AT524688A4 - METHOD OF PREDICTIVE ESTIMATING A HISTORY - Google Patents

Abstract

The invention relates to a method for predictively estimating a course of at least one first parameter (P1) of an ego motor vehicle on a journey along a defined route (FS) on the basis of data from historical reference courses (V-4*, V-3* , V-2*, V-1*, V0*, V-4**, V-3**, V-2**, V-1**, V0**, V-4***, V -3***, V-2***, V-1***, V0***). The following steps are carried out: • Selecting a first parameter (P1) from the parameter groups “Driving” (DR), “Energy” (EN) and/or “Emissions” (EM); • Creating or providing a database with a current time sequence (S) of profiles (V-4, V-3, V-2, V-1, V0) of the parameter (P1) over the path (d) for at least one section (FS1, FS2) of the route (FS) and a database with a historical time sequence (S*, S**, S***) of historical reference curves (V-4*, V-3*, V-2*, V-1*, V0*, V-4**, V-3**, V-2**, V-1**, V0**, V-4***, V-3***, V-2***, V-1***, V0***) of the selected first parameter (P1) over the route (d) for at least the section (FS1, FS2) of the route (FS); • Comparing the current time sequence (S) of the curves (V-4, V-3, V-2, V-1, V0) with at least one historical time sequence (S*, S**, S***) of historical reference courses (V-4*, V-3*, V-2*, V-1*, V0*; V- 4**, V-3**, V-2**, V-1**, V0**; V-4***, V-3***, V-2***, V-1***, V0***); • Selecting at least one historical time sequence (S*, S***) from historical reference curves (V-4*, V-3*, V-2*, V-1*, V0*; V-4***, V- 3***, V-2***, V-1***, V0***), which has a defined similarity to the temporal sequence (S) of current courses (V-4, V -3, V-2, V-1, V0) on at least one section of the route (FS); • Predicting at least one future course (V+1, V+2) of the first parameter (P1) for at least one future point in time (t0+1, t0+2) on the basis of the historical time sequence (S*, S*** ) of similar historical reference curves (V-4*, V-3*, V-2*, V-1*, V0*; V-4***, V- 3***, V-2***, V-1***, V0***).

Description

The invention relates to a method for predictively estimating a profile, in particular a time and/or route profile, of at least one first parameter of an ego motor vehicle traveling along a defined route, on the basis of data from historical reference profiles. further

the invention relates to a device for carrying out the method.

Under ego motor vehicle is here a - to understand motor vehicle, for example, own, of which at least a first parameter on the journey along the

route is to be predicted.

Predictive Energy Control is one possible component of an advanced energy management system for motor vehicles, particularly hybrid vehicles. The anticipatory energy management uses above all the exact knowledge of a planned driving route and information stored about these routes, above all altitude profiles and speed limits, in order to optimally calculate the speed profile, the acceleration and braking requirements for energy use, energy mix and

use energy recovery.

Predictive energy management functions using driver assistance systems such as radar and satellite navigation with electronic horizon and data connections such as V2V (Vehicle to Vehicle Communication), V2I (Vehicle to Infrastructure), V2X (Vehicle to Everything) and/or cloud computing are increasingly being used in production vehicles to estimate or reduce fuel or energy consumption. In particular, an important input for many of these functions is the predicted future speed profile of the controlled motor vehicle along the route driven. There are different approaches to predict such future speeds. These existing approaches typically rely heavily on historical average speeds, e.g. average speeds of multiple automobiles, collected across segments along the route

became.

Typically, the prediction accuracy of prior art approaches based on historical records is particularly low

longer-term predictions are significantly reduced because the current situation is not or

is too little depicted.

The object of the invention is to determine the accuracy of the prediction of the course

to improve at least one parameter on a route.

According to the invention, the object is achieved in that the following steps

be performed:

a. Selecting the at least one first parameter from the

“Driving”, “Energy” and/or “Emissions” parameter groups;

b. Creating or providing a database with at least one current curve or a current time sequence of curves of the parameter over the route for at least one section of the route and providing a database with at least one historical reference curve or at least one historical time sequence of historical reference curves of the selected first parameter above

the route for at least a portion of the route;

c. Comparing the current course or the current time sequence of the courses with at least one historical reference course or at least

a historical time sequence of historical reference curves;

i.e. selecting at least one historical reference curve or a historical time sequence of historical reference curves which has a defined—preferably the greatest—similarity to the current curve or to the current time sequence of curves on at least the section of the route;

e. Prediction of the course of the first parameter for at least one future point in time on the basis of step d. found at least one similar historical reference history or at least one historical time sequence of similar historical

reference histories.

The current profile is to be understood as meaning at least a profile of the first parameter on at least one section of the route, which is created for the current point in time. A current chronological sequence of profiles of the first parameter is to be understood as a sequence of profiles of the first parameter recorded consecutively at defined time intervals on at least one section of the route, which includes the current profile and at least one immediately before the current profile

lying history of the first parameter includes.

A historical reference history is a history of the first parameter at a point in time in the past that is prior to the current history and/or sequence of history. A historical sequence of historical curves is a sequence of historical curves of the first parameter recorded consecutively at defined time intervals on at least one section of the route, which occurred before the

current sequence.

The prediction based on the first parameter for at least one future point in time based on the in step d. found at least one similar historical reference history or at least one historical temporal

sequence of similar historical reference histories

e adopting the at least one (possibly averaged or weighted) similar historical reference course for at least one future point in time, and/or

e using the similar historical reference curve or the historical temporal sequence of similar historical reference curves as a basis for a further (based on other or additional criteria) adjusted (calculated) prediction, and/or

e the continuation of historical tendencies from the similar historical reference curves or the at least one historical time sequence of similar historical reference curves into the future, for example using mathematical regression methods.

It is preferably provided that after step d. in a step d2. at least one consecutive historical reference course found and

is selected, which is temporally based on the selected similar historical

Reference course or the selected similar sequence of historical reference courses follows, and that the prediction of the future course of the first parameter for the at least one future point in time on the basis of

at least one consecutive historical reference course takes place.

The invention is based on the consideration that the changes over time in similar historical reference curves are triggered by causes that also occur in current curves. Consecutive historical reference courses can thus be projected onto the current situation from similar historical reference courses, and at least one future course can be predicted on the basis of at least one consecutive historical reference course

will.

The at least one first parameter is in step a. selected from the parameter groups "Driving", "Energy" and/or "Emissions". At least one first parameter from the group vehicle speed, driving time, vehicle speed changes is preferably assigned to the “driving” parameter group. Alternatively or additionally, the "Energy" parameter group can include at least one first parameter from the group of energy consumption, energy efficiency, state of charge, tank contents, range and/or "Emissions" parameter group, at least one first parameter from the group of exhaust emissions, for example CO, HC, NOx, NHz3z, CO2, particle emissions -, tire wear, brake wear are assigned. At least one first parameter is thus selected from the group of vehicle speed, driving time, changes in vehicle speed, energy consumption, energy efficiency, state of charge, tank content, range, exhaust emissions, tire wear and brake wear.

The downloaded or created database with the current - preferably average - course and historical - preferably average reference courses of the selected first parameter is based on measurements and courses of this measurement data from motor vehicles, the current journeys and reference journeys in the past on the route or a section of the route covered to have. This can be reference runs of your own ego motor vehicle or of the same type motor vehicles or of

act in different types of motor vehicles.

In step b. At least one current profile or a time sequence of current profiles of the first parameter for the ego motor vehicle is created or downloaded on the basis of current data from motor vehicles traveling on the route or the section of the route. Furthermore, at least one historical reference curve of the first parameter or at least one sequence of historical reference curves is provided on the basis of historical data from motor vehicles driven on the route or the section of the route. This provision of historical data can be done online via a cloud via the Internet or offline via data storage in the vehicle

take place.

Thereafter, in step c. the one in step b. recorded at least one current course of the first parameter with the at least one historical

compared to the reference curve of the first parameter.

In step d. a reference curve or several historical reference curves, which has/have similarity to the current curve, are selected.

In step e. the future course of the first parameter is calculated for at least one future point in time on the basis in step d. found similar historical reference history or the chronological sequence of similar

historical reference curves predicted.

In one embodiment variant of the invention, it is provided that for the comparison in step c. Reference runs of the ego motor vehicle and/or motor vehicles of the same type as the ego motor vehicle are preferably selected.

Thus, previously recorded reference profiles of the ego motor vehicle are searched for on the first route and used for the comparison if a sufficiently large number of such reference profiles of the ego motor vehicle are available. Such reference courses should be available in particular when the ego motor vehicle is driving on a route that

represents a regular commuting route of one's own ego motor vehicle.

If such cannot be found or from the step b. for example from

current history of the selected downloaded or created from a cloud

first parameter for the route with the ego vehicle deviates too much, for the comparison also historical reference curves of other motor vehicles on the route or the section under consideration

route used.

In one embodiment variant of the invention, it is provided that the historical reference curves when creating in step b. at least one second parameter from a “status information” parameter group is assigned, the at least one second parameter from the “status information” parameter group being compared and selected in steps c. and/or d. is taken into account, with preferably the parameter group "status information" at least one parameter from the group time of day, day of the week, month, season, temperature, weather, road conditions, road conditions, driver type, vehicle type, traffic density, traffic jams, stops, stopping times, construction sites, traffic accidents

is assigned.

Preferably, for each historical reference profile, at least one current status parameter of the current trip of the ego motor vehicle on the route or the section of the route is compared with the corresponding second parameter of the "Status information" parameter group of the reference profile, whereby on the basis of the at least one second parameter from the parameter group

"Status information" the reference courses are classified according to relevance.

The method according to the invention can be significantly shortened if only reference curves with the highest relevance for steps c. and/or d.

be used.

For the selection in step d. a historical reference curve with the highest degree of similarity or a combination of several historical reference curves with the highest degree of similarity is used to predict the future curve of the first parameter for the ego motor vehicle.

The degree of similarity between the historical reference curves from the database and the measured current curves of the ego motor vehicle can be calculated using various mathematical approaches or methods in a similarity analysis. A simple example is the calculation of the degree of similarity using a FIT value or using Pearson correlation.

7730

Projecting or extrapolating the change over time in the current profile of the first parameter from the change over time in at least one historical reference profile can significantly improve the predictions of at least one first parameter in relation to a route or driving time

for a vehicle or powertrain or traffic.

In one embodiment variant of the invention, it is provided that the prediction of the course of the first parameter for at least one future point in time in step e. is formed on the basis of at least two reference curves--preferably having the highest degrees of similarity--with the reference curves being weighted in particular on the basis of their similarity to the current curve and/or the similarity of the second parameter of the reference curves and the second parameter of the current curve. This allows the

Improved prediction accuracy.

In a further embodiment of the invention, it is provided that at least a third parameter from a “route information” parameter group is provided with information about the second route section and is taken into account when predicting the course of the first parameter for the ego motor vehicle on the section or route. At least one third parameter from the group of expected average traffic speeds, magnitude of fluctuations in traffic speeds, typical acceleration or deceleration of traffic, average travel time, speed limits, road topology, traffic signs, traffic lights, distances between vehicles, weather, visibility is assigned to the "Route information" parameter group , Geofencing restrictions, road conditions, road conditions, traffic density, congestion, bus stops, holding times, construction sites, traffic accidents, roadblocks, driving bans, traffic restrictions. Geofencing is the automated triggering of an action by exceeding a geolocated boundary

designated.

Advantageously, the at least one third parameter from the parameter group “route information” is set using wireless communication, preferably via

Driver assistance systems, V2V, V2I, V2X and / or cloud computing provided.

It is provided within the scope of the invention that when the course of the first parameter is predicted for a future point in time in step e. a travel time between the current location of the ego motor vehicle and the predicted location is taken into account. The course can thus be predicted for a point in time in the future when the vehicle is at the defined predicted location.

The method can be carried out for at least two sections of the route. It is particularly favorable if the method for a section window moving dynamically along the route with the ego motor vehicle is ongoing

is carried out.

The method according to the invention can be applied to various powertrain topologies and technologies (internal combustion engine-based, hybridized, fully electrified, fuel cell-based) and vehicle types (passenger vehicles, commercial vehicles, road vehicles, off-road vehicles, rail vehicles).

The method according to the invention achieves good predictions for the first parameter, particularly in the case of a limited database, and is particularly suitable for sections of the route where the traffic changes significantly over time.

The current course of parameters is taken into account directly in the forecasts, so that the forecasts can be adapted quickly and automatically to specific changes in the traffic situation, for example.

Optionally, the approach can also be applied in cases where only limited or no off-board route or traffic data is available, especially on routes that are regularly traveled by the vehicle and for which data can therefore be collected purely on board the vehicle .

In principle, the approach can also be applied to any length of route, with the entire route conveniently being divided into discrete sections

is divided.

The method can be applied to any route length, and it is easily possible to include different route sections in the forecasts

assign different priorities or weights.

The invention is explained in more detail below with reference to the non-limiting figures. In it show schematic

1 shows a block diagram with the method according to the invention and

2 shows the principle of the method according to the invention,

3 shows a first exemplary embodiment of the method according to the invention,

4 shows a second exemplary embodiment of the method according to the invention,

5 shows a third exemplary embodiment of the method according to the invention and

6 shows a fourth exemplary embodiment of the method according to the invention.

1 shows the method according to the invention for anticipatory estimation of a time and/or path profile of a first parameter P1 when an ego motor vehicle is traveling on a defined route FS or a section FS1, FS2 of the route FS using a block diagram. The anticipatory estimation of the first parameter P1 over the route FS or a section FS1, FS2 of the route FS takes place on the basis of historical reference curves V-4*, V-3*, V-2*, V-1*, VO*; V-4**, V-3*%**, V-2%*, V-1**, VO**: Y-4* 44, \Y-34k, Y-244*, Y-1* **, VO*** of the first parameter P1, which were obtained during reference runs of at least one motor vehicle on the defined route FS or at least a section FS1, FS2 of the route FS and stored in a database. In detail

carried out the following steps:

e Selecting at least one first parameter P1 from the parameter groups

"Driving" DR, "Energy" EN and/or "Emissions" EM;

e Create or provide a database with at least one up-to-date

Course VO or a current time sequence S of courses V-4, V-3,

V-2, V-1, VO of the first parameter P1 of the ego motor vehicle over the path d for the route FS or at least a section FS1, FS2 of the route FS and providing a database with at least one historical reference profile V0* or at least one historical temporal sequence S*, S**, S*** of historical reference curves V-4*, V-3*, V2%, V-1*, VO*, V-dK, \- BE, \Y-Z0K, Ve LOK, YORE Ad KK, \/- 3ER, \/- 2, V-1***, VO*** of the selected first parameter P1 over the path d for the route FS or at least the section FS1, FS2 of the route FS - the at least one current course VO or the at least one current time sequence S and the at least one historical reference course or the at least one historical time sequence S*, S**, S*** can be in separate databases or in one be stored in a single database;

Comparing the current curve VO or the current time sequence S of the current curves V-4, V-3, V-2, V-1, VO with at least one historical reference curve VO*, VO0**, VO*** or at least one historical temporal sequence S*, S**, S*** of historical reference curves V-4*, V-3*, V-2*, V-1*, VO*, V-4**, /-3* *, V-2**, VDK, OO YORK. \/- 3, \/- KK. \/- LOK, YO X

Selecting at least one historical reference curve VO0* or a time sequence S$S* of historical reference curves V-4*, V-3*, V-2*, V-1*, VO*, which (r) a defined - preferably the greatest - similarity with the current profile VO or with the current time sequence S of current profiles V-4, V-3, V-2, V-1, VO on the defined route FS or at least the section FS1, FS2 of the route FS having;

Locating and selecting at least one consecutive historical reference curve V+1*, V+2*, which temporally corresponds to the selected similar historical reference curve VO* or to the selected similar historical sequence S* of historical reference curves V-4*, V-3*, V-2*, V-1*, VO* follows, and that the prediction of the future course V+1, V+2 of the first parameter P1 for the at least one future point in time to+1, to+2 on the basis of the at least a consecutive historical reference profile V+1*, V+2* takes place.

e prediction of at least one future profile V+1, V+2 of the first parameter P1 for at least one future point in time to+ı, to+2 based on the found similar historical reference profile VO* or the historical time sequence S* of similar historical reference profiles V-4*, V-3*, V-2*, V-1*, VO*,

The current curve VO is a curve of the first parameter P1 over the path d on at least one section FS1, FS2 of the route FS, which is created or provided for the current time to. A current time sequence S of curves V-4, V-3, V-2, V-1, VO of the first parameter P1 is a sequence of defined times to-4, to-3, to-2, to-1 , to to understand chronologically successively recorded curves V-4, V-3, V-2, V-1, VO of the first parameter P1 on at least the section FS1, FS2 of the route FS, which the current curve VO and at least one temporal the course V-1, V-2, V-3, V-4 des immediately before the current course VO

includes the first parameter P1.

A historical reference history V-4*, V-3*, V-2*, V-1*, VO*; V-4**, V-3**, \/-2**, V-1**, YORK: -4 4, \/-344*, \/-244*, V-1***, VO*** is a profile of the first parameter P1 at a point in time R in the past that occurred before the current profile VO and/or the current sequence S of profiles V-4, V-3, V-2, V-1, VO lies. A historical sequence S*, S**, S*** of historical curves V-4*, V3, V- 2, VL, VO Ed, BE, Ve 20, Ve TR, VOL ed, m 30, \/- 2 E, V-1***, VO*** is a sequence of defined time intervals to-4*, to-3*, to-2*, to1%, to*; toak*, to3%%, to2%, tot, tok ik: eo ak K, og KK, to 2 0K, Fo KK, eo ke consecutively recorded historical courses V-4*, V-3*, V2%, V-1*, VO*; V-dK, 3, 20, Ve LOK, YORE de, \/- 3, \/- 2 V/1***, VO*** of the first parameter P1 on at least the section FS1, FS2 of the

To understand route FS, which is before the current sequence S.

The parameter group “driving” DR has at least one first parameter P1 from the group vehicle speed, driving time and vehicle speed changes. The parameter group "Energy" EN has at least one first parameter P1 from the group of energy consumption, energy efficiency, state of charge, tank content and range. the

“Emissions” parameter group EM has at least one first parameter P1

the group of exhaust emissions, tire wear and brake wear. The first parameter P1 is thus selected from the group of vehicle speed, driving time, changes in vehicle speed, energy consumption, energy efficiency, state of charge, tank content, range, exhaust emissions, tire abrasion and brake abrasion.

For the comparison of the current curve VO or the time sequence S of the current curves V-4, V-3, V-2, V-1, VO with the historical reference curves V4%, V-3*, V-2*, VL , VOR: ed, BE, Ye 20, LK, YO di, \/- 3ER, \/2***, V-1***, VO*** are - if available - for example reference runs of the ego motor vehicle and /or by motor vehicles of the same type as this

Ego motor vehicle preferably selected.

When creating the historical reference curves V-4*, V-3*, V-2*, V-1*, VO*; VAK, 3, ZEV LK, BEFORE VdK. \/- 3. \/- KK, \/- 1% VO*** Wis advantageously added to each reference curve V-4*, V-3*, V-2*, V-1*, VO*; V-4**, VBao, 240, - 1, VOM: VdK, \/- 3, \/- 2% 1%, VO*** each assigned at least one second parameter P2 from a parameter group "Status information". The second parameters P2 from the "Status information" parameter group are compared and selected in steps c. and/or d. taken into account. The second parameter P2 can, for example, from the group time of day, day of the week, holiday, month, season, vacation time, temperature, weather, visibility, geofencing restrictions, road conditions, road conditions, driver type, driving style, vehicle type, vehicle condition, traffic density, traffic jams, stops, stopping times , construction sites, road accidents chosen

will.

For each historical reference curve V-4*, V-3*, V-2*, V-1*, VO*; V-4*%**, /-3**, V- 20, LK, YORE \/- da, \/- 3, \/- DK V/- 1% VO*** becomes at least a current status parameter VP2 of the ego motor vehicle compared with the corresponding second parameter P2 of the parameter group "status information" of the reference curve. On the basis of the at least one second parameter P2 from the "Status information" parameter group, the reference curves V-4*, V-3*, V-2*, V-1*, VO*: V-dk, - 34, 2, LK, VOM V-4***, \J-344*, \/-2%4*, Y-1***, VO*** classified by relevance, where

in particular only reference curves V-4*, V-3*, V-2*, V-1*, VO*; V-4**, V-3**, V-

ZH, LOK, VOM VL daR, 30, 20%, 1%, VO*** with the highest relevance

be used.

For each historical reference course considered V-4*, V-3*, V-2*, V1%, VO*, VdK, 1-3, 20, LOK, YORE LEO \/- 3. \/- KORK, \/- TE, VO*** or for each considered sequence S*, S**, S*** from historical reference history V-4*, V-3*, V-2*, V-1*, VO*; V-dik, Y- 3, 2, LE, VOM V- dk \/- 3, \/- 244 /-1***, VO***, a similarity analysis is carried out in relation to the current course VO at time to or in relation to the sequence S of current curves V-4, V-3, V-2, V-1, VO of the first parameter P1 of the ego motor vehicle.

The result of the similarity analysis is at least one similar historical reference profile VO0*, VO*** or at least one sequence S*, S*** of historical reference profiles V-4*, V-3*, V-2*, V-1* , VO*; V-4*%***, \Y-3**. \V/2%**, Y-1***, VO***, which satisfy predefined similarity criteria. For the selection of the historical reference profile(s) V-4*, V-3*, V-2*, V-1*, VO*; V-4***, \J-344*, \/-244*, YV-1***, VO*** are reference curves V-4*, V-3*, V2%, V-1*, VO*; V-dk, \/- 3, VD 14, VO*** with the highest degrees of similarity and/or the highest relevance. If no similar reference curve is found, the similarity analysis can also be carried out if necessary

be repeated with relaxed similarity criteria.

The similarity analysis can be carried out, for example, using an FIT value or using Pearson correlation, as explained below for a first parameter P1 formed by the vehicle speed v:

FIT value [Ein Bild D- mt EP FIT =1-— [Ei a, Siu old O — Sdy dr It. ED v(d,t) "measured" speed at the path position d at the time t vp(d ,t — t*) speed of one stored in the database

Reference course V* at the path position d at the time t — t*

=> that means it will be a different time (since the database

D contains only past data) is considered (> shift by —t* with respect to t), but no variation occurs with respect to position d

D([d,,d,>],[t,t>,]) Average of all "measured" values in the spatial range from d, to d, and in the temporal range from t, to t,. ForD items

from d, to d, and T elements from t, to t, thus results

d, tt,

1 5((dpdal, [tb t2D=z77 ) 2,700

d=d, t=t1

The larger this FIT value, the better the match.

The smaller this FIT value, the lower the agreement.

The FIT value thus provides a direct measure of similarity for a spatial and temporal range.

Pearson correlation

The correlation coefficient r(t) according to Pearson provides this measure of similarity for only one dimension (here over distance d) and can then be summed up over different points in time in order to also make a statement about spatial and

to obtain temporal similarity.

For the comparison of signals (here at the "fixed" point in time t), the following results:

here as an interim result:

Yaza (ld, t) v7 (Ld,, d,1, 6)) ) (vp (d, t— t”) Dp([d,, d,1, t— t*))

[Sa t) — D([d,,dz], 0)" ; (ee (vd, t—-t*)-Dp (Id, dl t— 5)

r(t) =

The larger r(t), the higher the agreement in the spatial range from d1 to d2 at time t. The smaller r(t), the less agreement there is.

This can now be carried out and summed up for further points in time.

The larger P, the better the match.

The smaller P, the less agreement there is.

Furthermore, at least a third parameter P3 from a parameter group "route information" with information about the second route section can be provided and when predicting the course V+1, V+2 of the first parameter P1 for the ego motor vehicle at the time to+1, to+ 2 of the route FS or the examined section FS1 of the route FS. The third parameter P3 from the "Route information" parameter group contains information about expected average traffic speeds, fluctuations in traffic speeds, typical acceleration or deceleration of traffic, average driving time, speed limits, road topology, traffic signs, traffic lights, distances between vehicles, weather, visibility, geofencing Restrictions, road conditions, road conditions, traffic density, traffic jams, stops, stopping times, construction sites, traffic accidents, roadblocks, driving bans, traffic restrictions, etc. in the second section of the route. This information is transmitted, for example, using wireless communication, in particular via driver assistance systems, V2V, V2I, V2X and/or cloud computing

or the like provided.

2 and 3 show the method according to the invention using a simple

first embodiment.

In the three-dimensional diagram shown in Fig. 2a) for the first parameter P1 for the route FS for different points in time to-4, to-3, to-2, to-1, to along the time axis t is a current time sequence S of curves V-4, V3, V-2, V-1, VO together with the current curve VO for the current point in time to in the

Present A, as well as looking ahead with the method according to the invention

Determined curves V+1, V+2 for points in time to+1, to+z In the future Z above the

applied way d.

By comparing chronologically adjacent successive curves V-4, V-3, V-2, V-1, VO of the current sequence S, the change over time in the curves V-4, V-3, V-2, V-1, VO of the first parameter P1 can be seen along the time axis t. These changes are due, for example, to dynamic developments in traffic, changes on the route, changes in the weather, changes in visibility or the like

attributed.

2b) shows a two-dimensional time t-path d diagram with the current time sequence S of profiles V-4, V-3, V-2, V-1, VO at the times to-4, to-3, to -4, to-ı, to, Without forecast courses V+1, V+2. 2c) shows an analog two-dimensional time t - path d diagram with the current time sequence S of profiles V-4, V-3, V-2, V-1, VO at the times to-4, to-3, to-2, to-ı, to, together with the courses V+1, V+2, predicted at the times to+1, to+2 in the future Z.

The determination of the future curves V+1, V+2 for the times to+1, to+2 is shown clearly in FIG.

The current profile VO of the first parameter P1 is, for example, an average of a number of profiles of vehicles currently on at least one section FS1, FS2 of the route FS and/or vehicles that have completed at least one section FS1, FS2 of the route FS immediately beforehand. The data for this can be found, for example, by so-called mobile crowdsourcing. Crowdsourcing generally refers to the outsourcing of traditionally internal tasks to a group of voluntary users, e.g. via the Internet. Mobile crowdsourcing includes crowdsourcing activities using smartphones or other mobile devices in connection with

satellite-supported positioning (e.g. GPS).

In order to estimate curves V+1, V+2 of the first parameter P1 lying in the future Z, historical curves V-4*, V-3*, V-2*, V-1*, VO*; V-4**, V3A, -244, V-14, VOR VdK, \/- 3, Y- 24, Y-1***, VO*** by a

Database provided and a prognosis procedure PR using the

subjected to the method according to the invention. For this purpose, the current temporal sequence S consists of a current course VO at a current point in time to and stored courses V-1, V-2, V-3, V-4, the points in time to-:1, to- that took place immediately before 2, to-3, to-4 are compared with at least one historical time sequence S*, which contains stored historical reference curves VO0*, V-1*, V-2*, V-3*, V-4* and subjected to a similarity analysis. As a result of the similarity analysis, the historical reference curves V-4*, V-3*, V-2*, V-1*, VO* are found, the sequence of which is most similar to the current time sequence S of curves V-4, V- 3, V-2, V-1, VO. Reference histories that are not similar are discarded and

no longer considered for the prognosis.

It is then examined whether at least one consecutive historical reference curve V+1*, V+2* can be found for the found similar historical reference curves V-4*, V-3*, V-2*, V-1*, VO0* . In the example shown in FIG. 3, consecutive historical reference curves V+1*, V+2* can be found at the times to+1*, to«2*. Thus, the future course V+1, V+2 of the first parameter P1 can be predicted for future points in time to+ı, to+2 on the basis of the at least one consecutive historical

Reference course V+1*, V+2* take place.

Fig. 4 shows a second exemplary embodiment of the invention, in which part of the route d, for example a first section FS1 of the route FS, which is to be traveled next, is given a higher weighting G than a second section FS2 of the route that is further away FS. The first section FS1 of the historical reference curves V-4*, V-3*, V-2*, V-1*, VO* is therefore weighted more highly in the similarity analysis than the second section FS2.

5 shows a third exemplary embodiment of the invention, in which a number of time sequences S*, S**, S*** of time-successive historical reference curves V-4*, V-3*, V-2*, V-1* , VO*, V-4**, V-3**, V-2*%, V-1**, VO**: Y-4* 44, \Y-344*, Y-244*, Y -1***, VO*** from the database to the closer selection. The historical reference curves V-4*, V-3*, V-2*, V-1*, VO* of the historical time sequence S* are the times to-4*, to-3*, to-2*, mapped to-1*, to*. The historical reference curves V-4**, V-3**, V-2**, V-

1**, VO0** of the historical temporal sequence S** correspond to the times to-4**, to-

3**, to-2**, to-1**, to** and the historical reference curves V-4***, V- 3, \/-2 4, Y-1***, VO* ** of the historical temporal sequence S*** are assigned to the times to-a***, t9o.3*%*%, to.,**%, to, ***, t9g***. The sequences S*, S**, S*** each have the same time steps between the times to-4*, to-3*, to-2*, to-1*, to*; to-4**, to-3**, to-2%%, to. **, dead; tod, to3 tk, to, to1, to KK on.

Only the historical reference histories V-4*, V-3*, V-2*, V-1*, VO*, V-4**, V-3**, VI 26K, \/-LK, YO RK \ /- daR, \/- 3, VD, 14 VO*** with the best agreement are considered for further selection and prediction, whereby the historical temporal sequence S** is discarded here due to poorer agreement... Therefore, the historical temporal sequence S** is not taken into account in the further prediction of the future course V+1, V+2. In contrast, for each of the historical time sequences S* and S***, consecutive historical reference curves V+1*, V+2*; V+1**, V+2** at times to+1*, to+2*; to+1**, to.2** can be found in the past R. The prediction of the profile V+1, V+2 of the first parameter P1 for the points in time to+1, to+2 in the future Z is based on the consecutive historical reference profiles V+1*, V+2*; V+1***, V+2***, The predicted curve V+1 is calculated from an average of the consecutive historical reference curves V+1*; V+1*** and the predicted course V+2 from an average of the consecutive historical

reference curves V+2*; V+2*** formed.

The prediction of the profile V+1, V+2 of the first parameter P1 is advantageously made for at least one future point in time to+1, to+2 on the basis of at least two reference profiles V-4*, V-3*, V-2*, V-1*, VOR: V-dk, \/-3k kV 1 tk, VO*** formed.

The historical reference curves V-4*, V-3*, V-2*, V-1*, VO*; V-4***, \/-3***, \V/-

2***, V-1***, VO0*** can, for example

e based on their similarity to the current course VO and/or

e based on the similarity of the second parameter P2 of the reference curves V4*, V-3*, V-2*, V-1*, VO*; V-4*, V-3#, V-2%, V-1#, VOR V- do, Ve 3, V-2***, V-1***, VO*** and the second parameter VP2 of the current

course VO

be weighted.

The embodiment variant shown in FIG. 6 differs from FIG. 5 in that, on the basis of the historical time sequences S*, S**, S***, a prediction of the future course V+1, V +2 is made. This is particularly advantageous, for example, when

e no comparable historical reference curves V-4*, V-3*, V-2*, V-1*, VO* for the second driving section FS2; V-dk, Y-34, Y- 2, Ve 14, VOM \/- dd, \/- 3, 2, 14%, VO*** are present, or

e the similarity analysis shows that the predefined similarity criteria are only applicable for the first section FS1, or

e consecutive historical reference curves V+1*, V+2*, V+1**, V/+2** could only be found for the first section FS1.

In addition, the prediction can be deliberately limited to the first section FS1.

In these cases, predictions for future curves V+1, V+2 can be made for the individual sections FS1, FS2, which are based on separate forecasts of different historical reference curves V-4*, V-3*, V-2*, V- 1*, VO*, VAO, BO, 20, LOK, YORE Ad. /- 3. /- 20, /- LK, YO based. The forecasts for each section FS1, FS2 can thus be based on different historical time sequences S*, S**, S*** and historical reference curves V-4*, V-3*, V-2*, V-1 *, VO*; V-4**, V-3*%**, V-2*%*, VL, OK daR. \/- 3, \/- 2%, \/- 14%, VO*** are met.

Claims (1)

PATENT CLAIMS Method for predictively estimating a course of at least one first parameter (P1) of an ego motor vehicle on a journey along a defined route (FS), on the basis of data from historical reference courses (V-4*, V-3*, V-2 *, V-1*, VO*, V-4**, V-3*%**, V-2*%*, V-1**, VOM dk, \/- 3, \/- 2, 1%, VO***), thereby characterized in that the following steps are carried out: a. Selecting a first parameter (P1) from the parameter groups “Driving” (DR), “Energy” (EN) and/or “Emissions” (EM); b. Creating or providing a database with a current course (VO) or a current temporal sequence (S) of courses (V-4, V-3, V-2, V1, VO) of the first parameter (P1) over the path (d ) for at least one section (FS1, FS2) of the route (FS) and a database with at least one historical reference course (VO*, V0**, VO***) or at least one historical time sequence (S*, S**, S***) of historical reference curves (V-4*, V-3*, V-2*, V-1*, VO*; V-4**, /-3**, V-26K, - LOK , OK: VdK, \/- 3, \/- 2, 1%, YO***) of the selected first parameter (P1) over the route (d) for at least one section (FS1, FS2) of the route (FS ); c. Comparing the current course (VO) or the current time sequence (S) of the courses (V-4, V-3, V-2, V-1, VO) with at least one historical reference course (VO0*, VO0**, VO0 ***) or at least a historical time sequence (S*, S**, S***) of historical reference curves (V-4*, V-3*, V-2*, V-1*, VO*, V-4**, V-3**, V-2**, V1**, VO**- V-4***, V-3***, V-2%**, V-1 ***, VO***); i.e. Selecting at least one historical reference curve (VO0*) or at least one historical time sequence (S*, S***) from historical reference curves (V-4*, V-3*, V-2*, V-1*, VO* : V-dk, Ye 3. \/- DE, V-1***, VO***), which has a defined - preferably the greatest similarity with the current course (VO) or with the temporal sequence ( S) of current profiles (V-4, V-3, V-2, V-1, VO) on at least the section (FS1) of the route (FS); 21730 e. Predicting at least one future course (V+1, V+2) of the first parameter (P1) for at least one future point in time (to+ı, to+2) on the basis of the step d. found at least one similar historical reference curve (V0*) or the at least one historical time sequence (S*, S***) of similar historical reference curves (V-4*, V3*, V-2*%, V-1*, VO: VdK, \/- 3, \/- 2, LK YO), Method according to claim 1, characterized in that after step d. in a step d2, at least one consecutive historical reference profile (V+1*, V+2*) is found and selected, which corresponds in time to the selected similar historical reference profile (VO*) or to the selected similar historical sequence (S*, S* **) from historical reference curves (V-4*, V-3*, V-2*, V-1*, VO*; V-dk, \/- 3, DK Ve 1***, VO*** ) follows, and that the prediction of the future course (V+1, V+2) of the first parameter (P1) for the at least one future point in time (to+ı, to+2) on the basis of the at least one consecutive historical reference course ( V+1*, V+2*; V+1***, /+2***). Method according to Claim 1 or 2, characterized in that the "driving" (DR) parameter group has at least one first parameter (P1) from the group of vehicle speed, driving time, Vehicle speed changes is assigned. Method according to one of Claims 1 to 3, characterized in that the parameter group "Energy" (EN) has at least one first parameter (P1) from the group of energy consumption, energy efficiency, state of charge, Tank capacity, range is assigned. Method according to one of claims 1 to 4, characterized in that the parameter group "Emissions" (EM) at least one first parameter (P1) from the group exhaust emissions, tire wear, brake wear is assigned. Method according to one of Claims 1 to 5, characterized in that for the comparison in step c. Reference runs of the ego motor vehicle and/or motor vehicles of the same type as the ego motor vehicle be selected preferentially. 22 Method according to one of Claims 1 to 6, characterized in that the historical reference curves (V-4*, V-3*, V-2*, V-1*, VO*; V-4**, VB, \- Z0K, Y-LOK, VOOKE VdK, \/- 3, \/- VL, VO***) when creating in step b. in each case at least one second parameter (P2) from a “status information” parameter group is assigned, the at least one second parameter (P2) from the “status information” parameter group being compared and selected in steps c. and/or d. is taken into account. Method according to Claim 7, characterized in that the second parameter (P2) of the "Status information" parameter group from the group time of day, day of the week, holiday, month, season, holiday period, temperature, weather, visibility, geofencing restrictions, road conditions, road conditions, driver type , driving style, vehicle type, vehicle condition, traffic density, traffic jams, stops, stopping times, construction sites, traffic accidents is chosen. Method according to Claim 7 or 8, characterized in that for each historical reference course (V-4*, V-3*, V-2*, V-1*, VO*; V-4**, VBao, 20, - 1K, YORE VL dd. \/- OR. \/- 2, \/- 1, VO KK) at least one current status parameter (VP2) of the ego motor vehicle with the corresponding second parameter (P2) of the parameter group "Status information" of the historical Reference course (V-4*, V-3*, V-2*, V1%, VO*: VdK, 3, \- 20, Ye LK, YORE YA. \/- 3ER, \/- DK \/1* **, VO***) is compared and on the basis of the at least one second parameter (P2) from the "Status information" parameter group, the reference curves (V-4*, V-3*, V-2*, V-1* , VO*;V-4##, Y-34%, Y- 2, 14, VO**: V-4 444, \/-344 \/-244*, YV-1***, VO** *) classified according to relevance, preferably only historical reference courses (V-4*, V-3*, V2%, V-1*, VO*; V-dk, \/- 3, VD, 1x4, VO** *) with highest Relevance to steps c. and/or d. be used. Method according to one of claims 1 to 9, characterized in that in step c. for each historical reference trend considered (V-4*, V-3%, V-2*%, V-1#, OH; V-dk, Ye 3, 20, LK, VOR: di, 34***, YV-2*%*%*, V-1***, VO***) or for each historical temporal sequence (S*, 12. 13. 14 23 S **, S ***) a similarity analysis in relation to the course (VO) of the first parameter (P1) at the current time (to) or the current time sequence (S) is carried out, with preferably the degree of similarity is determined by means of an FIT value or by means of Pearson correlation. Method according to one of Claims 1 to 10, characterized in that for the selection in step d. at least one reference course ( V-4*, V-3*, V-2%, V-1*, VO*; V-dk, \/- 3, VD, 14 VO***) with the highest similarity or at least one historical temporal sequence (S*, S***) with the highest similarity or a combination of several historical reference courses (V-4*, V-3*, V-2*, V-1*, VO*; V-dk, \/- 3, DK Ve 1***, VO0***) or historical temporal sequences (S*, S***) with highest Degrees of similarity and/or highest relevance is used. Method according to one of Claims 1 to 11, characterized in that the prediction of the profile (V+1, V+2) of the first parameter (P1) for at least one future point in time (to+1, to+2) in step e. on the basis of at least two reference curves - preferably having the highest degrees of similarity - (V-4*, V-3*, V-2*, V-1*, VO*; V-4***, V/34%, V-24**, V-1***, VO***) averaged reference course is carried out. Method according to one of Claims 1 to 12, characterized in that the prediction of the profile (V+1, V+2) of the first parameter (P1) for at least one future point in time (to+1, to+2) in step e. on the basis of at least two - preferably having the highest degrees of similarity - reference curves (V-4*, V-3*, V-2*, V-1*, VO*; V-dKk, 3, DK, 1***, VO ***) is formed, whereby in particular the reference curves (V-4*, V-3*, V-2*, V-1*, VOR: V-dK, \/-3K \/-2kk /-1 tk , VO***) based on their similarity to the current curve (VO) and/or the similarity of the second parameter (P2) of the reference curves (V-4*, V-3*, V-2*, V-1* , VO*; V-4*, V-3*, V-2%, V-1*, VOR ed, Ve 3, \/- 20, 1%, VO***) and of the second parameter (P2) of the current curve (VO). Method according to one of Claims 1 to 13, characterized in that at least a third parameter (P3) from a parameter group "Route information" with information about the second route section 24/30 16 17 18 19 24 provided and taken into account when predicting the course (V+1, V+2) of the first parameter (P1) for the ego motor vehicle on the route (FS) or a section (FS1) of the route (FS). Method according to one of claims 1 to 14, characterized in that the parameter group "Route information" at least a third parameter (P3) from the group expected average traffic speeds, size of fluctuations in traffic speeds, typical acceleration or deceleration of traffic, average travel time, speed limits , road topology, traffic signs, traffic lights, distances between vehicles, weather, visibility, geofencing restrictions, road conditions, road conditions, traffic density, congestion, stops, stopping times, construction sites, traffic accidents, road blocks, driving bans, traffic restrictions. Method according to Claim 14 or 15, characterized in that the at least one third parameter (P3) from the "route information" parameter group is provided by means of wireless communication, preferably via driver assistance systems, V2V, V2I, V2X and/or cloud computing becomes, Method according to one of Claims 1 to 16, characterized in that in the case of the prediction of the course of the first parameter (P1) for a future point in time in step e. a travel time between the current location of the ego motor vehicle and the predicted location is taken into account becomes, Method according to one of Claims 1 to 17, characterized in that the method is repeated for at least two sections (FS1, FS2) of the route (FS). Method according to one of Claims 1 to 18, characterized in that the method is carried out continuously for a section window moving dynamically along the route (FS) with the ego motor vehicle becomes, 20. Device for carrying out the method for anticipatory estimation of a course of at least one first parameter (P1) of an ego motor vehicle on a journey along a defined route (FS) according to any one of claims 1 to 19. 05/25/2021 FU