FR3132265A1 - Method and device for controlling a lateral guidance system of a vehicle - Google Patents

Abstract

The present invention relates to a method and a device for controlling a lateral guidance system (19) of a vehicle (10) traveling in a road area. For this purpose, line data (18) representing, in the form of polynomials, delimitations of the road zone are determined, these data comprising for each delimitation: a quality indicator (IC1) corresponding to the delimitation, an existence indicator (IC2) indicating a probability of existence of the delimitation polynomial, and an operability indicator (IC3) indicating whether a camera is operational. A line model (MD1) representing lines corresponding to the delimitations is generated and a confidence indicator (IC4) of a level of confidence of the line model is generated according to the aforementioned indicators (IC1, IC2, IC3) of the delimitations. The lateral guidance system (19) is controlled according to the confidence indicator (IC4). Figure for abstract: Figure 2

Description

Method and device for controlling a lateral guidance system of a vehicle

The present invention relates to methods and devices for controlling a lateral guidance system of a vehicle, for example a motor vehicle. The invention relates in particular to a semi-automatic lane change system, a system referred to in the literature by the acronym SALC (from the English “Semi Active Lateral Control”), of such a vehicle. The present invention also relates to a method and a device for determining a confidence level of a model of lines representing a road area on which such a vehicle is traveling. The present invention also relates to a method and a device for controlling a vehicle, in particular an autonomous vehicle.

Technology background

Some contemporary vehicles are equipped with functions or system(s) or driving assistance, known as ADAS (from English “Advanced Driver-Assistance System” or in French “Advanced Driving Assistance System”).

Among these systems, the semi-automatic lane change system, known as the SALC system (from English “Semi-Automatic Lane Change”), has the primary function of assisting the driver of a vehicle when the driver wishes to change taxiway. Upon detection of the activation of the indicators on one side of the vehicle to indicate its intention to change lanes from a current traffic lane to a target traffic lane on the side where the indicators were activated by the driver, the SALC system performs the lane change after carrying out a few checks, particularly on the lines it detects on the road area concerned.

These checks, however, prove insufficient to cover all life or driving situations of the vehicle, certain situations where changing lanes should be prohibited or inhibited remaining authorized by the SALC system.

Other lateral guidance functions of a vehicle are possible, for example to keep a vehicle on a current traffic lane, in particular by indicating to a driver when the trajectory of the vehicle deviates from the current traffic lane, or even by correcting automatically steers the vehicle.

Generally speaking, these lateral guidance functions are based on controls carried out from camera data (or video data), but a problem arises in that the quality of the camera data collected is not always of good quality, and can in particular be of insufficient quality when weather or visibility conditions are unfavorable or when ground markings are absent or degraded. These variations in camera data quality can make it difficult to implement a vehicle's lateral guidance function.

Summary of the present invention

One of the objects of the present invention is to solve at least one of the problems of the technological background described above.

Another object of the present invention is to improve the operation of a lateral guidance system of a vehicle, such as for example a SALC system or the like. The system which is the subject of the invention can for example be a lane crossing monitoring system, a system called by the acronym LKA (from the English “Lane Keeping Assist”), or even a lane keeping system, system called by the acronym LPA (from English “Lane Positioning Assist”).

According to a first aspect, the present invention relates to a method for controlling a lateral guidance system of a vehicle traveling in a road area, said method comprising:

- determination, from camera data received from at least one camera on board said vehicle, of line data representing in the form of polynomials the boundaries of the road zone, the line data comprising for each boundary:

● a quality indicator indicating a quality of detection of markings corresponding to the delimitation,

● an existence indicator indicating a probability of existence in the road zone of the polynomial of said boundary, and

● an operability indicator, function of visibility conditions, indicating whether said at least one camera is operational;

- generation, from line data, of a line model representative of lines corresponding to the boundaries of the road zone;

- determination, based on the quality indicator, the existence indicator and the operability indicator of the demarcations, of at least one confidence indicator representative of a confidence level of the generated line model ; And

- control of the lateral guidance system according to said at least one confidence indicator.

The control method is for example implemented by a control device to control the lateral guidance system.

Determining at least one confidence indicator makes it possible to evaluate a level of confidence in the line model generated by the lateral guidance system for a road zone in which a vehicle is traveling and thus to control said lateral guidance system according to this. trust level. It is thus possible to adapt the control of the lateral guidance system according to the confidence level which is determined for the generated line model, and thus improve the operation of said system. To do this, the confidence indicator is determined by taking into account at least the indicators previously mentioned, namely the quality indicator, the existence indicator and the operability indicator which are defined in the data of line for each delimitation of the road zone considered. It is thus possible, for example, to inhibit or block the lateral guidance system if said at least one confidence indicator does not meet a first determined condition, for example if it is not equal to a determined value (for example, the value '1'). In this way, if the confidence level determined for the line model is not sufficient, the lateral guidance system can be inhibited (or blocked).

According to a particular embodiment, said at least one confidence indicator is a confidence indicator representing a confidence level for at least two lines in the line model.

According to a particular embodiment, said at least one confidence indicator comprises two confidence indicators representing respective confidence levels of two lines of the line model, located on either side of the vehicle in the road zone.

According to a particular embodiment, if at least one said confidence indicator indicates a confidence level not satisfying a first condition, then the control of the lateral guidance system comprises triggering at least one control action.

According to a particular embodiment, said at least one control action comprises an inhibition (or blocking) of the lateral guidance system.

According to a particular embodiment, the lateral guidance system is inhibited if at least one confidence indicator is lower than an ICL threshold value for at least a first duration.

According to a particular embodiment, after the inhibition of the lateral guidance system, the control of the lateral guidance system comprises a reactivation of the lateral guidance system if said at least confidence indicator becomes greater than the ICL threshold value for at least one second duration.

According to a particular embodiment, if for at least one delimitation of the road zone, at least one of the following conditions is not met, then said at least one confidence indicator does not satisfy the first condition:

- the quality indicator indicates a detection quality greater than a first threshold value;

- the existence indicator indicates a probability of existence greater than a second threshold value; And

- the operability indicator indicates that said at least one camera is operational.

According to a particular embodiment, the determined line data further comprises, for each delimitation of the road zone, a marking type indicator indicating a type of marking corresponding to said delimitation,

in which said at least confidence indicator is also determined as a function of the boundary marking type indicator. For example, if for at least one demarcation of the road zone, the following condition is not met, then said at least one confidence indicator does not satisfy the first condition: the marking type indicator indicates that the demarcation corresponds to a predetermined type of marking.

According to a particular embodiment, the determined line data further comprise, for each delimitation of the road zone, a validity longitudinal distance indicator indicating a longitudinal distance, function of a current speed of the vehicle, over which the polynomial of the delimitation is considered valid, in which said at least confidence indicator is also determined as a function of the longitudinal distance indicator of validity of the delimitations. For example, if for at least one delimitation of the road zone, the following condition is not met, then said at least one confidence indicator does not satisfy the first condition: the validity longitudinal distance indicator indicates a distance longitudinal of the polynomial which is less than a third threshold value.

According to a particular embodiment, the method comprises:

- determination, from the polynomial of each delimitation, of an edge position variance of the corresponding line in the line model;

in which if, for at least one delimitation of the road zone, the following condition is not met, then said at least one confidence indicator does not satisfy the first condition: the line edge position variance is lower or equal to a fourth threshold value.

According to a particular embodiment, the method comprises:

- determination, from the line model, of a proportionality factor between a yaw speed of the vehicle and a steering angle of the vehicle as a function of a current speed of the vehicle;

in which if the proportionality factor exceeds a fifth threshold value, then said at least one confidence indicator does not satisfy the first condition.

According to a second aspect, the present invention relates to a lateral guidance control device, the device comprising a memory associated with a processor configured for implementing the steps of the control method according to the first aspect of the present invention.

Note that the different embodiments mentioned above in relation to the control method of the invention as well as the associated advantages apply analogously to the control device of the invention.

According to a third aspect, the present invention relates to a vehicle, for example of the automobile type, comprising a device as defined above according to the second aspect of the present invention.

According to a fourth aspect, the present invention relates to a computer program which comprises instructions adapted for the execution of the steps of the control method according to the first aspect of the present invention, in particular when the computer program is executed by at minus a processor. In other words, the different stages of the control process are determined by computer program instructions. This computer program is configured to be implemented in a control device as defined above, or more generally in a computer.

Such a computer program can use any programming language, and be in the form of a source code, an object code, or an intermediate code between a source code and an object code, such as in partially compiled form, or in any other desirable form.

According to a fifth aspect, the present invention relates to a recording medium (or information medium), readable by a computer (or a processor), on which is recorded a computer program comprising instructions for the execution of the steps of the control method according to the first aspect of the present invention.

On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium may comprise a storage means, such as a ROM memory, a CD-ROM or a ROM memory of the microelectronic circuit type, or even a magnetic recording means or a hard disk.

On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or terrestrial radio or by self-directed laser beam or by other ways. The computer program according to the present invention can in particular be downloaded onto an Internet type network.

Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in executing the method in question.

Brief description of the figures

Other characteristics and advantages of the present invention will emerge from the description of the particular and non-limiting examples of embodiment of the present invention below, with reference to the appended Figures 1 to 5, in which:

schematically illustrates an environment of a vehicle, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates the vehicle of the , comprising a control device and a lateral guidance system, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a model of lines representing a road zone, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a control device configured to control a lateral guidance system of the vehicle shown in Figures 1 and 2, according to a particular and non-limiting embodiment of the present invention;

illustrates a diagram of different stages of a method of controlling a lateral guidance system of the vehicle of Figures 1-2, according to a particular and non-limiting embodiment of the present invention.

Description of the implementation examples

A method and a device for controlling a lateral guidance system of a vehicle will now be described in what follows with reference jointly to Figures 1-5. Unless otherwise indicated, elements common or similar to several figures bear the same reference signs and have identical or similar characteristics, so that these common elements are generally not described again for the sake of simplicity.

The terms “first(s)” (or first(s)), “second(s)”, etc.) are used in this document by arbitrary convention to help identify and distinguish different elements (such as operations, threshold values, etc.) implemented in the embodiments described below.

As previously indicated, the invention relates in particular to a method for controlling a lateral guidance system of a vehicle, such as an automobile or other type vehicle, traveling in a road area. This method is for example implemented by a control device which can be external or form part of the lateral guidance system of the vehicle.

According to a particular and non-limiting example of embodiment of the present invention, this method comprises a determination of line data representing in the form of polynomials the boundaries of the road zone. These line data are for example determined from camera data (or video data, or image data) received from at least one camera on board the vehicle. Such line data may in particular be (or be included in) the aforementioned camera data, or be determined by processing applied to the camera data.

The line data thus determined comprise, for each delimitation of the road zone, indicators, namely: a quality indicator indicating a quality of detection of markings corresponding to the delimitation, an existence indicator indicating a probability of existence in the road zone of the polynomial of said delimitation, and an operability indicator, a function of current visibility conditions, indicating whether said at least one camera is operational. The control device generates, from the line data, a line model representative of lines corresponding to the boundaries of the road area. At least one confidence indicator (one or more confidence indicators) is further determined based on the quality indicator, the existence indicator and the operability indicator of the demarcations of the road area, said at least one confidence indicator being representative of a confidence level of the generated line model. The lateral guidance system is controlled based on said at least one confidence indicator.

For example, the control device can determine a confidence indicator representing a confidence level for at least two lines in the line model, for example for two lines located on either side of the vehicle traveling on the road area ( for example for left and right lines). Alternatively, the control device can determine two (or at least two) confidence indicators representing respective confidence levels of two lines of the line model, for example for lines located on either side of the vehicle in the zone route (for example left and right lines).

Thus, if at least one such confidence indicator indicates a level of confidence not satisfying a first determined condition, then the control of the lateral guidance system can include triggering at least one control action, such as for example inhibition (or blocking) of the lateral guidance system, which can thus make it possible to block a lateral guidance (or driving assistance) function of the lateral guidance system if the confidence level of the line model is not sufficient . In particular, the control device determines for example that a confidence indicator does not satisfy the first condition if, for at least one delimitation of the road zone, at least one of the quality indicator, the indicator of existence and the operability indicator does not satisfy a respective condition.

There schematically illustrates an environment 1 in which a vehicle 10 operates, according to a particular and non-limiting embodiment of the present invention.

There illustrates a vehicle 10, for example a motor vehicle, traveling on a road zone 2, that is to say a portion of the road in the environment 1. According to other examples, the vehicle 10 corresponds to a coach, a bus, a truck, a utility vehicle or a motorcycle, that is to say a vehicle of the motorized land vehicle type.

Vehicle 10 corresponds to a vehicle circulating under the full supervision of a driver or circulating in an autonomous or semi-autonomous mode. The vehicle 10 can circulate according to a level of autonomy equal to 0 or according to a level of autonomy ranging from 1 to 5 for example, according to the scale defined by the American federal agency which has established 5 levels of autonomy ranging from 1 to 5, level 0 corresponding to a vehicle with no autonomy, whose driving is under the total supervision of the driver, level 1 corresponding to a vehicle with a minimum level of autonomy, whose driving is under the supervision of the driver with minimal assistance from an ADAS system, and level 5 corresponding to a completely autonomous vehicle.

The 5 levels of autonomy in the classification of the federal agency responsible for road safety are:

- level 0: no automation, the vehicle driver has full control over the main functions of the vehicle (engine, accelerator, steering, brakes);

- level 1: driver assistance, automation is active for certain vehicle functions, the driver maintaining overall control over vehicle driving; cruise control is part of this level, like other aids such as ABS (anti-lock braking system) or ESP (programmed electro-stabilizer);

- level 2: automation of combined functions, the control of at least two main functions is combined in the automation to replace the driver in certain situations; for example, adaptive cruise control combined with lane centering allows a vehicle to be classified level 2, as does automatic parking assistance;

- level 3: limited autonomous driving, the driver can cede complete control of the vehicle to the automated system which will then be in charge of critical safety functions; however, autonomous driving can only take place in certain specific environmental and traffic conditions (only on motorways for example);

- level 4: complete autonomous driving under conditions, the vehicle is designed to ensure all critical safety functions alone over a complete journey; the driver provides a destination or navigation instructions but is not required to make himself available to regain control of the vehicle;

- level 5: completely autonomous driving without driver assistance in all circumstances.

According to a particular embodiment, the vehicle 10 circulates in a semi-autonomous or autonomous mode, that is to say with a level of autonomy greater than or equal to 2 according to the classification above.

According to the example of the , the vehicle 10 travels on a zone (or portion) of road 2 comprising a plurality of lanes, namely a current traffic lane 20 on which the vehicle 10 travels and an adjacent traffic lane 22 which extends along the current traffic lane 20. The configuration of road zone 2 in particular in terms of the number and shape of the lanes may vary depending on the case.

The configuration of the road zone 2 considered may depend in particular on the traffic rules in force for the geographical area in which the road zone 2 considered is located. In this example, vehicles travel on the right, as in France. The invention is, however, not limited to such an example and extends to all road configurations, including those where vehicles travel on the left.

In the example shown in , lanes 20 and 22 constitute traffic lanes intended for the circulation of vehicles, including vehicle 10. Other types of lane are, however, possible. At least one of the lanes of road zone 2 can thus constitute an emergency stopping lane (denoted BAU) provided so that a vehicle can stop on the side of the road in the event of an emergency ( for example a breakdown) or the shoulder of the roadway.

In the example considered, each of the paths 20 and 22 is materialized or delimited on either side by lateral delimitations (or also hereinafter “delimitations”) 32, 34 and 34 which correspond for example to marking lines on the ground 20. Thus, the current traffic lane 20 is delimited on both sides (right and left) by the boundaries 30 and 32 while the adjacent traffic lane is delimited on both sides (left and right ) by the boundaries 32 and 34. The central boundary 32 is therefore common to the traffic lanes 20 and 22. In this example, the boundaries 30, 32 and 34 are formed by markings on the ground. More precisely, the boundaries 30 and 34 are formed by continuous marking lines while the central boundary 32 is formed by a discontinuous marking line. Other types of delimitation are however possible, such as in particular delimitations formed by safety barriers (or barriers).

The number and type of boundaries defining the traffic lanes can be adapted as appropriate. In the example shown in , only two lanes are present in the road zone 2. Alternatively, a plurality of lanes can be located to the left and/or right of the vehicle 10 traveling on the current traffic lane 20. A plurality of lane boundaries, defining the other lanes are then positioned to the left and/or right of the vehicle 10 traveling on the current traffic lane 20. Implementations are also possible in which the road zone 2 considered only includes a single traffic lane (namely the current traffic lane on which the vehicle 10 is traveling).

Ground marking lines are also called horizontal markings and correspond to a set of 30-34 lines drawn on the ground. The ground marking lines 30-34 can be of several types, for example edge lines or center lines, with different characteristics. The ground marking lines can thus be of the continuous line, discontinuous line or mixed line type (comprising a continuous line and a discontinuous line parallel to the continuous line). A dashed line may also have different characteristics, with line spacing lengths varying from one dashed line type to another and/or line length varying from one dashed line type to another.

The dashed line 32 marks in this example the separation between the current traffic lane 20 and the adjacent traffic lane 22. This dashed line 32 is formed of lines of a determined length (for example equal to 3 m) spaced from each other. others with a spacing of a determined length (for example equal to 10 m). Such a broken line 32 is representative of a line which can be crossed by the vehicle 10, that is to say that a change of lane from lane 20 to lane 22, and vice versa, is authorized.

As shown in , the vehicle 10 has a lateral guidance system 19 configured to control the lateral position of (that is to say to laterally guide the) vehicle 10 in its current lane 20. This guidance system constitutes a system of driving assistance, known as ADAS (from the English “Advanced Driver-Assistance System” or in French “Advanced Driving Assistance System”). Various types of driver assistance systems are possible. The lateral guidance system 19 can for example be an LKA lane crossing monitoring system or an LPA lane keeping system.

The lateral guidance system 19 implements at least one lateral guidance function of the vehicle 10, the nature of this or these functions being able to vary depending on the case. The lateral guidance system 19 can for example be a semi-automatic lane change system, called SALC system (from the English “Semi-Automatic Lane Change”). A SALC system is based in particular on the detection and recognition of the marking lines on the ground to authorize or not the change of lane from a current traffic lane to a traffic lane adjacent to this current traffic lane, and when the change is authorized, to control the maneuver allowing the vehicle 10 to change lanes. The lateral guidance system 19 can also be configured to keep the vehicle 10 on its current traffic lane 20, in particular by indicating to a user when the trajectory of the vehicle 10 deviates from the current traffic lane 20, or even by automatically correcting the direction (or lateral position) of the vehicle 10.

The vehicle 10 further carries a control device 14 coupled to the lateral guidance system 19. The control device 14 is configured to control the lateral guidance system 19 by implementing a control process as described below. According to a particular example, the control device 14 is external to the lateral guidance system 19. Alternatively, the control device 14 is included in (or forms part of) the lateral guidance system 19.

As illustrated in , the vehicle 10 can further comprise a certain number of sensors, in particular one or more on-board cameras 12, which are coupled to the control device 14. It is assumed in this example that the vehicle 10 is equipped in particular with a front camera 12 configured to inspect the road zone 2 in which the vehicle 10 is traveling. The control device 14 is coupled to the camera 12, in particular to receive camera data (or video data, or image data) 16 generated by the camera 12, this camera data representing the road zone 2 (for example a front and/or rear portion of this zone) in which the vehicle 10 is traveling. The camera data 16 acquired by the camera 12 includes images making it possible to detect the boundaries of road zone 2, in particular road markings in the example considered here. Image processing can be applied, for example by the camera 12 or by the control device 14, to the images provided by the camera 12 to determine the presence of lines on the ground (or markings). An example of image processing to detect lines on the ground is for example described in document WO2017194890A1.

According to a particular example, the vehicle 10 also carries one or more of the following sensors (not shown) which are coupled to the control device 14:

- one or more millimeter wave radars arranged on the vehicle 10, for example at the front, at the rear, on each front/rear corner of the vehicle; each radar is adapted to emit electromagnetic waves and to receive the echoes of these waves returned by one or more objects, with the aim of detecting obstacles or other objects and their distances from the vehicle 10; and or

- one or more LIDAR(s) (from the English “Light Detection And Ranging”, or “Detection and estimation of the distance by light” in French), a LIDAR sensor corresponding to an optoelectronic system composed of a transmitter device laser, a receiving device comprising a light collector (to collect the part of the light radiation emitted by the transmitter and reflected by any object located in the path of the light rays emitted by the transmitter) and a photodetector which transforms light collected as an electrical signal; a LIDAR sensor thus makes it possible to detect the presence of objects located in the emitted light beam and to measure the distance between the sensor and each detected object.

The control device 14 is configured to implement a control process to control the lateral guidance system 19 (also called hereinafter “guidance system 14” or “system 14”), or more precisely to control a function of lateral guidance capable of being implemented by the lateral guidance system 14 to laterally guide the vehicle 10. It is assumed in this example that the control device 14 and the lateral guidance system 19 are on board the vehicle 10 although variants are possible where at least one of these elements is external to the vehicle 10 and can cooperate with the vehicle 10 to control (or guide) it laterally. As indicated above, the lateral guidance system 19 is in particular capable of implementing a lateral guidance function of the vehicle 10, this function being able to be activated or inhibited by the control device 14 selectively depending on the case considered. . The control device 14 can for example take the form of (or include a) calculator, or a combination of calculators. An example of implementation of the control device 14 is described later.

In a first operation, the control device 14 determines line data 18 representing in the form of polynomials (or in the form of polynomial coefficients) the boundaries of the road zone 2, namely the boundaries 30, 32 and 34 in this example . These line data 18 can be determined by the control device 14 from camera data (or video data, or image data) 16 received from one or more sensors, in particular from one or more cameras on board the vehicle 10, such as camera 12 in this example ( ). In a first example, the line data 18 determined by the control device 14 is, or includes, the camera data 16 received.

The control device 14 can for example receive this camera data 16 via one or more communication buses of the on-board system of the vehicle 10, for example a communication bus of the CAN data bus type (from the English "Controller Area Network" or in French “Réseau de controllers”), CAN FD (from the English “Controller Area Network Flexible Data-Rate” or in French “Réseau de controllers à rate flexible data”), FlexRay (according to the ISO 17458 standard), Ethernet (according to the ISO/IEC 802-3 standard) or LIN (from the English “Local Interconnect Network”, or in French “Réseau interconnectée local”).

According to a second example, the control device 14 determines the line data 18 by appropriate processing carried out on the camera data 16 transmitted by the camera 12.

As already indicated, the line data 18 determined (or obtained) by the control device 14 during the first operation define in this example the boundaries 30, 32 and 34 of the road zone 2 in the form of polynomials (or of polynomial coefficient). A respective polynomial (of degree 3) can thus define each boundary 30-34, for example in the following form: Dy = A3 * Dx ³ + A2 * Dx ² + A1 * Dx + A0 where Dy designates a lateral position of a corresponding delimitation with respect to the vehicle 10, Dx designates a longitudinal position of this delimitation with respect to the vehicle 10 and A0-A3 are polynomial coefficients.

The coefficient A0 represents for example a distance between the center of the vehicle 10 and each boundary considered. The coefficient A1 represents for example an angle between the trajectory of the vehicle 10 and a tangent to the traffic lane (the heading). The coefficient A2 represents for example a radius of curvature and the coefficient A3 represents for example a derivative of this radius of curvature. The form of the polynomials can be adapted depending on the case.

Furthermore, the line data 18 determined (or obtained) by the control device 14 during the first operation may include other information (or attributes), in particular the following indicators for each delimitation 30-34 of the zone of route 2: a quality indicator IC1, an existence indicator IC2 and an operability indicator IC3. In other words, each lane demarcation identified in the line data 18 is associated respectively with a quality indicator IC1, an existence indicator IC2 and an operability indicator IC3.

Similarly to the aforementioned polynomials Dy, the indicators IC1, IC2 and IC3 can be determined for each delimitation from the camera data 16 received from the camera 12.

More precisely, the quality indicator IC1 indicates a quality of detection of markings corresponding to the corresponding delimitation. The indicator IC1 is for example representative of the quality of detection of a marking line defining the edge of a lane of the road zone 2. This indicator can for example present one value among a plurality of predefined values (such as “low quality”, “medium quality”, “high quality”) representing quality levels different from the corresponding delimitation detected in road zone 2. The quality indicator IC1 must for example be greater than a threshold for the lateral guidance function of the guidance system 14 is authorized.

The existence indicator IC2 indicates a probability of existence in road zone 2 of the polynomial Dy of the corresponding boundary. This indicator IC2 indicates a probability that the polynomial Dy of the corresponding delimitation is valid (or applicable) over a given longitudinal distance (according to x) of road zone 2. This probability can for example be represented by a percentage value fixed between 0% and 100%. Such a probability must for example be greater than a threshold for the lateral guidance function of the guidance system 14 to be authorized.

The operability indicator IC3 indicates whether the camera(s) with which the control device 14 is coupled, namely the camera 12 in this example ( ), are operational. This operability indicator IC3 is for example a function of visibility conditions, in which the camera 12 has acquired the camera data 16.

As already indicated, the line data 18 can be determined (or obtained) by the control device 14 from camera data (or video data) 16 generated by the camera 12. These camera data 12, which make it possible to determine the topology of road zone 2, can pose a problem to the extent that their quality can vary greatly depending on their acquisition conditions, in particular depending on visibility conditions or weather conditions, or even the state of the road markings ( local absences of paint on the roadway, unexpected marks on the track, etc.). This operability indicator IC3 must for example indicate that the camera 12 is operational so that the lateral guidance function of the guidance system 19 is authorized.

The control device 14 can also receive object data and/or dynamic data (not shown). The object data are for example received from radar(s) and/or LIDAR(s) on board the vehicle 10, these data being representative of objects likely to be detected on the roadway or near the roadway of the zone of road 2. These object data make it possible in particular to identify static objects (sliders, panels, etc.) and/or dynamic objects (other vehicles for example which can travel in the same direction of traffic as the vehicle 10 or a different meaning). The dynamic data are for example received from an electronic trajectory control system (also called ESP system for “Electronic Stability Program” in English) which is on board the vehicle 10.

In a second operation ( ), the control device 14 generates, from the line data 18 (and in particular from the polynomials Dy of the road boundaries), a line model MD1 representative of lines corresponding to the boundaries of the road zone 2. This model MD1 makes it possible to model in the form of lines the boundaries 30, 32 and 34 (or at least part of them) of the road zone 2 in which the vehicle 10 is traveling. The line model MD1 can be generated so as to model in line form each delimitation of road zone 2 or at least one delimitation among those identified in the line data 18. represents a particular example of line model MD1 comprising two lines representing the left and right lateral boundaries 30, 32 of the current traffic lane 20. The line model MD1 can thus represent the topology of the road zone 2 in which the vehicle 10.

The operation of generating this line model MD1 may include in particular the recognition and classification of the boundaries defined by each polynomial Dy of the line data 18, for example by means of an automatic learning method (from the English " machine learning"). To do this, the control device 14 feeds for example a neural network, for example a neural network of the convolutional neural network type, also called a convolutional neural network or convolutional neural network and denoted CNN or ConvNet (from the English “Convolutional Neural Networks”), with the line data 18 including the polynomials Dy, and possibly other information included in the line data 18 such as the indicators IC1, IC2 and IC3.

In a third operation, the control device 14 determines, as a function of the quality indicator IC1, the existence indicator IC2 and the operability indicator IC3 of each delimitation of the road zone 2 (or at least for each delimitation identified in the line model MD1), at least one confidence indicator IC4 representative of a confidence level of the line model MD1 generated during the second operation. To do this, the control device 14 analyzes the aforementioned indicators IC1, IC2 and IC3 obtained in (or defined in) the line data 18. As described below, the manner in which the indicators IC1, IC2 and IC3 are analyzed and taken into account to determine the IC4 confidence indicator(s) can be adapted as appropriate.

According to a first example, the control device 14 generates a confidence indicator IC4 representing a level of confidence for at least two lines in the line model MD1, for example for two lines corresponding respectively to the lateral boundaries 30 and 32 of the track. current circulation 20. Thus, this confidence indicator IC4 represents a level of confidence for collectively the two lines corresponding to the two delimitations 30 and 32 ( ).

According to a second example, the control device 14 generates two (or at least two) confidence indicators IC4 representing respective confidence levels of two (or at least two) lines of the line model MD1, for example lines located on either side and on the other side of the vehicle 10 in the road zone 2. A respective confidence indicator IC4 can for example be generated for each line present in the line model MD1.

In a fourth operation, the guidance system 19 is controlled by the control device 14 as a function of the confidence indicator(s) IC4 determined during the third operation, that is to say as a function of the confidence level determined for the MD1 line model. In other words, a lateral guidance function capable of being implemented by the guidance system 19 is controlled according to the confidence indicator(s) IC4. The manner in which the control device 14 controls the guidance system 19 (or more precisely its lateral guidance function) can be adapted depending on the case.

For example, if at least one said confidence indicator IC4 indicates a confidence level not satisfying a first condition, then the control of the lateral guidance system 19 includes triggering at least one control action. This said at least one control action may include for example an inhibition (or blocking) of the lateral guidance system 19, or at least of the lateral guidance function considered. Thus, if for example a confidence indicator IC4 generated by the lateral guidance system 19 does not satisfy the first condition, then the lateral guidance system 19 can be inhibited or deactivated by the control device 14 to the extent that one considers that the level of confidence in the MD1 line model is insufficient to allow secure lateral guidance of the vehicle 10.

The control device 14 sets for example the confidence indicator IC4 at a first value (for example the value "1") if the first condition is met and at a second value (for example the value "0") if the first condition is not met. If the confidence indicator IC4 is at the second value, this means that the level of confidence in the line model MD1 is insufficient, as a result of which the control device 14 triggers said at least one control action.

As a non-limiting example, it is subsequently assumed for simplicity that the control device 14 determines a single confidence indicator IC4 representing a level of confidence for collectively the two lines corresponding to the two delimitations 30 and 32 ( ), although variations are possible as already indicated. It is further assumed subsequently that the control action triggered by the control device 14 when the confidence indicator IC4 does not satisfy the first condition is (or includes) the inhibition of the lateral guidance system 14, although other types of control action are possible to adapt the operation of the lateral guidance system 19 according to the confidence level of the line model MD1.

As described below, the nature of the first condition may vary depending on the case. For example, the lateral guidance system 14 is inhibited if the confidence indicator IC4 is less than a threshold value ICL. According to a particular example, the system 14 is inhibited if the first condition is not satisfied for at least a first determined duration. It is thus possible to avoid repeated and untimely blocking of the guidance system 19, particularly when the confidence level varies greatly and does not satisfy the first condition for short periods of time. If the level of confidence only remains low for limited periods of time, it is then possible to trust the line model MD1 to the extent that the guidance system 19 will be able to compensate for the uncertainties which temporarily weigh on the line model MD1 , possibly using additional information (such as the aforementioned object data and/or dynamic data).

According to a particular example, after the inhibition of the lateral guidance system 19, the control of the lateral guidance system 19 comprises a reactivation of said system 19 if the confidence indicator IC1 becomes greater than the threshold value ICL for at least a second duration determined. Thus, if the control device 14 detects a sufficient level of confidence for the line model MD1 for at least this second duration, it is considered that the lateral guidance system 19 can again be used with complete confidence, so that it this is reactivated.

Such a control process therefore makes it possible to reliably and efficiently control the lateral guidance system 19 whatever the current acquisition conditions or the quality of the camera data 16 which are acquired by the camera 12. A lateral guidance function of the guidance system 19 is only implemented if the level of confidence in the generated MD1 line model is sufficient, which makes it possible to improve the lateral guidance function and therefore to secure the vehicle 10 and its passengers. The control process can make it possible in particular to inhibit a semi-automatic change of lane to another lane by the lateral guidance system 14 (in the case of a SALC system).

As already indicated, the nature of the first aforementioned condition can be adapted depending on the case. According to a particular example, if for at least one delimitation of road zone 2 (or more precisely for at least one delimitation identified in the line model MD1), at least one of the following conditions (or sub-conditions) n is not met, then the confidence indicator IC4 is considered not to satisfy the first condition:

- the quality indicator IC1 indicates a detection quality greater than a first threshold value VS1;

- the existence indicator IC2 indicates a probability of existence greater than a second threshold value VS2; And

- the operability indicator IC3 indicates that the camera 12 is operational.

In other words, as long as the three sub-conditions above are satisfied for each delimitation identified in the line model MD1, then the confidence indicator IC4 is considered to satisfy the first condition and the lateral guidance system 19 can be maintained in the active state by the control device 14.

Note that additional sub-conditions may be taken into account to determine whether the first condition is satisfied or not. According to a particular example, the determined line data 18 further comprises, for each delimitation of the road zone 2 (or at least for each delimitation identified in the line model MD1), a marking type indicator IC5 indicating a type marking corresponding to said boundary. During the third operation, the confidence indicator IC4 is also determined based on the marking type indicator IC5 of the boundaries.

For example, if for at least one demarcation of road zone 2 the following condition is not met, then the confidence indicator IC4 is considered not to satisfy the first condition: the marking type indicator IC5 indicates that the delimitation corresponds to a first type of marking (or a predetermined type of marking). Thus, if for example a delimitation of the road zone 2 is detected as being of the safety barrier type (or slide) or of an unknown type, then the control device 14 inhibits the lateral guidance system 19 because the risk is judged too pupil. On the other hand, the lateral guidance system 19 can be maintained in the active state if, for example, the boundaries detected in the line model MD1 are continuous or discontinuous lines (low risk).

According to a particular example, the line data 18 determined during the first operation further comprises, for each delimitation of the road zone 2 (or at least for each delimitation identified in the line model MD1), an indicator IC6 of longitudinal distance of validity indicating a longitudinal distance (along x) over which the polynomial Dy of said delimitation is considered valid. This validity longitudinal distance indicator IC6 (also called “validity indicator”) is for example a function of a current speed of the vehicle 10.

During the third operation, the control device 14 can determine the confidence indicator IC4 also as a function of the longitudinal distance indicator IC6 of validity of the demarcations. For example, if for at least one delimitation of road zone 2 (or at least for at least one delimitation identified in the line model MD1), the following condition is not met, then the confidence indicator IC4 does not does not satisfy the first condition: the longitudinal validity distance indicator IC6 indicates a longitudinal validity distance, of the polynomial Dy of the delimitation, which is less than a third threshold value. In other words, if the indicator IC6 indicates a longitudinal distance of validity of the polynomial Dy for a delimitation of the road zone 2 which is less than a third threshold value, then the confidence indicator IC4 is considered not to satisfy the first condition, which triggers the inhibition of the lateral guidance system 14 by the control device 14 during the fourth operation. This third threshold value is for example equal to the current speed of the vehicle 10 multiplied by a horizon time chosen as a setting for the control device 14. For example, we can choose a horizon time of 1 .1 seconds.

According to a particular example, the particular examples described above are combined to control the guidance system 19 taking into account both the marking type indicator IC5 and the longitudinal distance validity indicator IC6 as described below. -before for each of these indicators.

In addition, additional information can be taken into account by the control device 14 to control the lateral guidance system 19 during the fourth operation, in order to further improve its operation and thus further secure the vehicle 10 and its passengers. . In particular, an edge position variance and/or a proportionality factor can be taken into account as described below.

According to a particular example, during the control process, the control device 14 determines, from the polynomial Dy of each delimitation of the road zone 2 (or at least each delimitation identified in the line model MD1), a variance edge position of the corresponding line in the MD1 line model. For example, if for at least one delimitation of road zone 2, the following condition is not met, then the confidence indicator IC4 does not satisfy the first condition: the line edge position variance is less than a fourth threshold value VS4. Thus, if the line edge position variance corresponding to at least one delimitation is less than a fourth threshold value VS4, then the confidence indicator IC4 is considered not to meet the first condition, in response to which the monitoring device control 14 inhibits the lateral guidance system 19.

According to a particular example, during the control process, the control device 14 determines, from the line model MD1, a proportionality factor (yes ratio) between a yaw speed of the vehicle 10 and a steering angle of the vehicle 10, and this as a function of a (or for a) given speed of the vehicle 10. The yaw speed defines a lateral acceleration of the vehicle 10 (expressed in rad.s ^-1 ). The steering angle (also known as “steering wheel angle”) defines a steering angle applied to the wheels of the vehicle 10. If the proportionality factor exceeds a fifth threshold value VS5, then the confidence indicator IC4 is considered not to fulfill the first condition, in response to which the control device 14 inhibits the lateral guidance system 14.

There schematically illustrates a control device 14 configured to control a lateral guidance system 19, such as a SALC system or other, according to a particular and non-limiting embodiment of the present invention. The control device 14 corresponds for example to a device on board the vehicle 10, for example a computer. As already indicated, the control device 14 can be separate from, or form part of, the lateral guidance system 19.

The control device 14 is for example configured for the implementation of the operations previously described with reference to Figures 1-3 and/or the steps of the method described below with regard to the . Examples of such a control device 14 include, without being limited to, on-board electronic equipment such as an on-board computer of a vehicle, an electronic computer such as an ECU (“Electronic Control Unit”), a smartphone, a tablet, a laptop. The elements of the control device 14, individually or in combination, can be integrated into a single integrated circuit, into several integrated circuits, and/or into discrete components. The control device 14 can be produced in the form of electronic circuits or software (or computer) modules or even a combination of electronic circuits and software modules.

The control device 14 comprises one (or more) processor(s) 40 configured to execute instructions for carrying out the steps of the method (or the control process) and/or for executing the instructions of the software(s) embedded in the control device 14. The processor 40 may include integrated memory, an input/output interface, and various circuits known to those skilled in the art. The control device 14 further comprises at least one memory 41 corresponding for example to a volatile and/or non-volatile memory and/or comprises a memory storage device which may comprise volatile and/or non-volatile memory, such as EEPROM , ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

The computer code of the embedded software(s) comprising the instructions to be loaded and executed by the processor is for example stored on the memory 41. The memory 41 can constitute an information medium according to a particular embodiment in that it comprises a computer program comprising instructions for carrying out the steps of the method (or control process) of the invention.

According to different particular and non-limiting examples of embodiment, the control device 14 is coupled in communication with other similar devices or systems and/or with communication devices, for example a TCU (from the English “Telematic Control Unit”). or in French “Telematic Control Unit”), for example via a communications bus or through dedicated input/output ports.

According to a particular and non-limiting exemplary embodiment, the control device 14 comprises a block 42 of interface elements for communicating with external devices, for example a remote server or the "cloud", or the vehicle 10 when the device control 14 corresponds to a smartphone or a tablet for example. The interface elements of block 42 include one or more of the following interfaces:

- RF radio frequency interface, for example of the Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or of the Bluetooth® type (according to IEEE 802.15.1), in the band frequency at 2.4 GHz, or Sigfox type using UBN radio technology (from English Ultra Narrow Band, in French ultra narrow band), or LoRa in the 868 MHz frequency band, LTE (from English “ Long-Term Evolution” or in French “Long-Term Evolution”), LTE-Advanced (or in French LTE-advanced);

- USB interface (from the English “Universal Serial Bus” or “Bus Universel en Série” in French);

- HDMI interface (from the English “High Definition Multimedia Interface”, or “Interface Multimedia Haute Definition” in French).

According to another particular and non-limiting example of embodiment, the control device 14 comprises a communication interface 43 which makes it possible to establish communication with other devices (such as other computers of the on-board system or on-board sensors) via a communication channel 45. The communication interface 45 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 45. The communication interface 43 corresponds for example to a wired network type CAN (from the English “Controller Area Network” or in French “Réseau de controlleres”), CAN FD (from the English “Controller Area Network Flexible Data-Rate” or in French “Network of data rate controllers”) flexible"), FlexRay (standardized by the ISO 17458 standard), Ethernet (standardized by the ISO/IEC 802-3 standard) or LIN (from the English "Local Interconnect Network", or in French "Local Interconnected Network").

The control device 14 is for example coupled to the lateral guidance system 19 by means of the block 42 of interface elements or the communication interface 43.

According to a particular and non-limiting embodiment, the control device 14 can provide output signals to one or more external devices, such as a display screen, touchscreen or not, one or more speakers and/or other devices (projection system) via respective output interfaces. According to a variant, one or the other of the external devices is integrated into the control device 14.

There illustrates a diagram of the different stages of a method of controlling a lateral guidance system 19 as previously described. This lateral guidance system 19 is for example a semi-automatic lane change system, called the SALC system, of a vehicle 10 traveling on a current lane 20 of a road (or road zone) 20, according to a particular and non-limiting embodiment of the present invention. The method is for example implemented by the control device 14 previously described, this device being able to be on board the vehicle 10.

In a first step 51, line data 18 are determined, these representing in the form of polynomials the boundaries of the road zone 2 ( ). These line data 18 are for example determined (or obtained) from camera data 16 received from at least one on-board camera 12 in the vehicle 10. These line data 18 can include for each delimitation of the road zone 2:

- a quality indicator IC1 indicating a quality of detection of markings corresponding to the delimitation,

- an existence indicator IC2 indicating a probability of existence in road zone 2 of the polynomial of said boundary, and

- an operability indicator IC3 indicating whether said at least one camera is operational (this indicator IC3 is for example a function of visibility conditions in which the camera data 16 are acquired).

In a second step 52, a line model MD1 is generated from the line data 18, this line model MD1 being representative of lines corresponding to the delimitations of road zone 2.

In a third step 53, at least one confidence indicator IC4 is determined as a function of the quality indicator IC1, the existence indicator IC2 and the operability indicator IC3 of the delimitations, this at least one indicator of confidence IC4 being representative of a confidence level of the line model MD1 generated in step 52.

In a fourth step 54, the lateral guidance system 19 is controlled according to said at least one confidence indicator IC4 determined in step 53.

According to alternative embodiments, the variants and examples of the operations described above in relation to Figures 1-3 apply to the stages of the process for controlling the .

A person skilled in the art will understand that the embodiments and variants described above constitute only non-limiting examples of implementation of the invention. In particular, those skilled in the art may consider any adaptation or combination of the embodiments and variants described above, in order to meet a very specific need.

The present invention is therefore not limited to the exemplary embodiments described above but extends in particular to a control method which would include secondary steps without thereby departing from the scope of the present invention. The same would apply to a device configured to implement such a process.

The present invention also relates to a lateral guidance system 19 comprising the control device 14 of the .

The present invention also relates to a vehicle, for example an automobile or more generally an autonomous vehicle with a land engine, comprising the device 14 for controlling the , and possibly also the lateral guidance system 19 above.

Claims (10)

Method for controlling a lateral guidance system (19) of a vehicle (10) traveling in a road zone (2), said method comprising:
- determination (51), from camera data (16) received from at least one camera (12) on board said vehicle, of line data (18) representing in the form of polynomials delimitations (30, 32, 34) of the road zone, the line data including for each demarcation:
● a quality indicator (IC1) indicating a quality of detection of markings corresponding to the delimitation,
● an existence indicator (IC2) indicating a probability of existence in the road zone (2) of the polynomial of said boundary, and
● an operability indicator (IC3), function of visibility conditions, indicating whether said at least one camera is operational;
- generation (52), from the line data (18), of a line model (MD1) representative of lines corresponding to the boundaries of the road zone (2);
- determination (53), based on the quality indicator, the existence indicator and the operability indicator of the demarcations, of at least one confidence indicator (IC4) representative of a level of confidence of the generated line model (MD1); And
- control (54) of the lateral guidance system (19) based on said at least one confidence indicator. A method according to claim 1, wherein said at least one confidence indicator (IC4) is a confidence indicator representing a confidence level for at least two lines in the line model. Method according to claim 1, in which said at least one confidence indicator (IC4) comprises two confidence indicators representing respective confidence levels of two lines of the line model, located on either side of the vehicle in the zone of road. Method according to any one of claims 1 to 3, wherein if at least one said confidence indicator (IC4) indicates a confidence level not satisfying a first condition, then the control of the lateral guidance system (19) comprises a triggering at least one control action. Method according to any one of claims 1 to 4, wherein said at least one control action comprises inhibition of the lateral guidance system (19). Method according to claim 4 or 5, wherein if, for at least one delimitation (30, 32, 34) of the road zone (2), at least one of the following conditions is not met, then said at least one least one confidence indicator does not satisfy the first condition:
- the quality indicator (IC1) indicates a detection quality greater than a first threshold value;
- the existence indicator (IC2) indicates a probability of existence greater than a second threshold value; And
- the operability indicator (IC3) indicates that said at least one camera (12) is operational. Method according to claim 6, wherein the determined line data (18) further comprises, for each delimitation of the road zone (2), a marking type indicator (IC5) indicating a type of marking corresponding to said delimitation ,
in which said at least confidence indicator (IC4) is also determined as a function of the boundary marking type indicator,
in which if, for at least one delimitation of the road zone (2), the following condition is not met, then said at least one confidence indicator (IC4) does not satisfy the first condition:
- the marking type indicator (IC5) indicates that the delimitation corresponds to a first type of marking. Method according to any one of claims 1 to 7, in which the determined line data further comprises, for each delimitation of the road zone, a valid longitudinal distance indicator indicating a longitudinal distance, function of a current speed of the vehicle, on which the polynomial of the delimitation is considered valid,
in which said at least confidence indicator is also determined as a function of the longitudinal distance indicator of validity of the delimitations,
in which, if for at least one delimitation of the road zone, the following condition is not met, then said at least one confidence indicator does not satisfy the first condition: the validity longitudinal distance indicator indicates a distance longitudinal of the polynomial which is less than a third threshold value. Control device (14) of a lateral guidance system (19) of a vehicle (10), said control device (14) comprising a memory (41) associated with at least one processor (40) configured for updating implementing the steps of the method according to any one of claims 1 to 7. Vehicle (10) comprising the control device (14) according to claim 9.