EP4168828A1 - Procédé et dispositif de contrôle du déplacement d'un véhicule - Google Patents
Procédé et dispositif de contrôle du déplacement d'un véhiculeInfo
- Publication number
- EP4168828A1 EP4168828A1 EP21732960.6A EP21732960A EP4168828A1 EP 4168828 A1 EP4168828 A1 EP 4168828A1 EP 21732960 A EP21732960 A EP 21732960A EP 4168828 A1 EP4168828 A1 EP 4168828A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- dimensional
- vehicle
- dimensional point
- cloud
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000006870 function Effects 0.000 claims description 7
- 238000002592 echocardiography Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 101000582320 Homo sapiens Neurogenic differentiation factor 6 Proteins 0.000 description 1
- 102100030589 Neurogenic differentiation factor 6 Human genes 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004313 glare Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000001429 visible spectrum Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4808—Evaluating distance, position or velocity data
Definitions
- the invention relates to a method and device for controlling the movement of a vehicle, in particular of the automobile type, from a cloud of three-dimensional data obtained by reflection of waves emitted by sensors on board the vehicle.
- ADAS driver assistance systems
- ADAS Advanced Driver-Assistance System
- French Advanced Driver Assistance System
- the most advanced driving assistance systems control the movement of the vehicle which becomes a so-called autonomous vehicle, that is to say a vehicle capable of driving in the road environment without the intervention of the driver.
- An autonomous vehicle of level higher than 2 must be able to estimate the free space all around the vehicle.
- this type of vehicle is generally equipped with various sensors such as video cameras, LIDAR (in English “Laser Detection And Ranging”) or other which are distributed all around the vehicle, in particular on the windshield, the windshields. front and rear shocks or on the roof.
- the data from these sensors can be used, for example by an ADAS system, to estimate the free space located near the vehicle and thus anticipate the driving of the vehicle to avoid any collision with an object in this environment. This is the case, in particular, when the vehicle is traveling on a lane and is approaching another vehicle. An estimate of the free space located between these two vehicles then makes it possible to anticipate possible braking. This is also the case when the vehicle must park in a parking space. An estimate of the free space between the vehicle and any object, wall, ceiling or other parked vehicle helps prevent a collision. This is also the case when the vehicle is traveling in an urban area where the estimation of the free space located in front, behind or on its sides can prove useful to anticipate any collision with possible cyclists, vehicles, street furniture. or other object.
- An object of the present invention is to improve the existing methods making it possible to control the movement of a vehicle by estimating the free space accessible to it. vehicle from a cloud of three-dimensional data from on-board sensors in this vehicle.
- the invention relates to a method for controlling the movement of a vehicle, comprising a step of acquiring a cloud of three-dimensional data obtained by reflection of waves emitted by sensors on board the vehicle; a step of transforming the three-dimensional data cloud into a two-dimensional point cloud expressed in a polar coordinate frame associated with a plane, to each three-dimensional data item corresponds a two-dimensional point defined by a radial distance between a pole of the polar coordinate frame and the two-dimensional point, and an azimuth angle defined between the plane and a segment connecting the pole and the two-dimensional point; an iterative step of modifying the two-dimensional point cloud by deleting a current two-dimensional point when two neighboring two-dimensional points current two-dimensional point are not sufficiently distant from each other to avoid a collision between the vehicle and an object near this vehicle; and a step of controlling the movement of said vehicle as a function of a convex envelope formed by the two-dimensional point cloud thus modified and defining a free space accessible to the vehicle
- the method transforms the three-dimensional data cloud into a two-dimensional point cloud and determines a polygonal convex envelope from a modified two-dimensional point cloud.
- This convex envelope provides an estimate of the free space accessible to the vehicle.
- a system for controlling the movement of the vehicle implementing the method can then control the movement of the vehicle as a function of this convex envelope.
- the method uses simple geometric principles of low complexity compared to those of a method based on a neural network for example. It therefore requires little computing resources.
- the convex envelopes obtained are representative of what is expected in terms of a convex envelope that closely matches a two-dimensional point cloud while respecting steric non-collision constraints.
- the method does not make use of artificial intelligence techniques, therefore does not suffer from the problems associated with this type of technique such as, in particular, validation and security problems.
- the method is independent of the technology or of the sensor model used, as long as the latter provides a cloud of three-dimensional data obtained by reflection of waves emitted by sensors on board the vehicle.
- the method is robust and capable of respecting the constraints of real hard time. This is one of the crucial elements for the development of autonomous driving systems above level 2 which must also operate in all conditions (night, precipitation, etc.).
- an iteration of the iterative step comprises a sub-step of obtaining at least one current two-dimensional point of the two-dimensional point cloud having a high radial distance; and for each current two-dimensional point, a sub-step of calculating a first minimum distance between a segment connecting a current two-dimensional point and the pole of the reference frame of polar coordinates, and another two-dimensional point of the two-dimensional point cloud determined so as to that the difference between the azimuth angle of said other two-dimensional point and the azimuth angle of the current two-dimensional point is minimal and positive; a sub-step of calculating a second minimum distance between said segment and another two-dimensional point of the two-dimensional point cloud determined so that the difference between the azimuth angle of said other two-dimensional point and the angle of azimuth of the current two-dimensional point is minimum and negative; and a sub-step of removing a current two-dimensional point from the two-dimensional point cloud when the sum of the first and second distances is
- an iteration of the iterative step comprises a substep for obtaining at least one pair formed of a first and a second successive two-dimensional points having distances minimum radials among a set of two-dimensional points sorted according to their azimuth angle; and for each current pair of two-dimensional points thus formed: a sub-step of deleting all the two-dimensional points from the two-dimensional point cloud whose azimuth angles are between the azimuth angles of the first and second two-dimensional points of a current torque when the absolute value of the difference between the azimuth angles of the first and second two-dimensional points of said current torque is less than a threshold value defined to avoid a collision between the vehicle and an object near this vehicle; said two-dimensional points of the two-dimensional point cloud are preserved when the absolute value of said difference is greater than the threshold value.
- the method further comprises an (optional) step of deleting the three-dimensional data corresponding to echoes from the ground. This step removes three-dimensional data which correspond to ground echoes and which are therefore irrelevant for estimating the free space around the vehicle.
- the method further comprises a step of filtering the cloud of two-dimensional points making it possible to keep only a single two-dimensional point per azimuth angle.
- At least one sensor is a transmitter / receiver of electromagnetic waves, preferably in the infrared range, of the LIDAR type or a radio wave transmitter / receiver such as a radar.
- the invention relates to a device for moving a vehicle, comprising at least one emitter / receiver of electromagnetic waves and / or radio waves and a memory associated with at least one processor configured for setting up. implementation of the steps of the above method.
- the invention relates to a vehicle comprising the above device.
- the invention relates to a computer program product comprising instructions adapted for performing the above method steps when the computer program is executed by at least one processor.
- FIG. 1 schematically illustrates a vehicle 1 carrying several sensors 10, 11, 12, 13 and 14 according to a particular and non-limiting embodiment of the present invention
- FIG. 2 schematically illustrates a three-dimensional mark associated with a vehicle according to a particular embodiment of the present invention
- FIG. 3 illustrates a flowchart of the various steps of a method for controlling the movement of a vehicle of FIG. 1, according to a particular and non-limiting example of the present invention
- FIG. 4 illustrates a flowchart of the various sub-steps of step 350 of FIG. 1, according to a particular and non-limiting exemplary embodiment of the present invention
- FIG. 5 schematically illustrates the various sub-steps of step 350 of FIG. 4, according to another particular and non-limiting example of embodiment of the present invention
- FIG. 6 illustrates a flowchart of the various sub-steps of step 350 of FIG. 1, according to another particular and non-limiting exemplary embodiment of the present invention
- FIG. 7 schematically illustrates the various sub-steps of step 350 of FIG. 6, according to another particular and non-limiting exemplary embodiment of the present invention.
- FIG. 8 schematically illustrates a device configured to control the movement of a vehicle of Figure 1, according to a particular non-limiting embodiment of the present invention.
- FIG. 1 schematically illustrates a vehicle 1, for example a motor vehicle or more generally a land motor vehicle, carrying several sensors 10, 11, 12, 13 and 14 according to a particular and non-limiting example of the present invention.
- the sensors 10 and 11 are positioned on the front and rear bumpers of the vehicle 1, the sensors 12 and 13 on the sides and the sensor 14 on the roof.
- This example of the positioning of the sensors as well as the number of sensors are given only as an indication and in no way limit the scope of the invention. Indeed, several other sensors can be positioned in various other places of the vehicle such as on the windshield, windows, doors, etc.
- the sensors 10 to 14 on board the vehicle 1 are sensors suitable for emitting and receiving waves and determining the distance from surrounding objects by analysis of the emitted waves which are reflected on objects located at proximity to the vehicle and in the field of action of these sensors.
- These sensors 10 to 14 are periodically active. The period between two emissions may depend on the movement of the vehicle. It may for example depend on the speed of the vehicle. The faster the vehicle, the shorter the period can be.
- the activity of sensors can still be continuous when, in particular, the vehicle is looking for a parking space and / or is maneuvering to park in a parking space.
- the activation of these sensors can also be individualized. For example, if the vehicle is backing up, the sensors on the front of the vehicle are not activated.
- a sensor once activated, makes it possible to detect objects in the environment of the vehicle and to measure the distance between the sensor and the detected objects. These objects can be, for example, other vehicles, pedestrians, cyclists, street furniture, reflective strips delimiting a parking space, etc.
- the active sensor emits waves that reflect off these objects.
- the active sensor collects these reflected waves and identifies the position and the distance of the objects located near the vehicle 1 as a function of these emitted and reflected waves.
- a multi-dimensional data cloud is then formed. Each of these multidimensional data corresponds to at least one emitted wave which has been reflected by an object.
- the free space accessible to a vehicle is defined as a set of data expressed in a multidimensional space. These data can theoretically take all the possible values in this space of the kinematic parameters of the vehicle, taking into account the constraints of non-collision with objects present around it.
- the multi-dimensional space is a subspace of M 6 corresponding to the three parameters of position (x, y, z) and orientation ⁇ a, b, g) of the vehicle in the space.
- the vehicle will be assumed to be spherical with a sufficient radius to ensure compliance with the non-collision constraints.
- the dimensions relative to the orientation are degenerated, and the data space is reduced to a three-dimensional space (x, y, z) as illustrated in figure 2.
- the dimensionality of this three-dimensional space (x, y, z) can be reduced by assuming that a vehicle is moving on a locally flat surface, and that the extension of the instantaneous scene of which the vehicle is the center is much less depending on the 'z axis than along the x and y axes.
- the dimensionality of the three-dimensional space can therefore be reduced to a two-dimensional space (x, y).
- the three-dimensional data obtained from the sensors on board the vehicle will therefore be represented by two-dimensional data expressed in a coordinate system (0, x, y).
- the invention then consists in determining a convex envelope in this two-dimensional space representing the free space accessible to the vehicle 1.
- This convex envelope complies with the constraints of non-collision between this vehicle and any surrounding objects. Due to the discrete nature of the information available, in the form of a three-dimensional data cloud, this convex envelope is a polygon whose vertices are two-dimensional points originating from the three-dimensional data cloud.
- FIG. 3 illustrates a flowchart of the various steps of a method for estimating free space accessible to a vehicle of FIG. 1, according to a particular and non-limiting example of the present invention.
- Each three-dimensional data represents the coordinates of a point in three-dimensional space.
- the three-dimensional data cloud can be represented by a matrix P of dimension 3xN formed of three vectors X, YZ of dimension N representing the coordinates xi, yi, zi of the three-dimensional data Pw [Math 1] with respectively ⁇ and of f Z represents the transpose of the vector X, respectively Y and Z.
- At least one sensor is a transmitter / receiver of electromagnetic waves, for example of the LIDAR type, and / or a transmitter / receiver of radio waves.
- a LIDAR sensor makes it possible to detect objects in the environment of the vehicle and to measure the distance between the sensor and the objects detected by the emission of light rays (electromagnetic waves) emitted by lasers radiating preferably in the non-visible range ( infrared for example).
- the method comprises a step 320 (optional) of deleting the three-dimensional data corresponding to echoes from the ground.
- the segmentation algorithm of B. Douillard et al. (On the Segmentation of 3D LIDAR Point Clouds", 2011 IEEE International Conference on Robotics and Automation (http://dx.doi.Org/10.1109/ICRA.2011.5979818)) can be used to isolate three-dimensional data that correspond to ground echoes of other three-dimensional data and remove those isolated three-dimensional data.
- We can also use the algorithm of I. Bogoslavskiy & C. Stachniss (“Efficient Online Segmentation for Sparse 3D Laser Scans", Photogrammetrie - Fernerkundung - Geoinformation 85, 41 (2016) (http://dx.doi.org/10.1007 / s41064-016-0003-y), or that of Y.
- the three-dimensional data cloud Pi is transformed into a cloud of two-dimensional points Mi expressed in a reference frame of polar coordinates (r, ⁇ p) associated with a plane P with r a polar coordinate called the radial distance defined between a pole O of the polar coordinate system and a two-dimensional point belonging to the plane P and f another polar coordinate called the azimuth angle defined between the plane P and a segment connecting the pole O and the two-dimensional point of the plane P as shown in the figure 5.
- each three-dimensional datum Pi corresponds a two-dimensional point Mi of the plane P.
- the case may arise where several two-dimensional points share the same azimuth angle. This may be due to a mode of operation of a sensor which can record several echoes for a single emitted wave, for example when the laser beam meets a window, then a solid obstacle further away. This can also be due to the sampling steps of the sensors to determine an azimuth angle.
- the transform of the three-dimensional data cloud Pi represented by points Mi expressed in the coordinate system (0, x, y), into a cloud P s of two-dimensional points Mi expressed in a coordinate system with polar coordinates (t, f) is given by:
- P s is a 2xN-dimensional matrix formed by two vectors R and F of dimension N and the function arctan2 is the four-quadrant arc tangent giving the value of an angle in the interval [0,2p [.
- P s can therefore be described as a function of a single scalar variable r ( ⁇ p).
- the method comprises a step 340 (optional) which filters the three-dimensional data cloud Pi by keeping only a single two-dimensional point Mi per azimuth angle value.
- step 340 when several two-dimensional points share a same azimuth angle value and different radial distance values, only the two-dimensional point having the smallest radial distance is kept in the two-dimensional point cloud.
- step 340 when several two-dimensional points share the same azimuth angle value and different radial distance values, a two-dimensional point is created with said azimuth angle value and an equal radial distance to a value obtained from the values of the radial distances of these two-dimensional points such as the average or the median of these radial distances.
- the cloud Ps of two-dimensional points is modified by deleting a current two-dimensional point when two two-dimensional points neighboring the current two-dimensional point are not sufficiently distant from each other to avoid a collision between the vehicle and an object near that vehicle.
- the two-dimensional point cloud Ps thus modified forms a convex envelope of the free space accessible to the vehicle.
- a step 360 the movement of the vehicle is controlled by a control system which implements the previous steps to obtain this cloud P s of two-dimensional points.
- This two-dimensional point cloud forms a convex envelope of the free space accessible to the vehicle and this control system can then indicate what are the possible movements of the vehicle as a function of this convex envelope.
- FIG. 4 illustrates a flowchart of the various sub-steps of step 350 of FIG. 1, according to a particular and non-limiting exemplary embodiment of the present invention.
- a sub-step 351 at least one current two-dimensional point Mi.max of the cloud P s of two-dimensional points having a high radial distance is obtained.
- a given number of current two-dimensional points Mi.max having the highest radial distances are obtained from the cloud P s of two-dimensional points.
- any two-dimensional point of the cloud Ps of two-dimensional points whose radial distance is greater than a given threshold value is a current two-dimensional point Mi.
- a current two-dimensional point Mi.max is obtained from a subset of the two-dimensional points of the cloud Ps of two-dimensional points.
- a current two-dimensional point Mi.max is then a two-dimensional point of this subset which has the maximum radial distance (the highest among the radial distances of the other two-dimensional points of this subset).
- a subset of the two-dimensional point cloud Ps can be obtained, for example, by grouping the two-dimensional points according to their azimuth angles sorted in ascending order, for example. It is in fact possible to partition a circle into different angular sectors and create a subset of two-dimensional points per angular sector.
- a two-dimensional point having its azimuth angle which belongs to a given angular sector then belongs to the subset associated with this angular sector. It is also possible to envisage forming subsets of a given number of successive two-dimensional points, that is to say of two-dimensional points whose azimuth angles follow one another in a list of the azimuth angles of the two-dimensional points sorted according to an order, for example ascending. A first two-dimensional point is added to a first subset. Then the two-dimensional point whose azimuth angle is the next in the list is also added to this first subset, and so on until the two-dimensional point subset has reached a given number of points two-dimensional. Another sub-subset is then formed until the two-dimensional points of the two-dimensional point cloud Ps are exhausted.
- Sub-steps 352, 353 and 354 are executed for each current two-dimensional point Mi.max
- a first minimum distance D1 is calculated between a segment connecting the current two-dimensional point Mi.max and the pole O of the coordinate system with polar coordinates, and another two-dimensional point Mi + i of the cloud P s of two-dimensional points or, according to a variant, of a subset of the cloud Ps.
- This two-dimensional point Mi + i is determined so that the difference between its azimuth angle ⁇ p i + 1 and l ' azimuth angle (p t of the current two-dimensional point Mi.max is minimal and positive when one considers that the azimuth angles increase in the anti-clockwise direction.
- a second minimum distance D2 is calculated between a segment connecting the current two-dimensional point Mi.max and the pole O of the reference frame of polar coordinates, and another two-dimensional point MM of the cloud Ps of two-dimensional points or, according to a variant, of a subset of the cloud Ps.
- This two-dimensional point MM is determined so that the difference between its azimuth angle and the azimuth angle (p t of the current two-dimensional point Mi is minimal and negative when one considers that the azimuth angles increase in the anti-clockwise direction.
- the distances D1 and D2 ensure that the two-dimensional points Mi + i and Mi-i are the “left” and “right” neighboring two-dimensional points of the closest current two-dimensional point Mi.max.
- the current two-dimensional point Mi.max is then deleted from the cloud P s of two-dimensional points when the sum of the first and second distances D1 and D2 is less than a threshold value T.
- the current two-dimensional point Mi.max is kept when the sum of the first and second distances is greater than the threshold value.
- the method determines whether a new iteration of step 350 is necessary by checking whether a condition is satisfied or not. If a new iteration of step 350 is required, substeps 351 to 354 are executed again. According to one example, the method stops when no two-dimensional point Mi, max is deleted in the previous step.
- the process stops when a number of two-dimensional points have been deleted.
- FIG. 6 illustrates a flowchart of the various sub-steps of step 350 of FIG. 1, according to another particular and non-limiting exemplary embodiment of the present invention.
- At least one pair formed of a first and a second successive two-dimensional points is formed.
- the two-dimensional points of the point cloud P s are sorted according to an order, for example increasing, of their azimuth angles.
- Two two-dimensional points are then said to be successive when the difference in azimuth angles is minimal.
- a first and a second two-dimensional point form a couple when they are successive and when they have the smallest (minimum) radial distances among the radial distances of a set of two-dimensional points.
- each pair of two-dimensional points Mj and Mk is obtained from the cloud P s of two-dimensional points.
- the two-dimensional points Mj and Mk are then successive two-dimensional points of the cloud Ps which have a radial distance less than a threshold value.
- each pair of two-dimensional points Mj and Mk is obtained from a subset of the two-dimensional points of the cloud Ps.
- the two-dimensional points Mj and Mk are then successive two-dimensional points of this subset of the cloud P s which have minimum radial distances (the smallest among the radial distances of the other two-dimensional points of this subset of the cloud P s ).
- a subset of the Ps cloud can be obtained, for example, by grouping the two-dimensional points according to their azimuth angles. It is in fact possible to partition a circle into different angular sectors and create a subset of two-dimensional points per angular sector. A two-dimensional point having its azimuth angle which belongs to a given angular sector then belongs to the subset associated with this angular sector. It is also possible to envisage forming sub- sets of a given number of successive two-dimensional points. A first two-dimensional point is added to a first subset. Then the two-dimensional point having a positive and minimum azimuth angle difference with the first two-dimensional point is also added to this first subset. And so on until the subset of two-dimensional points has reached a given number of two-dimensional points. Another sub-subset is then formed until the two-dimensional points of the cloud Ps are exhausted.
- a sub-step 356 illustrated in FIG. 7 for each pair of two-dimensional points Mj and Mk consult the two-dimensional points M P with j ⁇ p ⁇ k, corresponding to the two-dimensional points whose azimuth angles lie between the angles azimuth of the two-dimensional points Mj and Mk are then deleted when the absolute value of the difference between the azimuth angles of the two-dimensional points Mj and Mk is less than a threshold value T. Said two-dimensional points are kept when the absolute value of said difference is greater than the threshold value T.
- step 350 determines whether a new iteration of step 350 is necessary by checking whether a condition is true or not. If a new iteration of step 350 is required, substeps 355 through 357 are executed again.
- the process stops when a given number of two-dimensional points have been deleted.
- the method stops when no two-dimensional point has been deleted in a previous iteration.
- the threshold value T is defined to avoid any collision between the vehicle and an object near this vehicle. Indeed, only the two-dimensional points distant by a value greater than the threshold value T are used to form the convex envelope of the free space.
- the cloud P s is formed from three-dimensional data coming from sensors located on the front of the vehicle, the convex envelope formed by the corresponding two-dimensional points will indicate that the vehicle can pass between these two-dimensional points without risk of collision. It is the same for any convex envelope formed by a cloud of three-dimensional data. modified according to the invention. The vehicle can thus move without risk of collision between the three-dimensional data of the convex envelope.
- the threshold value T varies according to the dimensions of the vehicle.
- the threshold value T is at least equal to the width of the vehicle.
- the threshold value is at least equal to the length of the vehicle.
- the threshold value T is greater than the dimensions of the vehicle to increase the free space and thus facilitate maneuvering of the vehicle inside the convex envelope representing this free space without risk of collision
- FIG. 8 schematically illustrates a device 400 configured to control the movement of a vehicle based on the estimate of the free space accessible to this vehicle, according to a particular and non-limiting embodiment of the present invention.
- the device 400 corresponds for example to a device on board the vehicle, such as for example a computer or a set of computers.
- the device 400 is for example configured for the implementation of the steps of the method described with reference to FIGS. 3, 4 and / or 6.
- Examples of such a device 400 include, without being limited thereto, on-board electronic equipment such as 'an on-board computer of a vehicle, an electronic computer such as an ECU (“Electronic Control Unit”), a smart phone (from the English “smartphone”), a tablet, a laptop computer.
- ECU Electronic Control Unit
- smart phone from the English “smartphone”
- a tablet a laptop computer.
- the elements of the device 400 individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and / or in discrete components.
- the device 400 can be produced in the form of electronic circuits or software (or computer) modules or else a combination of electronic circuits and software modules.
- the device 400 is coupled in communication with other devices or similar systems, for example by means of a communication bus or through dedicated input / output ports.
- the device 400 comprises one (or more) processor (s) 410 configured to execute instructions for carrying out the steps of the method and / or for executing the instructions of the software (s) embedded in the device 410.
- the processor 410 can include integrated memory, an input / output interface, and various circuits known to those skilled in the art.
- the device 410 further comprises at least one memory 420 corresponding for example to a volatile and / or non-volatile memory and / or comprises a memory storage device which may comprise volatile and / or non-volatile memory, such as EEPROM, ROM , PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.
- EEPROM electrically erasable programmable read-only memory
- ROM read-only memory
- PROM electrically erasable programmable read-only memory
- RAM random access memory
- DRAM dynamic random access memory
- SRAM static random access memory
- flash magnetic or optical disk
- the computer code of the on-board software (s) comprising the instructions to be loaded and executed by the processor is for example stored in the memory 420.
- the device 400 comprises a block 430 of interface elements for communicating with external devices, for example a remote server or the “cloud”, devices such as a communication reader. near field or a radio receiver.
- Block 430 of interface elements is also configured to receive a three-dimensional data cloud from on-board sensors such as sensors 10-14.
- Block 430 of interface elements is also configured to emit a two-dimensional point cloud. and / or a convex envelope formed from this two-dimensional point cloud resulting from the method described with reference to FIGS. 3, 4 and / or 6.
- the interface elements of block 430 include one or more of the following interfaces:
- radiofrequency interface for example of the Bluetooth® or Wi-Fi® type, LTE (from English “Long-Term Evolution” or in French “Long-term Evolution”), LTE-Advanced (or in French LTE-advanced );
- USB interface from English “Universal Serial Bus” or “Bus Universel en Série” in French);
- the device 400 comprises a communication interface 440 which makes it possible to establish communication with other devices via a communication channel 450.
- the communication interface 440 corresponds for example to a transmitter configured for transmitting and receiving information and / or data via the communication channel 450 such as three-dimensional data clouds, two-dimensional point clouds and / or convex envelopes formed from these two-dimensional point clouds.
- the communication interface 440 corresponds for example to a wired network of the CAN type (standing for “Controller Area Network” or in French “Network of controllers”), CAN FD (standing for “Controller Area Network Flexible Data”). Rate ”or in French
- Flexible data rate controller network FlexRay (according to ISO 17458) or Ethernet (according to ISO / IEC 802.3).
- the device 400 can supply output signals to one or more external devices, such as a display screen, one or more speakers and / or other peripherals respectively via interfaces. output not shown.
- one or more external devices such as a display screen, one or more speakers and / or other peripherals respectively via interfaces. output not shown.
- the vehicle 1 of Figure 1 carries a device of Figure 7.
- the invention is not limited to the embodiments described above but extends to a method of controlling the use of a vehicle, and to the device configured for implementing the method.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR2006537A FR3111713B1 (fr) | 2020-06-23 | 2020-06-23 | Procédé et dispositif de contrôle du déplacement d’un véhicule |
PCT/FR2021/050798 WO2021260283A1 (fr) | 2020-06-23 | 2021-05-10 | Procédé et dispositif de contrôle du déplacement d'un véhicule |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4168828A1 true EP4168828A1 (fr) | 2023-04-26 |
Family
ID=73642973
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP21732960.6A Pending EP4168828A1 (fr) | 2020-06-23 | 2021-05-10 | Procédé et dispositif de contrôle du déplacement d'un véhicule |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP4168828A1 (fr) |
FR (1) | FR3111713B1 (fr) |
WO (1) | WO2021260283A1 (fr) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE1919782A1 (de) | 1968-04-19 | 1969-11-06 | Celanese Corp | Verfahren zur Herstellung von bis-Hydroxyalkyl-estern von Benzol-dicarbonsaeuren |
US10705220B2 (en) * | 2018-04-19 | 2020-07-07 | Faraday & Future Inc. | System and method for ground and free-space detection |
-
2020
- 2020-06-23 FR FR2006537A patent/FR3111713B1/fr active Active
-
2021
- 2021-05-10 EP EP21732960.6A patent/EP4168828A1/fr active Pending
- 2021-05-10 WO PCT/FR2021/050798 patent/WO2021260283A1/fr unknown
Also Published As
Publication number | Publication date |
---|---|
FR3111713B1 (fr) | 2022-07-08 |
FR3111713A1 (fr) | 2021-12-24 |
WO2021260283A1 (fr) | 2021-12-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA3063011A1 (fr) | Systeme et procede de detection et de suivi d`objets | |
FR3096637A1 (fr) | Procédé et dispositif de détermination d’un chemin pour un véhicule autonome | |
EP4176286A1 (fr) | Système et procédé de détection d'un obstacle dans un environnement d'un véhicule | |
EP3729327A1 (fr) | Methode de reconnaissance d'objets dans une scene observee en trois dimensions | |
EP4168828A1 (fr) | Procédé et dispositif de contrôle du déplacement d'un véhicule | |
WO2022152986A1 (fr) | Procédé et dispositif de suivi de trajectoire d'un véhicule circulant sur une voie de circulation | |
FR3106108A1 (fr) | Procédé et dispositif de détermination de trajectoire d’une route | |
FR3118669A1 (fr) | Procédé et dispositif de détermination d’une trajectoire d’un véhicule autonome | |
FR3119817A1 (fr) | Procédé et dispositif de détermination d’une trajectoire pour un véhicule autonome | |
EP4090565B1 (fr) | Procédé et dispositif de contrôle d'un vehicule | |
WO2024115827A1 (fr) | Procédé et dispositif de contrôle d'un système d'aide à la conduite dans un environnement comportant un croisement | |
WO2023144470A1 (fr) | Procédé et dispositif de contrôle de trajectoire d'un véhicule autonome circulant dans un environnement comprenant au moins un objet mobile | |
FR3118746A1 (fr) | Procédé et dispositif d’aide à la conduite d’un véhicule circulant sur une chaussée comprenant plusieurs voies de circulation | |
FR3123862A1 (fr) | Procédé et dispositif de contrôle d’un véhicule autonome | |
WO2023099828A1 (fr) | Procédé et dispositif de contrôle d'un système de régulation adaptative de vitesse d'un véhicule | |
FR3128678A1 (fr) | Procédé et dispositif de contrôle de trajectoire d’un véhicule autonome | |
FR3130228A1 (fr) | Procédé et dispositif de contrôle d’un système de changement de voie automatique | |
WO2022157433A1 (fr) | Procédé et dispositif de contrôle d'un premier véhicule suivant un deuxième véhicule sur une portion de route comprenant un virage | |
EP4351946A1 (fr) | Procédé de régulation de vitesse d'un véhicule circulant sur une chaussée à partir d'un véhicule cible | |
FR3123981A1 (fr) | Procédé et dispositif de contrôle de trajectoire d’un véhicule autonome | |
FR3129911A1 (fr) | Procédé et dispositif de contrôle d’un système d’aide à la conduite | |
EP4399135A1 (fr) | Procédé et dispositif de contrôle de vitesse d'un véhicule autonome | |
WO2023078936A1 (fr) | Traitement de données d'un capteur lidar | |
WO2022258892A1 (fr) | Procédé et dispositif de régulation de vitesse d'un véhicule à partir d'un véhicule cible | |
WO2023088932A1 (fr) | Titre : procédé de détermination de l'orientation relative de deux véhicules |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20221121 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: STELLANTIS AUTO SAS |