FR3119817A1 - Method and device for determining a trajectory for an autonomous vehicle - Google Patents

Abstract

The invention relates to a method and a device for determining a target trajectory for an autonomous vehicle (10). To this end, several candidate trajectories (101, 102) are determined from first data received from one or more first sensors. Information representative of a steering command is determined from a set of second data received from one or more second sensors on board the autonomous vehicle (10). A first example of a second sensor corresponds to a steering wheel angle sensor and a second example of a second sensor corresponds to a camera having in its field of vision the face of the driver of the autonomous vehicle (10). The target trajectory for the autonomous vehicle (10) is selected from the candidate trajectories (101, 102) based on information representative of a steering command Figure for the abstract: Figure 1

Description

Method and device for determining a trajectory for an autonomous vehicle

The invention relates to methods and devices for determining a vehicle trajectory, in particular an autonomous vehicle. The invention also relates to a method and a device for correcting a setpoint trajectory chosen by a vehicle, in particular an autonomous vehicle. The invention also relates to a method and a device for controlling the trajectory of a vehicle, in particular an autonomous vehicle.

Technology background

With the development of autonomous vehicles, solutions for automatically determining the trajectory that the vehicle must follow have appeared, depending in particular on the destination to be reached, the geometry of the road and/or the environment around the autonomous vehicle.

To ensure the safety and comfort of passengers in a vehicle traveling in an autonomous driving mode, some vehicles carry several systems configured to determine the trajectory to follow. These systems can, for example, be based on different data sets from different sources or sensors, which sometimes results in the determination of several trajectories.

When several candidate trajectories have been determined, the vehicle must make a choice concerning the trajectory to be selected from the list of candidate trajectories determined by each of the systems on board the vehicle, revealing needs in terms of decision support.

An object of the present invention is to provide a solution for selecting a trajectory from among a plurality of candidate trajectories.

Another object of the present invention is to improve the determination of the trajectory to be followed by a vehicle, in particular an autonomous vehicle.

According to a first aspect, the invention relates to a method for determining a target trajectory for a vehicle traveling according to an autonomous driving mode, the method comprising the following steps:

- determination of a plurality of candidate trajectories from first data received from first sensors on board the vehicle;

- determination of information representative of a steering command from second data received from at least one second sensor of a set of second sensors on board the vehicle comprising:
● a steering wheel angle sensor, and
● a camera having a face of a driver of the vehicle in a field of view of the camera;

- selection of the target trajectory among the plurality of candidate trajectories according to the information.

According to a variant, the method further comprises a step of selecting a target trajectory from among the plurality of candidate trajectories according to determined selection criteria, the selection of the target trajectory being prior to the selection of the target trajectory, the target trajectory being different from the setpoint trajectory.

According to another variant, the information corresponds to at least one steering wheel angle value or to one direction of a gaze of said driver.

According to an additional variant, the information corresponds to a combination of first information corresponding to at least one steering wheel angle value and second information corresponding to a direction of gaze of said driver.

According to an additional variant, the direction of the driver's gaze is determined by processing second data representative of at least one image of the driver's face acquired by the camera.

According to another variant, the plurality of candidate trajectories comprises at least two candidate trajectories from a set of candidate trajectories comprising:

- a candidate trajectory determined from first data received from a first sensor corresponding to a camera configured to detect a set of markings on the ground in front of the vehicle;

- a candidate trajectory determined from first data received from a first sensor corresponding to a receiver of a satellite location system and from mapping data of a road environment of the vehicle; And

- a candidate trajectory determined from first data received from at least a first sensor corresponding to an object detection sensor configured to detect another vehicle traveling in front of the vehicle.

According to yet another variant, each candidate trajectory of the plurality of candidate trajectories is different from the other candidate trajectories, the difference resulting from different first sensors from one candidate trajectory to another and/or from a different candidate trajectory determination method candidate trajectory to another.

According to a second aspect, the invention relates to a device for determining a trajectory for a vehicle traveling according to an autonomous driving mode, 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 invention.

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

According to a fourth aspect, the 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 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 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 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 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 invention will emerge from the description of the non-limiting embodiments of the invention below, with reference to the appended figures 1 to 3, in which:

schematically illustrates a plurality of candidate trajectories for a vehicle, according to a particular embodiment of the present invention;

schematically illustrates a device configured to determine a target trajectory for the vehicle of the , according to a particular embodiment of the present invention;

illustrates a flowchart of the different steps of a method for determining a target trajectory for the vehicle of the , according to a particular embodiment of the present invention.

A method and a device for determining a target trajectory for a vehicle traveling according to an autonomous driving mode will now be described in the following with reference in conjunction with FIGS. 1 to 3. The same elements are identified with the same signs of reference throughout the following description.

According to a particular and non-limiting embodiment of the invention, the determination of a target trajectory for a so-called autonomous vehicle, that is to say for a vehicle circulating according to an autonomous driving mode, comprises the determination of several candidate trajectories, each candidate trajectory being for example determined or obtained from a set of first data received from one or more first sensors, the sensors supplying the first data being for example different for the determination of each candidate trajectory. Information representative of a steering command is determined from a set of second data received from one or more second sensors on board the autonomous vehicle. A first example of a second sensor corresponds to a steering wheel angle sensor and a second example of a second sensor corresponds to a camera having in its field of vision the face of the driver of the autonomous vehicle. The information representative of a steering command corresponds for example to an intention of the driver as to the direction he wishes the autonomous vehicle to take. Finally, the target trajectory for the autonomous vehicle is selected from the list of candidate trajectories based on information representative of a steering command.

Such a method offers the advantage of choosing a trajectory from a list of possible (or candidate) trajectories based on an intention of the driver manifested by an action on the steering wheel and/or a direction of gaze. This makes it possible to select the trajectory on a formal or informal decision of the driver who sees the environment in which the autonomous vehicle is circulating, which makes it possible to correct, if necessary, the perception of the environment by the autonomous vehicle resulting from its on-board sensors, a such a perception may be fragmented or erroneous at times.

schematically illustrates a road environment 1 in which a vehicle 10 moves, according to a particular and non-limiting embodiment of the present invention.

There illustrates a road environment 1 in which two different trajectories 101, 102 have been determined for the vehicle 10, or at least two trajectory portions. The paths 101, 102 are for example determined as a function of information on the destination of the path (such a destination being for example entered via a man-machine interface, called HMI) supplied to the system in charge of determining the path or paths, by depending on the current position of the vehicle 10 and depending on information on the road environment 1.

According to the example of , the two trajectories 101, 102 have a common portion before separating along two different paths.

According to a particular example, the road environment 1 corresponds to a motorway and the two trajectories 101, 102 correspond to a lane splitting into two different lanes, for example when the number of lanes of a portion of motorway passes from 2 to 3 lanes, 3 to 4 lanes, 4 to 5 lanes for example.

According to the example of , the vehicle 10 corresponds to a motor vehicle. However, the object of the invention is not limited to motor vehicles, but extends to any type of land vehicle, for example a truck, a bus, a motorcycle.

The vehicle 10 advantageously corresponds to a vehicle traveling in an autonomous or semi-autonomous mode, for example according to a level greater than or equal to 3 according to the scale defined by the American federal agency which has established 5 levels of autonomy ranging from 1 to 5, level 0 corresponding to a vehicle with no autonomy, whose driving is under the full supervision of the driver, and level 5 corresponding to a completely autonomous vehicle. The vehicle 10 thus corresponds, for example, to a vehicle adapted to travel in an autonomous driving mode. The vehicle 10 corresponds to a vehicle equipped with one or more driving assistance systems, called ADAS (from the English “Advanced Driver-Assistance System” or in French “Advanced Driving Assistance System”), providing control of the vehicle 10 which is capable of driving in its environment 1 with limited intervention by the driver, or even without intervention by the driver.

The level 0 of autonomy and the 5 levels of the classification of the federal agency in charge of road safety are listed below:

- level 0: no automation, the driver of the vehicle fully controls the main functions of the vehicle (engine, accelerator, steering, brakes);

- level 1: driver assistance, automation is active for certain vehicle functions, the driver retaining overall control over the driving of the vehicle; cruise control is part of this level, like other aids such as ABS (anti-lock braking system) or ESP (programmed electro-stabilizer);

- level 2: automation of combined functions, the control of at least two main functions is combined in the automation to replace the driver in certain situations; for example, adaptive cruise control combined with lane centering allows a vehicle to be classified as level 2, as does automatic parking assistance;

- level 3: limited autonomous driving, the driver can hand over complete control of the vehicle to the automated system which will then be in charge of critical safety functions; however, autonomous driving can only take place under certain determined environmental and traffic conditions (only on the motorway, for example);

- level 4: complete autonomous driving under conditions, the vehicle is designed to carry out all the critical safety functions on its own over a complete journey; the driver provides a destination or navigation instructions but is not required to make himself available to regain control of the vehicle;

- level 5: completely autonomous driving without driver assistance in all circumstances.

A process for determining a target trajectory for the vehicle 10 is advantageously implemented by the vehicle 10, that is to say by a computer or a combination of computers of the on-board system of the vehicle 10.

In a first operation, several candidate trajectories 101, 102 are determined by the vehicle 10, from first data obtained from first sensors on board the vehicle 10. The number of candidate trajectories 101, 102 determined by the vehicle 10 is greater than or equal to at 2.

Each of the trajectories 101, 102 is called a candidate trajectory in that the trajectories have been calculated or determined and proposed to the vehicle 10, or to one or more computers on board the vehicle 10, so that the vehicle 10 (or the computer(s) (s)) makes a choice on the trajectory to follow among these two candidate trajectories 101, 102.

Of course, the number of candidate trajectories is not limited to 2 (which corresponds to the example of the provided for illustrative purposes only) but expands to any number, e.g. 2, 3, 4, 5 or more candidate trajectories.

Each candidate trajectory 101, 102 is for example obtained or determined from a set of first data from first different sensors for each candidate trajectory. For example, the type of the first sensor(s) collecting the first data to determine, estimate or calculate the candidate trajectory 101 is different from the type of the first sensor(s) collecting the first data to determine, estimate or calculate the candidate trajectory 102.

According to a variant embodiment, each candidate trajectory 101, 102 is determined, estimated or calculated according to a different method and/or system, from the same first data set or from different sets of first data.

The first data are advantageously obtained from first sensor(s) of the same type or from first sensors of different types, these first sensors being advantageously embedded in the vehicle 10.

According to a first example, one of the candidate trajectories, for example the candidate trajectory 101, is determined on the basis of first data obtained from a ground marking detection system. Such a system comprises one or more cameras for acquiring images of the traffic lane taken by the vehicle 10, for example the portion of road located in front and/or on the sides of the vehicle 10. ground marking detection is thus configured to detect the ground markings in the environment of the vehicle 10. The ground markings are also called horizontal signaling and correspond to a set of lines drawn on the ground. Image processing is applied to the images obtained from the camera(s) of the floor marking detection system to determine the presence of lines on the ground and to classify these lines into different categories, for example to determine whether the lines on the ground correspond to shore lines or center lines for example. An example of image processing to detect lines on the ground is for example described in the document WO2017194890A1. The floor marking detection system identifies, for example, the lines in solid line or in dotted line. The candidate trajectory 101 of the vehicle 10 is for example determined from the markings on the ground associated with the traffic lane of the vehicle 10. The set trajectory corresponds to the trajectory that the vehicle 10 must follow when it is traveling in autonomous mode, a such a candidate trajectory 101 being for example represented by a set of parameters supplied to the ADAS system(s) in charge of controlling the vehicle 10 so that the latter circulates in autonomous mode. These parameters include for example:

- data representing values of the steering angle of the vehicle 10, these values varying over time and the movement of the vehicle 10;

- data representative of speed values (for example the instantaneous speed and/or the acceleration) of the vehicle 10, these values varying over time and the movement of the vehicle 10.

The candidate trajectory 101 of the vehicle 10 is for example determined in such a way that the vehicle 10 remains in the middle of its traffic lane, the middle of the lane being determined or calculated from the markings on the ground laterally delimiting this traffic lane.

According to a second example, one of the candidate trajectories, for example the candidate trajectory 102, is determined on the basis of first data obtained from a sensor or receiver of a satellite positioning system and from mapping data of the road environment 1. The vehicle 10 thus determines the candidate trajectory 102 from mapping data of its environment associated with position data of the vehicle 10 obtained for example via a satellite positioning system, for example of the GPS type (from the English “Global Positioning System”, or “Global Positioning System” in French). The mapping data includes, for example, road map(s) data indicating the roads of the road environment of the vehicle 10, allowing the system embedded in the vehicle 10 in charge of determining the candidate trajectory 102 to determine this trajectory candidate 102, knowing the position of the vehicle 10 via the GPS positioning system, the mapping data and the destination of the route of the vehicle 10.

According to a variant embodiment, the candidate trajectory 101 or 102 is obtained based on a combination of ground marking data and mapping and position data.

According to a third example, a candidate trajectory, for example the candidate trajectory 101 or 102 or another candidate trajectory not illustrated on the , is determined based on data representative of the presence of another vehicle detected by the vehicle 10 in its environment 1. To this end, the vehicle 10 also embeds one or more sensors of one or more detection systems of object in the environment of the vehicle 10, the data obtained from this or these sensors making it possible, for example, to determine the speed of the other vehicle preceding, for example, the vehicle 10 as well as the position as a function of time of this other vehicle. 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; 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 acquiring one or more images of the environment around the vehicle located in the field of vision of the camera(s).

According to this third example, the candidate trajectory is determined on the basis of the trajectory of the other vehicle preceding the vehicle 10, the trajectory of the other vehicle being determined or calculated from the first data coming from or received from the sensors of the in-vehicle object detection systems 10.

According to a variant of this third example, a candidate trajectory 101, 102 determined for example via the ground markings and/or the mapping data is refined from the first data received from the sensors of the object detection system(s) of the vehicle 10 to obtain a new candidate trajectory, taking into account the trajectory of the other vehicle.

In a second optional operation, one of the candidate trajectories obtained in the first operation is selected by the vehicle 10 (or the computer or computers in charge of determining the trajectory to be followed), the selected candidate trajectory being called the setpoint trajectory.

This setpoint trajectory is advantageously selected according to determined selection rules, these rules comprising for example one or more of the following rules according to any possible combination:

- as a function of a confidence index associated with each candidate trajectory, the confidence index being for example calculated from a confidence index associated with the first data (for example provided by the first sensor(s) according to the reliability of data acquisition, depending on the situation) and/or from the method used: for example if the markings on the ground are detected with a high level of quality, then the candidate trajectory determined according to this method has a higher level of confidence that the others and conversely if the markings on the ground are detected with a low level of quality (with an ambiguity on a marking on the ground detected) high, then the candidate trajectory determined according to this method has a lower level of confidence than the others; and or

- depending on events detected on the traffic lane associated with a trajectory (for example in the event of work being detected, the method based on road markings is preferred to that based on mapping data, or the method based on the trajectory of the other vehicle preceding the vehicle 10 is preferred to the other methods).

In a third operation, information representative of a steering command is determined, calculated or obtained from second data received from one or more second sensors on board the vehicle 10.

The second sensor(s) correspond to one and/or the other of the following sensors:

- a steering wheel angle sensor; and or

- a camera embedded in the passenger compartment of the vehicle 10 and having the face of the driver of the vehicle 10 in its field of vision, in particular the eyes of the driver.

According to a first exemplary embodiment, the vehicle 10 thus advantageously embeds a steering wheel angle sensor (known as CAV sensor and also called steering angle transmitter) configured to measure the steering wheel angle values.

When the vehicle 10 is traveling in an autonomous driving mode, the system in charge of controlling the direction of the vehicle 10 receives setpoint steering wheel angle values which vary over time, so that the vehicle follows a trajectory determined by the system. in charge of determining the trajectory to follow (for example the setpoint trajectory determined in the second operation).

At any time, the driver of the vehicle 10 can regain control and control over the vehicle 10 to ensure its driving. To do this and according to a particular example, the driver of the vehicle 10 takes the steering wheel of the vehicle 10 in hand and turns it to steer the vehicle 10 in a given direction. When the steering wheel is controlled by the driver, the steering wheel angle sensor measures one or more steering wheel angle values corresponding to the angle(s) imparted by the driver when he turns the steering wheel. The computer(s) responsible for controlling the vehicle detect that the angle value(s) measured by the CAV sensor are different from the setpoint steering wheel angle value(s).

Such a difference makes it possible, for example, to trigger the deactivation of one or more ADAS systems of the vehicle 10 in charge of the automatic control of the vehicle, such as for example the LKA system (from the English “Lane-Keeping Assist” or in French “ Queue Keeping Assistant”).

Such steering wheel angle value(s) different from the setpoint steering wheel angle value(s) correspond to one or more pieces of information representative of the steering command indicating the will of the driver of the vehicle 10 to change direction, for example of following a direction different from the setpoint trajectory determined in the second operation when the latter has been implemented.

According to a second exemplary embodiment, the vehicle 10 embeds one or more cameras acquiring the face of the driver of the vehicle 10. Such a camera corresponds for example to a camera of a system known as the driver monitoring system. , known as the DMS system (from the English "Driver Monitoring System") and also called driver attention monitor or driver fatigue alert, such a system making it possible to monitor the driver's attention and alert the latter when a drowsiness or a drop in attention is detected.

According to a variant, the camera(s) is/are different from that(s) of the DMS system and correspond(s) to one or more cameras dedicated to detecting the driver's gaze to determine in which direction the driver of the vehicle is looking. vehicle 10.

The camera(s) correspond for example to one or more of the following acquisition devices:

- infrared camera ;

- RGB type image acquisition camera (from English “Red, Green, Blue” or in French “Rouge, vert, bleu”);

- image acquisition camera associated with one or more devices (for example one or more LEDs (from the English "Light-Emitting Diode" or in French "Diode electroluminescente") emitting light in the infrared or in the near infrared band.

The computer or computers receiving the second acquisition data from the camera or cameras puts or implements a set of functions ensuring, for example, the tracking of the driver's gaze (“gaze tracking”), the determination or the tracking the posture of the driver's head (from the English "head pose" or "head gaze") and/or the tracking of the face (from the English "face tracking"), which make it possible to determine in which direction the driver of the vehicle 10 looks by processing the image(s) acquired by the camera(s). The detection of the direction of gaze comprises for example the detection of the eyes in the image(s) of the face acquired by the camera(s) and the determination of the direction associated with the gaze of the driver, according to any method known in the art, for example according to the one of the methods described in the document entitled “A review and analysis of eye-gaze estimation systems, algorithms and performance evaluation methods in consumer platforms”, by Anuradha Kar and Peter Corcoran, published on June 21, 2017 in IEEE Access, volume 5.

The determination of the direction of gaze of the driver of the vehicle 10 thus provides an indication as to the direction in which the driver wishes the vehicle 10 to go. Such direction information then corresponds to information representing a direction command indicating the desire of the driver of vehicle 10 to change direction, for example to follow a direction different from the setpoint trajectory determined in the second operation when the latter has been Implementation.

According to a third exemplary embodiment, the vehicle 10 embeds a CAV sensor and one or more cameras configured for the acquisition of images of the face, in particular the eyes, of the driver of the vehicle 10.

According to this third example, the information representative of the direction command is determined from the second data received from the CAV sensor (as described according to the first embodiment example above), from the second data received from the camera (such as described according to the second embodiment) or from the second data received from the CAV sensor and the second data received from the camera.

The information representative of the steering command is thus obtained from the CAV sensor, from the camera or from a combination formed by the CAV sensor and the camera. When the information representative of the steering command is obtained from the combination formed by the CAV sensor and the camera, the information representative of the direction is for example determined from the steering wheel angle and confirmed from the direction of the gaze or vice versa. This variant makes it possible to obtain information representative of the steering command with a high level of confidence when the gaze direction information corresponds to the measurement of the steering wheel angle.

In a fourth operation, a target trajectory is determined from the information representative of direction control determined in the third operation.

When the second operation described above is not implemented, the target trajectory is selected from among the plurality of candidate trajectories. According to this example, the candidate trajectory selected corresponds to that corresponding to the information representative of the direction command, that is to say to the candidate trajectory comprising the point of the road in the direction of the gaze of the driver of the vehicle 10 and /or in the direction indicated by the steering wheel angle measurement.

For example, when the vehicle 10 is traveling on the portion of road common to the trajectories 101 and 102, the candidate trajectory 102 is selected as being the target trajectory if the direction of the driver's gaze is to the right and/or if the measurement of steering wheel angle corresponds to an angle indicating the driver's desire to go to the right.

When the second operation described above is implemented, the target trajectory is selected from the plurality of candidate trajectories. According to this example, the candidate trajectory selected corresponds to that corresponding to the information representative of the direction command. If the information representative of the direction command indicates a direction different from that corresponding to the setpoint trajectory, then the vehicle 10 (or the computer(s) executing the process described) selects the candidate trajectory corresponding to the direction indicated by the information representative of steering control. The vehicle 10 then follows a new trajectory different from the setpoint trajectory selected during the second operation.

If the steering command representative information indicates a direction corresponding to that of the target trajectory, then the target trajectory is confirmed as being the target trajectory and the vehicle 10 continues to follow the target trajectory which corresponds to the target trajectory. .

A target trajectory advantageously corresponds to the trajectory that the vehicle 10 must follow and whose parameters which describe it are transmitted to the computer(s) of the system(s) in charge of controlling the vehicle 10 when the latter is in autonomous driving mode.

schematically illustrates a device 2 configured to determine a target trajectory for a vehicle traveling according to an autonomous driving mode, according to a particular and non-limiting embodiment of the present invention. The device 2 corresponds for example to a device on board the vehicle 10, for example a computer.

The device 2 is for example configured for the implementation of the operations described with regard to the and/or the steps of the process described with regard to the . Examples of such a device 2 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 2, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and/or in discrete components. The device 2 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 various particular embodiments, the device 2 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"), for example via a communication bus or through dedicated input/output ports.

The device 2 comprises one (or more) processor(s) 20 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 2. The processor 20 can include integrated memory, an input/output interface, and various circuits known to those skilled in the art. The device 2 further comprises at least one memory 21 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 21.

According to a particular and non-limiting embodiment, the device 2 comprises a block 22 of interface elements for communicating with external devices, for example a remote server or the “cloud”, other nodes of the ad hoc network. Block 22 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 2 via the interface of block 22 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 2 comprises a communication interface 23 which makes it possible to establish communication with other devices (such as other computers of the on-board system) via a communication channel 230. The interface communication interface 23 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 230. The communication interface 23 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 2 can supply 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.

illustrates a flowchart of the different steps of a method for determining a target trajectory for a vehicle traveling according to an autonomous driving mode, according to a particular and non-limiting embodiment of the present invention. The method is for example implemented by a device on board the vehicle 10 or by the device 2 of the .

In a first step 31, a plurality of different candidate trajectories are determined from first data received from first sensors on board the vehicle 10.

In a second step 32, information representative of a steering command is determined from second data received from at least one second sensor on board the vehicle 10 and corresponding to:

- a steering wheel angle sensor; and or

- a camera having a face of a driver of the vehicle in a field of vision of the camera

In a third step 33, the target trajectory is selected from among the plurality of candidate trajectories determined in the first step as a function of information representative of a direction command determined in the second step.

According to a variant embodiment, the variants and examples of the operations described in relation to the apply to the process steps of the .

Of course, the invention is not limited to the embodiments described above but extends to a method for controlling the trajectory of a vehicle, in particular an autonomous or semi-autonomous vehicle, as well as to the device configured to the implementation of such a process.

The invention also relates to a vehicle, for example an automobile or more generally an autonomous land motor vehicle, comprising the device 2 of the .

Claims (10)

Method for determining a target trajectory for a vehicle (10) traveling in an autonomous driving mode, said method comprising the following steps:
- determination (31) of a plurality of candidate trajectories (101, 102) from first data received from first sensors on board said vehicle (10);
- determination (32) of information representative of a steering command from second data received from at least one second sensor of a set of second sensors on board said vehicle (10) comprising:
● a steering wheel angle sensor, and
● a camera having a face of a driver of said vehicle (10) in a field of view of said camera;
- selection (33) of said target trajectory from among the plurality of candidate trajectories according to said information. Method according to claim 1, further comprising a step of selecting a target trajectory from among the plurality of candidate trajectories (101, 102) as a function of determined selection criteria, the selection of the target trajectory being prior to said selection of the target trajectory, the target trajectory being different from the setpoint trajectory. Method according to claim 1 or 2, for which said information corresponds to at least one steering wheel angle value or to one direction of gaze of said driver. Method according to claim 1 or 2, for which said information corresponds to a combination of first information corresponding to at least one steering wheel angle value and second information corresponding to a direction of gaze of said driver. Method according to Claim 3 or 4, for which the said direction of the driver's gaze is determined by processing second data representative of at least one image of the driver's face acquired by the said camera. Method according to one of Claims 1 to 5, for which the said plurality of candidate trajectories (101, 102) comprises at least two candidate trajectories from a set of candidate trajectories comprising:
- a candidate trajectory determined from first data received from a first sensor corresponding to a camera configured to detect a set of markings on the ground in front of said vehicle;
- a candidate trajectory determined from first data received from a first sensor corresponding to a receiver of a satellite location system and from mapping data of a road environment of said vehicle; And
- a candidate trajectory determined from first data received from at least a first sensor corresponding to an object detection sensor configured to detect another vehicle traveling in front of said vehicle. Method according to one of Claims 1 to 6, for which each candidate trajectory of the said plurality of candidate trajectories (101, 102) is different from the other candidate trajectories, the difference resulting from different first sensors from one candidate trajectory to the other and/or from one candidate trajectory determination method to another candidate trajectory. Device (2) for determining a trajectory for a vehicle traveling according to an autonomous driving mode, said device (2) comprising a memory (21) associated with at least one processor (20) configured for the implementation of the steps of the method according to any one of claims 1 to 7. Vehicle (10) comprising the device (2) according to claim 8. Computer program comprising instructions for implementing the method according to any one of Claims 1 to 7, when these instructions are executed by a processor.