SITUATION-ADAPTED ACTUATION FOR DRIVER ASSISTANCE SYSTEMS AND SYSTEMS FOR THE AT LEAST PARTIALLY AUTOMATED CONTROL OF VEHICLES

Abstract

A method for generating an actuation signal for a driver assistance system and/or a system for the at least partially automated control of a vehicle. In the method, suggestions are made available for trajectories to be traveled by the vehicle and/or for other actions to be triggered that affect the driving dynamics of the vehicle. The suggestions are evaluated by a cost function, this cost function including a weighted sum of multiple cost terms, the weights being dynamically adapted. Utilizing the evaluations ascertained using the cost function, at least one trajectory or action is selected from among the suggestions. At least one actuation signal is generated that when conveyed to the driver assistance system or the system for the at least partially automatic control of the vehicle, induces the respective system to travel the selected trajectory with the vehicle or to trigger the suggested action.

Claims

1-12. (canceled)

13. A method for generating an actuation signal for a driver assistance system and/or for a system for the at least partially automated control of a vehicle, the method comprising the following steps: making available suggestions for trajectories to be traveled by the vehicle, and/or for other actions to be triggered that affect driving dynamics of the vehicle; evaluating the suggestions using a cost function, the cost function including a weighted sum of multiple cost terms, and each one of the cost terms representing a requirement and/or an optimization goal for behavior of the vehicle; selecting, utilizing the evaluations ascertained using the cost function, at least one trajectory or action from among the suggestions; and generating at least one actuation signal that when conveyed to the driver assistance system or to the system for the at least partially automatic control of the vehicle, induces the driver assistance system or to the system for the at least partially automatic control of the vehicle to travel the selected trajectory with the vehicle or to trigger the selected action; wherein weights of the cost function are dynamically adapted, relative to one another in the weighted sum, to a current driving situation of the vehicle.

14. The method as recited in claim 13, wherein the current driving situation is evaluated utilizing measuring data of at least one sensor installed in the vehicle and/or utilizing information obtained via a vehicle-to-vehicle communication and/or utilizing information obtained via a vehicle-to-infrastructure communication.

15. The method as recited in claim 14, wherein the measuring data and/or at least one variable derived from the measuring data are mapped by a trained artificial neural network to at least one characteristic variable that characterizes the current driving situation, and/or to the weights of the cost terms relative to one another.

16. The method as recited in claim 14, wherein the evaluation of the current driving situation includes an evaluation of a coefficient of friction for tire-road contact of the vehicle and/or a semantic meaning of traffic signs in an environment of the vehicle.

17. The method as recited in claim 14, wherein: from measured values of at least one measuring variable or values of a variable derived from the at least one measuring value that were recorded at different points in time or were evaluated from measured values recorded at different points in time, a model of a Gaussian process is ascertained that is in line with the measured values or values, and using the model, a value of the measuring variable or the variable derived from the at least one measuring value is ascertained for a point in time for which no measured values are available.

18. The method as recited in claim 13, wherein a correction of an estimation of the current driving situation and/or a correction of the weights of the cost terms is learned using learning reinforcement, and an intervention in the driving dynamics of the vehicle suggested and/or carried out by a driving-dynamics system and/or a driver assistance system independently of the suggestions is evaluated as a negative reward within the framework of the learning reinforcement.

19. The method as recited in claim 13, wherein the selection of a trajectory or an action from among the suggestions includes a check to ascertain to what a degree a current fill state of at least one energy store of the vehicle and/or a current degradation state of the vehicle, permits travel of the vehicle of the suggested trajectory or the triggering of the suggested action.

20. The method as recited in claim 13, wherein the cost function includes at least one cost term, which is a measure of: compliance with a predefined travel line, and/or an avoidance of collisions with stationary and/or dynamic objects, and/or compliance with predefined marginal conditions with regard to dynamics of the vehicle, and/or compliance with a minimum distance from a road delimitation.

21. A control unit configured to generate an actuation signal for a driver assistance system and/or for a system for the at least partially automated control of a vehicle, the control unit comprising: an environment model module configured to process observations of a vehicle environment into a model of the vehicle environment; a behavior planning module configured to: ascertain from the model of the vehicle environment trajectories that are collision-free for a predefined time period as suggested trajectories, dynamically adapt weights of cost terms in a weighted sum included in a cost function to a current driving situation of the vehicle, evaluate the suggestions using the cost function, and select at least one trajectory based on the evaluation, and a movement planning module configured to translate the selected trajectory into actuations of individual actuators of the vehicle.

22. The control unit as recited in claim 21, wherein the environment model module also processes map data into the model of the vehicle environment.

23. The control unit as recited in claim 21, wherein the movement planning module is configured to check to what extent a current fill state of at least one energy store of the vehicle and/or a current degradation state of the vehicle, permits travel of the selected trajectory.

24. A non-transitory machine-readable data carrier on which are stored machine-readable instructions for generating an actuation signal for a driver assistance system and/or for a system for the at least partially automated control of a vehicle, the machine-readable instruction, when executed by one or more computers, causing the one or more computers to perform the following steps: making available suggestions for trajectories to be traveled by the vehicle, and/or for other actions to be triggered that affect driving dynamics of the vehicle; evaluating the suggestions using a cost function, the cost function including a weighted sum of multiple cost terms, and each one of the cost terms representing a requirement and/or an optimization goal for behavior of the vehicle; selecting, utilizing the evaluations ascertained using the cost function, at least one trajectory or action from among the suggestions; and generating at least one actuation signal that when conveyed to the driver assistance system or to the system for the at least partially automatic control of the vehicle, induces the driver assistance system or to the system for the at least partially automatic control of the vehicle to travel the selected trajectory with the vehicle or to trigger the selected action; wherein weights of the cost function are dynamically adapted, relative to one another in the weighted sum, to a current driving situation of the vehicle.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0046] FIG. 1 shows an exemplary embodiment of method 100 for generating actuation signal 5, in accordance with the present invention.

[0047] FIG. 2 shows an exemplary embodiment of control unit 10, in accordance with the present invention.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0048] FIG. 1 is a schematic exemplary embodiment of method 100 for generating an actuation signal 5 for a driver assistance system 1a, and/or for a system 1b for the at least partially autonomous control of a vehicle, in accordance with the present invention.

[0049] In step 110, suggestions 2a-2d for trajectories 2 to be traveled by the vehicle are provided and/or suggestions for other actions 2′ to be triggered that influence the driving dynamics of the vehicle.

[0050] In step 120, suggestions 2a-2d are evaluated using a cost function 3. This cost function 3 includes a weighted sum 3* of multiple cost terms 3a-3c. Each cost term 3a-3c represents a requirement and/or an optimization goal for the behavior of the vehicle. According to block 121, the weights of cost terms 3a-3c in weighted sum 3* relative to one another are dynamically adapted to the current driving situation of the vehicle.

[0051] In step 130, utilizing evaluations 4a-4d ascertained using cost function 3, at least one trajectory 2 or action 2′ is selected from among suggestions 2a-2d. According to block 131, this may particularly include a check as to what extent a current fill state of at least one energy store of the vehicle and/or a current degradation state of the vehicle permit(s) travel of the suggested trajectory or triggering of the suggested action.

[0052] In step 140, at least one actuation signal 5 for driver assistance system 1a or for system 1b for the at least partially automated control of the vehicle is generated. This signal is developed in such a way that when conveyed to respective system 1a, 1b, it induces system, 1a, 1b to travel selected trajectory 2 with the vehicle or to trigger suggested action 2′.

[0053] Different possibilities for dynamically adapting the weights of cost terms 3a-3d to the current driving situation of the vehicle have been marked in box 121.

[0054] According to block 122, the current driving situation is able to be evaluated utilizing measuring data from at least one sensor installed in the vehicle and/or utilizing information included in a vehicle-to-vehicle (V2V) communication and/or utilizing information received via a vehicle-to-infrastructure (V2I) communication.

[0055] According to block 123, the measuring data and/or at least one variable derived therefrom is/are able to be mapped by a trained artificial neural network, ANN, to at least one characteristic variable that characterizes the current driving situation and/or to weights of the cost terms 3a-3c relative to one another.

[0056] According to block 124, a coefficient of friction for a tire-road contact of the vehicle and/or the semantic meaning of traffic signs in the environment of the vehicle is/are able to be evaluated.

[0057] According to block 125, from measured values of at least one measuring variable or values of a variable derived therefrom that were recorded at different points in time or were evaluated from measured values recorded at different points in time, a model of a Gaussian process that is in line with these measured values or values is able to be ascertained. According to block 126, a value of the measured variable or the derived variable is able to be ascertained with the aid of this model for a point in time for which no measured values are available.

[0058] According to block 127, a correction of an estimation of the current driving situation and/or the correction of the weights of the cost terms is/are able to be learned using reinforcement learning. An intervention in the driving dynamics of the vehicle suggested and/or carried out by a driving dynamics system and/or driver assistance system independently of suggestions 2a-2d to be checked is evaluated as a negative reward within the framework of this reinforcement learning. (Block 128). It is thus assumed that it was not the optimal mutual weighting of cost terms 3a-3c that was used when arriving at suggestion 2a-2d. If this weighting had been optimal, then suggestion 2a-2d, taken by itself, would already yield results for the actuation of the vehicle and would not additionally have to be “straightened out” by an intervention of another system.

[0059] FIG. 2 shows an exemplary embodiment of a control unit 10. Control unit 10 includes an environment model module 11, which is designed to process measuring data 6 from monitoring the vehicle environment and optionally also to process map data into a model 7 of the vehicle environment. This model 7 is forwarded to behavior planning module 12 of control unit 10.

[0060] Based on model 7 of the vehicle environment, behavior planning module 12 is used to ascertain as suggested trajectories 2a-2d trajectories that are collision-free for a predefined period of time. The predefined time period may be on the order of magnitude of 5 to 7 seconds, for instance.

[0061] Moreover, in behavior planning module 12, weights of cost terms 3a-3c in a weighted sum 3* which is included in a cost function 3 are furthermore dynamically adapted to the current driving situation of the vehicle. Suggestions 2a-2d are evaluated with the aid of this cost function 3. At least one trajectory 2 is selected from suggestions 2a-2d on the basis of evaluations 4a-4d of suggestions 2a-2d.

[0062] Movement planning module 13 of control unit 10 translates this selected trajectory 2 into actuations 8a-8f of individual actuators 9a-9f of the vehicle.