FR3075949A1 - METHOD FOR DETERMINING ANTICIPATION DISTANCE FROM THE TRACK OF A MOTOR VEHICLE - Google Patents

Abstract

The invention relates to a method for determining, over an anticipated distance, the trajectory of a motor vehicle traveling on a roadway of a road, characterized in that it comprises the verification steps, based on the captured data. by optical detection means monitoring the environment situated in front of said vehicle, the visibility of the demarcation lines defining said taxiway on said anticipation distance (200), reconstruction of the profiles of said lines from a model digital system based on the use of data transmitted by said optical detection means, the position of said vehicle provided by a satellite geo-positioning information receiver and data from an electronic map when said lines are not visible on said anticipation distance (300); and determining the trajectory of said vehicle on said anticipation distance from the profiles of said lines (500).

Description

METHOD FOR DETERMINING THE ANTICIPATION DISTANCE OF THE TRAJECTORY OF A MOTOR VEHICLE.

Field of the invention

The present invention relates to the field of driving assistance systems for motor vehicles. It relates in particular to a method for determining the distance of anticipation of the trajectory of a motor vehicle.

Invention background

Driver assistance systems are now widely used in recent motor vehicles and are experiencing rapid development.

Recently, we have started to see completely autonomous driving assistance systems simultaneously controlling the longitudinal and lateral movement of the vehicle.

This is particularly the case for highway driving assistance systems commonly designated under the acronyms HAD (for “Highway Automated Driving”) or AHDA (for “Automatic Highway Driving Assist”) and capable of completely relieving the driver in situations smooth traffic (speed close to the regulatory limit) on roads with separate carriageways.

The latter include in particular an active trajectory tracking assistance module detecting the lines of markings on the ground using optical means such as a camera or a lidar associated with a digital recognition model.

Although these active trajectory tracking assistance modules are becoming more and more efficient so as to detect the lines of markings on the ground in difficult contexts, the fact remains that the latter can find it difficult to ensure proper lateral guidance. in certain specific situations and in particular when these lines are dirty, partially erased, covered by other vehicles located upstream (for example, in the event of a traffic jam), or even when the track has too much curvature (for example, at a roundabout).

Other types of active trajectory assistance modules are also known, based on the use of a satellite geo-positioning information receiver and digital mapping referencing all of the roads constituting the network. road by associating ADAS (Advanced Driving Assistance System) road data relating to this position (curvature, slope, number of lanes, current speed limit, etc.) to each of the points on this map.

To ensure safe lateral guidance of the vehicle, these require the use of a very precise geo-positioning solution, the cost of which remains prohibitive, as well as high definition mapping (that is to say having a density high points) not yet available for the vast majority of existing road networks.

Patent application US 2014/0379164 A1 discloses an active assistance device for tracking the trajectory of a vehicle traveling on a traffic lane of a road delimited by marking lines, comprising optical means monitoring the environment located in front of the vehicle, a satellite geo-positioning information receiver capable of locating the position of the vehicle, a digital map of the road network associating at each point of this map route data relating to this position.

The device is capable of establishing a first trajectory model established from the taxiway demarcation lines detected by optical means, as well as a second trajectory model established from the position of the vehicle and data from electronic mapping.

This device also includes a verification module measuring the difference between the two models so as to determine a confidence index, as well as a selection module which opts for the first model when the demarcation lines are detected by optical means, and which opts for the second model when these lines are not detected by the optical means and the confidence index is greater than a predetermined level.

However, when these lines are not detected by optical means and the confidence index is lower than the predetermined level, this type of device does not make it possible to determine the trajectory for the vehicle.

Subject and summary of the invention

The present invention aims to improve the situation.

To this end, it proposes a method for determining over a distance of anticipation the trajectory of a motor vehicle traveling on a lane of a road, characterized in that it comprises the following steps: - verification, from data captured by optical detection means monitoring the environment in front of said vehicle, the visibility of the demarcation lines defining said taxiway over said anticipation distance; - reconstruction of the profiles of said demarcation lines from a digital model based on the use of data transmitted by said optical detection means, of the position of said vehicle supplied by a satellite geo-positioning information receiver and of data from an electronic cartography when said said demarcation lines are not visible over said anticipation distance; and - determination of the trajectory of said vehicle over said anticipation distance from the profiles of said demarcation lines.

The method according to the invention therefore makes it possible, when the lines of demarcation of the taxiway are not visible over a sufficient distance by the optical detection means, to reconstruct the profiles of the lines of demarcation of the taxiway (and therefore determine the trajectory of the vehicle) with good precision and without requiring a very precise geo-positioning solution or high definition mapping.

According to preferred characteristics of the method according to the invention, taken alone or in combination: - in said digital model, the profile of each of said demarcation lines is obtained by approximating them each by a corresponding polynomial function in an affine plane space f - said polynomial functions are of the third degree; the parameters defining the polynomial function of each said demarcation line include the initial derivative of the curvature of this line, its initial curvature, its initial heading and its initial lateral position; the initial heading and the initial lateral position of each said demarcation line are determined from the data transmitted by said optical detection means; the initial curvature and the initial derivative of the curvature of each said demarcation line are determined from the position of the vehicle and data from said electronic mapping; - When said said demarcation lines are visible over said anticipation distance, their profiles are reconstructed from another digital model based exclusively on the use of data transmitted by said optical detection means; - said anticipation distance is between 50 and 200 meters; and / or - said anticipation distance varies as a function of the speed of said vehicle and corresponds to the distance traveled by the latter during a predefined duration.

Brief description of the drawings The description of the invention will now be continued with the detailed description of an exemplary embodiment, given below by way of illustration but not limitation, with reference to the appended drawings, in which: - Figure 1 is a functional diagram of an automated driving assistance system incorporating an active assistance device for trajectory following according to the invention; and FIG. 2 represents a flow diagram of the method according to the invention for determining over a distance of anticipation of the trajectory of a motor vehicle.

detailed description

With reference to FIG. 1, the automated driving assistance system 1 comprises a detection module 10, an actuation module 20, an evaluation module of the driving environmental context 30, a navigation module 40, as well than a control unit 50.

The detection module 10 comprises optical detection means making it possible to assess the environmental context of driving the vehicle and comprising a video camera 11 located behind the windshield.

As a variant, the detection module 10 may include a lidar 12 to replace or in addition to the video camera 11.

The module 10 further comprises a plurality of sensors measuring certain internal driving parameters such as the instantaneous speed of the vehicle and the steering angle of the steering wheel.

The actuation module 20 comprises a plurality of actuators able to act on the steering, acceleration, braking and the gearbox to ensure fully automated driving of the vehicle.

The driving environmental context evaluation module 30 is able to determine from the data provided by the detection module 10 the type of road taken (motorway, expressway or secondary road), the markings on the ground (color, width and line spacing), the level of fluidity of road traffic and the possible presence of a barrier or a central reservation between the two directions of traffic.

The navigation module 40 includes a satellite geo-positioning information receiver 41 able to determine the position of the vehicle, a digital map 42 and an electronic horizon 43.

The satellite geo-positioning information receiver 41 is a receiver using the Global Positioning System (GPS) which picks up radio signals transmitted by at least three satellites of the GPS system and can, by calculating the propagation times of these i signals between the satellites and him, knowing his distance from them and, by trilateration, determining the position of the vehicle in visibility of the satellites.

As a variant, the satellite geo-positioning receiver 41 can use another satellite geo-positioning system i (GNSS), such as for example the GLONASS system, the BEIDOU system or even the GALILEO system.

The digital cartography 42 references all of the roads constituting the road network in the form of more or less spaced points which are linked together, by associating for each of its points i additional data ADAS (for Advanced Driving Assistance System) relating to the classification of the road, its geometry (curvature, slope, etc.), the number of lanes it comprises or even the speed limit in force.

This mapping 42 is stored in a local memory of the hard disk or flash type i, or else on a remote server. All of the information it contains may be updated by means of communication or means of reading a data medium. The electronic horizon 43 comprises a computer capable of determining from the mapping 42 a route on the road network i from a starting point defined by the user or corresponding to the current position of the vehicle, and up to a point of destination selected by the user. The control unit 50 which manages the autonomous driving of the vehicle, comprises at least one computer associated with storage means comprising non-volatile memory of EEPROM or FLASH type and random access memory.

When the context evaluated by the driving environmental context evaluation module 40 is suitable (for example, in the event of heavy traffic or congestion when the vehicle is traveling on a road with separate carriageways), the piloting 50 is able to control the actuation module 20 to ensure completely autonomous driving of the vehicle.

In particular, the control of the lateral movement of the vehicle is controlled by an active trajectory tracking assistance module 51 integrated into this control unit.

According to the invention, the non-volatile memory of the control unit 50 stores a process for determining over a distance of anticipation of the trajectory of the vehicle. We will now describe in detail and in support of the flowchart of Figure 2, the different stages of this process which is implemented periodically following a predetermined period preferably between 20 and 100 milliseconds and advantageously equal at 40 milliseconds. i This is initiated when the fully autonomous driving assistance mode is activated (initial step 100), the longitudinal and lateral movements of the vehicle then being managed entirely autonomously by the control unit 50.

The active trajectory tracking assistance module 51 then verifies i then in a step 200 if the demarcation lines defining the vehicle traffic lane are visible by the optical detection means in front of this vehicle over a distance d 'predetermined advance advantageously between 50 and 200 m.

If this is not the case (for example because these lines are dirty, partially erased, or covered by other vehicles located upstream), the profile of these demarcation lines is reconstructed from a digital model established from data transmitted by the optical detection means 11, the position of the vehicle provided by a satellite geo-positioning information receiver, and the electronic mapping 42 (step 300).

In this numerical model, the profile of the two lines of demarcation is obtained by approximating each one by a corresponding third degree polynomial function in a plane affine space provided with a Cartesian coordinate system (X, Y) centered on the vehicle: ii Y = - (initial derivative of the curvature) X3 + - (initial curvature) X2 + (initial course) X + Yo 6 2 where: - X and Y correspond respectively to the longitudinal and lateral components i of a point belonging to this line of demarcation ; the initial derivative of the curvature corresponds to the value of the derivative of the curvature at the origin of the reference frame, that is to say at the level of the vehicle at X = 0; i - the initial curvature corresponds to the value of the derivative of the curvature at the origin of the reference frame, that is to say at the level of the vehicle at X = 0; - the initial heading (or yaw angle) corresponds to the value of the heading at the origin of the benchmark, that is to say at the level of the vehicle at X = 0; and i - Yo corresponding to the initial lateral position of the line of demarcation at the origin of the reference point, that is to say at the level of the vehicle at X = 0.

The parameters (initial lateral position Yo) and (initial heading) of i each demarcation line defining the vehicle traffic lane are determined from the data transmitted by the optical detection means 11. The acquisition of these two parameters requires only '' a very low visibility distance of the optical means (of the order of a few i meters), these can therefore be easily obtained even in difficult contexts (dirty lines, partially erased or covered by other vehicles located in upstream, significant curvature of the road, etc.).

The two other parameters of the function (namely the initial curvature and the initial derivative of the curvature) are in turn determined from the curvature data (Y "i, Y" 2) associated with at least two points (Xi, Yi) and (X2, Y2) of the route taken by the vehicle, i referenced in digital mapping 42 in front of the vehicle at a distance less than or equal to the anticipation distance.

The curvature Y "which corresponds to the second derivative of the lateral position Y, can indeed be approximated by the following function: K" (X) = Curvature (X) = (initial derivative of the curvature) X + (initial curvature) 1

The initial curvature and the initial derivative of the curvature can thus be estimated by using for example and the method of least squares from at least two couples (Xi, Y "i) and (X2, Y" 2).

Advantageously and in order to obtain an optimal estimate, i these two parameters will be determined by taking into account all the points referenced by the digital mapping 42 over the anticipation distance, knowing that the latter will reference more points on a curved section of road only on a straight section.

It will be noted that the initial curvature and the initial derivative of the 1 curvature thus determined correspond to those of the profile of the center line of the road and not to those of the two lines of demarcation of the taxiway.

The active trajectory tracking assistance module 51 must therefore adjust these two parameters to obtain those i corresponding to the two lines of demarcation of the vehicle traffic lane.

This adjustment is a function of the spacing assumed to be constant between each of these demarcation lines and the center line of the road, the value of this spacing being obtained from the total width 1 of the road and the number of lanes of the latter. determined from optical means 11 or referenced by digital mapping 42.

Let us now return briefly to step 200 of verification.

If the process considers that the demarcation lines defining the lane of the vehicle are visible by the optical detection means over the entire anticipation distance, the profile of these demarcation lines is reconstructed from a second model. i digital based exclusively on the use of the data transmitted by the optical detection means 11 (step 400).

In this second model, the profiles of the demarcation lines will also advantageously be approximated in a flat affine space provided with a Cartesian coordinate system centered on the vehicle from i of a polynomial function of the third degree.

After reconstruction of the profile of the lines of demarcation of the taxiway, the process determines the trajectory of the vehicle over the anticipation distance (step 500) by for example ensuring that this vehicle remains permanently centered on the taxiway. According to alternative embodiments, the anticipation distance varies as a function of the speed of the vehicle and corresponds for example to the distance traveled by this vehicle for a predefined duration advantageously between 2 and 4 seconds and preferably equal to 3 seconds. In general, it is recalled that the present invention is not limited to the embodiments described and shown, but that it encompasses any variant of execution within the reach of the skilled person.

Claims (10)

1. Method for determining over a distance of anticipation of the trajectory of a motor vehicle traveling on a lane of a road, characterized in that it comprises the following steps: - verification, from data captured by optical detection means monitoring the environment located in front of said vehicle, the visibility of the demarcation lines defining said taxiway over said anticipation distance (200); - reconstruction of the profiles of said demarcation lines from a digital model based on the use of data transmitted by said optical detection means, of the position of said vehicle supplied by a satellite geo-positioning information receiver and of data from an electronic cartography when said said demarcation lines are not visible over said anticipation distance (300); and - determination of the trajectory of said vehicle over said anticipation distance from the profiles of said demarcation lines (500). 2. Method according to claim 1, characterized in that, in said digital model, the profile of each of said demarcation lines is obtained by approximating them each by a corresponding polynomial function in a plane affine space. 3. Method according to claim 2, characterized in that said polynomial functions are of the third degree. 4. Method according to one of claims 2 or 3, characterized in that the parameters defining the polynomial function of each said line of demarcation comprise the initial derivative of the curvature of this line, its initial curvature, its initial heading and its position initial lateral. 5. Method according to claim 4, characterized in that the initial heading and the initial lateral position of each said demarcation line are determined from the data transmitted by said optical detection means. 6. Method according to one of claims 4 or 5, characterized in that the initial curvature and the initial derivative of the curvature of each said demarcation line are determined from the position of the vehicle and data from said electronic cartography . 7. Method according to claim 6, characterized in that the initial curvature and the initial derivative of the curvature of each said demarcation line are determined from the curvature data associated with at least two points of said route referenced in said mapping at ahead of said vehicle at a distance less than or equal to said anticipation distance. 8. Method according to one of claims 1 to 7, characterized in that, when said said lines of demarcation are visible over said distance of anticipation, their profiles are reconstructed from another digital model based exclusively on the use of data transmitted by said optical detection means (400). 9. Method according to one of claims 1 to 8, characterized in that said anticipation distance is between 50 and 200 meters. 10. Method according to one of claims 1 to 8, characterized in that said anticipation distance varies as a function of the speed of said vehicle and corresponds to the distance traveled by the latter during a predefined duration.