WO2023011814A1 - Procédé et circuit de commande pour surveiller une condition d'approbation pour un mode de conduite automatique d'un véhicule à moteur, et véhicule à moteur comportant le circuit de commande - Google Patents

Procédé et circuit de commande pour surveiller une condition d'approbation pour un mode de conduite automatique d'un véhicule à moteur, et véhicule à moteur comportant le circuit de commande Download PDF

Info

Publication number
WO2023011814A1
WO2023011814A1 PCT/EP2022/068037 EP2022068037W WO2023011814A1 WO 2023011814 A1 WO2023011814 A1 WO 2023011814A1 EP 2022068037 W EP2022068037 W EP 2022068037W WO 2023011814 A1 WO2023011814 A1 WO 2023011814A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
class
motor vehicle
driving mode
road class
Prior art date
Application number
PCT/EP2022/068037
Other languages
German (de)
English (en)
Inventor
Oliver Hoffmann
Stefan GSCHLÖSSL
Mohamed Essayed Bouzouraa
Original Assignee
Cariad Se
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 Cariad Se filed Critical Cariad Se
Priority to CN202280053601.1A priority Critical patent/CN117795291A/zh
Publication of WO2023011814A1 publication Critical patent/WO2023011814A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G01C21/3815—Road data
    • 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
    • B60W60/005—Handover processes
    • B60W60/0051—Handover processes from occupants to vehicle
    • 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
    • B60W60/005—Handover processes
    • B60W60/0053—Handover processes from vehicle to occupant
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/05—Type of road, e.g. motorways, local streets, paved or unpaved roads
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/20—Data confidence level
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/35—Data fusion
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/40—High definition maps

Definitions

  • the invention relates to a method for monitoring a permissibility condition for an automated driving mode of a motor vehicle.
  • the admissibility condition includes that the driving mode may only be active when driving on roads that belong to at least one predetermined authorized road class.
  • the invention also relates to a control circuit that can carry out the method in a motor vehicle, and a motor vehicle with the control circuit.
  • ODD Operational Design Domain
  • the area of application permitted for this is defined by the so-called Operational Design Domain (ODD), ie the vehicle manufacturer can specify where such an automated driving mode may be activated.
  • ODD Operational Design Domain
  • the ODD is determined or limited by the road class, among other things. Road classes that are differentiated here are, for example, motorways, roads similar to motorways, country roads or city streets. Some automated driving modes, such as the highway pilot, are only designed for use on highways or highway-like roads and may therefore only be activated in these driving situations. In addition, they must automatically recognize a change in the road class and preferably proactively hand over control of the vehicle to the driver before deactivating. As a result, high To place security requirements on the system to reliably recognize the corresponding road classes.
  • the road class is usually recognized on the basis of so-called digital HD maps (road maps with entries for e.g. peripheral buildings and lane courses).
  • the road class is stored a-priori in the HD map or generally a digital road map and then read out on the map by localizing the vehicle (e.g. via GNSS - Global Navigation Satellite System, e.g. GPS - Global Positioning System).
  • Road class detection based solely on digital road maps brings with it some challenges.
  • localization errors can occur, for example due to GPS inaccuracies.
  • the map content must be continuously up-to-date, which is difficult to implement.
  • Highly automated systems with SAE level greater than 2 usually require a safety integrity level ASIL-D (ASIL - automotive safety level) for the detection of the ODD (according to ISO 26262). The resulting technical requirements would be associated with great effort and costs if implemented solely using a road map.
  • ASIL-D ASIL - automotive safety level
  • the road class can be determined on the basis of sensor measurement data.
  • a state machine is used that determines a road class based on human experience using environment data. If this does not come to a conclusion, the result of a decision tree induced by machine learning is used and a road class is estimated. Determining the road class on the basis of a state machine has the disadvantage that a state machine cannot indicate any uncertainty with regard to its own state depending on the reliability of its input data. It is known from DE 102 54 806 A1 to combine environmental data from a number of sensors and map data from a digital road map by means of a fusion of information in order to obtain information about the road class currently being traveled on. The disadvantage of such a merger is that a clear result from one information source can be put into perspective or weakened by uncertain results from another information source.
  • DE 10 2018 208 593 A1 discloses a method for checking whether the driving mode of the motor vehicle can be changed safely. In two consecutive test stages, it is first checked whether, according to the map data of a digital road map, there is even a permissible road type for activating the driving mode anywhere in the vicinity, and then, if the first test stage is passed successfully, a second test stage based on environmental data Sensors to detect whether the motor vehicle is actually on a road of this road class. The check only takes place for the road section currently being traveled on, which is why the activation of the driving mode is preferably checked by means of the method, but not the deactivation when leaving a permissible road class, ie when exiting the ODD.
  • the invention is based on the object of checking in a motor vehicle for the operation of an automated driving mode whether a permissible road class is present for which the operation of the automated driving function is permitted.
  • the invention includes a method for monitoring an admissibility condition for an automated driving mode of a Motor vehicle by a control circuit.
  • the admissibility condition includes that the driving mode may only be active when driving on roads of at least one predetermined authorized road class.
  • map data which indicate the road class of the road segment are read from a data memory and then checked whether they indicate such a road class, which corresponds to the at least one road class permitted for the driving mode.
  • the admissibility condition is checked in particular to check, in the case of an already activated driving mode, whether the driving mode has to be deactivated because the road segment ahead no longer corresponds to the at least one permitted road class.
  • driver assistance for driving on the freeway an ACC (automatic cruise control), an automatic distance control system, an overtaking assistant, for example, can be provided as a driving mode, to name just a few examples.
  • the automated driving mode can provide for longitudinal guidance (acceleration and/or braking) and/or lateral guidance (steering) to be carried out automatically in the activated driving mode by at least one control unit of the motor vehicle without any action on the part of the driver.
  • the road class can also be checked for the road section or road segment currently being traveled on, but according to the invention we primarily use a road segment ahead, for example a road segment that begins, for example, 10 centimeters to 10 meters in front of the motor vehicle and, for example, in 30 meters ends up to 1 kilometer in front of the motor vehicle.
  • the road map can be used to check whether the map data stored therein relating to this road segment ahead indicates that this road segment is part of or classified as an approved road class, ie as an element of the set of at least one approved road class. It can be one or more than one Road class be defined as permissible, which is why the wording "at least one predetermined approved road class" is used here. Which road class is approved for which driving mode depends on the driving mode and can be determined by a specialist.
  • a road map can result in outdated map data being available and/or a localization of the motor vehicle in relation to the road map being subject to a variance or tolerance or fluctuation, as is inherent to receivers of a position signal from a GNSS (Global Navigation Satellite System ), such as the GPS (Global Positioning System), is known.
  • GNSS Global Navigation Satellite System
  • GPS Global Positioning System
  • environmental data are received from an environmental sensor or multiple environmental sensors, which describe environmental features of the road segment (e.g., the presence of street signs or recognizable people), and using the environmental data, a predetermined estimation routine is used to determine characteristics of the road segment street segment (e.g. the characteristic "blue motorway signs" or "persons present”).
  • the surroundings data can be the sensor data from the at least one surroundings sensor and/or processed sensor data, for example filtered sensor data and/or sensor data combined by means of a sensor fusion.
  • the characteristic recognized in each case can include, for example: “Pedestrians present”, “Center barrier present”, “Motorway signs of a specific color present”, to name just examples.
  • a corresponding estimation routine to recognize such characteristics from environmental data can be provided, for example, on the basis of an algorithm for machine learning, for example an artificial neural network, as is known per se from the prior art for object recognition or machine vision.
  • the probability that the characteristics indicate the presence of a special road class or at least the presence of the set of permitted road classes can then be based on the estimation results for the individual characteristics, for example a key figure for the confidence or estimation variance, when estimating the respective characteristic . This is explained in more detail below.
  • the individual key figures of the characteristics ie their estimation certainty, then result in the probability of the existence of the at least one permitted road class.
  • the second signal path thus also signals, independently of the first signal path, whether the road segment ahead belongs to the at least one permitted road class or not. The membership signal is issued if the existence probability is greater than the threshold value. Otherwise it is signaled that the road segment ahead (or a partial interval thereof) does not belong to the at least one permitted road class.
  • Said actual checking of the admissibility condition includes that the presence of the at least one approved road class for the road segment ahead is finally only signaled if both the first signal path and the second signal path confirm or signal the existence of the road class, and otherwise a predetermined blocking measure for the driving mode is carried out.
  • the two signal paths are evaluated independently of one another and only if both signal paths independently of one another signal or confirm the presence or existence of the at least one permitted road class in the area of the road segment ahead is it assumed for the driving mode that the admissibility condition is met. Otherwise the blocking measure is carried out, which will be explained in more detail later. This means that one is not dependent on the signal paths being implemented absolutely error-free according to ASIL-D, but only the mutual comparison of both signal paths must lead to the ASIL-D level.
  • the two signal paths can be implemented, for example, as software modules operated independently of one another, as a result of which they can check the road class independently of one another.
  • the invention also includes developments that result in additional advantages.
  • a classifier such as an artificial neural network, responds to the presence of the characteristic at all, e.g. on "persons” in camera images
  • a "confidence of existence” of the characteristic the classifier signals the probability with which the characteristic is present or how reliable the estimate is
  • a "state” of the characteristic for example how many kilometers the characteristic has been present or which expression is present, such as “many pedestrians present” in contrast to “few pedestrians present”
  • Corresponding estimation routines are available per se from the prior art, for example in connection with monitoring the surroundings in a motor vehicle for operating an autopilot.
  • a development includes that the road segment ahead is divided in the direction of travel into several different distance intervals one behind the other in the direction of travel and a separate check of the admissibility condition is carried out using the two signal paths for each distance interval.
  • the map data and the characteristics from the respective distance interval are therefore used for each distance interval.
  • the road segment ahead is not monitored as a uniform area over which Overall, the probability of the existence of an approved road class is checked, but sections or sub-intervals with different distances to the motor vehicle (hence "distance intervals") are individually checked to see whether they meet the admissibility condition.
  • This has the advantage that indicators or characteristics are prevented from being "averaged out" over the entire road segment.
  • the road is no longer part of the at least one permitted road class in the furthest distance interval, corresponding characteristics that clearly signal this can be found in this furthest distance interval.
  • the admissibility condition "freeway available” can still be met for the distance interval immediately ahead, while at the end of the exit in a curve to leave the freeway the characteristic "curve with a curve radius smaller than X Meter” may be present, which signals that the "Autobahn" road class is no longer available here.
  • this unique characteristic would be averaged out in a calculation of the probability of existence for the “Autobahn” road class over the entire road segment ahead, because the characteristics for the “Autobahn” road class predominate in the preceding distance intervals.
  • the probability of existence of the road class “motorway” is calculated separately for the distance intervals, the characteristic relating to the curve radius can be reliably recognized for the last, furthest distance interval and it can be signaled that there is no motorway or generally permissible road class in this distance interval more is available.
  • the road segment is preferably divided into at least two distance intervals, preferably more than two, preferably more than three, in particular more than four distance intervals. A separate subdivision of the road segment into characteristic-related distance intervals of different lengths along the direction of travel can also be provided for each characteristic, for example distance intervals with a length of 50 meters, distance intervals with a length of 100 meters, just to name examples.
  • the blocking measure includes a transfer routine for transferring a longitudinal guidance and / or lateral guidance of the motor vehicle to a driver of the motor vehicle.
  • the handover routine is triggered or carried out as a blocking measure for blocking or deactivating the driving mode.
  • This handover routine is known per se from the prior art and can include, for example, an indication or an output to the driver that he should get ready to take control of the motor vehicle.
  • an emergency stop can be used to ensure that the driving mode does not have to be operated in the area of a non-approved or impermissible road class if, for example, the takeover procedure or takeover routine for the driver fails.
  • a development includes that said blocking measure includes that in the event that the admissibility condition is violated in the road segment ahead, activation of the driving mode is blocked when the driving mode is deactivated and/or handover to a driver and/or an emergency stop when the driving mode is activated carried out and then the driving mode is deactivated.
  • the blocking measure can prevent the driving mode from being activated.
  • a corresponding operating element in the motor vehicle which is provided for activating the driving mode, can be switched off or hidden (in the case of a touchscreen).
  • a further development includes that at least in the second signal path (environment data) the at least one permissible road class and/or at least one predetermined impermissible road class (driving mode must be deactivated here) is defined and the current probability of existence for each of the road classes is calculated in parallel.
  • a memory function for at least one of the road classes or all of the road classes also takes into account past road segments that have already been traveled through when calculating their probability of existence, with this memory function taking into account a degradation behavior of the characteristics estimated in these past road segments (ie a forgetting factor) as a function of a temporal and / or includes local distance to the respective past road segment.
  • a central barrier begins in a road segment and if the motor vehicle passes this start of the central barrier and the central barrier continues along the road, then, for example, after the motor vehicle has covered a distance of a predetermined minimum length, for example 1 kilometer, the characteristic “central barrier present “ not only for the current road segment, but also for previous ones that have already happened or by means of the memory function road segments traveled through or locations on the road are taken into account.
  • a characteristic loses its meaning or its informative value when estimating the probability of existence of the road class of the current road segment, which is why characteristics from the past in terms of time and/or location are removed or hidden using the forgetting factor.
  • a characteristic is hidden whose observation time or estimated time is further back than a time value in a range of, for example, 10 seconds to 15 minutes.
  • it can be determined, for example by means of the described localization of the motor vehicle, how great a spatial distance the motor vehicle has become to the observation point for a characteristic, with a distance in a range of more than 20 meters to more than 5 kilometers can be chosen, just to name examples. So if the indications or characteristics for a certain road class "multiply" or repeat or accumulate or aggregate during the journey, this can be recognized by means of the memory function and taken into account when calculating the probability of existence for a road class that has not yet been recognized.
  • a development includes that for each road class checked, for each characteristic, an overall index is calculated on the basis of measured classification uncertainties and/or existential uncertainties and/or status uncertainties when sensing the corresponding environmental features using the environment data, with the overall index signaling a degree of the extent of this characteristic, where, for example, a higher absolute value of the overall key figure means a stronger expression.
  • each characteristic can be quantized by a single total number.
  • This overall index describes how reliably the respective characteristic could be derived from the environmental data from the at least one sensor.
  • an output of an algorithm for machine learning for example an output of an artificial neural network, can be used.
  • a development includes that for each road class checked from the characteristics observed overall in the road segment, a class-specific selection and/or a class-specific weighting is carried out according to relevance data stored in the control circuit, which indicate a relevance of the characteristics with regard to the respective road class. It can thus be prevented that an estimation or calculation of an existence probability for a road class is made uncertain by considering a characteristic that is irrelevant for the calculation of the existence probability, for which there is, for example, a large observation uncertainty or estimation uncertainty and/or no reliable indication of a Road class is because it is typical of both a permitted and a prohibited road class.
  • this characteristic does not have to be observed for the current road segment, but that this characteristic should be signaled, for example by means of the memory function, at least temporarily within a past period of time, for example within the last ten minutes, or within a predetermined one Distance, for example within the past kilometer, must have been present.
  • a further development includes that in the event that the first signal path and the second signal path signal the same road class, the signaled road class is entered into an environment model (so-called dynamic digital environment map), on the basis of which a partially autonomous or fully autonomous driving function plans a driving trajectory in the automatic driving mode and selects a behavioral rule to be followed and/or a traffic rule to be observed depending on the road class entered in the environment model.
  • an environment model so-called dynamic digital environment map
  • a partially autonomous or fully autonomous driving function plans a driving trajectory in the automatic driving mode and selects a behavioral rule to be followed and/or a traffic rule to be observed depending on the road class entered in the environment model.
  • the checking of the admissibility condition is also used to control the road class signaled by both signal paths for determining a driving behavior of the motor vehicle. For example, a rule of conduct to be followed may state that overtaking is preferred or, conversely, that overtaking is to be avoided.
  • a traffic rule to be observed may be the traffic rule intended for the road class, which is implicitly given by the road class (such as a maximum speed or speed limit for country roads) and/or a driving style, e.g. the probability of an overtaking attempt.
  • the signal paths are thus also used to provide the information on the road class currently present in the environment model.
  • the invention comprises a control circuit for a motor vehicle, the control circuit having a processor device which is set up to carry out an embodiment of the method according to the invention.
  • the control circuit can have a data processing device or a processor device that is set up to an embodiment of the carry out the method according to the invention.
  • the processor device can have at least one microprocessor and/or at least one microcontroller and/or at least one FPGA (Field Programmable Gate Array) and/or at least one DSP (Digital Signal Processor).
  • the processor device can have program code which is set up to carry out the embodiment of the method according to the invention when executed by the processor device.
  • the program code can be stored in a data memory of the processor device.
  • the control circuit can be designed as a control unit or as a combination of several control units for the motor vehicle.
  • the control circuit can additionally or alternatively comprise a central computer for a motor vehicle.
  • the invention includes a motor vehicle with at least one sensor for generating sensor-based surroundings data and with an embodiment of the control circuit according to the invention.
  • the motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.
  • the invention also includes the combinations of features of the described embodiments.
  • the invention also includes implementations that each have a combination of the features of several of the described embodiments, unless the embodiments were described as mutually exclusive.
  • Fig. 1 is a schematic representation of an embodiment of the motor vehicle according to the invention with an embodiment of the control circuit according to the invention, through which a Embodiment of the method according to the invention can be carried out;
  • Fig. 2 is a sketch to illustrate a calculation of an existence probability of a permissible road class.
  • a motor vehicle 10 which can be a motor vehicle, in particular a passenger car or truck.
  • An automated driving function 11, for example an autopilot can be provided in motor vehicle 10, which can control a drive motor 12 and/or brakes 13 in motor vehicle 10, for example, for longitudinal guidance and a steering system 14 for lateral guidance.
  • a longitudinal guide or a transverse guide can also be provided, for example.
  • the autopilot 11 is active when a driving mode F is activated. Provision can be made here for the driving function 11 to be permitted only for predetermined road classes or at least one predetermined road class, ie may only be active on at least one permitted road class, for example a motorway or a country road.
  • the motor vehicle 10 can currently be moving on a road 16 along a direction of travel 15 .
  • Motor vehicle 10 can be checked or determined whether a road segment 17 ahead of the motor vehicle 10 in the direction of travel 15 corresponds to at least one approved or permitted road class.
  • a control circuit 18 can be provided in motor vehicle 10, which can be implemented, for example, by a control unit or a combination of a plurality of control units and/or a central computer of motor vehicle 10.
  • Two independent signal paths 19, 20 can be implemented in the control circuit 18, for example on the basis of a program code or software, in order to check an admissibility condition 21, which indicates that the road segment 17 ahead corresponds to the at least one authorized road class. If this admissibility condition 21 is violated, a predetermined blocking measure 22 can be triggered by the control circuit 18 . This can then deactivate driving mode F in driving function 11 or prevent its activation.
  • the signal path 19 can provide that a current geoposition 26 of the motor vehicle 10 is localized or determined by means of a receiver 23 for a position signal 24 of a GNSS 25, for example the GPS, and this geoposition data of the geoposition 26 is received by the control circuit 18.
  • a digital road map 27, for example from a navigation database 28, can be used to determine whether the road 16 at the geoposition 26 corresponds to the at least one approved road class. From the map data of the digital road map 27, a road class 29 that is currently available or is being traveled on or is ahead can be estimated. This road class 29, as signaled by the first signal path 19, can be used as an input for the admissibility condition 21.
  • the second signal path 20 can provide that an existence probability 30 of the road class and/or an estimated road class 31 determined by a threshold value comparison is signaled by the second signal path 20 for one or more possible road classes.
  • sensor data or surroundings data 33 can be received from at least one surroundings sensor 32 .
  • surroundings sensors 32 are: a camera, a radar, a lidar, an ultrasonic sensor.
  • the respective detection areas 34 of the environment sensors 32 can be aligned with the road segment 17 .
  • an estimation routine 35 for example an artificial neural network, can use environment features 36 described by environment data 33, for example objects in environment 37 of motor vehicle 10 in the area of road segment 17 or in the adjacent area to the right and left of road 16 , It can be determined which characteristics 38 are present in the road segment 17, for example whether there is a central barrier and/or whether pedestrians are present. Based on the respective characteristics or the degree of the characteristic 38, it can be decided or determined on the basis of relevance data 39 which of the characteristics 38 are to be used as a basis for which of the road classes that are checked, in order to use a probability estimate 40 to determine a respective probability of existence 41 for a Presence or presence of the respective road class in the road segment 17 to calculate.
  • the respective probability of existence 41 can then be compared with a threshold value 43 by means of a threshold value comparison 42 in order to determine which road class 31 is to be signaled by the second signal path 20 of the admissibility condition 21 as a further input.
  • the blocking measure 22 remains deactivated or unused only in the event that both signal paths 19, 20 signal the same road class 29, 31. If the blocking measure 22 is activated, then when driving mode F is active, a handover to the driver is carried out and/or an emergency stop is carried out.
  • FIG. 2 illustrates how the estimated road class 31 is ascertained in the motor vehicle 10 for the road segment ahead, for example in the second signal path 20 . It shows how different characteristics C1 to C6, for example “central crash barrier present”, “pedestrian presence”, have been estimated from the environmental data 33 and an overall index G has been determined for each characteristic 38 . Furthermore, it is shown that the overall index G within the road segment 17 for each characteristic 38 in different Distance intervals 50 can be calculated independently or individually. A separate length of the distance intervals 50 along the direction of travel 15 can be defined or provided for each characteristic 38 . In the overlapping areas of the distance intervals 50, the overall key figures G of the different characteristics 38 can be combined with one another or used together.
  • C1 to C6 for example “central crash barrier present”, “pedestrian presence”
  • the probability of existence E, 41 can be calculated and in this case using the relevance data 39 (represented by dashed lines) for determining the probability of existence E of a respective road class K1, K2, K3, K4 different overall key figures G are taken as a basis or combined.
  • An estimated road class 31 can then be estimated or signaled for each resulting distance interval, for example the road class K1 to K4 with the greatest probability of existence E or with an additional condition that the probability of existence E must be greater than a predetermined minimum value.
  • the blocking measure 22 is triggered, which, based on the still available distance interval 50 with a permissible road class, can carry out or trigger a takeover procedure for handing over the driving task to the driver, for example.
  • a decomposition according to ISO 26262 into two redundant ASIL B (D) road classifications is preferably carried out.
  • roads are classified by localization on an HD map (digital road map).
  • HD map digital road map
  • the aim of this new method is therefore to estimate the road class by comparing the characteristics recorded in the environment and their conditions with the characteristics determined from laws, guidelines and statistics.
  • ASIL B (D) road classifications In order to meet the safety requirements for road class detection, a decomposition according to ISO 26262 into two redundant ASIL B (D) road classifications is carried out.
  • roads are classified by localization on an HD map.
  • a classification is carried out with the help of environmental features that are detected by the vehicle's own environmental sensors. The result of this classification is a distribution over the road classes defined in the function, where the reliability is taken into account in the level of the probability value of each road class.
  • An environment feature is abstract information in the environment of the ego vehicle, which is recorded by various environment sensors (e.g. radar, lidar and camera), processed and then combined by a sensor data fusion.
  • Important environmental features are, for example, lane markings, traffic signs, crash barriers, delineators, walls, vehicles and living beings. In addition to the geometric position or the course in the vehicle's own coordinate system, they all also have other states such as vehicle type, speeds and accelerations for vehicles; Color, dash type and width for lane markings and plate type and content for traffic signs.
  • To determine the road class the states of all environmental features perceived in the area are analyzed. A comparison is then made with characteristics typical of the road class in order to determine a probability-based statement for the road class. Such characteristics are examined and defined a priori. Since these differ significantly in different countries or change during the life cycle of the product are stored in a database and kept up-to-date via updates.
  • the existing laws and guidelines of the respective country of use serve as a starting point for the definition of the characteristics of different road classes.
  • the StVO, VwV-StVO or the various guidelines for the construction of roads should be mentioned.
  • characteristics can be determined by data-driven, statistical analyses. For example, the occurrence or frequency of certain traffic signs in the various road classes, the existence and behavioral patterns of other road users or the road topology should be mentioned.
  • the aim of the method is therefore to estimate the road class by comparing the characteristics recorded in the environment and their conditions with the characteristics determined from laws, guidelines and statistics.
  • the environmental features used preferably correspond to safety integrity ASIL-B (D).
  • the environment model is enriched with the estimated road class.
  • the advantage of the method is that the reliability of the input data has a direct impact on the probability value of a road class. If the sensor measurement data is poor, this can be taken into account when deciding whether an automated driving function is available. In addition, uncertainty relationships can be established between two or more road classes. If all road classes with a significant probability value are approved for the automated driving function, a lower overall safety for a specific road class may also be sufficient to offer the driving function.
  • the redundancy for recognizing the road class using HD map Information enables higher safety integrity as well as reliability. Despite possible localization errors or errors in the HD map (digital road map), the road class can be determined by the onboard sensors. Furthermore, the decomposition of the road class detection into two redundant methods reduces the technical complexity and the security requirements for its implementation.
  • the existing environmental features are recorded by the vehicle's own sensors and brought together by a sensor data fusion. At the end of this fusion there are various properties of the environmental features, such as classification, existence measure, pose, kinematics and geometric progression.
  • This data is used to generate an environment model of the ego vehicle.
  • the characteristics to be checked are extracted from this environment model by the states and relationships of the environment features.
  • the characteristics are high-level indicators for properties that the environment model has. For example, the characteristic "pedestrians present" is determined from individual pedestrians in the environment model. These extracted characteristics are compared with the characteristics stored as relevant or typical for the road class. For each characteristic, a total key figure based on the measured classification uncertainties, existence uncertainties and
  • State uncertainties of the corresponding environmental features are calculated.
  • the overall key figure provides information about the extent of this characteristic, with a higher absolute value of the number meaning a stronger expression.
  • the characteristics are updated in each calculation step, taking into account the previous results.
  • the various characteristics can show an increase or decrease in behavior in order to stabilize the behavior and to take account of individual events that only have a limited validity in terms of time.
  • a location-dependent component can also be taken into account for characteristics that are determined from location-specific environmental features. For example, the distance to a specific environmental feature must exceed at least a specific distance so that the degradation behavior over time of the characteristic is applied.
  • the probability-based estimation of a road class is made by combining the characteristics relevant to this class.
  • the form in which the characteristics are combined to estimate a road class is not fixed, but is queried via the database. What is variable is which characteristics are used to estimate a road class, as well as their influence and weighting on the result of the estimation.
  • the characteristics relevant for a road class are divided into the categories absolutely necessary, conditionally necessary and optional. Characteristics that are absolutely necessary must have a minimum specification so that the road class can be output as existing. The same applies to conditionally necessary characteristics, with the difference that there is a condition that allows the road class to still be output as present. Optional characteristics contribute to the plausibility check of a road class, but have no direct influence on whether a road class can be output as existing or not.
  • All defined road classes are estimated in parallel and independently of each other, so that at the end of a processing step there is an estimated value for each defined road class.
  • the probabilities of existence of the characteristics are also evaluated as a function of the distance in the longitudinal direction of the road to the ego vehicle. This results in distance intervals for each characteristic, in which the expression of the characteristic and/or the probability of existence can differ.
  • the intervals of all Characteristics are combined and an estimate of each road class is performed for each resulting interval. In this way, pending changes in the road class can also be detected.
  • the combination of the individual estimates results in a distribution of the road classes with their determined probability values.
  • Lane marking properties width, dash type, gradient, reflectivity (can be measured by lidar sensor)

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

La présente invention concerne un procédé de surveillance d'un état d'approbation (21) pour un mode de conduite automatique d'un véhicule à moteur (10), la condition d'approbation (21) étant que le mode de conduite peut seulement être actif lors d'une conduite sur des routes (16) d'une classe de route autorisée prédéterminée (29, 31). Dans un premier trajet de signal (19), des données cartographiques provenant d'une carte routière numérique (27) pour un segment de route (17) situé devant sont vérifiées pour déterminer si elles spécifient la classe de route autorisée (29, 31). Selon l'invention et indépendamment du premier trajet de signal (19), des données d'environnement (33) sont reçues dans un second trajet de signal (20) à partir d'un capteur d'environnement (32), et les données d'environnement (33) sont utilisées pour vérifier si une probabilité d'existence (30, 41) d'une présence de la classe de route autorisée (29, 31) est supérieure à une valeur seuil prédéterminée. La condition d'approbation (21) n'est satisfaite que si le premier trajet de signal (19) et le second trajet de signal (20) confirment l'existence de la classe de route (29, 31).
PCT/EP2022/068037 2021-08-02 2022-06-30 Procédé et circuit de commande pour surveiller une condition d'approbation pour un mode de conduite automatique d'un véhicule à moteur, et véhicule à moteur comportant le circuit de commande WO2023011814A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202280053601.1A CN117795291A (zh) 2021-08-02 2022-06-30 用于监控机动车自动驾驶模式的准用条件的方法和控制单元及具有该控制单元的机动车

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102021120043.1A DE102021120043A1 (de) 2021-08-02 2021-08-02 Verfahren und Steuerschaltung zum Überwachen einer Zulässigkeitsbedingung für einen automatisierten Fahrmodus eines Kraftfahrzeugs sowie Kraftfahrzeug mit der Steuerschaltung
DE102021120043.1 2021-08-02

Publications (1)

Publication Number Publication Date
WO2023011814A1 true WO2023011814A1 (fr) 2023-02-09

Family

ID=82446665

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/068037 WO2023011814A1 (fr) 2021-08-02 2022-06-30 Procédé et circuit de commande pour surveiller une condition d'approbation pour un mode de conduite automatique d'un véhicule à moteur, et véhicule à moteur comportant le circuit de commande

Country Status (3)

Country Link
CN (1) CN117795291A (fr)
DE (1) DE102021120043A1 (fr)
WO (1) WO2023011814A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102022125804A1 (de) 2022-10-06 2024-04-11 Bayerische Motoren Werke Aktiengesellschaft Steuerung eines Kraftfahrzeugs

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10254806A1 (de) 2002-11-22 2004-06-17 Robert Bosch Gmbh Verfahren zur Informationsverarbeitung
US20140025292A1 (en) * 2012-07-19 2014-01-23 Continental Automotive Gmbh System and method for updating a digital map in a driver assistance system
DE102012218362A1 (de) 2012-10-09 2014-04-24 Bayerische Motoren Werke Aktiengesellschaft Schätzung des Straßentyps mithilfe von sensorbasierten Umfelddaten
DE102015006569A1 (de) * 2015-05-21 2015-12-17 Daimler Ag Verfahren zur bildbasierten Erkennung des Straßentyps
WO2019216386A1 (fr) * 2018-05-10 2019-11-14 本田技研工業株式会社 Dispositif de commande de véhicule et véhicule
DE102018208593A1 (de) 2018-05-30 2019-12-05 Continental Teves Ag & Co. Ohg Verfahren zur Überprüfung, ob ein Wechsel des Fahrmodus sicher erfolgen kann
DE102019208533A1 (de) * 2019-06-12 2020-12-17 Continental Teves Ag & Co. Ohg Verfahren zum Erkennen einer Straßenklasse

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10254806A1 (de) 2002-11-22 2004-06-17 Robert Bosch Gmbh Verfahren zur Informationsverarbeitung
US20140025292A1 (en) * 2012-07-19 2014-01-23 Continental Automotive Gmbh System and method for updating a digital map in a driver assistance system
DE102012218362A1 (de) 2012-10-09 2014-04-24 Bayerische Motoren Werke Aktiengesellschaft Schätzung des Straßentyps mithilfe von sensorbasierten Umfelddaten
DE102015006569A1 (de) * 2015-05-21 2015-12-17 Daimler Ag Verfahren zur bildbasierten Erkennung des Straßentyps
WO2019216386A1 (fr) * 2018-05-10 2019-11-14 本田技研工業株式会社 Dispositif de commande de véhicule et véhicule
DE102018208593A1 (de) 2018-05-30 2019-12-05 Continental Teves Ag & Co. Ohg Verfahren zur Überprüfung, ob ein Wechsel des Fahrmodus sicher erfolgen kann
DE102019208533A1 (de) * 2019-06-12 2020-12-17 Continental Teves Ag & Co. Ohg Verfahren zum Erkennen einer Straßenklasse

Also Published As

Publication number Publication date
CN117795291A (zh) 2024-03-29
DE102021120043A1 (de) 2023-02-02

Similar Documents

Publication Publication Date Title
EP3572293B1 (fr) Procédé d'aide à la conduite d'au moins un véhicule automobile et système d'assistance
EP3669142B1 (fr) Procédé de commande d'un système de véhicule d'un véhicule mis en place pour effectuer une opération de conduite automatique et dispositif pour la mise en oeuvre du procédé
DE102011086241B4 (de) Verfahren zum sicheren Abstellen eines Fahrzeuges
DE112010001354B4 (de) Bewegungsstrajektoriengenerator
DE102017204603B4 (de) Fahrzeugsteuersystem und Verfahren zum Steuern eines Fahrzeugs
DE102013012324A1 (de) Verfahren und Vorrichtung zur Fahrwegfindung
DE102015209137A1 (de) Verfahren und System zur Steuerung einer Fahrfunktion eines Fahrzeuges
DE102014223744A1 (de) Assistenzsystem zur Detektion von in der Umgebung eines Fahrzeuges auftretenden Fahrhindernissen
EP3373268A1 (fr) Procédé de fonctionnement d'un système d'aide à la conduite pour un véhicule sur une chaussée et système d'aide à la conduite
WO2020001698A1 (fr) Système d'aide à la conduite avec fonction d'arrêt d'urgence de véhicule, véhicule pourvu de celui-ci et procédé d'arrêt d'urgence d'un véhicule
DE102020117340A1 (de) Verfahren zur Umgebungserfassung mit wenigstens zwei unabhängigen bildgebenden Umgebungserfassungssensoren, Vorrichtung zur Durchführung des Verfahrens, Fahrzeug sowie entsprechend ausgelegtes Computerprogramm
DE102018210779A1 (de) Verfahren und System zur Rettungsgassenbildung durch ein Fahrzeug
DE102021123270B3 (de) Verfahren und Steuerschaltung zum Überprüfen, ob ein aktuell aktiver Fahrmodus innerhalb seiner ODD betrieben wird, sowie System und Backend-Server
DE102019215657A1 (de) Fahrzeugsteuerungsstystem und -verfahren
DE102018213378B4 (de) Fahrassistenzsystem für ein Fahrzeug, Fahrzeug mit demselben und Fahrassistenzverfahren für ein Fahrzeug
WO2023011814A1 (fr) Procédé et circuit de commande pour surveiller une condition d'approbation pour un mode de conduite automatique d'un véhicule à moteur, et véhicule à moteur comportant le circuit de commande
DE102019215815A1 (de) Fahrzeugsteuerungssystem und -verfahren
DE102021005764A1 (de) Vorrichtung und Verfahren zu einer Abstands- und Geschwindigkeitsregelung eines Fahrzeugs
DE102007030839B4 (de) Sicherheitssystem und Verfahren zum Betreiben des Sicherheitssystems
DE102020206128B4 (de) Verfahren zum Steuern einer flottenbasierten Zustandsüberwachung eines Straßenabschnitts eines Straßennetzes sowie zugehöriges System und Kraftfahrzeug und zugehörige Servereinrichtung
DE102018005864A1 (de) Verfahren zum Testen eines Totwinkelassistenzsystems für ein Fahrzeug
DE102018207719A1 (de) Vorrichtung und Verfahren zum Betreiben eines automatisierten Fahrzeugs
EP1643269A1 (fr) Système d'assistance au conducteur avec logique floue
DE102022000390B3 (de) Verfahren zum Betrieb eines zumindest teilautomatisiert steuerbaren Fahrzeugs
DE102022002082A1 (de) Verfahren zur Erkennung von semantischen Beziehungen zwischen Verkehrsobjekten

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22738469

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202280053601.1

Country of ref document: CN

122 Ep: pct application non-entry in european phase

Ref document number: 22738469

Country of ref document: EP

Kind code of ref document: A1