one embodiment, each sub-model new_MOD_TSPNj is defined by the triplet (new_aNj, new_bNj, new_nNj) calculated according to the formulas Math2 to Math4:

[0118] [Math.2] prev_.n^. n new_a Nj = wïjip; x prev_a Nj + xa f

[0119] [Math.3] prev^i^.. n. new_b Nj = x prev_b Nj + x bj

[0120] [Math.4] new_n Nj = prev_n Nj + nj

[0121] As a note, the new_Sj segments thus obtained are not systematically joined to each other. In order to obtain a continuous model, filters are applied to the new model new_MOD_TSPN. In one embodiment, the filters used may be linear filters of order 2. Alternatively, other types of filters may be used.

[0122] In the rest of the document the new_MOD_TSPN model is named MOD_TSPN. At the end of step E2, the MOD_TSPN model is the model resulting from the most recent learning phase of the Nth mission.

[0123] In an advantageous embodiment, if the observation data D_OBSN comprises meteorological data, a model can be created per meteorological condition of the set ENS_METEO, for example respectively a model for rainy, snowy and normal weather conditions.

[0124] In this case, - observations made in rainy weather conditions will be used to generate a first MOD_TSP_PN model of driver tracking time in rainy weather conditions, - observations made in snowy weather conditions will be used to generate a second MOD_TSP_NEn model of driver tracking time in snowy weather conditions, and - observations made in other weather conditions will be used to generate a third MOD_TSP_NOn model of driver tracking time in other weather conditions.

[0125] The method of constructing each of the MOD_TSP_NOn MOD_TSP_Pn and MOD_TSP_NEn models may be similar to the calculation method previously set out.

[0126] The obtained MOD_TSPN model is stored in the volatile memory 421.

[0127] Following sub-step E22, step E2, the method can continue either with an end-of-mission phase implemented in step E4, or with a phase of automatic application of a personalized monitoring time implemented in iterations of step E3: - If the value of the variable M0DE_V is M_STOP, this means that the driver has ended the Nth mission between times T_OBSP and T_OBSp+i. We therefore continue with step E4, the end of mission. - If the value of the variable M0DE_V is M_AUT0, this means that the driver has activated automatic tracking time management. In this case, we continue with step E3 of applying a personalized tracking time.

[0128] Step E3 comprises an iteration at different times T_AUTOq on two sub-steps E31 and E32.

[0129] At an iteration time T_AUTOq, in sub-step E31 the type of automatic tracking time that the driver wishes to apply is determined, i.e. predefined tracking times, or tracking times personalized by learning.

[0130] If the driver has configured the automatic driving mode to apply predefined following times, a predefined following time value is transmitted to the longitudinal speed control module 5. We then continue with sub-step E32.

[0131] If the driver has configured the automatic driving mode to apply a personalized tracking time by learning, the MOD_TSPN model available in memory is retrieved and used to calculate a personalized tracking time TSPq which will be applied automatically, at time T_AUTOq, between the motor vehicle 100 and the target vehicle 200. The personalized tracking time TSPq is calculated as a function of the longitudinal speed VLq of the motor vehicle 100 measured at time T_AUTOq.

[0132] [Fig.6] describes a method for calculating a personalized tracking time from the longitudinal speed VLq of the motor vehicle 100.

[0133] The longitudinal velocity VLq makes it possible to determine which segment SNj of the MOD_TSPn model will be used to calculate the personalized tracking time. The segment SNj is characterized by the triplet (aNj, bNj, nNj). We then determine the coordinates of the middle ZNj of the segment SNj, i.e. the abscissa VL_ZNj and the ordinate TSP_ZNj. The ordinate TSP_ZNj represents the middle tracking time of the segment SNj; it is determined by the following Math 5 formula:

[0134] [Math.5] TSP_ZNj = aNJ x VL_ZNj + hNj

[0135] From the middle tracking time TSP_ZNj and the longitudinal speed VLq measured at time T_AUTOq, the personalized tracking time TSP is determined by interpolation. q-

[0136] The personalized tracking time TSPq is then transmitted to the longitudinal speed control module 5.

[0137] Advantageously, the sub-step E31 may further comprise a determination of meteorological conditions METEO_Aq at the instant of application T_AUTOq. For example, from data originating from the perception means 1, in the sub-step E31 the presence of rain or snow is detected, then the value of the meteorological conditions METEO_Aq at the instant of application T_AUTOq is defined as being one of the conditions defined in the predefined set ENS_METEO, i.e. as being equal to M_NORMAL, M_RAIN, M_SNOW.

[0138] The METEO_Aq data is then used to choose the sub-model adapted to the meteorological conditions to determine a personalized monitoring time TSPq, among the sub-models MOD_TSP_NO, MOD_TSP_P, MOD_TSP_NE each corresponding respectively to each of the meteorological conditions, NORMAL, M_RAIN, M_SNOW.

[0139] Following sub-step E31, we continue with sub-step E32 in which we start a time delay of a duration equal to an iteration period P_ITER_AUTO. In one embodiment, the iteration period of sub-steps E31 and E32 is determined by the processing frequency of the computer, i.e. 100 Hertz.

[0140] The P_ITER_AUTO iteration period of sub-steps E31 and E32 may be different from the P_ITER_MAN iteration period of sub-steps E21 and E22.

[0141] The timer expires at a time T_AUTOq+i=T_AUTOq +P_ITER_AUTO.

[0142] At time T_AUTOq+i, we then check whether the Nth mission of the vehicle continues and whether the automatic driving phase continues.

[0143] To do this, we check that the value of the variable M0DE_V is indeed M_AUT0. If Yes, we loop back to application step E31.

[0144] If the value of the variable MODE_V is different from M_AUTO, then an end of the phase of automatic application of a personalized tracking time is detected, that is to say the end of a continuous phase of iterations of the sub-steps E31 and E32.

[0145] The method can then continue either on an end-of-mission phase implemented in step E4, or on a learning phase implemented in step E2: - If the value of the variable M0DE_V is M_STOP, this means that the driver has ended the Nth mission between times T_AUTOq and T_AUTOq+i. We therefore continue with step E4, the end of mission. - If the value of the M0DE_V variable is M_MANUEL, this means that the driver has disabled automatic tracking time management. In this case, we continue with learning step E2.

[0146] In the end-of-mission step E4, the MOD_TSPN model available in volatile memory 421 is recovered and saved in non-volatile memory 422.

[0147] The data previously recorded in volatile memory are erased. The MOD_TSPN model from the Nth mission (stored in a non-volatile memory 422) will subsequently serve as the initial model at the input of step E1 during the course of the N+1th mission.

[0148] The embodiments previously described for the MOD_TSPN model advantageously make it possible to preserve the lifetime of the volatile memory 422. Indeed, current computers make it possible to perform a million write cycles in non-volatile memories. In the case where a MOD_TSPN model takes into account the following parameters: - one user profile per vehicle, - three types of weather conditions: M_NORMAL, M_RAIN, M_SNOW, - twelve speed intervals Ij, - for each interval Ij three parameters determined by the least squares method: aj, bj, nj, and if we use four bytes to encode each parameter of the MOD_TSPn model, then each model uses 432 bytes in memory.

[0149] It is further verified that the frequency of the memory recordings induced by the implementation of the method according to the invention is compatible with the lifetime of the non-volatile memory 422. For this, a lifetime of twenty years is considered for the motor vehicle 100. Knowing that, over its entire lifetime, the non-volatile memory 422 can withstand up to one million write cycles, an average limit of 137 write cycles in non-volatile memory per day is calculated, for 20 years. This average daily limit greatly exceeds the daily writing needs in non-volatile memory of the motor vehicle 100 in the event of implementation work of the invention.

[0150] Thus, the size of the MOD_TSPN model and the frequency of recording a model at the end of each mission are compatible with the lifetime of the non-volatile memory 422.

[0151] [Fig.7] is a second flowchart of an automated management method according to the invention. In a first step 70, the mission of the motor vehicle 100 is started. In a step 71, it is tested whether the mission is completed.

[0152] If the mission is completed, we continue with step 79 for the end of mission, which may include recording data in non-volatile memory. Then, following step 79, we loop back to step 70.

[0153] If the mission continues, we move on to a step 72 of reading a personalized tracking time model from memory.

[0154] Then, in a step 73, the current driving mode of the motor vehicle 100 is identified.

[0155] Then, in a step 74, we check whether the current driving mode is manual: - If the current driving mode is manual, we continue with step 75 for learning a personalized setting for a tracking time. Then, in step 77, we test whether the mission is finished. If so, we continue with step 79 for mission end. If not, we loop back to step 73 for identifying the current driving mode. - If the current driving mode is automatic, we continue with a step 76 of automatic application of a personalized setting of a tracking time. Then, in a step 78, we test if the mission is finished. If yes, we continue with step 79 of mission end. If not, we loop back to step 73 of identification of the current driving mode.

[0156] [Fig.8] is a flowchart detailing an embodiment of step 75 of learning a driver tracking time. In a step 80, the learning is initialized.

[0157] Then we move on to a step Ml of testing rainy weather conditions.

[0158] If the weather conditions are rainy, then we move on to a learning process relating to rainy weather conditions, comprising - a step 81 of verification of learning conditions, then - a step 82 of observation of tracking times applied by the driver, then - a step 83 of updating a tracking time model applied by the driver in rainy weather conditions, then - we loop back to step 80.

[0159] If the weather conditions are not rainy, we continue with a stage M2 of testing snowy weather conditions.

[0160] If the weather conditions are snowy, then we continue with a learning process relating to snowy weather conditions, comprising - a step 84 of verification of learning conditions, then - a step 85 of observation of tracking times applied by the driver, then - a step 86 of updating a tracking time model applied by the driver in snowy weather conditions, then - we loop back to step 80.

[0161] If the weather conditions are neither rainy nor snowy, we continue with a learning process relating to normal weather conditions, comprising - a step 87 of verification of learning conditions, then - a step 88 of observation of tracking times applied by the driver, then - a step 89 of updating a tracking time model applied by the driver in normal weather conditions, then - we loop back to step 80.

[0162] [Fig.9] is a flowchart detailing one embodiment of step 76 of automatically applying a custom setting of a tracking time.

[0163] In a step 90, the automatic application of a personalized setting of a tracking time is started.

[0164] Then, in a step 91, it is checked whether the driver wishes an automatic determination of the tracking time according to personalized settings or according to non-personalized predefined settings.

[0165] Then, in a step 92, the weather conditions at the time of application are determined.

[0166] Then, in a step 93, we test whether the weather conditions are rainy.

[0167] If the weather conditions are rainy, then we continue with a step 94 of processing the application of a monitoring time relating to rainy weather conditions, then we loop back to step 90.

[0168] If the weather conditions are not rainy, we continue with a step 95 of testing snowy weather conditions.

[0169] If the weather conditions are snowy, then we continue with a step 96 of processing the application of a tracking time relating to snowy weather conditions, then we loop back to step 90.

[0170] If the weather conditions are not snowy, then we continue with a step 97 of processing the application of a monitoring time relative to normal weather conditions, then we loop back to step 90.

[0171] Finally, the method for managing longitudinal speed according to the invention has multiple advantages.

[0172] Firstly, it allows the motor vehicle 100 to learn a personalized tracking time over the missions carried out by the driver. The learning of the driver tracking time takes into account several criteria likely to influence the tracking time applied by a human driver. Firstly, the longitudinal speed of the motor vehicle 100 is an essential parameter of the model. The conditions in which the vehicle is traveling are also taken into account, in particular the weather conditions. Other conditions likely to influence the tracking time could also be taken into account, for example the exterior brightness or the state of the roadway. In addition or alternatively, the integration of information linked to traffic could allow an adaptation of the tracking time to the traffic density.Indeed, in heavy traffic situations, a driver might tend to reduce his following time to avoid vehicle insertions between his vehicle and the target vehicle.

[0173] Thus, thanks to the invention, the driver can find in an automatic longitudinal speed management mode the same driving sensations as those he would have in a manual driving mode. In addition, the customization of the tracking time can advantageously be differentiated according to different users of the motor vehicle 100. By imitating the behavior of the driver, the invention contributes to the acceptance of the autonomous driving system by the driver and therefore to an increase in the frequency of its use. The invention thus makes it possible to improve the safety of the driver and the occupants of the vehicle.

[0174] The method for managing longitudinal speed according to the invention also makes it possible to simplify the human-machine interface relating to the use of an automatic longitudinal speed management system.

[0175] The longitudinal speed management method according to the invention also makes it possible to reduce the number of parameters requiring predefined adjustment before the vehicle is put into circulation. The cost of vehicle development is therefore reduced.

[0176] Furthermore, the method for managing longitudinal speed according to the invention can operate solely from data originating from means on board the motor vehicle 100. In other words, the technical means required for implementing the invention are available on any vehicle whose autonomy level is greater than or equal to 1.

[0177] Furthermore, the method for managing longitudinal speed according to the invention uses the least squares method to construct a tracking time model. This embodiment makes it possible to reduce the impact of a few observations that would deviate from a trend defined by the majority of observations. In other words, the least squares method makes it possible to smooth the model created during the execution of the method for managing longitudinal speed according to the invention. The least squares method least squares also makes it possible to define a MOD_TSPN model which uses little space in non-volatile memory 422, as was previously developed, which makes it possible to preserve the lifespan of the non-volatile memory 422 and to avoid its obsolescence during the life of the vehicle.

[0178] The invention could also make it possible to evaluate the driving of a user of the vehicle, with the aim of providing him with indicators on a level of safety or a level of energy consumption in relation to his driving.

Claims

Claims

1. Method for managing the longitudinal speed of a first motor vehicle (100) comprising a means (1) for perceiving the environment located in front of the motor vehicle (100) and a first means (2) for determining the speed and acceleration of the motor vehicle (100), characterized in that it comprises an alternation between the following steps: - a learning step (E2) comprising an iteration, at different observation times (T_OBSP), of the following sub-steps: • a determination, at an observation time (T_OBSP), of a current driving mode of the first motor vehicle (100) as being of a first kind (M_MANUAL) if a longitudinal speed of the first motor vehicle (100) is controlled by a human driver, otherwise as being of a second kind (M_AUTO), then • if the current driving mode is of the first type (M_MANUAL), a sub-step (E21) of recording observation data (D_OBSP) comprising a measurement at the observation time (T_OBSP) of a longitudinal speed (VLP) of the first motor vehicle (100) and a calculation at the observation time (T_OBSP) of a driver following time (TSCP) separating the first motor vehicle (100) from a second motor vehicle (200) preceding the first motor vehicle (100) on its traffic lane (40), the driver following time (TSCP) being calculated as a function of the data from the perception means (1) and the first determination means (2), or • otherwise, an end-of-observation sub-step (E22) comprising a calculation of a model of a personalized tracking time (MOD_TSP) from the observation data (D_OBSP) collected during the different observation times (T_OBSP), the calculation of the model comprising a calculation according to the method of least squares, - an iteration of a step (E3) of automatic application of a personalized tracking time (TSPq) between the first motor vehicle (100) and the second motor vehicle (200), the personalized tracking time (TSPq) being calculated from the personalized tracking time model (MOD_TSP) and as a function of a longitudinal speed of the first motor vehicle (100) measured by the first determination means (2) at an instant (T_AUTOq) of iteration of the application step (E3).

2. Management method according to the preceding claim, the motor vehicle further comprising a second means (1) for determining a nature of meteorological conditions from a predefined set (ENS_METEO) of meteorological conditions (M_NORMAL, M_RAIN, M_SNOW), characterized in that: - the sub-step (E21) of recording observation data (D_OBSP) further comprises a determination and recording of meteorological conditions (METEO_MP) at the observation time (T_OBSP) from among the predefined set (ENS_METEO) of meteorological conditions (M_NORMAL, M_RAIN, M_SNOW), - the end of observation sub-step (E22) includes an update of a sub-model (MOD_TSP_NO, MOD_TSP_P, MOD_TSP_NE) of the consolidated model (MOD_TSP) by meteorological condition (M_NORMAL, M_RAIN, M_SNOW) of the predefined set (ENS_METEO), and - the application step (E3) comprises a sub-step of determining, from the predefined set (ENS_METEO), the meteorological conditions (METE0_Mq) at the iteration time (T_AUTOq), and the sub-model (MOD_TSP_NO, MOD_TSP_P, MOD_TSP_NE) used to calculate the personalized tracking time (TSPq) is determined by the meteorological conditions (METE0_Mq) determined at the iteration time (T_AUTOq).

3. Management method according to one of the preceding claims, characterized in that a personalized tracking time model (MOD_TSP) is a piecewise affine function (C5) which associates a driver tracking time (TSCP) with any longitudinal speed (VLP) included in a given value interval [VLmin, VLmax], the given value interval [VLmin, VLmax] being broken down into sub-intervals (Ib I2, Ij, ...) delimiting the pieces (Sb S2, Sj) of the piecewise affine function (C5).

4. Management method according to the preceding claim, characterized in that each given sub-interval (Ij) is associated with a subset (D_OBSj) of the set of observations (D_OBS) grouping the observations made when the longitudinal speed applied by the motor vehicle (100) was within the speed range defined by the given sub-interval (Ij), and in that the origin (aj) and the slope (bj) of the piece (Sj) of the piecewise affine function delimited by the sub-interval (Ij) are calculated by applying the least squares method to the observations of the subset (D_OBSj).

5. Management method according to the preceding claim, characterized in that the sub-intervals (Ib I2, Ij,) determine speed ranges of a fixed amplitude, for example speed ranges whose amplitude is equal to 10 kilometers per hour.

6. Management method according to one of the preceding claims, characterized in that the iterations of steps E2 and / or E3 are carried out at a frequency of a computer on which the method is executed, for example at a frequency of 100 Hertz.

7. Method according to one of the preceding claims, characterized in that the method comprises a driving phase delimited by - a driving phase start time, where an engine of the motor vehicle (100) is started by means of a key or an ignition button by a driver, and - a driving phase end time, where an engine of the motor vehicle (100) is stopped by means of a key or an ignition button by a driver, in that, between the driving phase start time and the driving phase end time, a personalized tracking time model (MOD_TSP) is recorded in a volatile memory (421) of the motor vehicle, and in that at the driving phase end time, a time model custom tracking (MOD_TSP) is stored in non-volatile memory (422) of the motor vehicle.

8. Device (10) for managing the longitudinal speed of a first motor vehicle (100), the motor vehicle being equipped with a longitudinal speed control module (5), an engine (6) and a braking system (7), the device comprising hardware and / or software elements (1, 2, 3, 4, 41, 42, 43, 411, 412, 413, 414, 421, 422) implementing the method according to one of claims 1 to 7

9. 'T Computer program product comprising program code instructions recorded on a computer-readable medium for implementing the steps of the method according to any one of claims 1 to 7 when said program runs on a computer.

10. A computer-readable data storage medium on which is recorded a computer program comprising program code instructions for implementing the method according to one of claims 1 to 7.

Images