WO2017134058A1 - Procédé de détection et d'identification d'une manoeuvre de conduite d'un usager de la route et véhicule à moteur - Google Patents
Procédé de détection et d'identification d'une manoeuvre de conduite d'un usager de la route et véhicule à moteur Download PDFInfo
- Publication number
- WO2017134058A1 WO2017134058A1 PCT/EP2017/052066 EP2017052066W WO2017134058A1 WO 2017134058 A1 WO2017134058 A1 WO 2017134058A1 EP 2017052066 W EP2017052066 W EP 2017052066W WO 2017134058 A1 WO2017134058 A1 WO 2017134058A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- driving maneuver
- movement
- motor vehicle
- radar
- pattern
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000003068 static effect Effects 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 230000008859 change Effects 0.000 claims description 48
- 230000002123 temporal effect Effects 0.000 claims description 27
- 230000001133 acceleration Effects 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 18
- 239000004065 semiconductor Substances 0.000 claims description 18
- 238000011161 development Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000000052 comparative effect Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000013459 approach Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000009499 grossing Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000010363 phase shift Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 229910001218 Gallium arsenide Inorganic materials 0.000 description 1
- 229910000577 Silicon-germanium Inorganic materials 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18154—Approaching an intersection
-
- 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/52—Discriminating between fixed and moving objects or between objects moving at different speeds
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
- G01S13/60—Velocity or trajectory determination systems; Sense-of-movement determination systems wherein the transmitter and receiver are mounted on the moving object, e.g. for determining ground speed, drift angle, ground track
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
- G01S13/874—Combination of several systems for attitude determination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/0209—Systems with very large relative bandwidth, i.e. larger than 10 %, e.g. baseband, pulse, carrier-free, ultrawideband
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
- G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
- G01S13/726—Multiple target tracking
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93271—Sensor installation details in the front of the vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93272—Sensor installation details in the back of the vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93274—Sensor installation details on the side of the vehicles
Definitions
- the invention relates to a method for identifying and identifying a driving maneuver of a traffic user using movement data describing the movement of the traffic user, wherein the driving maneuver is assigned as part of the identification of a driving maneuver class.
- the invention relates to a motor vehicle.
- a turn-off assistance system should assist the driver in making the turning maneuver.
- Such a function may include, for example, when, when turning to the right, a cyclist approaches from the rear right to warn the driver of an imminent collision via appropriate dispensing means.
- the recognition of one's own driving maneuvers is the trigger for measures of the driver assistance system or even only a criticality evaluation of the traffic situation. It is in many cases the case that certain driving maneuvers can only be recognized as a function of certain trigger signals. For example, a maneuver is only then recognized as a turning maneuver (and thus separated from cornering) when the direction indicator is pressed. Without the presence of the corresponding trigger signal no measures of the driver assistance system, so that especially in critical traffic situations no warning.
- a driver assistance system is a lane change assistance system.
- a lane change assistance system assists the driver in changing the lane. For example, by means of radar sensors or other environmental sensors other road users, in particular in the blind spot, can be detected. If another road user approaches from behind, for example, an LED, which represents an indication of this road user, can be activated. In known lane change assistants, this function is further refined by assuming a lane change intention when the direction indicator is set, and the warning is amplified, for example by flashing the said LED.
- the invention is therefore based on the object to provide a high-quality, reliable detection of driving maneuvers of a road user.
- each driving maneuver class at least one driving maneuver the driving maneuver class characterizing, temporal movement pattern is associated with at least one object containing comparison data structure and the recognition and identification by correlation of the movement patterns corresponding part of the movement data with the movement patterns of the at least one comparison data structure.
- the invention is therefore based on the finding that the movement relative to dynamic and static objects in the environment of the road user provides a significant, useful and at least in the correct compilation often also unique indicator of the actual driving maneuver.
- a correct interpretation and in particular a correct identification of the respective To achieve driving maneuvers relevant dynamic and static objects, highly accurate information about the static and dynamic objects and the movement of the road user relative to these objects are required.
- radar data After a combination of motion data and three-dimensionally determinable distance data is provided by radar sensors, it is proposed in the present invention to use radar data in which static and dynamic objects are distinguished in the environment of the road user and at least partially the relative movement data between the relevant dynamic and deliver static objects and the road user.
- CMOS complementary metal-oxide-semiconductor
- RF CMOS complementary metal-oxide-semiconductor
- a very low cost small radar sensor is possible, which can meet the space requirements significantly better and due to the short signal paths also has a very low signal-to-noise ratio and for high frequencies and larger, variable frequency bandwidths is suitable. Therefore, such small-sized radar sensors can also be used for short-range applications, for example in the range of 30 cm to 10 m.
- CMOS transceiver chip and / or a package with CMOS transceiver chip and antenna on a common circuit board with a digital signal processing processor (DSP processor) or the functions of the signal processing processor in the CMOS Integrate transceiver chip. Similar integration is possible for control functions.
- DSP processor digital signal processing processor
- a radar sensor with a semiconductor chip that realizes at least the radar transceiver is used.
- a digital signal processing component and / or a control unit of the radar sensor can also be realized by the semiconductor chip;
- the semiconductor chip and an antenna arrangement of the radar sensor are implemented as a package.
- Such small-scale semiconductor radar sensors, wherein preferably CMOS radar sensors are used, can also be particularly easily concealed on the force Install vehicle, for example in the bumper and / or behind corresponding radard take understanden windows in the doors.
- the radar sensor for recording the radar data is operated with a frequency bandwidth of at least two 2 GHz, preferably 4 GHz, and / or in a frequency range from 77 to 81 GHz.
- High frequency bandwidths allow high distance, angle, and Doppler resolution.
- a particularly advantageous development further provides that a plurality of radar sensors, in particular eight radar sensors, is used, which cover the surroundings of the motor vehicle in a 360 ° radius.
- a plurality of radar sensors in particular eight radar sensors, is used, which cover the surroundings of the motor vehicle in a 360 ° radius.
- information is available about dynamic and static objects around the motor vehicle, which can also be observed over a longer period of time.
- three small-scale semiconductor radar sensors are installed in a front bumper of the motor vehicle, three more in a rear bumper of the motor vehicle and two more laterally, especially in the doors.
- These are particularly preferably wide-angle radar sensors whose detection ranges can also overlap in order to enable data plausibility.
- an opening angle of more than 140 ° may be provided in the azimuth.
- the antenna arrangement of the radar sensor is designed in such a way that angles in two mutually perpendicular planes can be determined in order to actually obtain three-dimensional radar data on dynamic and static objects in the surroundings of the motor vehicle.
- embodiments of the present invention are conceivable in which the driving maneuver recognition is based exclusively on the radar data as movement data. In other embodiments, however, it is also possible to include further movement data, for example environment data of other environment sensors, or even ego data related to the state of the own motor vehicle.
- threshold values of a correlation value considered in the context of the correlation can be used to detect maneuvers, which means that as soon as a correlation of a certain size is present, it can be assumed that a maneuver is present.
- the largest correlation value determined in the context of the correlation is used, wherein the driving maneuver is assigned to the driving maneuver class whose movement pattern produced the greatest correlation.
- Movement patterns in the sense of the present invention usually relate to at least one temporal movement pattern progression, to which time series corresponding to the radar data can be derived, which can serve as comparison basis, wherein the movement patterns can also relate to properties of temporal pattern progressions or of combinations of temporal pattern progressions. as will be shown in more detail below.
- an advantageous development of the present invention that is used in its own motor vehicle as the road user, the temporal change of formed by objects road boundary contours of a road used by the motor vehicle as a movement pattern.
- a road boundary can in principle be determined by certain larger peripheral development objects, such as curbs and / or guardrails
- the actual course of the road boundary as the transition from the ground to the busy road to detect a different surface and thus to determine extremely accurately the course of the road boundary.
- the temporal changes can be compared with typical pattern profiles stored in the motion patterns, and thus pattern changes typical of the corresponding driving maneuvers of the driving maneuver class.
- pattern changes typical of the corresponding driving maneuvers of the driving maneuver class.
- a corner is ahead of the boundary around which the motor vehicle drives, for example with an ultimately constant distance, so that the turning process results from the time course of the appearance of this road boundary corner in the radar data derive.
- the general underlying idea here is therefore that the radar sensors of their own motor vehicle perceives the position change of objects from their perspective in a driving maneuver, even though the objects in the world coordinate system are static.
- At least a temporal Pattern course of at least one motion variable of the road user relative to a static or dynamic reference object and / or at least a relationship between temporal pattern progressions of at least one on different reference objects related motion magnitude is used, wherein the correlation using at least one at least partially derived from the radar data or contained in this measurement history the amount of movement of the road user is performed.
- movement quantities of the road user, in particular of the own motor vehicle, relative to at least one static or dynamic reference object are considered, whereby the decisive factor can also be a connection between several (different) pattern progressions.
- Object data related at least to the reference object for determining a measurement course from the radar data can be determined by classifying objects detected by the radar sensor and identifying the reference object in the classified objects. Also in this context, it is particularly preferred to use high-resolution, even semiconductor technology using radar sensors, which provide excellent quality radar data, which make it possible to classify dynamic and static objects in the environment of the motor vehicle and thus to find the required reference object. Basically known methods for the evaluation of radar data and classifiers for the assignment of detected objects to object classes or for the determination of more accurate information about an object can be used.
- a further road user and / or an object indicating the boundary of a currently traveled road and / or an urban development object and / or a distance from the object and / or a speed and / or an acceleration relative to the object can be used as the reference object be used.
- the concrete selection depends on the driving maneuver to be recognized and its special characteristics, with concrete examples being discussed in more detail below.
- driving maneuvers are not only characterized by a single characteristic with respect to a single static and / or dynamic object, but it is of course conceivable to use different typical movements within a driving maneuver class and combined in the context of identification and detection, and in particular be provided can be that a driving maneuver is detected only if several different movement patterns are met. In this case, therefore, a combination is used, which allows a reliable and unambiguous detection of driving maneuvers, for example, to distinguish turning operations from cornering and the like.
- a further development of the invention therefore provides that at least one movement pattern with at least two different pattern progressions is used, wherein a presence of a driving maneuver of the assigned driving maneuver class is determined only with sufficient agreement of all pattern progressions with the corresponding measuring progressions. If at least two characteristic properties of a maneuver that are present in radar data are required, the overall stability and reliability of the maneuver recognition is increased. Concrete options are now explained in more detail with regard to a lane change process as driving maneuvers. When modeling a lane change as a parabola, certain theoretical courses for the transverse offset, the transverse speed and the lateral acceleration with respect to a third-party vehicle detected by radar (other traffic participant) arise as a dynamic object.
- Corresponding real progressions can also be measured, whereby temporally asymmetrical as well as temporally symmetrical cases can be considered. If now a lane change detection based on the own lateral acceleration are made, it should first be noted that a detection based on the characteristic curve of the (absolute or relative) lateral acceleration at the beginning of the lane change is still not sufficient to ensure reliable, high quality lane change detection, otherwise False / false warnings could occur. Above all, this is due to the fact that a qualitatively similar course can also occur with pendulum movements, track corrections or cornering.
- both lateral acceleration curves can also be considered as measurement curves, in which case the connection should consist, after the other road user usually also changes lanes, that the gradient of the two measurement curves should be equal in magnitude.
- a lane change class is used as a driving maneuver class for lane change maneuvers, in which the relationship between a temporal pattern course of an absolute lateral acceleration and a temporal pattern course of a relative transverse acceleration to a moving in the same direction as the own motor vehicle reference object an equal slope and / or an intersection of the pattern curves is used and for correlation the presence of the hangs is checked at at least partially derived from the radar data traces.
- a preferred embodiment of the present invention with regard to a lane change detection provides that a lane change class is used as a driving maneuver class for lane change maneuvers, wherein as two pattern courses of a movement pattern a cross-shelf to a moving in the same direction as the own motor vehicle reference object and an absolute or relative to the reference object determined lateral acceleration of the motor vehicle can be used.
- a lane change class is used as a driving maneuver class for lane change maneuvers, wherein as two pattern courses of a movement pattern a cross-shelf to a moving in the same direction as the own motor vehicle reference object and an absolute or relative to the reference object determined lateral acceleration of the motor vehicle can be used.
- a preferred embodiment of the present invention provides that in case of unfinished driving maneuvers only a proportion corresponding to the completed portion of the driving maneuver is used for the correlation. This means that within the framework of the correlation it is also possible to use only a portion of the corresponding movement pattern which matches the time length in order to be able to identify as early as possible incipient or generally unfinished driving maneuvers. Especially when the obtained driving maneuver information for warning driver assistance systems are used, it is particularly useful to enable the earliest possible detection.
- the present invention allows not only the recognition of a completed maneuver, but also a recognition during the implementation of the maneuver or with particular advantage even at the beginning of a maneuver when appropriate movement patterns are used, for example, in the case of lane change detection the typical lateral acceleration curve as well as the cross-storage to another road user as a reference object. Then functions that warn against the completion / execution of the maneuver can be used early.
- a list of most probable driving maneuver classes is determined at least when driving maneuvers begin and / or when at least one correlation value of a further driving maneuver class determined within the correlation is below the correlation value of the driving maneuver class with the highest correlation within a tolerance interval ,
- a kind of stochastic prediction of the possible driving maneuvers is given, so that not only the driving maneuver with the highest correlation value is output by the method according to the invention as driving maneuver information, but, if several driving maneuvers are still conceivable, these velvet with the associated probabilities (in the form of their correlation values) are made available, and thus can be decided on the basis of thresholds within driver assistance systems themselves, as of when a particular maneuver leads to the triggering of a function, without necessarily this maneuver already the most likely present Driving maneuver must be.
- Such embodiments are particularly suitable for driver assistance systems that serve the safety of the driver, since then a greater increase in safety is given.
- the at least one determined driving maneuver class is preferably used in the context of at least one function of a driver assistance system of the motor vehicle.
- the determination of the driving maneuver class takes place in a central control unit which makes the resulting driving maneuver information available to a plurality of driver assistance systems, for example a lane change assistance system, a cornering assistance system, a overtaking assistance system, a turning assistance system and the like.
- the invention also relates to a motor vehicle, comprising at least one radar sensor and a control device designed for carrying out the method according to the invention. All statements relating to the method according to the invention can be analogously transferred to the motor vehicle according to the invention, with which therefore also the already mentioned advantages can be obtained.
- FIG. 1 is a schematic diagram of a motor vehicle according to the invention
- FIG. 2 shows a radar sensor used in the motor vehicle according to FIG. 1
- FIG. 3 is a flowchart of the method according to the invention
- Fig. 4 is a traffic situation to explain the inventive
- FIG. 5 shows the contour of a road boundary at different time points up to FIG. 7 in the traffic situation according to FIG. 4, FIG.
- Fig. 1 1 shows the time course of the absolute lateral acceleration together with the cross-storage to a reference object.
- FIG. 1 shows a schematic diagram of a motor vehicle 1 according to the invention.
- This has eight radar sensors 2, of which three are installed in the rear bumper, three in the front bumper and two in the doors of the motor vehicle. After it is a wide-angle radar sensors 2, as indicated by the indicated detection areas 3, a detection of the environment of the motor vehicle 1 in a 360 ° radius is possible.
- Fig. 2 shows the structure of the radar sensor 2 used in more detail.
- This is realized in semiconductor technology, here specifically CMOS technology, and is operated in a frequency band of 77 to 81 GHz with a frequency bandwidth of 4 GHz in order to deliver high-resolution radar data.
- the radar sensor 2 has a housing 4, in which a circuit board 5 is supported, the a package 6 carries, which is formed of a semiconductor chip 7 and an antenna assembly 8 of the radar sensor 2.
- the semiconductor chip 7, here a CMOS chip in addition to a radar transceiver 9, a control unit 10 of the radar sensor 2 and a digital signal processing component 1 1 (DSP) of the radar sensor 2 are realized.
- DSP digital signal processing component 1 1
- the radar data is used as at least part of the movement data in order to recognize and identify a driving maneuver of the motor vehicle 1, as carried out by a driver.
- the driving maneuver information obtained here is made available to different driver assistance systems 13, 14, 15, wherein in the present case the driver assistance system 13 is a lane change assistant, in which the driver assistance system 14 is an overtaking assistant and in the driver assistance system 15 is a turn assistant.
- a step S1 radar data of the environment of the motor vehicle 1 are recorded. These radar data are, as is known in principle, pre-evaluated, on the one hand to distinguish static and dynamic objects, on the other hand to at least partially classify these objects or to obtain more accurate information about these objects. Due to the high-resolution radar data of the radar sensor 2, this can be done with high quality. At least partially, the radar data is then added to the motion data to be used to identify and identify driving maneuvers.
- reference objects are determined and identified from the static and dynamic objects that are needed to establish a correlation between the movement data, comprising at least partial radar data, and movement patterns, each associated with a driving maneuver class.
- Driving maneuver classes describe certain Types of driving maneuvers and can be divided differently, for example, in a lane change class for lane change as Fahrma- növer, a turning class for a turning maneuver as a driving maneuver, a cornering class for cornering as driving maneuvers and the like.
- These temporal movement patterns for which specific examples are given below based on driving maneuvers, ultimately describe characteristic temporal processes with regard to reference objects which are characteristic of the driving maneuver whose driving maneuver class they are assigned.
- a plurality of movement patterns of a driving maneuver class can be assigned, which, for example, must be fulfilled jointly and / or in which results of the correlation of a plurality of movement patterns are combined as the correlation value for the driving maneuver class.
- correlation values for the individual movement patterns are then determined. For example, as will be explained in more detail below, measurement curves of a motion variable derived from the radar data can be compared with pattern patterns of the motion variable in the motion patterns; it is also conceivable to provide correlations between different pattern progressions as motion patterns and to check whether these Correlations are also present in the measurement progressions, which are at least partially extracted from the radar data. Also, the temporal change of contours can be considered in the context of a movement pattern, which is ultimately a pattern change with actual measurement changes, as they result from the radar data is compared.
- Correlation values between such courses, changes or connections can be determined, as is generally known in the prior art, in particular also taking account of reliability values for the radar data and the like, it being noted that the general reliability of radar data still has a plausibility check in the sense of lapping coverage areas 3 and / or can also be done via a temporal plausibility check.
- the proportion of temporal movement patterns is used, which is so far relevant; In order to find this proportion, for example, it may be attempted to achieve an optimal correlation while maintaining certain boundary conditions and the like.
- step S4 the driving maneuver information is then compiled. It can be provided that the driving maneuver with the highest correlation value, if it exceeds a threshold, is recognized as the currently performed driving maneuver; However, it is also conceivable, at least for incipient driving maneuvers and / or when at least one correlation value of a further driving maneuver class determined within the correlation lies within a tolerance interval below the correlation value of the driving maneuver class with the highest correlation to determine a list of most likely driving maneuver classes as driving maneuver information. Ideally, the correlation values or the derived probabilities of relevance are likewise stored in the driving maneuver information. The driving maneuver information is then forwarded to the driver assistance systems 13, 14, 15, where it can be evaluated accordingly with regard to the performance of functions.
- FIG. 4 shows a first traffic situation, in which the vehicle 1 is moved in the area of an intersection 16 and, according to the arrow 17, performs a turning maneuver as a driving maneuver. Due to the high-resolution radar data, it is possible to recognize the road boundary 18 as such, thus as a transition from the road surface of the currently traveled road 19 to another ground, as indicated by individual reflection points in FIG. 4. Considering now the turning process according to arrow 17 as such, the contour of the road boundary 18 to the current position 20 of the motor vehicle 1 will appear changed from time to time. is shown for three such times in Figs. 5-7. Ultimately, there is a continuous change in the contour of the road boundary 18 in the radar data, wherein the measured, resulting from the radar data measurement change can be compared with a pattern change of the corresponding movement pattern to recognize the bending process as such and identify.
- FIG. 8 shows a further traffic situation in which the motor vehicle 1 moves on a two-lane road 21. As indicated by the arrow 22, it performs a lane change here as a driving maneuver. Another road user 23 is already on the lane 24 to which the motor vehicle 1 would like to change.
- Fig. 9 shows various absolute, d. H. Pattern patterns of motion quantities relating to static objects during the lane change process are plotted against time.
- the curve 25 symbolizes the transverse position
- these relationships are not used for detecting a lane change after the derived from the radar data measurement history, in which the relationship should also be determined, only after a smoothing over several cycles similar continuously as the On the other hand, the two-fold derivative and a respective smoothing results in a phase shift, which at least makes it difficult to superimpose the curves resulting from the measurement curves.
- the lateral acceleration profile described again by the curve 27 is regarded as a further pattern profile, the transverse deviation described by the curve 30, FIG. 11, relative to the reference object, further road users 23, and thus the transverse deposition which also takes a characteristic course over time.
- the synopsis of these two pattern progressions, which are each compared with radar data determined in the course of the correlation, allows a stable and reliable detection of lane change operations as driving maneuvers even at early times during the maneuver.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Mathematical Physics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
L'invention concerne un procédé de détection et d'identification d'une manœuvre de conduite d'un usager de la route par l'utilisation de données de déplacement décrivant le déplacement de l'usager de la route, la manœuvre de conduite étant associée, dans le cadre de l'identification, à une classe de manœuvres. Selon ce procédé, les données de déplacement comprenant des données radar obtenues au moyen d'au moins un capteur radar (2) d'un véhicule à moteur (1), dans lesquelles des objets statiques et dynamiques dans l'environnement de l'usager de la route sont différenciés; au moins une structure de données de référence comprenant des modèles de déplacement temporels par rapport à au moins un objet, caractérisant des manoeuvres de la classe de manœuvres, est attribuée à chaque classe de manoeuvres et la détection et l'identification se font par corrélation d'une partie des données de déplacement correspondant aux modèles de déplacement avec les modèles de déplacement de ladite au moins une structure de données de référence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP17703096.2A EP3411729A1 (fr) | 2016-02-02 | 2017-01-31 | Procédé de détection et d'identification d'une manoeuvre de conduite d'un usager de la route et véhicule à moteur |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102016001101.7A DE102016001101A1 (de) | 2016-02-02 | 2016-02-02 | Verfahren zur Erkennung und Identifikation eines Fahrmanövers eines Verkehrsteilnehmers und Kraftfahrzeug |
DE102016001101.7 | 2016-02-02 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017134058A1 true WO2017134058A1 (fr) | 2017-08-10 |
Family
ID=57963201
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2017/052066 WO2017134058A1 (fr) | 2016-02-02 | 2017-01-31 | Procédé de détection et d'identification d'une manoeuvre de conduite d'un usager de la route et véhicule à moteur |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3411729A1 (fr) |
DE (1) | DE102016001101A1 (fr) |
WO (1) | WO2017134058A1 (fr) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109421731A (zh) * | 2017-09-05 | 2019-03-05 | 罗伯特·博世有限公司 | 可信度检验模块、驾驶辅助系统和校准传感器的方法 |
CN112255621A (zh) * | 2020-10-09 | 2021-01-22 | 中国第一汽车股份有限公司 | 一种车辆传感器的标定方法、装置、电子设备及存储介质 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102017214022A1 (de) * | 2017-08-11 | 2019-02-14 | Audi Ag | Verfahren zur Ermittlung von die Eigenbewegung eines Kraftfahrzeugs beschreibenden Egodaten und Kraftfahrzeug |
DE102019215863A1 (de) * | 2019-10-15 | 2021-04-15 | Continental Automotive Gmbh | Fahrzeug, umfassend eine Abbiegeassistenzvorrichtung, Abbiegeassistenzvorrichtung und Verfahren zum Betreiben eines Fahrzeugs |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10118265A1 (de) * | 2001-04-12 | 2002-10-17 | Bosch Gmbh Robert | Verfahren zur Erkennung eines Spurwechsels eines Fahrzeugs |
DE102008026397A1 (de) * | 2007-06-05 | 2009-01-29 | GM Global Technology Operations, Inc., Detroit | Radar-, Lidar- und Kamera-unterstützte Verfahren zur Schätzung der Fahrzeugdynamik |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102013210941A1 (de) * | 2013-06-12 | 2014-12-18 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Betreiben eines Fahrzeugs |
DE102013021813B4 (de) * | 2013-12-20 | 2018-05-24 | Audi Ag | Fahrerassistenzsystem mit adaptiver Reaktionsschwelle |
-
2016
- 2016-02-02 DE DE102016001101.7A patent/DE102016001101A1/de active Pending
-
2017
- 2017-01-31 EP EP17703096.2A patent/EP3411729A1/fr not_active Ceased
- 2017-01-31 WO PCT/EP2017/052066 patent/WO2017134058A1/fr active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10118265A1 (de) * | 2001-04-12 | 2002-10-17 | Bosch Gmbh Robert | Verfahren zur Erkennung eines Spurwechsels eines Fahrzeugs |
DE102008026397A1 (de) * | 2007-06-05 | 2009-01-29 | GM Global Technology Operations, Inc., Detroit | Radar-, Lidar- und Kamera-unterstützte Verfahren zur Schätzung der Fahrzeugdynamik |
Non-Patent Citations (2)
Title |
---|
JRI LEE ET AL.: "A Fully Integrated 77-GHz FMCW Radar Transceiver in 65-nm CMOS Technology", IEEE JOURNAL OF SOLID STATE CIRCUITS, vol. 45, 2010, pages 2746 - 2755 |
REINHARD FEGER ET AL: "Accuracy Improvement for Direction of Arrival Estimation by the Use of a Mirror Element", IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, IEEE SERVICE CENTER, PISCATAWAY, NJ, US, vol. 59, no. 4, 1 April 2011 (2011-04-01), pages 1016 - 1024, XP011372586, ISSN: 0018-9480, DOI: 10.1109/TMTT.2011.2112670 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109421731A (zh) * | 2017-09-05 | 2019-03-05 | 罗伯特·博世有限公司 | 可信度检验模块、驾驶辅助系统和校准传感器的方法 |
CN112255621A (zh) * | 2020-10-09 | 2021-01-22 | 中国第一汽车股份有限公司 | 一种车辆传感器的标定方法、装置、电子设备及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
EP3411729A1 (fr) | 2018-12-12 |
DE102016001101A1 (de) | 2017-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3254138B1 (fr) | Procédé de détermination d'une donnée position transversale d'un véhicule à moteur sur une chaussée, et véhicule à moteur | |
EP1577682B1 (fr) | Système de localisation d'objets pour véhicule automobile pour identifier des procédures de changement de voie | |
EP2068173B1 (fr) | Procédé destiné à la mesure de mouvements obliques dans un système d'assistance au conducteur | |
EP1853453B1 (fr) | Procede pour determiner la plausibilite d'objets dans des systemes d'assistance a la conduite | |
EP2867093B1 (fr) | Procédé et système d'utilisation de l'information | |
WO2015106913A1 (fr) | Procédé et système pour évaluer le tracé d'une voie de circulation | |
DE102004019651A1 (de) | Blindspot-Sensorsystem | |
EP3411729A1 (fr) | Procédé de détection et d'identification d'une manoeuvre de conduite d'un usager de la route et véhicule à moteur | |
DE102015012812B4 (de) | Verfahren zum Betrieb von Radarsensoren in einem Kraftfahrzeug und Kraftfahrzeug | |
EP1912844B1 (fr) | Procede pour produire des hypotheses relatives a l'environnement exterieur pour des fonctions d'assistance au conducteur | |
DE102013212359A1 (de) | Vorhersage von Fahrpfaden eines Fahrzeugs | |
EP3259614B1 (fr) | Procédé permettant de déterminer une information de localisation d'une automobile par rapport à un couloir de circulation et automobile | |
EP2046619A1 (fr) | Système d'assistance au conducteur | |
DE102013217486A1 (de) | Verfahren zur Repräsentation eines Umfelds eines Fahrzeugs in einem Belegungsgitter | |
WO2003036320A2 (fr) | Procede et dispositif de mesure des vitesses d'objets en mouvement | |
EP3091368B1 (fr) | Procede de fonctionnement d'un capteur radar dans un vehicule automobile, capteur radar et vehicule automobile | |
EP3136123A1 (fr) | Procédé d'attribution des positions de montage des capteurs automotives du radar installés à des positions respectives | |
DE102017214022A1 (de) | Verfahren zur Ermittlung von die Eigenbewegung eines Kraftfahrzeugs beschreibenden Egodaten und Kraftfahrzeug | |
EP1643269A1 (fr) | Système d'assistance au conducteur avec logique floue | |
DE102011113325A1 (de) | Verfahren zur Objekterkennung mittels Bilddaten | |
DE102012220191A1 (de) | Verfahren zur Unterstützung eines Fahrers bei der Querführung eines Fahrzeugs | |
DE102020105192B4 (de) | Verfahren zum Detektieren bewegter Objekte in einer Fahrzeugumgebung und Kraftfahrzeug | |
EP3564699B1 (fr) | Procédé de détermination de la vitesse absolue d'un autre usager de la route et véhicule automobile | |
DE102017103700A1 (de) | Vermeiden einer Kollision durch einen Lenkeingriff in Abhängigkeit von einer Bewegung eines fahrzeugexternen Objekts | |
WO2021104805A1 (fr) | Procédé de fonctionnement d'un dispositif de détection d'environnement avec évaluation basée sur une grille et fusion, et dispositif de détection d'environnement |
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: 17703096 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2017703096 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2017703096 Country of ref document: EP Effective date: 20180801 |