Method and device for autonomous vehicle driving

Abstract

The invention relates to a method and device for the autonomous driving of a vehicle, called the ego vehicle, said ego vehicle traveling on a road, said road comprising at least two lanes, a first lane and a second lane, said ego vehicle traveling on said first lane, a vehicle, called the target vehicle, traveling on said second lane, said method comprising the steps of: Receiving (201) a first probability indicator; Receiving (202) a location of said target vehicle; Receiving (203) an area focused by the gaze of a driver of said ego vehicle; Receiving (204) a model of said first and second lanes; Determining (205) whether the driver is focused on said first lane, said second lane, or the target vehicle; Generating (206) a second probability indicator; Issuing (207) an autonomous driving instruction based on said second probability indicator. Figure to be published for the abstract: Figure 2

Description

Title of the invention: Method and device for autonomous driving of a vehicle Technical field of the invention

[0001] The invention is in the field of autonomous vehicle driving assistance systems. In particular, the invention relates to a method and a device for autonomous driving of a vehicle. State of the art

[0002] "Vehicle" means any type of vehicle such as a motor vehicle, a moped, a motorcycle, a storage robot in a warehouse, etc. "Autonomous driving" of a "vehicle" means any process capable of assisting the driving of the vehicle, the "vehicle" is then also called an "autonomous vehicle". The process may thus consist of partially or totally steering the vehicle or providing any type of assistance to a natural person driving the vehicle. The process thus covers all autonomous driving, from level 0 to level 5 in the OICA scale, for International Organization of Motor Vehicle Manufacturers.

[0003] The methods capable of assisting the driving of the vehicle are also called AD AS (from the English acronym “Advanced Driver Assistance Systems”), AD AS systems or driving assistance systems. Currently, a marketed vehicle includes several AD AS systems known as, at least, an adaptive cruise control, also called cruise control, system or function or ACC from the English acronym “Auto Cruise Control”, a lane position maintenance aid, also called LPA or LPA system from the English acronym “Lane Positioning Assist”, ...

[0004] Some AD AS systems, such as ACC or LPA, require adapting their regulations according to the behavior of adjacent cars. These systems determine a future trajectory of the vehicle, called the ego vehicle, which amounts to determining the future locations of the ego vehicle, or corridor. To allow safe movement of the ego vehicle, these systems determine a future trajectory of the ego vehicle according to a probability distribution of the presence of other vehicles on said trajectory of the ego vehicle.

[0005] Such a system is known from document FRI872874. However, there are still life situations in which another vehicle is not taken into account as a driver would. For example, if the ego vehicle is traveling on a 2-lane highway, the ego vehicle overtaking a truck, another vehicle being in front of the truck traveling on the same lane as the truck, this other vehicle, hidden by the truck, is not not immediately detected by sensors embedded in the ego vehicle. Indeed, these AD AS systems use a RADAR sensor which is very directional, only allowing an object to be detected in a cone in the longitudinal axis of normal advancement of the ego vehicle. These AD AS systems also use an on-board camera, with associated image processing, at the top of a windshield of the ego vehicle. The truck obscuring the view of the other vehicle, once the ego vehicle has passed the truck, once the other vehicle becomes detectable by the sensors of the ADAS system, the ADAS system must confirm temporally (perform a certain number of successive coherent detections) before being certain of correctly detecting the other vehicle.

[0006] This other vehicle may intend to change lanes and, thus, find itself, before said time confirmation, at least partly in the lane of the ego vehicle in front of the ego vehicle. The insertion into the lane of the ego vehicle, in front of the ego vehicle, by another vehicle is called a "cut-in" (from the English). In this situation, an ADAS system must react early enough to manage it well, such as braking the ego vehicle in a comfortable and non-anxiety-inducing manner. It is also necessary to avoid any braking that could be considered untimely when the approaching other vehicle is in the adjacent lane. With current sensors, it is difficult to configure the ADAS system to have a good compromise.

[0007] Devices for monitoring an occupant of a vehicle are also known, in particular devices for analyzing the gaze and monitoring the driver's attention. These devices are capable of determining the direction of the gaze and determining an area focused by the driver's gaze. This area may be a location located on the driver's seat, such as a predetermined area of ​​a display. This area may also be a location outside the vehicle such as another vehicle (therefore in the longitudinal axis of normal advancement of the vehicle), or such as another vehicle outside the longitudinal axis. Summary of the invention

[0008] An object of the present invention is to remedy the aforementioned problem, in particular to select as soon as possible a new vehicle, called target vehicle, by an ADAS system during a cut-in of said target vehicle.

[0009] To this end, a first aspect of the invention relates to a method for autonomous driving of a vehicle, called an ego vehicle, said ego vehicle traveling on a road, said road comprising at least two lanes, a first lane and a second lane, said ego vehicle traveling on said first lane, a vehicle, called a target vehicle, traveling on said second lane, said method being implemented by a processor and comprising the steps of: - Receiving a first probability indicator, said first indicator ca characterizing a probability that a future path of said target vehicle intercepts a future path of said ego vehicle; - Receiving a location of said target vehicle; - Receiving an area focused by a gaze of a driver of said ego vehicle, the areas which can be focused by the gaze being predetermined, said area being emitted by a system for analyzing a gaze of a driver; - Reception of a modeling of said first and second channels; - Determination, based on said location of the target vehicle, of said focused area and of said modeling, if said driver focuses his gaze on the first lane or, if the driver focuses on said second lane or the target vehicle; - Generation of a second probability indicator based on said first probability indicator and said determination; - Issuance of an autonomous driving instruction based on said second probability indicator.

[0010] Thus, autonomous driving is contextualized by the gaze of said driver. Depending on the area focused by the driver's gaze, the probability that the trajectory of the target vehicle intercepts the trajectory of the ego vehicle will be adapted. Autonomous driving will then be adapted.

[0011] Advantageously, when the driver focuses his gaze on the second lane or the target vehicle, said second probability indicator generated is greater than said first probability indicator.

[0012] The driver's gaze, and therefore his attention, is directed towards the danger. Thus, when the driver's attention is directed towards an adjacent lane or a target vehicle, by increasing the probability indicator, the autonomous driving will take the target vehicle into account more quickly, said target vehicle interfering more probably with the trajectory of the ego vehicle. Then, the taking into account of the target vehicle by the autonomous driving will be anticipated.

[0013] Advantageously, when the driver focuses his gaze on said first channel, said second probability indicator generated is smaller than said first probability indicator.

[0014] Thus, when the driver's attention is not focused on the target vehicle, in other words when the driver's attention is focused on the trajectory of the ego vehicle, by a reduction in the probability of an interception of the trajectory of the ego vehicle by a trajectory of the target vehicle, the target vehicle is taken less into account by autonomous driving. Then, a target vehicle which does not present a danger according to the driver will be taken less into account by autonomous driving, avoiding thus false detections and / or inappropriate modifications of the ego vehicle's trajectories.

[0015] Advantageously, said method further comprises a step of determining a duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined duration.

[0016] Advantageously, said method further comprises a step of determining a percentage, over a predetermined time, of the duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined percentage.

[0017] Thus, the longer, in absolute or relative terms, the driver's attention is focused on the target vehicle, the more this target vehicle can be a danger for the ego vehicle. The second indicator then reflects the importance that the driver places on the target vehicle.

[0018] Advantageously, said autonomous driving is an adaptive cruise control based on a set inter-vehicle time, the method further comprising a step of determining a set inter-vehicle time as a function of said second probability indicator.

[0019] Advantageously, said autonomous driving is an adaptive cruise control based on a set speed, the method further comprising a step of determining a set speed as a function of said second probability indicator.

[0020] Thus, in the case of autonomous driving based on an adaptive cruise control, the speed of the ego vehicle is adapted according to the focus of the driver's gaze.

[0021] A second aspect of the invention relates to a device comprising an autonomous driving device, a system for analyzing a driver's gaze and a memory associated with at least one processor configured to implement the method according to the first aspect of the invention.

[0022] The invention also relates to a vehicle comprising the device.

[0023] The invention also relates to a computer program comprising instructions which, when the program is executed by the device according to the second aspect of the invention, lead the latter to implement the method according to the first aspect of the invention. Brief description of the figures

[0024] 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, in which:

[0025] [Fig.l] schematically illustrates a device, according to a particular example of rea- lization of the present invention.

[0026] [Fig.2] schematically illustrates a method for autonomous driving of a vehicle, according to a particular exemplary embodiment of the present invention. Detailed description of the invention

[0027] The invention is described below in its non-limiting application to the case of an autonomous motor vehicle traveling on a road or on a traffic lane. Other applications such as a robot in a storage warehouse or a motorcycle on a country road are also conceivable.

[0028] [Fig. 1] represents an example of a device 101 included in the vehicle, in a network (“cloud”) or in a server. This device 101 can be used as a centralized device in charge of at least certain steps of the method described below with reference to [Fig. 2]. In one embodiment, it corresponds to an autonomous driving computer.

[0029] In the present invention, the device 101 is included in the vehicle.

[0030] This device 101 can take the form of a box comprising circuits printed, from any type of computer or even from a mobile phone (“smartphone”).

[0031] The device 101 comprises a random access memory 102 for storing instructions for the implementation by a processor 103 of at least one step of the method as described above. The device also comprises a mass memory 104 for storing data intended to be retained after the implementation of the method.

[0032] The device 101 may further comprise a digital signal processor (DSP) 105. This DSP 105 receives data to format, demodulate and amplify, in a manner known per se, this data.

[0033] The device 101 also comprises an input interface 106 for receiving the data implemented by the method according to the invention and an output interface 107 for transmitting the data implemented by the method according to the invention.

[0034] For example, the input interface 106 can receive the following data: position or geographical location of the vehicle, speed and / or acceleration of the vehicle, set or predetermined positions / speeds / accelerations, engine speed, position and / or travel of the clutch, brake and / or acceleration pedal, detection of other vehicles or objects, position or geographical location of the other vehicles or objects detected, speed and / or acceleration of the other vehicles or objects detected, operating states of sensors, confidence index of data originating from or processed by sensors and / or devices similar to the device 101. For example, the sensors capable of providing data are: GPS associated or not with mapping, tachometers, accelerometers, RADAR, LIDAR, lasers, ultrasound, camera, device for analyzing a gaze, etc.

[0035] In an exemplary embodiment, the input interface receives a probability indicator, of a location of a vehicle, an area focused by a driver's gaze, said area possibly being a lane on which the ego vehicle is traveling, a lane adjacent to the lane on which the ego vehicle is traveling, a target vehicle, ..., a modeling of lanes of a road, a duration or a percentage of focusing time, a set inter-vehicle time, a set vehicle speed,

[0036] For example, the output interface 107 can transmit data similar to the data received by the input interface 106. The output interface 107 can transmit a focus of the first lane, of the second lane or of a target vehicle by a driver's gaze, a probability indicator, an autonomous driving instruction, a duration or percentage of focusing time, a set inter-vehicle time, a set speed, etc.

[0037] [Fig.2] schematically illustrates a method of autonomous driving of a vehicle, according to a particular embodiment of the present invention. The vehicle is called an ego vehicle. Said ego vehicle travels on a road, said road comprising at least two lanes, a first lane and a second lane. Said ego vehicle travels on said first lane. A vehicle, called a target vehicle, travels on said second lane. The method is implemented by the processor 103.

[0038] It is known that an AD AS system, via a perception system in combination with a geolocation system associated with mapping, is capable of determining a road, lanes on this road and objects on the lanes, an object possibly being a vehicle. This system is also capable of determining whether the ego vehicle is traveling on said first lane and whether the target vehicle is traveling on said second lane.

[0039] Step 201, RxProbl, is a step of receiving a first probability indicator, said first indicator characterizing a probability that a future path of said target vehicle intercepts a future path of said ego vehicle.

[0040] It is known that an AD AS system, in particular autonomous driving as in FRI872874, is capable of determining a future trajectory of said ego vehicle and said target vehicle. This trajectory estimation is generally based on an extrapolation of the positions, measured or determined by sensors, of the vehicles. This probability estimates a rate of insecurity and risk of accident.

[0041] Generally, these trajectories are expressed in the same reference frame shared between AD AS systems. From the estimates, these systems can provide a probability that a future path of said target vehicle intercepts a future path of said ego vehicle.

[0042] Step 202, RxLoc, is a step of receiving a location of said target vehicle. Conventionally, the location is expressed in a reference frame shared between the AD AS systems. Otherwise, said location is expressed in a reference frame whose definition (origins, axes) is known by the method, and said method is capable of carrying out a change of reference to express said location in a reference known and used by the method.

[0043] Step 203, RxZone, is a step of receiving a zone focused by a gaze of a driver of said ego vehicle, the zones which can be focused by the gaze being predetermined, said zone being emitted by a system for analyzing a gaze of a driver.

[0044] It is known that a gaze analysis system is capable of identifying an area focused by the driver's gaze. This area is identified by an intersection between measured gaze directions and / or by a measured position, direction and / or orientation of a driver's head, and a geographical representation of the regions of what a driver can see. This area is also expressed in a known reference frame by the method. Otherwise, said method is capable of carrying out a change of reference frame to express said area in a known reference frame used by the method.

[0045] Step 204, RxMdl is a step of receiving a modeling of said first and second channels. In an identical manner, the method receives this information and is able to carry out a change of reference to express said zone in a reference known and used by the method, if this information is not already expressed in the same shared reference.

[0046] Step 205, DetFocal, is a step of determining, as a function of said location of the target vehicle, said focused area and said modeling, whether said driver focuses his gaze on the first lane or whether the driver focuses on said second lane or the target vehicle.The location of the target vehicle, the focused area and the modalization of the lanes being expressed in the same shared reference frame, (or if this is not the case, the method is able to carry out the necessary change of reference frame), by comparisons, it is determined whether the driver focuses his attention on the first lane (in this case the focused area is on a region of the shared reference frame corresponding to a location of the first lane), on the second lane (in this case the focused area is on a region of the shared reference frame corresponding to a location of the second lane) or on the target vehicle (in this case the focused area is on a region of the shared reference frame corresponding to a location of the located vehicle).

[0047] Step 206, Prob2, is a step of generating a second probability indicator as a function of said first probability indicator and said determination. Depending on the focused area, the region to which the driver's attention is directed, the second probability indicator is adapted.

[0048] Advantageously, when the driver focuses his gaze on the second lane or the target vehicle, said second generated probability indicator is greater than said First indicator of probability. If the driver focuses his attention on the target vehicle or on a lane other than the one in which the ego vehicle is traveling, it means there is a danger. Objects, such as the target vehicle, in the driver's direction of vision must be taken into account for safe autonomous driving. Since the probability of an accident is greater, autonomous driving will adapt the trajectory and speed of the ego vehicle in anticipation of the state of the art.

[0049] Advantageously, when the driver focuses his gaze on said first lane, said second generated probability indicator is smaller than said first probability indicator. If the driver does not focus his attention on the target vehicle or on a lane other than the lane in which the ego vehicle is traveling, it is because the driver considers that there is little danger and that he wants to continue in his direction. Objects, such as the target vehicle, must be taken into account less for safe autonomous driving. Since the probability of an accident is lower, autonomous driving will adapt less, taking less account of the target vehicle, the trajectory and the speed of the ego vehicle compared to the state of the art.

[0050] Step 207, Txlns, is a step of issuing an autonomous driving instruction from said second probability indicator. The probability indicator has been updated according to the attention paid by the driver. The autonomous driving of the vehicle will take this probability into account to adapt the trajectory to a speed of the ego vehicle, thus providing the expected advantages.

[0051] Advantageously, said method further comprises a step of determining a duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined duration.

[0052] Advantageously, said method further comprises a step of determining a percentage, over a predetermined time, of the duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined percentage.

[0053] Advantageously, said autonomous driving is an adaptive cruise control based on a set inter-vehicle time, the method further comprising a step of determining a set inter-vehicle time as a function of said second probability indicator.

[0054] Advantageously, said autonomous driving is an adaptive cruise control based on a set speed, the method further comprising a step of determining a set speed as a function of said second probability indicator.

[0055] The present invention is not limited to the embodiments described above as examples: it extends to other variants.

[0056] For example, the method has been described according to a sequence of steps. Certain steps can be carried out in parallel or according to another sequence.

Claims

Claims

1. Method for autonomous driving of a vehicle, called an ego vehicle, said ego vehicle traveling on a road, said road comprising at least two lanes, a first lane and a second lane, said ego vehicle traveling on said first lane, a vehicle, called a target vehicle, traveling on said second lane, said method being implemented by a processor (103) and comprising the steps of: - Receiving (201) a first probability indicator, said first indicator characterizing a probability that a future path of said target vehicle intercepts a future path of said ego vehicle; - Receiving (202) a location of said target vehicle; - Receiving (203) an area focused by a gaze of a driver of said ego vehicle, the areas that can be focused by the gaze being predetermined, said area being emitted by a system for analyzing a gaze of a driver;- Reception (204) of a modeling of said first and second lanes; - Determination (205), as a function of said location of the target vehicle, of said focused zone and of said modeling, whether said driver focuses his gaze on the first lane or, whether the driver focuses on said second lane or the target vehicle; - Generation (206) of a second probability indicator as a function of said first probability indicator and of said determination; - Transmission (207) of an autonomous driving instruction from said second probability indicator.;

2. The method of claim 1, wherein when the driver focuses his gaze on the second lane or the target vehicle, said generated second probability indicator (206) is greater than said first probability indicator.

3. Method according to one of the preceding claims, wherein, when the driver focuses his gaze on said first path, said second generated probability indicator (206) is smaller than said first in- probability indicator.

4. Method according to one of the preceding claims, in which said method further comprises a step of determining a duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined duration.

5. Method according to the preceding claim, in which said method further comprises a step of determining a percentage, over a predetermined time, of the duration of focusing of said target vehicle by the gaze of said driver, the generation of said second indicator being a function, furthermore, of said determined percentage.

6. Method according to one of the preceding claims, in which said autonomous driving is an adaptive cruise control based on a set inter-vehicle time, the method further comprising a step of determining a set inter-vehicle time as a function of said second probability indicator.

7. Method according to one of the preceding claims, in which said autonomous driving is an adaptive cruise control based on a set speed, the method further comprising a step of determining a set speed as a function of said second probability indicator.

8. Device (101) comprising an autonomous driving device, a system for analyzing a driver's gaze and a memory (102) associated with at least one processor (103) configured to implement the method according to one of the preceding claims.

9.

10. Vehicle comprising the device according to the preceding claim. Computer program comprising instructions which, when the program is executed by the device (101) according to claim 8, cause the latter to implement the method according to one of claims 1 to 7.

Images