FR3103891A1 - MOST PROBABLE LANE NAVIGATION ASSISTANCE DEVICE FOR A VEHICLE, AND ASSOCIATED DRIVING ASSISTANCE PROCESS - Google Patents

Abstract

A navigation aid device (DAN) assists a vehicle (V) comprising a change of direction indicator having a state chosen by the driver and a camera (CO) acquiring images of the environment. This device (DAN) has cartographic data defining lanes (VC1-VC2) of a portion of a route (R) taken by the vehicle (V) and includes a calculator (CA) determining among the lanes (VC1-VC2 ) of this portion that on which the vehicle is traveling (V) as a function of its current geographical position and of analysis data resulting from the analysis of images and representative of at least one so-called observed lane on which the vehicle is traveling ( V), then determining the most probable lane that the vehicle (V) will soon take as a function of this determined lane, the chosen state and the cartographic data. Figure to be published with the abstract: Fig. 1

Description

NAVIGATION AID DEVICE FOR DETERMINING THE MOST LIKELY LANE FOR A VEHICLE, AND ASSOCIATED DRIVING ASSISTANCE METHOD

Technical field of the invention

The invention relates to land vehicles that can travel on roads, and more specifically to assistance (or aid) to the navigation and driving of such vehicles.

State of the art

Some land vehicles include an adaptive speed regulation device which is responsible for regulating their speed from a speed setpoint, possibly chosen by their driver, and able to adapt this speed setpoint according to the context in which they are moving. For example, the context may be traffic or a change in the speed limit or an upcoming change of direction or an upcoming crossing of an intersection or a crossroads or even a variation in the distance separating the vehicle in question from the vehicle preceding this last.

The context of a vehicle can, for example, be determined by analyzing images acquired by at least one on-board camera or a radar (or lidar) in the environment located in front of this vehicle.

In certain situations, if we want to adapt the speed setpoint of a vehicle sufficiently early, we must know its next context in advance. This is the case, for example, when the vehicle is going to have to change direction to take a new traffic lane or is going to have to cross an intersection or a crossroads or is going to enter a roundabout or a tight bend or is going to take a new traffic lane with a lower speed limit than the current one. It will be understood that these adaptations require that we know internally the route that the vehicle will soon follow. However, to have such knowledge, the route of the vehicle must have been previously determined internally by an on-board navigation aid device. Indeed, in this case, and as described in the patent document US-A1 2017/0010617, the next context of the vehicle can be determined in advance from the cartographic data defining the traffic lanes and their possible speed limits. , and thus adapt the speed setpoint of the speed regulator.

However, the solution described in the aforementioned patent document only concerns fully automated (or autonomous) driving vehicles, and therefore it cannot be implemented in a manually driven vehicle when its route is not determined by its device. navigation aid, which is relatively frequent.

The aim of the invention is therefore in particular to improve the situation.

Presentation of the invention

It proposes in particular for this purpose a navigation aid device, on the one hand, intended to aid a vehicle comprising a change of direction indicator having a state chosen by a driver and at least one camera acquiring images of a environment situated in front of it, and, on the other hand, having cartographic data defining routes of a portion of a road taken by the vehicle and of a current geographical position of the latter.

This navigation aid device is characterized in that it comprises at least one computer:

- determining, among the lanes of this portion of road, the one on which the vehicle is traveling according to its current geographical position and analysis data resulting from an analysis of the images acquired and representative of at least one so-called observed lane on which drives the vehicle, then

- determining the most probable lane that the vehicle will soon take according to this determined lane, the chosen state and the map data.

Thanks to the invention, we can now know in advance the path that the vehicle will probably take soon, even though we do not know the route that its driver wants to follow.

The navigation aid device according to the invention may comprise other characteristics which may be taken separately or in combination, and in particular:

- its computer can use analysis data which define at least the delimitations of at least the track observed;

- its computer can also use analysis data defining at least one width of the lane observed in order to determine, among the lanes of the section of road, the one on which the vehicle is traveling;

- in the event of detection by its computer in the analysis data of a passage of the vehicle from one lane to another lane, its computer may consider that the observed lane is the one in which the vehicle is passing;

- in the event of detection by its computer in the analysis data of a first number of lanes greater than a second number of lanes of the portion of road, defined by the cartographic data, its computer may only use the first number to determine, among the lanes of the portion, the one on which the vehicle is traveling;

- in the event of detection by its computer in the map data of at least two lanes that can be taken from the determined traffic lane and involving the same change of direction, its computer may consider that the most probable lane is the one that is closest to the vehicle when the state is representative of this change of direction;

- in the event of detection by its computer in the map data of at least two traffic lanes that can be taken from the determined lane and involving different changes of direction, its computer may consider that the most probable lane is the one which is the closest to the vehicle when the state is not representative of a change of direction.

The invention also proposes a vehicle, possibly of the automobile type, and comprising a change of direction indicator having a state chosen by a driver, at least one camera acquiring images of an environment situated in front of him, and an aid device navigation of the type presented above.

The invention also proposes a driving assistance method intended to assist a vehicle comprising a direction change indicator having a state chosen by a driver and at least one camera acquiring images of an environment located in front of him, and having cartographic data defining lanes of a portion of a road taken by the vehicle and of a current geographical position of the latter.

This driving assistance method is characterized by the fact that it includes a step in which:

- the one on which the vehicle is traveling is determined from among the lanes of this portion of road according to its current geographical position and analysis data resulting from an analysis of the images acquired and representative of at least one lane said to be observed on which the vehicle is traveling, then

- a most probable route that the vehicle will soon take is determined according to this determined route, the chosen state and the map data.

The invention also proposes a computer program product comprising a set of instructions which, when it is executed by processing means, is suitable for implementing a driving assistance method of the type presented here. -forward to determine a most likely lane that a vehicle will soon take comprising a direction change indicator having a state chosen by a driver and at least one camera acquiring images of an environment located in front of him, and having cartographic data defining lanes of a portion of a road taken by the vehicle and of a current geographical position of the latter.

Brief description of figures

Other characteristics and advantages of the invention will appear on examination of the detailed description below, and of the appended drawings, in which:

schematically and functionally illustrates a portion of a road comprising two lanes having the same direction of traffic and on one of which a land vehicle is traveling equipped with a speed regulation device and an example of a driving aid device navigation according to the invention and about to join another route,

schematically and functionally illustrates an embodiment of a navigation aid device according to the invention, and

schematically illustrates an example of an algorithm implementing a driving assistance method according to the invention.

Detailed description of the invention

The object of the invention is in particular to propose a navigation aid device DAN intended to help a land vehicle V to determine the route which it has the greatest probability of shortly taking, and a driving assistance method associated.

In what follows, it is considered, by way of non-limiting example, that the land vehicle V is of the automobile type. This is for example a car, as illustrated without limitation in Figure 1. But the invention is not limited to this type of land vehicle. It relates in fact to any type of land vehicle that can travel on roadways. Thus, it also concerns utility vehicles, camper vans, minibuses, coaches, trucks, motorcycles, road construction machinery, construction machinery and agricultural machinery, for example.

There is schematically shown in Figure 1 a portion of a road R comprising first VC1 (j = 1) and second VC2 (j = 2) lanes having the same direction of traffic, the first lane VC1 allowing access to a third way VC3.

It is important to note that the invention relates to any road comprising at least one lane. Therefore, the portion of road R could consist of only one lane or more than two lanes, and for example three or four lanes, or even more.

In the example illustrated without limitation in Figure 1, a single land vehicle V (here a car) travels on the first lane VC1 which allows access to the third lane VC3, and another vehicle travels on the second lane VC2 a little downstream of the vehicle V.

The (land) vehicle V is, here, equipped with a speed regulation device DR, an example of a navigation aid device DAN according to the invention, a change of direction indicator (or turn signals ) whose state can be chosen by the driver, and at least one CO camera.

This CO camera is responsible for acquiring digital images of at least the environment which is located in front of the vehicle V. For example, it can be fixedly attached to a part of the windshield (preferably upper) or to a rear-view mirror inner center.

The speed regulation device DR is preferably of the adaptive type. In this case, it is responsible for regulating the speed of the vehicle V according to a speed setpoint, possibly chosen by the driver, and for adapting this speed setpoint according to the context in which the vehicle V is moving.

It will be noted that this speed regulation device DR is not necessary for the implementation of the invention, but it uses the most probable route, which is determined by the navigation aid device DAN and defined more away, when the path of the vehicle V is not determined by the navigation aid device DAN.

It will be noted that in the example illustrated without limitation in FIG. 1, the navigation aid device DAN forms a permanent part of the vehicle V. But this is not mandatory. Indeed, it could be part of a communication device temporarily on board the vehicle V, communicating with the vehicle V, and accompanying a passenger, such as for example a smart mobile telephone (or “smartphone”) or a communicating electronic tablet. It (DAN) could also be landed in a server exchanging permanently with the vehicle V, and in particular receiving information defining the current context of the vehicle V and transmitting to it as it moves information defining the path that he will probably borrow soon (as explained later).

As illustrated in FIGS. 1 and 2, a navigation aid device DAN, according to the invention, comprises at least one computer CA and has map data which defines lanes VCj of roads R that can be taken by the vehicle V and the current geographical position of the latter (V).

These cartographic data are for example stored in a memory MC of the navigation aid device DAN. But they could also be stored in a remote server and accessible via an at least partly wireless communication network to which it is possible to connect by wave from the vehicle V. Generally, these map data define the number of lanes of each portion of each road listed, the direction of traffic in these lanes, the speed limits in force on these lanes, as well as possibly the respective widths of these lanes and the connections between lanes.

The current geographical position of the vehicle V is determined periodically by the navigation aid device DAN according to information provided by wave by a satellite positioning system (possibly of the GPS type ("Global Positioning System") ))

The computer CA is arranged so as to determine from among the lanes VCj of the portion of road R taken by the vehicle V that on which it is traveling according to its current geographical position and analysis data which result from an analysis of the images acquired by the camera CO and which are representative of at least one so-called observed lane on which the vehicle V is traveling.

This analysis of the acquired images can be carried out by a dedicated computer, on board the vehicle V and possibly forming part of the camera CO. But it could also be performed by the navigation aid device DAN (and in particular by its computer CA).

In addition, the computer CA is arranged so as to determine a most probable path that the vehicle V will soon take as a function of this determined path, of the state of the change of direction indicator chosen by the driver, and of the cartographic data which defines the portion of road R taken by the vehicle V. Here, the term “most probable route” means the route which has the greatest probability of soon being taken by the vehicle V.

In other words, the computer CA uses all the available information defining the current context of the vehicle V (lane observed by the camera CO on which it is traveling, chosen state of the direction change indicator (activated on the right or to the left or inactivated), and cartographic data defining the portion of road R) to determine the lane that the vehicle V will probably take soon.

This determined most probable path can then be used, for example, by the regulation device DR, possibly to decide on an adaptation of the chosen speed setpoint. It can also be useful to the driver, so that he can adapt the driving (and in particular the speed) of the vehicle V. To this end, the representation of the most probable lane determined (and also preferably its speed limit) may ( ven) t be displayed on a screen present in the vehicle V and in direct view of the driver. Thus, it can, for example, be displayed on the screen of the CC central instrument panel which is installed in or on the dashboard or on a central console housed under the dashboard.

By way of example, when the section of road R comprises two lanes in the same direction VC1 and VC2 when approaching an exit VC3 and the driver has chosen to activate the direction change indicator on the right, as in the example of Figure 1, then if the computer CA detects that the vehicle V is on the right lane VC1 of the road portion R, it deduces that the driver wants to take the exit VC3 which is then the lane more likely.

Also by way of example, when the portion of road comprises two lanes in the same direction, one of which continues straight ahead and the other turning for example to the right, then if the computer CA detects that the vehicle V is on the right lane of the portion of road, it deduces therefrom that the driver wants to remain on this right lane which is then the most probable lane, whereas if the computer CA detects that the vehicle V is on the left lane of the portion of road, he deduces from this that the driver either wants to stay in this left lane, which is then the most probable lane, if the turn signal is not activated on the right, or wants to take the right lane, which is then the most probable lane. probable, if the turn signal is activated on the right.

Also by way of example, when the section of road comprises two lanes in the same direction with no exit but arriving at an intersection and the driver has chosen to activate the direction change indicator on the right, then if the CA computer detects that the vehicle V is on the right lane of the portion of road, it deduces that the driver wants to turn right in the intersection to join a lane which is then the most probable lane (in the case of a country where driving is on the left). This example can be immediately transposed to the case of a country where driving is on the right.

For example, and as illustrated without limitation in FIGS. 1 and 2, to perform its technical operations (or ensure its functions), the computer CA may comprise at least one processor PR, for example of digital signal (or DSP (“Digital Signal Processor”). ")), and at least one memory MD, and therefore can be produced in the form of a combination of circuits or electrical or electronic components (or "hardware") and software modules (or "software"). The memory MD is live in order to store instructions for the implementation by the processor PR of at least part of the driving assistance method described below (and therefore ensure the functions). The processor PR can comprise integrated (or printed) circuits, or else several integrated (or printed) circuits connected by wired or wireless connections. By integrated (or printed) circuit is meant any type of device capable of performing at least one electrical or electronic operation.

It will be noted that the computer CA can use analysis data which define at least delimitations of at least the observed channel. In most situations, it is possible to determine in the images acquired at least the delimitations of the observed lane, but also the presence of a lane to the right and/or of a lane to the left of this observed lane.

It will also be noted that the computer CA can use analysis data which also defines at least the width of the lane observed in order to determine, among the lanes VCj of the portion of road R, that on which the vehicle V is traveling. a lane can be used to recognize that the observed lane is a hard shoulder and therefore not a real lane (typically when the width is less than 2.5 m). If the computer CA detects in the analysis data that there is a lane of reduced width to the right of the determined lane on which the vehicle V is traveling but that the map data does not define such a lane to the right, it deduces therefrom that the reduced-width lane is an emergency lane on the right.

It will also be noted that the computer CA can detect in the analysis data the passage of the vehicle V from one lane VCj to another lane VCj' (j' ≠ j). In this case, the computer CA can consider that the observed lane is the one in which the vehicle V is passing. It will in fact be understood that during such a passage (or line crossing) the vehicle V is located for a few moments in the two lanes VCj and VCj′.

It will also be noted that the computer CA can detect in the analysis data a first number of lanes which is greater than a second number of lanes VCj of the road portion R, defined by the cartographic data, for example due to a failure to record a possibly recent exit channel (or link). In this case, the computer CA can only use the first number to determine from among the lanes VCj of the portion of road R that on which the vehicle V is traveling. This detection of an erroneous number of lanes in the cartographic data is in particular useful in combination with the detection of a line crossing to achieve a resolution of ambiguity in certain situations.

For example, the CA computer can detect in the analysis data that the section of road includes three lanes while the cartographic data defines only two. In this case, if the computer CA detects in the analysis data that there is a lane to the right and a lane to the left of the right-hand lane taken by the vehicle V, then it concludes that there is a additional way out. Consequently, if the driver has chosen to activate the direction change indicator on the right, the computer CA deduces from this that the driver wants to take the additional exit lane, which is then the most probable lane, and in the absence activation of the change of direction indicator, the computer CA deduces that the driver wants to continue on his lane, which is then the most probable lane.

It will also be noted that the computer CA can detect in the cartographic data at least two lanes of traffic that can be taken from the determined lane and involving the same change of direction. In this case, the computer CA can consider that the most probable lane is that which is closest to the vehicle V when the chosen state of the change of direction indicator is representative of this change of direction. In the example illustrated without limitation in Figure 1, the right turn signals of the vehicle V are in operation, which means, a priori, that the driver is about to turn right to take the third lane VC3, which is then the most likely route.

It will also be noted that the computer CA can detect in the cartographic data at least two lanes of traffic that can be taken from the determined lane and involving different changes of direction. In this case, the computer CA can consider that the most probable lane is that which is closest to the vehicle V when the chosen state of the direction change indicator is not representative of a change of direction. The term “lane closest to vehicle V” is understood here to mean the lane which is located at the shortest distance from vehicle V.

It will also be noted, as illustrated without limitation in FIG. 2, that the computer CA can also comprise, in addition to its random access memory MD and its processor PR, a mass memory MM, in particular for storing analysis data, cartographic data of the portion of road R, of the current geographical position, of the chosen state of the change of direction indicator, and of intermediate data involved in all its calculations and processing. In this case, the navigation aid device DAN also comprises an input interface IE for receiving at least the analysis data and the chosen state of the direction change indicator, and the computer CA also includes, optionally, a digital signal processor PR' for formatting and/or demodulating and/or amplifying, in a manner known per se, the analysis data, the cartographic data of the road portion R and the position geographic map in progress, to use them in calculations or processing. In addition, the navigation aid device DAN also comprises an output interface IS, in particular to deliver a definition of each most probable lane determined by its computer CA, in particular for the speed regulation device DR.

The invention can also be considered in the form of a driving assistance (or assistance) method intended to assist (or assist) the vehicle V (comprising a change of direction indicator having a state chosen by its driver and at least one camera CO acquiring images of an environment located in front of him (V), and having cartographic data defining lanes VCj of the portion of road R taken by this vehicle V and of the current geographical position of this last (V)). This driving assistance method can be implemented at least partially by the navigation assistance device DAN.

This driving assistance method comprises a step 10-40 in which one begins by determining from among the lanes VCj of this portion of road R the one on which the vehicle V is traveling according to its current geographical position and data from analysis resulting from the analysis of the images acquired and representative of at least one so-called observed lane on which the vehicle (V) is traveling. Then, a most probable lane that the vehicle V will soon take is determined as a function of this determined lane, of the chosen state of the direction change indicator and of the cartographic data.

This process constitutes a real driving aid since it makes it possible to provide the most probable route to the cruise control device DR and/or to the driver, in order to adapt the driving (and in particular the speed).

Schematically illustrated in Figure 3 is an example of an algorithm implementing a driving assistance method according to the invention.

The algorithm comprises a sub-step 10 in which analysis data resulting from the analysis of the images acquired and representative of at least part of the road portion R are obtained, and the chosen state of the indicator change of direction.

Then, in a sub-step 20, the observed lane on which the vehicle V is traveling is determined in the analysis data.

Then, in a sub-step 30, among the lanes VCj of the road portion R, the one on which the vehicle V is traveling is determined according to its current geographical position and the analysis data.

Then, in a sub-step 40, a most probable path that the vehicle V will soon take is determined as a function of this path determined in the sub-step 30, of the chosen state of the direction change indicator and of the map data.

It will be noted that one or more sub-steps of the step of the driving assistance method can be performed by different components. Thus, the driving assistance method can be implemented by a plurality of digital signal processors, random access memory, mass memory, input interface, output interface.

It will also be noted that the invention also proposes a computer program product (or computer program) comprising a set of instructions which, when it is executed by processing means of the electronic circuit (or hardware) type, such as for example the processor PR, is able to implement the driving assistance method described above to determine a most probable path that the vehicle V will soon take.

Claims (10)

Navigation aid device (DAN) for aiding a vehicle (V) comprising a direction change indicator having a state chosen by a driver and at least one camera (CO) acquiring images of an environment located in front of it ( V), said device (DAN) having cartographic data defining lanes (VCj) of a portion of a road (R) taken by said vehicle (V) and a current geographical position of the latter (V) , characterized in that it comprises at least one computer (CA) determining from among said lanes (VCj) of this portion that on which said vehicle (V) is traveling as a function of said current geographical position and of analysis data resulting from an analysis of said images acquired and representative of at least one so-called observed lane on which said vehicle (V) is traveling, then determining a most probable lane that said vehicle (V) will soon take as a function of said determined lane, of said state selected and said map data. Device according to Claim 1, characterized in that the said computer (CA) uses analysis data defining at least the delimitations of at least the said path observed. Device according to Claim 1 or 2, characterized in that the said computer (CA) also uses analysis data defining at least one width of the said lane observed in order to determine among the said lanes (VCj) of the portion that on which said vehicle (V). Device according to one of Claims 1 to 3, characterized in that in the event of detection by the said computer (CA) in the said analysis data of a passage of the said vehicle (V) from one lane (VCj) to a another lane (VCj'), said computer (CA) considers that said observed lane is the one in which said vehicle (V) is passing. Device according to one of Claims 1 to 4, characterized in that in the event of detection by the said computer (CA) in the said analysis data of a first number of channels greater than a second number of channels (VCj) of said portion, defined by said cartographic data, said computer (CA) uses only said first number to determine among said lanes (VCj) of the portion that on which said vehicle (V) travels. Device according to one of Claims 1 to 5, characterized in that in the event of detection by the said computer (CA) in the said cartographic data of at least two traffic lanes which can be taken from the said determined lane and involving a same change of direction, said computer (CA) considers that said most probable path is that which is closest to said vehicle (V) when said state is representative of this change of direction. Device according to one of Claims 1 to 6, characterized in that in the event of detection by the said computer (CA) in the said cartographic data of at least two traffic lanes which can be taken from the said determined lane and involving different direction changes, said computer (CA) considers that said most probable path is that which is closest to said vehicle (V) when said state is not representative of a change of direction. Vehicle (V) comprising a direction change indicator having a state chosen by a driver and at least one camera (CO) acquiring images of an environment located in front of it (V), characterized in that it further comprises a navigation aid device (DAN) according to one of the preceding claims. Driving assistance method for assisting a vehicle (V) comprising a change of direction indicator having a state chosen by a driver and at least one camera (CO) acquiring images of an environment located in front of him (V), and having cartographic data defining lanes (VCj) of a portion of a road (R) taken by said vehicle (V) and of a current geographical position of the latter (V), characterized in that it comprises a step (10-40) in which the one on which said vehicle (V) is traveling is determined from among said lanes (VCj) of this portion as a function of said current geographical position and of analysis data resulting from an analysis of said images acquired and representative of at least one so-called observed lane on which said vehicle (V) is traveling, then a most probable lane that said vehicle (V) will soon take is determined as a function of said determined lane, of said chosen state and of said map data. Computer program product comprising a set of instructions which, when it is executed by processing means, is capable of implementing the driving assistance method according to claim 9 for determining a most probable path that will soon take a vehicle (V) comprising a change of direction indicator having a state chosen by a driver and at least one camera (CO) acquiring images of an environment located in front of him (V), and having cartographic data defining lanes (VCj) of a portion of a road (R) taken by said vehicle (V) and of a current geographical position of the latter (V).