FR3130229A1 - Method and device for trajectory control of an autonomous vehicle - Google Patents

Abstract

The present invention relates to a method and a device for trajectory control of an autonomous vehicle (11). For this purpose, a visibility zone around the autonomous vehicle (11) is determined and represented by first segments. A traffic lane (102) forming an intersection with a traffic lane (101) on which the autonomous vehicle (11) travels is represented by segments. A point of intersection between the first segments and the second segments is determined, this intersection point being located at the limit of the zone of visibility of the autonomous vehicle (11) at the level of the second traffic lane (102). Second data representative of a space occupied by a moving object (12) moving along the second lane of travel from the point of intersection is determined. The trajectory of the autonomous vehicle (11) is controlled according to the second data. Figure for abstract: Figure 1

Description

Method and device for trajectory control of an autonomous vehicle

The present invention relates to methods and devices for controlling an autonomous vehicle, for example an autonomous motor vehicle. The present invention also relates to a method and a device for controlling the trajectory of an autonomous vehicle. The invention also relates to a method and a device for planning the trajectory of an autonomous vehicle.

Technology background

With the development of autonomous vehicles, needs in terms of planning the trajectory to follow, in particular according to the geometry of the road and/or the environment around the autonomous vehicle, have appeared.

One of the problems associated with the determination of the trajectory relates to the lack of visibility of the autonomous vehicle, part of the environment of which is masked by objects, such as for example constructions, vegetation, vehicles present at the edge of a traffic lane used by the autonomous vehicle.

The visibility problem is all the greater when the autonomous vehicle is approaching an intersection, in particular when the traffic lane on which the autonomous vehicle is traveling is not a priority.

A lack of visibility for the autonomous vehicle then poses safety problems for the passengers of the autonomous vehicle and for other road users, with an increased risk of collision, in particular in an urban environment.

Summary of the present invention

An object of the present invention is to solve at least one of the drawbacks of the prior art.

Another object of the present invention is to improve the safety and control of an autonomous vehicle.

According to a first aspect, the present invention relates to a method for controlling the trajectory of an autonomous vehicle, the autonomous vehicle traveling on a first traffic lane of a road environment approaching an intersection with a second traffic lane of the road environment, the method comprising the following steps:

- receipt of initial data representative of the road environment;

- determination of a first set of first segments from at least part of the first data, the first segments forming a limit surrounding a zone of visibility around the autonomous vehicle;

- determination of a second set of second segments from at least part of the first data, the second segments being representative of the second traffic lane;

- determination of a point of intersection between a first segment of the first set and a second segment of the second set;

- determination of second data representative of a space occupied by a mobile object moving along the second traffic lane from the point of intersection with a speed corresponding to a maximum speed authorized on the second traffic lane, the second data comprising spatial information representative of successive positions taken by the mobile object along the second traffic lane from the point of intersection and time information associated with the spatial information;

- control of the trajectory of the autonomous vehicle according to the second data.

According to a variant, the successive positions are determined for each temporal instant of a set of successive temporal instants forming a temporal interval comprised between a current instant and a determined maximum instant, the temporal information comprising each temporal instant associated with each position of the moving object.

According to another variant, the maximum instant is determined as a function of a comfort braking time of the autonomous vehicle, the comfort braking time being determined from a current speed of the autonomous vehicle and a deceleration value comfort of the autonomous vehicle.

According to an additional variant, the moving object being represented by a polygon, the space occupied is determined for each successive position of the moving object as a function of a space covered by the polygon during a time interval starting at the time instant associated with each successive position and ending at the determined maximum instant.

According to yet another variant, the space occupied is represented by a single polygon covering all of the successive positions taken by the moving object over the time interval.

According to an additional variant, the control of the trajectory of the autonomous vehicle comprises:

- a determination of a trajectory of the autonomous vehicle according to which the autonomous vehicle passes the intersection before the mobile object; Or

- a determination of a trajectory of the autonomous vehicle comprising a stop of the autonomous vehicle before the intersection so as to let the mobile object pass before crossing the intersection.

According to another variant, the first data representative of the road environment are received from:

- At least one sensor on board the autonomous vehicle; and or

- at least one sensor arranged in the road environment via a wireless connection; and or

- at least one other vehicle via a wireless connection; and or

- at least one remote device via a wireless connection.

According to a second aspect, the present invention relates to a device for controlling the trajectory of an autonomous vehicle, the device comprising a memory associated with a processor configured for the implementation of the steps of the method according to the first aspect of the present invention.

According to a third aspect, the present invention relates to an autonomous vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the present invention.

According to a fourth aspect, the present invention relates to a computer program which comprises instructions adapted for the execution of the steps of the method according to the first aspect of the present invention, this in particular when the computer program is executed by at least one processor.

Such a computer program can use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

According to a fifth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for the execution of the steps of the method according to the first aspect of the present invention.

On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium may comprise a storage means, such as a ROM memory, a CD-ROM or a ROM memory of the microelectronic circuit type, or even a magnetic recording means or a hard disk.

On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or hertzian radio or by self-directed laser beam or by other ways. The computer program according to the present invention can in particular be downloaded from an Internet-type network.

Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the method in question.

Brief description of figures

Other characteristics and advantages of the present invention will emerge from the description of the particular and non-limiting examples of embodiments of the present invention below, with reference to the appended FIGS. 1 to 5, in which:

schematically illustrates a road environment in which an autonomous vehicle moves, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a zone of visibility of the autonomous vehicle of the , according to a particular and non-limiting embodiment of the present invention;

schematically illustrates the space occupied by a mobile object moving in the road environment of the , according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a device configured to control the trajectory of the autonomous vehicle from the , according to a particular and non-limiting embodiment of the present invention;

illustrates a flowchart of the different steps of a method for controlling the trajectory of the autonomous vehicle of the , according to a particular and non-limiting embodiment of the present invention.

Description of the examples of realization

A method and a device for controlling the trajectory of an autonomous vehicle will now be described in the following with reference in conjunction with FIGS. 1 to 5. The same elements are identified with the same reference signs throughout the description. who will follow.

According to a particular and non-limiting embodiment of the present invention, the control of the trajectory of an autonomous vehicle, implemented by one or more processors of one or more computers of the on-board system of the autonomous vehicle, comprises the reception of first data representative of the road environment in which the autonomous vehicle travels. The autonomous vehicle travels for example on a first traffic lane of the road environment and is approaching an intersection with a second traffic lane of the road environment. A first set of first segments is determined from at least part of the first data received, these first segments delimiting a zone of visibility around the autonomous vehicle, that is to say a zone covered by the detection sensors of object or analysis of the environment embedded in the autonomous vehicle. A second set of second segments is determined from at least a portion of the first data received, the second segments being representative of the second traffic lane forming an intersection with the first traffic lane. A point of intersection is determined or calculated between a first segment of the first set and a second segment of the second set, this point of intersection being located at the limit of the zone of visibility of the autonomous vehicle at the level of the second traffic lane . Second data representative of a space occupied by a moving object moving along the second traffic lane from the point of intersection with a speed corresponding to a maximum authorized speed on the second traffic lane is determined. These second data advantageously comprise spatial information representative of the prediction of successive positions taken by the mobile object along the second traffic lane from the point of intersection and temporal information associated with the spatial information (for example the temporal instant at which the mobile object will be present in each position and/or the duration of the space around each position occupied by the mobile object). This second data is then used to control the trajectory of the autonomous vehicle in order to avoid any collision with the moving object.

The mobile object corresponds to any object that can move along the second traffic lane and corresponds for example to a vehicle. The existence of this mobile object is not proven. The assumption of the presence of such a moving object at the limit of the visibility zone moving with maximum speed makes it possible to calculate the trajectory of the first moving object arriving at the intersection from a temporal point of view. The analysis of such a hypothetical situation by the autonomous vehicle makes it possible to avoid the risks of collision with such a moving object if it existed, the determination of the existence not being able to be implemented because the zone of visibility being restraint.

Such a method makes it possible to improve the safety of the passengers of the autonomous vehicle and of other road users by limiting the risks of collision with a moving object arriving from an area not visible from the autonomous vehicle.

The following vocabulary will be used in the rest of the description:

- path: a path corresponds to a geometric object representing the spatial displacement of a vehicle without considering speed. The representation of the path and its discretization are therefore independent of time, such a representation being for example arbitrary (fixed or determined number of points) or determined by a length between each point;

- trajectory: a trajectory is a geometric object representing the spatial and temporal movement of a vehicle. The representation of a trajectory and its discretization are directly dependent on time: each point of a trajectory is advantageously associated with a time at which the position will be reached;

- path/speed pair: a path/speed pair corresponds to the association of a speed to be respected (or setpoint speed) at each point of the path, such an association also being called speed profile on the path. A path/speed pair is for example transformed into a trajectory by resampling the points of the path so that each point of the trajectory corresponds to the position reached after having traversed the path for a given time interval while following the speed profile.

There schematically illustrates a road environment 1 in which an autonomous vehicle 11 moves, according to a particular and non-limiting embodiment of the present invention.

There illustrates a portion of the road environment 1 in which the vehicle 11 travels. This environment corresponds for example to an urban environment. According to the particular and non-limiting example of the , the vehicle 11 is approaching a crossroads or an intersection between a first traffic lane 101 on which the autonomous vehicle 11 travels and a second traffic lane 102 crossing the first traffic lane 101 or leading to the first lane traffic 101.

The first traffic lane 101 is for example represented by the center of the lane 110 (corresponding to the path followed by the vehicle 11). The second traffic lane 102 is for example represented by the center of the lane 120 (corresponding for example to the path followed by a moving object, for example a vehicle 12, moving on this second traffic lane 102).

The second traffic lane 102 corresponds for example to a priority lane or road with respect to the first traffic lane 101. This means that any mobile object moving on this second traffic lane has priority of passage at the level of the intersection relative to any vehicle moving along the first traffic lane 101.

According to the example of , the traffic rule applying to the intersection, corresponding to the intersection of the first traffic lane 101 and the second traffic lane 102, corresponds to the so-called right priority rule. Thus, any mobile object 12 arriving from the right of the autonomous vehicle 11 (according to the direction of movement of the autonomous vehicle) has priority over the autonomous vehicle to pass the intersection.

The vehicle 11 advantageously corresponds to an autonomous vehicle. An autonomous vehicle corresponds to a vehicle equipped with a successful driver assistance system ensuring control of the vehicle which is able to drive in its road environment with limited intervention from the driver, or even without intervention from the driver. A vehicle authorizing such an autonomous driving mode must have an autonomous driving level at least equal to 2, whether in the classification published by the federal agency responsible for road safety in the USA which includes 5 levels or in the classification published by the International Organization of Automobile Manufacturers which includes 6 levels.

The vehicle 11 corresponds for example to a vehicle with a heat engine, an electric vehicle or a hybrid vehicle (combining heat engine and electric motor).

The vehicle 10 advantageously follows a route determined in the environment 1, corresponding for example to the path 110 which corresponds to the center of the first lane 101, this route being for example calculated from a set of data comprising for example the current position of the vehicle 11 and a destination. According to a variant, the data further comprises data for mapping the environment 1 of the vehicle 11. The position of the vehicle 11 is for example obtained via a satellite location system, for example a GPS system (from the English “ Global Positioning System” or in French “Global Positioning System”). Such a system is for example integrated into the vehicle 11, for example implemented by a computer of the on-board system of the vehicle 11, or by a mobile device (for example a smart phone) on board the vehicle 11 and communicating with the vehicle 11 by radio link (for example in Bluetooth® or Wifi®). The destination is for example entered by the driver of the vehicle 11 into a route calculation system via a tactile graphical interface or a voice-activated interface. Such a system is for example implemented by a computer of the on-board system of the vehicle 11, or by a mobile device (for example a smart telephone) on board the vehicle 11 and communicating with the vehicle 11 by radio link. The mapping data is for example received from a remote server, for example as the vehicle 11 moves. According to another example, the mapping data is stored in the memory of a system on board the vehicle 11 and /or in memory of the mobile device.

The vehicle 11 advantageously obtains a set of first data representative of the road environment 1 in which the vehicle 11 is moving. The first data includes for example:

- data on the presence of static or dynamic object(s), for example located on the edge of traffic lanes, (for example constructions such as buildings or houses 13, 14, 15, 16, vehicles, street furniture, vegetation) in the environment of the vehicle 11, these data comprising for example information on the location and dimensions of the footprint on the ground;

- data associated with the road environment, such as for example information on speed limits, on the presence of traffic signs, traffic lights (with for example the status of the traffic light), information on road traffic in the environment 1, on the presence of works, on the climatic conditions, that is to say any information or data likely to have an impact on the traffic conditions of the vehicle 11 and on the rules of behavior to be adopted by the vehicle 11 and/or the other road users.

The environment data, or at least a part of them, are for example obtained from one or more sensors on board the autonomous vehicle 11. Such sensors are associated with or form part of one or more detection systems of object on board the vehicle 11, the data obtained from this or these sensors making it possible, for example, to determine the nature or the type of the detected objects (construction, vegetation, vehicles, street furniture, the type of the object being for example determined by classification or by implementing artificial intelligence). This or these object detection systems are for example associated with or included in one or more driving assistance systems, called ADAS system(s) (from the English "Advanced Driver-Assistance System" or in French " Advanced driver assistance system”).

The sensor(s) associated with these object detection systems correspond, for example, to one or more of the following sensors:

- one or more millimeter wave radars arranged on the vehicle, for example at the front, at the rear, on each front/rear corner of the vehicle; each radar is adapted to emit electromagnetic waves and to receive the echoes of these waves returned by one or more objects, with the aim of detecting obstacles and their distances vis-à-vis the vehicle 10; and or

- one or more LIDAR (s) (from the English "Light Detection And Ranging", or "Detection and estimation of the distance by light" in French), a LIDAR sensor corresponding to an optoelectronic system composed of a transmitter device laser, a receiver device comprising a light collector (to collect the part of the light radiation emitted by the emitter and reflected by any object located on the path of the light rays emitted by the emitter) and a photodetector which transforms the light collected as an electrical signal; a LIDAR sensor thus makes it possible to detect the presence of objects located in the light beam emitted and to measure the distance between the sensor and each object detected; and or

- one or more cameras (associated or not with a depth sensor) for the acquisition of one or more images of the environment around the vehicle 10 located in the field of vision of the camera or cameras.

According to a variant, the first data, or at least part of it, is for example obtained from sensors arranged in the environment and/or from vehicles circulating in the environment and/or from a remote device (for example a “cloud” server (or “cloud” in French)) via a V2X type communication system (from the English “Vehicle to Everything” or in French “Véhicule vers tout”). According to another variant, the first data is obtained both from the V2X communication system and from the sensor or sensors on board the vehicle 11.

A communication system of the V2X type comprises in particular a set of communication modes, including a vehicle-to-vehicle communication mode called V2V (vehicle-to-vehicle), a vehicle-to-pedestrian communication mode called V2P ( from the English "vehicle-to-pedestrian"), and a vehicle-to-infrastructure communication mode V2I (from the English "vehicle-to-infrastructure"), within the framework of a network infrastructure using communication technologies such than the ITS G5 (from English "Intelligent Transportation System G5" or in French "Système de transport intelligent G5") in Europe or DSRC (from English "Dedicated Short Range Communications" or in French "Communications dedicated to short range") in the United States of America, both of which are based on the IEEE 802.11p standard, or the technology based on cellular networks called C-V2X (from the English "Cellular - Vehicle to Everything" or in French " Cellular – Vehicle to everything”) which is based on 4G based on LTE (from English “Long Term Evolution” or in French “Evolution à longue terme”) and soon 5G.

The autonomous vehicle 11 thus receives a set of first data relating to the presence of objects (positions and dimensions for example), such as constructions 13 to 16 according to the example of the , masking or obscuring part of the road environment 1 according to the point of view of the autonomous vehicle 11.

These first data make it possible in particular to define one or more concealed zones, that is to say not visible from the autonomous vehicle 11.

For example, the presence of an occulted or non-visible zone 130 appears on the . This zone 130 results from the presence of a building 13 located on the right side of the first traffic lane 101. The presence of the building 13 thus reduces the visibility of the autonomous vehicle, that is to say the visibility of the driver of the vehicle 11 as well as the visibility of the sensors on board the autonomous vehicle 11 configured to analyze the environment of the vehicle 11 and supply data on this environment 11 to the computers of the on-board system of the vehicle 11.

The autonomous vehicle 11 advantageously implements a trajectory calculation process comprising a collision avoidance process with one or more mobile objects 12 that could potentially arise or arrive from a concealed zone such as the zone 130.

Knowing the path to follow, the determination of a trajectory amounts to determining acceleration values to be applied, from which result setpoint speed values for the autonomous vehicle 11 to be associated with the points forming the path. The determination of the trajectory is also implemented by taking into account the limits of visibility of the vehicle 11, and the associated risks of collision with a moving object 12 which may emerge from a concealed zone 130.

The determination of the trajectory is also for example implemented by respecting a set of constraints such as a maximum speed for each point of the path that the autonomous vehicle 11 must respect, such a maximum speed determined according to the situation (for example maximum authorized speed, wheel clutter, danger, priority to yield).

The speed regulation is for example implemented by an ADAS system of the autonomous vehicle such as a speed regulation system, for example an adaptive cruise control system, called ACC (from the English "Adaptive Cruise Control ").

A trajectory control process of the autonomous vehicle 11 is advantageously implemented by the autonomous vehicle 11, for example by one or more computers of the on-board system of the vehicle 11. Such a process comprises for example the control of the current speed of the vehicle 11 , through the control of one or more on-board systems such as the ACC system.

In a first operation, first data representative of the road environment 1 are received.

The first data representative of the road environment 1 are for example received from one or more of the following devices:

- one or more sensors (for example LIDAR, radar and/or camera) embedded in the autonomous vehicle 11; and or

- A navigation system embedded in the autonomous vehicle 11 or implemented in a mobile communication device (for example a smart phone, or "Smartphone" in English) connected in wireless communication with the vehicle 11; and or

- one or more sensors (for example one or more cameras) arranged in the road environment 1, these data being received via a wireless connection of the V2I or LTE 4G or 5G type; and or

- one or more other vehicles, these data being received via a wireless connection according to a V2X communication mode for example; and or

- one or more remote devices (for example one or more “cloud” servers, one or more mobile communication devices), these data being received via a 4G or 5G type wireless connection

The motor vehicle 11 thus has, for example, the following information obtained from the first data:

- lanes to which the autonomous vehicle 11 must pay particular attention depending on the situation, such as lane 102 for example, this information being for example obtained from a road map, for example in high definition, and from a on-board situation analysis module whose role is to identify these particular routes, such a module analyzing the data to implement processing or reasoning based on the highway code or using automatic learning mechanisms for this purpose; And

- limits of visibility of the vehicle 11, this information being for example obtained from the various sensors of the vehicle (LIDAR, cameras, etc.), and/or from a cartography and/or from sensors landed from the infrastructure and/or other vehicles.

In a second operation, a first set of first segments is determined from at least part of the first data received during the first operation. The first segments form a limit surrounding a zone of visibility around the autonomous vehicle 11.

There illustrates such a zone of visibility 2, according to a particular and non-limiting embodiment of the present invention.

On the , the visibility zone surrounding the vehicle 11 is delimited by first segments, a part of these first segments being referenced 21 to 25.

Visibility limits are given in the form of a series of dots (black on the ) connected by segments, or polyline, 21 to 25. This series of points is circular, that is to say that the segments form a closed polygon, not necessarily convex, inside which the autonomous vehicle 11 is located. .

In a third operation, a second set of second segments 201 is determined from at least part of the first data (for example different from the first data used to determine the first segments). These second segments are advantageously representative of the second traffic lane 102.

Just like the first segments, each lane studied, for example each lane having priority with respect to the taxiway 101, is given in the form of a sequence of points connected by segments (polyline). For reasons of clarity, only one priority lane is taken into account according to the example of the and some , this channel 102 being represented by only one segment 201.

For each identified study path, the objective is to construct the trajectory of the first non-visible obstacle (called mobile object) able to cross the visible space of the autonomous vehicle 11. Such a mobile object is necessarily located at the visibility boundary in the obscured space 130, and moves at the maximum authorized speed. The assumption is made that the vehicles and other users of road environment 1 respect the highway code, that is to say that the maximum speeds are respected.

In a fourth step, the initial or starting position of an invisible moving object that can cross the trajectory of the autonomous vehicle is determined. This initial position is illustrated by a gray dot 210 on the , such a point being at the limit of visibility of the autonomous vehicle 11.

To identify the initial position, the intersection of the traffic lane 102 (corresponding for example to a priority lane with respect to the traffic lane 101 of the autonomous vehicle 11) with the limits of visibility of the autonomous vehicle 11 is sought.

This search is based on the first and second segments respectively representing the limits of visibility and the taxiway 102. For each pair of segments (S ₁ ,S ₂ ) such that S ₁ is a first segment of the first set corresponding to the limits of visibility and S ₂ a second segment of the second set corresponding to the taxiway 102, it is verified whether the intersection of S ₁ and S ₂ exists.

If so, an intersection between the visibility limits and taxiway 102 exists. In some cases, several points of intersection can be found, for example if a bush or another vehicle limits a small portion of the field of vision of the autonomous vehicle 11.

In these cases, several approaches emerge:

- keep only the intersection point closest to the planned path of the autonomous vehicle: this allows to have only one virtual obstacle to deal with per traffic lane studied; And

- keep each intersection point and generate as many virtual obstacles as intersection points found: this approach requires more calculations and takes longer to implement, even if potentially more complete.

The rest of the description is described with regard to the first approach according to which only the point of intersection closest to the planned path of the autonomous vehicle 11 is kept.

Of course, the invention also relates to the second approach which consists in reproducing the operations described with regard to the single point of intersection 210 for each point of intersection found.

In what follows, the intersection illustrated by point 210 is denoted X _inter .

In a sixth operation, the trajectory followed by the mobile object 12 is determined, generated or calculated.

The trajectory is determined from the maximum speed v _max authorized on the portion of road 102, this maximum speed cue being for example obtained from part of the first data received or obtained during the first operation.

The maximum trajectory of the virtual object 102 is determined as follows, under the assumption of a constant speed, in a curvilinear frame:

Where s(t) represents the curvilinear abscissa reached by the mobile object 12 at time t on the second traffic lane 102, with s _inter the curvilinear abscissa of the point of intersection X _inter projected on the second traffic lane 102 .

According to a variant embodiment, a speed different from the maximum speed v _max is considered for the determination of the trajectory of the mobile object 12. This speed value is for example increased to have a more cautious behavior, and reduced to have a more aggressive (but less safe) behavior.

The positions s reached by the mobile object are calculated for each time of a discrete set of times T = {t ₀ =0, …, t _N-1 =t _max }, containing N points, such that t ₀ =0 corresponds to the current time, and of which we denote the time interval δt between the instant two consecutive instants of indices i and i+1:

.

According to a particular illustrative example, t _max is for example equal to 5 seconds and δt is equal to 0.1 second, which gives N=51 points. This set of times T is advantageously consistent with the planning horizon used in the path planning method of the autonomous vehicle 11 to search for collisions with dynamic obstacles.

The planning horizon (5 seconds according to the example above) is for example fixed.

According to a variant, the planning horizon is variable and depends on the speed of the autonomous vehicle 11 or on the situation. For example, this planning horizon is greater than the braking time t comfortable _braking of the autonomous vehicle 11, which is for example calculated from the speed v _ego and the comfort deceleration d _comf :

A large planning horizon increases anticipation, but requires more processing time.

It is assumed that the known extension of the second taxiway 102 is sufficient to contain all the calculated positions s. This can for example be obtained from the road network by searching for the routes accessible from the second traffic lane 102, using sensors on board the vehicle 11, dismounted and/or mapping for example. It is for example assumed that only one extension of the second taxiway 102 is used. However, in the case of multiple junctions or intersections in the road environment, several possibilities of paths are possible for the mobile object 12. It is then possible to process this particular case by considering several mobile objects, each taking a particular path. The process is thus reiterated for each moving object following a path from the set of possible paths.

For each time t _i of T, the coordinates of each point s(ti) are determined in the two-dimensional 2D space (x,y) of the autonomous vehicle 11. If the second traffic lane 102 is given or obtained under the form of a function linking the curvilinear abscissa directly to the coordinates (x,y), then the calculated values of s are used directly. Otherwise, if a 2D discretization (x,y) of the second traffic lane 102 is known, then the result between two points is interpolated from the calculated values of s.

A trajectory Τ of the mobile object 12 is defined by:

where each point P _i , corresponding to the middle of the rear axle of a conventional vehicle (considering that the mobile object 12 corresponds for example to a vehicle), is reached at time t _i . The orientation θ _i is necessary to represent the mobile object 12 by a polygon which must be oriented correctly. This orientation can for example be deduced from the analytical expression of the second traffic lane 102, if it is available, or by the interpolation carried out. The dimensions of the polygon correspond for example to those used to represent the size of a conventional vehicle.

The previously determined trajectory Τ represents the maximum trajectory (that is to say the fastest) of a masked or occulted moving object. Such a trajectory groups together the furthest positions that the mobile object 12 can reach at each time t _i by following the path 120. Considering this trajectory alone does not make it possible to consider all the possibilities of initial position and speed that could having a moving object masked or occulted, nor the possibility that several moving objects (for example several vehicles) follow each other for example.

To take all these configurations into account, and according to a particular and non-limiting embodiment, it is considered that each position P _i reached by the fastest moving object 12 is occupied by the time t _i (the time at which the position is occupied at the earliest) until time t _max . There is thus obtained a temporal extension of the potential obstacles of the autonomous vehicle 11 along the path 120, which makes it possible to represent all the possible trajectories according to the initial position and speed for the moving object or objects potentially masked or concealed. This also makes it possible, at the level of the constraints imposed on the trajectory planning of the autonomous vehicle 11, to make possible only a passage before the fastest possible trajectory of the mobile object 12.

According to the trajectory planning method used for the autonomous vehicle, the constraint posed by the virtual object 12 is considered in one of the following ways:

- As part of a method where the constraints are represented by polygons at specific times, when comparing the position of the autonomous vehicle and other vehicles at time t _i :

● it is considered that all the positions P _j , j ≤ i of the mobile objects as being occupied by creating a polygon representative of a classic vehicle on each position Pj, as illustrated in the (this has the consequence of increasing the number of polygons in the scene and therefore can potentially lengthen the processing time because there are more polygons when searching for intersections); Or

● a unique polygon covering all the positions P _j , j ≤ i, is created, (this makes it possible to have a unique polygon to process but the construction of this polygon is not necessarily simple in general, in bends for example )

- As part of a method where the constraints are represented by times prohibited at particular positions for the autonomous vehicle 11, each position P _i is associated with the time interval [t _i , t _max ] at which the position is prohibited , and this time interval is exploited during the construction of a collision matrix between the autonomous vehicle 11 and the mobile object 12.

There illustrates the space occupied by the mobile object 12 along the path 120, with two consecutive time instants t ₀ and t ₁ , t ₁ following t ₀ from a temporal point of view.

At time t ₀ corresponding to the current time, the moving object is at point P1 corresponding to X _inter . The mobile object is represented by a polygon 31 (or bounding box) to determine the space occupied by the mobile object at point P1.

At time t ₁ , the moving object is at point P2 corresponding to the first point following point P1 on the trajectory calculated for the moving object, time t ₁ being associated with point P2. The moving object is represented by a polygon 32 to determine the space occupied by the moving object at point P2.

Polygon 31 is kept from time t ₀ to t _max and polygon 32 is kept from time t ₁ to t _max . Each successive position P1, P2, P3, P4 is associated with a polygon representing the space occupied or covered by the mobile object 12 during a time interval beginning at the instant t _i associated with the point considered and ending at t _max .

In the case where a single polygon is used to represent the space occupied by the mobile object, the polygons 31 and 32 form a single polygon.

In a seventh operation, the trajectory of the autonomous vehicle is controlled according to second data representative of the space occupied by the mobile object 12 and determined in the sixth operation. These second data comprise the spatial information representative of successive positions P _i taken by the mobile object along the second traffic lane 102 from the point of intersection P1 and time information t _i (and also t _max according to a variant) associated with spatial information.

In the absence of other vehicles detected by the autonomous vehicle, two scenarios arise:

- either a solution exists to cross the intersection, and it is guaranteed that the passage of the intersection by the autonomous vehicle 11 is possible before any occulted mobile object present in the occulted zone 130 at the current instant t ₀ and circulating at the maximum at the maximum authorized speed; And

- either no solution exists, and a stopping path before the intersection must be determined for the autonomous vehicle 11, which means that the visibility is not sufficient to guarantee the passage of the intersection in complete safety for the autonomous vehicle 11.

Of course, the process described above with regard to FIGS. 1 to 3 is not limited to cross intersection situations. Indeed, the use of a geometric representation for the mobile object makes it possible to adapt to various situations.

For example, the second traffic lane 102 corresponds for example to a lane of a roundabout on which the first traffic lane 101 emerges. According to this example, the mobile object 12 is for example constructed as a virtual object represented by a rounded polygon whose length is also calculated so as to cover the entire length traveled by the mobile object (for example a vehicle) over the time horizon.

This shows the genericity of the above process with respect to situations that may be encountered in urban areas in particular. Indeed, it is possible to process any type of intersection with limited visibility, whatever the source of this visibility limitation (parked vehicles, vegetation, etc.) without having to define a specific mathematical model of the situation. The safety conditions are induced by the representation which varies the constraint over time, which therefore makes it possible to explicitly check whether or not passage is possible given the available visibility.

The process described above is also applicable in the presence of other vehicles detected by the autonomous vehicle 11. In this case, the trajectory of the autonomous vehicle 11 is checked with respect to these detected vehicles as well as to the mobile object 12, the resulting trajectory being adapted to the strongest constraint for the autonomous vehicle 11.

There schematically illustrates a device 4 configured to control the trajectory of an autonomous vehicle, for example the autonomous vehicle 11, according to a particular and non-limiting example embodiment of the present invention. The device 4 corresponds for example to a device on board the vehicle 11, for example a computer.

The device 4 is for example configured for the implementation of the operations described with regard to the to 3 and/or for the implementation of the steps described with regard to the . Examples of such a device 4 include, but are not limited to, on-board electronic equipment such as a vehicle's on-board computer, an electronic computer such as an ECU ("Electronic Control Unit"), a telephone smart phone, tablet, laptop. The elements of device 4, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and/or in discrete components. The device 4 can be made in the form of electronic circuits or software (or computer) modules or else a combination of electronic circuits and software modules. According to different particular embodiments, the device 4 is coupled in communication with other similar devices or systems and/or with communication devices, for example a TCU (from the English “Telematic Control Unit” or in French “Unité Telematics Control System”), for example via a communication bus or through dedicated input/output ports.

The device 4 comprises one (or more) processor(s) 40 configured to execute instructions for carrying out the steps of the method and/or for executing the instructions of the software or software embedded in the device 4. The processor 40 can include integrated memory, an input/output interface, and various circuits known to those skilled in the art. The device 4 further comprises at least one memory 41 corresponding for example to a volatile and/or non-volatile memory and/or comprises a memory storage device which can comprise volatile and/or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

The computer code of the on-board software or software comprising the instructions to be loaded and executed by the processor is for example stored on the memory 41.

According to a particular and non-limiting embodiment, the device 4 comprises a block 42 of interface elements for communicating with external devices, for example a remote server or the “cloud”. Block 42 interface elements include one or more of the following interfaces:

- RF radio frequency interface, for example of the Bluetooth® or Wi-Fi® type, LTE (from English "Long-Term Evolution" or in French "Evolution à long terme"), LTE-Advanced (or in French LTE-advanced );

- USB interface (from the English "Universal Serial Bus" or "Universal Serial Bus" in French);

- HDMI interface (from the English “High Definition Multimedia Interface”, or “Interface Multimedia Haute Definition” in French);

- LIN interface (from English “Local Interconnect Network”, or in French “Réseau interconnecté local”).

Data are for example loaded to the device 4 via the block 42 interface using a Wi-Fi® network such as according to IEEE 802.11, an ITS G5 network based on IEEE 802.11p or a mobile network such as a 4G network (or LTE Advanced according to 3GPP release 10 – version 10) or 5G, in particular an LTE-V2X network.

According to another particular embodiment, the device 4 comprises a communication interface 43 which makes it possible to establish communication with other devices (such as other computers of the on-board system) via a communication channel 430. The interface communication interface 43 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 430. The communication interface 43 corresponds for example to a wired network of the CAN type (from the English " Controller Area Network" or in French "Network of controllers"), CAN FD (from English "Controller Area Network Flexible Data-Rate" or in French "Network of controllers with flexible data rate"), FlexRay (standardized by the ISO 17458 standard) or Ethernet (standardized by ISO/IEC 802-3 standard).

According to an additional particular embodiment, the device 4 can provide output signals to one or more external devices, such as a display screen, one or more loudspeakers and/or other peripherals respectively via interfaces output not shown.

There illustrates a flowchart of the different steps of a method for controlling the trajectory of an autonomous vehicle, for example the vehicle 11, according to a particular and non-limiting example embodiment of the present invention. The method is for example implemented by one or more devices on board the vehicle 11 or by one or more devices 4 of the .

In a first step 51, first data representative of the road environment in which the autonomous vehicle is moving are received.

In a second step 52, a first set of first segments is determined from at least part of the first data, the first segments forming a limit surrounding a visibility zone around the autonomous vehicle.

In a third step 53, a second set of second segments is determined from at least some of the first data, the second segments being representative of the second traffic lane.

In a fourth step 54, a point of intersection is determined between a first segment of the first set and a second segment of the second set.

In a fifth step 55, second data representative of a space occupied by a mobile object moving along the second traffic lane from the point of intersection with a speed corresponding to a maximum speed authorized on the second traffic lane are determined, the second data comprising spatial information representative of successive positions taken by the moving object along the second traffic lane from the point of intersection and time information associated with the spatial information.

In a sixth step 56, the trajectory of the autonomous vehicle is controlled according to the second data.

According to a variant, the variants and examples of the operations described in relation to one of FIGS. 1 to 3 apply to the steps of the method of .

Of course, the present invention is not limited to the exemplary embodiments described above but extends to a method for controlling an autonomous vehicle or to a method for controlling the speed of an autonomous vehicle which would include steps secondary without departing from the scope of the present invention. The same would apply to a device configured for the implementation of such a method.

The present invention also relates to a vehicle, for example automobile or more generally an autonomous land motor vehicle, comprising the device 4 of the .

Claims (10)

Method for trajectory control of an autonomous vehicle (11), said autonomous vehicle (11) traveling on a first traffic lane (101) of a road environment (1) approaching an intersection with a second traffic lane (102) of the road environment (1), said method comprising the following steps:
- reception (51) of first data representative of said road environment (1);
- determination (52) of a first set of first segments (21 to 25) from at least a part of said first data, said first segments forming a limit surrounding a zone of visibility (2) around said autonomous vehicle (11 );
- determination (53) of a second set of second segments (201) from at least a part of said first data, said second segments being representative of said second traffic lane (102);
- determination (54) of a point of intersection (210) between a first segment (23) of said first set and a second segment (201) of said second set;
- determination (55) of second data representative of a space occupied by a mobile object (12) moving along said second traffic lane (102) from said point of intersection (210) with a speed corresponding to a speed maximum authorized on said second traffic lane (102), said second data comprising spatial information representative of successive positions taken by said mobile object (12) along said second traffic lane (102) from said point of intersection (210 ) and temporal information associated with said spatial information;
- control (56) of the trajectory of said autonomous vehicle (11) according to said second data. Method according to Claim 1, for which the said successive positions are determined for each temporal instant of a set of successive temporal instants forming a temporal interval comprised between a current instant and a determined maximum instant, the said temporal information comprising each temporal instant associated with each position of said moving object (12). Method according to claim 2, for which said maximum instant is determined as a function of a comfort braking time of said autonomous vehicle (11), said comfort braking time being determined from a current speed of said autonomous vehicle (11 ) and a comfort deceleration value of said autonomous vehicle (11). Method according to claim 2 or 3, for which, said mobile object (12) being represented by a polygon (31, 32), said occupied space is determined for each successive position of said mobile object as a function of a space covered by said polygon (31, 32) during a time interval beginning at the time instant associated with said each successive position and ending at said determined maximum instant. Method according to Claim 2 or 3, for which the said occupied space is represented by a single polygon covering all the successive positions taken by the said mobile object over the said time interval. Method according to one of claims 1 to 5, for which said control of the trajectory of said autonomous vehicle (11) comprises:
- a determination of a trajectory of said autonomous vehicle (11) according to which said autonomous vehicle passes said intersection before said moving object (12); Or
- a determination of a trajectory of said autonomous vehicle (11) comprising a stop of said autonomous vehicle before said intersection so as to let said mobile object (12) pass before crossing said intersection. Method according to one of claims 1 to 6, for which said first data representative of said road environment are received from:
- at least one sensor on board said autonomous vehicle; and or
- at least one sensor arranged in said road environment via a wireless connection; and or
- at least one other vehicle via a wireless connection; and or
- at least one remote device via a wireless connection. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor. Device (4) for controlling the trajectory of an autonomous vehicle, said device (4) comprising a memory (41) associated with at least one processor (40) configured for the implementation of the steps of the method according to any one of claims 1 to 7. Vehicle (11) comprising the device (4) according to claim 9.