EP4176376A1 - Procédé et appareil de commande pour la commande d'un véhicule automobile - Google Patents

Procédé et appareil de commande pour la commande d'un véhicule automobile

Info

Publication number
EP4176376A1
EP4176376A1 EP21735216.0A EP21735216A EP4176376A1 EP 4176376 A1 EP4176376 A1 EP 4176376A1 EP 21735216 A EP21735216 A EP 21735216A EP 4176376 A1 EP4176376 A1 EP 4176376A1
Authority
EP
European Patent Office
Prior art keywords
dimensional
road
motor vehicle
road user
trajectory
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.)
Withdrawn
Application number
EP21735216.0A
Other languages
German (de)
English (en)
Inventor
Till Nattermann
Anne Stockem Novo
Martin Krüger
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZF Friedrichshafen AG
Original Assignee
ZF Friedrichshafen AG
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZF Friedrichshafen AG filed Critical ZF Friedrichshafen AG
Publication of EP4176376A1 publication Critical patent/EP4176376A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—Longitudinal speed

Definitions

  • the invention relates to a method for controlling a motor vehicle.
  • the invention also relates to a control unit for a system for controlling a motor vehicle, a motor vehicle and a computer program.
  • One of the tasks of driver assistance systems which control a longitudinal movement and a lateral movement of a motor vehicle in a partially automated manner, and above all for fully automated motor vehicles, is to analyze a specific situation in which the motor vehicle is located and, based on this, to carry out appropriate driving maneuvers for the vehicle To determine and execute motor vehicle in real time.
  • the complexity of the calculation of the driving maneuvers generally increases with the duration of the individual driving maneuvers. If different, possible driving maneuvers are to be determined for a longer period of time, for example longer than three seconds, or complex driving maneuvers with several lane changes are involved, previously known methods are often no longer able to determine these in real time.
  • the object of the invention is therefore to provide a method and a control unit for controlling a motor vehicle that predicts possible driving maneuvers by other road users.
  • the object is achieved according to the invention by a method for controlling a motor vehicle which is driving on a road in a current lane, the motor vehicle having at least one sensor which is designed to detect at least one area of the current lane lying in front of the motor vehicle, and being on the current lane and/or at least one other road user is in at least one other lane.
  • the method comprises the following steps: acquiring environmental data using the at least one sensor, the environmental data including information about properties of the current lane, properties of the at least one other lane and/or the at least one other road user;
  • the utility value function assigning a utility value for the at least one other road user to different spatial regions of the current lane and/or the at least one other lane in each case at a predefined point in time;
  • the benefit represents a cost-benefit analysis for the at least one other road user to go to the corresponding area
  • a high utility value corresponds to high costs or a low benefit, while a low utility value corresponds to low costs or a high benefit.
  • the utility value is increased, for example, if traffic rules have to be broken in order to reach the corresponding area. Furthermore, the utility value is increased if predefined longitudinal and/or transverse distances to other road users are undercut, high accelerations are necessary, etc.
  • the utility value is reduced, for example, if the relevant area of the road enables the destination to be reached quickly and collisions are safely avoided the corresponding driving maneuver requires only low acceleration, etc.
  • the two-dimensional representation is a depiction of the traffic situation in an area surrounding the motor vehicle at a specific point in time. Accordingly, the two-dimensional representation has two spatial axes, in particular one of the spatial axes corresponding to a direction of travel of the motor vehicle and the other of the spatial axes corresponding to a transverse direction.
  • the method according to the invention is based on the basic idea of not calculating the probable trajectory of the at least one other road user directly from the utility value function using a conventional algorithm, but instead determining the two-dimensional representation of the utility value function and applying pattern recognition to the two-dimensional representation. The expected trajectory is then determined based on this pattern recognition.
  • the probable trajectory can be a family of trajectories. In other words, different possible trajectories together with their respective probability can be determined for the at least one other road user.
  • One aspect of the invention provides that a two-dimensional representation of the corresponding utility value function is determined at several predefined points in time, in particular in the past, and the at least one expected trajectory of the at least one other road user is determined based on the two-dimensional representations by a Pattern recognition is applied to the two-dimensional representations.
  • the set of two-dimensional representations at different points in time represents the course of the traffic situation over an observation period.
  • several utility value functionals and their respective two-dimensional representations are determined for the observation period, each representing a fixed point in time.
  • the data from the observation period are then used to predict the future trajectory of the at least one other road user.
  • the observation period can be between one second and five seconds, for example, in particular between two and three seconds.
  • a three-dimensional tensor is determined based on the two-dimensional representations, the at least one probable trajectory of the at least one other road user being determined based on the tensor by applying pattern recognition to the tensor.
  • the data available from the observation period is summarized in a single three-dimensional tensor, so that all data from the observation period can be used for pattern recognition.
  • the two-dimensional representations are stacked on top of each other along the time dimension to determine the tensor.
  • the three-dimensional tensor thus has two dimensions, which correspond to the spatial dimensions of the road, and a temporal dimension.
  • the different spatial areas are represented as grid points.
  • the road is divided into a two-dimensional grid, with the individual grid points of the grid each representing an area of the road.
  • the utility value functional assigns the corresponding utility value for the at least one other road user to each of the grid points.
  • the pattern recognition is preferably carried out using an artificial neural network, in particular using a convolutional neural network.
  • Artificial neural networks in particular convolutional neural networks, are particularly well suited for pattern recognition in multidimensional structures.
  • a further aspect of the invention provides that the artificial neural network has two-dimensional and/or three-dimensional filter kernels and/or that the artificial neural network has two-dimensional or three-dimensional pooling layers.
  • the artificial neural network has two-dimensional filter kernels and two-dimensional pooling layers. All time strips of the three-dimensional tensor are processed here simultaneously by means of the two-dimensional filter kernel, with a depth of the filter kernel in the time direction corresponding to a number of input channels.
  • the number of input channels is equal to the number of time strips of the three-dimensional tensor, i.e. equal to the number of two-dimensional representations in the observation period. It has been found that the artificial neural network in this embodiment of the invention can be trained more easily and faster and that less data has to be stored.
  • the artificial neural network includes three-dimensional filter kernels and three-dimensional pooling layers. Accordingly, here only a predefined number of time strips of the three-dimensional tensor are processed simultaneously by means of the three-dimensional filter kernel. Accordingly, the depth of the filter kernels in the time direction is also smaller here than the number of time strips of the three-dimensional tensor. In addition to being shifted along the spatial dimensions, the filter kernels are also shifted along the time dimension, so that pattern recognition is also possible along the time dimension takes place. It has been found that although the artificial neural network is more difficult to train in this embodiment of the invention, the accuracy of the probable trajectory of the at least one other road user is significantly improved.
  • the artificial neural network is also preferably trained with a training data set before it is used in the motor vehicle.
  • this offers the advantage that the same training data record can be used for each motor vehicle, so that not every motor vehicle first has to be trained when it is in use.
  • this offers the advantage that the time-consuming and computationally intensive training of the artificial neural network can be carried out centrally on a computer or computer network equipped accordingly with computing resources.
  • the two-dimensional representation is a two-dimensional image, in particular with a color of the individual pixels being determined based on the value of the corresponding utility value.
  • the current traffic situation is translated into one or more images.
  • the predicted trajectory of the at least one other road user is then predicted based on the pattern recognition that is applied to the image or images.
  • the value of the utility value in the two-dimensional representation is encoded in shades of gray, in particular at the corresponding grid points.
  • any other suitable color scheme can also be used.
  • a higher value of the useful value can correspond to a darker pixel in the two-dimensional representation and a lower useful value to a lighter pixel in the two-dimensional representation.
  • a higher value of the useful value can also correspond to a lighter pixel and a lower useful value to a darker pixel in the two-dimensional representation.
  • other road users who are spatially within a predefined distance from one another are regarded as a group of other road users, with a common benefit functional being determined for the group of other road users. This saves computing time, since a separate utility value functional or a separate tensor does not have to be determined for each additional road user.
  • a separate probable trajectory is calculated for each of the other road users.
  • a further aspect of the invention provides that, in particular for each other road user in the group, a previous trajectory of the at least one other road user is determined, with the at least one expected trajectory of the at least one other road user being determined based on the determined previous trajectory , in particular the result of the pattern recognition and the previous trajectory being supplied to an artificial neural network which determines the at least one anticipated trajectory.
  • the probable trajectory of the at least one other road user is determined based on a combination of pattern recognition and observation of the previous trajectory, in particular by means of another artificial neural network, whose input data are the result of the pattern recognition and the determined previous trajectory.
  • the previous trajectory is determined using a trajectory detection module.
  • the probable trajectory can take place by means of a trajectory determination module.
  • the structure and functioning of the trajectory recognition module and the trajectory determination module per se are already known from the publication "Convolutional Social Pooling for Vehicle Trajectory Prediction” by N.Deo and MM Trivedi, arXiv: 1805.06771, which is based on presented at the IEEE CVPR Workshop 2018.
  • these modules are combined with pattern recognition, which recognizes patterns in the two-dimensional representations or in the three-dimensional tensor.
  • the information about the properties of the current lane and/or about the properties of the at least one other lane can include at least one of the following elements: location and/or course of lane markings, type of lane markings, location and/or type of traffic signs, location and/or or course of crash barriers, location and/or circuit status of at least one traffic light, location of at least one parked vehicle.
  • the information about the at least one other road user includes a location of the at least one other road user, a speed of the at least one other road user and/or an acceleration of the at least one other road user.
  • the at least one probable trajectory is transferred to a driving maneuver planning module of the motor vehicle.
  • the driving maneuver planning module determines a driving maneuver to be carried out by the motor vehicle based on the at least one anticipated trajectory and based on the environmental data. In this case, an interaction of the motor vehicle with the other road users via the probable trajectories of the other road users is taken into account.
  • the driving maneuver to be carried out is then transferred to a trajectory planning module of the motor vehicle.
  • the trajectory planning module determines the specific trajectory that the motor vehicle should follow.
  • the motor vehicle can then be controlled automatically at least partially, in particular completely, based on the determined trajectory.
  • At least the current lane and/or the at least one further lane are transformed into a Frenet-Serret coordinate system.
  • every road is free of curvature, so that every road traffic situation can be treated in the same way, regardless of the actual course of the road.
  • control unit for a system for controlling a motor vehicle or for a motor vehicle, the control unit being designed to carry out the method described above.
  • the object is also achieved according to the invention by a motor vehicle with a control unit as described above.
  • a computer program with program code means to carry out the steps of a method described above when the computer program is executed on a computer or a corresponding processing unit, in particular a processing unit of a control device described above.
  • program code means to carry out the steps of a method described above when the computer program is executed on a computer or a corresponding processing unit, in particular a processing unit of a control device described above.
  • Program code means are to be understood here and below as computer-executable instructions in the form of program code and/or program code modules in compiled and/or uncompiled form, which can be present in any programming language and/or in machine language.
  • FIG. 1 schematically shows a road traffic situation
  • FIG. 2 is a schematic block diagram of a system for controlling a motor vehicle by means of a method according to the invention
  • FIG. 3 shows a flow chart of the steps of a method according to the invention
  • FIGS. 4 (a) and 4 (b) schematically show a road before a transformation into a Frenet-Serret coordinate system and the road after a transformation into a Frenet-Serret coordinate system;
  • FIG. 6 shows schematically a stack of two-dimensional representations of one of the utility functionals from FIG. 5 at different points in time;
  • FIG. 7 shows a schematic block diagram of a computer program for carrying out the method according to the invention.
  • FIG. 8 shows schematically a first possible architecture of an artificial neural network of the computer program of FIG. 7;
  • FIG. 9 shows schematically a second possible architecture of an artificial neural network of the computer program of FIG. 7.
  • FIG. 10 schematically an alternative architecture of the computer program of figure 7.
  • a road traffic situation is shown schematically in FIG. 1, in which a motor vehicle 10 is driving on a road 12 in a current lane 14 .
  • a first other road user 18, a second other road user 20 and a third other road user 21 are also driving on the road 12 in the current lane 14 or in the other lane 16.
  • the other road users 18, 20, 21 are passenger cars, but they could also be trucks, motorcycles or any other road user.
  • the dashed lines 22 and 24 indicate that the first other road user 18 is planning in the near future to change from the current lane 14 to the other lane 16 or that the second other road user 20 is planning in the near future to leave the other lane 16 to switch to the current lane 14 of the motor vehicle 10 .
  • This is indicated by the other road users 18, 20, for example, by using the corresponding direction indicator.
  • FIG. 1 shows a coordinate system with a longitudinal axis and a normal axis, the longitudinal axis defining a longitudinal direction L and the normal axis defining a transverse direction N.
  • the origin of the coordinate system is in the longitudinal direction L at the current position of the front of the motor vehicle 10 and, seen in the longitudinal direction L, on the right-hand side of the road.
  • motor vehicle 10 has a system 26 for controlling motor vehicle 10 .
  • System 26 includes a plurality of sensors 28 and at least one control unit 30.
  • the sensors 28 are arranged at the front, rear and/or side of the motor vehicle 10 and are designed to detect the surroundings of the motor vehicle 10 , to generate corresponding surroundings data and to forward them to the control unit 30 . More precisely, the sensors 28 record information at least about the current lane 14, the other lane 16 and the other road users 18, 20, 21.
  • the sensors 28 are in each case a camera, a radar sensor, a distance sensor, a LIDAR sensor and/or any other type of sensor that is suitable for detecting the surroundings of the motor vehicle 10 .
  • At least one of sensors 28 can be designed as an interface to a control system that is assigned to at least the section of road 12 shown and is designed to transmit environmental data about road 12 and/or about other road users 18, 20, 21 to the Motor vehicle 10 and / or to the other road users 18, 20, 21 to transmit.
  • one of the sensors 28 can be designed as a mobile radio communication module, for example for communication according to the 5G standard.
  • control unit 30 processes the environmental data received from the sensors 28 and controls the motor vehicle 10 based on the processed environmental data at least partially automatically, in particular fully automatically.
  • a driver assistance system is therefore implemented on control unit 30, which can control a transverse movement and/or a longitudinal movement of motor vehicle 10 at least partially automatically, in particular fully automatically.
  • control unit 30 is designed to carry out the method steps explained below with reference to FIGS. 3 to 10.
  • control unit 30 includes a data carrier 32 and a computing unit 34, data medium 32 storing a computer program which is executed on computing unit 34 and includes program code means for carrying out the steps of the method explained below.
  • step S1 environmental data are recorded by means of the sensors 28 (step S1).
  • the environmental data includes all information about the environment of motor vehicle 10 that is important for the automated control of motor vehicle 10.
  • the environmental data includes information about the properties of the current lane 14 and the properties of the other lane 16 as well as information about the other road users 18, 20, 21.
  • the information about the properties of the current lane 14 and the properties of the other lane 16 include one or more of the following elements: location and/or course of lane markings, type of lane markings, location and/or type of traffic signs, location and/or course of Crash barriers, location and/or circuit status of at least one traffic light, location of at least one parked vehicle.
  • the information about the other road users 18, 20, 21 includes a respective location of the other road users 18, 20, 21, a respective speed of the other road users 18, 20, 21 and/or a respective acceleration of the other road users 18, 20, 21 .
  • the information about the other road users 18, 20, 21 further a type of the respective Road users 18, 20, 21 include, for example, whether it is a car, a truck, a cyclist or a pedestrian.
  • the road 12 more precisely an image of the current lane 14 and the further lane 16 based on the environmental data received from the sensors 28, is transformed into a Frenet-Serret coordinate system (step S2).
  • Step S2 is illustrated in FIG. Figure 4(a) shows the road 12 as it actually runs.
  • the road viewed in the longitudinal direction L, curves to the left.
  • a local coordinate transformation transforms the road 12 into the Frenet-Serret coordinate system in which the road 12 no longer has any curvature, the result of this transformation being shown in FIG. 4(b).
  • the road 12 runs straight and without curvature along the longitudinal direction L in this coordinate system.
  • a utility value functional is determined, which assigns a utility value for the other road users 18, 20, 21 to various spatial areas of the road 12 at a predefined point in time (step S3).
  • a common utility value functional is determined for groups of other road users who are within a predefined distance from one another.
  • the first other road user 18 is far away from the other two other road users 20, 21. Therefore, a separate utility value functional is determined for the first additional road user.
  • the second and third other road users 20, 21, however, are close together.
  • a common utility value functional is therefore determined for the second and third additional road users 20, 21.
  • the road 12 is divided into a two-dimensional grid in order to determine the utility value function, with the individual grid points of the grid each representing a region of the road 12 .
  • the utility value functionals assign the corresponding utility value for the first additional road user 18 or for the group of second and third additional road users 20, 21 to each of the grid points.
  • the respective utility value at the individual grid points represents a cost-benefit analysis for the first additional road user 18 or for the group of second and third additional road users 20, 21 to go to the corresponding area.
  • a high utility value corresponds to high costs or a low benefit, while a low utility value corresponds to low costs or a high benefit.
  • the utility value is increased, for example, if traffic rules have to be broken in order to reach the corresponding area. Furthermore, the utility value is increased if predefined longitudinal and/or transverse distances to other road users are undercut, high accelerations are necessary, etc.
  • the utility value is reduced, for example, if the corresponding area of the road enables the destination to be reached quickly, collisions are safely avoided, the corresponding driving maneuver only requires low acceleration, etc.
  • step S3 is illustrated in FIG. 5, in which two exemplary plots of utility functionals are shown.
  • the utility value functional is a function U of the longitudinal coordinate L and the transverse coordinate N and assigns a utility value U(L,N) to the individual grid points with coordinates (L,N).
  • the utility functional is a superposition of several utility functions, each of which reflects one or more of the aspects mentioned above.
  • U RE is a contribution from road 12 boundaries to the utility functional.
  • areas outside the road 12 receive a maximum utility value, ie high costs, since the other road users 18, 20, 21 would have to leave the road 12 in order to get there.
  • U LM is a contribution of road markings and their type, traffic signs and their type and/or traffic lights and their switching status.
  • U ov is a contribution from other road users. This post reflects other road users blocking areas of the road. Furthermore, this contribution can also reflect the type of other road users 18, 20, 21 since, for example, a greater distance must be maintained from vulnerable road users.
  • U DV is a contribution from a desired speed to be achieved.
  • the utility functionals can be determined with a predefined frequency, so that a predefined number of utility functionals is determined over a predefined observation period.
  • the predefined frequency can be between 5 and 20 Hz, for example, in particular 8 to 15 Hz, for example 10 Hz.
  • the observation period can be between one second and five seconds, for example, in particular between two and three seconds.
  • the observation period extends from a starting point in the past to the present.
  • a two-dimensional representation of the corresponding utility value functional is determined for each of the determined utility value functionals (step S4).
  • the two-dimensional representations are each a two-dimensional image, with a color of the individual pixels being determined based on the value of the corresponding utility value at the corresponding grid point.
  • the value of the utility at the corresponding grid point is grayscale encoded.
  • any other suitable color scheme can also be used.
  • a higher value of the useful value can correspond to a darker pixel and a lower useful value to a lighter pixel in the two-dimensional representation.
  • a higher value of the useful value can also correspond to a lighter pixel and a lower useful value to a darker pixel in the two-dimensional representation.
  • a two-dimensional representation is determined for each of the utility value functionals that are determined at different times.
  • a two-dimensional representation is determined for a number of time strips in the observation period.
  • the obtained two-dimensional representations are stacked along the time direction so that a three-dimensional tensor is obtained (step S5).
  • each grid point (L,N) is assigned a color value of the corresponding pixel for each of the time strips.
  • a probable trajectory is determined for each of the other road users (step S6).
  • step S6 is illustrated in FIG. 7, which shows schematically the structure of a corresponding computer program and its computer program modules.
  • the computer program includes a pattern recognition module 36, a trajectory recognition module 38 and a trajectory determination module 40.
  • trajectory detection module 38 and the trajectory determination module 40 per se are already known from the publication "Convolutional Social Pooling for Vehicle Trajectory Prediction” by N.Deo and M.M. Trivedi, arXiv: 1805.06771, which was presented at the IEEE CVPR Workshop 2018.
  • the pattern recognition module 36 has an artificial neural network 42 and a flattening layer 44 .
  • the artificial neural network 42 is preferably designed as a convolutional neural network.
  • the artificial neural network 42 receives the determined three-dimensional tensor as an input variable and generates an output variable by means of pattern recognition.
  • the output variable of the artificial neural network 42 differs depending on the architecture of the artificial neural network 42.
  • FIG. 1 A first possible architecture of the artificial neural network is shown in FIG. 1
  • the artificial neural network 42 here has two-dimensional filter kernels and two-dimensional pooling layers.
  • All time strips of the three-dimensional tensor are processed here simultaneously by means of the two-dimensional filter kernel, with a depth of the filter kernel in the time direction corresponding to a number of input channels.
  • the number of input channels here is equal to the number of time strips of the three-dimensional tensor.
  • the output of the artificial neural network 42 is a two-dimensional matrix, which is converted into a vector by means of the flattening layer 44 .
  • FIG. 1 A second possible architecture of the artificial neural network is shown in FIG. 1
  • the artificial neural network 42 here has three-dimensional filter kernels and three-dimensional pooling layers.
  • the depth of the filter kernels in the time direction is smaller than the number of time strips of the three-dimensional tensor.
  • the filter kernels are also shifted along the time dimension, so that pattern recognition also takes place along the time dimension.
  • the output variable of the artificial neural network 42 is a three-dimensional output tensor here, which is converted into a vector by means of the flattening layer 44 .
  • the three-dimensional initial tensor can be converted directly into the vector, i.e. directly from three to one dimension.
  • one or more two-dimensional intermediate layers can also be provided, with the last intermediate layer then being converted into the vector.
  • the output of the pattern recognition module 36 is a vector in each case.
  • the trajectory recognition module 38 determines the previous trajectories of the other road users 18, 20, 21, the output variable of the trajectory recognition module 38 also being a vector.
  • the output vectors of the pattern recognition module 36 and the trajectory recognition module 38 are linked to one another and passed to the trajectory determination module 40 .
  • the trajectory determination module 40 determines the probable trajectory for each of the other road users 18, 20, 21, ie also separately for each other road user 20, 21 of a group.
  • the probable trajectory can be a family of trajectories. In other words, different possible trajectories together with their probabilities can be determined for each of the other road users 18, 20, 21.
  • the anticipated trajectories determined are then transferred to a driving maneuver planning module of motor vehicle 10 or of control unit 30 .
  • the driving maneuver planning module determines a driving maneuver to be carried out by motor vehicle 10 based on the anticipated trajectories and based on the environmental data.
  • an interaction of the motor vehicle 10 with the other road users 18, 20, 21 via the expected trajectories of the other road users 18, 20, 21 is taken into account.
  • the driving maneuver to be carried out is then transferred to a trajectory planning module of motor vehicle 10 or control unit 30 .
  • the trajectory planning module determines the specific trajectory that motor vehicle 10 should follow.
  • the motor vehicle can be controlled at least partially automatically, in particular fully automatically.
  • the individual time strips of the three-dimensional tensor are each processed in the pattern recognition module 36 by means of a two-dimensional filter kernel, as a result of which a two-dimensional matrix is generated as the output variable.
  • the two-dimensional filter kernels can each have the same weighting factors for the different time strips.
  • the two-dimensional matrices are each converted into a vector and combined with a corresponding state vector h t of the trajectory recognition module 38, where hi is the state vector for the time strip i.
  • the linked vectors are each the input variables for a feedback neural network (RNN) of the trajectory detection module 38, with the output variable of the feedback neural network serving as the input variable for the next feedback neural network or, in the case of the last feedback neural network, the output variable of the T rajectory detection module 38 represents.
  • RNN feedback neural network
  • the output variable of the trajectory recognition module 38 is transferred to the trajectory determination module 40, which then determines the probable trajectories of the other road users 18, 20, 21, for example by means of at least one additional feedback neural network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé de commande d'un véhicule automobile qui circule sur une route dans une voie de circulation momentanée. Des données d'environnement sont déterminées au moyen d'un capteur. Au moins une fonction de valeur utile est déterminée sur la base des données d'environnement, la fonction de valeur utile associant, à un instant prédéfini, respectivement une valeur utile pour au moins un autre usager de la route, à des zones spatiales différentes de la voie de circulation momentanée et/ou d'au moins une autre voie de circulation. Une représentation bidimensionnelle de l'au moins une fonction de valeur utile est déterminée. Au moins une trajectoire prévue de l'au moins un autre usager de la route est déterminée sur la base de la représentation bidimensionnelle de la fonction de valeur utile en utilisant une reconnaissance de formes sur la représentation bidimensionnelle. L'invention concerne en outre un appareil de commande, un véhicule automobile et un programme informatique.
EP21735216.0A 2020-07-06 2021-06-17 Procédé et appareil de commande pour la commande d'un véhicule automobile Withdrawn EP4176376A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102020208421.1A DE102020208421A1 (de) 2020-07-06 2020-07-06 Verfahren sowie Steuergerät zum Steuern eines Kraftfahrzeugs
PCT/EP2021/066487 WO2022008200A1 (fr) 2020-07-06 2021-06-17 Procédé et appareil de commande pour la commande d'un véhicule automobile

Publications (1)

Publication Number Publication Date
EP4176376A1 true EP4176376A1 (fr) 2023-05-10

Family

ID=76641666

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21735216.0A Withdrawn EP4176376A1 (fr) 2020-07-06 2021-06-17 Procédé et appareil de commande pour la commande d'un véhicule automobile

Country Status (5)

Country Link
US (1) US20230257002A1 (fr)
EP (1) EP4176376A1 (fr)
CN (1) CN115812052A (fr)
DE (1) DE102020208421A1 (fr)
WO (1) WO2022008200A1 (fr)

Also Published As

Publication number Publication date
DE102020208421A1 (de) 2022-01-13
CN115812052A (zh) 2023-03-17
US20230257002A1 (en) 2023-08-17
WO2022008200A1 (fr) 2022-01-13

Similar Documents

Publication Publication Date Title
EP3144920B1 (fr) Détermination d'une trajectoire théorique d'un véhicule
EP3765927B1 (fr) Procédé servant à générer un jeu de données d'entraînement servant à entraîner un module à intelligence artificielle pour un dispositif de commande d'un véhicule
DE102019110217B4 (de) Verfahren zum automatisierten Steuern eines Kraftfahrzeugs
DE102019104974A1 (de) Verfahren sowie System zum Bestimmen eines Fahrmanövers
EP3873784A1 (fr) Système de commande et procédé de commande de planification, sur la base d'échantillonnages, de trajectoires possible pour des véhicules automobiles
DE102013225057A1 (de) Verfahren zum steuern eines fahrzeugs, vorrichtung zum erzeugen von steuersignalen für ein fahrzeug und fahrzeug
DE102018212318B4 (de) Adaptive geschwindigkeitsregelung
EP3627386A1 (fr) Procédé et dispositif de fourniture d'une représentation d'environnement d'un environnement d'un dispositif mobile et véhicule automobile doté d'un tel dispositif
DE102019118366A1 (de) Verfahren sowie Steuergerät für ein System zum Steuern eines Kraftfahrzeugs
DE102019107414A1 (de) Verfahren sowie Steuergerät für ein System zum Steuern eines Kraftfahrzeugs
DE102020103030A1 (de) Adaptives sensorsystem für fahrzeuge und verfahren zum betreiben desselben
DE102018009927A1 (de) Steuerungssystem und Steuerungsverfahren für einen hybriden Ansatz zum Ermitteln einer möglichen Trajektorie für ein Kraftfahrzeug
WO2020127010A1 (fr) Procédé et système de commande d'un véhicule automobile
DE102017223206A1 (de) Niederdimensionale Ermittlung von abgegrenzten Bereichen und Bewegungspfaden
DE102017127600A1 (de) Verfahren zum automatischen Parken für ein Kraftfahrzeug mit einem Fahrunterstützungssystem
DE102019129879A1 (de) Verfahren sowie Steuergerät zum Steuern eines Kraftfahrzeugs
DE102021109395A1 (de) Verfahren, systeme und vorrichtungen für benutzerverständliche erklärbare lernmodelle
WO2020069812A1 (fr) Procédé de guidage au moins partiellement automatisé d'un véhicule automobile sur une voie de circulation
DE102019122250A1 (de) Verfahren sowie Steuergerät für ein System zum Steuern eines Kraftfahrzeugs
DE102016220450A1 (de) Vorrichtung, Fortbewegungsmittel und Verfahren zur Abschätzung einer Kollisionswahrscheinlichkeit zwischen einem Fortbewegungsmittel und einem Umgebungsobjekt
WO2019120709A1 (fr) Procédé et unité de commande servant à commander une fonction d'un véhicule se déplaçant au moins en partie de manière automatisée
DE102016203522A1 (de) Verfahren und Vorrichtung zum Vorhersagen von Trajektorien eines Kraftfahrzeugs
DE102020109662A1 (de) Computerimplementiertes Verfahren zur Trajektorienplanung für ein Fahrzeug
DE102019204187A1 (de) Klassifizierung und temporale Erkennung taktischer Fahrmanöver von Verkehrsteilnehmern
DE102019216235A1 (de) Verfahren zum Vorhersagen der Bewegung eines Fahrzeugs und zumindest eines weiteren Fahrzeugs

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: 20221221

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)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20230825