Method for providing lane change assistance for vehicle and lane change assistance method for vehicle

Abstract

The invention relates to a method (100) for providing lane change assistance for a vehicle (10, FF), comprising providing (110) driving data of the vehicle (10), the driving data relating to a first driving situation of the vehicle (10, FF); performing (120) a simulation of a second driving situation on the basis of the driving data of the first driving situation in order to generate simulated data, the first driving situation comprising at least one lane change and the second driving situation not comprising a lane change, or the second driving situation comprising at least one lane change and the first driving situation not comprising a lane change; and training (130) a lane change algorithm on the basis of the driving data and / or the simulation data.

Description

Technical Field

[0001] This invention relates to a method for providing lane change assistance to a vehicle, a lane change assistance method for a vehicle, and a system for performing the above method. The invention particularly relates to, for example, calculating and initiating the optimal lane change during autonomous driving. Background Technology

[0002] Assistance systems for autonomous driving are always important. Autonomous driving can be achieved using different levels of automation. Exemplary levels of automation are driver assistance, semi-autonomous driving, conditional autonomous driving, highly automated driving, or fully automated driving. These five levels of automation correspond to SAE Levels 1 through 5 according to the SAE J3016 (SAE - Society of Automotive Engineers) standard as of April 30, 2021. In fully automated driving (SAE Level 5), the system can perform all aspects of dynamic driving tasks under any road and environmental conditions, and it is also controlled by a human driver.

[0003] Modern vehicles increasingly utilize so-called lane change assistants. Depending on the level of automation, the driver can either manually execute a lane change or initiate an automatic lane change, or the vehicle can execute the lane change fully automatically. In at least some of these cases, the vehicle can execute an automatic lane change plan, such as when the vehicle checks for sufficient space, changes lanes as necessary to maintain the planned route, or when the vehicle is blocked in its current lane by a slower vehicle ahead.

[0004] Lane changes are generally associated with increased safety risk because collisions with other vehicles are more likely than staying in the current lane. In SAE Level 2 lane change assist, the driver must monitor the function, which puts the driver in a higher state of alertness, thus reducing driving comfort. Similarly, driving comfort may decrease due to the large number of lane changes the driver must monitor. This may prompt the driver to disable the function. Disabling lane change assist can negatively impact safety in road traffic, as it typically provides greater safety compared to manual driving. Furthermore, too many or too few lane changes can negatively affect vehicle travel time and / or traffic flow. Summary of the Invention

[0005] The objective of this invention is to provide a method for providing lane change assistance to a vehicle, a lane change assistance method for a vehicle, and a system for performing the above method, which can reliably estimate in advance whether a lane change is meaningful under the current circumstances. Furthermore, the objective of this invention is to maximize the service life of the lane change assistance, and thus improve road traffic safety.

[0006] This task is addressed by the subject matter of the independent claims. Advantageous design solutions are described in the dependent claims.

[0007] According to an independent aspect of the present invention, a method for providing lane change assistance for a vehicle, particularly a motor vehicle, is provided. The method includes providing driving data of the vehicle, wherein the driving data relates to a first driving situation of the vehicle; performing a simulation of a second driving situation based on the driving data of the first driving situation to generate simulation data, wherein the first driving situation includes at least one lane change while the second driving situation does not include a lane change, or wherein the second driving situation includes at least one lane change while the first driving situation does not include a lane change; and training a lane change algorithm based on the driving data and / or the simulation data.

[0008] According to the present invention, a data-driven method is used to train a lane-changing algorithm that can determine whether a lane change is advantageous under current circumstances. To this end, actual convoy driving is evaluated, for example. In particular, actual driving with lane changes is simulated against corresponding driving without lane changes, or actual driving without lane changes is simulated against corresponding driving with lane changes. Based on the comparison between actual and simulated driving situations with and without lane changes, the advantage of a lane change can be deduced. A lane-changing algorithm trained based on these insights can be implemented in real vehicles and reliably estimate whether a lane change is meaningful under current circumstances during actual operation.

[0009] The lane-changing algorithm is trained based on driving data and / or simulation data. In some implementations, the lane-changing algorithm may be trained using (only) data corresponding to better alternatives. In other implementations, the lane-changing algorithm may be trained using both driving data from actual operations and simulation data.

[0010] Preferably, performing a simulation of the second driving scenario includes determining the driving behavior of the vehicle and the driving behavior of at least one external vehicle. Specifically, changes in the vehicle's driving behavior and changes in the driving behavior of the at least one external vehicle can be determined with respect to the addition or cancellation of lane changes. This allows for the determination and analysis of driving behavior in two scenarios: one with a lane change and one without.

[0011] Preferably, the method further includes performing a comparison between a first driving situation and a second driving situation (or corresponding driving situation-related data); and determining, based on the comparison, whether at least one lane change was advantageous. The terms "advantageous" and "disadvantageous" refer here to an objective criterion that describes which driving situation is more efficient and / or more advantageous.

[0012] Preferably, the comparison between the first and second driving scenarios is performed based on at least one comparison criterion. The at least one comparison criterion is an objective standard that indicates which driving scenario is more efficient or advantageous. Therefore, the first and second driving scenarios can be objectively compared and thus evaluated.

[0013] In some implementations, at least one comparison criterion is selected from the following group, which includes (or consists of):

[0014] - Travel time difference; and / or

[0015] - Speed ​​difference with at least one external vehicle; and / or

[0016] - Distance from at least one outside vehicle; and / or

[0017] - Differences in driver attention; and / or

[0018] - Vehicle energy consumption; and / or

[0019] - Acceleration behavior of the vehicle and / or at least one external vehicle.

[0020] Regarding travel time differences, it can be determined, for example, whether the journey to the destination is faster with or without lane changes. Travel situations with shorter travel times can be categorized as advantageous.

[0021] Regarding the speed difference of at least one oncoming vehicle, it can be determined, for example, how large the speed difference is between the vehicle and the oncoming or preceding vehicle. If the speed difference is large and the vehicle is faster than the preceding vehicle, then changing lanes to overtake the preceding vehicle may be more advantageous than not changing lanes or staying behind the preceding vehicle. Conversely, if the speed difference is small and the vehicle is faster than the preceding vehicle, then changing lanes to overtake the preceding vehicle may be more disadvantageous due to the only slight reduction in travel time and the increased collision risk through lane changing than not changing lanes or staying behind the preceding vehicle.

[0022] The distance to at least one oncoming vehicle can be determined, for example, by the distance to an oncoming vehicle or the vehicle in front of the vehicle. If the distance is large and the vehicle is only slightly faster than the vehicle in front, then changing lanes to overtake the vehicle in front may be more disadvantageous than not changing lanes or staying behind the vehicle in front, due to the slight reduction in travel time and the increased risk of collision caused by changing lanes.

[0023] Regarding differences in driver attention, it's possible to determine the required level of attention for a driver in two driving situations. Generally, situations involving lane changes require higher levels of attention than situations without lane changes. If the difference in attention is significant, then not changing lanes may be more advantageous than changing lanes. Large differences in attention are particularly likely to be accompanied by a significantly increased risk of accidents, making it potentially more advantageous to forgo changing lanes.

[0024] Regarding a vehicle's energy consumption (e.g., fuel and / or electricity), it can be determined how much energy is consumed and / or how much the difference in energy consumption is between the two driving conditions. Driving conditions with lower energy consumption can be classified as favorable driving conditions.

[0025] The acceleration behavior of the vehicle and / or at least one other vehicle can be determined, for example, whether the acceleration behavior present in two driving scenarios is assessed as positive or negative. For instance, it might be necessary for the vehicle to accelerate sharply to overtake the vehicle in front. In this case, changing lanes to overtake the vehicle in front might be more disadvantageous due to the increased collision risk from changing lanes than not changing lanes or remaining behind the vehicle in front. In another example, it might be necessary for the vehicle to decelerate sharply without changing lanes to avoid colliding with the vehicle in front. In this case, changing lanes to overtake the vehicle in front might be more advantageous than not changing lanes or remaining behind the vehicle in front.

[0026] In some implementations, driving data for a first or actual driving situation is selected from a group that includes (or consists of):

[0027] - Vehicle location data; and / or

[0028] - Vehicle dynamic data, especially speed data; and / or

[0029] - Environmental data from the vehicle's environmental sensor system; and / or

[0030] - Vehicle operating data; and / or

[0031] - Vehicle driving and maneuvering data.

[0032] Regarding vehicle location data, GPS location data from the first or actual driving scenario can be fed into the simulation, for example. This location data can, for example, determine the vehicle's driving path under the first or actual driving scenario.

[0033] Regarding vehicle dynamics data, parameters describing vehicle motion from first-hand or actual driving conditions can be fed into the simulation. Dynamic data may include, but are not limited to, velocity data and / or acceleration data (e.g., longitudinal acceleration and / or lateral acceleration).

[0034] Regarding environmental data from the vehicle's environmental sensor system in a first or actual driving situation, the environmental data may be selectively and / or (pre)processed (e.g., as detection) fed into the simulation. Preferably, the environmental sensor system includes at least one laser ranging system and / or at least one radar system and / or at least one camera and / or at least one ultrasonic system. The environmental sensor system can provide environmental data (also referred to as "surrounding data") that depicts the vehicle's environmental area.

[0035] Regarding vehicle operating data from a first or actual driving scenario, the operating data can be fed into the simulation to depict the vehicle's behavior as accurately as possible in the simulation and to establish a correlation between the first or actual driving scenario and a second or simulated driving scenario. Vehicle operating data may relate to, for example, the operation of drives (e.g., burner, electric drive, operating mode, etc.) and / or the operation of driver assistance systems and / or vehicle status (e.g., tire pressure), but is not limited to these examples.

[0036] Regarding driving maneuver data from the first or actual driving situation, driving maneuver data can describe what driving maneuvers the vehicle performed. Driving maneuvers may involve, for example, lane changes, steering maneuvers, braking maneuvers, acceleration maneuvers, etc., but are not limited to these examples.

[0037] Preferably, the simulation of the second driving situation is performed based on the driving data and additional data of the first driving situation.

[0038] In some implementations, additional data is selected from a group that includes (or consists of):

[0039] - Digital map data; and / or

[0040] - External vehicle information (e.g., location, speed, vehicle type); and / or

[0041] - Dynamic traffic information (e.g., congestion, traffic jams); and / or

[0042] - Environmental information (e.g., hazard notices, construction sites, weather conditions, etc.); and / or

[0043] - Traffic infrastructure information (e.g., lanes, number of lanes, lane geometry, etc.).

[0044] Preferably, the method further includes providing a trained lane-changing algorithm for a convoy of multiple vehicles. In particular, the trained lane-changing algorithm can be implanted into the vehicles of the convoy and used there in actual operation in order to estimate whether a lane change is meaningful in the current situation.

[0045] Preferably, the lane-changing algorithm includes or at least one neural network, particularly a trained neural network. The neural network consists of a series of processing units, so-called neurons, interconnected by communication channels. Neurons process input data and transmit the processing results to other neurons via communication channels. Through parallel processing of data (which can be achieved through the association between neurons and their processing functions), complex nonlinear relationships can be mapped into the input data. The neural network is trained using appropriate learning techniques (such as machine learning) to learn these relationships. Training of the neural network can be performed using empirical data, also known as training data.

[0046] Preferably, the lane-changing algorithm is a machine learning-based algorithm. Machine learning (ML) refers to the artificial generation of knowledge from experience. Here, the algorithm learns from empirical data and is able to generalize the experience after the learning phase. To this end, the algorithm builds a statistical model based on empirical data. The empirical data used to train the algorithm is usually called "training data".

[0047] According to another independent aspect of the invention, a system for providing lane change assistance to a vehicle is provided. The system includes one or more processors; and at least one memory connected to the one or more processors and containing instructions executable by the one or more processors to implement the method for providing lane change assistance to a vehicle described in this document.

[0048] Preferably, the system includes at least one server and / or at least one backend, or is implemented by at least one server and / or at least one backend.

[0049] A processor or processor module is a programmable calculator, i.e. a machine or electronic circuit, that controls other components according to transmitted commands and thereby advances an algorithm (process).

[0050] According to another independent aspect of the invention, a lane change assist method for vehicles, particularly motor vehicles, is provided. The lane change assist method includes determining, using a lane change algorithm trained with the methods described in this document, whether a lane change should be performed given the vehicle's current driving condition.

[0051] Preferably, the lane change assist method further includes providing appropriate suggestions to the driver of the vehicle and / or performing automatic lane change when it is determined that a lane change should be performed.

[0052] Preferably, the lane change assist method further includes determining at least one driving maneuver to be performed based on whether a lane change should be performed given the vehicle's current driving conditions. The at least one driving maneuver to be performed may involve a driving maneuver different from or different from a lane change, and in particular may be an additional driving maneuver. In some embodiments, the at least one driving maneuver to be performed may include acceleration and / or braking maneuvers, but is not limited to these examples.

[0053] Preferably, the lane change assist method further includes outputting a corresponding suggestion to the driver of the vehicle regarding at least one driving maneuver to be performed, and / or automatically performing at least one driving maneuver.

[0054] According to another independent aspect of the invention, a driving assistance system for a vehicle is provided. The driving assistance system includes one or more processors; and at least one memory connected to the one or more processors and containing instructions executable by the one or more processors to implement the lane change assistance method described in this document.

[0055] Preferably, the driving assistance system is designed for autonomous driving.

[0056] Within the scope of this document, the term "autonomous driving" is understood as driving with automatic longitudinal and / or lateral guidance. Automated driving can be, for example, driving for extended periods on a highway or driving within a parking area for a limited time. The term "autonomous driving" includes autonomous driving with any level of automation. Exemplary levels of automation are driver assistance, semi-autonomous driving, conditional autonomous driving, highly automated driving, and fully automated driving (each with an increased level of automation). These five levels of automation correspond to SAE Levels 1 to 5 according to the SAE J3016 (SAE - Society of Automotive Engineers) standard as of April 30, 2021.

[0057] In Driver Assistance (SAE Level 1), the system provides longitudinal or lateral guidance in specific driving situations. In Semi-Autonomous Driving (SAE Level 2), the system takes over longitudinal and lateral guidance in specific driving situations, where, as in Driver Assistance, the driver must continuously monitor the system. In Conditional Automated Driving (SAE Level 3), the system takes over longitudinal and lateral guidance in specific driving situations, and the driver does not need to continuously monitor the system; however, the driver must be able to take over vehicle guidance at the system's request for a certain period. In Highly Automated Driving (SAE Level 4), the system takes over vehicle guidance in specific driving situations, even when the driver does not respond to intervention requests, thus the driver is no longer a backup. In Fully Automated Driving (SAE Level 5), the system can perform all aspects of dynamic driving tasks under any road and environmental conditions, and is also controlled by a human driver.

[0058] Furthermore, within the scope of this document, the term "at least semi-autonomous or fully automated" is understood to mean semi-autonomous driving, conditional automated driving, highly automated driving, and fully automated driving. In other words, the term "at least semi-autonomous driving" is understood to mean the level of automation starting from SAE Level 2 (inclusive).

[0059] Preferably, the driving assistance system includes or is designed to perform automatic lane changes.

[0060] However, embodiments of the present invention are not limited to autonomous driving or automatic lane changing. In alternative embodiments, when the vehicle is manually driven, the driving assistance system may output driver instructions using at least one output device. Driver instructions may, for example, be a suggestion regarding whether a lane change should be performed given the vehicle's current driving conditions.

[0061] At least one output device may include at least one display device and / or at least one speaker. The at least one display device may include a monitor, particularly an LCD monitor, a plasma monitor, or an OLED monitor. Additionally or alternatively, the at least one display device may include a projection device designed to display information directly in the driver's field of vision, particularly projecting information onto the windshield. In some embodiments, the at least one display device may be a central information output device for an infotainment system, such as a head unit or a pillar-to-pillar display. Preferably, the at least one output device is fixedly mounted in the vehicle.

[0062] According to another independent aspect of the invention, a vehicle, particularly a motor vehicle, is provided. The vehicle includes a driving assistance system according to an embodiment of the invention.

[0063] The term "vehicle" includes passenger cars, trucks, transport vehicles, buses, RVs, motorcycles, etc., used for transporting people, goods, etc. This term particularly includes motor vehicles used for transporting people.

[0064] According to another independent aspect of the invention, a software (SW) program is provided. The software program can be designed to execute on one or more processors, and thereby perform the methods described in this document.

[0065] According to another independent aspect of the invention, a storage medium is provided. The storage medium may include a software program designed to execute on one or more processors, and thereby perform the methods described herein.

[0066] According to another independent aspect of the invention, software having program code is provided. This software is designed to execute the methods described herein when the software is run on one or more software-controlled devices. Attached Figure Description

[0067] Embodiments of the present invention are shown in the accompanying drawings and will subsequently be described in detail. Wherein:

[0068] Figure 1 A flowchart of a method for providing lane change assistance to a vehicle according to an embodiment of the present invention is shown.

[0069] Figure 2 A system for providing lane change assistance to a vehicle according to an embodiment of the present invention is shown.

[0070] Figure 3 A flowchart of a lane change assist method according to an embodiment of the present invention is shown.

[0071] Figure 4 The illustration schematically depicts a vehicle with a driving assistance system for autonomous driving according to an embodiment of the present invention. Detailed Implementation

[0072] Subsequently, unless otherwise stated, the same reference numerals are used for elements that are the same and have the same function.

[0073] Figure 1 A flowchart illustrating a method 100 for providing lane change assistance to a vehicle according to an embodiment of the present invention is shown schematically. Figure 2 A system for providing lane change assistance to a vehicle according to an embodiment of the present invention is shown. In particular, the system may include a central unit 200 designed to perform method 100. The central unit 200 may be a server or a backend.

[0074] Method 100 includes providing driving data of the vehicle in block 110, wherein the driving data relates to a first driving situation of the vehicle; in block 120, performing a simulation of a second driving situation based on the driving data of the first driving situation to generate simulation data, wherein the first driving situation includes at least one lane change while the second driving situation does not include a lane change, or wherein the second driving situation includes at least one lane change while the first driving situation does not include a lane change; and in block 130, training a lane change algorithm based on the driving data and / or the simulation data.

[0075] According to the present invention, a data-driven method is used to train a lane-changing algorithm that can determine whether changing lanes is advantageous under current conditions. This involves evaluating, for example, the actual driving conditions of a convoy FF. Specifically, it involves simulating corresponding driving conditions without lane changes for actual driving conditions with lane changes, or simulating corresponding driving conditions with lane changes for actual driving conditions without lane changes. Based on a comparison of actual driving conditions with and without lane changes with the simulated driving conditions, it is possible to deduce whether changing lanes is advantageous. The lane-changing algorithm trained based on these insights can be implemented in a real vehicle 10 and, in actual operation, can reliably estimate whether changing lanes is meaningful under current conditions.

[0076] In detail, a large amount of data about the actual driving of the fleet's FF is collected and evaluated in the backend 200. The evaluation results in whether changing lanes at a specific time point t during that driving period is advantageous, or whether it is better for the vehicle to stay in the current lane at that time point.

[0077] For each decision time point t, two variables are calculated and compared. Possible implementations are simulated in addition to actual driving conditions. This simulation is fed vehicle data, digital maps, dynamic traffic information, and / or environmental information. Examples of such input data include, but are not limited to, the spatial and temporal location, speed, and / or type of external vehicles; current lane, route, number of lanes, and road geometry in current and subsequent road segments; traffic information, hazard notices, and / or construction sites.

[0078] If the behavior of other vehicles is not present in the data, it can be predicted using modern micro-simulation. The behavior of the vehicle is recalculated and predicted based on the control software within the vehicle itself. In comparing the implementation of variant schemes at time point t, factors such as travel time differences, speed differences with other vehicles, distances to other vehicles, additional driver attention requirements, fuel / energy consumption, and differences in acceleration values ​​among all vehicles can be considered.

[0079] Using this prepared dataset, an ML model can be trained to calculate whether a lane change is desirable at the current or future time point based on the vehicle's current situation, including environmental models, location, and selected route. This model is then transferred to the fleet and run on the controllers within the vehicles.

[0080] Figure 3 A flowchart of a lane change assist method 300 according to an embodiment of the present invention is shown.

[0081] The lane change assist method 300 includes, in block 310, using a lane change algorithm trained with the methods described herein to determine whether a lane change should be performed given the vehicle’s current driving conditions; and in block 320, it includes outputting appropriate suggestions to the vehicle’s driver and / or performing automatic lane change when it is determined that a lane change should be performed.

[0082] In some implementations, probabilities can be calculated that illustrate the significance of the lane change. Alternatively or supplementarily, additional maneuvers, such as braking or acceleration, can be associated with the lane change. Alternatively or supplementarily, a lane change can be suggested to the driver, who must first agree to it. Alternatively or supplementarily, the method can be personalized by having the driver provide feedback after the lane change regarding whether it was considered positive or negative. This feedback can then be incorporated into the algorithm's training.

[0083] In an illustrative example, a Level 3 autonomous vehicle is traveling in autopilot mode at 130 km / h in the right lane on a two-lane highway. A convoy of trucks traveling at 80 km / h appears in front of the vehicle. There is heavy traffic, and the vehicle should exit the highway in two kilometers. It might be possible to save time by changing lanes, overtaking the trucks, and re-merging into them. However, the system, previously trained for similar situations, does not recommend overtaking because, in similar scenarios, high occupancy can prevent re-entering the right lane and thus miss the exit.

[0084] Figure 4 The illustration schematically shows a vehicle 10 having a driving assistance system 400 for autonomous driving according to an embodiment of the present invention.

[0085] The driver assistance system 400 includes a lane change assist or a function that enables lane change assist. Specifically, the driver assistance system 400 can use a lane change algorithm trained using the methods described in this document to determine whether a lane change should be performed given the current driving conditions of the vehicle 10. If it is determined that a lane change should be performed, the driver assistance system 400 can automatically perform the lane change.

[0086] In the automated driving system according to an embodiment of the present invention, lateral guidance (and optionally longitudinal guidance) of the vehicle 10 is performed automatically. Therefore, the driving assistance system 400 takes over vehicle guidance. For this purpose, the driving assistance system 400 controls the steering device 26 via an intermediate unit (not shown), and optionally controls the drive unit 20, the transmission 22, and the service brake 24.

[0087] To plan and execute autonomous driving, the driver assistance system 400 receives environmental information from an environmental sensor system that observes the vehicle's environment. Specifically, the vehicle 10 may include at least one environmental sensor 12 designed to record environmental data describing the vehicle's environment. The at least one environmental sensor 12 may, for example, include one or more laser ranging systems, one or more radar systems, one or more ultrasonic sensors, and / or one or more cameras.

[0088] In some embodiments, the driver assistance system 400 includes a control element for a direction indicator, wherein the control element may be designed to automatically perform a lane change when operated or triggered by the driver. Here, the control element may be a turn signal stalk and has multiple functions, namely activating the direction indicator and triggering a lane change. In other embodiments, the driver assistance system 400 may automatically perform a lane change without driver intervention.

[0089] However, embodiments of the present invention are not limited to autonomous driving. In an alternative embodiment, if the vehicle is driven manually, the driving assistance system may use at least one output device to output driving instructions related to lane changing. Driver instructions may provide the driver with guidance regarding lane changing, such as whether the lane change is possible, impossible, not dangerous, dangerous, advantageous, etc. If the lane changing algorithm determines that a lane change is appropriate or advantageous, the driving assistance system 400 may, for example, suggest a lane change.

[0090] At least one output device may include at least one display device and / or at least one speaker. The at least one display device may include a monitor, particularly an LCD monitor, a plasma monitor, or an OLED monitor. Alternatively or supplementarily, the at least one display device may include a projection device designed to display information directly in the driver's field of vision, particularly projecting information onto the windshield. In some embodiments, the at least one display device may be a central information output device for an infotainment system, such as a head unit or a pillar-to-pillar display. Preferably, the at least one output device is fixedly mounted in the vehicle.

[0091] While the invention has been described and explained in detail through preferred embodiments, it is not limited to the disclosed examples, and other variations can be derived by those skilled in the art without departing from the scope of protection of the invention. Therefore, it is clear that multiple variations are possible. It is also clear that the exemplary embodiments mentioned are merely examples and should not be construed in any way as limiting the scope of protection, application possibilities, or configuration of the invention. Rather, the foregoing description and accompanying drawings enable those skilled in the art to specifically implement the exemplary embodiments, wherein various variations can be made by those skilled in the art, such as variations concerning the function or arrangement of the various elements mentioned in the exemplary embodiments, without departing from the scope of protection defined by the claims and their legal counterparts, such as the further interpretations in the specification.

Claims

1. A method (100) for providing lane change assistance to a vehicle (10), comprising: Provide driving data of vehicles (10, FF) (110), wherein the driving data relates to a first driving situation of the vehicles (10, FF); Based on the driving data of the first driving situation, a simulation of the second driving situation is performed (120) to generate simulation data, wherein the first driving situation includes at least one lane change while the second driving situation does not include a lane change, or wherein the second driving situation includes at least one lane change while the first driving situation does not include a lane change; and The (130) lane change algorithm is trained based on the driving data and / or the simulation data.

2. The method (100) according to claim 1, wherein, Performing (120) the simulation of the second driving data includes determining the driving behavior of the vehicle and determining the driving behavior of at least one external vehicle.

3. The method (100) according to claim 1 or 2, further comprising: Perform a comparison between the first driving scenario and the second driving scenario; and The comparison is used to determine whether at least one lane change is advantageous or disadvantageous.

4. The method (100) according to claim 3, wherein, The comparison between the first driving scenario and the second driving scenario is performed based on at least one comparison criterion, wherein the at least one comparison criterion includes: - Travel time difference; and / or - Speed ​​difference with at least one external vehicle; and / or - Distance from at least one outside vehicle; and / or - Differences in driver attention; and / or - The energy consumption of the vehicles (10, FF); and / or - The acceleration behavior of the vehicle (10, FF) and / or at least one external vehicle.

5. The method (100) according to any one of claims 1 to 4, wherein, The driving data includes: - Location data of the vehicles (10, FF); and / or - Dynamic data of the vehicles (10, FF), especially speed data; and / or - Environmental data from the environmental sensor system of the vehicle (10, FF); and / or - The operating data of the vehicles (10, FF); and / or - Driving and maneuvering data of the vehicles (10, FF).

6. The method (100) according to any one of claims 1 to 5, wherein, Based on the driving data and additional data from the first driving scenario, a simulation of the second driving scenario is performed, wherein the additional data includes: - Digital map data; and / or - Information on visiting vehicles; and / or - Dynamic traffic information; and / or - Environmental information; and / or - Transportation infrastructure information.

7. The method (100) according to any one of claims 1 to 6, further comprising: Provide a trained lane-changing algorithm for a convoy (FF) consisting of multiple vehicles (10).

8. A lane change assist method (300) for a vehicle (10), comprising: In the case of using a lane-changing algorithm trained with the method (100) according to any one of claims 1 to 7, it is determined (310) whether a lane change should be performed in the current driving condition of the vehicle (10); and Output (320) a corresponding suggestion to the driver of the vehicle (10), and / or perform an automatic lane change when it is determined that a lane change should be performed.

9. The lane change assist method (300) according to claim 8, further comprising: At least one driving maneuver to be performed is determined based on whether the lane change should be performed under the current driving conditions of the vehicle (10), and in particular, the at least one driving maneuver to be performed involves a driving maneuver different from the lane change; and Output corresponding suggestions to the driver of the vehicle (10) regarding the at least one driving maneuver to be performed, and / or automatically perform the at least one driving maneuver to be performed.

10. A system (200, 400) comprising: One or more processors; and At least one memory, connected to one or more of the processors and containing instructions executable by one or more of the processors to implement the method (100) according to any one of claims 1 to 7 or the lane change assist method (300) according to claim 8 or 9.

Images