EP4373723A1

EP4373723A1 - Device and method for detecting a vehicle exiting its lane

Info

Publication number: EP4373723A1
Application number: EP22738503.6A
Authority: EP
Inventors: Jérémy LEDUC
Original assignee: Continental Autonomous Mobility Germany GmbH
Current assignee: Continental Autonomous Mobility Germany GmbH
Priority date: 2021-07-20
Filing date: 2022-07-15
Publication date: 2024-05-29
Also published as: WO2023001703A1; CN117836186A; FR3125495A1; FR3125495B1

Abstract

What is proposed is a device (1) for detecting a vehicle (V) exiting its lane, said device being configured, when the vehicle is being driven on a road comprising at least one traffic lane, to: estimate, on the basis of the shape and position of at least one road boundary, the shape and position of each boundary of the lane being taken by the vehicle, estimate a path followed by the vehicle, determine, depending on the shape and on the position of the boundaries of the traffic lane, and on the path followed by the vehicle, a time interval before the vehicle will reach one of the boundaries of the traffic lane, compare the time interval to a determined threshold and, if the time interval is shorter than the threshold, determine that the vehicle is in the process of exiting its lane.

Description

Title: Device and method for detecting lane departure of a vehicle Technical field

The present disclosure relates to a device and a method for detecting and even predicting lane departure from a land vehicle. This disclosure applies to a vehicle that is not equipped with a sensor capable of detecting lane marking lines.

Prior technique

[0002] Land vehicles, in particular cars, trucks, etc., include more and more driving assistance functionalities aimed at alerting a driver to certain dangers, or even assisting or replacing the driver in vehicle control.

[0003] In this context, it is useful to be able to detect that a vehicle is in the process of leaving its traffic lane, or even the road, as soon as possible in order to be able, if necessary, if the lane departure is not undesired, warn the driver or prevent it from taking place.

[0004] In this respect, lane change detection algorithms are already known. Document US 10,406,980, for example, discloses a lane change detection system for a vehicle, which comprises a camera positioned at the front of the vehicle, a radar sensor, and a computer, which detects the markings on the ground (lines of lane separation) on the images acquired by the camera, determines whether the vehicle is in the process of changing lanes as a function of an approach of the vehicle to a lane separation line, and detects, thanks to the radar, a risk of collision with a vehicle in an adjacent lane.

[0005] However, some vehicles are not necessarily equipped with a camera capable of acquiring images on which the markings on the ground are visible. In this type of vehicle, this type of lane detection method by analysis of the markings on the ground cannot be implemented. In addition, even when the vehicle is equipped with a camera, some roads are not always provided with markings (secondary roads, track repair works, etc.).

[0006] Document US 10,586,455 also discloses a lane change detection method implemented by a device comprising a radar sensor and a computer, the method comprising the calculation of a vehicle trajectory, the identification of a point of inflection in the path of the vehicle, and using the identification of the inflection point to confirm a lane change of the vehicle. [0007] However, the point of inflection on the trajectory of the vehicle can only be detected when the vehicle has already made the lane change, or is in the process of changing lanes. This method does not detect a lane change before it occurs.

Summary

[0008] This disclosure improves the situation.

[0009] In particular, an object of the present disclosure is to propose a device and a method making it possible to detect a lane departure even in the absence of a camera in the vehicle. Another object of the present disclosure is to allow the detection of a lane departure before this departure has taken place. [0010] A device for detecting lane departure from a land vehicle is proposed, comprising a radar on board the vehicle, the radar being adapted to acquire information relating to the environment of the vehicle making it possible to estimate the shape and position of at least one edge of the road taken by the vehicle, and at least one computer, the prediction device being characterized in that it is configured for, when the vehicle is traveling on a road comprising at least one traffic lane: a. estimating, from the shape and position of at least one curb of the road taken by the vehicle, the shape and the position of each curb of the traffic lane taken by the vehicle, on either side of that -ci, b. estimating a trajectory followed by the vehicle, c. determining, depending on the shape and position of the edges of the traffic lane, and the trajectory followed by the vehicle, a time interval before the vehicle reaches one of the edges of the traffic lane, d. comparing the time interval to a determined threshold and, if the time interval is less than the threshold, determining that the vehicle is in the process of leaving its traffic lane, the device still being configured to estimate, on the basis of data acquired by the radar, the shape and position of at least one road edge, by a curve of the clothoid type, a width of the traffic lanes and the number of traffic lanes of the road, and to deduce therefrom the shape and the position of each edge of the traffic lane used by the vehicle.

[0011] In embodiments, the device is configured to determine said time interval by determining a point of intersection between a border of the lane and the trajectory of the vehicle, and by calculating the time interval necessary for the vehicle to reach said point of intersection. [0012] In some embodiments, if the trajectory of the vehicle has a point of intersection with each of the edges of the traffic lane, the device is configured to select the point of intersection closest to the vehicle.

In some embodiments, the device is configured to calculate a distance to be traveled by the vehicle between its current position and the intersection point, and to deduce therefrom the time interval necessary for the vehicle to reach the point of intersection, taking into account the speed of the vehicle and its acceleration.

[0014] In some embodiments, the device is configured to implement steps a. to d. iteratively, and for, during a first iteration: - to estimate the trajectory followed by the vehicle by considering that the vehicle is in the middle of its traffic lane, if the time interval is greater than the first determined threshold but lower than a second determined threshold higher than the first threshold, determining a lateral displacement of the vehicle in its lane and updating, for the next iteration, the lateral positions of the edges of its traffic lane relative to the vehicle.

[0015] Device according to any one of the preceding characteristics, configured to, if the time interval is less than the first determined threshold, implement at least one action from the following group: generate a lane departure alert at the attention of a driver of the vehicle, - generating instructions to modify the trajectory of the vehicle in order to keep the vehicle in the lane. generate instructions to slow down the vehicle.

[0016] In embodiments, the radar is an optical radar (i.e. lidar).

[0017] According to another object, there is described a method for detecting lane departure of a land vehicle, implemented by a device according to the preceding description, characterized in that it comprises: the estimation the shape and position of each curb of a traffic lane taken by the vehicle, based on the shape and position of at least one curb of the road containing the traffic lane, - the estimation of a trajectory followed by the vehicle, the determination, depending on the shape and position of the curbs of the traffic lane, and the trajectory followed by the vehicle, of a time interval before the vehicle reaches a curb the traffic lane, and comparing the time interval to a determined threshold and, if the time interval is less than said threshold, determining that the vehicle is in the process of or is going to leave its traffic lane.

According to another object, a computer program product is described, comprising code instructions for implementing the method described above, when this program is executed by a processor.

According to another object, there is described a non-transitory recording medium readable by a computer on which is recorded a program for the implementation of the method described above, when this program is executed by a processor.

[0020] The proposed device can be implemented in a vehicle without a camera making it possible to obtain images of the road, since it only requires the use of a radar making it possible to detect the edges of the road, this radar possibly being a optical radar (aka lidar). The device can also be used in a vehicle normally using the ground markings to detect a lane departure, when the vehicle is traveling on a road where the ground markings are absent or barely visible.

[0021] This device makes it possible to predict a lane departure, whether it is a lane change or a road exit, before this exit actually takes place, according to a point of departure. lane departure calculated by the device and a time interval remaining before the vehicle reaches the lane departure point.

[0022] This device can therefore be used to alert a driver on his trajectory before the lane departure takes place, or to control the activation of other driving assistance functions linked to a possibility of changing of way.

Brief description of the drawings

[0023] Other characteristics, details and advantages will appear on reading the detailed description below, and on analyzing the appended drawings, in which:

Fig. 1

[0024] [Fig. 1] schematically shows a vehicle carrying a device according to one embodiment, and notation conventions for estimating the trajectory of the vehicle and the shape and position of the edges of the lane and/or road.

Fig. 2

[0025] [Fig. 2] schematically shows the notation conventions used for determining the distance to be traveled by the vehicle to reach a point of intersection between a lane edge and the trajectory of the vehicle. Fig. 3

[0026] [Fig. 3] schematically shows the notation conventions used for the calculation of a lateral displacement of the vehicle.

Fig. 4 [0027] [Fig. 4] schematically shows the main steps of a method implemented by a lane departure detection device according to one embodiment.

Description of embodiments

[0028] Reference is now made to Figure 1, in which there is shown a land vehicle V, typically an automobile, a two-wheeler, a heavy goods vehicle, etc., incorporating a lane departure detection device 1 . This device comprises a radar 10 on board the vehicle, adapted to acquire data relating to the environment of the vehicle making it possible to detect the edges of the road taken by the vehicle. The radar 10 can also be an optical radar (or lidar). The device 1 further comprises at least one computer 11. The radar or lidar can comprise in known manner a sensitive element comprising a transmitter/receiver of radio waves, in the case of a radar, or of a laser beam, in the case an optical radar (lidar), and a computer suitable for processing the signals acquired by the transceiver to deduce therefrom data that can be interpreted by humans or by another processing system. In some embodiments, the computer 11 of the device 1 is combined with the computer of the radar 10, so that the lane departure detection device can be considered as a radar or lidar 10 having additional detection functionalities.

Alternatively, the computer 11 of the detection device 1 can be a separate computer from that of the sensor 10. It can be for example a processor, a controller, a microcontroller, or any other type of computer suitable for implementing the processing operations described below.

[0030] In the case where the computer of the detection device is separate from the radar, this computer is not necessarily on board the vehicle. It may be for example a remote computer in communication with the vehicle by means of a telecommunications interface on a wireless communication network. In this case, lane change detection information obtained by the computer can be returned to the vehicle so that certain actions described below can be implemented at the level of the vehicle.

The lane departure detection device 1 is configured to implement a method for detecting a lane departure, the main steps of which are represented in Figure 4. As described in more detail below, this method is implemented iteratively. This method can for example be implemented at the same frequency as a frequency of the radar 10 for the acquisition 90 of data relating to the environment of the vehicle. For example, the method can be implemented at a frequency of between 1 and 50 Hz, for example of the order of 20 Hz, that is to say every 50 ms.

[0032] During this method, the device 1 is configured to, during movement of the vehicle on a road, which may include one or more traffic lanes, estimate the shape and position of the edges of the traffic lane taken by the vehicle during a step 100, from measurements taken by the radar 10 during a step 90. [0033] In what follows, an edge of a traffic lane may correspond to a road edge, for example in the case where the right edge of a traffic lane located furthest to the right on the road is considered. A traffic lane edge can also correspond to a delimitation between two adjacent traffic lanes, which can be, but not necessarily, materialized on the ground by a demarcation line. However, the lane detection device does not need to actually detect a marking on the ground of a demarcation line in order to estimate the position of a traffic lane edge.

[0034] In embodiments, the device 1 estimates the shape and position of the two edges of the traffic lane located on either side of the vehicle. It can be a curb on one side of the vehicle, and a curb delimiting two adjacent traffic lanes on the other side of the vehicle. Alternatively, for a road comprising more than two traffic lanes, the two traffic lane curbs on either side of the vehicle may be lane curbs delimiting two adjacent traffic lanes.

[0035] During step 100, the device 1 determines the shape and position of the edges of the traffic lane taken by the vehicle, from the shape and position of at least one roadside containing the traffic lane, and the configuration of the road. The configuration of the road includes the number of traffic lanes of the road, as well as a typology of the width of the traffic lanes in the road.

[0036] Step 100 includes a step 110 of determining the shape and position of at least one edge of the road, and preferably of the two edges of the road taken by the vehicle. In one embodiment, this step is implemented by the computer of the radar 10, alternatively, it is implemented by the computer 11 of the device 1. For the implementation of the lane departure detection method, the shape of a roadside is estimated by a curve of clothoid type. It is a curve with a constant variation in curvature, defined by:

C _r (0 — C _r0 + C _rl £ Where C _r0 represents the initial curvature of the curve, C _rl represents the gradient of curvature as a function of the curvilinear distance from the origin; and { represents the curvilinear distance from l 'origin.

[0038] In an orthogonal frame of reference (X, Y) centered on the vehicle, and more precisely centered on a point located halfway across the front end of the vehicle, and represented in FIG. 1, each roadside is represented by an equation of the type: y(x) = Y + qc + —~x ² + - -x ⁶

2 6

Where Y represents the lateral position of the point of intersection between the curve defining the road edge and the Y axis of the marker (X,Y), and Q represents the angle between the direction of movement of the vehicle and the tangent to the roadside or lane. Y and Q are values measured by the radar and are independent of the advancement x of the vehicle.

The device 1 can therefore determine the curvature and the curvature gradient of each road edge, to deduce therefrom a clothoid curve equation associated respectively with the left edge and the right edge. In some cases, the curvature and curvature gradient of the left and right edges of the road may be identical.

[0040] Step 100 also includes a step 120 for determining the configuration of the road, comprising determining a number of lanes and a type of width for each lane of the road. For example, traffic lanes can be classified into several categories, such as "normal width", "narrow width", or even "very narrow width". Each category can be associated with an average lane width value. Step 120 can be implemented either by the radar 10, by means of processing algorithms implemented by the computer of the radar 10, or by the computer 11.

The device 1 then determines 130, from at least one of the edges of the road and the determined road configuration, the shape and position of the edges of the lanes taken by the vehicle.

[0042] In the case where the road has only one traffic lane, the shape and position of the curbs correspond to those of the curbs. [0043] If the number of lanes on the road is greater than 1, one of the waysides can be confused with a roadside, but at least one wayside is a border separating two traffic lanes. For this type of curb, the device 1 estimates the shape and position of the curb separating two traffic lanes from the shape and position of one of the curbs. For this, the shape of a roadside separating two lanes of traffic is approximated by the same equation above. In the case where two different equations are determined for the two left and right road edges, the following conventions are then taken:

A curb located to the left of the vehicle (in its direction of travel) has the same shape (curvature and gradient of curvature) as the curb located to the left of the vehicle,

A curb on the right of the vehicle (in its direction of travel) has the same shape as the curb on the right of the vehicle.

[0044] The value of Y, which fixes the lateral position of the point of intersection between the edge of the road with respect to the Y axis of the reference centered on the vehicle, is determined by considering by default that the vehicle is in the middle of its own lane, and therefore this value is equal to half the width of the lane on which the vehicle is located. The width of the lane can be obtained by the radar, because as indicated above this radar can determine a lane classification corresponding to the lane taken, and deduce an associated width therefrom. Alternatively, in case the lane width is not available, it can be set to the standard lane width (3.75m).

For more precision, one can however take into account, in the case where the edge of the road corresponds to a roadside, the actual distance between the vehicle and the roadside. This gives a distance Y _d , between the edge of the right lane and the vehicle, defined by:

Where B _d is the absolute value of the distance between the vehicle and the right road edge and LW is the width of the lane the vehicle is on. Y _d is a negative value with respect to the Y axis shown in Figure 1. On the other hand, the distance Y _g between the left lane edge and the vehicle is defined (according to the notation conventions of Figure 1) by : Where B _g is the absolute value of the distance between the vehicle and the left road curb and LW is the width of the lane the vehicle is on.

Thus to summarize, the device 1 determines, from information acquired by the radar on the shape and the position of at least one of the edges of the road, the shape and the position of the edges of the way, located respectively to the left and to the right of the vehicle (in relation to its direction of travel).

The radar 10 or the computer 11 is also configured to determine or receive from the host vehicle information relating to the dynamics of the vehicle, including in particular the speed and the acceleration of the vehicle, making it possible to estimate the trajectory of the vehicle under the shape of a simplified clothoid composed of a curvature and a gradient of the curvature of the trajectory as a function of the distance traveled by the vehicle.

Thus, starting from the information relating to the dynamics of the vehicle, the device 1, at the level of the computer of the radar 10 or of the computer 11, is configured to estimate 200 the trajectory of the vehicle by the following equation: where C _eo is the estimated curvature of the vehicle trajectory and C _el the estimated curvature gradient of the vehicle trajectory.

The order of implementation of steps 100 and 200 is arbitrary, steps 100 and 200 only require that the radar 10 or the Hait computer acquire the information relating on the one hand to the position of the edges of the road, and on the other hand to the dynamics of the vehicle.

[0050] The computer 11 is then configured to determine 300, from the trajectory of the vehicle and the equations defining the shape and position of the curbs with respect to the vehicle, a time interval before the vehicle reaches a curb. traffic way. This time interval corresponds to the time taken by the vehicle to reach the point of intersection between its trajectory and one of the edges of the lane in which the vehicle is located.

To do this, with reference to Figure 2, the device 1 first determines 310 the coordinates (x,, y,) of the point of intersection I between the path of the vehicle and one of the edges of the road , by solving the following system with two equations and two unknowns: This system can be solved for example with the Cardan method or the Tschirnhaus method.

[0053] Since the device 1 has two equations modeling the shape and the position respectively of the two waysides, on the left and on the right, of the vehicle, the number of solutions of this system can depend on the configuration of the road. Indeed, there may be cases in which several solutions are found.

In one embodiment, the device 1 calculates the solution(s) of this system and, in the case where several solutions are obtained, selects the point of intersection of the vehicle with a roadside located ahead of the vehicle, and located closest to the vehicle.

Thus, in the case where the two curbs have the same shape, the device 1 calculates a single point of intersection with the curb which intersects the trajectory with an intersection point whose coordinate x is positive.

[0056] In the case where the two edges have a different shape, then several cases exist. In one case, the device 1 does not determine any point of intersection between the trajectory of the vehicle and a roadside with a positive xi coordinate. In this case, the processing implemented by the device to detect a lane departure ends without detecting a lane departure.

In another case, the device 1 determines a single point of intersection between the trajectory of the vehicle and one of the edges of the road with a positive xi coordinate. In this case, this intersection point is used for the rest of the processing.

In a last case, the device 1 determines two points of intersection whose x coordinate is positive, between the trajectory of the vehicle and each of the edges of the road. In this case, the nearest intersection point, i.e. having the lowest x coordinate, is chosen for the rest of the processing.

Alternatively, the device 1 can select only one of the two equations corresponding to one of the edges of the tracks to solve the system indicated above. This border can be chosen according to its curvature and that of the vehicle, as being the border that the vehicle has the greatest risk of crossing. For example, if the two lane edges on either side of the vehicle are modeled with the same curvature C _r o and the same curvature gradient Cn, then if the estimated curvature of the vehicle C _e o is greater than C _r o , according to the notation conventions represented in the figures, it is the edge of the road located to the left of the vehicle which risks intersecting the trajectory of the vehicle. In this case, the device only determines a point of intersection between the trajectory of the vehicle and the modeling of this edge of the road. Conversely, if CeCXCrO, an intersection is sought between the trajectory of the vehicle and the edge of the lane located to the right of the vehicle, still in the direction of movement of the vehicle.

Once the intersection point l(xi, yi) has been determined (and if necessary, selected), the device 1 determines 320 a distance to be traveled by the vehicle to reach this intersection point. With reference to figure 2, to simplify the calculations, this distance is approximated by the length s of the smallest arc of the circle of radius 1/C _eo passing through: the origin of the reference, and the point of intersection (x, , y,) between the trajectory of the vehicle and the edge of the road that it intersects. By definition we have:

Where a is the angle formed between the normal to the trajectory of the vehicle at the origin of the coordinate system and the normal to the trajectory of the vehicle at the level of the point of intersection.

[0061] By noting c the length of the chord of the arc of a circle corresponds to the curvilinear length 8, that is to say the rectilinear distance between the current position of the vehicle and the position of the point of intersection (xi, yi ):

Furthermore, as can be deduced from the diagram in Figure 2, the length c can also be calculated as follows:

[0063] Consequently, the distance to be traveled to reach the intersection point is calculated by applying the following formula:

Finally, the computer 11 deducts 330 from this distance the time T required for the vehicle to reach the intersection point, given the distance and the speed of the vehicle. For greater precision, the calculation of the time required can also take into account a correction factor on the speed taking into account the current acceleration of the vehicle: T = -

V(t) + a(t) * At

Where V(t) is the instantaneous speed of the vehicle, a(t) its instantaneous acceleration, and At the time lapse between two iterations of the method.

The successive iterations of the method make it possible to follow the evolution over time of this time T before the vehicle crosses a roadside.

In one embodiment, during a step 400, the device compares this time T with a predetermined threshold T1 and, if T is less than this threshold, it determines 510 that the vehicle is in the process of exiting his way. T 1 is preferably less than 5 seconds, preferably between 1 and 3 seconds. Alternatively, and as shown in Figure 4, T is compared to two thresholds T1 and

T2, where T2 is greater than the threshold T 1 determining the lane departure. T2 can for example be between 3 and 10 seconds.

[0068] In this case, when T becomes lower than the threshold T2, this implies that the vehicle is approaching the edge of the road in question and that it will perhaps leave the lane. In this case, the device 1 updates 520, for the following iterations of the method, the lateral positions of the edges of the road relative to the vehicle, that is to say the values of Yg and Yd, taking into account a lateral movement of the vehicle in its lane. This lateral displacement is determined from the instantaneous speed of the vehicle, and from the initial angle measured between the vehicle and the edge of the road having made it possible to determine the shape and position of the edge of the road concerned by the time T before intersection . Lateral displacement DL can be calculated as follows:

DL = sin(0) * v(t) * At

The updating of the lateral positions of the edges of the road is then obtained by:

¾,¾:+ 1 ^— ¾, _f c ^— DL Yr,fc+ 1 ⁼ ^r,fc + DL

Where k and k+1 designate two successive iterations of the process.

This updating of the lateral position of the curbs implies, for the following iteration, a reduction in the time T before the intersection with one of the curbs. At each following iteration, the device 1 continues to compare the time T with the two thresholds T1 and T2 and:

If T is between T2 and T1, the device 1 implements the same update 520 of the lateral position of the road edges described above, If T is less than T1, device 1 detects 510 a lane departure,

If T becomes greater than T2 again, then device 1 resets 530 the values of Yg and Yd in accordance with what was indicated in the description of step 100 above. [0071] When, in step 510, the device 1 detects a lane departure, it can transmit a signal to an on-board computer of the vehicle so that the latter generates an audible or visual alert for the attention of the vehicle driver. . As a variant, the alert can be generated directly by the device 1. According to yet another variant, the lane departure information can be transmitted by the device 1 to the vehicle's on-board computer to implement other reactions, including for example one of the following reactions: generating instructions to modify the trajectory of the vehicle in order to keep the vehicle in the lane. generate instructions to slow down the vehicle.

[0072] Thus, the method therefore makes it possible to detect a vehicle lane departure, which may be a lane change or a road exit, before this exit has actually taken place, which makes it possible to take measures for the 'to avoid. In addition, this method is adaptable to different road configurations, and allows detection to be carried out without analysis of ground markings.

Claims

[Claim 1] Device (1) for detecting lane departure from a land vehicle (V), comprising a radar (10) on board the vehicle (V), the radar being adapted to acquire information relating to the environment of the vehicle making it possible to estimate the shape and position of at least one edge of the road taken by the vehicle, and at least one computer (11), the prediction device (1) being characterized in that it is configured for, when the vehicle is traveling on a road comprising at least one traffic lane: a. estimating (100), from the shape and position of at least one edge of the road taken by the vehicle, the shape and position of each edge of the traffic lane taken by the vehicle, on both sides other of this one, b. estimating (200) a trajectory followed by the vehicle, c. determining (300), depending on the shape and position of the edges of the traffic lane, and the trajectory followed by the vehicle, a time interval (T) before the vehicle reaches one of the edges of the traffic lane traffic, d. comparing (400) the time interval to a determined threshold and, if the time interval is less than the threshold, determining (510) that the vehicle is in the process of leaving its traffic lane, the device still being configured to estimating, from data acquired by the radar (10), the shape and the position of at least one road edge, by a curve of the clothoid type, a width of the traffic lanes and the number of traffic lanes of the road, and to deduce the shape and position of each edge of the traffic lane taken by the vehicle.

[Claim 2] Device (1) according to claim 1, the device being configured to determine (300) said time interval (T) by determining (310) a point of intersection (I) between an edge of the lane and the trajectory of the vehicle, and by calculating the time interval necessary for the vehicle to reach said point of intersection.

[Claim 3] Device according to Claim 2, in which if the trajectory of the vehicle has a point of intersection with each of the edges of the traffic lane, the device (1) is configured to select the nearest point of intersection of the vehicle.

[Claim 4] Device (1) according to claim 2 or 3, the device being configured to calculate (320) a distance to be covered by the vehicle between its current position and the point of intersection (I), and to deduce therefrom ( 330) the time interval needed by the vehicle to reach the point of intersection, taking into account the speed of the vehicle and its acceleration.

[Claim 5] Device (1) according to any one of the preceding claims, the device being configured to implement steps a. to d. iteratively, and for, during a first iteration: estimating the trajectory followed by the vehicle by considering that the vehicle is in the middle of its traffic lane, if the time interval (T) is greater than the first threshold (T1) determined but lower than a second threshold (T2) determined higher than the first threshold, determining a lateral displacement of the vehicle in its lane and updating (520), for the next iteration, the lateral positions of the edges of its lane of traffic relative to the vehicle.

[Claim 6] Device according to any one of the preceding claims, configured for, if the time interval (T) is less than the first determined threshold (T1), implementing at least one action from the following group: generating a lane departure alert to a driver of the vehicle, generating instructions to modify the trajectory of the vehicle in order to maintain the vehicle in the lane. generate instructions to slow down the vehicle.

[Claim 7] Apparatus according to any preceding claim, wherein the radar (10) is an optical radar.

[Claim 8] Method for detecting lane departure of a land vehicle, implemented by a device (1) according to any one of the preceding claims, characterized in that it comprises: the estimation (100 ) the shape and position of each curb of a traffic lane taken by the vehicle, based on the shape and position of at least one curb of the road containing the traffic lane, the estimate (200 ) of a trajectory followed by the vehicle, the determination (300), depending on the shape and position of the edges of the traffic lane, and the trajectory followed by the vehicle, of a time interval before the vehicle reaches an edge of the traffic lane, and comparing (400) the time interval to a determined threshold and, if the time interval is less than said threshold, determining that the vehicle is in the process of or will leave its traffic lane, estimating the shape and position of at least one roadside, by a clothoid type curve, of a width of the traffic lanes and the number of traffic lanes of the road, to deduce therefrom the shape and position of each edge of the traffic lane taken by the vehicle being produced from data acquired by the radar (10).

[Claim 9] Computer program product, comprising code instructions for implementing the method according to the preceding claim, when this program is executed by a processor.

[Claim 10] Non-transitory computer-readable recording medium on which is recorded a program for carrying out the method according to claim 8, when this program is executed by a processor.