FR3060737A1 - SYSTEM AND METHOD FOR CONSTRUCTING A VIRTUAL HORIZON - Google Patents

Abstract

A system for constructing a virtual horizon, comprises: - a processing unit (12) designed to identify, by analysis of captured data (CAPT) by at least one sensor (2; 4) fitted to a vehicle, events (Ei ) occurring in an environment of the vehicle; - a storage unit (14) of said events each associated with information identifying the event concerned along a path taken by the vehicle; and an assembly (16, 20) for determining at least one characteristic (C1; C2) of road environment to be assigned to the path on the basis of at least two memorized events (Ei). An associated method is also provided.

Description

Holder (s): VALEO SCHALTER UND SENSOREN GMBH Simplified joint-stock company.

Extension request (s)

Agent (s): VALEO COMFORT AND DRIVING ASSISTANCE.

(54) SYSTEM AND METHOD FOR CONSTRUCTING A VIRTUAL HORIZON

FR 3 060 737 - A1 (5d) A system for building a virtual horizon, includes:

- a processing unit (12) designed to identify, by analysis of data captured (CAPT) by at least one sensor (2; 4) fitted to a vehicle, events (Ei) occurring in an environment of the vehicle;

- a storage unit (14) of said events each in association with information identifying the event concerned along a route taken by the vehicle; and

- an assembly (16, 20) for determining at least one characteristic (C1; C2) of the road environment to be assigned to the journey on the basis of at least two stored events (E,).

An associated method is also proposed.

System and method for constructing a virtual horizon

Technical field to which the invention relates

The present invention relates to driver assistance systems and the recognition, in this context, of a context of evolution of a vehicle.

It relates more particularly to a system and a method for constructing a virtual horizon.

TECHNOLOGICAL BACKGROUND

In order to know a context of the evolution of a vehicle, a cartographic database and a device for geolocation of the vehicle are frequently used today.

Indeed, the geolocation device of the vehicle makes it possible to know its current position and therefore to extract from the cartographic database the characteristics of the immediate environment of the vehicle.

It is thus possible in particular to build on the basis of this cartographic data an electronic horizon in order to anticipate the situations that is likely to encounter the vehicle.

However, this solution cannot function correctly when the geolocation device is faulty (for example due to a reception problem, typically in a tunnel) or when the environment is modified without this change being reflected in the database cartographic data, for example in the event of a change in the traffic plan or during work on the roadway.

Object of the invention

In this context, the present invention provides a system for constructing a virtual horizon, comprising a processing unit designed to identify, by analysis of data captured by at least one sensor fitted to a vehicle, events occurring in a vehicle environment; a unit for memorizing said events each in association with information identifying the event concerned along a route taken by the vehicle; and a set for determining at least one characteristic of the road environment to be assigned to the journey on the basis of at least two stored events.

A virtual horizon is thus constructed which describes the road environment and can be used like the electronic horizon mentioned above, but which is constructed in real time and therefore does not depend on a cartographic database or on a location. of the vehicle using an external system.

According to other optional features (and therefore non-limiting):

the system comprises a unit for determining, on the basis of the stored events, information associated with a characteristic of the environment for a plurality of points of the journey;

- the determination unit is designed to produce a probability associated with said information;

the system comprises an automaton comprising internal registers and arranged to successively traverse the points of the path, to update said internal registers as a function of the information associated with said characteristic for the current point and to produce information for detecting the context according to said internal registers;

- the controller is designed to produce, for each current point, a confidence index associated with the context detection information;

- the information identifying the event is a curvilinear abscissa along the route;

- the storage unit is designed to determine said curvilinear abscissa as a function of a current curvilinear abscissa of the vehicle delivered by an odometer;

- the information identifying the event is temporal information;

- the system includes a driving assistance system designed to activate or deactivate a functionality according to the characteristic of the determined road environment;

- the functionality is an autonomous driving functionality.

The invention also provides a method for constructing a virtual horizon, comprising the following steps:

- identification by means of a processing unit, by analysis of data captured by at least one sensor fitted to a vehicle, of events occurring in an environment of the vehicle;

- memorization of said events each in association with information identifying the event concerned along a route taken by the vehicle;

- determination of at least one characteristic of the road environment to be assigned to the journey on the basis of at least two stored events.

Detailed description of an exemplary embodiment

The description which follows with reference to the accompanying drawings, given by way of nonlimiting examples, will make it clear what the invention consists of and how it can be carried out.

In the accompanying drawings:

- Figure 1 shows an example of an on-board system in accordance with the teachings of the invention;

- Figure 2 schematically shows a first type of processing carried out within the system of Figure 1;

- Figure 3 schematically shows a second type of processing carried out within the system of Figure 1; and

- Figure 4 schematically shows a vehicle equipped with an on-board system such as that of Figure 1.

FIG. 1 represents an example of an on-board system, here in a motor vehicle (such as that of FIG. 4), in accordance with the teachings of the invention.

This on-board system includes various sensors, here an image sensor 2 (such as a video camera) and a time-of-flight sensor 4 (such as a laser rangefinder).

These sensors produce CAPT captured data representative of the vehicle environment. In the case of the image sensor 2, the captured data CAPT is representative of the light received by the image sensor 2 at each of its pixels (associated respectively with different directions of the field of vision of the image sensor 2 ). In the case of the time-of-flight sensor 4, the data captured CAPT is representative of the distance from the first object encountered by the beam emitted, this for a plurality of directions of the environment.

The on-board system also includes an odometer 5 which provides a measure of the distance traveled by the vehicle along its path, that is to say the instantaneous curvilinear abscissa s along the path of the vehicle.

The on-board system also includes a location device

6, for example a geolocation device (or GPS for Global Positioning

System). Such a location device 6 produces positioning information POS of the vehicle in a given frame of reference, here the ground frame of reference.

The on-board system comprises a cartographic database 7 containing descriptive elements of the environment which the vehicle is likely to use. These descriptive elements notably include descriptive data of the roads present in this environment, in particular for example an identifier of the road, the geographical location of the road, and, for different portions of this road, the number of traffic lanes and the speed limit allowed for the portion concerned.

The aforementioned descriptive elements may possibly also include descriptive data of other elements of the environment.

Note that the descriptive elements present in the cartographic database 7 describe the environment as it existed during the construction of the database; this environment may however have been modified at certain points during the effective passage of the vehicle and the cartographic database 7 therefore does not always perfectly represent the environment crossed by the vehicle.

The cartographic database 7 is stored here in the vehicle, for example on a hard disk or an optical disk present on board the vehicle. As a variant, the cartographic database 7 could be stored on a remote server and accessible from the vehicle by means of a telecommunication system equipping the vehicle.

The on-board system comprises a navigation module 8 which extracts, from the cartographic database 7, ADAS data relating to the environment close to the vehicle, according to the current position of the vehicle given by the positioning information POS produced by the location device 6.

The location device 6, the cartographic database 7 and the navigation module 8 form a navigation unit 9.

The on-board system of FIG. 1 finally comprises a recognition system 10 making it possible to identify at least one context of vehicle evolution (here several contexts C1, C2 of vehicle evolution) or, more generally, to determine a characteristic d road environment to be assigned to the route taken by the vehicle, as described below.

The recognition system 10 is for example constructed on the basis of a microprocessor architecture: in this case, a memory associated with the microprocessor stores computer program instructions whose execution by the microprocessor allows the implementation of the different functional units described now.

The recognition system 10 thus comprises a processing unit 12 which analyzes the captured data CAPT (for example by means of shape recognition algorithms), recognizes (by means of this analysis) objects in the environment (for example traffic signs, traffic lights, fixed or mobile objects, traffic lanes adjacent to the lane taken, markings on the ground, etc.) and deduce certain events E, to be listed as explained below. (Such an event E, for example, is the presence of a speed limit sign authorized at a given speed.)

The recognition system 10 comprises a storage unit 14 which receives on the one hand the events E produced by the processing unit 12 and on the other hand the curvilinear abscissa s measured by the odometer 5, and can thus memorize each of the events E, in association with information identifying the event concerned along the route taken by the vehicle (this information here being the curvilinear abscissa along the route).

We note that the curvilinear abscissa recorded in association with an event E, given is not necessarily equal to the curvilinear abscissa s provided by the odometer 5, but is determined according to the curvilinear abscissa s provided by the odometer and the position of the event E, relative to the vehicle (an event E, such as a traffic sign which can for example be detected by the image sensor 2 at the front of the vehicle, eg at 100 m at the front of the vehicle). The position of an event E, with respect to the vehicle is for example in this case provided by the processing unit 12 as data appended to the event E ,.

According to another possible possibility, the information identifying the event concerned along the route taken could be temporal.

Anyway, the storage unit 14 thus constructs a virtual horizon vHor which lists the events E, past or future (within the range of the sensors 2, 4) along the path of the vehicle.

In order to limit the consumption of memory due to the memorization of past events, the memorization unit 14 can only keep in memory the events E, relating to curvilinear abscissas whose distance to the curvilinear abscissa is less than one predetermined threshold (this threshold being for example equal to 1000 m in practice).

The recognition system 10 includes a pattern recognition unit 16 (in pattern matching) which analyzes the events E, stored in the virtual horizon vHor and deduces therefrom, for a plurality of characteristics PROF1, PROF2 of the environment of the vehicle. , information 11, I2, to which is possibly associated a probability P1, P2 (which represents a level of confidence associated with the information 11, I2 concerned).

For a PROF1 characteristic corresponding to the number of lanes of the route taken, information 11 is for example an indication of passage from 2 to 3 lanes of traffic, or an indication of passage from 3 to 2 lanes of traffic. Each item of information 11, I2 delivered by the pattern recognition unit 16 can be associated with item of information identifying this item of information 11, I2 along the path taken by the vehicle (here the curvilinear abscissa s).

The operation of the pattern recognition unit 16 is shown diagrammatically in FIG. 2.

The pattern recognition unit 16 implements a plurality of algorithms ALGO1, ALGO2, each algorithm ALGO1, ALGO2 producing (at each point of the path taken by the vehicle) information 11, I2 for achieving a given characteristic PROF1 , PROF2 (associated with this algorithm) on the basis of events E, stored in the virtual horizon vHor. At least some of these algorithms can also produce a probability P1, P2 (or confidence index) associated with the information 11, I2 produced by the algorithm concerned.

In the following, we will call profit 'each characteristic PROF1, PROF2 thus evaluated because this characteristic PROF1, PROF2 generally makes it possible to identify a particular road profile. Such a characteristic PROF1, PROF2, or profile, can be for example the number of traffic lanes on the road, a given speed limit, or a particular road context (city, motorway, junction, etc.).

The algorithms ALGO1, ALGO2 can for example be probabilistic algorithms based on the Dempster-Shafer theory.

The pattern recognition unit 16 thus makes it possible to determine (and memorize), for each of the characteristics PROF1, PROF2 being monitored, performance information 11, I2 and, optionally, a probability value P1, P2 associated with this information. realization 11, I2, and this for each point of the path taken by the vehicle (the points of the path thus considered being for example separated by a fixed step).

The recognition system 10 also includes a formatting unit 18 designed to construct information I3, I4 relating to characteristics PROF3, PROF4 of the environment, this time on the basis of the ADAS data extracted by the navigation module 8. From such functionalities are generally mentioned under the term electronic horizon or eHorizon.

The characteristics PROF3, PROF4 followed by the formatting unit 18 may include characteristics (such as characteristics PROF1, PROF2) also monitored by the pattern recognition unit 16 and / or characteristics distinct from those monitored by the unit pattern recognition 16.

Like the pattern recognition unit 16, the formatting unit 18 makes it possible to determine (and thus store) for each of the characteristics PROF3, PROF4 monitored, information I3, I4 and, optionally, a probability value P3, P4 associated with each of these pieces of information I3, I4, and this for each point of the path taken by the vehicle. These probability values can for example be determined as a function of the date of updating of the cartographic database 7 and / or of the quality of the signal processed by the location device 6.

The recognition system 10 finally comprises a synthesis unit 20 which uses the information 11, I2, I3, I4 (as well as possibly the probability values P1, P2, P3, P4) determined respectively for the different characteristics PROF1, PROF2, PROF3, PROF4 of the environment (either by the pattern recognition unit 16, or by the formatting unit 18) to produce different characteristics of the road environment to be attributed to the route taken, that is to say here different context detection information C1, C2.

As schematically represented in FIG. 1, the synthesis unit 20 can possibly receive directly (ie without processing by the pattern recognition unit 16) events E, and use them in the same way as the information 11, I2, I3 , I4 (as described below).

The synthesis unit 20 here comprises an automaton (for example a state machine or, more generally, an automaton designed to implement a particular processing algorithm) specific for each characteristic of the road environment (in practice for each context) C1, C2 to watch. Figure 3 shows the operation of one of these machines.

Such an automaton can be called a visitor because, as schematically represented in FIG. 3, this automaton traverses all the points t of the path and takes into account, at each point t of the path, information 11, I2, I3, I4 ( as well as optionally probability values P1, P2, P3, P4) respectively associated with the different characteristics PROF1, PROF2, PROF3, PROF4 as explained above.

Specifically, at each point t of the journey, the automaton or visitor updates (ie changes) its internal registers R as a function of the information 11, I2, I3, I4 (and, where appropriate, of the probability values P1, P2, P3, P4) respectively associated with the different characteristics PROF1, PROF2, PROF3, PROF4 for the point t concerned, and determines information for detecting a given context Ci (associated with the visitor) according to the state of its registers internal R.

The context detection information C1, C2 is for example a binary value which indicates whether or not the context concerned is identified.

Furthermore, at least some visitors can produce a confidence index associated with the context detection information C1, C2 delivered.

Such a context Ci (or characteristic of the road environment) is for example the circulation of the vehicle on a multi-lane road, the presence of works, the end of the traffic lane on a multi-lane road, the approach of a toll or speed limit allowed.

The characteristics (such as PROF1, PROF2, PROF3, PROF4) traversed (and scanned) by a visitor depend on the context that this visitor seeks to identify. For example, a visitor designed to detect a multi-lane road may in particular use a lateral distance characteristic of traffic signs; a visitor designed to detect the presence of works can use a characteristic relating to the presence of certain specific road signs and a characteristic relating to the color of the markings on the ground; a visitor designed to detect the end of a traffic lane may in particular use a characteristic relating to the presence of arrows marked on the ground; a visitor designed to detect the approach of a toll may in particular use a characteristic relating to the presence of more than 3 lanes of traffic and a characteristic relating to the presence of other vehicles in the vicinity.

We also note that in practice, the detection information delivered (at any time) by a visitor can be used as input for another visitor (as a value representative of a characteristic of the environment).

The context detection information C1, C2 delivered by a visitor can furthermore possibly be recorded in the virtual horizon vHor (by the storage unit 14), this visitor playing in a way the role of a virtual sensor.

The use of PROF1, PROF2 characteristics (or profiles) based on the virtual horizon vHor (and therefore on the detections carried out in real time by sensors 2, 4), in addition to the PROF3, PROF4 characteristics from the electronic horizon , makes it possible to obtain (by merging information 11, I2, I3, I4 associated with these different characteristics PROF1, PROF2, PROF3, PROF4 by means of the visitor concerned) particularly reliable context detection information C1, C2, which takes account in particular possible modifications made in the environment since the establishment of the cartographic database 7. The production of such detection information could then cause the generation of an alert or a deactivation of an autonomous driving mode, as explained below.

For example, a visitor designed to detect the approach of a toll can use characteristics based on the virtual horizon (a characteristic relating to the presence of more than 3 lanes of traffic and a characteristic relating to the presence of other nearby vehicles as indicated above) and one or more characteristics based on the electronic horizon (for example a characteristic relating to the presence of the toll).

The context detection information (or characteristics of the road environment) C1, C2 provided by the recognition system 10 (precisely here by the synthesis unit 20) can indeed be used by various systems of the vehicle.

In the example described here, two distinct context detection information C1, C2 are used by an autonomous driving management system 30 to authorize or prohibit (according to the values of the information C1, C2) the implementation of a functionality autonomous driving.

The context detection information C1 is for example information indicative of a motorway type situation and the context detection information C2 is for example information indicative of a branching type situation '.

The autonomous driving management system 30 can then authorize a rapid autonomous driving mode of the vehicle if the context detection information C1 indicates a motorway type situation and if the context detection information C2 does not indicate a situation branch type '.

On the other hand, as soon as the context detection information C1 no longer indicates a motorway type situation or when the context detection information C2 indicates a branching type situation, the autonomous driving management system 30 deactivates fast autonomous driving mode (and can then switch to an autonomous driving mode at reduced speed, or to a manual driving mode after warning the driver and receiving confirmation thereof, for example).

In another conceivable embodiment, the context detection information (delivered by a visitor) could be information indicative of a given speed limit (or alternatively information indicative of the approach to a toll); such information can then for example be used by a system for controlling the effective speed of the vehicle (for example in the case of an autonomous vehicle, but also in the case of a vehicle with a cruise control function) in order to order a reduction in vehicle speed.

Claims (11)

1. Virtual horizon construction system (vHor), comprising: - a processing unit (12) designed to identify, by analysis of captured data (CAPT) by at least one sensor (2; 4) fitted to a vehicle, events (E,) occurring in an environment of the vehicle; - a storage unit (14) of said events each in association with information identifying the event concerned along a route taken by the vehicle; and - a set (16, 20) for determining at least one characteristic (C1; C2; Ci) of the road environment to be assigned to the journey on the basis of at least two stored events (E,). 2. The system as claimed in claim 1, comprising a unit for determining (16), on the basis of the stored events (E,), of information (11; I2) associated with a characteristic (PROF1; PROF2) of the environment. for a plurality of path points. 3. The system as claimed in claim 2, in which the determination unit is designed to produce a probability associated with said information (11; I2). 4. System according to claim 2 or 3, comprising an automaton comprising internal registers (R) and arranged to successively traverse the points of the path, to update said internal registers (R) according to the information (11; I2 ) associated with said characteristic for the current point (t) and producing context detection information (Ci) as a function of said internal registers (R). 5. The system as claimed in claim 4, in which the automaton is designed to produce, for each current point (t), a confidence index associated with the context detection information (Ci). 6. System according to one of claims 1 to 5, in which the information identifying the event is a curvilinear abscissa along the path. 7. The system as claimed in claim 6, in which the storage unit is designed to determine said curvilinear abscissa as a function of a current curvilinear abscissa (s) of the vehicle delivered by an odometer (5). 8. System according to one of claims 1 to 5, in which the information identifying the event is temporal information. 9. System according to one of claims 1 to 8, comprising a driving assistance system (30) designed to activate or deactivate a functionality according to the characteristic of the determined road environment (C1; C2). 10. The system of claim 9, wherein the functionality is an autonomous driving functionality. 11. Method for constructing a virtual horizon (vHor), comprising the following steps: - identification by means of a processing unit (12), by analysis of captured data (CAPT) by at least one sensor (2; 4) fitted to a vehicle, of events (E,) occurring in a vehicle environment; - storage of said events (E,) each in association with information identifying the event concerned along a route taken by the vehicle; - determination of at least one characteristic (C1; C2; Ci) of the road environment to be assigned to the journey on the basis of at least two stored events (E,). 1/1 -1000 0 200 L — .l —- I—> Fig. 3