FR3078565A1 - METHOD AND APPARATUS FOR CONSTRUCTING ENVIRONMENTALLY ADAPTIVE ROAD GUIDANCE INSTRUCTIONS - Google Patents

Abstract

The invention relates to a method for producing environmentally-friendly route guidance instructions, comprising steps of: - determining a path between a starting position and a desired destination, from a database cartographic; - acquisition of an image in the direction of vision of the individual; searching for at least one visible point of interest on the acquired image; - assessing the visibility of the point of interest on the acquired image through a level of visibility; - generation of a guidance instruction highlighting a direction to take relative to the point of interest; and - transmitting the guidance instruction to the individual. The invention also relates to a device for generating adaptive route guidance instructions to the environment.

Description

Technical field to which the invention relates

The present invention relates generally to guidance systems, and in particular to guidance systems integrated in motor vehicles.

It relates more particularly to a process for developing route guidance instructions that are adaptive to the environment.

It also relates to a device for generating route guidance instructions adaptive to the environment, comprising a cartographic database, a navigation and geolocation system, a computer memory adapted to record each journey made, a processing module adapted to receive and combining elements from the cartographic database, the navigation and geolocation system and the computer memory, an image sensor adapted to be directed in the direction of vision of an individual, and an interface adapted to transmit an indication to the individual.

TECHNOLOGICAL BACKGROUND

Satellite navigation and positioning systems are particularly effective and popular for determining the route to be taken, particularly for a driver of a vehicle.

The advantage compared to a paper map is considerable, in particular because the position of the individual is updated in real time. Most navigation systems display the directions to follow on maps corresponding to schematic representations of the vehicle environment.

However, in certain situations, the direction to take is not clear, especially in the case where a large number of different directions are available to the driver.

Document W02006132522 then knows a solution consisting in superimposing an image acquired by a camera filming the road in front of the vehicle and the directions to follow. The combination of the real-time environment image and navigation directions allows for quicker and easier interpretation of the navigation instructions to follow.

However, the proposed solution requires special attention from the driver since it forces him to regularly look at the image display screen, which momentarily distracts him even when he arrives in a potentially dangerous environment.

Object of the invention

The present invention proposes to improve the development of guidance instructions by using points of interest present in the environment of a vehicle.

More particularly, according to the invention, there is proposed a method for developing route guidance instructions adaptive to the environment, comprising steps of:

- determination of a route between a starting position and a desired destination, from a cartographic database;

- acquisition of an image in the direction of vision of the individual;

- search for at least one visible point of interest on the acquired image;

- evaluation of the visibility of the point of interest on the acquired image by means of a visibility level;

- generation of a guidance instruction highlighting a direction to take relative to the point of interest; and

- transmission of the guidance instruction to the individual.

Thus, thanks to the present invention, the guidance instructions are based on points of interest of the environment, which then make it possible to avoid the difficulties of interpretation of these instructions.

There is also provided in the method a step of determining a familiarity index of at least one segment of said journey for said individual.

Advantageously, the guidance instructions are then adapted as a function of the individual's knowledge of the route. For example, if the individual is passing on a segment of the route that he has already met, the guidance instructions that will be transmitted to him will be minimal. On the other hand, if it is on a completely new part of the route, the guidance instructions will be specified thanks to the points of interest present in the environment of the vehicle.

Other non-limiting and advantageous characteristics of the process for preparing road guidance instructions according to the invention, taken individually or in any technically possible combination, are the following:

- it is planned to store said journey in a computer memory and the familiarity index is determined from a frequency, a number of passages on at least part of the segments of said journey and a recent character of the passages on said part of the segments of said path, which frequency, number of passages and recentness of the passages are determined from paths stored in the computer memory;

- It is planned to store in the computer memory a parameter associated with said journey, which parameter is linked to the individual or to the manner in which said journey was taken by said individual, and in which said frequency and said number of passages are modulated by at least one factor related to said parameter;

- Said parameter includes the presence or absence of guidance instructions during a passage on the path segment during a past path stored in the computer memory, and / or the age of the individual and / or a measure of the difficulty of the driving task when passing over the path segment during a past path stored in the computer memory;

- the point of interest is a temporary element of the environment identified on the acquired image, which is called dynamic point of interest;

- the point of interest is a static element read in the cartographic database, which is called static point of interest;

- it is also provided in the process:

- in the research stage, to find at least one static point of interest visible on the acquired image and listed in the cartographic database and at least one dynamic point of interest visible on the acquired image;

- at the evaluation stage, to determine the level of visibility of said static point of interest and the level of visibility of the dynamic point of interest;

- a step of comparing the level of visibility of the static point of interest and the level of visibility of the dynamic point of interest;

a step of selecting a useful point of interest from among the static point of interest and the dynamic point of interest, said useful point of interest having the greatest level of visibility; and

- in the generation step, generate said guidance instruction so as to highlight the direction to take relative to the point of useful interest;

- in the absence of transmission of guidance instructions for a determined duration, the method also comprising steps of:

- selection of an informative point of interest in the environment;

- generation of an information instruction from the informative point of interest, said information instruction not inducing any maneuver on the part of the individual; and

- transmission of the information instruction to the individual;

- the level of visibility is determined from the readability and contrast of the point of interest;

- the transmission of the guidance instruction includes the statement of a voice indication;

- if the familiarity index indicates that the environment is familiar to the individual, the vocal instruction is silenced as long as no guidance deviation is observed; and

- There is also provided in the process a step of issuing a request for confirmation of guidance on the part of the individual.

The invention also provides a device for developing route guidance instructions adaptive to the environment as described in the introduction and characterized in that the processing module is suitable for implementing the method mentioned above.

Detailed description of an exemplary embodiment

The description which follows with reference to the appended 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 provides a schematic representation of the passenger compartment of a motor vehicle equipped with a device for generating route guidance instructions adaptive to the environment according to the invention; and

- Figure 2 shows an example of a guide unit according to the invention.

In FIG. 1, the interior of a motor vehicle 1 is schematically represented equipped with a device for generating route guidance instructions that are adaptive to the environment.

This device comprises a guide unit 5, an image sensor 10 and an interface 11 adapted to transmit an indication to an individual (here the driver of the motor vehicle 1).

The image sensor 10 comprises at least one camera, here an infrared camera. The image sensor 10 can further comprise in this case an infrared emitting element (not shown here) irradiating the areas of the road targeted by the aforementioned camera (in particular so that the acquisition device can operate even in the event of night driving).

The image sensor 10 is adapted to be directed in the direction of vision of the driver, that is to say towards the front of the vehicle.

Each camera is arranged in the passenger compartment of the motor vehicle 1 so as not to obstruct the driver's field of vision.

The image sensor 10 is for example located in the passenger compartment of the vehicle, in a region close to an upper part of the windshield, so as to acquire images of the road located in front of the vehicle.

The interface 11, which is recalled that it is designed to transmit an indication to the driver, preferably includes a system for transmitting an audio signal 12. In addition, it here comprises a screen 14. As a variant, it could not include only one or the other of these two elements 12, 14.

The audio signal transmission system 12 is adapted to transmit a voice indication to the individual. It is arranged in the passenger compartment, at a distance from the individual such that the latter can clearly hear the voice indications communicated. In practice, these are the speakers installed in the vehicle for listening, for example to the radio.

Screen 14 is adapted to transmit a visual indication to the individual. Screen 14 is located in a visually accessible area, without effort for the individual. The screen 14 is for example positioned on the dashboard of the vehicle 1. In practice, this is the display screen installed in the central console of the vehicle, for example for controlling the radio.

As a variant, the screen 14 considered may be the screen of a head-up display device (sometimes called a combiner).

The guidance unit 5 is shown in detail in FIG. 2. It includes a cartographic database 20, a navigation and geolocation system 22, a computer memory 24 (hereinafter called "memory

") And a processing module 25.

The cartographic database 20 includes two-dimensional or even three-dimensional map data, and in particular the locations (longitude and latitude) of the roads in a given space (for example in Europe). The cartographic database 20 also includes additional information such as the shape of the buildings, the location of petrol stations and places characteristic of the environment (for example historic monuments or rivers). The cartographic data is provided to be able to be read by the processing module

25.

The navigation and geolocation system 22 is suitable for determining the current position of the motor vehicle in space and for determining a path between the current position (or starting position) of the motor vehicle 1 and the desired destination, taking into account the data stored in the cartographic database 20. The navigation and geolocation system 22 can for example be a navigation and positioning system by satellite (or “GPS” according to the acronym commonly used). The current position of the vehicle and the route are provided so that it can be read by the processing module 25.

The route determined by the navigation and geolocation system 22 is stored in the memory 24. The memory 24 also stores the previous trips made. The memory 24 also stores various parameters relating to the individual and the manner in which he took the route. All the elements stored in the memory 24 are capable of being read by the processing module 25. These elements will be detailed in the remainder of this presentation.

The processing module 25 is adapted to receive and combine the various elements coming from the cartographic database 20, from the navigation and geolocation system 22 and from the memory 24. The processing module 25 is also adapted to receive and analyze the images recorded by the image sensor 10. The processing module 25 is also adapted to transmit data to the audio signal transmission system 12 and to the screen 14 in order to communicate guidance indications to the individual. In practice, this processing module 25 is formed by a microcontroller.

The device for generating guidance instructions described above makes it possible to implement the method described below.

According to the invention, when the vehicle 1 is started, the processing module 25 determines, during a first step, the path that the motor vehicle 1 must take.

For this, the current (starting) position is determined using the navigation and geolocation system 22. As a variant, the individual can specify a starting position different from the position at which he is currently located by manually entering the position of target departure. For example, the individual can record the target starting position via screen 14.

The individual then specifies a desired destination. For example, the desired destination can be entered on screen 14.

The processing module 25 combines the starting position, the desired destination as well as the map data corresponding to the geographic area concerned. The processing module 25 transmits this information to the navigation and geolocation system 22 which then generates a route.

The determined route is stored in the memory 24. Thus, in the memory 24, there is a database register in which the routes previously taken by the motor vehicle 1 are stored.

From the routes previously taken, the processing module 25 calculates, during a second step, a familiarity index for each of the segments constituting the route that the driver wishes to take.

Here, a segment of the journey can be defined as a portion of the road that lies between two successive intersections.

The familiarity index for each segment of the journey is statistical in nature. It allows to know if the driver has a good knowledge or not of the road which he will take. The underlying idea is indeed, if he knows the route, to silence the voice instruction or not to provide the individual with information of which he is already aware. Conversely, if he does not know the route (or that he has limited knowledge of it), the idea is to provide him with all the necessary information.

The familiarity index could be obtained simply, for example by asking the driver whether he knows the route.

However, here the familiarity index is determined on the basis of a frequency, a number of passages of the vehicle on each segment of the journey as well as the recent nature (or not) of the passages of the vehicle on each segment of the journey. The frequency, the number of passages and the recent passage on each segment are determined from the paths previously carried out, which are stored for this purpose in memory 24.

To make this familiarity index more reliable, its calculation may only take into account journeys made by the driver himself (and not take into account journeys made by third parties). For this, the register stored in memory 24 will have to associate with each trip the identity of the driver who has made this trip.

To make this familiarity index even more relevant, the frequency and the number of passages are preferably modulated by at least one parameter linked to the driver and / or to the manner in which the driver has taken the segment of the journey. For this, the register stored in the memory 24 will have to associate with each path the parameter or parameters considered.

In a first example, this parameter can for example be the presence or absence of guidance instructions during a previous passage on the segment of the route considered.

Thus, if no guidance instruction was issued during the previous passage of the vehicle on the route segment, this route segment will be considered as known to the driver. The parameter linked to the guidance instructions will then be determined so as to increase the familiarity index.

In a second example, the parameter could be the age of the individual.

Thus, in the case of a young driver, the instructions will have to be more detailed so that, during his first driving experiences, questions about the directions to follow do not disturb him. The parameter in this case will be determined so as to decrease the familiarity index.

In a third example, the parameter could be a measure of the difficulty of the driving task when passing on the path segment during the past path.

For example, the measure of the difficulty of the driving task can be assessed from micro-vibrations on the steering wheel. Micro-vibrations on the steering wheel indeed characterize an individual's state of stress and testify to a momentary loss of control of the vehicle. The driving task in this case is assessed as difficult (in comparison for example with other parts of the journey on which no indication of a possible state of stress is detected). The parameter will then be determined so as to decrease the familiarity index.

These examples can be combined so that several parameters are considered in the calculation of the familiarity index.

If the familiarity index indicates that the environment and the segment of the journey are familiar to the individual, the guidance instructions are minimized and for example reduced to only visual instructions (the voice instructions being silenced as long as no deviation from the guidance is observed). They can correspond, for example, only to the announcement of the direction to follow if the driver seems to be mistaking the direction (for example if he does not put his turn signals in the direction to take).

In the case where the familiarity index indicates that the environment and the path segment are little or not known to the individual, the processing module 25 will implement other calculation steps, in order to be able to state guidance instructions easier for the driver to understand than a simple direction to follow. These guidance instructions will be based on the environment as seen by the driver. As examples, these instructions may announce to the driver:

- follow the yellow vehicle which, at 100 meters, turns left, or

- turn after the blue advertising panel, or

- to follow the only direction which is displayed on a panel with a green background (when all the other directions are displayed on panels with white backgrounds).

For this, in a third step, the image sensor 10 acquires an image in the direction of vision of the individual, that is to say towards the front of the vehicle.

Then, during a fourth step, the processing module 25 analyzes the acquired image. In particular, the processing module 25 evaluates the visual environment when approaching the place of the next maneuver. The processing module 25 searches the acquired image for at least one visible point of interest. This point of interest corresponds to a visual element useful for guidance. A statistical model, of the deep learning algorithm type (or “deep learning” according to the Anglo-Saxon designation of origin commonly used), makes it possible to identify said point of interest.

The point of interest can correspond to a temporary element of the environment identified on the acquired image. In this case, we speak of a dynamic point of interest. For example, a dynamic point of interest can be a pedestrian or a cyclist or a motor vehicle spotted in the acquired image.

The point of interest can also be a static element of the environment. It is read in the cartographic database 20. In this case, we speak of a point of static interest. A static point of interest can for example be a bridge or a building which appears on the acquired image and which is listed in the cartographic database 20.

Once the point of interest is located on the acquired image, the processing module 25 evaluates the visibility thereof by means of a visibility level. The visibility of the point of interest is integrated into the process of developing route guidance instructions in order to offer the individual only easily visible elements of the environment. In particular, the evaluation of the visibility makes it possible to detect possible problems of masking of elements usually used for route guidance (and possibly present in the cartographic database 20). The masking problems can for example arise from particular weather conditions, abundant vegetation, the presence of a truck in front of the vehicle, etc.

The level of visibility is determined from the readability and contrast of the point of interest. Different levels of visibility are established using a contrast sensitivity function. The sensitivity function can take into account the spatial frequency of a pattern in an image and the contrast of this pattern in the image. The pattern can for example be a letter of the alphabet appearing on an indication panel.

The spatial frequency measures the degree of repetition of the pattern in a part of the image. Contrast analysis identifies the pattern visible to the human eye in the image.

Visibility levels allow you to establish predetermined thresholds from which the point of interest will be considered visible by the individual.

The readability of the point of interest also takes into account the distance at which the point of interest is located in order to assess its visibility.

The readability is also based on the definition of a visual zone in which the point of interest will be considered to be visible to the individual. The processing module 25 evaluates the location of the point of interest in the visual area determined using an algorithm. If the point is outside the visual zone, the visibility level will be considered low.

This evaluation can for example be carried out according to the use of the Easterman criterion. As part of this criterion, the visual area is defined angularly, between - 60 and +60 degrees horizontally and between -10 and +10 degrees vertically around the longitudinal axis of the vehicle (these angles may vary depending on the vehicle speed).

As a variant, an algorithm present in the processing module 25 can determine a beam of trajectories a priori visible to the driver. The trajectories actually visible to the driver will be those present in a region defined by the angle of vision of the driver. The visual area in which the point of interest used will be selected will then be defined from the determined trajectory beam, the visual area being superimposed on the driver's viewing angle.

Anyway, at this stage, the processing module 25 is able to assign to the point of interest considered a level of visibility which will be all the more higher than it will be visible to the driver.

The search for a point of interest in the acquired image can lead to the identification of several points of interest, for example at least one static point of interest and at least one dynamic point of interest. The level of visibility is then evaluated for each static point of interest and for each dynamic point of interest. Visibility levels are then compared. A "useful" point of interest, among the static and dynamic points of interest, is selected as that corresponding to the highest level of visibility.

Once the useful point of interest has been identified, the processing module 25 generates a guidance instruction highlighting a direction to take relative to this point of interest.

The generated guidance instruction is then transmitted to the driver so that he can perform the next maneuver. The guidance instruction is transmitted in advance of the maneuver to be performed.

The processing module 25 converts the guidance instruction according to the appropriate transmission form. The guidance instruction can be transmitted to the driver via the audio signal transmission system 12 (for example loudspeakers) and / or to the screen 14.

The transmission of the guidance instruction to the individual can thus for example consist in transmitting to the loudspeakers a signal such that the driver hears the direction to take in the form of a voice indication.

As a variant or in addition, the transmission of the guidance instruction may consist in transmitting to the screen 14 a signal such that it displays the direction to take.

The transmission of the guidance instruction may be adapted according to the driver, in particular according to individual preferences. For example, an individual may prefer a representation of the guidance instructions in the form of a map while another individual may prefer a guidance procedure corresponding to a series of instructions. The preference for the representation of the guidance instructions can be specified when the vehicle is started by choosing from a drop-down menu offered, for example, on screen 14.

It is understood that if the familiarity index indicates that the environment along the part of the route taken is well known to the driver, an absence of guidance instructions can be observed for a fairly long period (corresponding to the course of the segments of known route). During this time, the driver may wonder about the proper functioning of the route guidance instruction generation device, which can result in tension regarding the conduct to be adopted.

In order to avoid this inconvenience, the device is provided for announcing information messages intended for the driver, so that the latter understands that the device is still active as well as to confirm the general orientation.

For this, the processing module 25 selects a point of interest, said to be informative, visible on the acquired image. For example, an informative point of interest could be the presence of a river or a monument. An information instruction is generated from this informative point of interest. This information instruction is transmitted to the individual. However, this instruction of information does not induce a navigation maneuver on the part of the individual. The instruction could for example note the passage of vehicle 1 next to the Eiffel Tower.

The processing module 25 also makes it possible to generate driving adaptation incentives. The processing module 25 can generate driving instructions as a function of the driving parameters of the individual, for example as a function of the speed of the vehicle. For example, if the road segment ahead has a very sharp turn and the vehicle is in an overspeed situation, the driving adaptation instruction will recommend slowing down before the turn.

The processing module 25 can also receive a request for confirmation of guidance from the individual. For example, the individual can voice a request which is recorded by the audio signal acquisition system. The voice request can be accompanied by a gestural indication recorded by an image sensor directed towards the individual. The individual can for example ask for confirmation on the direction to take by showing this direction of the arm.

The processing module 25 is then adapted to analyze the request for guidance confirmation and generate a response to the request. The response includes confirmation or a new statement of the guidance instruction.

The implementation of this variant would require the installation of an additional image sensor directed towards the driver and designed to record any gestural indication made by the driver. This variant would also require the use of a microphone positioned near the driver and designed to record a confirmation request formulated by the driver.

As a variant, several cameras may be placed in the passenger compartment of the vehicle so as to capture images of the road from different angles of view.

The invention is not limited to the embodiment illustrated in the figures.

So, for example, it could be implemented on a pedestrian’s mobile phone. So, the pedestrian will have to hold his phone so that his camera acquires images of the environment and that his screen displays the direction to follow in the form of a message based on the environment as seen by the camera.

Claims (14)

1. Method for developing route guidance instructions adaptive to the environment, comprising steps of: - determination of a route between a starting position and a desired destination, from a cartographic database (20); - acquisition of an image in the direction of vision of the individual; - search for at least one visible point of interest on the acquired image; - evaluation of the visibility of the point of interest on the acquired image by means of a visibility level; - generation of a guidance instruction highlighting a direction to take relative to the point of interest; and - transmission of the guidance instruction to the individual. 2. Method according to claim 1, also comprising a step of determining a familiarity index of at least one segment of said path for said individual. 3. Method according to claim 2, in which it is planned to store said path in a computer memory (24) and in which the familiarity index is determined from a frequency, from a number of passages over a part at least segments of said path and of a recent nature of the passages on said part of the segments of said path, which frequency, number of passages and recent character of the passages are determined from paths stored in the computer memory (24). 4. Method according to claim 3, in which provision is made to store in the computer memory (24) a parameter associated with said route, which parameter is linked to the individual or to the manner in which said route has been taken by said individual. , and wherein said frequency and said number of passes are modulated by at least one factor related to said parameter. 5. The method as claimed in claim 4, in which said parameter comprises the presence or absence of guidance instructions during a passage on the path segment during a past path stored in the computer memory (24), and / or the age of the individual and / or a measure of the difficulty of the driving task when passing over the path segment during a past path stored in the computer memory (24). 6. Method according to any one of claims 1 to 5, wherein the point of interest is a temporary element of the environment identified on the acquired image, which is called dynamic point of interest. 7. Method according to any one of claims 1 to 6, in which the point of interest is a static element read in the cartographic database (20), which is called static point of interest. 8. Method according to claims 6 and 7, in which it is provided: - at the research stage, to find at least one static point of interest visible on the acquired image and listed in the cartographic database (20) and at least one dynamic point of interest visible on the acquired image ; - at the evaluation stage, to determine the level of visibility of said static point of interest and the level of visibility of the dynamic point of interest; - a step of comparing the level of visibility of the static point of interest and the level of visibility of the dynamic point of interest; a step of selecting a useful point of interest from among the static point of interest and the dynamic point of interest, said useful point of interest having the greatest level of visibility; and - in the generation step, generate said guidance instruction so as to highlight the direction to take relative to the point of useful interest. 9. Method according to any one of claims 1 to 8, in which, in the absence of transmission of guidance instruction for a determined period, the method also comprising steps of: - selection of an informative point of interest in the environment; - generation of an information instruction from the informative point of interest, said information instruction not inducing any maneuver on the part of the individual; and - transmission of the information instruction to the individual. 10. Method according to any one of claims 1 to 9, wherein the level of visibility is determined from the readability and the contrast of the point of interest. 11. Method according to any one of claims 1 to 10, in which the transmission of the guidance instruction includes the statement of a voice indication. 12. The method of claims 2 and 11, wherein, if the familiarity index indicates that the environment is familiar to the individual, the voice instruction is killed as long as no guide deviation is observed. 13. Method according to any one of claims 1 to 12, also comprising a step of issuing a request for confirmation of guidance from the individual. 14. Device for generating environment-friendly route guidance instructions, comprising: - a cartographic database (20), - a navigation and geolocation system (22), - a computer memory (24) adapted to record each journey made, a processing module (25) adapted to receive and combine elements coming from the cartographic database (20), from the navigation and geolocation system (22) and from the computer memory (24), - an image sensor (10) adapted to be directed in the direction of vision of an individual, and - an interface (11) adapted to transmit an indication to the individual, characterized in that the processing module (25) is adapted to implement a method according to any one of claims 1 to 13. 1/1