EP4313711A1 - Analyse de conducteur basée sur un segment et assistance au conducteur individualisée - Google Patents
Analyse de conducteur basée sur un segment et assistance au conducteur individualiséeInfo
- Publication number
- EP4313711A1 EP4313711A1 EP22714449.0A EP22714449A EP4313711A1 EP 4313711 A1 EP4313711 A1 EP 4313711A1 EP 22714449 A EP22714449 A EP 22714449A EP 4313711 A1 EP4313711 A1 EP 4313711A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data
- route
- driving
- test
- driver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title description 7
- 238000012360 testing method Methods 0.000 claims abstract description 124
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000001133 acceleration Effects 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000036461 convulsion Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000010426 asphalt Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 description 1
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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
- B60W40/08—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 drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- 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
- B60W30/02—Control of vehicle driving stability
- B60W30/025—Control of vehicle driving stability related to comfort of drivers or passengers
-
- 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
- B60W40/10—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 vehicle motion
- B60W40/105—Speed
-
- 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
- B60W40/10—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 vehicle motion
- B60W40/107—Longitudinal acceleration
-
- 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
- B60W40/10—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 vehicle motion
- B60W40/109—Lateral acceleration
-
- 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
- B60W40/10—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 vehicle motion
- B60W40/114—Yaw movement
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/085—Changing the parameters of the control units, e.g. changing limit values, working points by control input
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0063—Manual parameter input, manual setting means, manual initialising or calibrating means
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
- B60W2050/0095—Automatic control mode change
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/10—Number of lanes
-
- 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
- B60W2552/30—Road curve radius
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/406—Traffic density
-
- 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
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/20—Ambient conditions, e.g. wind or rain
-
- 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
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
- B60W2555/60—Traffic rules, e.g. speed limits or right of way
Definitions
- the present invention relates to a method for controlling a vehicle on a route to be driven.
- the present invention relates to a corresponding driver assistance system and a motor vehicle with such a driver assistance system.
- Driver assistance systems and driving functions are usually not very individualized and therefore offer the driver little scope for an emotional driving experience or generate little acceptance due to incomprehensible interventions.
- Individual driver assistance systems enable improved customer acceptance and the associated added value or increased motivation to configure the vehicle accordingly.
- a driving dynamics analysis of the driving behavior and driving skills of a driver is usually done in known methods by assigning the driver to individual classes, such as "sporty”, “cautious”, etc. This assignment can be done, for example, in the form of GG diagrams (acceleration diagrams) in which the longitudinal and lateral acceleration are plotted two-dimensionally. In this way, a rough description of the limits of driving behavior or driving ability can be made, but detailed preferences in driving the vehicle cannot be taken into account in this way.
- Patent US 2021/0012590 A1 discloses a monitoring device for providing vehicle telemetry data.
- the monitoring device includes a sensor for detecting vibrations caused by vehicle and engine movements in vehicle parts in order to generate corresponding vibration data. From the vibration data, vehicle or engine characteristics can be extracted.
- the publication WO 2019/134110 A1 discloses a method and a system for autonomous driving.
- a driving situation map is generated from sensor data.
- a deep learning algorithm is trained to generate a driving command based on the driving situation map.
- the publication DE 102017209258 A1 discloses a method and a device for monitoring a driving stability of a vehicle on a driving route ahead.
- a current speed, a current steering angle and a current position of the vehicle are determined.
- a driver type is also determined.
- a speed signal and a steering angle signal are predicted using this data.
- Document US 2016/0026182 A1 discloses personalized driving of autonomous vehicles. For this purpose, at least part of a driving profile is loaded onto a vehicle. The vehicle is controlled based on the driving profile.
- the object of the present invention consists in proposing a driver assistance system with which more individual support for the driver is possible.
- a method for controlling a vehicle on a route to be traveled is provided. Such a method is carried out in a driver assistance system, for example. However, the method can also be used to control a vehicle autonomously. In one case, the driver receives individual support tailored to the driver, and in the other case, the steering is completely relieved by guiding the vehicle individually according to the driver's habits.
- test track is driven on by a driver.
- this driver can then also drive on other test routes in order to obtain corresponding test data.
- the test track or the test tracks should have as many different features as possible so that a wide variety of test data can be obtained.
- Geometric test data is collected from the test track. This acquisition of the geometric test data can be done by means of the vehicle's sensors. When driving on the test track, these sensors record such geometric test data as lane width or track width, curvature of the track and the like. However, such geometric test data can also be made available, for example, from a database and loaded into the vehicle on occasion. This Geometric test data are the basis for classifying routes or route sections to be traveled in the future.
- driving dynamics test data are recorded.
- Such test data include, for example, accelerations, speeds and the like.
- these driving dynamics test data are assigned to the geometric test data. This is the only way to determine the driver's behavior individually, for example when cornering.
- the driving dynamics test data is determined and saved by a sensor system in the vehicle. If necessary, these driving dynamics test data are transmitted together with the geometric test data to a vehicle-external computing unit in order to process them there and to send correspondingly processed data back to the vehicle.
- the driving dynamics test data provide information about the driving behavior of the driver in certain situations or on certain sections of the road.
- the recorded or partially provided test data ie the geometric test data and possibly further objective situational data, together usually form a cloud of points in a test data space, which is usually multidimensional.
- Each parameter of the geometric test data and the further situation data forms its own dimension in the test data space.
- the test data space or point cloud is now divided into clusters.
- a cluster analysis can be carried out in order to discover similarity structures in the database.
- the cluster analysis is based on objectifiable variables such as track width, curvature, gradient, gradient, temperature, traffic volume, weather (wet, dry,...), subsoil (asphalt, cobblestones), planning reference variables (speeds, acceleration, yaw angle, etc.). .) but not based on the subjective dimensions of a driver.
- the clustering serves to automatically subdivide driven routes into scenarios / segments. It is intended to serve as a tool to objectively provide areas for extracting the driving style. In this way, the test data space or the test data can be divided into a large number of clusters, which can serve as a basis for a later classification.
- the driving dynamics data for each cluster is determined on the basis of the driving dynamics test data of the respective cluster.
- the clustering identifies scenarios in which a driver is highly likely to behave in a reproducible manner, and the behavior is now determined on this basis and later applied.
- the driver drives on a left turn Hard shoulder road closer to the outer edge of the road than to the center line. This has been proven, for example, in several test drives.
- the driver keeps a distance of one meter to the outer edge of the lane in such situations. Therefore, this distance to the outer edge of the road is defined as a dynamic data set for precisely this cluster. If the vehicle then drives autonomously or with assistance, the vehicle will try to maintain exactly this individual distance of one meter to the outer edge of the lane when driving through the left-hand bend. As a result, the driver can be supported exactly as he would decide himself.
- route sections of the route to be driven are assigned to the clusters using geometric data of the route to be driven.
- a new, unknown route that the driver wants to drive is automatically divided into segments.
- Each segment, i.e. each route section, is assigned to a cluster.
- the assignment is made, among other things, via geometric data that is available before the route to be traveled and, if necessary, other data that describes the respective scenarios (route width, curvature, inclination, gradient, temperature, traffic volume, weather, subsoil, reference variables for planning, etc.) .
- the geometric data was obtained from a navigation system or from a database external to the vehicle.
- the geometric data of the route to be driven can be taken into account in order, for example, to assign each point on the route to be driven to a cluster.
- a centroid method can be used to assign each point on the route to be driven to a respective cluster.
- the point is assigned to the cluster to which the point has the smallest distance in the data space.
- the entire route to be traveled can be subdivided into route sections or segments, each of which is assigned to one of the clusters.
- At least one vehicle component of the vehicle is controlled in one of the route sections in accordance with the defined driving dynamics data of the respective cluster. At least one vehicle component is therefore activated accordingly, which means that the driver is either supported or the vehicle is controlled autonomously. Since the route section to be traveled has been clearly classified, ie has been assigned to a cluster, precisely those defined driving dynamics data of the respective cluster can be used for control. For example, if the section to be traveled falls within the “straight stretch” cluster and the driver always drove such “straight stretches” at a speed of 90 km/h during the test drives, the individual Driver support controls the vehicle so that it drives 90 km/h on the "straight line”.
- the geometric test data contain position data, a curvature, a route width, a combination of route section types (e.g. curve followed by a straight line, etc.) and/or a number of lanes of the test route.
- the geometry of the test track is sufficiently known. Further information can be obtained from this geometric test data, such as the length of a straight stretch, the length of a curve, the gradient and the like.
- this test data it is also possible with this test data to analyze the interaction of route sections. For example, a driver will drive differently into a left turn if the stretch of road ahead was a straight stretch of road or a right turn.
- additional situational data relating to the weather, time of day, traffic density and/or environment can be used when driving on the test track are recorded, the situation data being included in the test data space and the formation of clusters, current situation data for driving on the route to be traveled being recorded and the assignment of the route sections to the clusters also taking place as a function of the current situation data.
- Related situation data thus describe the situation or the scenario in which the forthcoming journey is embedded.
- the weather can play a role if the road surface is wet or snow-covered.
- the time can also play a role, according to which traffic jams can be predicted, for example.
- the traffic density can be determined, for example, via additional information channels such as radio and the like.
- it can also be important for the driving situation how the area around the route is designed.
- the driving behavior changes, for example, if the route is not in an open environment but in a tunnel.
- the situation data relating to the surroundings also include, for example, traffic signs at the edge of the road. For example, a driver in an urban area, which is limited to a maximum speed of 50 km/h, usually drives 55 km/h, while another driver in this situation usually drives exactly 50 km/h.
- This situation-specific individual behavior can also be taken into account here by recording the driving dynamics test data (here the speed) for the “local area” route section and using it for individual control.
- the above situation data can be taken into account in the test data space as separate dimensions.
- Special scenarios or clusters can thus be formed, such as “cornering on a wet road”, “cornering in a local area”, “cornering on a country road” and the like.
- the algorithm can access cluster elements that contain the situation “rain” or “wet road”. In this way, the route sections of the route to be traveled can be assigned to situation-specific clusters due to the current situation.
- the vehicle can be controlled using the driving dynamics data from these clusters.
- the driving dynamics data for several driving modes of the driver is recorded and the test data space is divided into clusters also depending on the several driving modes, one of the several driving modes is selected for the route to be driven, and the assignment the route sections to the clusters depending on the selected driving mode.
- the driver himself chooses his driving style, such as sport, comfort, eco, etc., and the algorithm nevertheless assists the driver individually or takes over control.
- the driver wants to drive safely or comfortably on the test track and enter this as a parameter during the test drive.
- the algorithm will then divide the route sections into clusters for this specific driving mode and carry out the control accordingly.
- the driving dynamics data can include one or more parameters both for the test drive and for the control of a route to be driven in the future or currently.
- One of these parameters is the route, which a driver usually chooses individually when driving down a route.
- the alignment can also be different, for example with the same geometry in different situations.
- Each driver chooses the right safety distance individually and depending on the situation. Older road users in particular keep a greater safety distance than younger road users.
- This driver-specific safety distance differs again in the various situations.
- the other parameters such as acceleration, speed and jerk are usually very driver-specific. For example, each driver chooses an individual acceleration when starting at a traffic light. The driver accepts such driver assistance all the more if it selects precisely this individual acceleration.
- provision can be made for the geometric data of the route to be driven and/or the current situation data to be individually weighted when assigning route sections of the route to be driven to the clusters.
- the assignment of route sections of the route to be traveled to the clusters is based on machine learning.
- this machine learning can take place unsupervised.
- a neural network is used. Such a network can, for example, be trained with the test data and used to classify the route sections of the route to be driven.
- the test data space also contains vehicle data about the vehicle, and that the at least one vehicle component is controlled specifically for the vehicle.
- vehicle data about the vehicle
- the at least one vehicle component is controlled specifically for the vehicle.
- the driver can obtain the driving dynamics test data specifically for a vehicle. If the driver drives the same test track in a different vehicle, the driving dynamics test data can be quite different.
- it can be advantageous to also store vehicle data and in particular the vehicle type in addition to the test data. In this way, the driver can use his test database for several vehicles and, for example, select a vehicle type for the current control.
- a driver assistance system for controlling a vehicle on a route to be driven with a detection device for detecting geometric test data of the test track and for detecting driving dynamics test data when a driver drives on a test track, a classification device for splitting a test data space formed by the geometric test data in clusters and a data processing device for determining driving dynamics data for each cluster on the basis of those driving dynamics test data that can be assigned to a respective cluster, the classification device being designed to assign route sections of the route to be driven to the clusters based on geometric data of the route to be driven and the driver assistance system has a control device for controlling at least one vehicle component of the vehicle in one of the routes Sections according to the defined driving dynamics data of the respective cluster.
- the clustering is based on objectifiable variables such as route width, curvature, incline, gradient, temperature, traffic volume, weather (wet, dry,...), Ground (asphalt, cobblestones), planning reference values (speed, acceleration, yaw angle, etc.), but not based on the subjective values of a driver.
- Such a driver assistance system therefore has a detection device, which in turn has a corresponding sensor system, for example.
- the detection device can also include suitable interfaces for recording test data.
- the classification device of the driver assistance system can be based on vector machines or neural networks or the like. In any case, the classification device has a processor and corresponding memory components for the automated classification.
- the data processing device of the driver assistance system is also equipped with a corresponding processor and memory modules. If necessary, the classification device and the data processing device are implemented in one unit.
- the driver assistance system has a control device with which vehicle components of the vehicle can be controlled. Appropriate drivers may need to be provided for this purpose.
- the driver assistance system is preferably capable of executing the method described above and its further developments. This results in the same advantages for the driver assistance system as for the corresponding methods.
- a motor vehicle can be equipped with the driver assistance system mentioned above.
- the motor vehicle can thus be controlled or supported individually with the characteristics of a driver.
- the invention also includes the combinations of features of the described embodiments.
- FIG. 2 shows an acceleration diagram for one of the two routes of FIG. 1 for a specific driver
- Figure 3 shows an acceleration diagram of the other route of Figure 1 for the same driver; 4 shows one of the two routes in segmented form; and
- the exemplary embodiments explained below are preferred exemplary embodiments of the invention.
- the described components each represent individual features of the invention that are to be considered independently of one another, which also develop the invention independently of one another and are therefore also to be regarded as part of the invention individually or in a combination other than that shown.
- the exemplary embodiments described can also be supplemented by further features of the invention already described.
- the present invention aims to enable a driver and a vehicle to cope with a driving task in symbiosis.
- the driver should be given as much freedom as possible and the assistance system should monitor the action and status space in a task-specific manner and intervene as required.
- driver-specific properties and characteristics should be identified as precisely and situation-dependently as possible, which can be identified according to a given task and made available for a future assistance system.
- driver-specific characteristics can be derived from a difference to a planned, objectively describable trajectory, which are transferred to objectively describable classes in relation to the respective route segment.
- Driver-specific characteristics can be derived from a difference to a planned, objectively describable trajectory, which are transferred to objectively describable classes in relation to the respective route segment.
- a preferred route an individually selected safety distance, acceleration, speed and jerks according to the analyzed route geometry should provide a driver-specific “fingerprint” that enables local mapping and goes beyond the classification into global classes.
- unknown route segments can also be evaluated.
- future vehicle guidance preferences can be mapped to unknown route segments and customized support can be provided.
- driver data is recorded in different modes (e.g. Sport, Comfort, Eco, Race). Under certain circumstances, however, only a single mode is recorded and used as the data basis.
- modes e.g. Sport, Comfort, Eco, Race.
- route data and edge data can be stored.
- the data can be clustered according to route geometry (curvature), route width, reference speed, reference acceleration and the future route.
- route geometry curvature
- route width route width
- reference speed reference speed
- reference acceleration future route
- the driver's leadership behavior can now be analyzed in these clusters. Parameters that describe the driving behavior or the driving style can now be derived from this in relation to the geometric segments. For a support algorithm, unknown route data can be analyzed according to the clusters formed and the driving behavior in these segments can be predicted.
- a driver's fingerprint can be formed, which can be transferred to an "ADAS" (Advanced Driver Assistance System) for an individually adapted support function.
- ADAS Advanced Driver Assistance System
- test track 1 is driven on by a driver.
- test track 1 shows this test track 1 in a Cartesian coordinate system with x-coordinates and y-coordinates.
- a second route 2 is also shown in FIG. 1, which reflects the route to be traveled. The vehicle or that The driver assistance system should therefore be "taught" with test track 1, and on the basis of the data obtained, route 2 should be assisted or driven autonomously.
- geometric test data of the test track 1 are recorded.
- this geometric test data can also be recorded before the test drive, for example by providing the test data from a database for the control system.
- driving dynamics test data are also recorded by the driver.
- driving dynamics test data characterize the driver. They represent the driver-specific fingerprint mentioned above and relate, for example, to speeds, accelerations, the safety distance and the like in relation to the geometric test data of test track 1.
- FIGS. 2 and 3 show acceleration diagrams that can be obtained, for example, on routes 1 and 2 with one and the same driver. Specifically, the acceleration a y in the y-direction to the right and the acceleration a x in the x-direction upwards are shown in both figures.
- the acceleration a y in the y-direction to the right and the acceleration a x in the x-direction upwards are shown in both figures.
- the two point clouds are intended to show that a two-dimensional data space can be obtained in relation to driver behavior.
- other of the data mentioned above for example the acceleration, the width of the route and the like, can also be recorded on the routes. Accordingly, the recorded data result in a multidimensional data space or a multidimensional point cloud.
- FIG. 2 there is a region 3 at the top center in FIG. 2 which contains data points which occur more frequently than the other points. These points are around the lateral acceleration value of 0 m/s 2 .
- the longitudinal acceleration a x is usually slightly positive in this area 3 .
- the acceleration diagram of FIG. 2 relates to route 2 of FIG. 1. This route 2 has longer straight sections and only a few curves. The driver accelerates on the straight sections, so that the longitudinal acceleration a x shows a corresponding positive value. Since there are only a few strong curves, high transverse accelerations a y occur only with low frequency. 3, on the other hand, shows the acceleration diagram for the test track 1. In the cloud of points in FIG.
- This area 4 is located here in the diagram at the top right, ie with small positive longitudinal acceleration values and with positive transverse acceleration values. This is due to the fact that test track 1 has more curves and, because of the circuit, has more right-hand bends when driving clockwise. These right-hand curves result in positive transverse acceleration values a y in the diagram in FIG. 3 .
- test track 1 is first traveled over for the test data.
- data from route 2 could also be used as test data.
- the test data from test track 1 are used to extrapolate the behavior of the driver onto track 2.
- test track 1 is first divided into segments 5.
- Each segment 5 represents a route section and is therefore assigned to part of the geometric test data.
- Each segment is assigned to one of the given clusters A to J.
- the entire test data space is divided into ten different clusters A to J, for example.
- the number of clusters can be chosen arbitrarily. It is therefore also possible to choose fewer or more than ten clusters into which the test data space is divided.
- each point on the test track is assigned to one of the clusters A to J. This results in a large number of connected groups of points on the route, each of which is assigned to one of the clusters. Geometrically, each group of points represents a segment of this test track 1.
- driving dynamics data should correspond to a cluster.
- all driving dynamics data of the points of the clusters are averaged.
- a median value of the respective parameter (eg speed or acceleration) for the cluster could also be chosen as a fixed value, for example.
- the division into clusters leads to segments on the route that are geometrically similar and are driven on in a similar way in terms of driving dynamics. These formed clusters can now be used to classify and assign unknown route segments.
- the results of the driving analysis of the test track can then be transferred to the assistance system. The analysis of the test track can thus be transferred to the route 2 to be driven.
- the geometric data of the new route 2 to be traveled are known. If necessary, they are determined via a navigation system or the like. Based on this geometric data, clustering into segments can take place. The clusters that were generated in advance in the test data room are used for this. The clustering results in the segments 5 for the route 2 to be traveled according to FIG. Each segment 5 stands for a specific scenario, eg a longer straight stretch, heading for a curve, initial speed 50 km/h, braking acceleration ⁇ 2 m/s 2 etc.
- the driver assistance system can then, for example, display the speed values when driving on stretch 2 in the respective segment and set acceleration values specified for the associated cluster.
- a segment-based analysis offers the possibility of subdividing the driver or his identification into subsets.
- more aspects can be implemented in the description or the parameters can be weighted differently.
- individual driver-specific characteristics can be mapped (such as routing in a scenario that is difficult to see, safety margin and route width, etc.), which are not averaged for each route, but for the one described scenario can be evaluated individually.
- more natural support for the driver can be achieved, which is perceived less as an imposition of a management behavior defined by experts.
- understandable support can be achieved with a high degree of acceptance by the driver.
- certain modes for the driving dynamics support (such as sport, comfort, eco, ...) can be provided in combination with the classification of the driver's ability (eg sporty, careful).
- all of the exemplary embodiments mentioned have the advantage of extracting features that describe the driver behavior based on scenarios in a targeted manner and implementing them in an individualized assistance system. This leads to higher acceptance of the driving dynamics support. Furthermore, the function could be offered as an additional feature to an existing function, thereby adding value to the product without significant additional costs.
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
La présente invention vise à pouvoir garantir une assistance au conducteur aussi individuelle que possible lors de la conduite sur des itinéraires inconnus. À cet effet, la présente invention concerne un procédé pour commander un véhicule, dans lequel des données de test géométrique et des données de test de dynamique de conduite sont obtenues sur un itinéraire de test (1). Les données de test sont divisées en groupes, et des données de dynamique de conduite spécifiques à un groupe sont définies pour chaque groupe. Enfin, l'itinéraire (2) à parcourir est regroupé et le véhicule est commandé dans une section d'itinéraire (5) conformément aux données de dynamique de conduite définies du groupe respectif.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102021203057.2A DE102021203057A1 (de) | 2021-03-26 | 2021-03-26 | Segmentbasierte Fahreranalyse und individualisierte Fahrerassistenz |
PCT/EP2022/057188 WO2022200217A1 (fr) | 2021-03-26 | 2022-03-18 | Analyse de conducteur basée sur un segment et assistance au conducteur individualisée |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4313711A1 true EP4313711A1 (fr) | 2024-02-07 |
Family
ID=81325368
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP22714449.0A Pending EP4313711A1 (fr) | 2021-03-26 | 2022-03-18 | Analyse de conducteur basée sur un segment et assistance au conducteur individualisée |
Country Status (5)
Country | Link |
---|---|
US (1) | US20240140481A1 (fr) |
EP (1) | EP4313711A1 (fr) |
CN (1) | CN117120314A (fr) |
DE (1) | DE102021203057A1 (fr) |
WO (1) | WO2022200217A1 (fr) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102023002133A1 (de) | 2023-05-25 | 2023-08-10 | Mercedes-Benz Group AG | Verfahren und Fahrassistenzsystem zur Erfassung eines individuellen Parameterprofils eines Fahrzeugfahrers |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8260515B2 (en) | 2008-07-24 | 2012-09-04 | GM Global Technology Operations LLC | Adaptive vehicle control system with driving style recognition |
GB2522728A (en) | 2014-01-31 | 2015-08-05 | Cambridge Consultants | Monitoring device |
US9766625B2 (en) | 2014-07-25 | 2017-09-19 | Here Global B.V. | Personalized driving of autonomously driven vehicles |
EP3240714B1 (fr) | 2014-12-29 | 2023-08-30 | Robert Bosch GmbH | Systèmes et procédés pour faire fonctionner des véhicules autonomes an utilisant des profils de conduites personnalisés |
CN107531244B (zh) * | 2015-04-21 | 2020-04-21 | 松下知识产权经营株式会社 | 信息处理系统、信息处理方法、以及记录介质 |
DE102016216335B4 (de) | 2016-08-30 | 2020-12-10 | Continental Automotive Gmbh | System und Verfahren zur Analyse von Fahrtrajektorien für einen Streckenabschnitt |
DE102016117136A1 (de) | 2016-09-13 | 2018-03-15 | Valeo Schalter Und Sensoren Gmbh | Verfahren zum Bestimmen eines Fahrverhaltens eines Fahrers eines Kraftfahrzeugs zum Betrieb eines Fahrerassistenzsystems des Kraftfahrzeugs, Fahrerassistenzsystem sowie Kraftfahrzeug |
JP2018135069A (ja) * | 2017-02-23 | 2018-08-30 | パナソニックIpマネジメント株式会社 | 情報処理システム、情報処理方法及びプログラム |
DE102017209258A1 (de) | 2017-06-01 | 2018-12-06 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Überwachen einer Fahrstabilität eines Fahrzeugs auf einer vorausliegenden Fahrroute |
CA3087361A1 (fr) | 2018-01-05 | 2019-07-11 | Driving Brain International Ltd. | Procedes et systemes de conduite autonome |
DE102019205892B4 (de) | 2019-04-25 | 2022-12-29 | Volkswagen Aktiengesellschaft | Verfahren zum Betreiben eines Kraftfahrzeugs sowie Kraftfahrzeug, das dazu ausgelegt ist, ein derartiges Verfahren durchzuführen |
CN110329271B (zh) * | 2019-06-18 | 2021-01-26 | 北京航空航天大学杭州创新研究院 | 一种基于机器学习的多传感器车辆行驶检测系统及方法 |
KR20210030528A (ko) * | 2019-09-09 | 2021-03-18 | 현대자동차주식회사 | 자율 주행 제어 장치 및 그 방법 |
DE102019219534A1 (de) | 2019-12-13 | 2021-06-17 | Robert Bosch Gmbh | Verfahren zum Bestimmen von Regelparametern für ein Regelsystem |
-
2021
- 2021-03-26 DE DE102021203057.2A patent/DE102021203057A1/de active Pending
-
2022
- 2022-03-18 WO PCT/EP2022/057188 patent/WO2022200217A1/fr active Application Filing
- 2022-03-18 US US18/550,962 patent/US20240140481A1/en active Pending
- 2022-03-18 CN CN202280024906.XA patent/CN117120314A/zh active Pending
- 2022-03-18 EP EP22714449.0A patent/EP4313711A1/fr active Pending
Also Published As
Publication number | Publication date |
---|---|
US20240140481A1 (en) | 2024-05-02 |
CN117120314A (zh) | 2023-11-24 |
DE102021203057A1 (de) | 2022-09-29 |
WO2022200217A1 (fr) | 2022-09-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3436325B1 (fr) | Procédé de génération de données de commande pour aider un conducteur sur la base de règles | |
DE102017208159B4 (de) | Verfahren zum Betreiben einer Fahrerassistenzvorrichtung eines Kraftfahrzeugs, Fahrerassistenzvorrichtung und Kraftfahrzeug | |
EP3707470B1 (fr) | Procédé et système d'aide à la conduite pour améliorer le confort de conduite d'un moyen de locomotion et moyen de locomotion | |
DE102016121691A1 (de) | Verfahren und System zum Betreiben eines Kraftfahrzeugs | |
DE102016214574B4 (de) | Verfahren und Vorrichtung zum Schätzen von Reibwerten eines Rades eines Fahrzeugs gegenüber einem Untergrund | |
EP2632784A1 (fr) | Procédé et dispositif pour déterminer un paramétrage de régulation transversale pour une régulation transversale d'un véhicule | |
DE102019118366A1 (de) | Verfahren sowie Steuergerät für ein System zum Steuern eines Kraftfahrzeugs | |
DE102019107414A1 (de) | Verfahren sowie Steuergerät für ein System zum Steuern eines Kraftfahrzeugs | |
DE102018212033A1 (de) | Verfahren und Steuergerät zum Bestimmen einer Fahrttrajektorie für ein querdynamisches Fahrmanöver für ein Fahrzeug | |
DE102018213971A1 (de) | Verfahren und Vorrichtung zur Auswahl eines Fahrmanövers | |
DE102021105159A1 (de) | Erfassung von fahrzeugen und reaktion darauf | |
DE102019217346B4 (de) | Verfahren zur Darstellung von Informationen auf einer Mensch-Maschine-Schnittstelle eines Kraftfahrzeugs, Computerprogrammprodukt, Mensch-Maschine-Schnittstelle sowie Kraftfahrzeug | |
DE102018128563A1 (de) | Verfahren und vorrichtung für eine autonome systemleistung und einen vergleich | |
EP4313711A1 (fr) | Analyse de conducteur basée sur un segment et assistance au conducteur individualisée | |
WO2020108839A1 (fr) | Calcul d'une vitesse prescrite de véhicule en fonction d'une situation | |
DE102018007298A1 (de) | Verfahren zur Routenplanung | |
WO2019120709A1 (fr) | Procédé et unité de commande servant à commander une fonction d'un véhicule se déplaçant au moins en partie de manière automatisée | |
DE102021000792A1 (de) | Verfahren zum Betrieb eines Fahrzeuges | |
DE102020201931A1 (de) | Verfahren zum Trainieren wenigstens eines Algorithmus für ein Steuergerät eines Kraftfahrzeugs, Verfahren zur Optimierung eines Verkehrsflusses in einer Region, Computerprogrammprodukt sowie Kraftfahrzeug | |
DE102017200477A1 (de) | Verfahren, Vorrichtung, mobiles Anwendergerät und ein korrespondierendes Computerprogramm zum Bereitstellen einer Information zur Beeinflussung der Führung des Fahrzeugs im Zusammenhang mit lokalen Geländeartefakten | |
DE102019216235A1 (de) | Verfahren zum Vorhersagen der Bewegung eines Fahrzeugs und zumindest eines weiteren Fahrzeugs | |
DE102017204952A1 (de) | Verfahren zum Betreiben eines Autonomfahrsystems und einer Zentraleinheit, Autonomfahrsystem in einem Kraftfahrzeug sowie Zentraleinheit | |
DE102021207781A1 (de) | Verfahren, Steuereinrichtung und System zum Adaptieren einer assistierten oder automatisierten Fahrfunktion eines Fahrzeugs | |
DE102020212966A1 (de) | Verfahren, Computerprogramm und Vorrichtung zum Anpassen einer Route | |
EP3398828B1 (fr) | Système d'aide à la conduite et procédé permettant d'assister un conducteur d'un véhicule ferroviaire |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20231026 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |