Method for determining the trajectory of a vehicle

Abstract

The invention relates to a method for determining the trajectory of a vehicle travelling on a roadway, the method being implemented by a device comprising at least one computer, characterised in that it comprises: - obtaining a set of data relating to the path of the vehicle, comprising at least: - high-definition map data and - an itinerary of the vehicle; - detecting, on the basis of the data obtained, at least one intersection on the itinerary of the vehicle; - determining an intersection model on the basis of the intersection detected and the set of data obtained; - determining, on the basis of the determined intersection model and the itinerary of the vehicle in the determined intersection model, a trajectory to be taken by the vehicle in the vicinity of the intersection and in order to cross the intersection.

Description

Method for determining the trajectory of a vehicle Technical field

[0001] The present disclosure relates to a method for determining the trajectory of a vehicle, more particularly, a connected autonomous or semi-autonomous vehicle. Prior art

[0002] It has been proven that a vehicle equipped with a driver assistance system can significantly improve the comfort and safety of road users. By using a set of sensors, such as cameras, such an autonomous or semi-autonomous vehicle can understand its surroundings and act accordingly. This allows it to warn the driver of dangerous situations, or to make driving easier.

[0003] For example, accident prevention systems are known. Similarly, systems are known that allow slower vehicles to be safely overtaken on expressways, thereby maintaining a more stable driving speed and smoothing traffic flow.

[0004] However, the vehicle's onboard sensor suite doesn't always allow an autonomous or semi-autonomous vehicle to fully understand its surroundings. Typically, signs such as road markings can be erased, or a road sign can be hidden by a bulky vehicle or even damaged.

[0005] These problems limit the use of driver assistance systems in autonomous or semi-autonomous vehicles in urban journeys, where signaling is both more complex and more difficult than in the countryside or on fast roads such as motorways.

[0006] More specifically, in complex intersections, the arrangements are specific and non-standardized. There are thus a multitude of different intersections, whose rules are often specified by several signage elements. On the contrary, we sometimes find intersections where signage is absent or missing. In these conditions, the information provided by the car's various sensors does not always allow us to understand the intersection in its entirety.

[0007] Under these conditions, autonomous or semi-autonomous vehicles based on prior art are not sufficiently efficient.

[0008] In special cases such as driving an autonomous or semi-autonomous vehicle on a motorway, it is also known to use high-definition map data to enable precise driving adapted to the geometry of the motorway. However, this use is limited to very simple cases such as driving on a motorway. Summary

[0009] The present disclosure improves the situation by proposing a method for determining the trajectory that an autonomous or semi-autonomous vehicle must take around an intersection and for crossing it, in particular by adding high-definition map data to the information from the sensors.

[0010] A method for determining the trajectory of a vehicle traveling on a roadway is proposed, the method being implemented by a device comprising at least one computer, comprising: obtaining a set of data relating to the journey of the vehicle, comprising at least: o high-definition cartographic data, o a route of the vehicle, detecting, from the data obtained, at least one intersection on the route of the vehicle, determining an intersection model from the detected intersection and the set of data obtained, determining, from the determined intersection model and the route of the vehicle in the determined intersection model, a trajectory to be taken by the vehicle around the intersection and to cross the intersection.

[0011] In a variant, the data set obtained further comprises data from sensors on board the vehicle, such as an image acquisition device, and the method further comprises: a verification of the optimization of said trajectory to be taken by the vehicle from the data from on-board sensors, and a rectification of said trajectory, if said trajectory is not optimal.

[0012] Alternatively, the obtained data set comprises at least: data relating to the destination of the vehicle, data relating to a departure lane of a route of the vehicle, such as the lane in which it is geographically positioned, and the route of the vehicle is deduced from the data relating to the destination and the departure lane of the vehicle, and high definition map data.

[0013] In one embodiment, determining an intersection model from the detected intersection comprises: accessing an intersection crossing history database to determine whether intersection crossing history data exists for said intersection, and o if there is crossing history data for said intersection, the intersection model corresponds to the detected intersection, o if there is no crossing history data for said intersection, determining a category of the intersection from among a plurality of predetermined categories.

[0014] In a variant, the determination of a category of the intersection is carried out by the application of a predefined grouping model, previously trained on a learning database comprising at least histories of vehicle trajectories of intersection crossings from high-definition cartographic data, and preferably augmented with static and dynamic data of these intersections from on-board sensors.

[0015] In one embodiment, the method comprises reinforcing the determination of the trajectory, by manually correcting or validating said determined trajectory.

[0016] In one variant, said vehicle is equipped with an autonomous or semi-autonomous driving system, characterized in that the set trajectory of the driving system is the determined trajectory.

[0017] Alternatively, the trajectory is further determined according to a predefined driving profile.

[0018] In one variant, the vehicle is said to be “connected”, that is to say equipped with a vehicular communication system allowing it to communicate and receive a set of information, characterized in that the set of data obtained includes information received by said vehicular communication system.

[0019] Alternatively, the vehicular communication system is a V2X type device or a variation of the V2X type such as V2V or V2N.

[0020] In one embodiment, the vehicle is equipped with at least one sensor characterized in that the data set comprises information from said at least one sensor.

[0021] Alternatively, the data set includes static data, such as horizontal or vertical signage, lane geometry, or the arrangement of certain road or lane-related features.

[0022] Alternatively, the dataset includes dynamic data, such as traffic lane congestion, traffic light status, the precise position of the vehicle in its lane, or the time.

[0023] According to another object, a computer program product is provided, comprising code instructions for implementing the method according to the preceding description, when executed by a computer. Brief description of the drawings

[0024] Other features, details and advantages will become apparent upon reading the detailed description below, and upon analyzing the attached drawings, in which:

[0025] Figure 1 shows a schematic representation of the process flow according to one embodiment.

[0026] Figure 2a schematically illustrates a 2D representation of a model of a first intersection in which the method takes place according to one embodiment.

[0027] Figure 2b schematically illustrates a 2D representation of a second model of the first intersection.

[0028] Figure 3 schematically illustrates a 2D representation of a model of a second intersection.

[0029] Figure 4 schematically illustrates a vehicle of the method according to one embodiment. Description of the embodiments

[0030] In order to prepare for an autonomous or semi-autonomous vehicle to cross an intersection, the vehicle must be able to determine in advance a trajectory to be taken. Reference is now made to Figure 1, which schematically represents a flowchart of the progress of the method for determining the trajectory of the vehicle according to one embodiment, and to Figure 4 which represents such a vehicle according to one embodiment of the method. This method is implemented by a device 400 for determining the trajectory of the vehicle, comprising at least one computer 401, for example of the processor, microprocessor, microcontroller, programmable logic circuit (FPGA, etc.) type, and / or a specialized integrated circuit (ASIC, etc.). The computer 401 is advantageously embedded in the vehicle.Alternatively, the computer 401 may be located remotely from the vehicle and be in remote communication with an on-board communication device 403 and / or vehicle components 404, 405, 406. The device may further comprise a memory 402, storing code instructions executed by the computer 401 to be able to implement the method. The memory 402 may also store one or more pre-trained models described in more detail below to be able to determine a type of intersection that a vehicle is approaching, and a trajectory to follow in this intersection. The memory 402 may be a non-volatile electronic memory, an optical hard disk, etc.

[0031] In order to determine a vehicle's trajectory in an intersection, it is first necessary to determine in which intersection the vehicle must follow the trajectory.

[0032] An intersection is a place where two or more roads join or cross, regardless of the angle(s) of the axes of these roadways. When the order of priority of vehicles is not obvious in the intersection, their passage is often organized by signaling elements. Such an intersection is thus considered complex when it includes specific and non-standardized arrangements specified by signaling elements. Complex intersections thus differ from roundabouts or Indonesian-style intersections.

[0033] The method firstly comprises obtaining 110 by the computer 401, a set of data relating to the route that the vehicle will take or is taking. This set advantageously comprises high-definition cartographic data. They can be retrieved from a memory 402 local to the vehicle or from a server, where appropriate, the vehicle being equipped with a communication device 403 configured to communicate at least to the server.

[0034] High-definition maps (HD maps) are highly accurate maps that include details not found in traditional, standard-definition maps. These maps include identification of individual traffic lanes. They can be accurate to within a decimeter and often include signage information. Their accuracy makes it possible to differentiate between lanes that make up a road, rather than individual roads, a common limitation with traditional maps.

[0035] High-definition maps can, for example, include descriptive elements of traffic rules in the lanes, such as information concerning the direction of travel in the lanes, but also priority or reserved lanes such as bus or taxi lanes. They also include various elements related to the road and the lanes, such as signs, whether on the side or above the road, streetlights linked to road lighting, physical separators such as concrete separations or rails, etc. These elements particularly help with the precise geolocation of the vehicle in the lane, especially in the context of urban canyons which significantly degrade GNSS geolocation.

[0036] The data set also includes a vehicle route, i.e. the sequence of roads it will take. The route can thus be communicated directly to the computer 401, for example by communication with a server.

[0037] Alternatively, the vehicle or the on-board computer integrates a receiver 404 of satellite geolocation data, for example of the GNSS or GPS type, hereinafter referred to as the GNSS receiver, and the data set simply comprises the destination provided by the driver and a starting point for a route, such as the position of the GNSS receiver 404, which can then deduce a route. Similarly, the computer 401 receives the destination by communication with a server or by the driver, and the starting point by a simple on-board GNSS beacon 404, then takes charge of calculating the route, advantageously from high-definition maps.

[0038] The method then comprises detecting 120 the intersection in which to determine the trajectory, from the data set.

[0039] It is noted that it is possible for the intersection to be detected 120 before the vehicle even approaches it, or even from the beginning of the journey. For example, for an autonomous or semi-autonomous vehicle configured so that the driver does not have to intervene, the route is necessarily known from start to finish. It is thus possible, from high-definition map data, to detect 120 in advance the intersections that will be encountered during the journey following the planned route.

[0040] In a variant, the intersection is detected 120 when the vehicle is physically near it, the obtained data set 110 can also include information from any sensors on board the vehicle. The vehicle can then retrieve information on the road so that the detection is more reliable. In addition to the position of the vehicle retrieved by satellite and compared with the high-definition maps, images from on-board image acquisition devices 405, such as on-board cameras, and processed by algorithms for processing images acquired by such cameras 405 for the recognition of markings or signaling elements, can be transmitted to the computer 401 to obtain information relating to the markings or signaling that define the intersection. Further, lidars 406 can also inform the computer of the 2D or 3D geometry of the intersection.

[0041] This is the map data that includes a sufficient majority of information about the environment of the route's intersections. The various sensor data can, if necessary, augment the information present on the high-definition map, but are limited to the physical environment close to the vehicle that equips them.

[0042] It is also noted that the sensor data can be used, for example, to update the map data when content detected by the sensors differs from the map data, such as when a road sign has been changed. The computer can then update the map information stored locally in the vehicle or transmit this information to a server with the communication device.

[0043] The data in the dataset can be categorized into two groups: static data, which is data that does not change or hardly changes, such as the geometry of the road lanes, or certain signaling elements such as road markings or traffic signs, and dynamic data, which changes over the time of a journey, such as traffic lane congestion, vehicle position or certain signaling elements such as a traffic light.

[0044] Some static data in the data set, such as some of the map data, may advantageously be pre-stored in the vehicle so that it can be accessed at any time. However, this requires that they be kept updated regularly so as not to provide the computer with outdated information. For example, an update may be performed automatically if the vehicle is connected to the internet via a mobile communication device 403 or Wi-Fi.

[0045] Advantageously, the vehicle may be equipped with a vehicular communication system 403 in order to receive data via said communication system. For example, equipped with a V2X (for “Vehicle-to-Everything”) type communication system, the vehicle could communicate and receive part of the data.

[0046] V2X vehicular communication systems can be broken down into several specific communication cases, such as with a network server in V2N (for "Vehicle-to-Network" in English), another vehicle in V2V (for "Vehicle-to-Vehicle" in English), a pedestrian in V2P (for "Vehicle-to-Pedestrian" in English), the road infrastructure in V2I (for "Vehicle-to-lnfrastructure" in English), etc.

[0047] With a server, via the internet in V2N, transmitting up-to-date map data to it, it is possible to obtain map data including dynamic data, for example the congestion of a lane of the route in real time.

[0048] With another vehicle connected in V2V, it is also possible to obtain data concerning the physical environment of the third-party vehicle, or for example the time spent recently crossing an intersection on the route.

[0049] By these vehicular communication systems, the method advantageously comprises obtaining 110 data concerning an intersection, in real time, optionally from sensors, even before the vehicle is physically there.

[0050] Obtaining a set of varied and numerous data advantageously allows for reliable and complete detection of an intersection.

[0051] Advantageously, high-definition map data makes it possible to know the exact geometry of an intersection, which greatly facilitates its detection 120.

[0052] After its detection 120, the method comprises the determination 130 of an intersection model corresponding to the detected intersection 120. This model is thus a digital representation of the detected intersection 120 which can be translated into several forms.

[0053] For example, the determined model 130 may be a simplified or detailed version of a set of data characteristic of the intersection. It may advantageously comprise a 2D or 3D reconstruction of the detected intersection 120 and its surroundings, allowing a trajectory to be located there. It can also advantageously include all the traffic rules in the intersection and its surroundings.

[0054] The characteristics of the determined model 130 can be mainly classified into two categories: geometry characteristics, which include the physical boundaries of the lanes and the road, elements related to the road, etc. and rule characteristics, which include the traffic rules related to the different types of signaling elements, the topology of the intersection, etc.

[0055] Advantageously, it is possible to use a database of intersection crossing histories to determine 130 a model of the detected intersection 120. Indeed, by aggregating the intersection crossing history data of the same vehicle and advantageously of other vehicles, it is possible to constitute a large intersection database and models to which the data of the detected intersection 120 can be compared.

[0056] If in the database, we find historical data of crossing the detected intersection 120, the associated intersection model then corresponds, effectively, to the detected intersection 120.

[0057] If, on the contrary, there is no history of crossing the detected intersection 120 in the database, the method then comprises the determination 131 of a category to which to attach the detected intersection 120 among the intersection models associated in the database.

[0058] The matching of the detected intersection 120 to a category can be carried out on the similarity of the detected intersection 120 with the intersections associated with the crossing histories of the database.

[0059] Alternatively, it is possible to compare the intersections with each other based on all of their characteristics, and thus categorize them by their similarity.

[0060] Indeed, for example, by grouping intersections whose geometry is close, whose topology is similar, and whose traffic and priority rules are identical inside, it is possible to determine the category to which the detected intersection 120 belongs, and therefore to determine an intersection model corresponding to the intersection. For example, the determined model may be an average of the models of the intersections in the category, or an average weighted by the similarity with the detected intersection 120.

[0061] Advantageously, the categorization and matching of the intersections of the database and the detected intersection 120 can be carried out using a clustering machine learning algorithm. The clustering of the intersections can thus be done firstly on the geographical position of the intersection, but also from static data such as the marking and geometry of the intersection as well as the traffic rules that result from it. Further, it is also possible that the grouping is carried out on dynamic data, such as the congestion of the lanes in the intersection or simply the time of passage. Such an algorithm effectively allows for the categorization of historical data once trained on this type of data.

[0062] Once the intersection model 130 has been determined, the method comprises determining 140 the trajectory from the model. Preliminarily, the computer determines a starting lane of a trajectory and a destination that the vehicle must follow in the intersection, in order to respect the route. This essentially involves first determining by which lane the vehicle will enter the intersection and in which direction it must head to follow the overall route.

[0063] Generally, if the vehicle is near the detected intersection, the starting lane of the trajectory is the lane in which the vehicle is positioned.

[0064] In a variant where the intersection detection is predictive (where the vehicle is not yet physically close to it), a departure lane can be automatically determined near the intersection, based on the planned route and traffic rules conventions.

[0065] From the route, the calculator deduces the route to take to exit the intersection, in order to follow the route. Advantageously, the exact route to exit the intersection can be known or determined at the same time.

[0066] The method finally comprises determining 140 a trajectory to be taken by the vehicle to cross the intersection.

[0067] From the intersection model it is possible to determine 140 a trajectory starting at a departure lane and in the direction of the destination road.

[0068] The trajectory, however, corresponds to the passage from one lane (departure) to another (exit or arrival) and in particular embodiments, several trajectories are possible in order to cross the intersection by following the route, in particular if the destination road has several lanes.

[0069] Alternatively, the trajectory may also include a lane change to get to the departure lane.

[0070] Alternatively, the determination 140 of the trajectory may further depend on a predetermined driving profile chosen by the driver. For example, a comfortable driving profile may tend to avoid overtaking compared to a normal driving profile when it is not really necessary. Conversely, a sporty driving profile may more often take overtaking trajectories to save travel time.

[0071] Advantageously, the trajectory can be determined 140 using the intersection crossing history database for the detected intersection 120.

[0072] Furthermore, in variants when, for example, the destination road comprises several lanes, the method may advantageously comprise a verification 150 of the determined trajectory before the vehicle takes it. Indeed, during the time elapsed since obtaining the information 110 and until the determination 140 of the trajectory, the environment of the vehicle may have evolved and the initially determined trajectory 140 may not be optimal. In particular, the exit route from the determined trajectory may be less optimal than another possible route.

[0073] We therefore proceed to the verification 150 of the trajectory optimization: mainly using sensors, we verify that the determined model 130 is not obsolete in relation to the current environment of the vehicle. In particular, we verify that the exit lane of the trajectory is the smoothest lane among all the possible exit lanes. For example, we verify 150 using cameras on board the vehicle that the second exit lane, determined 140, is indeed and much less congested than the first exit lane. And particularly, we verify for a trajectory which includes a lane change that this change can be carried out safely.

[0074] In the case where the verification 150 indicates that the determined route is not optimal, the method advantageously comprises the rectification 160 of the determined trajectory 140. The rectification 160 thus modifies the determined trajectory for a rectified trajectory, more optimal in the present environment. For example, if a determined trajectory 140 includes overtaking a congested route, and the verification 150 indicates that the initially congested route is no longer sufficiently congested for the determined trajectory 140 to no longer be optimal, the rectification can modify the determined trajectory for a rectified determined trajectory which avoids the overtaking which has become obsolete and useless.

[0075] Advantageously, the rectification 160 takes into account the viability of a trajectory, in particular if a third-party vehicle would prevent the vehicle from taking a more optimal rectified trajectory.

[0076] Verification 150 and rectification 160 thus take into account the trajectory to be followed in the intersection in real time.

[0077] Even more advantageously, the trajectory can be determined 140 by the application of a reinforcement learning machine model, in which the driver evaluates the determined trajectory 140 advantageously rectified 160. For example, if the trajectory is incorrect, the driver can correct it by taking back the wheel, and reinforce the model by indicating the trajectory which should have been determined.

[0078] Optionally, the driver can also manually validate the determined trajectory, for example passively, i.e. not take the wheel for it modify - since not correcting it amounts to approving it - or actively, with an interaction which consists of rating or approving it.

[0079] Machine learning, clustering, and reinforcement learning models can be advantageously pre-trained on historical intersection crossing data. For example, during a preliminary training phase, a database of intersection crossings is built with one or more vehicles whose trajectories are tracked, for example using a GNSS beacon and high-definition map data, as well as an inertial unit to measure the speed, acceleration, and orientation of the vehicle. This database is then used to pre-train the learning models. Historical crossing databases can also include the state, or values, of sensors onboard a vehicle when crossing different intersections.

[0080] Advantageously, crossing an intersection and strengthening the model can update the intersection crossing database, so as to store the driver's driving habits for certain trajectories. Thus, as corrections are made to the same trajectory, the determined trajectory 140 will become increasingly closer to the driver's usual trajectory.

[0081] Verification 150 and rectification 160 thus allow the vehicle to follow an optimal trajectory, including when the vehicle is in unexpected environmental conditions.

[0082] Alternatively, the reinforcement learning model can be advantageously optimized to determine a trajectory in real time, when the dataset additionally includes onboard sensor data. In this way, verification 150 and rectification 160 are not necessary, since the trajectory is therefore always optimized for the real-time situation.

[0083] Reference is now made to Figure 2a, which schematically illustrates a 2D representation of an intersection model. In one embodiment, the method determines the trajectory for the vehicle 201 to cross the intersection from its position in the right lane 210 to one of the oncoming lanes 220 and 221.

[0084] Several trajectories are possible among the lane changes at the intersection so that the vehicle goes straight ahead: the vehicle can stay 202 in the right lane, that is to say, go from the right lane 210 before the intersection to the right lane 220 of the road ahead, or the vehicle can change 203 from the right lane 210 before the intersection to the left lane 221 of the road ahead.

[0085] The trajectory is determined 140 according to the model which includes the traffic rules in the intersection: staying in the right lane is therefore the preferred trajectory.

[0086] In Figure 2b, the intersection model is different, although it is physically the same intersection. This is because the model takes into account lane congestion, and it differs from the model in Figure 2a because the right lane 210 is congested in the intersection.

[0087] The trajectory is also determined 140 according to the driver's driving comfort and the preferred trajectory is therefore overtaking 203 the congestion by passing into the left lane 221.

[0088] Advantageously, the model of the intersection includes the approaches to the intersection, the determined trajectory 140 can thus anticipate the intersection. As illustrated in FIG. 2b, the overtaking trajectory 231 can thus begin before the intersection so that the vehicle 201 goes directly into the left lane 211.

[0089] Reference is now made to Figure 3, which schematically illustrates a 2D representation of a model of a second intersection. In this embodiment of the method, the vehicle 201 has as its destination the left road 320 and 321.

[0090] Similarly, two trajectories are possible to reach the left road: a first 331 from the left lane 311 to the right lane 320 of the destination road, and a second 332 from the left lane 311 to the left lane 321 of the destination road, the right lane 310 not allowing the left road to be taken according to the traffic rules in the intersection.

[0091] Taking into account the approaches to the intersection in the model thus makes it possible to determine a more natural trajectory that respects traffic rules. Indeed, since it is necessary to start the trajectory from the left lane 311, a first part 330 of the trajectory is to place oneself on said left lane 311, and finally to begin crossing 331 or 332 of the intersection.

[0092] Advantageously, if, for example, the right lane 320 of the destination road is congested near the exit of the intersection, the trajectory is determined 140 taking this into account and the left lane 321 will then be favored at the exit.

[0093] By reinforcement, when a driver usually passes through the intersection when it is congested, for example at the same times, the trajectory 332 determined 140 with the left lane 321 at the exit may be preferred by default.

[0094] Advantageously, the vehicle 201 may include a computer enabling the implementation of the various stages of the method. This computer may be embedded in the vehicle or remote.

[0095] In particular, the vehicle 201 equipped with a communication system, for example of the V2X type, can transmit data to a remote computer which then responds with the results.

Claims

Claims 1. Method for determining the trajectory of a vehicle traveling on a roadway, the method being implemented by a device comprising at least one computer, characterized in that it comprises: obtaining a set of data relating to the journey of the vehicle, comprising at least: o high-definition cartographic data, comprising an identification of the traffic lanes and descriptive elements of the traffic rules in the lanes, o a route of the vehicle, o data from sensors on board the vehicle, a detection, at least from the high-definition cartographic data and the route of the vehicle, of at least one intersection on the route of the vehicle, a determination of an intersection model from the detected intersection and the set of data obtained, comprising characteristics of the geometry of the intersection and of traffic rules in the intersection, a determination,from the determined intersection model and the vehicle's route in the determined intersection model, a trajectory to be taken by the vehicle around the intersection and to cross the intersection, a verification of the optimal nature of the trajectory to be taken by the vehicle, in the current environment of the vehicle, from data from on-board sensors, and a rectification of said trajectory, if said trajectory is not optimal in the current environment of the vehicle., 2. Method according to claim 1, in which the obtained data set comprises at least: data relating to the destination of the vehicle, data relating to a departure lane of a route of the vehicle, such as the lane in which it is geographically positioned, and the route of the vehicle is deduced from the data relating to the destination and the departure lane of the vehicle, and high definition map data.

3. A method according to any preceding claim, wherein determining an intersection model from the detected intersection comprises: accessing an intersection crossing history database to determine whether intersection crossing history data exists for said intersection, and o if there is crossing history data for said intersection, the intersection model corresponds to the detected intersection, o if there is no crossing history data for said intersection, determining a category of the intersection from among a plurality of predetermined categories.

4. Method according to the preceding claim in which the determination of a category of the intersection is carried out by the application of a predefined grouping model, previously trained on a learning database comprising at least histories of vehicle trajectories of intersection crossings from high definition cartographic data, and preferably augmented with static and dynamic data of these intersections from on-board sensors.

5. Method according to any one of the preceding claims, characterized in that it comprises a reinforcement of the determination of the trajectory, by the manual correction or validation of said determined trajectory.

6. Method according to any one of the preceding claims for which said vehicle is equipped with an autonomous or semi-autonomous driving system, characterized in that the set trajectory of the driving system is the determined trajectory.

7. Method according to any one of the preceding claims for which the trajectory is further determined according to a predefined driving profile.

8. Method according to any one of the preceding claims for which the vehicle is said to be “connected”, that is to say equipped with a vehicular communication system allowing it to communicate and receive a set of information, characterized in that the set of data obtained comprises information received by said vehicular communication system.

9. Method according to the preceding claim in which the vehicular communication system is a V2X type device or a variation of the V2X type such as V2V or V2N.

10. Method according to any one of the preceding claims for which the vehicle is equipped with at least one sensor characterized in that the data set comprises information from said at least one sensor.

11. Method according to any one of the preceding claims, characterized in that the data set comprises static data, such as horizontal or vertical signage, the geometry of traffic lanes, or the arrangement of certain elements related to the road or traffic lanes.

12. Method according to any one of the preceding claims, characterized in that the data set comprises dynamic data, such as congestion. of a traffic lane, the status of a traffic light, the precise position of the vehicle in its lane, or the time.

13. Computer program product, comprising code instructions for implementing the method according to any one of the preceding claims, when executed by a computer.

14. Device for determining the trajectory of a connected vehicle comprising at least one computer, characterized in that said determination device is configured to implement the method according to one of claims 1 to 12.

Images