Method for controlling an autonomous vehicle

Abstract

A method for controlling an autonomous vehicle (100) comprising at least one means of perception (21) and a first map (M1) containing stored digital data representative of a real infrastructure of an environment of the autonomous vehicle (100), the method comprising the steps of: (E1) defining a first trajectory (T1) and a first associated kinematic profile (P1) of the autonomous vehicle (100); (E2) detecting, from data transmitted by the at least one means of perception (21), a situation to be optimized on a given segment (S) of the first trajectory (T1), the given segment (S) being located over a distance less than a maximum distance of detection (DLIM) from the at least one means of perception (21) in front of the autonomous vehicle (100); and (E3) determining a first trajectory (T1) and a first associated kinematic profile (P1) of the autonomous vehicle (100). and a step (E3) of optimizing at least one element from a kinematic profile (P1) of the given segment (S), wherein the optimization of the first map comprises determination of a local map (M2) on the given segment (S) and / or the optimization of the first kinematic profile (P1) comprises determination of a second kinematic profile (P2) associated with the given segment (S), wherein at least one parameter of the second kinematic profile (P2) differs from a parameter of the first kinematic profile (P1), and a step (E4) of controlling the displacement of the autonomous vehicle (100) over the given segment (S) taking into account the local map (M2) and / or the second kinematic profile (P2).

Description

Summary of the Invention

[0001] The present invention relates to a method for controlling an autonomous vehicle. The present invention further relates to a device for controlling an autonomous vehicle. The present invention also relates to a computer program implementing the above-mentioned method. Finally, the present invention relates to a storage medium on which such a program is stored.

[0002] Autonomous vehicle technology essentially uses high definition maps associated with speed profiles that satisfy the lateral and longitudinal constraint parameters of the autonomous vehicle to pre-define trajectories corresponding to different autonomous driving scenarios in a given traffic zone.

[0003] For example, when an autonomous vehicle approaches an X-junction, the potential trajectories for approaching the intersection (turn right, turn left, go straight) are already pre-mapped, as are the associated speed profiles.

[0004] However, these techniques have the drawback that they are essentially limited to traffic scenarios that are predefined from maps.

[0005] The document US 9511767 (B1) discloses a method for controlling an autonomous vehicle using data coming from a perception system to adapt the trajectory of the autonomous vehicle depending on the behavior of the surrounding vehicles. However, this solution has drawbacks.

[0006] It is an object of the present invention to provide a device and a method for controlling an autonomous vehicle that overcomes the above-mentioned drawbacks and improves the devices and methods for controlling autonomous vehicles known from the prior art. In particular, it is an object of the present invention to provide a device and a method that is simple, reliable and improves autonomous driving.

[0007] To this end, the invention relates to a method for controlling an autonomous vehicle comprising at least one perception means and a first map comprising stored digital data representative of the real infrastructure of the environment of the autonomous vehicle, the control method comprising the steps of: - defining a first trajectory and a first associated kinematic profile for an autonomous vehicle; - detecting a situation to be optimized on a given segment of the first trajectory from data transmitted by the at least one perception means, the given segment being located in front of the autonomous vehicle over a distance that is smaller than a maximum detection distance of the at least one perception means; - optimizing at least one element from the first map and the first kinematic profile, optimizing the first map includes determining a local map on a given segment; and / or optimizing the first kinematic profile includes determining a second kinematic profile associated with the given segment, wherein at least one parameter of the second kinematic profile differs from a parameter of the first kinematic profile; optimizing at least one element; - controlling movement of the autonomous vehicle on the given segment taking into account the local map and / or the second kinematic profile; Includes.

[0008] Determining the local map may enable a new curve for a given segment to be determined between an entry point and an exit point of the given segment, in particular by a Bézier curve, the new curve having a continuity G2 with the first trajectory at the entry and exit points.

[0009] Determining a second kinematic profile associated with a given segment can include calculating a maximum collision-free speed threshold from data resulting from at least one perception means, and the second kinematic profile can have a maximum speed below the maximum collision-free speed threshold.

[0010] The maximum crash-free speed threshold may be calculated by solving an equation such that the maximum crash-free speed threshold is equal to the square root of the product of the braking value required to reach the maximum crash-free speed threshold and twice the maximum detection range of the at least one sensing means.

[0011] The step of detecting the situation to be optimized includes measuring a holding time that the autonomous vehicle remains in the situation to be optimized and comparing the holding time to a triggering threshold associated with the situation, and the optimization step may be performed when the holding time is greater than the triggering threshold.

[0012] A set of predefined situations may be stored in the electronic memory, and the step of detecting the situation to be optimized may comprise comparing perception resulting from the at least one perception means with the set of predefined situations.

[0013] The set of predefined situations may include negotiating a roundabout with two empty lanes, and / or entering a roundabout in dense traffic conditions, and / or two lanes of traffic merging into a single lane, and / or crossing a congested junction, and / or overtaking an extremely slow vehicle on a bidirectional road with a single lane in each direction.

[0014] The second kinematic profile may have at least a 20% higher maximum velocity, and / or at least a 200% higher maximum acceleration, and / or at least a 1,000% higher jerk than the first kinematic profile.

[0015] The invention also relates to a device for controlling an autonomous vehicle, the autonomous vehicle being equipped with motion actuators, the device comprising hardware and / or software elements implementing the method defined above, in particular hardware and / or software elements designed to implement the method according to the invention, and / or the device comprising means for implementing the method defined above.

[0016] The invention further relates to an autonomous vehicle comprising a control device according to the preceding claims.

[0017] The invention also relates to a computer program product comprising program code instructions stored on a computer readable medium for implementing the steps of the method defined above, when said program runs on a computer. The invention also relates to a computer program product downloadable from a communications network and / or stored on a computer readable data medium and / or which can be executed by a computer, the computer program product comprising instructions which, when the program is executed by a computer, cause the computer to implement the method defined above.

[0018] The invention also relates to a computer readable data storage medium storing a computer program comprising program code instructions for implementing the method defined above. The invention also relates to a computer readable storage medium comprising instructions which, when executed by a computer, cause the computer to implement the method defined above.

[0019] The invention further relates to a data-carrier signal carrying a computer program product as defined above.

[0020] The accompanying drawings show, by way of example, an embodiment of a control device according to the invention and an arrangement for carrying out the control method according to the invention. [Brief description of the drawings]

[0021] [Figure 1] FIG. 1 illustrates an embodiment of an autonomous vehicle equipped with a control device. [Diagram 2] FIG. 1 illustrates a configuration for determining a kinematic profile of an autonomous vehicle in accordance with an embodiment of the present invention. [Diagram 3] 4 is a flow chart of a configuration for carrying out a control method according to one embodiment of the present invention. [Figure 4] FIG. 2 illustrates a first example for implementing a control method according to an embodiment of the present invention. [Diagram 5] FIG. 2 illustrates a second example for implementing a control method according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] The autonomous vehicle 100 according to an embodiment of the present invention may be any type of autonomous vehicle, in particular a passenger car, a utility vehicle, a truck, or even a public transportation vehicle such as a bus or shuttle.

[0023] The autonomous vehicle 100 comprises a control system 10 and a motion actuator 4 .

[0024] The motion actuators 4 form part of the chassis of the autonomous vehicle 100. The motion actuators 4 include, among others, an engine torque actuator, a brake actuator, and a rotation actuator for the steering wheel. The motion actuators 4 receive commands from the control system 10 to implement the movement of the autonomous vehicle along a trajectory determined by the control system 10.

[0025] The control system 10 mainly comprises the following elements: a perception system 2 comprising perception means 21 and a module 22 for processing the electronic horizon, - Electronic memory 3, as well as a computing unit 5 comprising a microprocessor 1, a local electronic memory 6 and a communication interface 7 enabling the microprocessor 1 to communicate with a perception system 2 and with a motion actuator 4.

[0026] The perception means 21 may comprise all or part of the set of the following equipment: cameras and / or lidars and / or radars. Alternatively or additionally, the perception means 21 may comprise a vehicle-to-vehicle communication system (V2V system) or a vehicle-to-everything communication system (V2X system) enabling vehicles to exchange information with each other, with infrastructure and with pedestrians.

[0027] Advantageously, the perception means 21 enable the environment located 360° around the autonomous vehicle 100 to be perceived.

[0028] In a preferred embodiment, the perception means 21 comprises five cameras and one LIDAR. Images from the cameras are periodically and synchronously captured and aggregated with data resulting from one rotation of the LIDAR.

[0029] Based on the data coming from the perception means 21, a module for processing the electronic horizon 22 builds a structured perception of the driving scene.

[0030] Periodically, in particular each time data is received, the module 22 determines the maximum capacity of the perception system 2, i.e. the maximum detection distance DLIM of the perception means 21, which varies according to the driving scenario. For example, when the autonomous vehicle 100 travels on a highway, the distance DLIM is greater than when it travels on a traffic circular intersection, usually called a "roundabout".

[0031] The distance DLIM also depends on other parameters, such as weather conditions, brightness, the presence of road infrastructure elements (eg tunnels) or surrounding traffic (eg trucks).

[0032] Throughout the remainder of this specification, the term "roundabout" refers to a traffic circular intersection whereby vehicles proceeding on the intersection have priority over vehicles entering the intersection. Furthermore, the maximum detection distance of the perception means is referred to as the "perception limit distance (DLIM)".

[0033] The perception limit distance DLIM can be determined from the perception limits of each perception means. In one embodiment, the perception limit distance DLIM is the minimum between the perception limit for the image originating from the camera and the perception limit of the data originating from the lidar.

[0034] The perception limit of the image resulting from the camera can be defined as the maximum distance at which the height of any object of interest (vehicle, pedestrian) is greater than a minimum threshold, for example 25 pixels. The magnitude of this first limit is several tens of meters, for example 40 meters under normal visibility conditions, especially with regard to weather.

[0035] The perception limit of data resulting from a lidar can be defined as the maximum distance at which the number of laser points reaching an object of interest (vehicle, pedestrian) is greater than a minimum threshold.

[0036] In the perception zone, defined by a circle centered on the autonomous vehicle and with a radius equal to the perception limit distance DLIM, the module 22 for processing the electronic horizon builds an occupancy grid of the driving scene. The point cloud resulting from the lidar is to some extent discretized into cells. Each cell of the grid is determined to be vacant, occupied or not. This determination is based in particular on the processing of the heights of the points of the cell, such as the application of minimum and maximum height thresholds of the points in the cell.

[0037] The occupancy grid defines a collision risk free zone around the position of the autonomous vehicle 100, as well as a three-dimensional representation of obstacles located in the perception zone.

[0038] The data resulting from the module 22 for processing the electronic horizon provides a structured perception of the driving scenario over the perception zone, in particular the perception of the traffic around the autonomous vehicle 100, in terms of traffic density and location of objects of interest (vehicles, pedestrians).

[0039] The control system 10 further comprises an electronic memory 3 in which a set of digital data is stored that represents the actual infrastructure of the environment of the autonomous vehicle 100. This digital data generally relates to all elements from which it is possible to infer choices regarding driving the autonomous vehicle 100. Those elements relate in particular to the layout and limits of the navigable roadway portions, the number of lanes of the roadway portions, the speed limits applicable to the roadway portions, the type of ground markings and their location, the presence and position of traffic signs, traffic signals and roundabouts.

[0040] This digital data will be referred to below simply as "Map M1."

[0041] In an embodiment of the invention, the computer 1 enables software to be executed comprising the following modules: - a module 11 for determining a trajectory, which cooperates with the perception system 2 and the map 3; - a module 12 for detecting situations to be optimized, cooperating with the perception system 2; - an optimization module 13, which cooperates with the perception system 2; a module 14 for controlling the movement of the autonomous vehicle, cooperating with the motion actuator 4.

[0042] A mode for carrying out the method for controlling an autonomous vehicle is described below with reference to figure 3. The method comprises steps E1 to E4.

[0043] In a first step E1, a planned trajectory T1 is determined between the starting point and the destination point of the autonomous vehicle 100. For this purpose, a map M1 stored in an electronic memory 3 and data originating from the perception system 2 are notably used.

[0044] Throughout the remainder of this specification, the term "trajectory" is used to designate the evolution over time of a state vector that defines the characteristics of the movement of autonomous vehicle 100. In a preferred embodiment, the state vector comprises a position, in particular coordinates x, y, longitudinal and lateral velocity and / or longitudinal and lateral acceleration and / or yaw rate and / or jerk. Throughout the remainder of this specification, the term "position" is used to designate either the x, y coordinates of the state vector, or the state vector as a whole.

[0045] The planned trajectory T1 is preferably divided into trajectory segments, also referred to as "segments" throughout the remainder of this specification.

[0046] Advantageously, the segments are each defined such that when autonomous vehicle 100 enters the segment it is possible to be entirely located in the perception zone of autonomous vehicle 100. In particular, the length of the segment is less than the perception limit distance DLIM.

[0047] The term "kinematic profile" is used throughout the remainder of this specification to designate the general velocity, acceleration and jerk profile implemented by the vehicle. To some extent, the kinematic profile serves as a template for calculating the velocity, acceleration and jerk implemented in the trajectory calculation. The template defined by the kinematic profile sets limits on the velocity, acceleration and jerk.

[0048] The kinematic profile takes into account the constraints imposed by the road infrastructure, i.e. the road layout, the number of lanes, the width of each lane, the presence of intersections and / or traffic signals, speed limits, etc. The kinematic profile is also determined depending on the technical characteristics of the autonomous vehicle. The kinematic profile is further defined based on driving comfort criteria, in particular relating to maximum speed and / or lateral acceleration and / or jerk thresholds.

[0049] In one embodiment, the kinematic profile may be defined according to the method for limiting jerk (jerk is the derivative of acceleration) shown in FIG.

[0050] FIG. 2 is a graph with three curves, J(t), a(t) and v(t), which represent the jerk, acceleration and velocity, respectively, of the autonomous vehicle 100 over time.

[0051] The curve J(t) is a stepped curve, where time is divided into fixed duration intervals and the value of the jerk is constant over each interval. The duration of the intervals depends on the acceleration limits of the vehicle and the distance available to accelerate or brake.

[0052] In the illustrated example, the jerk can assume three discrete values: 0, a maximum value Jmax, and a minimum value −Jmax.

[0053] The value of Jmax is small to promote comfort for users of the autonomous vehicle 100. In one embodiment, the value of Jmax is 1 m / s -3 is set to.

[0054] The curve J(t) therefore determines the variation in time of the acceleration a(t). - the curve a(t) consists of linear segments whose slope is determined by the value of Jmax and the duration of the time interval; The curve a(t) varies between the acceleration values ​​Amax and -Amax.

[0055] The curve a(t) determines the time variation of the velocity v(t) between zero velocity and a maximum velocity Vmax, which may be determined by the velocity limit for the trajectory segment.

[0056] This method is repeated on each trajectory segment to define a trajectory T1 that follows the road infrastructure and is as comfortable as possible without slowing down the traffic. Thus, for each trajectory segment the applied speed, acceleration and jerk are determined depending on the kinematic profile and the map M1.

[0057] Throughout the remainder of this specification, a trajectory T1 is defined as a set of N segments S1, ..., S N The first kinematic profile P1 i is each segment S i , the first kinematic profile P1 i Each of the segments S is defined according to a first map M1. i Each of the first map M1 and the first profile P1 associated with the first map M1 i It is defined according to:

[0058] Thus, the term "track segment" designates the curve of the track as well as the speed, acceleration and jerk values ​​that are applied to move the vehicle along the curve of the segment.

[0059] Thus, given two distinct points C and D, the two segments connecting point C to point D are considered different if their respective curves are different or if the speed or acceleration or jerk values ​​respectively applied to move the vehicle on one or the other of the curves of the segments are different. Thus, the trajectory T1 divided into trajectory segments is stored in the local memory 6 of the computing unit 5.

[0060] Then, step E2 follows. In step E2, the intention is to determine whether the segment S of the trajectory T1 located in front of the autonomous vehicle 100 is i The aim is to detect situations that should be optimized on segment S. i lies entirely within the perceptual limit DLIM of the perceptual means 21.

[0061] In other words, step E2 is performed by determining the segment S of the trajectory T1, in which the situation to be optimized is located. i Determine the segment S i is located in front of the vehicle, which is the segment S i forms a part of the trajectory T1 that has not yet been traversed by the autonomous vehicle.

[0062] In the described embodiment, it is assumed that the situation to be optimized is limited to an isolated segment. In alternative embodiments, it may be considered that the situation to be optimized can extend over several consecutive trajectory segments. However, all segments must be within the perception limit DLIM.

[0063] The situation to be optimized is a traffic scenario in which the movement of the autonomous vehicle is hindered by the first trajectory T1, in particular by the limitations of the first kinematic profile P1 associated with the trajectory T1, V1max and / or A1max and / or J1max. For example, in dense traffic conditions, the autonomous vehicle 100 may remain stuck at the entrance to a roundabout for a very long time if the kinematic profile associated with that trajectory does not allow the autonomous vehicle 100 to accelerate sufficiently to enter the traffic.

[0064] In other words, the kinematic profile P1 implemented by the trajectory T1 was defined according to driving comfort criteria that limit the responsiveness of the autonomous vehicle. The profile P1 allows the autonomous vehicle to manage most situations under optimal safety and comfort conditions. However, the profile P1 may prove to be inappropriate for some situations. This inadequacy may therefore slow down the vehicle significantly, for example when the vehicle is unable to overtake a truck in front of it or even when keeping the vehicle stationary for a long time, for example when the vehicle is unable to enter a roundabout due to traffic density.

[0065] Other situations to be optimized may not be with respect to the first kinematic profile P1, but with respect to the first map M1, which represents the actual infrastructure of the traffic environment of the autonomous vehicle 100. In some cases, the first map M1 induces a particular trajectory of the vehicle that does not correspond to the normal behavior of a human driver and does not optimize driving. This occurs, for example, on a trajectory segment crossing a two-lane roundabout where no other vehicles are proceeding. The first trajectory T1 determines a movement on the outer lane of the roundabout, which requires a significant reduction in the speed of the autonomous vehicle before it enters the roundabout. The trajectory T1 was therefore defined with respect to the map M1, which represents a roundabout with two lanes. However, when a human driver approaches a multi-lane roundabout where no other vehicles are proceeding, the human driver adapts the trajectory of his vehicle to this situation, i.e., he expects to reduce the curvature of his trajectory by using two lanes, and therefore approaches the roundabout at a speed significantly greater than the speed he would use if he were to proceed only on the outer lanes of the roundabout. The adaptation implemented by the human driver roughly corresponds to modifying the road infrastructure, in particular by considering the roundabout to comprise only one lane.

[0066] In a form for carrying out the method, data received from the perception system 2, in particular data originating from the module for processing the electronic horizon 22, are compared with a set of predefined situations stored in the local electronic memory 6.

[0067] Throughout the remainder of this specification: - the data resulting from the module 22 for processing the electronic horizon are called "sensory data", - a set of predefined situations, stored in a local electronic memory 6, is called a "situation table", The data contained in the situation table and relating to the predefined situations are called "situation parameters".

[0068] The predefined situation corresponds to the situation to be optimized. This may include: - the entrance to a roundabout with two empty lanes, referred to throughout the remainder of this specification as an "empty roundabout situation", and / or - long stops when entering a roundabout in dense traffic conditions, referred to throughout the remainder of this specification as "congested roundabout situations", and / or - Merging of two lanes of traffic into a single lane in congested traffic conditions, and / or - Long stops at busy intersections, and / or - Being stuck behind a very slow vehicle for a long period of time on a two-way road with a single lane in each direction.

[0069] Each of the predefined situations may be associated with one or more situation parameters, including road infrastructure elements and / or traffic density and / or triggering thresholds.

[0070] Thus, comparing the perception data with all predefined situations may include comparing the road infrastructure elements taken by the trajectory T1 with road infrastructure elements associated with each of the predefined situations. The road infrastructure elements may include, for example, a multi-lane roundabout, or an X-junction or a junction between two lanes, or a two-way road with one lane in each direction.

[0071] Furthermore, comparing between the perception data and the predefined situations may also include comparing the traffic density resulting from the perception data with a density threshold associated with each of the predefined situations. The density threshold associated with the predefined situations may be, for example, a minimum density threshold for a congested roundabout situation. The density threshold may also be, for example, a maximum threshold for an empty roundabout situation.

[0072] Furthermore, the situation parameters may include a "triggering" threshold corresponding to a minimum time to remain in said situation. The minimum time to remain in a situation varies according to a predefined situation. The minimum time to remain in a situation may be, for example, 0 for an empty roundabout situation. The minimum time to remain in a situation may be on the order of one minute or more for a congested roundabout situation.

[0073] Other situational parameters not described herein may be contemplated.

[0074] A situation to be optimized is detected when all situation parameters related to this situation are examined, in particular when compared with the sensory data.

[0075] If no situation to be optimized is detected, step E4 follows, which involves controlling the movement of the autonomous vehicle 100.

[0076] When a situation to be optimized is detected, step E3 follows, which involves optimizing the trajectory.

[0077] The trajectory is determined by a first map M1 and / or a first kinematic profile P1, in particular a segment S in which the situation to be optimized is located. i Kinematic profile P1 associated with i This is optimized by modifying

[0078] Advantageously, the situation table associates at least one predefined optimization method with each predefined situation.

[0079] The predefined optimization methods are - Map fixes, or - Kinematic profile correction, or - Map and kinematic profile corrections It could be.

[0080] For an empty roundabout situation, the situation table can associate the empty roundabout situation with a map modification which involves creating a local map M2 that transforms the two-lane roundabout into a one-lane roundabout. Optionally, the situation table can associate map and kinematic profile modifications to this situation under some traffic conditions.

[0081] In case of a congested roundabout situation, the situation table considers the congested roundabout situation as a kinematic profile correction and a new trajectory segment S' i The curve can be related to the calculation of the segment S i The kinematic profile P1 is superimposed on the curve of i Kinematic profile P2 with maximum velocity and / or acceleration and / or jerk thresholds greater than those of i Implement.

[0082] In a preferred embodiment, the second kinematic profile P2 i Determining the second kinematic profile P2 includes calculating a maximum collision-free speed threshold VCOL based on data originating from the perception means 2. i is defined to include speeds below a maximum collision-free speed threshold, VCOL.

[0083] The threshold VCOL is the maximum speed that the autonomous vehicle can travel while still having the potential to stop to avoid colliding with an obstacle detected by the perception system 2.

[0084] The threshold value VCOL is calculated from an occupancy grid of a driving scene defined by a module for processing the electronic horizon 21. The driving scene is used to determine which obstacles, particularly objects of interest such as other vehicles or pedestrians, are closest to autonomous vehicle 100.

[0085] In a simplified embodiment, the threshold value VCOL may be calculated by solving the following equation Math1: [Math1] TIFF2024519698000002.tif5170, where A is the acceleration and in particular the braking value required to reach the speed VCOL, - DLIM is the perceptual limit distance.

[0086] Second kinematic profile P2 i The previously described method for limiting jerk may be used to determine jerk limit. In this case, the increase in responsiveness of the autonomous vehicle 100 is determined by the second profile P2 i The maximum speed threshold of the first profile P1 iAdvantageously, the maximum acceleration and / or jerk thresholds Amax2 and Jmax2 of the second profile are respectively set to a value Vmax2 greater than the maximum velocity threshold Vmax1 of the first profile P1 and less than the maximum collision-free velocity VCOL. i is greater than the Amax1 and Jmax1 thresholds.

[0087] Local map M2 and / or second kinematic profile P2 i After determining, the method further comprises: i , or the optimized segment S' i Returning to step E1 of determining the trajectory in order to calculate the first trajectory segment S i Replace with.

[0088] Optimized segment S' i is the local map M2 and / or the second kinematic profile P2 i is determined to fit.

[0089] Optimized segment S' i In particular, when map M1 was not modified, the first segment S i However, the segments differ with respect to the velocity and / or acceleration and / or jerk that they implement.

[0090] Optimized segment S' i is the sum of the segments S i Connect the entry and exit points of the optimized segment S'. i is advantageously determined by the continuity G2, i.e. the optimized segment S' i The continuity of curvature between the various arcs forming the optimized segment S' at point A. i The continuity of the curvature with the preceding trajectory segment and the optimized segment S' at point B iThe curvature of the trajectory segment is determined to be continuous with the trajectory segment that follows.

[0091] In one embodiment, the optimized segment S' i can be defined by a fifth order polynomial, in particular using a Bézier curve.

[0092] Then, step E4 follows. In a fourth step E4, the movement of the autonomous vehicle is controlled according to the trajectory determined in the preceding step, which trajectory may optionally be an optimized segment S' i Equipped with.

[0093] The trajectory is sent to the control laws of the autonomous vehicle 100 for conversion into command orders that are sent to the motion actuators 4 of the autonomous vehicle 100 .

[0094] Two examples for implementing the control method are illustrated in Figures 4 and 5. It should be noted that the positions of the autonomous vehicle 100 in these figures represent step E4 of moving the vehicle along an optimized trajectory.

[0095] 4 shows a first example for implementing the method. At a moment T, an autonomous vehicle 100 travels along a segment S of a trajectory T1. i-1 The trajectory T1 is calculated according to the map M1 and the kinematic profile P1. i is completely located in the perception zone defined by the perception limit distance DLIM calculated at the moment T. i implements a movement on the outer lane of the roundabout. If there is no traffic on the roundabout, an empty roundabout situation is detected in step E2. In step E3, the map M1 is locally modified by the local map M2 to replace the two-lane roundabout with a one-lane roundabout. Then, the new trajectory S' i is calculated in step E1 using the local map M2, and a new trajectory S'i is the segment S i The entry point A of the segment S i In step E4, the autonomous vehicle 100 connects to the exit point B of the segment S′ between points A and B. i Controlled to move up.

[0096] FIG. 5 shows a second example for implementing the method. In this second example, the following segment S i determines a movement on the outside lane of the roundabout. The traffic on the roundabout is dense and the autonomous vehicle 100 must stop at the entrance to the roundabout. When the given duration during which the autonomous vehicle is stationary at the entrance to the roundabout expires, in step E2, a congested roundabout situation is detected. In step E3, a new kinematic profile P2 i is defined to facilitate the vehicle entering the roundabout. Then, the kinematic profile P2 i In step E1, a new segment S' is created that connects points A and B. i is used to determine the segment S i and S' i In step E4, the autonomous vehicle 100 calculates the segment S' between points A and B. i Controlled to move up.

[0097] Finally, the control method according to the invention uses perception means to detect a set of traffic scenarios and optimize the trajectory of the autonomous vehicle according to the identified traffic scenarios.

[0098] The trajectory optimization according to the present invention implements two optimization levers that can be used independently of each other or simultaneously. The first optimization lever involves locally modifying the map representing the infrastructure of the identified traffic scenario. The second optimization lever involves temporarily increasing the responsiveness of the autonomous vehicle by increasing the maximum speed and / or acceleration and / or jerk thresholds applied in the autonomous vehicle's trajectory.

[0099] The optimization levers are determined depending on the surrounding traffic in order to avoid any collisions. The map modification is preferably performed in the absence of surrounding traffic. The increase in the vehicle's responsiveness is performed under dense traffic conditions and takes into account the maximum collision-free speed calculated from the electronic horizon data. Thus, the trajectory optimization is performed in safe conditions.

[0100] In addition to its reliability in terms of road safety, the present invention has several advantages. First, the present invention reduces the risk of an autonomous vehicle being in a congested situation with high traffic density. By periodically increasing the responsiveness of the autonomous vehicle, this allows it to enter dense traffic more easily and to return to an optimal driving comfort level once the entering maneuver is completed. Thus, the present invention promotes traffic fluidity and driving comfort by adapting the driving style of the autonomous vehicle to the surrounding traffic. More generally, in a given set of situations, the present invention allows an autonomous vehicle to reproduce the optimal choices of a human driver faced with these situations.

[0101] The invention thus enables an autonomous vehicle to adapt its driving responsiveness depending on sensory data related to static data (infrastructure) and dynamic data (in particular traffic) of the driving scene. The driving fluidity of the autonomous vehicle is thus improved, while respecting driving safety, and in particular congested situations are avoided.

Claims

1. A method for controlling an autonomous vehicle (100) comprising at least one perception means (21) and a first map (M1) comprising stored digital data representative of a real infrastructure of an environment of the autonomous vehicle (100), the method comprising the steps of: - a step (E1) of defining a first trajectory (T1) of said autonomous vehicle (100) and an associated first kinematic profile (P1); a step (E2) of detecting, from data transmitted by said at least one perception means (21), a situation to be optimized on a given segment (S) of said first trajectory (T1), said given segment (S) being located in front of said autonomous vehicle (100) over a distance less than a maximum detection distance (DLIM) of said at least one perception means (21); a step (E3) of optimizing at least one element of said first map (M1) and of said first kinematic profile (P1), optimizing the first map comprises determining a local map (M2) on the given segment (S); and / or optimizing the first kinematic profile (P1) comprises determining a second kinematic profile (P2) associated with the given segment (S), wherein at least one parameter of the second kinematic profile (P2) is different from a parameter of the first kinematic profile (P1); Step (E3); - a step (E4) of controlling the movement of said autonomous vehicle (100) on said given segment (S) taking into account said local map (M2) and / or said second kinematic profile (P2); A method comprising:

2. 2. The method according to claim 1, characterized in that determining a local map (M2) enables a new curve of the given segment (S) to be determined between an entry point (A) and an exit point (B) of the given segment (S), in particular by a Bézier curve, and that the new curve has a continuity G2 with the first trajectory (T1) at the entry point (A) and at the exit point (B).

3. 2. The control method according to claim 1, characterized in that determining a second kinematic profile (P2) associated with the given segment (S) comprises calculating a maximum collision-free speed threshold (VCOL) from data originating from the at least one perception means (21), and the second kinematic profile (P2) has a maximum speed below the maximum collision-free speed threshold (VCOL).

4. 4. The method of claim 3, wherein the maximum collision-free speed threshold (VCOL) is calculated by solving an equation such that the maximum collision-free speed threshold (VCOL) is equal to the square root of the product of the braking value required to reach the maximum collision-free speed threshold (VCOL) and twice the maximum detection distance (DLIM) of the at least one sensing means (21).

5. 2. The method of claim 1, wherein the step (E2) of detecting a situation to be optimized comprises measuring a holding time during which the autonomous vehicle (100) remains in the situation to be optimized and comparing the holding time with a triggering threshold associated with the situation, and wherein the optimizing step (E3) is performed when the holding time is greater than the triggering threshold.

6. 2. A control method according to claim 1, characterized in that a set of predefined situations is stored in an electronic memory (6) and that the step (E2) of detecting a situation to be optimized comprises comparing a perception resulting from the at least one perception means (21) with said set of predefined situations.

7. 7. The control method of claim 6, characterized in that the set of predefined situations includes negotiating a roundabout with two empty lanes, and / or entering a roundabout in dense traffic conditions, and / or two lanes of traffic merging into a single lane, and / or crossing a congested junction, and / or overtaking a very slow vehicle on a bidirectional road with a single lane in each direction.

8. 2. The method of claim 1, wherein the second kinematic profile (P2) has a maximum velocity that is at least 20% higher and / or a maximum acceleration that is at least 200% higher and / or a jerk that is at least 1,000% higher than the first kinematic profile (P1).

9. A device (10) for controlling an autonomous vehicle (100), the autonomous vehicle being equipped with a motion actuator (4), the device comprising hardware and / or software elements (1, 2, 3, 5, 6, 7, 11, 12, 13, 14, 21, 22) implementing the method according to any one of claims 1 to 8, in particular hardware and / or software elements (1, 2, 3, 5, 6, 7, 21, 22) designed to implement the method according to any one of claims 1 to 8 and / or the device comprising means for implementing the method according to any one of claims 1 to 8.

10. An autonomous vehicle (100), characterized in that it comprises a control device (10) according to claim 9.

11. 9. A computer program product comprising program code instructions stored on a computer readable medium for implementing the steps of the method according to any one of claims 1 to 8 when the program is executed on a computer or a computer program product downloadable from a communications network and / or stored on a computer readable data medium and / or executable by a computer, characterized in that the computer program product comprises instructions which, when the program is executed by the computer, cause the computer to implement the method according to any one of claims 1 to 8.

12. A computer readable data storage medium storing a computer program comprising program code instructions for implementing the method of claim 1 or as claimed in claim 11, or a computer readable storage medium comprising instructions which, when executed by a computer, cause the computer to implement the method of claim 1.

Images