DE102020215780A1 - Method for selecting an automated driving process using a driver assistance system - Google Patents

Abstract

The invention relates to a method for selecting an at least partially automated driving process using an autonomous driver assistance system of a vehicle.

Description

The invention relates to a method for selecting an at least partially automated driving process using a driver assistance system of a vehicle.

Driving assistance systems are known which, based on the current driving scenario, can calculate a driving trajectory on which the vehicle moves automatically, i.e. without steering intervention by the driver and/or without the driver actuating the gas or brake pedal. In particular, driver assistance systems according to autonomy level 2 (SAE level 2) are known, which have the ability to keep in lane, but cannot change lanes without the driver's initiative. If a driver initiates a lane change, this can then be carried out automatically again.

Depending on the respective driving scenario, it is possible to initiate different driving processes. For example, on a multi-lane road when approaching a slower vehicle ahead, it is possible to reduce the speed at different points in time or at different distances from this vehicle. This depends in particular on whether it can be assumed that the driver of the ego vehicle with a driver assistance system according to autonomy level 2 or less will initiate a lane change or not.

In another driving scenario, the possible traffic action of an external actor decides whether it is advantageous to initiate a certain driving process or not. This means that the trigger, which cannot be influenced by the driver assistance system, is not triggered by the driver of the ego vehicle, but by another road user (e.g. other vehicle, pedestrian, cyclist, etc.) or a traffic-regulating unit (traffic light, barrier, etc.).

If it is expected that the driver will initiate a lane change, it is advantageous not to reduce the speed early, since this leads to an unnecessary speed reduction from the point of view of a human driver. In contrast to this, it is advantageous to reduce the speed at an early stage if it is to be expected that the driver will not initiate a lane change, in order to prevent driving too close to the other vehicle ahead and the associated heavy braking. The same applies to driving scenarios in which a traffic action by an external actor decides which driving process is advantageous in terms of safety and/or comfort.

Proceeding from this, it is the object of the invention to specify a method for selecting an at least partially automated driving process by means of a driver assistance system, which enables the vehicle to be controlled as closely as possible to human driving behavior.

The object is solved by a method having the features of independent patent claim 1 . Preferred embodiments are the subject matter of the dependent claims. A driver assistance system is the subject of independent claim 14 and a vehicle with such a driver assistance system is the subject of independent claim 15.

• Zunächst wird das aktuelle Fahrszenario bestimmt, d.h. die Fahrsituation, in der sich das Fahrzeug aktuell befindet. Dies kann beispielsweise sein: „Fahrzeug fährt auf rechter Spur einer zweispurigen Straße, linke Fahrspur frei, 150m voraus langsameres Fremdfahrzeug“. Basierend auf dem aktuellen Fahrszenario werden durch das Fahrassistenzsystem mehrere unterschiedliche, zukünftig mögliche Fahrvorgänge ermittelt. Diese können in dem vorbeschriebenen Fahrszenario beispielsweise sein: Spurwechsel mit gleichbleibender Geschwindigkeit, Spurhalten mit gleichbleibender Geschwindigkeit, Spurhalten mit Verzögern. Es versteht sich, dass diese Fahrvorgänge zu unterschiedlichen Zeitpunkten eingeleitet werden können.

According to a first aspect, the invention relates to a method for selecting an at least partially automated driving process using a driver assistance system of a vehicle. The procedure includes the following steps:

• First, the current driving scenario is determined, ie the driving situation in which the vehicle is currently located. This can be, for example: "Vehicle is driving in the right lane of a two-lane road, left lane free, 150m ahead of a slower other vehicle". Based on the current driving scenario, the driver assistance system determines several different driving processes that are possible in the future. In the driving scenario described above, these can be, for example: changing lanes at a constant speed, staying in lane at a constant speed, staying in lane with deceleration. It goes without saying that these driving processes can be initiated at different points in time.

A decision structure, also referred to below as a decision tree, is then automatically created using a processing unit of the driver assistance system. Several decision levels of the decision tree, also referred to below as nodes, are determined, with the nodes each being linked to specific points in time in the future. Depending on the driving scenario, at least one decision to be made by the driver of the vehicle or by an external actor regarding a lane change or a traffic action is at least partially assigned to the nodes. A third-party actor can be, for example, a third-party vehicle, a pedestrian, a cyclist or another object that can carry out a traffic action, for example a lane change, a change of direction, entering the roadway, etc.

In addition, the nodes are at least partially each at least two from the driver assistance assigned to decisions or options for action to be made by the system. Thus, according to the decision tree, several decisions can be made at the times that are linked to the nodes of the decision tree, either initiated by the driver of the host vehicle (own lane change) or by an external actor (e.g. lane change of another vehicle) or by a decision of the driving assistance system itself (e.g. lane keeping with deceleration, lane keeping without deceleration, heavy braking to avoid collision).

Partial driving processes that are part of a driving process that has a longer duration are defined via the decisions to be made at the respective nodes. In other words, a driving process is made up of several partial driving processes that are assigned to the branches of the decision tree. A path through the decision tree, which extends over several nodes, for example, is composed of several decisions and the associated partial driving processes.

Travel trajectories are then calculated, with each travel trajectory being associated with a defined path through the decision tree and each path comprising one or more decisions to be made one after the other. The respective travel trajectory defines, for example, the movement path of the vehicle in a two-dimensional coordinate system and preferably also defines the speed of the vehicle at which this movement path is traveled. When calculating the driving trajectory, the longitudinal and lateral acceleration or the longitudinal and lateral jerk can also be determined. Thus, in this step, several travel trajectories are calculated that can be traveled through in the current driving scenario, depending on the respective decisions that can be made according to the decision tree.

In addition, evaluation indicators for the travel trajectories are calculated. The evaluation indicator is a measure of the comfort and/or the safety of the respective travel trajectory. The evaluation indicator is preferably a number, so that the individual travel trajectories can be compared with one another in terms of comfort and/or safety by comparing the evaluation indicators.

In addition, probability values associated with the nodes of the decision tree are calculated. The probability values each indicate the probability with which the driver of the vehicle or an external actor makes a decision to change lanes or some other traffic action at the point in time that is assigned to the node. In other words, the probability value indicates how likely it is that the driver of the vehicle or an external factor will make a decision at the point in time assigned to the node, to which the driver assistance system of the host vehicle has to react by providing a driving trajectory.

A number of decision indicators are then calculated, with one decision indicator each being assigned to a node. The calculation of the decision indicator is based at least in part on the probability value of the respective node, which indicates that the driver of the vehicle or the foreign actor will make a decision to change lanes or to take a traffic action at the time associated with the node. Furthermore, the calculation of the decision indicator is based at least on an evaluation indicator of a travel trajectory, which is determined by a decision to be made at the time of the respective node.

Finally, an at least partially automated driving process is initiated by the autonomous driving assistance system based on the decision tree, the decision indicators and depending on whether the driver of the vehicle or the external actor initiates a lane change or a traffic action at the point in time assigned to the node or not, selected. In particular, in the event that a decision by the driver of the ego vehicle or a decision by an external actor does not force the initiation of another driving process beforehand, the decision tree is run through to the node with the lowest decision indicator and a decision is made there automatically by the driver assistance system to keep in lane with a simultaneous slight deceleration (e.g. at least 80% or 90% less deceleration than with emergency braking).

The technical advantage of the method according to the invention is that by taking into account the probability that a lane change or a traffic action will be initiated and taking into account the trajectory properties with regard to comfort and / or safety, a driving process is automatically selected that is as natural as possible enables a driving experience that is oriented towards human driving behavior. In other words, a driving process is selected that corresponds very closely to the driving behavior of a human driver.

According to one embodiment, the values of the decision are used to select an at least partially automated driving process indicators of the nodes of the decision tree are compared. The selected driving process is based on a driving trajectory that initiates a lane change or a deceleration process at the time associated with the node with the smallest decision indicator value. In other words, a comparison of the decision indicators of the nodes is carried out and it is determined which node is assigned the lowest decision indicator value. The lowest decision indicator value is an indication that, considering the probability that the driver will initiate a lane change at the time of the node and the evaluation indicators of the driving trajectories of this node, it is advantageous to either initiate the lane change at this time (which can be done by the driver of the own vehicle or the other vehicle must be initiated) or to stay in lane and decelerate the vehicle (initiated by the driver assistance system alone).

It should be noted that preferably only the initiative for changing lanes has to be taken by the driver. The lane change itself can be carried out automatically by the driver assistance system.

According to one embodiment, the decision indicators of the nodes are calculated at least in part by adding the results of a first multiplication and a second multiplication, respectively. In the first multiplication, the probability value that the driver of the vehicle or the external actor initiates a lane change or a traffic action at the time assigned to the node is multiplied by the evaluation indicator of the driving trajectory, by means of which the lane change is carried out. In the second multiplication, the probability value that the driver of the vehicle or the external actor does not initiate a lane change or traffic action at the time assigned to the node is compared with the evaluation indicator of the driving trajectory, by means of which the lane is kept and the vehicle is decelerated, multiplied. In order to calculate the decision indicators that are assigned to the nodes and thus to the respective decision times, both the evaluation indicators of the travel trajectories that are selected at this point in time and the probabilities that these travel trajectories are due to the behavior of the driver of the own vehicle or the external actor are selected, taken into account.

According to one exemplary embodiment, a decision to be made by the driver of the vehicle by setting the turn signal and/or a steering intervention that causes a lane change is detected. The driver assistance system can thus recognize when the driver wants to change lanes.

According to one exemplary embodiment, a decision to be made by the external actor is detected by detecting a turn signal and/or a lane change by an external vehicle, by an external vehicle turning, by an external vehicle starting and cutting into its own lane, or by a person entering the lane. This can be detected, for example, using a sensor system suitable for this purpose, which has a camera, a radar sensor and/or a LIDAR sensor, for example. The driver assistance system can thus recognize whether the other vehicle is changing lanes or the other person is carrying out a traffic action that may necessitate a driving process to be carried out by the driver assistance system.

According to one exemplary embodiment, the calculation of a travel trajectory includes the calculation of multidimensional coordinates along which the vehicle moves when driving through the travel trajectory, the calculation of longitudinal and lateral acceleration values and/or the calculation of longitudinal and lateral jerk values. It can thus be determined whether the trajectory is collision-free and what forces act on the occupants of the vehicle when the vehicle is moved on the travel trajectory. These are essential parameters for the comfort and safety impression of the driving trajectory.

According to one exemplary embodiment, the evaluation indicator of a travel trajectory is calculated taking into account the distance of the vehicle from other vehicles and/or objects, the difference from a set speed and/or the frequency of lane changes. These are also essential parameters for the comfort and safety impression of the driving trajectory.

According to an exemplary embodiment, a travel trajectory corresponds to a path through the decision tree, the travel trajectory being based on decisions which are associated with the path of the decision tree. The travel trajectory can be made up of a number of partial trajectories, for example initially keeping to the lane at a constant speed and only later changing lanes.

According to one exemplary embodiment, the probability value that the driver will initiate a lane change at a future time associated with a node is calculated based on a neural network that uses data which were obtained from past driving processes of the driver is trained. This allows the probability of a lane change to be estimated or calculated from statistical relationships obtained in the past.

According to an exemplary embodiment, the probability value that the driver initiates a lane change at a future point in time assigned to a node is calculated based on the evaluation indicators of the driving trajectories, which are initiated by means of decisions at the points in time of the respective nodes. A human driver often initiates a lane change when a driving trajectory is available that enables a lane change that is sufficiently good in terms of comfort and/or safety. The evaluation indicators of the travel trajectories can thus be used to determine or estimate the probability of a lane change initiated by the driver.

According to one exemplary embodiment, the probability value that the driver will initiate a lane change at a future point in time assigned to a node is calculated on the basis of driver behavior detected by at least one sensor. For example, the sensor can detect whether the driver has already looked in the side mirror, looked over his shoulder, only looked ahead at his own lane for a long time, etc. This allows a sensor-based calculation or estimation of a lane change probability.

According to one exemplary embodiment, a plurality of decision indicators are calculated for at least some of the nodes, which are based on different probability values that the driver of the vehicle or an external actor will make a decision to change lanes or take a traffic action at the point in time assigned to the node, and that the largest decision indicator for selecting an at least partially automated driving process is used for each node. The probability values relating to a lane change or a traffic action are subject to an imprecision that becomes greater the further in the future the point in time to which the probability value relates. By calculating the decision indicators based on different probability values, a driving process can be selected that enables a driving process that is optimized in terms of comfort and/or safety, even if the probability values are inaccurate.

According to one embodiment, the decision to be made by the driver of the vehicle includes a lane change from a right lane to a left lane or a lane change from a middle lane to a left or right lane.

1. a) Bestimmen des aktuellen Fahrszenarios und mehrerer unterschiedlicher möglicher, zukünftiger Fahrvorgänge basierend auf dem aktuellen Fahrszenario durch das Fahrassistenzsystem;
2. b) Automatisiertes Erstellen eines Entscheidungsbaums mittels einer Recheneinheit des Fahrassistenzsystems durch Bestimmen mehrerer Knoten des Entscheidungsbaums, wobei die Knoten mit Zeitpunkten in der Zukunft verknüpft sind, wobei den Knoten in Abhängigkeit von dem Fahrszenario zumindest teilweise jeweils zumindest eine vom Fahrer des Fahrzeugs oder von einem Fremdakteur zu treffende Entscheidung bezüglich eines Spurwechsels oder einer Verkehrsaktion zugeordnet wird und wobei den Knoten zumindest teilweise jeweils mindestens zwei vom Fahrassistenzsystem selbst zu treffende Entscheidungen bzw. Handlungsoptionen zugeordnet werden;
3. c) Berechnen von Fahrtrajektorien mittels eines automatisierten Trajektorienplaners, wobei jede Fahrtrajektorie einem definierten Pfad durch den Entscheidungsbaum zugeordnet ist und jeder Pfad eine oder mehrere nacheinander zu treffende Entscheidungen umfasst;
4. d) Automatisiertes Berechnen eines Bewertungsindikators für die Fahrtrajektorien, wobei der Bewertungsindikator ein Maß für den Komfort und/oder die Sicherheit der jeweiligen Fahrtrajektorie ist;
5. e) Berechnen von Wahrscheinlichkeitswerten, wobei die Wahrscheinlichkeitswerte Knoten des Entscheidungsbaums zugeordnet sind und die Wahrscheinlichkeitswerte jeweils angeben, mit welcher Wahrscheinlichkeit der Fahrer des Fahrzeugs oder ein Fremdakteur an dem Zeitpunkt, der dem Knoten zugeordnet ist, eine Entscheidung zu einem Spurwechsel oder einer Verkehrsaktion trifft;
6. f) Berechnen mehrerer Entscheidungsindikatoren, wobei jeweils ein Entscheidungsindikator einem Knoten zugeordnet ist, wobei die Berechnung des Entscheidungsindikators zumindest teilweise basiert auf
   • - dem Wahrscheinlichkeitswert des jeweiligen Knotens, der angibt, dass der Fahrer des Fahrzeugs oder ein Fremdakteur an dem Zeitpunkt, der dem Knoten zugeordnet ist, eine Entscheidung zu einem Spurwechsel oder einer Verkehrsaktion trifft; und
   • - zumindest einem Bewertungsindikator einer Fahrtrajektorie, die durch eine zum Zeitpunkt des jeweiligen Knotens zu treffende Entscheidung festgelegt wird;
7. g) Auswählen eines zumindest teilweise automatisierten Fahrvorgangs durch das autonome Fahrassistenzsystem basierend auf dem Entscheidungsbaum, den Entscheidungsindikatoren und in Abhängigkeit davon, ob der Fahrer des Fahrzeugs oder der Fremdakteur an dem Zeitpunkt, der dem Knoten zugeordnet ist, einen Spurwechsel oder eine Verkehrsaktion initiiert oder nicht.

According to a further aspect, the invention relates to a driver assistance system for a vehicle, which is designed to select an at least partially automated driving process from a large number of possible driving processes. The driver assistance system is designed to carry out the following steps:

1. a) determination of the current driving scenario and several different possible future driving processes based on the current driving scenario by the driving assistance system;
2. b) Automated creation of a decision tree by means of a processing unit of the driver assistance system by determining a plurality of nodes in the decision tree, the nodes being linked to points in time in the future, the nodes depending on the driving scenario being at least partially assigned by the driver of the vehicle or by an external actor a decision to be made regarding a lane change or a traffic action is assigned, and at least two decisions or options for action to be made by the driver assistance system itself are assigned at least partially to the nodes;
3. c) calculating travel trajectories using an automated trajectory planner, each travel trajectory being associated with a defined path through the decision tree and each path comprising one or more decisions to be made one after the other;
4. d) Automated calculation of an evaluation indicator for the travel trajectories, the evaluation indicator being a measure of the comfort and/or safety of the respective travel trajectory;
5. e) calculating probability values, the probability values being associated with nodes of the decision tree and the probability values each indicating the probability with which the driver of the vehicle or an external actor at the point in time associated with the node makes a decision to change lanes or take a traffic action;
6. f) calculating a plurality of decision indicators, one decision indicator each being assigned to a node, the calculation tion of the decision indicator is based at least in part on
   • - the probability value of the respective node, which indicates that the driver of the vehicle or an external actor makes a decision on a lane change or a traffic action at the point in time associated with the node; and
   • - at least one evaluation indicator of a travel trajectory, which is determined by a decision to be made at the time of the respective node;
7. g) Selecting an at least partially automated driving process by the autonomous driving assistance system based on the decision tree, the decision indicators and depending on whether the driver of the vehicle or the external actor initiates a lane change or a traffic action at the time assigned to the node or not .

According to yet another aspect, the invention relates to a vehicle with a driver assistance system according to one of the exemplary embodiments described above.

A “decision tree” within the meaning of the present invention is to be understood as meaning a decision structure with a number of decision stages (also referred to as nodes). The decision levels are assigned to different points in time in the future. At the decision stages, decisions are to be made that are to be made either by the driver assistance system itself or the driver of the driver's own vehicle or the driver or the driver assistance system of the third-party vehicle.

“External actor” within the meaning of the present invention is to be understood as meaning any actor who can take an action that can influence the driving processes of the ego vehicle. This is, for example, a third-party vehicle, a bus approaching from the bus stop, a pedestrian who is likely to enter the lane, a cyclist who may be changing from the cycle path to the lane, a car possibly turning off the side street at an intersection, but also a traffic light or a barrier.

“Traffic action” within the meaning of the present invention is to be understood as meaning any action by the driver of the ego vehicle or an external actor, the occurrence of which restricts the options for action or the freedom of decision of the driver assistance system. For example, a person stepping onto the road limits the options for action of the driver assistance system in such a way that a driving trajectory "keeping in lane at the same speed" is no longer possible and instead an attempt is made to either change lanes or brake.

The terms “approximately”, “substantially” or “roughly” mean deviations from the exact value by +/-10%, preferably by +/-5% and/or deviations in the form of changes that are insignificant for the function .

Further developments, advantages and possible applications of the invention also result from the following description of exemplary embodiments and from the figures. All of the features described and/or illustrated are fundamentally the subject matter of the invention, either alone or in any combination, regardless of how they are summarized in the claims or how they relate back to them. The content of the claims is also made part of the description.

• 1 beispielhaft und schematisch ein Fahrzeug in einem Fahrszenario, in der eine Entscheidung bezüglich eines Spurwechsels oder einem Spurhalten mit Geschwindigkeitsreduzierung zu treffen ist;
• 2 beispielhaft ein Entscheidungsbaum, der eine Auswahl mehrerer möglicher Fahrvorgänge für das in 1 gezeigte Fahrszenario ermöglicht;
• 3 beispielhaft eine schematische Darstellung der Fahrvorgänge gemäß dem Entscheidungsbaum der 2;
• 4 beispielhaft der Entscheidungsbaum gemäß 2 mit den Entscheidungen zugeordneten Wahrscheinlichkeitswerten;
• 5 beispielhaft der Entscheidungsbaum gemäß 4 mit Bewertungsindikatoren für die Fahrtrajektorien und den Knoten zugeordneten Entscheidungsindikatoren;
• 6 beispielhaft und schematisch ein Blockschaltbild eines Fahrassistenzsystems zur Durchführung des Auswahlverfahrens; und
• 7 beispielhaft und schematisch ein Ablaufdiagramm, das die Schritte des Verfahrens zur Auswahl eines zumindest teilautomatisierten Fahrvorgangs veranschaulicht.

The invention is explained in more detail below with reference to the figures of exemplary embodiments. Show it:

• 1 by way of example and schematically, a vehicle in a driving scenario in which a decision regarding a lane change or lane keeping with speed reduction is to be made;
• 2 A decision tree, for example, which selects several possible driving processes for the in 1 shown driving scenario allows;
• 3 example, a schematic representation of the driving processes according to the decision tree 2 ;
• 4 as an example, the decision tree according to 2 with probability values associated with the decisions;
• 5 as an example, the decision tree according to 4 with evaluation indicators for the travel trajectories and decision indicators assigned to the nodes;
• 6 by way of example and schematically a block diagram of a driver assistance system for carrying out the selection method; and
• 7 by way of example and schematically, a flowchart that illustrates the steps of the method for selecting an at least partially automated driving process.

1 shows an example of a driving scenario in which a vehicle 1, also referred to as an ego vehicle, drives on a multi-lane road, on which one or more other vehicles 2, 2' are also driving.

The driving scenario is characterized in particular by the fact that another vehicle 2' is driving in front of the vehicle 1 in the same lane, but at a lower speed, so that the distance d between the vehicles 1, 2' is increasingly reduced.

The driving situation can also be characterized by another vehicle 2 approaching from behind in a left-hand lane of the road.

In such a driving scenario, several driving processes are conceivable. First, as indicated by the arrow, the vehicle 1 can initiate a lane change or reduce the driving speed without changing lanes and drive behind the other vehicle 2 driving in front of it.

These two basic driving processes can be initiated at different times. For example, the speed of the vehicle 1 can be reduced slightly even if the distance d from the other vehicle 2' is large, in order to slowly drive onto the other vehicle 2' driving ahead. Alternatively, the deceleration process can be initiated later, requiring more deceleration. In the same way, the lane change of the vehicle 1 can be initiated at different points in time and thus at different distances d from the other vehicle 2'.

In vehicles with a driving assistance system in accordance with autonomy level 2 (SAE Level 2), a lane change must be initiated by the driver, i.e. the autonomous driving assistance system cannot independently initiate a lane change, but only when the driver has initiated it, for example by using the indicator or by a steering intervention causing a lane change. After this initiation, the lane change can then be carried out automatically.

The method described below makes it possible, depending on the probability that the driver will initiate a lane change at a certain point in time, to carry out a driving process that is as comfortable as possible and is adapted to the natural driving behavior of a human driver. This means in particular that driving processes that require abrupt braking or an abrupt lane change can be effectively avoided.

2 shows a decision tree 3, based on which a selection of an at least partially automated driving process can be made.

The decision tree 3 comprises a root 3a along which several nodes 3.1 are provided. Branches 3b branch off from nodes 3.1. Each branch 3b illustrates a decision 3.2. The branches 3b of the tree each end in a so-called leaf, which corresponds to a driving trajectory 3.3. In other words, making one or more decisions 3.2 leads to a certain travel trajectory 3.3. The travel trajectory is automatically calculated by a trajectory planner and indicates the trajectory on which the vehicle 1 is automatically moved when the decisions 3.2 leading to this travel trajectory 3.3 are made one after the other.

The nodes 3.1 are each linked to points in time t0 to t3, the points in time t0 to t3 following one another chronologically, starting from the current point in time (“now”). The trunk 3a of the decision tree 3 with its nodes 3.1 thus forms a time axis. The times t0 to t3 linked to the nodes 3.1 indicate which decisions linked to the nodes 3.1 can be made at which point in time.

The decision tree 3 thus maps the decisions 3.2 to be made at different points in time with the driving processes resulting therefrom, including driving trajectories 3.3. The entire decision tree can, for example, cover a time period in the future of 5 to 15 seconds, the time periods between two nodes can be between 1 and 5 seconds, for example, preferably 1, 2 or 3 seconds.

In the decision tree 3 according to 2 For example, at time t0 the decisions “change lane and keep speed”, “keep lane and keep speed” and keep lane and reduce speed” are possible.

Some of the decisions 3.2 to be made at a node must be initiated by the driver himself, for example. Another part of the decisions to be made 3.2 can be initiated by the autonomous driving assistance system itself. For example, the decision 3.2 "changing lanes" must be initiated by the driver of the vehicle 1, whereas the decisions 3.2, in which the lane is kept, can be initiated by the autonomous driver assistance system itself, i.e. there is no special initiative by the driver, such as sitting down of the blinker is required.

3 illustrated in the decision tree according to 2 possible driving processes shown graphically. When the vehicle 1 moves towards the other vehicle 2', the lane change can be initiated at different times and thus at different distances between the vehicles. The travel trajectories Trj1, Trj3, Trj5 correspond, for example, to the lane change trajectories if the lane change is initiated at times t0, t1 or t2.

It should be mentioned that a travel trajectory does not refer to just one decision, but rather corresponds to a complete path through the decision tree 3 from “now” to the respective leaf and thus includes a chain of several decisions 3.2 made one after the other. For example, the use of the driving trajectory Trj5 presupposes that the decision “keep in lane and maintain speed” was made at times t0 and t1 and that the driver initiated the lane change at time t2.

The driving trajectories Trj2, Trj4, Trj6 relate to the fact that the driver does not initiate a lane change and that the deceleration is initiated at different points in time t0 to t2.

If the driver does not initiate a lane change and no reduction in driving speed is initiated beforehand, emergency braking is finally automatically initiated by the emergency brake assistant of the vehicle 1 .

It is described below how, depending on the probability that the driver will initiate a lane change in the respective driving situation, an improved selection of an at least partially automated driving process from a large number of possible driving processes is made possible in terms of comfort and safety.

4 shows the decision tree 3 according to FIG 2 , probability values being additionally attached to the branches 3b of the decision tree 3 . In particular, the probability values p0, p1, p2 are assigned to the branches 3b, which relate to decisions 3.2 which relate to a lane change initiated by the driver. The probability values are each linked to a node and thus indicate the probability p0 to p2 with which a driver will make a decision to change lanes at a point in time t0 to t2.

In the exemplary embodiment shown, the driver assistance system can therefore make one of the other two decisions at the respective points in time t0 to t2 with a probability of 1-p0, 1-p1, 1-p2, i.e. stay in lane and either decelerate or keep the speed constant.

The probabilities p0 to p2 that the driver will initiate a lane change are calculated or estimated in advance for all nodes 3.1 or points in time t0 to t2.

The calculation of the probabilities p0 to p2 for a lane change at the times t0 to t2 is possible in different ways. Below are some examples of how probabilities are calculated. It goes without saying that there are also different options for calculating the probability.

Information from the driving history of the respective driver, i.e. in particular from past lane change events, can be used to determine the probability of a lane change at a specific point in time. In particular, this information from the driving history of the respective driver can be used as training data for a machine-learning system, in particular a neural network, so that it recognizes statistical relationships at which point in time a driver initiates a lane change in a given driving scenario. After training, the machine-learning system can be used in the current driving scenario to calculate the probability of a lane change at the respective points in time in the future.

According to a further alternative, evaluation indicators assigned to the respective driving trajectories are used to estimate the probabilities p0 to p2 for a lane change at times t0 to t2. The evaluation indicator assigned to a driving trajectory indicates the comfort (e.g. longitudinal and lateral acceleration below a specified threshold, longitudinal and lateral jerk below a specified threshold, frequency of lane changes) and safety (e.g. distance to other vehicles and/or objects in the area) of the driving trajectory. The calculation of the probabilities p0 to p2 for a lane change at the times t0 to t2 based on the evaluation indicators takes place against the background that a human driver typically changes lanes if this can be carried out with a high level of comfort and safety. Thus, in all probability, the probability of a lane change will be highest at the point in time when a driving trajectory with the greatest comfort or the greatest safety is available.

• - der Blinker gesetzt ist;
• - mittels einer Fahrerkamera feststellbar ist, dass der Fahrer in den Seitenspiegel schaut, der auf die Zielspur gerichtet ist;
• - durch Umfelderkennungsmittel (d.h. einen oder mehrere Sensoren) feststellbar ist, dass die Zielspur frei ist;
• - mittels einer Fahrerkamera feststellbar ist, dass der Fahrer einen Schulterblick in Richtung der Zielspur vollzieht;
• - das Navigationssystem eine Route vorschlägt, für die ein Spurwechsel vorteilhaft ist, um das Navigationsziel zu erreichen.

According to a further alternative, further available information can also be used be used to calculate the lane change probabilities. For example, information can be used as to whether:

• - the indicator is set;
• - It can be determined by means of a driver's camera that the driver is looking into the side mirror, which is directed towards the target lane;
• - It can be determined by environment detection means (ie one or more sensors) that the target lane is clear;
• - It can be determined by means of a driver's camera that the driver is looking over his shoulder in the direction of the target lane;
• - the navigation system suggests a route for which it is advantageous to change lanes in order to reach the navigation destination.

• - über eine Fahrerüberwachungskamera erkennbar ist, dass der Fahrer für längere Zeit nur auf die aktuelle Fahrspur blickt;
• - über eine Fahrerüberwachungskamera erkennbar ist, dass der Fahrer für längere Zeit nur auf ein Hindernis auf der aktuellen Fahrspur blickt;
• - das Navigationssystem eine Route vorschlägt, für die das Halten der Fahrspur vorteilhaft ist, um das Navigationsziel zu erreichen.

According to a further alternative, further available information can be used to calculate the lane change probabilities. For example, information can be used as to whether:

• - it can be seen via a driver monitoring camera that the driver is only looking at the current lane for a longer period of time;
• - it can be seen via a driver monitoring camera that the driver is only looking at an obstacle in the current lane for a longer period of time;
• - the navigation system suggests a route for which it is advantageous to stay in lane in order to reach the navigation destination.

A combination of these examples for calculating the probabilities p0 to p2 for a lane change at the times t0 to t2 is also possible.

As explained above, a travel trajectory is at least partially calculated for decisions to be made according to the decision tree 3 . On the one hand, the travel trajectory indicates the movement path of the vehicle in space, for example based on two-dimensional coordinates. On the other hand, information such as speed in the x and y directions, longitudinal and lateral acceleration or longitudinal and lateral jolts are also assigned to the travel trajectory. This makes it possible to determine how comfortable driving through the trajectory is for the driver.

In addition, when calculating the travel trajectory, further information can also be determined, for example the distance the vehicle maintains from third-party vehicles or objects in the vicinity.

It should be noted that the calculated travel trajectories must be collision-free in order to be considered in decision tree 3.

• - Halten der Fahrspur;
• - Wechseln der Fahrspur;
• - Halten der Fahrspur mit Verzögerung;
• - Halten der Fahrspur ohne Verzögerung für x Sekunden und anschließende Verzögerung, wobei x eine ganze Zahl ist.

The travel trajectory can be planned by a trajectory planner. This can calculate trajectories for different driving maneuvers. The driving maneuvers can be in particular:

• - staying in lane;
• - changing lanes;
• - lane keeping with deceleration;
• - Stay in lane without delay for x seconds and then delay, where x is an integer.

In addition, a unit is provided that enables the planned travel trajectories to be assessed with regard to comfort and safety. An evaluation indicator assigned to the respective travel trajectory is preferably calculated, which indicates the comfort and safety of the travel trajectory in the form of a number. The evaluation indicator can thus be used to determine what comfort and safety impression the driver of the vehicle has when the vehicle travels through the respective travel trajectory.

For example, a first driving trajectory, in which the driving trajectory is traversed with a low longitudinal and lateral acceleration, has a lower evaluation indicator than a second driving trajectory, in which a high longitudinal and lateral acceleration occurs.

Also, a travel trajectory in which the vehicle is slowly decelerated will have a lower evaluation indicator than a travel trajectory in which the vehicle is abruptly decelerated.

In other words, the evaluation indicator of a driving trajectory is a measure of how a human driver perceives a driving trajectory in terms of comfort and safety.

5 shows the decision tree according to 4 , wherein the individual trajectories Trj1 to Trj6 are each assigned an evaluation indicator C _sw0 , C _sw1 , C _sw2 , C _sh0 , C _sh1 , C _sh2 . The subscript "sw" stands for lane change and the subscript suffix "sh" for lane keeping. The evaluation indicator C _sw0 thus forms, for example, the evaluation indicator for the trajectory Trj1, the Evaluation indicator C _{sh0 e.g.} the evaluation indicator for the trajectory Trj2 etc.

Decision indicators can be calculated based on the probabilities (p0 to p2) for a lane change and the evaluation indicators of the driving trajectories. In each case one decision indicator is preferably assigned to one node 3.1. In 5 the decision indicator of the first node is labeled Cost_0, the decision indicator of the second node is labeled Cost_1 and the decision indicator of the third node is labeled Cost_2.

Based on a comparison of the decision indicators of the different nodes 3.1, the driver assistance system can decide whether, in the event that the driver does not initiate a lane change at a certain node, it is more favorable in terms of the driver's comfort and safety to stay in lane and initiate a delay or stay on track without delay.

The calculation of the decision indicators Cost_x of the different nodes 3.1 (x stands for the node index or the time point index) can be done as follows, for example: $$\text{Cost\_x}={\text{p}}_{\text{x}}*{\text{C}}_{\text{swx}}+\left(\text{1}-{\text{p}}_{\text{x}}\right)*{\text{C}}_{\text{shx}}$$

Cost_x:

Entscheidungsindikator des jeweiligen Knoten;

px:

Wahrscheinlichkeit für einen vom Fahrer eingeleiteten Spurwechsel zum Zeitpunkt tx

Cswx:

Bewertungsindikator der Spurwechseltrajektorie am Knoten x

Cshx:

Bewertungsindikator der Spurhaltentrajektorie am Knoten x

where:

Cost_x:

decision indicator of the respective node;

pixels:

Probability of a lane change initiated by the driver at time tx

Cswx:

Lane change trajectory evaluation indicator at node x

cshx:

Evaluation indicator of lane keeping trajectory at node x

In addition, the highest possible evaluation indicator or decision indicator value C _NB (NB: emergency braking) is assigned to the emergency braking option.

After a decision indicator Cost_x has been calculated for all nodes 3.1, the node that has the lowest decision indicator value is first determined. For example, if node 0 has a decision indicator Cost_0 of 40, node 1 has a decision indicator Cost_1 of 30, node 2 has a decision indicator Cost_2 of 50, and node 3 has a decision indicator C _NB of 100, node 1 is selected because it has the lowest Has decision indicator value.

The lowest decision indicator value means that, taking into account the probability that the driver initiates a lane change at the node to which this lowest decision indicator value is assigned, the costs of the decisions or the costs of the travel trajectories assigned to these decisions are lowest.

Alternatively, the lowest decision indicator value may mean that the expected value of the cost at that node is lowest. This may be due to the fact that all leaves of the branches of this node have low-cost trajectories, or the low-cost trajectory has a high probability compared to the high-cost trajectory.

The decision tree 3 is then run through depending on the driving behavior of the driver and the decision indicators of the nodes 3.1. For example, at node 0 (time t0), which has a higher decision indicator value than node 1 (time t1), in the event that the driver does not initiate a lane change, the decision tree continues to node 1, i.e. does not go through the trajectory Trj2, since driving maneuvers optimized in terms of comfort and safety are available at node 1.

If the driver does not initiate a lane change at node 1 either, it is decided on the basis of the minimum decision indicator value that the automated driver assistance system initiates the trajectory Trj4 at time t1, i.e. the lane is maintained and the speed is reduced.

In other words, if the driver does not initiate a lane change at time t0 and the trajectory Trj1 is therefore run through, either the trajectory Trj3 is initiated at time t1, specifically when the driver initiates a lane change, or the trajectory Trj4 is initiated , i.e. staying in lane and reducing speed.

• Wie zuvor beschrieben, werden die den Knoten 3.1 zugeordneten Entscheidungsindikatoren (Cost_0 bis Cost_2) durch die Wahrscheinlichkeitswerte (p0 bis p2), dass ein Fahrer zu einem bestimmten Zeitpunkt, der dem Knoten 3.1 zugeordnet ist, einen Spurwechsel einleitet, beeinflusst. Diese Wahrscheinlichkeitswerte unterliegen einer Ungenauigkeit. Die Ungenauigkeit der Wahrscheinlichkeitswerte wird umso größer, je weiter der Knoten bzw. der Zeitpunkt, dem der Wahrscheinlichkeitswert zugeordnet ist, in der Zukunft liegt.

The method described above for selecting an at least partially automated driving process can be modified as required, as described below:

• As previously described, the decision indicators (Cost_0 to Cost_2) associated with nodes 3.1 are influenced by the probability values (p0 to p2) that a driver will initiate a lane change at a particular time associated with node 3.1. These probability values are subject to inaccuracy. The inaccuracy of the probability values is the greater the further in the future the node or point in time to which the probability value is assigned is.

Therefore, it is proposed to determine the decision indicators for different probability deviations from the originally calculated probability values, e.g. for a first scenario with no deviation, a second scenario with a deviation of +20%, a third scenario with a deviation of -20%, a fourth scenario with a deviation of +30%, a fourth scenario with a deviation of -30%. The decision indicators of the nodes can then be calculated for all of these scenarios and the decision indicator with the largest value can be selected for each node. The at least partially automated driving processes are then selected based on these decision indicators of the nodes, which are the largest in terms of value.

According to a further embodiment of the invention, when running through the decision tree 3 at the nodes, a decision can be made as to whether trajectory planning should be carried out again based on the current environmental information and the decision tree 3 is therefore regenerated and the possible trajectories, probabilities, evaluation indicators of the travel trajectories and decision indicators are calculated must. As a condition, collision-free trajectories for the respective decisions should be available at least at two points in time/nodes in the future.

The invention was described above using an exemplary embodiment in which the vehicle changes lanes to a left-hand lane in order to start an overtaking maneuver. It goes without saying that the invention can also be applied to other driving scenarios in which the vehicle changes lanes to a right-hand lane. It is also conceivable to apply the invention to driving scenarios in which a lane change to the left and right is possible.

In addition, the invention can also be applied to driving scenarios in which an automated driving process is carried out depending on whether it is to be expected that another vehicle will cut into your own lane or not. In other words, it is not the probability of initiating a lane change by the driver of the host vehicle (host vehicle) that is predicted, but rather the probability of initiating a lane change by another vehicle.

The probability values linked to the nodes of the decision tree thus indicate how likely it is that the other vehicle will initiate a lane change into the lane of the host vehicle. The decision tree can be used to decide to initiate a driving process when the other vehicle is changing lanes or, if the other vehicle is not changing lanes, to decide whether it is better to prepare for a lane change of the other vehicle by a moderate reduction in speed or maintain speed and apply harder braking later when changing lanes.

6 shows a schematic representation of a driver assistance system for carrying out at least partially automated driving processes.

The driver assistance system preferably has a central control unit 11 which provides computing and storage means for carrying out the processes described below. Alternatively, a decentralized computer architecture can also be provided, or the processes can be carried out or calculated on a computer unit of a sensor, provided the sensor provides sufficient computing power.

The control unit 11 has an environment model unit 12 in which the environment model of the environment of the vehicle is provided. This environment model unit 12 receives information from one or preferably more sensors 13. The sensors 13 can be cameras, radar sensors, LIDAR sensors, ultrasonic sensors, etc., for example. The environment model unit 12 uses the information from the sensors 13 to generate an environment model that is made available to a driving process planner 14 . The driving process planner 14 is a planner that can calculate one or more driving trajectories based on the environment model, preferably depending on the current driving scenario, multiple driving trajectories that can be used in this driving scenario and can be carried out without collision.

The driving process planner 14 preferably also calculates the evaluation indicator for the respective driving trajectory. The previously described method for selecting a driving process can also be carried out in the driving process planner 14 .

If a travel trajectory is defined on which the vehicle is to be moved, corresponding information is then transmitted to a vehicle movement controller 15 . This vehicle movement control 15 can be provided either in the control unit 11 or discreetly ral, ie provided in a separate control unit. The vehicle motion controller 15 generates output signals for the steering, braking system and power train.

7 shows a flow chart of a method for selecting an at least partially automated driving process using a driver assistance system of a vehicle.

First, the current driving scenario and several different possible future driving processes are determined by the driver assistance system based on the current driving scenario (S10).

A decision tree is then created automatically (S11). The decision tree has multiple nodes, with the nodes being linked to points in time in the future. Depending on the driving scenario, at least one decision to be made by the driver of the vehicle or another vehicle regarding a lane change is assigned to the nodes at least partially. In addition, at least two decisions to be made by the driver assistance system itself are at least partially assigned to the nodes.

In addition, travel trajectories are calculated, with each travel trajectory being associated with a defined path through the decision tree and each path comprising one or more decisions to be made one after the other (S12).

Evaluation indicators are then calculated for the travel trajectories, the evaluation indicator being a measure of the comfort and/or safety of the respective travel trajectory (S13).

In addition, probability values are calculated, the probability values being assigned to nodes in the decision tree and the probability values each indicating the probability of the driver of the vehicle or another vehicle making a decision to change lanes at the point in time assigned to the node (S14).

Subsequently, a plurality of decision indicators are calculated (S15). In each case, a decision indicator is assigned to a node. The calculation of the decision indicator is based at least in part on the probability value associated with the respective node, which indicates that the driver of the vehicle or another vehicle will make a decision to change lanes at the time associated with the node. In addition, the calculation of the decision indicator is based on at least one evaluation indicator of a travel trajectory, which is determined by a decision to be made at the time of the respective node.

Finally, an at least partially automated driving process is selected by the autonomous driving assistance system (S16), based on the decision tree, the decision indicators and depending on whether the driver of the vehicle or the other vehicle is changing lanes at the time assigned to the node initiated or not.

The invention has been described above using exemplary embodiments. It goes without saying that numerous changes and modifications are possible without leaving the scope of protection defined by the patent claims.

Reference List

1

vehicle

2, 2'

foreign vehicle

3

decision tree

3a

tribe

3b

branch

3.1

node

3.2

decision

3.3

driving trajectory

10

driver assistance system

11

control unit

12

Environment Model Unit

13

sensor

14

driving process planner

15

vehicle motion control

i.e

Distance

Claims (15)

Method for selecting an at least partially automated driving process using a driver assistance system of a vehicle (1) comprising the following steps: a) determining the current driving scenario and several different possible future driving processes based on the current driving scenario by the driver assistance system (S10); b) Automated creation of a decision structure (3) by means of a processing unit of the driver assistance system by determining a plurality of decision stages (3.1) of the decision structure (3), the decision stages (3.1) being linked to points in time in the future, the decision stages (3.1) depending on the driving scenario at least in part at least one decision to be made by the driver of the vehicle (1) or an external actor (2). (3.2) is assigned with regard to a lane change or a traffic action and wherein at least two decisions (3.2) to be made by the driver assistance system itself are assigned at least partially to the decision stages (3.1) (S11); c) calculating travel trajectories (3.3), each travel trajectory being assigned to a defined path through the decision structure (3) and each path comprising one or more decisions (3.2) to be made one after the other (S12); d) calculating evaluation indicators for the travel trajectories (3.3), the evaluation indicator being a measure of the comfort and/or safety of the respective travel trajectory (3.3) (S13); e) Calculation of probability values, the probability values being assigned to decision stages (3.1) of the decision structure (3) and the probability values each indicating the probability of the driver of the vehicle (1) or an external actor (2) at the point in time which corresponds to the decision stage ( 3.1) is assigned, makes a decision (3.2) on a lane change or a traffic action (S14); f) calculating a plurality of decision indicators (S15), one decision indicator being assigned to a decision level (3.1), the calculation of the decision indicator being based at least in part on - the probability value of the respective decision level (3.1), which indicates that the driver of the vehicle (1 ) or an external actor (2) makes a decision (3.2) on a lane change or a traffic action at the point in time that is assigned to the decision stage (3.1); and - at least one evaluation indicator of a travel trajectory (3.3), which is determined by a decision to be made at the time of the respective decision stage (3.1); g) Selecting an at least partially automated driving process by the autonomous driving assistance system based on the decision structure (3), the decision indicators and depending on whether the driver of the vehicle (1) or the external actor (2) at the point in time that the decision stage (3.1 ) is assigned initiates a lane change or traffic action or not (S16). procedure after claim 1 , characterized in that the values of the decision indicators of the decision stages (3.1) of the decision structure (3) are compared in order to select an at least partially automated driving process, and in that the selected driving process is based on a driving trajectory (3.3) which, at the point in time at which the decision stage ( 3.1) associated with the smallest decision indicator value initiated a lane change or a deceleration process. procedure after claim 1 or 2 , characterized in that the decision indicators of the decision stages (3.1) are calculated at least partially by adding the results of a first multiplication and a second multiplication, with the first multiplication of the probability value that the driver of the vehicle (1) or the external actor ( 2) at the point in time assigned to the decision stage (3.1), initiates a lane change, is multiplied by the evaluation indicator of the driving trajectory, by means of which the lane change is carried out, and in the second multiplication, the probability value that the driver of the vehicle (1) or the external actor (2), at the time assigned to the decision stage (3.1), does not initiate a lane change or any traffic action, is multiplied by the evaluation indicator of the driving trajectory, by means of which the lane is maintained and the vehicle (1) is decelerated. Method according to one of the preceding claims, characterized in that a decision (3.2) to be made by the driver of the vehicle (1) by setting the indicator and/or a steering intervention which causes a lane change is detected. Method according to one of the preceding claims, characterized in that a decision to be made by the external actor (2) is detected by detecting a blinker, by turning off and/or a foreign vehicle changing lanes or by a person (2) entering the lane. Method according to one of the preceding claims, characterized in that the calculation of a travel trajectory (3.3) the calculation of multidimensional coordinates along which the vehicle (1) moves when driving through the travel trajectory, the calculation of longitudinal and transverse acceleration values and / or the calculation of longitudinal and lateral jerk values. Method according to one of the preceding claims, characterized in that the calculation of the evaluation indicator of a travel trajectory (3.1) including the distance of the vehicle (1) to other vehicles (2, 2 ') and / or objects, the difference to a set speed and/or the lane change frequency. Method according to one of the preceding claims, characterized in that a travel trajectory (3.3) corresponds to a path through the decision structure (3), the travel trajectory (3.3) being based on decisions (3.2) which are assigned to the path of the decision structure (3). Method according to one of the preceding claims, characterized in that the probability value that the driver will initiate a lane change at a future time assigned to a decision stage (3.1) is calculated on the basis of a neural network which is obtained using data obtained from the driver's past driving processes been trained. Method according to one of the preceding claims, characterized in that the probability value that the driver will initiate a lane change at a future time assigned to a decision stage (3.1), based on the evaluation indicators of the travel trajectories (3.3), which are made by means of decisions at the times of the respective nodes (3.1) are initiated is calculated. Method according to one of the preceding claims, characterized in that the probability value that the driver will initiate a lane change at a future point in time assigned to a decision stage (3.1) is calculated on the basis of driver behavior detected by at least one sensor. Method according to one of the preceding claims, characterized in that a plurality of decision indicators are calculated at least for part of the decision stages (3.1), which are based on different probability values that the driver of the vehicle (1) or the external actor (2) at the time is assigned to the decision stage (3.1), makes a decision on a lane change or a traffic action, and that the largest decision indicator for the selection of an at least partially automated driving process is used for each decision stage (3.1). Method according to one of the preceding claims, characterized in that the decision to be made by the driver of the vehicle (1) comprises a lane change from a right lane to a left lane or a lane change from a middle lane to a left or right lane. Driving assistance system for a vehicle (1), which is designed to select an at least partially automated driving process from a large number of possible driving processes, the driving assistance system being designed to carry out the following steps: a) determining the current driving scenario and several different possible future driving processes based on the current driving scenario by the driver assistance system; b) Automated creation of a decision-making structure (3) by means of a processing unit of the driver assistance system by determining a plurality of decision-making stages (3.1) of the decision-making structure (3), the decision-making stages (3.1) being linked to points in time in the future, the decision-making stages (3.1) depending on at least one decision (3.2) to be made by the driver of the vehicle (1) or an external actor (2) regarding a lane change or a traffic action is at least partially assigned to the driving scenario, and at least two of the decision stages (3.1) are assigned at least partially by the driver assistance system itself relevant decisions (3.2) are assigned; c) calculating travel trajectories (3.3) using an automated trajectory planner, each travel trajectory being assigned to a defined path through the decision structure (3) and each path comprising one or more decisions (3.2) to be made one after the other; d) automated calculation of an evaluation indicator for the travel trajectories (3.3), the evaluation indicator being a measure of the comfort and/or safety of the respective travel trajectory (3.3); e) Calculation of probability values, the probability values being assigned to decision stages (3.1) of the decision structure (3) and the probability values each indicating the probability of the driver of the vehicle (1) or an external actor (2) at the point in time which corresponds to the decision stage ( 3.1) makes a decision on a lane change or traffic action; f) calculating a plurality of decision indicators, one decision indicator being assigned to a decision level (3.1), the calculation of the decision indicator being based at least in part on - the probability value of the respective decision level (3.1), which indicates that the driver of the vehicle (1) or a External actors (2) make a decision (3.2) on a lane change or a traffic action at the point in time that is assigned to the decision stage (3.1); and - at least one evaluation indicator of a travel trajectory (3.3) to be taken by a decision stage (3.1) at the time of the respective decision Decision (3.2) is established; g) Selecting an at least partially automated driving process by the autonomous driving assistance system based on the decision structure (3), the decision indicators and depending on whether the driver of the vehicle (1) or the external actor (2) at the point in time that the decision stage (3.1 ) is assigned, initiates a lane change or traffic action or not. Vehicle comprising a driver assistance system according to Claim 14 .

Images