Method for carrying out highly automated driving of a vehicle

Abstract

Method for performing highly automated driving of a vehicle comprising the following steps: A) Reading driving behavior recommendation data into the vehicle for at least one route sequence (1) on which a journey of the vehicle is planned; B) Performing highly automated driving of the vehicle based on the driving behavior recommendation data read in according to step A).

Description

Prior ArtFor systems for highly automated and / or even autonomous driving operation of vehicles, special data are required which enable the planning of the highly automated and / or even autonomous driving operation. Such data are usually also referred to as map data. Unlike map data which are used, for example, for a customary navigation system in a vehicle, which only describe the course of roads, map data for highly automated and possibly even autonomous driving functions contain considerably more detailed information. Such map data may include, for example, an accurate digital description of the environment of a road or lane. In particular embodiments, however, such map data can also contain specific recommendations, for example how a vehicle should travel on a specific road in order to participate in the traffic situation in an advantageous manner.Such map data are usually obtained by a variety of approaches. For example, so-called crowd-based approaches exist in which a plurality of vehicles are used in the field and perform observations and collect raw data that is transmitted to a central data collector. This central data collector creates map data based on the crowd-based collected raw data, which map data are made available via service providers for the highly automated and / or even autonomous driving operation.Specific recommendations for vehicles to behave in a specific manner along specific travel routes may include, for example, recommendations for specific travel speeds, recommendations for specific trajectories that a vehicle is to follow in a lane, and similar information.Disclosure of the InventionProceeding from this, it is an object of the present invention to at least partially solve the problems described with reference to the prior art and in particular to propose a method with which a highly automated or possibly even autonomous driving function can implement a particularly natural driving behavior, possibly even a driving behavior that is particularly similar to a human driver.These objects are achieved by a method according to the features of the independent claim. Further advantageous embodiments are specified in the dependent patent claims and in the description and in particular also in the description of the figures. It should be noted that the person skilled in the art can combine individual features with one another in a technically expedient manner and thus arrive at further embodiments of the invention.A method for carrying out a highly automated driving operation of a vehicle is to be described here, having the following steps: A) reading driving behavior recommendation data into the vehicle for at least one route sequence on which a travel of the vehicle is planned; B) carrying out a highly automated driving operation of the vehicle on the basis of the driving behavior recommendation data read in according to step A).It is particularly advantageous if the driving behavior recommendation data read in in step A) have been previously generated according to the following steps: a) collecting driving behavior data from a plurality of vehicles during a driving operation; b) defining predefined route sequences (1) for which driving behavior data are to be created; and c) creating driving behavior recommendation data for predefined route sequences (1) based on the driving behavior data.Such driving behavior recommendation data can thus be collected, for example, as statistical information on the driving behavior of drivers in crowd-based approaches. Data collected in these ways can be obtained in particular when human drivers are driving specific routes. This occurs in step a). The driving behavior of human drivers can be evaluated and driving recommendation data can then be generated for highly automated / autonomous driving functions based on this driving behavior, which make it possible for the highly automated (possibly autonomous) driving functions to realize a natural, almost human driving behavior. This occurs in step c).The route sequences for which the driving behavior recommendation data are read in in step A) and for which the driving behavior recommendation data are created according to step c) have preferably been previously established on the basis of a topological map of the traffic infrastructure. The route sequences preferably always map route sections on which a driving behavior of a vehicle matched across the route sections is advantageous. Route sequences preferably comprise a plurality of route sections between which so-called route elements are located, which can contain, for example, curves, intersections, branches or circular traffic.Such route sequences can also be referred to as route combinations. Route elements can also be referred to as route transitions.The route sequences or routes for the respective driving behavior recommendation data according to step c) can be established manually and / or automatically.At a branch, drivers travel straight ahead, for example, or they bend. It can be noted and easily understood that drivers who are turning already brake beforehand, while drivers who are driving straight ahead lower their speed significantly less. A first route sequence could in this case be a route section before the branch and a further route section after the branch on the roadway aligned straight ahead. A further second route sequence could in this case be a route section before the branch and a route section after the branch on the branching road. Different driving behavior recommendation data could then be stored for the first route sequence and the second route sequence, which make it possible for the highly automated / autonomous driving function to adapt its driving behavior (in this case the speed of the vehicle) accordingly.It is particularly preferred if, for the execution of step c), a statistical evaluation of driving behavior data of vehicles collected according to step a) takes place, which the predefined route sequences have been completely followed when the respective driving behavior data are acquired.Preferably, such driving behavior data are selected in order to generate the respective driving behavior recommendation data for the respective route sequence.The pre-definition of route sequences according to step b) can likewise be carried out on the basis of statistical evaluations of the driving behavior data collected according to step a).Route sequences can also comprise a plurality of route sections and route elements-for example a sequence of curves which drivers normally pass through in a manner coordinated with one another.The approach described herein to provide driving behavior recommendation data for route sequences offers a number of advantages. The provision of statistical information on the driving behavior for each direction of travel (as becomes clear in the case of the example given above with a first route sequence and a second route sequence around a branch) is valuable information for a vehicle which is driving onto one of the two routes / route sequences or comes from one of the two routes. If the route sections before and after the branch were each viewed separately from each other, driving behavior data of vehicles traveling straight and driving behavior data of vehicles turning when driving behavior recommendation data is created according to step c) would be mixed together. This would not correspond to the natural driving behavior of human drivers.It is particularly preferred if driving behavior data collected in step a) comprise at least one of the following data types:- driving speed information;acceleration information;trajectory information;behavior information regarding a driver of the vehicle;distance information;time information;weather information; orbrightness information.All of these data may be recorded and collected during vehicle drives (particularly human driver drives) for use in generating driving behavior recommendation data.It is furthermore preferred if route sequences are defined such that driving along a route sequence by a vehicle comprises carrying out at least one driving maneuver.It is also preferred if route sequences comprise at least one of the following driving maneuvers:- bending;driving straight ahead despite the possibility of turning;- lane change;threading;- stopping; oraccelerating.It is also preferred if route sequences pass through at least one of the following route elements:- intersection;- branching; - branching;ramp-on;departure;- curve; orTraffic circuits.Track sequences preferably consist of track sections between which the described track elements are arranged. Vehicles which pass over the route elements preferably each have to perform at least one driving maneuver.With the method described here, driving maneuvers or the driving behavior that vehicles are executing on the basis of route elements are observed. This observed behavior is used to generate driving behavior recommendation data. The driving behavior recommendation data are then used for other vehicles and for carrying out highly automated (possibly autonomous) driving functions of these vehicles on the route sequences.Route sections are preferably part of different route sequences in the map data. Depending on how many route elements (branches, etc.) there are in the environment of a route section, the more route sequences the route section can occur. Map data including the driving behavior recommendation data track sequences described herein may include a plurality of partially overlapping track sequences. In the route planning for a vehicle to travel with highly automated, possibly even autonomous, driving functions, the route sequences that best match the respective planned route are determined and taken into account using the respective best driving behavior recommendation data.It is particularly preferred if driving behavior recommendation data include at least one of the following data for controlling the highly automated driving operation on the respective route sequence:trajectory information;- driving speed information;acceleration information; ordistance information.All these types of data can be advantageous for highly automated, possibly autonomous, driving operation of a vehicle. Trajectory information may include, for example, data of where a vehicle is to sort in a lane to follow a particular route sequence, for example. For example, for turning it may be useful that a vehicle rather sorts into the side of the branch. In other situations, it may be useful (to achieve a greater radius of curvature) for a vehicle to initially move to the side of a lane opposite a branch and then only follow the branch. Such information can be contained as trajectory information or as trajectory recommendations in driving behavior recommendation data.Driving speed information as driving behavior recommendation data can help to adapt the driving speed of a vehicle to the respective situation in a meaningful manner. The same applies to acceleration information.Distance information may include information on which distance a vehicle should keep from preceding vehicles. Such information can also be collected as driving behavior data and provided in the form of driving behavior recommendation data.Various other data or information are useful as driving behavior recommendation data.It is particularly advantageous if the processing of driving behavior recommendation data for carrying out the highly automated driving operation in step B) takes place as a function of at least one of the following situation information:time information;- weather information;brightness information;- driving speed information; oracceleration information;Preferably, situation information is acquired in step B). The driving behavior recommendation data are preferably constructed in such a way that different driving behavior recommendations can be determined from the driving behavior recommendation data as a function of the respective situation information.The invention and the technical field of the invention are explained in more detail below with reference to the figures. The figures show a preferred embodiment to which the invention is not limited. It should be noted that the figures and the size relationships illustrated in the figures are only schematic. They show, by way of example and schematically: FIG. 1 : An example of a situation with two different route sequences in the vicinity of a branch; FIG. 2 : shows an example of driving behavior recommendation data for the first route sequence shown in FIG. 1 ; and FIG. 3 : shows an example of driving behavior recommendation data for the second route sequence shown in FIG. 1.FIG. 1 shows a road situation with a straight roadway and a diverging roadway. The straight roadway is formed by the track sections 5 aand 5 c. The branching roadway is formed by the route section 5 band branches off from the roadway directed straight at the branching point forming a route element 3. The direction of travel 6 is marked by an arrow in FIG. 1. For the method described here, a first route sequence 1 aincluding the route sections 5 aand 5 band the branch as route element 3 between them and a second route sequence 1 bincluding the route sections 5 aand 5 band the branch as route element 3 between them are stored in map data. Exemplary depicted are trajectories 4 which travel along vehicles which follow either the first route sequence 1 aor the second route sequence 1 b. Vehicles following the first route sequence 1 aappear a different driving behavior than vehicles following the second route sequence 1 b.The different driving behavior of vehicles which follow the first route sequence 1 aand vehicles which follow the second route sequence 1 bis stored in each case for the route sequence 1 a, 1 bin driving behavior recommendation data which can be generated according to the described method and used for the highly automated (possibly autonomous) driving operation.The different driving behavior of vehicles which follow the first route sequence 1 aand vehicles which follow the second route sequence 1 band the corresponding different driving behavior recommendation data are illustrated by way of example in FIGS. 2 and 3.FIG. 2 relates to the second route sequence 1 bin accordance with FIG. 1 (straight-ahead travel) and FIG. 3 relates to the first route sequence 1 ain accordance with FIG. 1 (turning travel). On the speed axis 7, the speed profile 9 is plotted over the distance axis 8, respectively. The speed profile 9 according to FIG. 2 runs substantially constant. The vehicle travels straight along the route section 5 a, 5 c,so that lowering of the vehicle speed at the branch (the route element 3) is not necessary. The speed profile 9 according to FIG. 3 is reduced by the vehicle on the route section 5 ato pass through the branch (the route element 3) at reduced speed and subsequently accelerate it again on the route section 5 b. The speed profiles 9 according to FIGS. 2 and 3 can be driving behavior recommendation data which are generated according to step c), read in according to step A) and used according to step B) for the highly automated (possibly autonomous) driving function.This driving behavior recommendation data can be generated, for example, using statistical methods from driving behavior data collected in step a). In order to clarify why the distinction between a first route sequence 1 aand a second route sequence 1 bis very advantageous, FIGS. 2 and 3 each show a comparative speed profile 10 for the route section 5 afor comparison. If the evaluation of driving behavior data does not differ between the first route sequence 1 aand the second route sequence 1 b,but driving behavior data of vehicles which follow these two different route sequences are evaluated in a mixed manner, this comparative speed profile 10 results, which does not correctly fit either the meaningful driving behavior along the first route sequence 1 aand the meaningful driving behavior along the second route sequence 1 b. This can be prevented by taking into account route sequences consisting of a plurality of route sections according to the method described here.

Claims

Method for carrying out a highly automated driving operation of a vehicle, having the following steps: A) reading driving behavior recommendation data into the vehicle for at least one route sequence (1) on which a journey of the vehicle is planned; B) carrying out a highly automated driving operation of the vehicle on the basis of the driving behavior recommendation data read in according to step A).Method according to Claim 1, wherein the driving behavior recommendation data read in in step A) have been previously generated according to the following steps: a) collecting driving behavior data from a multiplicity of vehicles during their driving operation; b) defining predefined route sequences (1) for which driving behavior data are to be created; and c) creating driving behavior recommendation data for predefined route sequences (1) on the basis of the driving behavior data.Method according to Claim 2, wherein, for carrying out step c), driving behavior data of vehicles which have collected according to step a) and which have completely followed the predefined route sequences (1) when the respective driving behavior data are acquired are statistically evaluated.Method according to claim 2 or 3, wherein driving behavior data collected in step a) comprises at least one of the following types of data: - driving speed information; - acceleration information; - trajectory information; - behavior information relating to a driver of the vehicle; - distance information; - time information; - weather information; or - brightness information.Method according to one of the preceding claims, wherein route sequences (1) are defined such that driving along a route sequence (1) by a vehicle comprises carrying out at least one driving maneuver (2).Method according to one of the preceding claims, wherein route sequences (1) comprise at least one of the following driving maneuvers (2): - turning; - driving straight ahead despite the possibility of turning; - lane change; - merging; - stopping; or - accelerating.Method according to one of the preceding claims, wherein route sequences (1) run through at least one of the following route elements (3): - intersection; - branching; - entry; - exit; - curve; or - circular traffic.Method according to one of the preceding claims, wherein driving behavior recommendation data comprise at least one of the following data for controlling the highly automated driving operation on the respective route sequence (1): - trajectory information; - driving speed information; - acceleration information; or - distance information.Method according to one of the preceding claims, wherein the processing of driving behavior recommendation data for carrying out the highly automated driving operation in step B) takes place as a function of at least one of the following situation information: - time information; - weather information; - brightness information; - driving speed information; or - acceleration information;

Images