DE102019134499A1 - Method and device for determining the driving behavior of a vehicle within a platoon, as well as a vehicle with such a device - Google Patents

Abstract

A method for determining the driving behavior of a vehicle (LV, FV1, FV2) within a platoon (1) with at least one leading vehicle (LV) and at least one or more following vehicles (FV1, FV2) following the leading vehicle (LV), the leading vehicle (LV) and the following vehicles (FV1, FV2) move following a respective trajectory (L), comprises the following steps: Acquisition, by a processing device (30), of driving dynamics parameters of the vehicle (LV, FV1, FV2), which are a current Speed (vx) and a current acceleration (ax) of the vehicle include, detection, by the processing device (30), of vehicle data of the vehicle (LV, FV1, FV2), which a current engine speed (nMo) and data indicative of a currently inserted Have gear (G) of the transmission, and prediction, by the processing device (30), at least one shift operation of the vehicle (LV, FV1, FV2) in the future on the basis the detected driving dynamics parameters and vehicle data for determining a trajectory (L) of at least one of the vehicles (LV, FV1, FV2) of the platoon (1). This enables control objectives and properties of platooning with regard to comfort and safety to be adhered to better and also to adapt and optimize the trajectory.

Description

The present invention relates to a method and a device for determining a driving behavior of a vehicle within a platoon with at least one leading vehicle and at least one or more following vehicles following the leading vehicle, the leading vehicle and the following vehicles moving following a respective trajectory. In addition, the invention relates to a vehicle, in particular a utility vehicle, which has such a device or can at least be coupled to it.

A platoon of vehicles, such as commercial vehicles, typically consists of a leading vehicle driving ahead (also referred to as a "leading vehicle"), which specifies a longitudinal movement path, such as a speed profile and / or acceleration profile, and one or more, with a relatively small distance following vehicles (also referred to as “Following Vehicle” or “Follower” for short), whereby a following vehicle is based on the vehicle ahead. A platoon is therefore a convoy of vehicles with relatively short distances of, for example, approx. 10 meters, which is intended to achieve both fuel savings with a corresponding reduction in CO ₂ emissions and more efficient use of the traffic infrastructure with increased traffic safety . In so-called platooning, in which several vehicles can drive one behind the other at a very short distance with the help of a technical control system, highly developed technologies such as local wireless networks (so-called WLAN networks), radar and camera systems allow vehicles to be wirelessly networked with one another at short intervals drive. By using the driving information of the vehicle ahead in the platoon, the following vehicles can automatically accelerate, brake and / or steer.

A technical challenge is estimating your own trajectory or planning and following a desired trajectory. A trajectory generally designates a movement path or a part of a movement path along which the vehicle in question moves. It can be one or more dimensional. An estimated or real trajectory of a vehicle within the platoon can serve as additional information for following vehicles, with which they can better plan their own trajectory and thus, for example, better maintain distances.

Particularly during acceleration processes, however, shifting processes of the transmission, which result in a brief drive interruption of the vehicle, can result in relatively large deviations of the real trajectory from the estimated or desired trajectory of the vehicle. This results from the usually unknown shift logic of the transmission and from the fact that it is not known in advance when the next shift will occur. The vehicle's own control targets can therefore only be achieved with difficulty due to these unforeseeable deviations.

During a follow-up trip, such as in platooning, the information from the trajectory of the vehicle in front can be used to plan your own desired trajectory in order to set a desired follow-up behavior (e.g. constant distance, reduce follow-up errors, distance never below minimum distance, comfortable, chain-stable convoy behavior, etc. ). However, if the transmitted trajectory is not precise enough, as both vehicles travel their trajectories with too great deviations, the minimum distance may be fallen below, the distance may not be kept constant and / or reactions may introduce disruptive influences that have a negative effect on control objectives, comfort and safety .

In US 9 297 455 B2 describes a method for modifying a standard transmission shift schedule for a vehicle, which comprises monitoring current vehicle parameters and determining future lane information at a predetermined distance in front of the vehicle. Future vehicle parameters are predicted based on the determined future lane information. The default shift schedule for the transmission is changed based on the current vehicle parameters and the predicted future vehicle parameters.

In Byung-Kwan Shin et al .: "A Supervisor-Based Neural-Adaptive Shift Controller for Automatic Transmissions Considering Throttle Opening and Driving Load", KSME International Journal, Vol. 14, No. 4, pages 418-425, 2000, a supervisor based on a neural network for a vehicle switching control is presented, which takes into account the throttle valve opening, changes in the throttle valve opening and the driving load. To use the traffic load information, an observer-based traffic load estimation algorithm is proposed. A proportional-integral-derivative control together with an open loop control is used as a low level control for controlling the gear shifts, and a supervisory control for properly adjusting the shift control parameters of the low level shift control is designed using ANFIS.

The present invention is based on the object of specifying a method and a device for determining the driving behavior of a vehicle within a platoon of the type mentioned at the outset, which allow control objectives and properties of platooning to be better adhered to with regard to comfort and safety.

The invention relates to a method and a device for determining a driving behavior of a vehicle within a platoon according to the attached claims. Advantageous training and further developments are specified in the subclaims.

• Erfassen, durch eine Verarbeitungseinrichtung, von fahrdynamischen Parametern des Fahrzeugs, welche eine momentane Geschwindigkeit und eine momentane Beschleunigung des Fahrzeugs beinhalten,
• Erfassen, durch die Verarbeitungseinrichtung, von Fahrzeugdaten des Fahrzeugs, welche eine momentane Motordrehzahl und Daten bezeichnend für einen momentan eingelegten Gang des Getriebes aufweisen, und
• Prädiktion, durch die Verarbeitungseinrichtung, wenigstens eines Schaltvorgangs des Fahrzeugs in der Zukunft auf Grundlage der erfassten fahrdynamischen Parameter und Fahrzeugdaten zur Bestimmung einer Trajektorie wenigstens eines der Fahrzeuge des Platoons.

In particular, one aspect of the present invention relates to a method for determining a driving behavior of a vehicle within a platoon with at least one leading vehicle and several following vehicles following the leading vehicle, wherein the leading vehicle and the following vehicles move following a respective trajectory, and the vehicle has a motor and a vehicle having the engine coupled transmission for propelling the vehicle. The procedure consists of the following steps:

• Detection, by a processing device, of driving dynamics parameters of the vehicle, which include a current speed and a current acceleration of the vehicle,
• Detecting, by the processing device, vehicle data of the vehicle which have a current engine speed and data indicative of a currently engaged gear of the transmission, and
• Prediction, by the processing device, of at least one switching process of the vehicle in the future on the basis of the detected driving dynamics parameters and vehicle data to determine a trajectory of at least one of the vehicles in the platoon.

• Erfassen von fahrdynamischen Parametern des Fahrzeugs, welche eine momentane Geschwindigkeit und eine momentane Beschleunigung des Fahrzeugs beinhalten,
• Erfassen von Fahrzeugdaten des Fahrzeugs, welche eine momentane Motordrehzahl und Daten bezeichnend für einen momentan eingelegten Gang des Getriebes aufweisen, und
• zur Prädiktion wenigstens eines Schaltvorgangs des Fahrzeugs in der Zukunft auf Grundlage der erfassten fahrdynamischen Parameter und Fahrzeugdaten zur Bestimmung einer Trajektorie wenigstens eines der Fahrzeuge des Platoons.

Another aspect of the invention relates to a device for determining a driving behavior of a vehicle within a platoon with at least one lead vehicle and several follower vehicles following the lead vehicle, the lead vehicle and the follower vehicles moving following a respective trajectory, and the vehicle having an engine and one with the Motor-coupled transmission for driving the vehicle, wherein the device has a processing device which is configured to:

• Acquisition of driving dynamics parameters of the vehicle, which include a current speed and a current acceleration of the vehicle,
• Acquisition of vehicle data of the vehicle, which have a current engine speed and data indicative of a currently engaged gear of the transmission, and
• for the prediction of at least one switching process of the vehicle in the future on the basis of the recorded driving dynamics parameters and vehicle data for determining a trajectory of at least one of the vehicles in the platoon.

In addition, the invention relates to a vehicle, in particular a utility vehicle, which has such a device according to the invention or can at least be coupled to it for determining a switching process of the vehicle within the platoon.

The invention also relates to a computer program product or computer program with software code sections which are set up to carry out a method according to the invention when these are loaded into an internal memory of at least one processor device of the processing device.

With the invention, a driving behavior of a vehicle within a platoon, in particular a prediction of at least one shift in the future, can thus be determined in such a way that control objectives and properties of the platooning with regard to comfort and safety are better adhered to and also a trajectory of at least one of the vehicles of the Platoons can be adjusted and tweaked. In particular, by means of the method according to the invention, in particular by means of the processing device, a trajectory of at least one of the vehicles of the platoon can be determined on the basis of the prediction of the at least one shift operation in the future.

According to one embodiment of the invention, the prediction of at least one switching process in the future includes an estimate of the switching process in a predefined or dynamic time in the future. According to one embodiment, the prediction includes an estimate of whether a switching process will occur after the time.

According to one embodiment of the invention, the method also has the following steps: determining, by the processing device, a trajectory of the vehicle on the basis of the at least one predicted shifting process, and using, by the processing device, the determined trajectory and associated driving dynamics parameters and vehicle data of the Vehicle to predict at least one shift of the vehicle in the future.

According to one embodiment, the specific trajectory of the vehicle is used by means of a mapping of a transmission logic of the transmission in order to identify shift processes in the future.

According to one embodiment of the invention, the driving dynamics parameters of the vehicle can additionally include a requested engine torque. According to a further embodiment, the vehicle data of the vehicle can additionally include engine speed change, accelerator pedal angle of the vehicle (for example in the case of the lead vehicle), accelerator pedal travel of the vehicle (for example in the case of the lead vehicle), travel path gradient, steering wheel angle, brake pedal position and / or vehicle data from the past .

According to one embodiment, at least one output variable of the prediction contains one or more of the following information: direct gear, shifting or not shifting, holding gear, upshifting, downshifting. If, in particular, a previously calculated trajectory is examined for switching processes, the time itself after which this switching process occurs can also be used as the output variable.

According to one embodiment of the invention, the prediction uses a control method that includes an observer's system.

According to a further embodiment, the prediction uses a control method that includes a regression analysis.

The method according to the invention advantageously includes an optimization method for an artificial neural network. According to one embodiment, the neural network has one or more intermediate layers (so-called “hidden layers”) between an input layer (so-called “input layer”) and an output layer (so-called “output layer”). The driving dynamics parameters and vehicle data of the vehicle are used as inputs to the input layer. One or more outputs of the output layer contain information which is indicative of the prediction of the switching process in the future.

The various embodiments can be used alongside one another, for example as alternatives, or in any combination with one another.

According to one embodiment, the method for determining the prediction includes a gear shift model of the transmission, and optionally a vehicle model of the vehicle.

The prediction can be used by the processing device in connection with at least one vehicle component of one or more vehicles of the platoon, for example a drive of the relevant vehicle, in order to achieve at least one or more of the following control objectives: maintaining a distance between neighboring vehicles, maintaining a minimum distance between neighboring vehicles, support of the chain stability of the platoon, more comfortable driving behavior of one or more vehicles of the platoon by reducing acceleration and / or deceleration changes, and / or increasing the energy saving potential of one or more vehicles of the platoon.

All of the embodiments and method features described above and below can be implemented accordingly by means of suitable hardware and / or software in the processing device and / or in other components of the described device for determining a driving behavior of a vehicle within a platoon, so that the processing device (or another component ) is set up to perform the corresponding function. Thus, all advantageous embodiments of the method are also corresponding advantageous embodiments of the described device for determining driving behavior of a vehicle within a platoon.

The invention can moreover be applied equally to a manually shiftable transmission and an automatically shiftable transmission (automatic transmission) of a vehicle. With both types of transmission, a more or less significant drive interruption as a result of a manual or automatic shift from one gear to the next higher or lower gear can be detected, which leads to a deviation of the estimated trajectory from the real trajectory.

• 1 eine schematische Darstellung einer Fahrzeugkolonne mit einem Führungsfahrzeug und mehreren Folgefahrzeugen, die eine Platoonformation oder kurz einen Platoon bilden,
• 2A-C jeweilige Diagramme eines beispielhaften Verlaufs einer geschätzten und einer realen Trajektorie (2A), der zugehörigen Geschwindigkeit (2B) und Beschleunigung (2C) eines der Fahrzeuge des Platoons über eine bestimmte Zeitspanne,
• 3A-B jeweilige Diagramme eines weiteren beispielhaften Verlaufs einer geschätzten und einer realen Trajektorie (3A) und der zugehörigen Beschleunigung (3B) eines der Fahrzeuge des Platoons über eine bestimmte Zeitspanne,
• 4 ein schematisches Blockdiagramm eines Steuerungssystems zweier benachbarter Fahrzeuge FV1 und FV2 eines Platoons gemäß 1 und einen Signalverlauf innerhalb und zwischen den benachbarten Fahrzeugen mit einer Ausführungsform einer erfindungsgemäßen Einrichtung zur Bestimmung eines Fahrverhaltens eines der Fahrzeuge,
• 5-9 jeweilige schematische Darstellungen von Ausführungsformen eines zum Zwecke der Prädiktion wenigstens eines Schaltvorgangs eines Platoon-Fahrzeugs verwendeten Optimierungsverfahrens eines künstlichen neuronalen Netzes.

The invention is explained in more detail below with reference to the figures shown in the drawing. Show it:

• 1 a schematic representation of a column of vehicles with a lead vehicle and several following vehicles that form a platoon formation or, for short, a platoon,
• 2A-C respective diagrams of an exemplary course of an estimated and a real trajectory ( 2A) , the associated speed ( 2 B) and acceleration ( 2C ) one of the vehicles of the platoon over a certain period of time,
• 3A-B respective diagrams of a further exemplary course of an estimated and a real trajectory ( 3A) and the associated acceleration ( 3B) one of the platoon's vehicles for a certain period of time,
• 4th a schematic block diagram of a control system for two adjacent vehicles FV1 and FV2 according to a platoon 1 and a signal curve within and between the neighboring vehicles with an embodiment of a device according to the invention for determining a driving behavior of one of the vehicles,
• 5-9 respective schematic representations of embodiments of an optimization method of an artificial neural network used for the purpose of predicting at least one switching process of a platoon vehicle.

1 shows a schematic representation of a column of vehicles with a lead vehicle LV ("Leading Vehicle") and several FV ("Follow Vehicle") vehicles, here as an example FV1 and FV2 , etc. having a platoon 1 form. The vehicles LV , FV1 , FV2 etc. drive at a respective distance d to the vehicle in front, with the respective distances d the same, partly the same, or different between the vehicles. The vehicles move in a respective trajectory L. which can be the same, partly the same, or different depending on the point in time. In general, each of the vehicles in a platoon moves following a trajectory, with a following vehicle typically being sent data on the trajectory of the platoon participant traveling ahead. A trajectory generally designates a path or part of a path along which the vehicle in question moves. It can be one or more dimensional. A longitudinal trajectory, for example, generally designates a trajectory in the current direction of travel of the vehicle in question.

Each of the vehicles LV , FV1 , FV2 , etc. has a respective sensor system that allows the vehicle in the platoon 1 is movable. A front-side sensor system of the following vehicle can have, for example, at least one radar sensor and / or at least one camera sensor and / or possibly further suitable sensors with a downstream evaluation and computing unit to detect the relative deviation of the vehicle in front. In addition, there are many possibilities, such as measurement information with the aid of vehicle-to-vehicle communication between the vehicles LV , FV1 , FV2 , etc. can be exchanged.

Estimating your own trajectory is a technical challenge L. or planning and following a desired trajectory L. . In particular during acceleration processes, shift processes in the transmission of the respective vehicle result in more or less strong deviations of the real trajectory from the estimated or desired trajectory. Such deviations result from the usually unknown shift logic of the transmission and from the fact that it is not known in advance when the next shift is planned. Often times, your own control targets can only be achieved with difficulty during switching operations due to these unpredictable deviations.

During a follow-up trip, as in platooning, the information of the trajectory L. of the vehicle in front for planning your own desired trajectory L. can be used to set a desired follow-up behavior (e.g. constant distance, reduce follow-up errors, distance never below the minimum distance, comfortable, chain-stable column behavior, etc.). However, if the transmitted trajectory is not accurate enough, as both vehicles travel their trajectories with too great deviations, the minimum distance can be undershot, the distance cannot be kept constant and reactions can introduce disruptive influences that have a negative effect on control objectives, comfort and safety.

2A-C show respective diagrams of an exemplary course of an estimated and a real trajectory ( 2A in which a distance traveled s over time t is shown), the associated speed v ( 2 B) and acceleration a ( 2C ) one of the vehicles LV , FV1 , FV2 of the platoon 1 over a certain period of time t . What is illustrated here is an exemplary brief drive interruption at time t _g during the acceleration of one of the vehicles as a result of a shifting process of the transmission at time t _g , which is coupled to the drive motor of the vehicle. In 2 B is the resulting speed v , and in 2C the resulting acceleration a shown.

According to 2A a trajectory is estimated (estimated trajectory GT ). However, your may due to the shifting process of the transmission at the time daily and the resulting drive interruption are not followed, resulting in a real trajectory RT results. These give way at a certain point in time t about a deviation Δs ₉ from each other. The real speed differs accordingly v and acceleration a (solid lines in 2 B , 2C ) as a result of the switching process of the estimated speed and acceleration (dashed line) without switching process. For example, a trajectory of the vehicle LV estimated, gets the following vehicle FV1 the trajectory from the preceding one vehicle LV transmitted; however, it cannot be followed due to switching operations because the estimated trajectory GT of the vehicle FV1 from its real trajectory RT deviates.

The same applies to a further exemplary course of an estimated trajectory GT and a real trajectory RT according to 3A and the associated acceleration a according to 3B one of the vehicles LV , FV1 , FV2 of the platoon 1 over a certain period of time t as a result of a gear shifting process at time t _g . Here's the acceleration a not constant, but increases over time t to.

4th shows a schematic block diagram of a control system for two neighboring vehicles FV1 and FV2 of the platoon 1 according to 1 according to one embodiment of the invention. In 4th is also a schematic of a signal curve within and between the neighboring vehicles FV1 and FV2 and other vehicles of the platoon.

The vehicle FV1 contains a receiving circuit 11 which is used to acquire data V2V _LV from a vehicle in front LV transmitted trajectory is formed. The receiving circuit 11 is also used to acquire sensor data SD _{FV1 of} the own vehicle FV1 (Egofahrzeug) formed, such as data of a speed sensor, distance sensor and / or engine data such as engine speed, etc. of the vehicle FV1 . The one from the receiving circuit 11 recorded trajectory data V2V _LV and sensor data SD _FV1 are sent to a controller unit 12th transmitted, with the help of which, among other things, driving dynamics parameters and vehicle data of the vehicle FV1 are determinable. The controller unit 12th is with a dynamic system 13th coupled, via which, for example, at least one kinematic variable of the vehicle FV1 , such as speed or acceleration, is set or regulated. The dynamic system 13th can be composed of one or more individual systems and / or contain a chain of individual systems, such as engine control, engine and brake system of the vehicle FV1 . The vehicle also contains FV1 a vehicle-to-vehicle communication device 14th with which, for example, information regarding the distance to the vehicle in front LV , Speed, acceleration and other trajectory data V2V _{FV1 of} the vehicle FV1 to the following vehicle FV2 can be transmitted, which in turn, this information together with sensor data SD _{FV2 of} the vehicle FV2 via a receiving circuit 21 can capture.

The vehicle FV2 contains with the receiving circuit 21 , Controller unit 22nd , the dynamic system 23 and the vehicle-to-vehicle communication device 24 for the transmission of trajectory data V2V _{FV2 of} the vehicle FV2 Components that go to the components 11 to 14th of the vehicle FV1 are analogous and are therefore not repeated here in relation to the vehicle FV2 should be explained. The more similar the trajectories of the two vehicles FV1 and FV2 (and the lead vehicle LV ), the better the chain stability of the platoon, among other things 1 .

The vehicle FV2 has a processing device in the present exemplary embodiment 30th on. This can, for example, contain one or more data processing processors, such as one or more microprocessors with associated internal memories (not shown) of a known type. In another embodiment, the processing device 30th also be a distributed system which, for example, via a network, such as the Internet, connects several data processing processors to one another, some of which are in the vehicle FV2 and another part, stationary, for example, can be contained in a server computer (not shown) with which the vehicle FV2 communicated over the Internet. In this case is the vehicle-to-vehicle communication device 24 additionally equipped with a SIM card, for example, in order to establish an Internet connection via a telecommunications network. The processing device 30th , which will be explained in more detail below, completely outside the vehicle FV2 arranged, for example in a remote server computer (not shown) and / or in one of the other vehicles LV and FV1 be included. In this case the vehicle points FV2 at least one interface, for example in a central unit (head unit) or in the ECU (Electronic Control Unit) of the vehicle, which is set up, for example by means of suitable hardware and / or software with a processing device 30th to be paired wirelessly directly or via the Internet.

Overall, with regard to the arrangement and implementation of the processing device 30th various embodiments are conceivable.

The processing facility 30th is part of an institution 2 to determine a driving behavior of one or more of the vehicles LV , FV1 , FV2 within the platoon 1 , in the present embodiment of the vehicle FV2 . The processing facility 30th records dynamic driving parameters of the vehicle concerned (here FV2 ) whose driving behavior or gear changes are to be determined in the future. The recorded driving dynamics parameters include an instantaneous speed v _x and a current acceleration a _{x of} the vehicle FV2 . The driving dynamics Vehicle parameters FV2 can also add a requested engine torque of the vehicle FV2 include. The processing facility 30th In addition, it records vehicle data from the vehicle FV2 , which is a current engine speed n _Mon and data indicating a gear currently engaged G the transmission of the vehicle FV2 exhibit. The recorded vehicle data for the vehicle in question FV2 You can also change the engine speed n ° _MO , accelerator pedal angle of the vehicle (for example in the case of the lead vehicle), accelerator pedal travel of the vehicle (for example in the case of the lead vehicle), slope of the route on which the vehicle is traveling, steering wheel angle, brake pedal position and / or vehicle data from the past include. In particular, current values are recorded as driving dynamics parameters and vehicle data. The acquisition of instantaneous values essentially includes the acquisition of the corresponding variables in the present or in a time range around the present in order to predict at least one switching operation in the future.

The processing facility 30th is set up, as explained in more detail below, to calculate a prediction of at least one shift operation of the relevant vehicle in the future on the basis of the recorded driving dynamics parameters and recorded vehicle data by recording this data. The prediction is designed in such a way that it can be used to determine a trajectory L. at least one of the vehicles LV , FV1 , FV2 of the platoon 1 is usable.

The aim is to predict switching processes to improve a trajectory. In particular, the aim is to be able to determine in advance when in the future or whether a switching process will take place in the near future. A system with a human-driven vehicle poses a major challenge LV (so-called “SAE Level 0”) at the beginning of the platoon and highly automated follow-up vehicles FV (so-called “SAE Level 4”).

According to one embodiment, the trajectory L. of the lead vehicle LV (or one of the following vehicles FV1 , FV2 ) estimated by means of driving inputs and can be improved with the prediction of future gear changes. The improved estimated trajectory can serve as additional information for following vehicles with which they can better plan their own trajectory. Also in the following vehicles FV1 , FV2 (see. 4th ) one's own switching processes can be predicted, which can be used to improve one's own trajectory. These trajectories can in turn be made available to following vehicles.

An advantage of improving the estimate in the lead vehicle LV is based on the fact that its estimate is improved and it does not, contrary to its estimate, fall behind and thus the distance to the following vehicle FV1 gets smaller, which introduces a disruption to the entire platoon. A benefit of improving the estimate in the following vehicles FV1 , FV2 is based on the fact that the additional information from the lead vehicle LV upcoming deviations can be prevented and the prediction can identify upcoming deviations from switching processes and counteract them with an improved trajectory so that the own control goal is achieved.

• - Halten des Abstands zwischen benachbarten Fahrzeugen
• - Einhalten eines Mindestabstandes (Sicherheit)
• - Unterstützung der Kettenstabilität
• - Komfortableres Fahrverhalten durch weniger Beschleunigungs- und Verzögerungsänderungen
• - Energieeinsparungspotential

Overall, the following overarching control objectives can be better achieved:

• - Keeping the distance between neighboring vehicles
• - Maintaining a minimum distance (safety)
• - Support of chain stability
• - More comfortable driving behavior due to fewer changes in acceleration and deceleration
• - Energy saving potential

• - Fahrdynamische Größen (v, a), gegebenenfalls angefordertes Motormoment
• - Fahrzeugdaten (Motordrehzahl, Motordrehzahländerung, momentaner Gang, und/oder Gaspedalwinkel), und/oder Steigung (kann z.B. aus anderen Größen geschätzt werden)
• - Gegebenenfalls Lenkradwinkel, Bremspedal
• - Gegebenenfalls vergangene Größen

The following input variables are primarily used for the prediction:

• - Driving dynamics variables ( v , a ), possibly requested engine torque
• - Vehicle data (engine speed, change in engine speed, current gear, and / or accelerator pedal angle), and / or gradient (can be estimated from other variables, for example)
• - If applicable, steering wheel angle, brake pedal
• - Past sizes, if applicable

• - Direkter Gang
• - Schalten / kein Schalten
• - Gang halten / Hochschalten / Runterschalten

The output variables of the prediction can be:

• - Direct walk
• - Switching / no switching
• - Hold gear / upshift / downshift

• In einer ersten Variante, Nutzung einer Prädiktion (insbesondere eines Beobachters oder einer Regressionsanalyse) zur Schätzung eines Schaltvorgangs in einer vordefinierten (gegebenenfalls auch dynamischen) Zeit in der Zukunft (z.B. ΔTSchätzung = 0...2000ms): Schauen mit einer bestimmten Blickweite in die Zukunft und Schätzung, ob nach der Zeit erfahrungsgemäß ein Schaltvorgang auftritt.

An embodiment of a prediction is particularly conceivable in the following variants:

• In a first variant, use of a prediction (in particular an observer or a regression analysis) to estimate a switching process in a predefined (possibly also dynamic) time in the future (e.g. ΔTestimation = 0 ... 2000ms): look at the Future and estimation of whether, based on experience, a switching process will occur.

Correspondingly, according to one embodiment, the prediction uses a control method that includes an observer's system. In control engineering, an observer is a system known to those skilled in the art, which reconstructs non-measurable variables (states) from known input variables (e.g. manipulated variables) and output variables (measured variables) of an observed reference system. To do this, it simulates the observed reference system as a model and uses a controller to track the measurable state variables that are therefore comparable with the reference system.

According to another embodiment, the prediction uses a control method that includes regression analysis. A regression or regression analysis in control engineering is an analysis method known to the person skilled in the art, the aim of which is to model relationships between a dependent and one or more independent variables.

Another variant includes the use of the calculated trajectories and the associated driving dynamics and vehicle variables to check for upcoming gear changes. The existing knowledge about the future course is used and shifting processes are identified by means of a mapping of the manual transmission logic.

• - Neuronales Netz mit vielen Zwischenlagen HL („hidden layers“) (Variante 1) oder wenigen Zwischenlagen HL (Variante 2)
• - Eingänge der Eingabeschicht IL („input layer“) bilden oben genannte Größen
• - Ausgänge der Ausgabeschicht OL („output layer“) bilden oben genannte Größen

According to a preferred embodiment of the invention, the method includes an optimization method for an artificial neural network. In particular, a possible configuration using so-called Artificial Neural Networks (ANN) can take place as follows:

• - Neural network with many intermediate layers HL ("Hidden layers") (variant 1 ) or a few intermediate layers HL (Variant 2 )
• - Inputs of the input layer IL (“Input layer”) form the sizes mentioned above
• - Outputs of the output layer OIL (“Output layer”) form the sizes mentioned above

5 shows a schematic representation of a first embodiment of an optimization method of an artificial neural network used for the purpose of prediction. The KNN has one or more intermediate layers HL between an input layer IL and an output layer OIL on, being the inputs of the input layer IL the driving dynamics parameters v _x and a _x , and the vehicle data n _Mon , n ° _Mon and G can be used, and one or more outputs of the output layer OIL at the time of the forecast tp = xx ms contain information that is indicative of the prediction, here the direct gait designation 1 , 2 , ..., 15.

6th shows a schematic representation of a further embodiment in which one or more outputs of the output layer OIL contain information as to whether a shift is pending or whether the gear is being held.

7-9 show further analogous schematic representations of further embodiments of an ANN optimization method used for the purpose of prediction.

• Eingänge des KNN werden genutzt, um Schaltvorgänge in einer definierten Zeitspanne in der Zukunft (50-2000ms) zu identifizieren (Netz wird genau darauf trainiert).

The goals of using an ANN to predict a gear change in the following forms are:

• Inputs of the ANN are used to identify switching processes in a defined time span in the future (50-2000ms) (network is trained precisely on this).

Finally, the system knows whether or not there is a switching process at the prediction time tp = xx ms, and if so, in which direction ( 7th ).

In another variant according to 8th the ANN is used as a regression (image) of a gear shift diagram and learned accordingly. With the help of the planned trajectory, a shifting process can be identified in the future by keeping a gear, but examining the planned speed and acceleration profile for a shifting process.

Another approach is a variant that not only includes a gear shift model, but also a complete vehicle model that is likely to require more input and output variables and also needs a deep network with a recurrent component. 9 shows an ANN that has a (small) time step tp predicted. The outputs of this time step tp (t → t + 1) are used as input for the next step. Point of time t denotes the current acquisition time.

An embodiment is also conceivable in which a signal from the past can be present at the input of the ANN if it improves the prediction. In this case, the ANN would have to be designed as a recurrent network. In this way, an analysis and / or research can be carried out on switching strategies to determine the extent to which switching operations are dependent on previous states.

List of reference symbols

LV, FV1, FV2

vehicle

d

distance

L, GT, RT

Trajectory

t

time

v, vx

speed

a, ax

acceleration

s

path

Δs9

deviation

daily

time

tp

Prediction time

V2Vx

Trajectory data

SDx

Sensor data

nMo

Engine speed

n ° Mon

Engine speed change

G

engaged gear

IL

Input layer

OIL

Output layer

HL

Intermediate layer

1

Platoon

2

Facility

11.21

Receiving circuit

12, 22

Controller unit

13, 23

dynamic system

14, 24

Vehicle-to-vehicle communication device

30th

Processing facility

QUOTES INCLUDED IN THE DESCRIPTION

This list of the documents listed by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent literature cited

• US 9297455 B2 [0006]

Claims (15)

Method for determining the driving behavior of a vehicle (LV, FV1, FV2) within a platoon (1) with at least one lead vehicle (LV) and at least one or more following vehicles (FV1, FV2) following the lead vehicle (LV), whereby the lead vehicle ( LV) and the following vehicles (FV1, FV2) move following a respective trajectory (L), the vehicle (LV, FV1, FV2) having an engine and a gearbox coupled to the engine for driving the vehicle, with the following steps: detecting, by a processing device (30), of driving dynamics parameters of the vehicle (LV, FV1, FV2), which contain at least a current speed (v _x ) and a current acceleration (a _x ) of the vehicle, detection, by the processing device (30), of vehicle data of the vehicle (LV, FV1, FV2), which have a current engine speed (n _Mo ) and data indicative of a currently engaged gear (G) of the transmission, and prediction, by the processing device (30), at least one switching operation of the vehicle (LV, FV1, FV2) in the future on the basis of the detected driving dynamics parameters and vehicle data to determine a trajectory (L) of at least one of the vehicles (LV, FV1, FV2) of the platoon (1). Procedure according to Claim 1 , wherein the prediction of at least one shift in the future includes an estimate of the shift in a predefined or dynamic time in the future, in particular includes an estimate of whether a shift will occur after the time. Procedure according to Claim 1 or 2 , further comprising: determining, by the processing device (30), a trajectory (L) of the vehicle (LV, FV1, FV2) on the basis of the predicted at least one shifting process, and using, by the processing device (30), the determined trajectory (L ) and associated driving dynamics parameters and vehicle data of the vehicle (LV, FV1, FV2) for predicting at least one switching process of the vehicle (LV, FV1, FV2) in the future. Procedure according to Claim 3 , the specific trajectory (L) of the vehicle (LV, FV1, FV2) being used by means of a mapping of a transmission logic of the transmission in order to identify future shifts. Method according to one of the Claims 1 to 4th , wherein the driving dynamics parameters of the vehicle (LV, FV1, FV2) additionally include a requested engine torque and / or the vehicle data of the vehicle (LV, FV1, FV2) additionally include at least one or more of the following data: engine speed change, accelerator pedal angle of the vehicle, accelerator pedal travel of the vehicle, route gradient, steering wheel angle, brake pedal position, vehicle data from the past. Method according to one of the Claims 1 to 5 , wherein at least one output variable of the prediction contains one or more of the following information: direct gear, shifting or not shifting, holding gear, upshifting, downshifting, a time after which the shift occurs. Method according to one of the Claims 1 to 6th , wherein the prediction uses a control method involving an observer's system. Method according to one of the Claims 1 to 7th , wherein the prediction uses a control method that includes regression analysis. Method according to one of the Claims 1 to 8th , the method including an artificial neural network optimization method. Procedure according to Claim 9 , the neural network having one or more intermediate layers (HL) between an input layer (IL) and an output layer (OL), the dynamic driving parameters and vehicle data of the vehicle (LV, FV1, FV2) being used as inputs of the input layer (IL) and one or more outputs of the output layer (OL) contain information which is indicative of the prediction. Method according to one of the Claims 1 to 10 , wherein the method contains a gear shift model of the transmission, and optionally a vehicle model of the vehicle (LV, FV1, FV2), for determining the prediction. Method according to one of the Claims 1 to 11 , the prediction being used in connection with at least one vehicle component of one or more vehicles (LV, FV1, FV2) of the platoon (1) by the processing device (30) in order to achieve at least one or more of the following control objectives: maintaining a distance ( d) between neighboring vehicles (LV, FV1, FV2), maintaining a minimum distance between neighboring vehicles (LV, FV1, FV2), supporting the chain stability of the platoon (1), more comfortable driving behavior of one or more vehicles (LV, FV1, FV2) of the Platoons (1) by reducing changes in acceleration and / or deceleration, Increasing the energy saving potential of one or more vehicles (LV, FV1, FV2) of the platoon (1). Computer program product with software code sections which are set up to carry out a method according to one of the preceding claims when these are loaded into an internal memory of at least one processor device of the processing device (30). Device (2) for determining the driving behavior of a vehicle (LV, FV1, FV2) within a platoon (1) with at least one lead vehicle (LV) and several following vehicles (FV1, FV2) following the lead vehicle (LV), the lead vehicle ( LV) and the following vehicles (FV1, FV2) move following a respective trajectory (L), the vehicle (LV, FV1, FV2) having an engine and a gearbox coupled to the engine for driving the vehicle (LV, FV1, FV2) , wherein the device (2) has a processing device (30) which is set up for: detecting driving dynamics parameters of the vehicle (LV, FV1, FV2), which a current speed (v _x ) and a current acceleration (a _x ) of the Vehicle (LV, FV1, FV2) include acquisition of vehicle data of the vehicle (LV, FV1, FV2), which have a current engine speed (n _Mo ) and data indicative of a currently engaged gear (G) of the transmission, and to predict who At least one switching process of the vehicle (LV, FV1, FV2) in the future on the basis of the recorded driving dynamics parameters and vehicle data to determine a trajectory (L) of at least one of the vehicles (LV, FV1, FV2) of the platoon (1). Vehicle (LV, FV1, FV2), in particular commercial vehicle, which has a device (2) according to Claim 14 contains or has at least one interface which is set up with a device (2) according to Claim 14 to be coupled to determine a switching process of the vehicle (LV, FV1, FV2) within the platoon (1).

Images