Method for monitoring at least one lane edge boundary and associated motor vehicle
The method enhances lane edge boundary monitoring in driver assistance systems by combining sensor data to provide continuous and reliable tracking, addressing safety concerns from sensor failures.
Patent Information
- Application Number
- FR2022004095
- Authority / Receiving Office
- FR · FR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-04-29
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2042-04-29
AI Technical Summary
Existing driver assistance systems and autonomous vehicles lack reliable methods for continuously monitoring lane edge boundaries, leading to potential safety issues due to instantaneous sensor failures.
A method for monitoring lane edge boundaries using data from multiple sensors, combining initial and updated representations of lane edges through spiral modeling and Kalman filtering to ensure continuous and reliable tracking, even in the presence of sensor faults.
Ensures continuous and reliable monitoring of lane edges, reducing the risk of errors and maintaining safety by utilizing previous data to validate instantaneous sensor readings.
Smart Images

Figure 00000019_0000 
Figure 00000019_0001 
Figure 00000020_0000
Abstract
Description
Title of the invention: Method for monitoring at least one traffic lane edge boundary and associated motor vehicle Technical field of the invention
[0001] The present invention relates generally to driving aids for motor vehicles.
[0002] It applies more particularly to cars and other motorized vehicles traveling on roads, but also applies to other fields such as robotics.
[0003] The invention relates to a method for monitoring at least one edge limit of a traffic lane used by a motor vehicle.
[0004] It also relates to a motor vehicle adapted to implement such a tracking method. State of the art
[0005] In an effort to make motor vehicles safer, they are currently being equipped with driver assistance systems (or AD AS for "Advanced driver-as-assistance Systems" according to the commonly used acronym of Anglo-Saxon origin) or even highly automated driving systems.
[0006] In the case of such systems or the autonomous vehicle, the detection and representation of the boundaries of the traffic lanes must be reliable since they condition the commands generated subsequently.
[0007] Currently, it is known to use a sensor, such as a camera, which incorporates image processing means in order to represent the edges of traffic lanes.
[0008] It is also known to use several sensors, such as a camera coupled to a RADAR remote sensor, then to process together the data from these different sensors, for example by data fusion, in order to characterize these edges of traffic lanes (in particular by specifying the type of edge, for example a continuous line, a discontinuous line, a border, and the characteristics associated with it).
[0009] These different solutions make it possible to obtain an instantaneous representation of the edges of the traffic lanes used by the motor vehicle.
[0010] However, they are not entirely satisfactory because, in the case of an instantaneous fault in a sensor, no information on the edges of the traffic lanes is available to ensure control of the motor vehicle. This therefore does not offer the desired safety guarantees. Presentation of the invention
[0011] In order to remedy the aforementioned drawbacks, the present invention proposes to improve the monitoring of the edges of traffic lanes.
[0012] More particularly, the invention proposes a method for tracking at least one lane edge boundary of a traffic lane on which a motor vehicle is moving, the method comprising steps of: at a first step in time, - acquisition of at least one initial data item associated with said track edge limit, - determination of a first representation of the track edge limit on the basis of said acquired initial data item, then, at a second time step, - acquisition of at least one updated data item of said trackside limit, - determination of a second representation of the track edge limit based on the updated data, and - determination of a final representation of the track edge limit by combining the first representation and the second representation.
[0013] Thus, thanks to the invention, the lane edge limits are represented on the basis of the data acquired at the current instant but also at one or more previous instants, during the movement of the motor vehicle on its traffic lane. “Continuous” monitoring of these lane edge limits is therefore possible throughout the movement of the vehicle.
[0014] This makes it possible to guarantee safety in driving the vehicle because the track edge limits, necessary for generating the driving control instructions, are then always known.
[0015] In addition, the use of previously acquired data makes the instantaneous representation of each track edge boundary more reliable. This therefore makes it possible to avoid representation errors based on instantaneous defects of the different sensors allowing data acquisition.
[0016] Furthermore, this tracking is based solely on data acquired by the various sensors present in the motor vehicle. No connectivity with other motor vehicles or other infrastructures is necessary to enable tracking.
[0017] Other advantageous and non-limiting characteristics of the tracking method according to the invention, taken individually or in all technically possible combinations, are the following: - a step of evaluating the compatibility of said first representation and said second representation is also provided by determining a distance between said first representation and said second representation, the determination of the final representation being implemented only if the first representation and the second representation are compatible; - the determination of the final representation is implemented only if the determined distance is less than a predetermined threshold value; - the determined distance is a Mahalanobis distance; - if the determined distance is greater than the predetermined threshold value, the final representation of the track edge limit is determined from said second representation only; - during the evaluation stage, sub-stages of: (a) projection of an initial point of the first representation into a first projected point on the second representation, and b) projection of an initial point of the second representation into a second point projected onto the first representation, the determination of the distance being implemented when at least one of the first projected point and the second projected point belongs respectively to the second representation or to the first representation; - if neither the first projected point nor the second projected point belongs to either the first representation or the second representation, the final representation is determined from the second representation only; - the first representation and the second representation have a clothoid shape; - the determination of the second representation is a function of the movement of the vehicle between the first time step and the second time step; - at least one of the first representation and the second representation is determined from a plurality of initial data acquired by several sensors included in the motor vehicle; and - at the stage of determining the final representation, the combination of the first representation and the second representation is implemented by fusion by Kalman filtering.
[0018] The invention also relates to a motor vehicle comprising a computer configured to implement a tracking method as introduced previously.
[0019] Of course, the various features, variants and embodiments of the invention may be combined with each other in various combinations to the extent that they are not incompatible or mutually exclusive. Detailed description of the invention
[0020] The description which follows with reference to the appended drawings, given as non-limiting examples, will make it clear what the invention consists of and how it can be implemented.
[0021] In the attached drawings:
[0022] [Fig.l] represents a schematic view of a motor vehicle suitable for implementing a method in accordance with the present invention;
[0023] [Fig.2] is a schematic top view of the motor vehicle of [Fig.l], on which traffic lanes and the edge limits of these traffic lanes appear;
[0024] [Fig.3] represents, in the form of a flowchart, an example of a method for monitoring traffic lane edge limits in accordance with the invention;
[0025] [Fig.4] illustrates an example of a final representation for a track edge boundary of circulation obtained following the implementation of the tracking method in accordance with the invention and a first example of orthogonal projections used in this method;
[0026] [Fig.5] represents a second example of orthogonal projections used in this process; and
[0027] [Fig.6] represents a third example of orthogonal projections used in this process.
[0028] In [Fig.l], a motor vehicle 10 is shown which is suitable for implementing the invention.
[0029] This is a car. Alternatively, it could be another type of vehicle (truck, motorcycle, etc.).
[0030] Here, this vehicle 10 conventionally comprises a passenger compartment in which there are in particular a seat for the driver 20 of the vehicle, a dashboard with a display screen, and a steering wheel 12.
[0031] This vehicle 10 comprises a powertrain, a braking system and a steering system for turning the vehicle (not visible in the figure). Conventionally, the steering system comprises an electronically controllable power steering actuator, the powertrain comprises an electronically controllable engine control actuator, and the braking system comprises an electronically controllable braking actuator.
[0032] The vehicle 10 further comprises an electronic and / or computer processing unit (hereinafter called computer 11) comprising at least one microprocessor or microcontroller, at least one memory and input and output interfaces.
[0033] Thanks to its input interfaces, the computer 11 is adapted to receive different input data, which come from sensors or third-party computers.
[0034] Among these sensors, the following are provided, for example: - a device such as a front camera and / or a side camera, making it possible to locate the position of the motor vehicle 10 in relation to its traffic lane, and - a device such as a RADAR remote sensor and / or a LIDAR remote sensor, allowing the edges of the road to be detected.
[0035] Thanks to its output interfaces, the computer 11 is adapted to control the display screen, the power steering actuator, the engine control actuator, and the brake actuator.
[0036] Thus, the computer 11 is adapted to implement driving assistance functions and / or automated driving functions (thanks to which the vehicle can move in traffic autonomously, without intervention from the driver).
[0037] Thanks to its memory, the computer 11 stores a computer application, consisting of computer programs comprising instructions whose execution by the computer allows the implementation of the monitoring method described below.
[0038] Generally, the vehicle 10 travels on a traffic lane 1. In the situation shown in [Fig.2], the vehicle 10 travels on a road R with three traffic lanes 1, 2, 3.
[0039] Each traffic lane 1, 2, 3 is delimited, on either side of the traffic zone, by two lane edge limits IA, IB, 2A, 3B.
[0040] In this description, the term "road edge boundary" means any means of delimiting traffic lanes. This includes, for example, continuous road marking lines, discontinuous road marking lines, double road marking lines, barriers, curbs, or even road edges.
[0041] Here, considering the direction of movement of the vehicle 10 shown by an arrow in [Fig.2], the central traffic lane 1 is delimited, on the left, by the track edge limit IA and, on the right, by the track edge limit IB.
[0042] Similarly, as can be seen in [Fig.2], the left traffic lane 2 is delimited, on the left, by the trackside lane 2A and, on the right, by the trackside lane IA. Finally, the right traffic lane 3 is delimited, on the left, by the trackside boundary IB and, on the right, by the trackside boundary 3B.
[0043] The present invention relates to a method for monitoring at least one lane edge boundary IA, IB, 2A, 3B present on the road R taken by the vehicle 10 during its movement. This method aims to enable regular temporal monitoring during the movement of the vehicle of each lane edge boundary IA, IB, 2A, 3B of the road R taken.
[0044] More particularly, the data measured by the various sensors included in the vehicle 10 make it possible to represent, at regular time intervals, each limit IA, IB, 2A, 3B of the track edge so as to have reliable knowledge of it for the subsequent generation of driving commands for the vehicle 10.
[0045] The method makes it possible to follow, for example, one of the limits IA, IB, 2A, 3B of the road edge delimiting the traffic lanes 1, 2, 3 of the road R which the vehicle 10 takes during its movement.
[0046] In a particularly advantageous manner, the method according to the invention allows the simultaneous monitoring of a number N of lane edge limits present on the road taken by the vehicle 10, N being an integer between 1 and 6. example here, the tracking method described below allows the simultaneous tracking of the four lane limits IA, IB, 2A, 3B of the road R during the movement of the vehicle 10.
[0047] For this, the tracking method is implemented iteratively, at regular time intervals, while the vehicle 10 is moving on the road R. This method is for example executed continuously between the starting and stopping of the vehicle.
[0048] As is apparent from the description which follows and which is represented, in the form of a flowchart, in [Fig. 3], certain steps of the method are therefore repeated in a loop at regular time steps. This time step is for example between 30 and 200 milliseconds, preferably of the order of 40 milliseconds.
[0049] As shown in [Fig.3], the method begins at step E2 of initializing a time variable t. This time variable t corresponds to the start time of implementation of the method. For example, here, this time variable t is initialized at time t0. This time t0 corresponds, for example, to the start time of the vehicle 10.
[0050] The method then continues in step E4. During this step, one or more of the sensors of the vehicle 10 acquire initial data relating to the lane edge limits IA, IB, 2A, 3B of the road R.
[0051] These initial data include in particular a time stamp data thereof (for example here the instant to). These initial data also characterize the number of track edge limits IA, IB, 2A, 3B identified (here four as visible in [Fig.2]). They also characterize the type of track edge limit identified, for example a continuous ground marking line for track edge limits 2A, 3B or a discontinuous ground marking line for track edge limits IA, IB.
[0052] The initial data also includes information concerning, for example, the color or thickness of the road marking lines.
[0053] The initial data finally includes data relating to the posture and / or the kinematics of the motor vehicle 10 in its traffic lane 1. This is kinematic data which is preferably obtained using only the sensors on board the motor vehicle 10.
[0054] Here, these data include values of: - speed V of the motor vehicle relative to the ground, expressed in m / s, - longitudinal acceleration ax of the motor vehicle along the X axis, expressed in m / s 2 - lateral acceleration ay of the motor vehicle along the Y axis, expressed in m / s2, - yaw rate of the motor vehicle, expressed in rad / s, - yaw acceleration of the motor vehicle, expressed in rad / s2, - angle of the front wheel of the motor vehicle, expressed in rad, - angle of the rear wheel of the motor vehicle, expressed in rad, and - instantaneous curvature c0,ego of the trajectory of the motor vehicle (this curvature being defined here by the inverse of the radius of curvature, expressed in m1).
[0055] In practice, the initial data can be provided directly by a sensor or pre-processed. If several sensors provide measurements simultaneously at time to, the initial data are obtained by merging these different measurements.
[0056] The initial data acquired are then stored in the memory of the computer 11 (step E6).
[0057] The method continues in step E8, during which the computer 11 determines a first representation CiAt, CiBt, C2At, C3Bt of each track edge limit IA, IB, 2A, 3B identified in step E4.
[0058] As an example, it could be provided that the first representation of each road edge boundary is modeled in a polynomial form. However, here, it is modeled in the form of a clothoid, this form being preferred because it provides better results (for an identical number of coefficients taken into account). In addition, this clothoid form is particularly advantageous for representing the road edge boundaries of roads because the roads themselves generally have a clothoid shape.
[0059] Such a clothoid is defined as having a curvature c which depends on its length, which can be written:
[0060] [Math.l] ^0 = Co +
[0061] In this equation: - it is therefore the equation of the clothoid, -1 is the curvilinear abscissa of the arc of the clothoid, which varies between 0 inclusive and L inclusive, - L is the length of the arc of the spiral, - c0 is the curvature at the origin of the arc, and - Ci is the rate of change of curvature of the arc.
[0062] In other words, a clothoid can be defined by six coefficients which are: - x0, the abscissa of the origin point of the clothoid in the (X, Y) frame, - y0 the ordinate of this point of origin, - Wo which is the heading angle at the origin of the arc, -L, - c0, and - Here.
[0063] In the following, each clothoid will be defined by the set C of these six coefficients, which can be noted as follows: C (x0, yo, ^o, c0, cb L).
[0064] For information, the heading angle along the clothoid can be written as follows:
[0065] [Math.2] W(l) = % + u)du = W0 + c&l + ^.Z2
[0066] The Cartesian coordinates (x, y) of a point located along the clothoid can be written as follows:
[0067] [Math.3] f? x(Z) = x Q + J 0cos(¥(M)).dw y(Q = y Q + J o sin(^ ( U ) ^du
[0068] For the following, we also define, for each clothoid C, the associated state vector s(l) depending on the curvilinear abscissa 1 (with 1 belonging to the interval [0; L]) and noted in the following manner: s(l)=(x(l), y(l), W(l), c(l), Ci). For the starting point of the clothoid, this state vector s(0) is therefore written: s(0)=(x0, y0, Wo, c0, Ci).
[0069] During this step E8, it can be envisaged that the computer 11 receives the coefficients defining each clothoid CiAt, CiBt, C2At, C3Bt (for each limit IA, IB, 2A, 3B of the track edge concerned) from one of the sensors on board the vehicle (for example from the camera if the latter is equipped with a processor adapted to carry out the operations necessary for the determination of the coefficients allowing the determination of the clothoids).
[0070] Alternatively, the computer 11 could receive the data recorded by several of the vehicle's sensors, merge this data, and deduce the desired coefficients.
[0071] As a further variant, the computer could receive coefficients defining the track edge limits in polynomial forms (for example in the form of coefficients of polynomials of order 3). The computer would then have to transform these coefficients so as to find, by calculation, the values of the six coefficients sought. Such a calculation is well known to those skilled in the art and will therefore not be provided here.
[0072] During this step E8, in addition to the aforementioned coefficients, the computer 11 receives variance-covariance matrices S (hereinafter called covariance matrices S) associated respectively with the coefficients of the track edge limits IA, IB, 2A, 3B. Each covariance matrix S makes it possible to take into account the uncertainty in the detection of each track edge limit by the sensor(s).
[0073] These matrices are for example provided by the manufacturer of the sensors used. Alternatively, they can be determined during a sensor test campaign and recorded in the computer memory. The coefficients of these matrices are preferably invariable.
[0074] It should be noted here that if several sensors are used to determine the coefficients characterizing a track edge boundary, their uncertainties will be associated with each other in order to obtain the covariance matrix of a detected track edge boundary.
[0075] Thus, at the end of step E8, a first representation CiAt, CiBt, C2At, C3Bt in the form of a clothoid is associated with each lane edge limit IA, IB, 2A, 3B identified on the road R at time t0. In the example here, four first representations CiAt, CiBt, C2At, C3Bt in the form of clothoids are therefore determined.
[0076] These are stored in the memory of the computer 11 in step E10.
[0077] As shown in [Fig.3], the tracking process continues at step E12, during which the time variable t is incremented by a predetermined time step. The instant at which the following steps are implemented (after incrementation) is called in the following “current instant”.
[0078] Steps E12 to E32 are here implemented in a loop with a regular time step. For example, they are implemented every 40 milliseconds, during the movement of the vehicle 10 on the road R. Alternatively, the time step could be greater than 40 milliseconds, for example of the order of a hundred milliseconds.
[0079] In step E14, the computer 11 receives, from the various sensors, updated data concerning the lane edge limits IA, IB, 2A, 3B at the current time. As for the initial data acquired in step E14, this updated data also concerns data relating to the posture and / or the kinematics of the motor vehicle 10 in its traffic lane 1 at the current time.
[0080] In step E16, the computer 11 verifies that the updated data have a more recent timestamp than the data used at time t0. It may indeed happen that this is not the case in the event of a problem with the sensors for example. If the updated data are not more recent than the data used at time to, the method resumes at step E12, so that new, more recent data are acquired.
[0081] If the timestamp of the updated data obtained at the current time is more recent than that of the data used at time t0, the method continues at step E18, during which the updated data is stored, with the data used at the previous times, in the memory of the computer 11.
[0082] As shown in [Fig. 3], the method then continues in step E20. During this step, and in a similar manner to step E8 described previously, the computer 11 determines a second representation CiAm, CiBm, C2Am, C3Bm of each track edge boundary IA, IB, 2A, 3B identified in step E4. Here too, it could be provided that the second representation of each track edge boundary is modeled in a polynomial form. However, it is also modeled in the form of a clothoid CiAm, c1Bm, C2Am, C3Bm.
[0083] As each second representation CiAm, CiBm, C2Am, C3Bm, here each clothoid C1Am, CiBm, C2Am, C3Bm, is determined on the basis of the updated data acquired at step E14, each second representation CiAm, CiBm, C2Am, C3Bm therefore takes into account the movement of the vehicle 10 from time t0 to the current time.
[0084] In order to carry out reliable monitoring of the track edge limits IA, IB, 2A, 3B, the method continues with step E22, during which the computer 11 evaluates whether it is possible to associate each second representation CiAm, CiBm, C2Am, C3Bm with the corresponding first representation C[At, CiBt, C2At, C3Bt to reconstruct each track edge limit IA, IB, 2A, 3B in a quasi-continuous manner despite the movement of the vehicle 10 between the instant t0 and the current instant.
[0085] Generally, it will be possible to associate, for each limit IA, IB, 2A, 3B, a first representation C[At, CiBt, C2At, C3Bt with a second representation CiAm, CiBm, C2Am, C3Bm if these relate to the same trackside limit IA, IB, 2A, 3B and if they are not too far apart in order to reliably monitor each of the trackside limits IA, IB, 2A, 3B. Step E22 therefore aims to determine a distance between each first representation CiAt, CiBt, C2At, C3Bt and each second representation CiAm, CiBm, C2Am, C3Bm.
[0086] In practice, step E22 is implemented by pair of first and second representations which have been stored in the memory of the computer 11. It is implemented for all possible pairs between the first and second representations (even those which involve first and second representations which do not concern the same track edge limit).
[0087] In the case of [Fig.2], as there are four track edge limits IA, IB, 2A, 3B and therefore four corresponding first representations C[At, CiBt, C2At, C3Bt and four corresponding second representations CiAm, CiBm, C2Am, C3Bm, sixteen pairs are therefore considered at step E22.
[0088] As shown in [Fig.3], step E22 comprises two sub-steps E22a and E22b.
[0089] In order to ensure that it is consistent to determine a distance between a first representation CiAt, CiBt, C2At, C3Bt and a second representation CiAm, CiBm, C2Am, C3Bm of each pair, the calculator 11 first determines the pairs which are compatible (i.e. those for which a calculated distance would make sense).
[0090] This compatibility is evaluated by orthogonal projection of points belonging respectively to the first representation C[At, CiBt, C2At, C3Bt and to the second representation CiAm, CiBm, C2Am, C3Bm on the other representation.
[0091] Advantageously, these are points close to each origin of each clothoid which are projected onto the other clothoid because the variance is minimal at the origins of the clothoids. For the following, the orthogonal projection of each origin of the first representation CiAt, CiBt, C2At, C3Bt and of the second representation CiAm » C1Bm, C2Am, C3Bm is carried out.
[0092] In practice, we consider [Fig.4] representing, for a given couple, a first representation Cit in the form of a clothoid, with origin Mt, and a second representation Cjm in the form of a clothoid, with origin Mm. As shown in [Fig.4], the orthogonal projection of the origin Mt of the first representation Cit is a projected point Pm on the second representation Cim. In the same way, the orthogonal projection of the origin Mm of the second representation Cim is a projected point Pt on the first representation Ct.
[0093] From these orthogonal projections, the calculator 11 considers that the first representation Cit and the second representation Cim of the pair concerned are compatible if at least one of the projected points belongs to the first representation Cit or to the second representation Cim.
[0094] For example, in [Fig.4], the projected point Pt belongs to the first representation Cit while the projected point Pm does not belong to the second representation Cim (it is located outside the clothoid corresponding to this second representation Cim). As one of the two projected points belongs to one of the first or second representations (here the first representation Cit), the first representation Cit and the second representation Cim are considered compatible.
[0095] As an illustration, [Fig.5] shows an example in which the projected points Pm, Pt both belong to the first and second representations Cit, Cim. [Fig.6] shows, for its part, an example in which the projected points Pm, Pt do not belong to either of the first or second representations.
[0096] On the basis of the orthogonal projections produced, the method continues at step E22b, during which, for each pair of first representation CiAt, CiBt, C2At, C3Bt and second representation CiAm, CiBm, C2Am, C3Bm, the distance between the two is determined.
[0097] In practice, this distance calculation makes it possible to select, for each limit IA, IB, 2A, 3B of the track edge, the best candidate pair of first and second representations to represent its tracking along the movement of the vehicle 10 on the road R.
[0098] This distance takes into account the uncertainty in the parameterization of the clothoids, due to potential sensor errors. This is then a Mahalanobis distance dM-
[0099] Generally speaking, the Mahalanobis distance between two vectors x and y to which the covariance matrices Sx and S y are respectively associated is expressed as follows:
[0100] [Math.4]
[0101] This formula can be adapted for a calculation of distance between two clothoids Ci and C2, to which are respectively associated the state vectors si(li) to a first curvilinear abscissa li and s2(l2) to a second curvilinear abscissa 12 and the corresponding covariance matrices Si (h) and S2(l2):
[0102] [Math.5]
[0103] By definition, the covariance matrix S depends on the corresponding curvilinear abscissa. At the starting point of the clothoid, the covariance matrix is zero.
[0104] The following scenarios are then considered, depending on the result of the orthogonal projections carried out in step E22a to determine the distance between the first representation Ct and the second representation Cm of each pair.
[0105] According to a first case (corresponding to the situation of [Fig.6]), if none of the projected points belongs to either of the first and second representations, the distance between the first representation and the second representation is set equal to a predetermined maximum distance dmax. This maximum distance is for example of the order of 100 meters. In practice, in this case, the first representation and the second representation are not compatible because they are considered to be too far apart and will not be associated in the rest of the method.
[0106] According to a second case, shown in [Fig.4], only one of the projected points exists (i.e. belongs to one or the other of the first representation and second representation, here with the projected point Pt which belongs to the first representation Cit). In this case, the distance is calculated between the origin Mm of the clothoid Cim and the projected point Pt on the clothoid Cit is given by the following formula:
[0107] [Math.6] / ( rr to - j U \ \ \ " "Uzxzpj.M
[0108] According to a third case (corresponding to [Fig.5]), the two projected points exist (that is to say that the two projected points Pt, Pm each belong to one or the other of the first and second representations). This case occurs in particular when the first representation and the second representation do not have the same curvature at the level of the orthogonal projections as is visible on the [Fig.5],
[0109] In this case, the projection (i.e. the projected point) with the smallest curvilinear abscissa is used to determine the distance between the first representation and the second representation. In the case of [Fig.5], it is the projected point Pt which is used because it corresponds to the smallest curvilinear abscissa at the level of the orthogonal projection. This choice is advantageous because it corresponds to the projected point which
[0110] [YES]
[0112]
[0113]
[0114]
[0115]
[0116] is closest to the origin of the associated clothoid, which then corresponds to the smallest covariance and therefore to the smallest uncertainty. Thus, considering the two clothoids Cit and Cim and the associated curvilinear abscissas at the level of the projected points Ipt and lPm, the distance is expressed according to either of the following two formulas: [Math.7] r,(Wnr,„(0) / / ' s' Pl e” aM\C^ ~ aM\ vr / / \ I f Sl lPt ~ lPm In the case of [Fig.5], it is the first formula of the equation Math. 7 which is applied (using the projected point Pt as indicated previously). Thus, at the end of step E22b, the distance is determined between each first representation CiAt, CiBt, C2At, C3Bt and second representation CiAm, CiBm, C2Am, C3Bm of each pair. Here, there are therefore sixteen distances determined. At the end of step E22, the computer 11 then determines, for each track edge limit IA, IB, 2A, 2B, the pair of first and second representations for which an association is possible. In practice, the pairs corresponding to the first case described previously, that is to say whose distance has been set equal to the maximum distance (the projected points not existing), are eliminated for the rest of the process. More particularly, for each track edge boundary IA, IB, 2A, 3B, the pairs of first and second representations for which an association is possible correspond to a minimum distance among the distances determined in step E22b. It is important to note that there is only one possible combination of association between a first representation CiAt, CiBt, C2At, C3Bt and a second representation CiAm, CiBm, C2Am, C3Bm to be able to follow the corresponding track edge boundary IA, IB, 2A, 3B. With the notations used, the pairs which can be the subject of association between the first and second representations are the following: (CiAt, CiAm), (CiBt, CiBm), (C2At, C2Am) and (C3Bt, C3Bm).The minimum distance therefore ensures that, for each track edge limit IA, IB, 2A, 3B, it is the first and second relevant representations which will be associated (i.e. it is not, for example, the first representation associated with the track edge limit IA which is associated with the second representation associated with the track edge limit 3B). At the end of step E22, the other pairs are therefore eliminated (and not used for the rest of the process). In other words, the selection implemented at this step allows to ensure that the first representation CiAt, CiBt, C2At, C3Bt and the second representation CiAm, CiBm, C2Am, C3Bm of the pair concerned are relative to the same track edge limit.
[0117] If step E22 leads to the elimination concerning one of the track edge limits IA, IB, 2A, 3B (in practice, if the projected points do not exist for example for this track edge limit), this means that the monitoring of this track edge limit IA, IB, 2A, 3B cannot be carried out by association of a first representation C iAt, CiBt, C2At, C3Bt and a second representation CiAm, CiBm, C2Am, C3Bm as determined respectively in steps E8 and E20. The method then continues in step E24.
[0118] During this step, the computer 11 defines, for the limit IA, IB, 2A, 3B of the edge track concerned (by eliminating all the pairs involving it), the second representation Cia™ CiBm, C2Am, C3Bm corresponding as the final representation C[Af, CiBf, C2Af, C3Bf of this limit IA, IB, 2A, 3B of the edge track at the current time.
[0119] This final representation Cw, CiBf, C2Af, C3Bf is then stored in the memory of the computer 11 (step E26). It then becomes the current representation for the trackside limit IA, IB, 2A, 3B concerned, i.e. the first representation of this trackside limit IA, IB, 2A, 3B for the next instant at which the method is implemented.
[0120] Moreover, in step E28, the time variable is incremented by one time step to execute the tracking method at the next instant. The method then resumes at step E12.
[0121] For the track edge limits IA, IB, 2A, 3B which were not affected by step E24 and the pairs of first representation CiAt, CiBt, C2At, C3Bt and second representation CiAm, CiBm, C2Am, C3Bm which were not eliminated in step E22, the computer 11 considers that the association of the first and second representations is possible to represent each track edge limit. The tracking method then continues in step E30.
[0122] Thus, during step E30, and in order to ensure that, for each track edge limit IA, IB, 2A, 3B, the relevant candidates of the first and second representations can actually be associated, the determined distances are compared to a predetermined threshold value. This predetermined threshold value is here of the order of 2 meters, thus guaranteeing that each selected pair comprises the first representation CiAt, CiBt, C2At, C3Bt and the second representation CiAm, CiBm, C2Am, C3Bm associated with a relevant track edge limit IA, IB, 2A, 3B and that these first and second representations are not too far apart.
[0123] Thus, only the pairs for which the associated distance determined in step E22b is less than this predetermined threshold value are selected for the rest of the process.
[0124] For unselected pairs, i.e. pairs whose associated distance is greater than the predetermined threshold value, the method continues at steps E24 to E28 described previously. Essentially in this case, the computer 11 defines the second representation as the final representation.
[0125] For the selected pairs (CiAt, CiAm), (CiBt, CiBm), (C2At, C2Am) and (C3Bt, C3Bm), whose distance is less than the predetermined threshold value, the method continues at step E32.
[0126] During this step, for each pair (CiAt, CjAm), (CiBt, CiBm), (C2At, C2Am) and (C3Bt, C3Bm) selected, the computer 11 determines the final representation C[Af, CiBf, C2Af, C 3Bf of the limit IA, IB, 2A, 3B of the track edge concerned by combining the first and second representation of this pair.
[0127] More precisely here, the two clothoids corresponding to the first and second representations are merged so as to form a final clothoid CiAf, CiBf, C2Af, C3Bf (which corresponds to the final representation CiAf, CiBf, C2Af, C3Bf).
[0128] Here, this combination is implemented by Kalman filter fusion.
[0129] During this step, the computer 11 therefore determines the state vector sf and the matrix of covariance Sf defining the final clothoid CiAf, CiBf, C2Af, C3Bf from the respective state vectors and covariance matrices of the two clothoids of the couple concerned.
[0130] More precisely, the fusion by Kalman filtering involves an innovation vector yK and a covariance matrix SK- These two parameters are defined by the following formulas:
[0131] [Math. 8] yg $m "
[0132] Furthermore, a Kalman gain K is also determined:
[0133] [Math.9] K =
[0134] From these quantities, the computer 11 therefore determines the state vector sf and the covariance matrix Sf defining the final clothoid C[Af, CiBf, C2Af, C3Bf:
[0135] [Math. 10] s f = s, + Ky K L f = (I-K'jL^I-Kf+K^K 7
[0136] With I an identity matrix and the notation ..T corresponding to the matrix transposition operator.
[0137] An example of a final clothoid Cif obtained at the end of this step is shown in [Fig.4],
[0138] By construction here, the total length Lif of the final clothoid Cif corresponds to the common part of the two merged clothoids Cit and Cim. This common part is obtained by projection of the end points of each of the clothoids Cit and Cim onto the final clothoid Cif. After this projection, the curvilinear abscissa lif of the final clothoid Cif corresponds to the smallest of the two curvilinear abscissas resulting from the two projections onto the final clothoid Cif.
[0139] Alternatively, it may be possible to define the curvilinear abscissa lif of the final clothoid Cif as the larger of the two curvilinear abscissas resulting from the two projections onto the final clothoid Cif.
[0140] As a further variant, it could be possible to use a combination of the two curvilinear abscissas resulting from the two projections onto the final clothoid Cif.
[0141] As a further variant, the total length and the curvilinear abscissa of the final clothoid could be defined differently, for example by considering a different origin for this final clothoid.
[0142] As shown in [Fig.3], the method continues with steps E26 and E28 described previously so as to execute the method at the following instant from the new final representation obtained.
[0143] Although not shown in [Fig.3], it is important to note that the determined final representation is then used to generate the command for the vehicle 10.
[0144] Alternatively, the combination of the first and second representations could be implemented other than by fusion by Kalman filtering. For example, it would be possible to determine an average clothoid from the clothoids corresponding to the first and second representations, for example by applying a weighting to the first and second representations.
[0145] Alternatively, the combination of the first and second representations could be based on the identification of critical points of the first and second representations (such as, for example, starting points and end points of each of the first and second representations) and defining a final clothoid on the basis of these identified critical points (while respecting predefined continuity conditions).
Claims
Claims
1. Method for tracking at least one lane edge boundary (IA, IB, 2A, 3B) of a traffic lane (1, 2, 3) on which a motor vehicle (10) is moving, the method comprising steps of: at a first time step, - acquiring at least one initial data item associated with said lane edge boundary (IA, IB, 2A, 3B), - determining a first representation (Cit) of the lane edge boundary (IA, IB, 2A, 3B) on the basis of said acquired initial data item, then, at a second time step, - acquiring at least one updated data item of said lane edge boundary (IA, IB, 2A, 3B), - determining a second representation (Cim) of the lane edge boundary (IA, IB, 2A, 3B) on the basis of the updated data item, - evaluating a compatibility of said first representation (Cit) and said second representation (Cim) by determining a distance between said first representation (Cit) and said second representation (Cim), then,if said first representation (Cit) and said second representation (Cim) are compatible, - determining a final representation (Cif) of the trackside boundary (IA, IB, 2A, 3B) by combining the first representation (Cit) and the second representation (Cim), in which sub-steps are provided during the evaluation step: - projecting an initial point (Mt) of the first representation (Cit) into a first projected point (Pm) on the second representation (Cim), and - projecting an initial point (Mm) of the second representation (Cim) into a second projected point (Pt) on the first representation (Cit), the determination of the distance being implemented when at least one of the first projected point (Pm) and the second projected point (Pt) belongs respectively to the second representation (Cim) or to the first representation (Cit).,
2. Method according to claim 1, wherein the determination of the final representation (Cif) is implemented only if the determined distance is less than a predetermined threshold value.
3. Method according to one of claims 1 or 2, in which the determined distance is a Mahalanobis distance.
4. A method according to any one of claims 1 to 3, wherein, if none of the first projected point (Pm) or second projected point (Pt) belongs to either the first representation (Cit) or the second representation (Cim), the final representation (Cif) is determined from the second representation (Cim) only.
5. A method according to any one of claims 1 to 4, wherein the first representation (Cit) and the second representation (Cim) have a clothoid shape.
6. Method according to any one of claims 1 to 5, in which at least one of the first representation (Cit) and the second representation (Cim) is determined from a plurality of initial data acquired by several sensors included in the motor vehicle (10).
7. Method according to any one of claims 1 to 6, wherein, in the step of determining the final representation (Cif), the combination of the first representation (Cit) and the second representation (Cim) is implemented by fusion by Kalman filtering.
8. Motor vehicle (10) comprising a computer (11) configured to implement the tracking method according to claims 1 to 7.
