WO2022090040A1

WO2022090040A1 - Method and device for controlling a vehicle along a journey trajectory

Info

Publication number: WO2022090040A1
Application number: PCT/EP2021/079153
Authority: WO
Inventors: Michael Fleps-Dezasse; Julian KING; Stephan Pollmeyer; Volker Wagner
Original assignee: Zf Friedrichshafen Ag
Priority date: 2020-10-29
Filing date: 2021-10-21
Publication date: 2022-05-05
Also published as: DE102020213615A1

Abstract

The present invention relates to a method (300) for controlling a vehicle (100) along a journey trajectory (110). The method (300) comprises a step of reading in (310) a journey trajectory (110), a journey parameter (x) and at least one operating parameter (xs) of at least one component (140) of the vehicle (100), wherein the journey trajectory (110) represents a path to a planned destination of a journey of the vehicle (100), the journey parameter (x) represents a physical variable during the journey of the vehicle (100) and the operating parameter (x_s) represents at least one physical variable or a value derived therefrom that reflects an operating point of the component (140) of the vehicle (100). The method (300) furthermore comprises a step of ascertaining (320) an operating point value (S), wherein the at least one operating parameter (x_s) is processed in an ascertainment algorithm (145). Finally, the method (300) comprises a step of determining (330) a control parameter (u) for actuating a driving actuator and/or the component (140) of the vehicle (100) using the journey trajectory (110), the journey parameter (x) and the operating point value (S) in order to actuate a journey of the vehicle (100) to the destination on the journey trajectory (110).

Description

Method and device for controlling a vehicle along a travel traiektor- rie

The present invention relates to a method and a device for controlling a vehicle along a travel trajectory according to the main claims.

High demands are placed on systems for driver assistance (ADAS = automated driving/automated steering) and automated driving (AD = automated driving) in terms of tracking accuracy, availability, safety, comfort, energy efficiency and other system properties. These properties should be ensured throughout the working range of the system. Systems for driver assistance (ADAS) and automated driving (AD) are often implemented in a modular architecture, which consists, for example, of a planning component and a control or implementation component. This architecture offers advantages when it comes to achieving the system goals of availability and safety and also enables a high level of flexibility and scalability of the systems to different vehicle configurations. However, the vehicle configuration should be known very precisely in the planning component in order to address the properties "comfort" and "energy efficiency" in particular, since these e.g. B. are closely connected to the available powertrain. This results in a high level of effort when applying the ADAS or AD system to a specific vehicle, since both the implementation and the planning component would have to be explicitly tailored to the vehicle to be considered and cannot be universally used or programmed.

Against this background, the present invention creates an improved method and an improved device for controlling a vehicle along a travel trajectory according to the main claims. Advantageous configurations result from the dependent claims and the following description.

The approach presented here creates a method for controlling a vehicle along a travel trajectory, the method having the following steps: Reading in a travel trajectory to be traveled by the vehicle, a travel parameter and at least one operating parameter of at least one component of the vehicle, the travel trajectory representing a route to a planned destination of a journey of the vehicle, the travel parameter representing a physical variable during the journey of the vehicle and the operating parameter representing at least represents a physical quantity or a value derived therefrom, which maps an operating point of the component of the vehicle;

determining an operating point value from the operating parameter, the at least one operating parameter being processed in a determination algorithm; and

Determining a control parameter for controlling a driving actuator of the vehicle using the driving trajectory, the driving parameter and the operating point value in order to control a driving of the vehicle to the destination along the driving trajectory.

A travel trajectory can be understood, for example, as information about location coordinates that the vehicle should reach in the immediate future when driving. In the present case, a vehicle can be understood to mean, for example, a passenger car, but also a truck, a bus, a motorcycle or another motor vehicle driving freely on a roadway. A travel parameter can be understood, for example, as a physical quantity describing the travel of the vehicle, for example a speed, a yaw rate, an acceleration or the like. A component of the vehicle can be understood, for example, as a component required for the drive or the steering, for example an engine, transmission or a steering system. However, the component of the vehicle can be understood to mean another element such as an energy store. An operating parameter of such a component of the vehicle can be understood, for example, as a temperature, a voltage, a speed or the like, in particular which can change during the operation of the vehicle while driving. In the present case, an operating point value can be understood to mean a variable that can be obtained or derived from the operating parameter using a determination algorithm. The operating parameter can also be in the form of a time series of values that form the physical quantity of the component of the vehicle at different points in time. In the present case, a determination algorithm can be understood to mean an algorithm that can determine the operating point value, taking into account the information from the operating parameter. For this purpose, for example, the determination algorithm can link values of the operating parameter detected at different points in time with one another and/or with other variables in order to optimize a target function, for example. Such a target function can be, for example, a function that achieves the highest possible energy efficiency when driving the vehicle (e.g. fuel consumption while the vehicle is driving as possible) and/or maximizes comfort for a user of the vehicle (e.g. a rolling of the vehicle on the Travel along the travel trajectory minimized as much as possible). A driving actuator can be understood, for example, as an element that influences or controls the guidance of the vehicle along the driving trajectory. For example, a driving actuator can be a drive motor of the vehicle, a steering motor, a braking system or the like, which enables or implements guidance of the vehicle along the driving trajectory.

The approach proposed here is based on the knowledge that by determining the operating point value before and independently or decoupled from the determination of the control parameter for controlling the driving actuator of the vehicle, a significant reduction in the numerical and/or circuitry complexity for determining this control parameter is possible. It is therefore no longer necessary to take into account a large number of combinations of different operating point values of the vehicle when determining the control parameter for controlling the driving actuator. Rather, in the determination step, using the determination algorithm, a "pre-optimization" can take place, in which the corresponding operating point value is determined from the operating parameter, taking into account vehicle and/or journey-specific conditions, which is then used in the journey trajectory planning or a trajectory conversion or -Regulation can only be considered as a simple parameter with correspondingly little effort for determining the control parameter. An embodiment of the approach proposed here is advantageous in which a scalar operating point value is determined in the determination step. Such an embodiment offers the advantage of being able to use very compact information in the form of a scalar for the operating point value when determining the control parameter. A significant reduction in the complexity of determining the control parameter can thus also be achieved.

An embodiment of the approach proposed here can be implemented in a technically very elegant manner and with methods that are already mature, in which, in the step of determining the operating point value, a determination algorithm based on a neural network, an algorithm with artificial intelligence, an algorithm of the monitored and/or or reinforcement learning, a function approximation method, an algorithm for finding a value from a look-up table, a heuristic algorithm and/or a predictive control model. Such an embodiment offers the advantage of also determining the operating point value reliably and precisely or quickly when a number of different operating parameters or vehicle parameters or corresponding parameters have to be taken into account at different points in time for the optimization of driving behavior.

According to an advantageous embodiment of the approach proposed here, a value can be read in as an operating parameter in the reading step, which at least includes a speed, a switching state of the component of the vehicle, a temperature, a state of charge, a force acting on a vehicle element, a moment or one of represents at least one parameter derived from these values. In the present case, a speed can be understood to mean, for example, a speed of the vehicle. A shift state can be understood, for example, as an engaged gear of a transmission. A temperature can represent, for example, a temperature of a drive motor, a brake unit or an energy store, with a state of charge also being understood as a variable, for example in relation to an energy store such as a battery of the vehicle. A force or moment acting on a vehicle element can, for example, have a Wheels of the vehicle acting force or a moment acting on one of these elements are understood. Such an embodiment of the approach proposed here offers the advantage that such operating parameters in particular provide important information about the driving behavior of the vehicle, for example also in relation to an optimization problem such as an energy-efficient or comfortable driving style. Taking into account such an operating parameter or an operating point value derived therefrom thus enables the vehicle's travel to be optimized on a desired travel trajectory.

Another particularly favorable embodiment of the approach proposed here is one in which a time series is read in as the operating parameter in the reading step, the elements of which represent the at least one physical variable or the value of the vehicle component derived from the at least one physical variable at different points in time. Such an embodiment offers the advantage that a variation of the operating parameter over time can be taken into account when determining the (also current) operating point value, so that an effect of the change in the operating point value can be recognized and, for example, the operating point value can be adjusted according to a desired target function or a desired optimization problem .

Also conceivable is an embodiment of the approach proposed here in which, in the step of determining, the operating point value is determined using a cost function to minimize energy required for the journey or a cost function to increase the comfort of a vehicle occupant. Such an embodiment offers the advantage of increasing the acceptance of the approach proposed here by a user of the vehicle and at the same time, for example, of avoiding unnecessary pollution of the environment through emissions.

Another particularly advantageous embodiment of the approach proposed here is one in which, in the reading step, a course of location coordinates is read in as a journey trajectory, which when the vehicle is traveling within a maximum of ten driving times, in particular within a maximum driving time of one minute and/or during a journey of the vehicle within a distance of is reached at most 1000 meters, in particular within a distance of at most 100 meters and/or wherein topography information about a route to be traveled by the vehicle is also read in as a travel trajectory. Such an embodiment offers the advantage of enabling the driving behavior of the vehicle to be optimized specifically for the route section to be traveled immediately afterwards. For example, such an optimization can be implemented by early activation of the motor to accelerate from the incline or a timely reduction of a drive torque before a traffic light system switched to "stop", so that on the one hand there is as little or as abrupt a change in the vehicle movements as possible and on the other hand a high energy efficiency of the driving style of the vehicle can be reached.

According to a further embodiment of the approach proposed here, a control parameter for controlling a drive motor, a braking element and/or a steering actuator can also be determined in the step of determining, in particular in order to automatically control the vehicle. Such an embodiment offers the advantage of being able to control at least one central vehicle control element using the control parameter and thereby being able to quickly and reliably realize the aforementioned advantages.

According to a particularly favorable embodiment of the approach proposed here, the steps of the method can be carried out repeatedly, in particular with the determination algorithm being changed in the repeatedly carried out step of determining using operating parameters read in the step of reading in and operating parameters read in in the repeatedly carried out step of reading in being carried out. Such an embodiment of the approach proposed here offers the advantage that by repeatedly executing the steps of the method, the determination algorithm can be trained in order to be able to determine a control parameter as quickly and efficiently as possible, which also corresponds to the one in the cost function or the underlying optimization problem as well as possible. Also conceivable is an embodiment of the approach proposed here, in which at least one second operating parameter of at least one other component of the vehicle is read in the reading step, with the second operating parameter representing at least one physical variable or a value derived therefrom, which represents an operating point of the other component of the vehicle and wherein in the determination step at least the second operating parameter is processed in the determination algorithm in order to determine the operating point value. By determining the operating point value using the second operating parameter, which also represents a physical variable or a value derived therefrom, the determination algorithm can be used very flexibly to solve an optimization problem based on a number of operating parameters. In turn, it is advantageous that the operating point value can be determined independently and/or before the determination of the control parameter for controlling the component of the vehicle, so that the complexity of this determination of the control parameter can be reduced numerically and/or in terms of circuitry and thus accelerated.

Another favorable embodiment of the approach proposed here is one in which at least one dynamics parameter is also read in the reading step, which represents a driving dynamics limit state of at least one component of the vehicle, with the at least one dynamics parameter being processed in a dynamics algorithm in the determining step in order to to obtain a dynamic value and wherein in the step of determining the control parameters are determined using the dynamic value. Such a dynamics parameter can be understood, for example, as a driving dynamics limit that the vehicle must not exceed without getting into an uncontrollable driving state. For example, such a dynamic parameter can represent a maximum static friction of a tire on the road, which must be taken into account when controlling the components of the vehicle. The use of such a dynamic algorithm in parallel or in addition to the determination algorithm and the consideration of the dynamic value determined by the dynamic algorithm when determining the control parameter can also reduce the numerical and/or circuit complexity when determining this control parameter can be achieved, so that this determination of the control parameter can run faster and thus less critical in terms of time.

Embodiments of this method can be implemented, for example, in software or hardware or in a mixed form of software and hardware, for example in a control device or a device.

The approach presented here also creates a device that is designed to carry out, control or implement the steps of a variant of a method presented here in corresponding devices. The object on which the invention is based can also be achieved quickly and efficiently by this embodiment variant of the invention in the form of a device.

A device can be an electrical device that processes electrical signals, for example sensor signals, and outputs control signals as a function thereof. The device can have one or more suitable interfaces, which can be designed in terms of hardware and/or software. In the case of a hardware design, the interfaces can be part of an integrated circuit, for example, in which the functions of the device are implemented. The interfaces can also be separate integrated circuits or at least partially consist of discrete components. In the case of a software design, the interfaces can be software modules which are present, for example, on a microcontroller alongside other software modules.

A computer program product with program code, which can be stored on a machine-readable medium such as a semiconductor memory, a hard disk memory or an optical memory and is used to carry out the method according to one of the embodiments described above, is also advantageous if the program is on a computer or a device is performed.

The invention is explained in more detail by way of example with reference to the attached drawings.

Show it: 1 shows a block diagram of a vehicle with an exemplary embodiment of a device for controlling a vehicle along a travel trajectory;

FIG. 2 shows a block diagram of a vehicle with a further exemplary embodiment of a device for controlling a vehicle along a travel trajectory; FIG. and

3 shows a flowchart of an exemplary embodiment of a method for controlling a vehicle along a travel trajectory.

In the following description of favorable exemplary embodiments of the present invention, the same or similar reference symbols are used for the elements which are shown in the various figures and have a similar effect, with a repeated description of these elements being dispensed with.

The exemplary embodiments described and shown in the figures are only selected as examples. Different exemplary embodiments can be combined with one another completely or in relation to individual features. An exemplary embodiment can also be supplemented by features of a further exemplary embodiment.

1 shows a block diagram of a vehicle 100 with an exemplary embodiment of a device 105 for controlling the vehicle 100 in a travel trajectory 110. The travel trajectory 110 is formed here by a sequence of location coordinates 115 that the vehicle 100 is to travel or reach in the future. Favorably, these location coordinates 110 are directly in front of the vehicle 100, so that the driving style in the immediate future should be specifically controlled by the device 100. The planning of a travel trajectory 110 over a distance of several hundred kilometers, for example, takes a back seat here.

In order to achieve the advantages mentioned above, the device 105 has a read-in interface 120 , a determination unit 125 and a determination unit 130 . The read-in interface 120 is formed, for example, from a memory (not shown in Figure 1) or a planning unit (such as for example a satellite-supported navigation system) to determine a travel trajectory 110, which is read in as trajectory data O together with, for example, further environmental data characterizing a roadway 135. In addition, read-in interface 120 is designed to read in at least one travel parameter x and at least one operating parameter _xs , where travel parameter x represents, for example, a physical variable while vehicle 100 is moving and the operating parameter represents a physical variable or a value derived therefrom that represents a Operating point of a component 140 of the vehicle depicts. The travel parameter can represent, for example, a speed, a torque or a current energy consumption of a drive motor as component 140 of vehicle 100 . The operating parameter x _s can represent, for example, a temperature of the drive motor as component 140, a state of charge and/or a temperature of an energy store (not explicitly shown in Figure 1) (for example in the form of an accumulator) as component 140 of vehicle 100 or the like , it being possible for the operating parameter Xs to change while the vehicle 100 is being driven and, for example, to also influence other variables such as fuel consumption.

In the determination unit 125 (which can also be referred to below synonymously with the terms "Value Dealer" or "Critic"), an operating point value S is now determined using a determination algorithm 145 from the operating parameter x _s according to the procedure explained in more detail below and the determination unit 130 fed. In determination unit 130, using trajectory data O representing travel trajectory 110, travel parameter x, and operating point value S, a control parameter u is determined, which is provided for controlling a driving actuator 155 of vehicle 100, which is used here, for example, as a drive motor for driving wheels 150 of the vehicle 100, a braking unit, a steering unit or the like is configured.

Driving actuator 155 can, for example, also be component 140 of the vehicle itself, for example if driving actuator 155 is configured as an internal combustion engine and operating parameter x _s represents a temperature of component 140 of the vehicle, here driving actuator 155 . It is also conceivable that the operating parameter x _s can be used as a time series of several different ones Physical quantities recorded at points in time is read in, so that information about the development over time or the course over time of this operating parameter x _s is available in determination algorithm 145 and a necessary change in operating point value S can be recognized as a result, in order to achieve a specific goal, for example, which is an underlying represents an optimization problem and/or is in the form of a cost function or objective function.

According to the exemplary embodiment illustrated in FIG. 1, two separate modules are provided in the determination unit 130, with a trajectory planning module 160 for calculating a target trajectory P from the trajectory data O, the operating point value S and the travel parameter x and as a first module second module, a trajectory control module 165 is provided, in which a specific determination of the control parameter u for controlling the driving actuator 155 takes place, so for example the direct control of the power supply for the drive motor or a steering actuator as a driving actuator 155. The trajectory planning module! 160 thus takes over, for example, the fine control of the trajectory data O present, for example, as navigation data in a specific, direct actuator control, whereas the trajectory control module, for example, implements the physical control of the driving actuator 155 .

For the approach presented here, a particular advantage is recognized for the development and application of ADAS and AD systems in that the effort required for a planning module 160 of a target trajectory P can be significantly reduced and the overall system performance of the vehicle control can be increased if an abstraction of system properties such as energy efficiency and comfort could be achieved. Unlike the driving dynamics limits, the system properties such as energy efficiency and comfort cannot be described using "constraints" (i.e. secondary conditions), i.e. an envelope for the system states, as is done below by considering a dynamic parameter using a dynamic algorithm when determining a dynamic value is provided because energy efficiency cannot be achieved uniformly over a specific operating range, but is linked to at least one specific operating point. These operating points are strongly dependent on the vehicle configuration, Internal combustion engine, transmission, electric motor, hybrid, etc. as components 140 dependent. These dependencies are usually taken into account directly in the planning module 160 (e.g. via corresponding characteristic diagrams) in order to B. to calculate an energy-efficient (target) trajectory P, which calculates the optimal curves in terms of gear, power distribution between the internal combustion engine and electric motor and vehicle speed, etc. However, this means that all vehicle configurations are mapped in trajectory planning module 160, which means that the variety of variants increases significantly and the development effort and development time are lengthened, but also in actual vehicle operation a reaction time and the required numerical and/or circuitry effort is sometimes significantly increased.

The problem described above with regard to the lack of abstraction of system properties such as comfort and energy efficiency can be solved by an adaptation and extension in the form of a separate determination unit 125, such a determination unit 125, for example, with a determination algorithm 145 in the form of, for example, methods of reinforcement Learnings can be implemented. As a solution, the determination unit 125 is proposed as a new component, which can also be referred to as a “value trader”. As shown in FIG. 1, the value handler 125 calculates the operating point value S, which can also be synonymously referred to as a state value function, and provides this operating point value S to the trajectory planning module 160 . The planning component 160 can calculate the optimal trajectory as a target trajectory P based on this state value function S, without knowing the vehicle configuration, that is to say concrete forms of the operating parameters x _s . The architecture of trajectory planning module 160 and value handler 125 is methodically derived from the actor-critic method of reinforcement learning. The value handler 125 or critical calculates the value of these vehicle and environmental states in the form of the operating point value S from selected vehicle and environmental states x _s and provides this value S to the trajectory planning module 160, which can also be referred to as an actor. The trajectory planning module 160 then calculates the optimal (target) trajectory P on the basis of the state value function and makes this available to a conversion component such as the trajectory conversion module 165 . The proceedings, which can be used for the calculation and approximation of the state-value function S are diverse, for example, neural networks in connection with supervised learning or reinforcement learning can be named as the most obvious realizations for the implementation of the determination algorithm 145 . However, other function approximation methods are also conceivable. Reinforcement learning can also be used as a trajectory planning method. However, any optimization method can also be used for the state-value function S or the determination algorithm 145 on which it is based. B. Model Predictive Control. For this purpose, the inverse of the state value function can be included in the cost function of the optimization.

The energy-efficient driving strategy for a conventional drive train is considered below as a greatly simplified example. In this case, the statuses or operating parameters x _s for determining the state-value function S would be e.g. B. vehicle speed, acceleration and gear. Optimization goal and thus value is, for example, fuel consumption. In this case, the state value function or the operating point value S represents a generalized fuel consumption, which results from the current fuel consumption and the fuel consumption to be expected in the future. The two components can be weighted using a parameter in the form of the operating point value S. The consideration of the consumption to be expected in the future can be used to smooth the state value function or the operating point value S and to take into account other dependencies of the fuel consumption, such as e.g. B. an increase (or reduction) in consumption due to an increase in engine temperature as the operating parameter Xs. The state value function or the operating point value S consequently also guides the actor or the trajectory planning module 160 in such a way that the motor as the driving actuator 155 or component 140 is not brought into a highly unfavorable temperature range in the long term.

In this example, the algorithm which determines the driving strategy would correspond to the determination algorithm 145 in the determination unit 125, which is also referred to as an actor. Any method that uses the state-value function or the operating parameter(s) x _s can evaluate, e.g. B. correspondingly suitable optimization methods, KI methods (KI = artificial intelligence) such as reinforcement learning (engl. = reinforcing learning) but also heuristic methods or search methods. In the simplest case, where the driving strategy only provides a driver with the optimal gear as a control parameter, the driving strategy could consist of a method that evaluates the state value function with the current values of the states and for each gear and then the gear with the best value forwarded to the driver as a default.

Fig. 2 shows a block diagram of a vehicle 100 with a further embodiment of a device 105 for controlling a vehicle 105 in a travel trajectory 110. The device 105 corresponds to the device shown in FIG Dynamics algorithm 200 for processing a dynamics parameter XD read in by read-in interface 120, for example from a memory 210, is read in as a dynamics value D, with the dynamics parameter XD indicating a driving-dynamics limit state of at least one of the vehicle-specific components of vehicle 100 (such as, for example, a static friction value of the tires or wheels currently in use 150 of the vehicle 100). The control parameter u is determined in the determination unit 130 using the dynamic value D. FIG. The dynamic algorithm 200 can, for example, be designed or implemented analogously to the determination algorithm 160, that is, for example, also implemented as an algorithm with an artificial intelligence, as an algorithm with reinforcing learning properties or as a neural network.

With regard to the driving dynamics limits of the vehicle, there are also concepts for introducing an abstraction between the planning component, such as the trajectory planning module 160 here, and the vehicle 100 or an implementation component or the driving actuator 155 . A dynamic algorithm is used in determination unit 125, for example, which can also be referred to as a "constraint dealer" and which provides trajectory planning module 160 of determination unit 130 with an abstract description of the driving dynamics limits in the form of dynamic value D, so that the trajectory planning module 160 not with the vehicle configuration and z. B. needs to deal with the tires.

The proposed "Value Dealer" or the implementation of the determination algorithm 145 can be seamlessly combined with the already known "Constraint Dealer" as a dynamic algorithm 200, so that the trajectory planning module 160 as a planner/actor can see both the envelope of the states and their derivation as the value of the states can also be provided, as shown in FIG.

According to one exemplary embodiment, an ADAS/AD architecture with a value function can also be implemented with the following devices, as described in more detail above.

- At least one actuator z. B. of the type steering, drive, brake to influence the driving condition as driving actuator 155;

- At least one control device for calculating and converting the input variables of the actuators as the determining unit

- at least one algorithm for calculating the input variables of the actuators (trajectory conversion module 165) and

- At least one algorithm for calculating the target trajectory P der

trajectory conversion (trajectory planning module 160);

- At least one algorithm for calculating the state-value function S for abstracting the desired system property, such as comfort or energy efficiency (value handler) as the determination algorithm 145 in the determination unit 125;

- At least one read-in interface 120 to a sensor for detecting the environment, vehicle and/or driving condition O, x and x _s , or at least one communication device for receiving information about the environment, vehicle and/or driving condition.

FIG. 3 shows a flowchart of an exemplary embodiment of a method 300 for controlling a vehicle along a travel trajectory. The method 300 includes a step 310 of reading in a travel trajectory to be traveled by the vehicle, a travel parameter and at least one operating parameter at least one component of the vehicle, with the travel trajectory representing a route to a planned destination of a journey of the vehicle, the travel parameter representing a physical quantity during the journey of the vehicle and the operating parameter representing at least one physical quantity or a value derived therefrom, which represents an operating point of the Component of the vehicle depicts. Furthermore, the method 300 includes a step 320 of determining an operating point value operating parameter, wherein the at least one operating parameter is processed in a determination algorithm. Finally, the method 300 includes a step 330 of determining a control parameter for controlling a driving actuator and/or the component of the vehicle using the driving trajectory, the driving parameter and the operating point value in order to control a journey of the vehicle in the driving trajectory to the destination.

Furthermore, the method steps presented here can be repeated and carried out in a different order than the one described.

If an embodiment includes an "and/or" link between a first feature and a second feature, this can be read in such a way that the embodiment according to one embodiment includes both the first feature and the second feature and according to a further embodiment either only the first Feature or has only the second feature.

reference sign

100 vehicle

105 Device for controlling a vehicle along a travel trajectory

110 travel trajectory

115 location coordinates of the travel trajectory

120 read-in interface

125 investigation unit

130 determination unit

135 lane

140 component of the vehicle

145 Discovery Algorithm

150 wheels, tires

160 trajectory planning module

165 trajectory conversion module

O trajectory data x travel parameters

X's operating parameters

S operating point value

P time trajectory u control parameters

200 dynamics algorithm

210 memory

XD dynamic parameters

D Dynamic value

300 method for controlling a vehicle along a travel trajectory

310 step of reading

320 step of discovering

330 step of determining

Claims

patent claims

1. Method (300) for controlling a vehicle (100) along a travel trajectory (110), the method (300) having the following steps:

Reading in (310) a travel trajectory (110) to be traveled by the vehicle (100), a travel parameter (x) and at least one operating parameter (x _s ) of at least one component (140) of the vehicle (100), the travel trajectory (110) having a path to a planned destination of a journey of the vehicle (100), the journey parameter (x) represents a physical quantity during the journey of the vehicle (100) and the operating parameter (x _s ) represents at least one physical quantity or a value derived therefrom, which represents a operating point of the component (140) of the vehicle (100);

determining (320) an operating point value (S) from the operating parameter (x _s ), the at least one operating parameter (x _s ) being processed in a determination algorithm (145); and

Determining (330) a control parameter (u) for controlling a driving actuator and/or the component (140) of the vehicle (100) using the driving trajectory (110), the driving parameter (x) and the operating point value (S) in order to start driving the To control the vehicle (100) in the travel trajectory (110) to the destination.

2. Method (300) according to claim 1, characterized in that a scalar operating point value (S) is determined in the step of determining (320).

3. The method (300) according to any one of the preceding claims, characterized in that in step (320) of determining the operating point value (S) using a determination algorithm (145) on the basis of a neural network, an algorithm with an artificial intelligence, one Algorithm of supervised and/or reinforcement learning, a function approximation method, an algorithm for finding a value from a look-up table, a heuristic algorithm and/or a model of a predictive control is determined.

4. The method (300) according to any one of the preceding claims, characterized in that in step (310) of reading in, a value is read in as the operating parameter (x _s ) which contains at least a speed, a switching state of the component (140) of the vehicle (100 ), a temperature, a state of charge, a force acting on a vehicle element (150), a moment or a parameter derived from at least one of these values.

5. The method (300) according to any one of the preceding claims, characterized in that in the step of reading (310) s as the operating parameter (x _s ) a time series is read, the elements of which are at least one physical variable or derived from the at least one physical variable Value of the component (140) of the vehicle (100) represented at different times.

6. The method (300) according to any one of the preceding claims, characterized in that in the step of determining (320) s the operating point value (S) using a cost function to minimize energy to be expended for the journey or a cost function to increase comfort of a vehicle occupant is determined.

7. The method (300) according to any one of the preceding claims, characterized in that in the step (310) of reading in as a travel trajectory (110) a course of location coordinates (115) is read in, which during a journey of the vehicle (100) within at most ten minute travel time, in particular within a maximum travel time of one minute and/or which is achieved when the vehicle (100) travels within a maximum distance of 1000 meters, in particular within a maximum distance of 100 meters and/or where the travel trajectory (110 ) furthermore, topography information about a route to be traveled by the vehicle (100) is read in.

8. The method (300) according to any one of the preceding claims, characterized in that in step (330) of determining a control parameter (u) for controlling a drive motor, a braking element and / or a Steering actuator is determined as a driving actuator (155), in particular to automatically control the vehicle (100).

9. The method (300) according to any one of the preceding claims, characterized in that the steps (310, 320, 330) of the method (300) are carried out repeatedly, in particular wherein in the repeatedly carried out step (320) of determining a change in the determination algorithm ( 145) using the operating parameter (x _s ) read in in the step (310) of reading in and the operating parameter (x _s ) read in in the repeatedly executed step (310) of reading in.

10. The method (300) according to any one of the preceding claims, characterized in that in the step (310) of reading in at least one second operating parameter of at least one further component of the vehicle (100) is read in, the second operating parameter being at least one physical variable or one thereof derived value representing an operating point of the further component of the vehicle (100) and wherein in step (320) of determining at least the second operating parameter is processed in the determination algorithm (145) in order to determine the operating point value (S).

11 . Method (300) according to one of the preceding claims, characterized in that in step (310) of reading in, at least one dynamics parameter (XD) is also read in, which represents a driving dynamics limit state of at least one of the components (150) of the vehicle (100), wherein in step (320) of determining the at least one dynamics parameter (XD) is processed in a dynamics algorithm (200) in order to obtain a dynamics value (D) and wherein in step (330) of determining the control parameters (u) using the dynamics value ( D) is determined.

12. Device (105) that is set up to execute and/or control the steps (310, 320, 330) of the method (300) according to one of the preceding claims in corresponding units (120, 125, 130).

13. Computer program that is set up to execute and/or control the steps (310, 320, 330) of the method (300) according to one of the preceding claims.

14. Machine-readable storage medium on which the computer program according to claim 13 is stored.

21