DE102017213694A1 - A method, apparatus, mobile user equipment, machine learning computer program for a sensor system of a vehicle - Google Patents

Abstract

A method for machine learning for a sensor system of a vehicle, comprising: determining a trajectory pattern of a first vehicle when driving a route section, determining a parameter representing a Sensierungsartefakt in the first vehicle in connection with the determined Trajektorienmuster, and assigning the determined parameter of Sensierungsartefakts to the trajectory pattern and storage of the associated data, - Upon detection of at least one trajectory pattern, in particular when repeatedly driving the route section, driving at least one sensor, and / or adjusting at least one Umfassungsfassungs measured value based on one or more sensors and / or a processed measured value the sensor system of at least the first and / or a second vehicle.

Description

The invention relates to a method, apparatus and a corresponding computer program for machine learning for a sensor system of a vehicle. Furthermore, the scope of the invention also includes a suitably equipped mobile user device.

Modern motor vehicles have a variety of vehicle functions based on the evaluation of sensor data that capture an immediate or remote environment of the vehicle. In this case, areas can typically be detected before, behind or at the side of the vehicle. Examples of such vehicle functions are a parking distance control, a parking assistant, a reversing camera, a so-called surround-view system, etc., speed control systems, warnings on vehicles in a blind spot area or a lateral approach of other objects. Furthermore, at least partially automated, highly automated or automatic driving relies on such sensor systems.

Sensor systems may include sensors based on different physical principles. For example, ultrasonic sensors, radar sensors and camera systems, LIDAR sensors are used as sensors. In order to be able to provide a vehicle function, in particular a driver assistance function, the measured values for a situation interpretation supplied by the various sensors can be partially fused.

A basic problem is that each type of sensor has more or less pronounced weaknesses. These include, for example, incorrect or deviating from an objective value measured values for a certain condition of the metrologically to be detected objects. Some sensors are prone to interference, especially mutual interference from other sensors. Errors can occur, for example, in the case of ultrasound sensors due to frequently occurring echoes, extraneous ultrasound or ultrasound-absorbing object surfaces. In a camera system, certain objects, e.g. Edge boundaries or median strips, under certain boundary conditions, such as rain, side or snow driving are not properly recognized and measured. Radar sensors have the problem that carbon bodies are not visible to the sensors. Depending on their nature or the specified boundary conditions, certain objects can thus not be recognized or not correctly recognized as a specific type of object.

Deviations of the measured values of a single sensor can make a fusion of several measured values difficult and lead to unsatisfactory results. In particular, nonlinear effects on deviations from measured values may be different in certain sensing situations when using different sensor types. Since a large number of driver assistance functions depend on the measured values of the sensor system, there is the risk of processing erroneous measured values of the sensors and a corresponding malfunction of a vehicle function, possibly accompanied by a considerable risk for traffic safety.

It is an object of the present invention to specify a method and a device which lead to an improved operation or an improved design of a sensor system with regard to the data of the sensor system that can be used in various vehicle functions.

The object is solved by the features of the independent claim. Advantageous embodiments are characterized in the subclaims.

The invention is characterized by a method of machine learning for a sensor system of a vehicle. The invention is also characterized by a device which is designed to carry out the method. The method comprises determining a trajectory pattern of a first vehicle when driving on a route section. A determination is made of a parameter representing a sensation artifact in the first vehicle in connection with the determined trajectory pattern, and an assignment of the determined parameter of the sensation artifact to the trajectory pattern and storage of associated data. Upon detection of at least one trajectory pattern, in particular during repeated driving on the route section, at least one sensor and / or adaptation of at least one surroundings detection measured value are based on one or more sensors and / or a processed measured value of the sensor system of at least the first and / or one second vehicle.

Decisive for the said trajectory pattern is not necessarily the absolute position. Thus, even a deliberate decoupling from the geographical position can be achieved.

In particular, the reference of position values to one another and / or to relative positions, in particular the shape of a curve, in which the vehicle engages e.g. approaching an object to be sensed, and the like.

For example, the relative positions may be positions relative to immobile conditions and / or moving objects associated with the appearance of the sensing artifact.

Particularly preferably, the relative positions in relation to road markings, posts, sidewalks, tunnels, traffic lights, traffic light masts, crosswalks, etc. may be taken into account.

In particular, the sensing artifact is a sensing error or a portion of the sensor data having unsatisfactory, low quality or plausibility. A sensing artifact or a corresponding portion of the sensor data is particularly indicated by e.g. Excessively high measurement deviations, fluctuations in the values, too low a match of the sensor data relating to a part of the surroundings of the vehicle, which have been detected with at least two different sensors or based on at least two different physical principles. For example, a sensing artifact may correspond to such a deviation that results in a significant undue impact on a sensor functionality based on the sensor or sensor system.

As a parameter representing a sensing artifact, e.g. serve a classification of the Sensation Artifact. This is advantageous for the later adaptation. Examples include a performance hit on a portion of the sensor data and / or a characteristic of the physical sensing principle error, e.g. a wave reflection and / or a not or not sufficiently plausible value within the data of the sensor system and / or a short-term failure or unavailability of the sensor.

According to one embodiment of the invention, a control of the sensor system of the first vehicle or another (second) vehicle can be carried out.

Alternatively or additionally, in the method, depending on the assigned data, a change of the priority or qualifiers of the data of at least one sensor, in particular predictively, before or while reaching a certain position information and / or an adaptation of at least one associated with an environment detection vehicle function of the first and or second vehicle.

When driving the route section through the respective vehicle, depending on the assigned data, control information for driving the sensor system and / or a vehicle function based on the sensor data, e.g. of a driver assistance system, and e.g. be provided wirelessly to the electrical system of the respective vehicle. In this case, said control information may be dependent on recognition (recognition), preferably on prediction of the trajectory pattern.

Alternatively or additionally, in the method, scene detection may be performed with respect to a subject surround detection situation in which the sensing artifact has occurred, and the scene taken into account in determining the associated data, as described below.

According to an optional embodiment, an environment detection situation, in particular a scene that is related to the appearance of the Sensierungsartefakts recognized, in particular classified and processed when determining the associated data.

The scene is classified in particular with pattern recognition. In this case, for example, an image-based classification and pattern recognition in images or image sequences with respect to the captured in the vicinity of the vehicle images or image sequences can be performed. This is preferably a scene that stands at least in a certain (spatial, temporal) relationship with at least one sensing artefact.

A Sensierungsartefakt can be related to a problematic, in particular a statistically problematic Umfelderfassungssituation, or Umfelderfassungssituation a certain kind. This can additionally be taken into account in the method in that the scene is recognized as being in the surroundings detection situation and is expressed on the basis of qualitative and / or quantitative values and / or preferably classified and / or coded.

The said environment detection situation and / or the scene can be determined and / or recognized as certain parameters characterizing this, in particular information about specific (suitably predefined) types or classes.

For example, the associated data may also represent, include, or include a class of the corresponding scene. The scene to the surrounding detection situation may e.g. as a type and / or parameter range of a situation, e.g. a so-called use case, which is related to the appearance of the Sensierungsartfaktts.

Such scenes for the surroundings detection situation are, for example, a standard, typical garage, a garage with incline such as a duplex garage, a bends between 30 - 70 km / h with bushes and the like. Such a scene can be detected, recognized and taken into account, for example, by means of a situation vector.

The information acquired with respect to said surroundings detection situation and / or the scene may be information which in itself does not permit an immediate inference of the at least one particular sensing artifact or features of a sensing artifact. In other words, in the method, it is not necessary to determine a logical, computationally comprehensible relationship between an environment detection situation or scene in general and the occurrence of said sensing artifacts.

Information about the surroundings detection situation may e.g. in the first vehicle or in a spaced-apart computing unit, e.g. running in a backend. The information, in particular the class of the surroundings detection situation, is preferably taken into account when determining the assigned data.

Preferably, a sensing artifact may be placed in the method in the context of a particular use case that results (e.g., repeatedly) in sensor errors or related functional errors, particularly in certain portions or locations within the route. Thus, the method can be very efficiently used mainly to close functional gaps in certain situations, or certain types of Sensierungssituationen.

The surroundings detection situation can be characterized by one or more objects which are located in the detection area of the sensor system and have a predetermined condition. The surroundings detection situation can be characterized by a specific constellation of movable and / or immovable objects, which is located in the detection area of the sensor system. The environment detection situation can also be characterized by certain boundary conditions which are sufficient for detection of the environment by means of the sensor system, e.g. by one or more specific physical principles. Such boundary conditions may be, for example, the prevailing brightness (too light or too dark) in the surroundings of the vehicle, snow, fog, icing of one or more sensors and the like.

Particularly preferably, a number of quantitative criteria of the surroundings detection situation are determined and taken into account. The recognition of the surroundings detection situation can, in particular, be a recognition of a class of surroundings detection situation, for example, depending on the number of quantitative criteria. Preferably, recognizing the surroundings detection situation may be at least the detection of one of a plurality of (determined) classes (e.g., belonging to one of a plurality of possible classes or category values) of environment sensing situations.

Recognition of the environment detection situation may be performed by a variety of predetermined factors. The recognition of a given environment detection situation can be done by means of the first vehicle. A specific (special) environment detection situation can be determined (and recognized as such) in the method by means of a plurality of method variants described below. For example, For example, a specific type of environment detection situation can be determined by a recognized situation (use case) and / or by means of a specific position information (coordinates).

According to a further optional embodiment, a control information dependent on the stored data, in particular learning data, is determined, which causes a change in the properties of a sensor and / or the applied sensing method, in particular to a certain quantitative extent, in particular the emission of light or waves and / or or interpretation of the received light reflection or wave echo by the sensor system of the first and / or second vehicle.

The control information can be determined by means of the vehicle, in particular within the sensor or a sensor fusion unit.

The control information is preferably a quantitative information and / or a multiplicity of different parameters. In this case, the triggering can also take place in a multiplicity of the parameters of the sensor system (which serve, for example, for determining different measured variables) for improved detection of the present specific environment identification situation.

The interpretation of the received light reflection or the wave echo by the sensor system of the first vehicle, for example, by activating or activating one or more alternative or at least partially complementary mutually activatable modes, states, mode transitions or state transitions of the sensor system or downstream of the sensor system Functionality of the respective vehicle done.

Preferably, said change or adaptation takes place essentially for the duration and / or in a quantitative dependency on the surroundings detection situation or the determined scene of the surroundings detection, in particular of at least one qualitative and / or quantitative parameter of the surroundings detection situation or the scene.

• - eine oder mehreren Wellenlängen in der eine Sensierung durchgeführt wird, und/oder
• - eine Pulsfolge oder Pulssequenz, insbesondere eine Kombination und/oder zeitliche Abhängigkeit von bzw. zwischen zumindest zwei Messvorgängen, und/oder
• - eine Veränderung der Phase eines oder mehrerer Messimpulse oder Berücksichtigung der jeweils veränderten Phase der empfangenen Impulse.

According to a further optional embodiment, the sensor system with the determined control information is controlled such that the adaptation relates to:

• one or more wavelengths in which a sensing is performed, and / or
• a pulse sequence or pulse sequence, in particular a combination and / or temporal dependence on or between at least two measurement processes, and / or
• - A change in the phase of one or more measuring pulses or taking into account the respective changed phase of the received pulses.

The sensors (ultrasonic sensors, different radars, light-emitting sensors, such as laser scanners, LED sensors) in the sensor system can be controlled differently. In this case, a Sensierungsmodus (wavelength, phases, pulses) or even the Sensierungsverfahren be changed.

In other words, depending on the determination of at least one data set, the sensor system alters its properties (at the points or matching the points within the route where at least one sensor of the first vehicle causes or has delivered a sensing artifact and / or in one to avoid or Attenuation of the Sensierungsartefakts required measures), so that correct or at least the reality better corresponding measurement data or depending on the measured values (downstream) functionality of the vehicle result. In particular, specific (for example, often occurring in the particular situation) sensory-related errors (special echoes, crosstalk of the sensors, special reflections) can be avoided or their consequences the corresponding sections of the sensor data or a dependent vehicle functionality can be significantly reduced.

For example, For example, the measuring order of ultrasonic sensors can be changed depending on the spatially determined assigned data, such that disturbances in a cross-over measurement or other artifacts or physical effects are reduced for the specific environment detection situation or certain types of environment detection situations and / or in connection with certain Position information is typical.

Also, depending on the associated data, or the control information, a spatial sensing region, e.g. an elevation of radar systems varies, in particular be adjusted. Thereby, a more targeted detection of certain spatial areas, in particular to avoid certain (special) disturbances, take place.

According to a further optional embodiment, the control information causes an alternating, in particular temporally alternating, change of the properties of a sensor and / or the applied sensing method.

Even a modified mode of a sensing method may have its particular weaknesses. It is therefore advantageous, in particular within the same surroundings detection situation, to change over two or more sensing methods of the sensor system or a repeated change in the characteristics of at least one sensor with respect to the same or similar scene in the surroundings detection.

In this case, the method may also include a further step in which the resulting measured values (data of the sensor system), which were recorded in two different sensing phases (each having at least two characteristics of a sensor and / or the sensing method used), are compared (and possibly merged).

Such a comparison of the data can be particularly effective depending on the data, which represent information about the performance of at least one sensor or the sensor system.

In other words, at a problematic location (eg, a complex constellation of objects, eg, in a tidy garage) where the sensor system of the vehicle does not provide satisfactory data, for example, the position information and (in this case, the own garage, etc.). ), the particular nature of the scene in connection with the questionable Umstandsfassungssituation detected (eg a particular type of garage, especially from a specific position or direction). The sensor system consisting of a side radar system with 4 side radars and an ultrasound system of 8-12 sensors is set into a mode that provides better results for this environment detection situation. The sensor system is offset approximately every second in at least two different modes each identify different strengths and weaknesses. The In a further step of the method, the resulting measured data are compared to one another, in particular fused in such a way that the strengths of both modes are maximally emphasized and / or the weaknesses (susceptibility to errors, nonlinearities and others) are at least partially compensated or mitigated. In this case, the information representing a performance of at least one sensor or sensor system of the vehicle and / or the associated data, in particular the learning data, can be taken into account.

• - Erfassen eines Trajektorienmusters, welches zumindest einer lokalen Position in Relation zu zumindest einer Fahrbahnmarkierung, Fahrbahnbegrenzung oder Leitplanke der Fahrbahn entspricht, im Zusammenhang mit dem besagten Sensierungsartefakt,

bevorzugt auch umfassend:

• - Erfassen einer globalen Position, die mit dem Auftritt des Sensierungsartefakts zusammenhängt durch das erste Fahrzeug,
• - Ermitteln von Zuordnungsdaten, die repräsentativ sind für ein Abgleichen der erfassten lokalen Position zu zumindest einer Spurenmarkierung, Leitplanke oder Fahrbahnrand zu einer globalen Position im Zusammenhang mit dem Auftritt des besagten Sensierungsartefakts.

According to a further optional embodiment, the method additionally comprises

• Detecting a trajectory pattern corresponding to at least one local position in relation to at least one lane marking, lane boundary or guardrail of the lane, in connection with said sensing artifact,

preferably also comprising:

• Detecting a global position associated with the occurrence of the sensation artifact by the first vehicle,
• Determining mapping data representative of matching the detected local position to at least one of a lane marker, guardrail, or lane edge to a global location associated with the occurrence of said sensing artifact.

The method preferably comprises determining at least one track marking, guardrail and / or roadway boundary by means of a sensor system of the first vehicle. The method comprises determining at least one expected local position which is related to the occurrence of the sensing artifact, at least in the transverse direction relative to at least one track mark, guardrail and / or roadway boundary determined by the sensor system of the first vehicle and / or determining at least one parameter of the Sensation artifacts, in particular the nature of the sensing artifact (type, class, eg low data quality, fail, failure, unavailability, etc.) depending on the information provided based on the mapping data.

• - Berücksichtigung der Zuordnungsdaten beim Ermitteln der zugeordneten Daten, und/oder
• - Bereitstellen, insbesondere Übermitteln einer von den Zuordnungsdaten abhängigen Information an eine Recheneinheit zur Nutzung in dem ersten/und oder zweiten Fahrzeug.

Preference is then given to:

• Consideration of the assignment data when determining the assigned data, and / or
• Providing, in particular, transmission of information dependent on the assignment data to a computing unit for use in the first and / or second vehicle.

According to another optional embodiment, the trajectory pattern is based on a sequence of vehicle coordinates, e.g. global coordinates of the movement of the vehicle in connection with the occurrence of a Sensierungsartenfaktts, in particular the Sensierungsartfakts determined type.

In particular, the control information is determined as a function of two or more position information, particularly preferably dependent on a position sequence.

Particularly preferably, in the surroundings detection, the scene is determined by a sequence of positions of the first vehicle which contains absolute and / or relative time information, e.g. Time interval information on the positions includes.

For example, a situation when approaching a narrow passage from two different angles (and position sequences) is treated differently, as described below by way of example.

For example, For example, in a first position sequence (first approach trajectory), first control information is determined, e.g. reduces an influence of an ultrasonic sensor in the surroundings detection, which would cause errors in such an approach trajectory. In a second position sequence (second approach trajectory), a second control information is determined, which causes a change of the mode of the ultrasound system and fuses the resulting values at the same time with other sensor data or confirm.

In determining the control information, it may also be preferable to consider from which relative position (e.g., distance, offset, angle information) the first and / or second vehicle is in relation to a particular constellation of objects and / or how fast it approaches the situation.

According to a further optional embodiment, the assigned data are linked to one or more specific application conditions, wherein the one or more application conditions are taken into account during repeated driving on the roadway section by at least the first and / or second vehicle.

The one or more application conditions can be determined depending on the conditions prevailing in the first vehicles when the sensation artifact is established.

In this case, a corresponding embodiment of the control of the sensor of the first and / or second vehicle can be carried out depending on the fulfillment of at least one application condition.

For example, depending on the application condition, one of a plurality of driving actions may be selected, each of which is responsive to an application condition, e.g. refer to a range of speeds, e.g. 10-20 km / h, 20-30 km / h, ... 70-80 km / h, ... 180-210 km / h. These may then depend on the satisfaction of the application condition, e.g. at the time of the current speed of the first and / or second vehicle in the repeated driving on said route section are applied. Simplified, the stored data may include a "leaflet" with one or more conditions of use.

Optionally, in the method, data representing a specific surroundings detection situation can be determined, in particular when the first and / or second vehicle approaches the corresponding location (or object), in particular at <20, 15, 10, 5, 3, 1 meter.

According to a further optional embodiment, the sensor system also comprises means or methods for carrying out a sensor fusion, wherein the fusion of the sensor data is varied by at least two sensors depending on a detected environment sensing situation and / or a determined control information.

• - Zuordnung von Messwerten eines oder unterschiedlicher Sensoren zueinander und/oder zu bestimmten Objekten oder ausgewählten Raumbereichen (Areas of Interest), und/oder
• - Gewichtung von Messwerten zumindest zweier Sensoren beim Ermitteln zumindest eines fusionierten Messwerts, und/oder
• - Zeitversatzes zwischen den zu fusionierenden Messwerten zumindest zweier Sensoren.

Preferably, the fusion of the sensor data is varied with respect to one or more of the following points:

• - Assignment of measured values of one or different sensors to each other and / or to specific objects or selected areas of space (areas of interest), and / or
• Weighting of measured values of at least two sensors when determining at least one fused measured value, and / or
• Time offset between the measured values of at least two sensors to be fused.

In this case, the performance of a static or dynamic environment modeling can be subsumed under the term "sensor system".

According to a further optional embodiment, a prediction for the occurrence of a specific scene in the surroundings detection for the near future is determined, and a, in particular anticipatory, planning for controlling the sensor system and / or the vehicle function based thereon is determined.

Also, a wireless unilateral or mutual agreement of the change of the characteristics of a sensor and / or the applied sensing method between at least two vehicles can be performed.

According to a further optional embodiment, in the first and / or second vehicle, depending on the stored data, a weighting between a map information and surroundings detection data is carried out for operating at least one vehicle function, in particular a driver assistance function.

In a simplified example, for an expected sensing artifact, e.g. a wrong environment sense or lower quality of a sensor information switching a customer function of a substantially dependent on the environment sensing operation on a substantially based on a map information operation, in particular be changed for a suitable time interval.

This can also be done within (within) the relevant vehicle function based on the sensor system, e.g. Driver assistance function are executed.

• - Erkennen, insbesondere prädizieren eines Trajektorienmusters,
• - Prädizieren eines Sensierungsartefakts, insbesondere eines Sensierungsartefakts mit einem bestimmten Parameter, in einer nahen Zukunft abhängig von dem Trajektorienmuster,
• - Ermitteln einer Steuerungsinformation zum Ansteuern des Sensoriksystems des ersten und/oder zweiten Fahrzeugs in Abhängigkeit von der erkannten bestimmten Umfelderfasungssituation,

ferner bevorzugt umfassend:

• - Ermitteln zumindest einer Zeitinformation und/oder Positionsinformation auf die sich die Steuerungsinformation bezieht,
• - Ansteuern des Sensoriksystems des ersten und/oder zweiten Fahrzeugs oder einer mit dem Sensoriksystem zusammenhängende Fahrzeugfunktion abhängig von der Steuerungsinformation, bevorzugt abgängig von dem Trajektorienmuster.

According to another optional embodiment, the method additionally comprises:

• Recognition, in particular prediction of a trajectory pattern,
• Predicting a sensing artifact, in particular a sensing artifact having a certain parameter, in the near future depending on the trajectory pattern,
• Determining control information for activating the sensor system of the first and / or second vehicle as a function of the identified specific surroundings fouling situation,

further preferably comprising:

• Determining at least one time information and / or position information to which the control information relates,
• - Driving the sensor system of the first and / or second vehicle or related to the sensor system vehicle function depending on the control information, preferably departing from the Trajektorienmuster.

The said prediction of a certain Sensierungsartefakts, in particular a Sensierungsartfakts with a certain parameter, in the near future can also with Any (further) means. Within the scope of said prediction, only a rudimentary parameter, which in itself would not be sufficient to avoid or compensate for the sensation artifact, can be determined. Thereupon, in the method, a (much more precise, in particular tailored to the expected Sensierungsartefakt) control information can be determined, with which in turn can be done controlling the at least one sensor and / or the sensor system of the vehicle.

In this case, the driving may relate in particular to at least one time interval and / or route interval, in particular a specific time interval and / or route interval. In this case, a particularly targeted adjustment can be achieved.

• - abhängig von den Daten über eine aktuelle und/oder für die nahe Zukunft prädizierte Positionsinformation des ersten und/oder zweiten Fahrzeugs,

und/oder

• - abhängig von der Information über eine bestimmte Szene bei der fraglichen Umfelderfassung, insbesondere im Zusammenhang mit einem bestimmten Manöver, durchgeführt oder beabsichtigt wird.

According to a further optional embodiment, a prediction of a specific sensation artifact, in particular a sensation artifact with a specific parameter, is determined in a near future,

• dependent on the data about a current and / or predicted position information of the first and / or second vehicle for the near future,

and or

• - Is carried out or intended, depending on the information about a particular scene in the Umfeldfassung in question, in particular in connection with a particular maneuver.

In particular, a position at which a Sensierungsartefakt is to be expected, from the global coordinates (eg in the vicinity of a garage, parking garage, a bottleneck, a special property), and / or the detection of a specific maneuver (eg a parking or Shunting maneuver, parking, Auspark- maneuvering, turning maneuver, narrow passage) are determined.

Preferably, a sensing artifact (to be expected in the near future) may be predicted from a particular (currently performed or predicated) maneuver at a particular location (e.g., lane section of +/- 10, 5, 2, 1 meter) depending on the positional information.

A particular maneuver can also affect a particular type of maneuver. The type of maneuver may e.g. also be detected depending on a vehicle operation by the driver (reverse gear, steering angle, operating sequence, etc.). For example, a particular maneuver or type of maneuver may be detected by the recognition of a particular (typical, characteristic) pattern, e.g. Combination of signals are detected.

The sensor system of the first vehicle is thereby prepared to carry out a change in the characteristics of a sensor and / or the applied sensing method (according to a specific planning, in particular comprising time information, for example sequence). The information representing such planning may be communicated to at least one vehicle in the environment, and / or the planning (on-board planning) may be changed depending on information transmitted from another vehicle.

• - der zugeordneten Daten auf Basis eines mehrmaligen Befahren des Fahrstreckenabschnitts,

und/oder

• - der zugeordneten Daten von mehreren ersten Fahrzeugen ausgeführt wird.

According to a further optional embodiment, control information for controlling at least one sensor of another vehicle is determined on the basis of the one or more associated data of the first vehicle, wherein in particular a comparison:

• the assigned data on the basis of a repeated driving on the route section,

and or

• - The assigned data is executed by several first vehicles.

In this case, the alignment of the assigned data in a computing unit of the first vehicle and / or in the arithmetic unit of the second vehicle and / or in the arithmetic unit of a mobile user device (with the first vehicle or with a second vehicle) can be executed.

In this case, the matching of the assigned data may comprise an aggregation of said assigned data. Particularly preferably, an improved, optimized control information for driving the sensor system comprising at least one sensor of the second vehicle is determined by the adjustment.

According to a further aspect, the invention is characterized by a mobile user device, configured to perform a method for machine learning for a sensor system of a vehicle together with a first vehicle and / or with a second vehicle, wherein the mobile user device is set up, at least perform a part of the method for determining or providing the data based on the assignment and / or a part of the method for determining the information for driving the sensor system of at least one second vehicle.

In this case, the mobile user device can be configured to execute at least a part of the method according to the first aspect. For example, the mobile user device may also cause the execution of certain features of the method in the (first or second) vehicle in which it is carried.

In the context of this description, the mobile application device may include a smartphone, tablet, smart watch, smart closes, in particular a garment with an electronic device integrated in the garment, motorcycle helmet with a man-machine interface, data glasses for the driver of the vehicle, be with the vehicle mitführbarer and connectable to the vehicle with a data interface vehicle computer, an external navigation device, or an analogous development of such devices.

According to a further aspect, the invention is characterized by a computer program, in particular a computer program product comprising a computer program, wherein the computer program is designed, when executed on a computing unit of the first vehicle, the second vehicle or in a first vehicle or in a second Car entrained mobile user device to perform the method according to any one of claims 1-14.

A second vehicle is preferably a vehicle other than the first vehicle. Exceptionally, however, a second vehicle (temporarily, in a repeated driving of the route section) correspond to a first vehicle.

• 1 Ein Ablaufdiagramm zum maschinellen Lernen für ein Sensorsystem eines Fahrzeugs und
• 2 eine Abbildung des maschinellen Lernens für das Sensorsystem des Fahrzeugs.

Embodiments of the invention are explained in more detail below with reference to the schematic drawings. Show it:

• 1 A machine learning flowchart for a sensor system of a vehicle and
• 2 a picture of machine learning for the sensor system of the vehicle.

The 1 shows a flowchart for machine learning for a sensor system of a vehicle.

The program can be executed by one device or distributed by several devices. For this purpose, the device comprises in particular a computing unit, a program and data memory, as well as, for example, one or more communication interfaces.

The program will be in one step S1 started in which variables can be initialized if necessary.

In one step S3 there is a determination of a trajectory pattern of a first vehicle when driving on a route section.

In one step S5 a determination is made of a parameter representing a sensing artifact in the first vehicle in conjunction with the determined trajectory pattern.

In one step S7 the determined parameter of the sensing artifact is assigned to the trajectory pattern and a storage of the assigned data.

In one step S9 upon detection of at least one trajectory pattern, in particular during repeated driving of the route section, activation of at least one sensor, and / or adaptation of at least one surroundings detection measured value based on one or more sensors and / or a processed measured value of the sensor system of at least the first and / or one second vehicle.

In one step S11 the program terminates and may again be in the step S1 to be started.

The method may optionally include one or more of the following steps:

A step in which an environment detection situation, in particular a scene that is related to the appearance of the Sensierungsartefaktts, recognized, in particular classified and is processed when determining the associated data.

A step, in which one of the stored data, in particular learning data dependent control information is determined, which causes a change in the properties of a sensor and / or the applied Sensierungsverfahren, in particular in a certain quantitative measure, in particular the emission of light or waves and / or Interpretation of the received light reflection or wave echo by the sensor system of the first and / or second vehicle.

• - eine oder mehreren Wellenlängen in der eine Sensierung durchgeführt wird, und/oder
• - eine Pulsfolge oder Pulssequenz, insbesondere eine Kombination und/oder zeitliche Abhängigkeit von bzw. zwischen zumindest zwei Messvorgängen, und/oder
• - eine Veränderung der Phase eines oder mehrerer Messimpulse oder Berücksichtigung der jeweils veränderten Phase der empfangenen Impulse.

A step in which the sensor system with the determined control information is controlled such that the adaptation relates to:

• - one or more wavelengths in which a sensing is performed, and / or
• a pulse sequence or pulse sequence, in particular a combination and / or temporal dependence on or between at least two measurement processes, and / or
• - A change in the phase of one or more measuring pulses or taking into account the respective changed phase of the received pulses.

A step in which the control information causes an alternating, in particular temporally alternating change in the properties of a sensor and / or the applied Sensierungsverfahrens.

• - Erfassen eines Trajektorienmusters, welches zumindest einer lokalen Position in Relation zu zumindest einer Fahrbahnmarkierung, Fahrbahnbegrenzung oder Leitplanke der Fahrbahn entspricht, im Zusammenhang mit dem besagten Sensierungsartefakt,

bevorzugt auch umfassend:

• - Erfassen einer globalen Position, die mit dem Auftritt des Sensierungsartefakts zusammenhängt durch das erstes Fahrzeug,
• - Ermitteln von Zuordnungsdaten, die repräsentativ sind für ein Abgleichen der erfassten lokalen Position zu zumindest einer Spurenmarkierung, Leitplanke oder Fahrbahnrand zu einer globalen Position im Zusammenhang mit dem Auftritt des besagten Sensierungsartefakts.

One step:

• Detecting a trajectory pattern corresponding to at least one local position in relation to at least one lane marking, lane boundary or guardrail of the lane, in connection with said sensing artifact,

preferably also comprising:

• Detecting a global position associated with the occurrence of the sensing artifact by the first vehicle,
• Determining mapping data representative of matching the detected local position to at least one of a lane marker, guardrail, or lane edge to a global location associated with the occurrence of said sensing artifact.

A step in which the trajectory pattern is determined on the basis of a sequence of vehicle coordinates, in particular global coordinates of the movement of the vehicle in connection with the occurrence of a sensation artifact, in particular the sensation artifact of a certain type. A step of attaching the associated data to one or more particular conditions of use, wherein the one or more conditions of use are taken into account in re-driving the lane section through at least one of the first and second vehicles.

A step in which the sensor system also includes means or methods for performing a sensor fusion, wherein depending on a determined environment sensing situation and / or determined control information, the fusion of the sensor data is varied by at least two sensors.

A step in which a prediction for the occurrence of a specific scene in the surroundings detection is determined for the near future, and a, in particular anticipatory, planning for the control of the sensor system and / or the vehicle function based thereon is determined.

A step in which in the first and / or second vehicle, depending on the stored data, a weighting between a map information and surroundings detection data for operating at least one vehicle function, in particular a driver assistance function, takes place.

• - Erkennen, insbesondere prädizieren eines Trajektorienmusters,
• - Prädizieren eines Sensierungsartefakts, insbesondere eines Sensierungsartefakts mit einem bestimmten Parameter, in einer nahen Zukunft abhängig von dem Trajektorienmuster,
• - Ermitteln einer Steuerungsinformation zum Ansteuern des Sensoriksystems des ersten und/oder zweiten Fahrzeugs in Abhängigkeit von der erkannten bestimmten Umfelderfasungssituation,

ferner bevorzugt umfassend:

• - Ermitteln zumindest einer Zeitinformation und/oder Positionsinformation auf die sich die Steuerungsinformation bezieht,
• - Ansteuern des Sensoriksystems des ersten und/oder zweiten Fahrzeugs oder einer mit dem Sensoriksystem zusammenhängende Fahrzeugfunktion abhängig von der Steuerungsinformation, bevorzugt abgängig von dem Trajektorienmuster.

One step:

• Recognition, in particular prediction of a trajectory pattern,
• Predicting a sensing artifact, in particular a sensing artifact having a certain parameter, in the near future depending on the trajectory pattern,
• Determining control information for activating the sensor system of the first and / or second vehicle as a function of the identified specific surroundings fouling situation,

further preferably comprising:

• Determining at least one time information and / or position information to which the control information relates,
• - Driving the sensor system of the first and / or second vehicle or related to the sensor system vehicle function depending on the control information, preferably departing from the Trajektorienmuster.

• - abhängig von den Daten über eine aktuelle und/oder für die nahe Zukunft prädizierte Positionsinformation des ersten und/oder zweiten Fahrzeugs,

und/oder

• - abhängig von der Information über eine bestimmte Szene bei der fraglichen Umfelderfassung, insbesondere im Zusammenhang mit einem bestimmten Manöver, durchgeführt oder beabsichtigt wird.

A step in which a prediction of a particular sensation artifact, in particular a sensation artifact with a particular parameter, is determined in a near future,

• dependent on the data about a current and / or predicted position information of the first and / or second vehicle for the near future,

and or

• - Is carried out or intended, depending on the information about a particular scene in the Umfeldfassung in question, in particular in connection with a particular maneuver.

• - der zugeordneten Daten auf Basis eines mehrmaligen Befahren des Fahrstreckenabschnitts,

und/oder

• - der zugeordneten Daten von mehreren ersten Fahrzeugen

ausgeführt wird.A step, in which a control information for controlling at least one sensor of another vehicle is determined on the basis of one or more associated data of the first vehicle, in particular a comparison:

• the assigned data on the basis of a repeated driving on the route section,

and or

• - The assigned data from several first vehicles

is performed.

The method may optionally be carried out together with a method for adapting a sensor system, which will be described below.

• Erkennen einer vorgegebenen Umfelderfassungssituation mit Mitteln des Fahrzeugs;
• Ermitteln einer Steuerungsinformation zum Ansteuern des Sensorsystems des Fahrzeugs in Abhängigkeit von der erkannten, vorgegebenen Umfelderfassungssituation; und Ansteuern des Sensorsystems des Fahrzeugs derart, dass die im Zusammenhang mit der erkannten Umfelderfassungssituation erfassten oder zu erfassenden Messwerte zumindest eines der Sensoren und/oder aus den Messwerten eines oder mehrerer Sensoren des Sensorsystems ermittelte Daten zum Betreiben zumindest einer Fahrzeugfunktion zumindest teilweise korrigiert werden.

The method for adapting a sensor system may comprise the following steps:

• Recognizing a predetermined environment detection situation with means of the vehicle;
• Determining a control information for driving the sensor system of the vehicle as a function of the detected, predetermined environment detection situation; and triggering of the sensor system of the vehicle in such a way that the measured values of at least one of the sensors and / or data determined from the measured values of one or more sensors of the sensor system for operating at least one vehicle function are at least partially corrected in accordance with the detected surroundings detection situation.

The sensor system of the vehicle is a system that i.a. Provides data for a vehicle function, in particular a driver assistance function, a driver information system, a vehicle dynamics function or a vertical dynamic function of the vehicle.

In particular, the given surroundings detection situation is a situation which represents an increased complexity or an increased degree of difficulty or a considerably pronounced specificity for a sensory detection of the surroundings with the aid of the sensor system.

A predetermined environment detection situation exists in particular even if there is an increased complexity or an increased degree of difficulty for the evaluation of the data supplied by the sensor system. A given environment detection situation can thus also be a specific application, which repeatedly led in the past to errors of the sensor system and related functional errors.

The method aims, in particular, to close functional gaps (a temporary unavailability or a faulty functionality of one or more vehicle functions) associated with predetermined (difficult) surroundings detection situations and thus also to provide a preferably continuous experience for the user of the vehicle. The method may include that a detection of (possible) incorrect, qualitatively inferior measured values of the sensor system and / or the operation of the at least one vehicle function is performed. The execution of further steps of the method can then take place depending on the detection of the faulty, qualitatively inferior measured values of the sensor system and / or the mode of operation of the at least one vehicle function.

The data for operating at least one vehicle function determined from the measured values of one or more sensors of the sensor system may be so-called environment model data, which may be e.g. Describe parts of the environment of the vehicle, a data model, which refers to at least one point in time represent.

Alternatively or additionally, the data determined from the measured values of one or more sensors of the sensor system for operating at least one vehicle function may be one or more desired variables and / or a control variable of a vehicle function.

The surroundings detection situation can be characterized by one or more objects which are located in the detection area of the sensor system and have a predetermined condition. The surroundings detection situation can be characterized by a specific constellation of movable and / or immovable objects, which is located in the detection area of the sensor system. The environment detection situation can also be characterized by certain boundary conditions which are sufficient for detection of the environment by means of the sensor system, e.g. by one or more specific physical principles. Such boundary conditions may be, for example, the prevailing brightness (too light or too dark) in the surroundings of the vehicle, snow, fog, icing of one or more sensors and the like.

Particularly preferably, a number of quantitative criteria of the surroundings detection situation are determined and taken into account. The recognition of the surroundings detection situation can, in particular, be a recognition of a class of surroundings detection situation, for example, depending on the number of quantitative criteria. Preferably, recognizing the surroundings detection situation can at least detect one of a plurality of (specific) classes (eg as Belonging to one of several possible classes or category values) of environment sensing situations.

Recognition of the environment detection situation may be performed by a variety of predetermined factors. The recognition of a given environment detection situation can be done by means of the vehicle. The detection of a predetermined environment detection situation can be carried out in the method depending on the measured values of at least one of the sensors and / or dependent on data determined from the measured values of one or more sensors of the sensor system.

In this case, the detection of the predefined surroundings detection situation can take place as a function of the measured values of at least one first sensor and / or as a function of data determined from the measured values of one or more first sensors of the sensor system, and then the vehicle's sensor system can be triggered in such a way that the vehicle in In connection with the detected surroundings detection situation, measured values of at least one second sensor and / or data determined from the measured values of one or more second sensors of the sensor system are at least partially corrected for operating at least one vehicle function. In this case, the at least one first sensor and the at least one second sensor may be different and / or at least partially based on different physical principles.

For example, in the method, depending on the measured values of a radar sensor, the activation of an ultrasound sensor and / or a camera system of the vehicle take place, wherein the resulting values of the ultrasound sensor and / or the camera system are at least partially corrected, e.g. be improved according to predetermined criteria. For example, in the method, depending on the measured values of a camera system, the activation of an ultrasonic sensor and / or a radar sensor of the vehicle take place, the resulting values of the ultrasound sensor and / or the radar sensor being at least partially corrected, e.g. be improved according to predetermined criteria.

Alternatively or additionally, the recognition of the predetermined surroundings detection situation can take place with the aid of information about a specific driving maneuver carried out by the vehicle. For example, a recognized situation, which corresponds to a particular application, may fall under it.

The detection of the surroundings detection situation can furthermore be determined on the basis of specific relative position information of the vehicle to form an object constellation. Alternatively or additionally, in the method, depending on the detection of the environment detection situation, a result and / or a consequence of a specific (possible, available for selection) control or change of the sensor system or control information can be determined or estimated. Depending on the determined result and / or a consequence of a specific activation, it can be decided in the method, for example, to perform or not carry out a specific activation and / or to select one of several possible control information for activating the at least one sensor of the sensor system.

The control information can be determined in the method by a computing unit of the vehicle. The arithmetic unit may be one of the measured values of a sensor or the arithmetic unit which processes the measured values of all the different sensor systems of the vehicle.

The control information is quantitative information and / or parameters which can be used, e.g. a measuring method of one or more sensors can be influenced. Preferably, a sequence of a measuring method relating to at least one sensor and / or quantitative measures associated with the measuring method can be adapted. The driving can be a variety of parameters of the sensor system, which are used to determine different measures and / or improved detection of the predetermined environment detection situation.

• - Ermitteln der Umfelderfassungssituation, zumindest als eine Klasse der Umfelderfassungssituation;
• - Bestimmen der zu optimierenden Kriterien zu einem Messverfahren;
• - Erzeugen der Steuerungsinformation;
• - Durchführen zumindest eines Messvorgangs und/oder der Verwendung der Sensorwerte unter Berücksichtigung der ermittelten Steuerungsinformation.

Preferably, control information can be determined which influences the measurement method in favor of a result desired for the surroundings detection situation. Such a variant of the method may include:

• Determining the surroundings detection situation, at least as a class of the surroundings detection situation;
• Determining the criteria to be optimized for a measuring method;
• - generating the control information;
• - Performing at least one measurement process and / or the use of the sensor values taking into account the determined control information.

The method is based on the consideration that in certain situations, eg with certain problematic objects or a certain object constellation (arrangement of objects) in the environment, the sensor system is controlled by activation is changed so that an improved (largely error-free and precise) environment detection is possible. For example, the parameters of an infrared light emitted by a sensor (in the case of a lidar or time-of-light sensor), electromagnetic waves (in the case of radar sensors) or ultrasound waves (in the case of ultrasonic sensors) can be adapted to the situation adapted to the sensory acquisition. Such an adaptation takes place depending on the nature of certain objects, a specific object constellation or prevailing boundary conditions. As described, an adaptive correction of quantitative parameter values and / or the evaluation or processing of the measured values can also take place. An adaptation can also be effected by a different weighting of the data of different sensors in a sensor fusion as well as the changed control of the sensors or in the evaluation of measured values or phase information.

The method starts where a specific situation in the surroundings of the vehicle has proven to be problematic for its sensor system with predetermined (i.e., factory provided) parameters in the past. Such situations include, for example, objects detected too late within a specially trained road, a construction site, a car wash, etc. These situations are accommodated by the adaptation of the sensor system.

The method may also be made adaptable by means of an application running on the vehicle and configurable, for example, by means of an app running on a user's mobile user device (= application, i.e. an application program).

In a first variant, the method can be implemented, for example, in one of the following ways: detection of a given surroundings detection situation by means of the vehicle; Determining a first control information for driving the sensor system of the vehicle in dependence on the detected, predetermined Umfassungsfassungssituation; and activating the sensor system of the vehicle such that the measured values of at least one of the sensors detected or to be detected in connection with the detected surroundings detection situation are at least partially corrected.

The method can be implemented in a second variant, for example, in the following manner: detection of a predetermined environment detection situation with means of the vehicle; Determining a second control information for driving the sensor system of the vehicle in dependence on the detected, predetermined Umfassungsfassungssituation; and activating the sensor system of the vehicle such that the data determined in connection with the detected surroundings detection situation from the measured values of one or more sensors of the sensor system for operating at least one vehicle function are at least partially corrected.

The method can preferably be implemented in a third variant, for example, in the following manner: detection of a predetermined surroundings detection situation with means of the vehicle; Determining a second control information for driving the sensor system for the correction of data determined from the measured values of one or more sensors of the sensor system for operating at least one vehicle function of the vehicle in dependence on the detected, predetermined Umfassungsfassungssituation; Activating the sensor system of the vehicle such that the data determined in connection with the detected surroundings detection situation from the measured values of one or more sensors of the sensor system for operating at least one vehicle function are at least partially corrected; Determining a first control information for driving the sensor system of the vehicle for the at least partial correction of the measured values to be detected at least one of the sensors in dependence on the detected, predetermined Umfelderfassungssituation; and activating the sensor system of the vehicle such that the measured values of at least one of the sensors to be detected in connection with the detected surroundings detection situation are at least partially corrected.

In other words, in the third variant, the second variant is first carried out, in which the measured values for operating at least one vehicle function are at least partially corrected. In this case, a fast corrective response to the sensor system can be applied, so that the vehicle function can be operated with at least partially corrected measured values. This is followed by the execution of the first variant of the method, in which a control of at least one sensor takes place with the first control data. This control can also include, for example, an adaptation of the measurement signals radiated by the sensor, etc. Along with an embodiment of the first variant, the execution of the second variant can be reduced or adjusted.

The third variant has the advantage of a very fast reaction and a subsequent correction (improvement) of the underlying sensor data, in particular the raw data of at least one sensor.

The method for adapting a sensor system may optionally include the following step:

A step in which the control information changes properties of one or more of the sensors of the sensor system and / or an applied measuring method of the sensor system.

The change in the properties takes place, in particular, with regard to the duration of a measurement performed by a sensor and / or in a quantitative manner. The change in an applied measuring method of the sensor system can be realized, for example, by a change in the order of measurements of one or more sensors.

The method for adapting a sensor system may optionally include the following step:

A step in which, for changing the properties of the sensor (s), a respective sensor is triggered in such a way that it emits a signal with one or more wavelengths during a measurement.

For example, all sensors can emit a signal of a given wavelength at a time. Alternatively, one sensor can emit a signal of one wavelength and at least one other sensor can emit a signal of a different wavelength. Likewise, different wavelengths can be emitted by a sensor in temporal succession. Alternatively or additionally, it can be provided that, for changing the properties of the sensor (s), a respective sensor is triggered in such a way that it emits a pulse train or pulse sequence during a measurement. A pulse sequence may e.g. a combination of pulses or pulse sequences. There may be a time dependence between the two measuring processes. Such a temporal dependency is not mandatory.

In particular, in the method, the influence of (in a certain way) changed wavelength of the emitted signal on a first measured value detected by the sensor (s), in particular a first reflection value resulting from the changed wavelength, can be determined, the subsequent driving of the sensor system is varied depending on the first measured value.

The method for adapting a sensor system may optionally include the following step:

A step in which, for changing the properties of the sensor (s), a respective sensor is triggered in such a way that it emits a specific, in particular an altered, pulse sequence or pulse sequence during a measurement.

The method for adapting a sensor system may optionally include the following step:

A step in which, for changing the characteristics of the sensor (s), a respective sensor is triggered in such a way that it alters a phase of one or more measuring pulses, and optionally processes the respectively changed phases of received measuring pulses.

By means of these embodiments, it is possible to provide different types of sensors (for example ultrasound sensors, different radars, light-emitting sensors, such as laser scanners or LED sensors) differently.

In this case, a measuring mode with regard to wavelength, phase, pulse sequence or even the measuring method can be changed. This means that, depending on the detected surroundings detection situation, one or more sensors change their properties, so that correct or at least better corresponding measurement data results from it. This makes it possible to avoid specific errors occurring in a particular situation and caused by measurement. Such errors include special echoes, crosstalk of the sensors or reflections.

Depending on spatially determined data, the measurement sequence of ultrasound sensors can be changed to reduce interference in a cross-over or other artifacts or physical effects that are typical for certain Sensierungssituationen or types of Sensierungssituationen.

Also, a spatial detection range of one or more sensors, e.g. an elevation of radar sensors, can be varied. As a result, a more targeted detection of certain spatial areas, in particular to avoid disturbances, take place.

The method for adapting a sensor system may optionally include the following step:

A step in which an alternating, in particular temporally alternating, change of the properties of the sensor (s) and / or the measuring method is initiated by the control information.

In order to further improve the result and processing of the measured values of the sensors of the sensor system, it is expedient, within the same environment detection situation, between two or three several, different measurement methods of the sensor system or a repeated change in the properties of at least one sensor to change. This change preferably takes place automatically, for example in the presence of a special type of environment detection situation. For example, for this purpose, a sensor system comprising four side radar sensors and eight to twelve ultrasonic sensors as sensors can be put into a mode which provides better results for the surroundings detection situation.

For example, the sensor system can alternate between two different measurement modes every second, with each measurement mode having different strengths and weaknesses. The resulting measurement data of the at least two different measurement modes are compared and / or merged with each other in a processing step that emphasizes the strengths of both measurement modes and / or at least partially compensates for or at least mitigates the weaknesses in terms of susceptibility to errors, non-linearity and the like. In this case, for example, the performance of a sensor or sensor type of the vehicle can be taken into account. Likewise, the consideration of learning data is possible.

According to a further expedient embodiment, it is possible to compare and combine the resulting measured values of the sensor system, which were recorded in different measuring phases or different measuring modes.

• Einen Schritt, bei dem abhängig von den Messwerten und/oder von aus den Messwerten eines oder mehrerer Sensoren des Sensorsystems ermittelten Daten ein bestimmtes Muster erkannt, und
• abhängig von dem erkannten Muster ein Erkennen der vorgegebenen Umfelderfassungssituation, insbesondere zumindest eine Klasse der Umfelderfassungssituation, erfolgt.

The method for adapting a sensor system may optionally include the following step:

• A step in which, depending on the measured values and / or data determined from the measured values of one or more sensors of the sensor system, a specific pattern is detected, and
• Depending on the detected pattern, a recognition of the predetermined environment detection situation, in particular at least one class of the surroundings detection situation, takes place.

Thereupon, in particular as a function of the at least one inference to the predetermined surroundings detection situation, a control information for controlling the at least one first sensor and / or at least one second sensor of the sensor system of the vehicle can be determined. In this case, the one or more first sensors and the second sensor or sensors may be the same or different sensor or sensor type.

Such a pattern can be detected on the basis of an amplitude curve, a phase curve, a signal shape, a dependence on a temporal behavior of at least one measured value and / or interruptions of the measured values of at least one of the sensors and / or data determined from the measured values of one or more sensors of the sensor system.

Thereupon, depending on the recognized pattern, the inference to the predefined surroundings detection situation can be determined. In particular, such a conclusion can be a classification of the surroundings detection situation and / or an exclusion of one or more specific environment detection situations, preferably an assignment to a specific environment detection situation, or a predetermined class of the environment detection situation.

In this case, a pattern can be detected as a function of the measured values of the first sensor or sensors, which indicates a specific sensor inaccuracy, and then triggering a second sensor, such that the at least one of the second sensor determined data for operating at least one vehicle function at least partially corrected.

Alternatively or additionally, an object constellation, when approaching a narrow passage from two different angles, which is determined by respective sequences of positions of the vehicle relative to the object constellation, may be considered two different surround sensing situations, or recognized as different surround sensing situations in the method, and processed differently accordingly become.

In one example of the method, upon approaching the vehicle to the object constellation with a first approaching trajectory, first control information, e.g. an influence of one or more sensors, e.g. Ultrasonic sensors in the surrounding detection reduced, which would cause errors in such an approach trajectory. When approaching in accordance with a second approach trajectory, a second control information can be determined which causes a change in the control of the ultrasonic sensor (s) and optionally fuses the resulting values with further sensor data in order to obtain or confirm the improved measurement results.

According to a further expedient embodiment, information about a mobility of at least one object detected by the sensor system is processed. In particular, an environment detection situation can be detected on the basis of the approach trajectory. At the same time is the detection of mobility at least one of the objects to be sensed possible. An approach trajectory may refer to a relative trajectory between the vehicle or its sensor (s) and an object constellation. In the method, a mobility of an object can take place on the basis of the (otherwise determined, a priori known or assigned) object class.

The method for adapting a sensor system may optionally include the following step:

A step in which the control information is determined depending on data of a power supply-free data carrier, which is mounted and / or learned in the sensory environment of the vehicle.

A power supply-free data carrier may be a passive chip for wireless near-field communication, in particular an RFID chip or a machine-readable code.

An RFID chip can be programmed in a desired manner. In particular, this may be assigned to one of a plurality of available surround sensing situations, such as e.g. there is a narrow passage, there is a parking situation, the parking lot has no limits. Likewise, the RFID chip can carry the information that at the location of the energy supply-free data carrier detection with a sensor of the vehicle system is not possible or possibly is associated with difficulties.

For example, the machine-readable code can be configured as a QR code. For example, a QR code can be read out using a standardized software as soon as the QR code is recognized by a camera of the vehicle. Such a code can also be read out and checked with a user's terminal. Machine-readable code that exhibits contrasts in an infrared spectrum that depend on the stored information is advantageous because this comparison to code in visible light has better resistance to contamination. Likewise, this can be better detected in low light conditions.

Likewise, the energy supply disk may consist of a combination of a passive chip for wireless near-field communication and a machine-readable code.

For example, such a power supply-free data carrier can be placed at various locations where there is a difficult environment detection situation as described above. An identifier can be used to assign a specific location to an energy-free data carrier. The assignment of the label of the energy-free data carrier and location can be stored in a data record. The data of the data set can be read out by the arithmetic unit of the sensor system. For this purpose, the database can be learned by a learning process by the vehicle. Likewise, the database may be stored outside the vehicle, so that a corresponding exchange of data takes place through a communication between the computing unit of the vehicle and the database.

Using a typical reading range of commercially available passive chips for near field wireless communication, the vehicle can be approximated to the location or object labeled with a non-powered media at less than 20m, 15m, 10m, 5m, 3m, 1m.

The method for adapting a sensor system may optionally include the following step:

One step in which the sensor system comprises means for carrying out a sensor fusion, by means of which the fusion of the measured values of at least two sensors of the sensor system is varied depending on the sensory environment of the vehicle and / or on the determined control information.

In particular, an assignment of measured values of one or more sensors to one another and / or to specific objects or selected spatial regions of the environment can be performed. Alternatively or additionally, a weighting of measured values of at least two sensors can be carried out when determining at least one fused measured value. As an alternative or in addition, a time offset between the measured values to be fused can be processed between at least two sensors. In this case, logical and / or quantitative relationships of the fusion process can be adjusted.

The method for adapting a sensor system may optionally include the following step:

A step in which a prediction for the occurrence of the predetermined environment detection situation for the near future is determined, and a, in particular anticipatory, regulation or planning for driving the sensor system of the vehicle is determined.

The method for adapting a sensor system may optionally include the following step:

• - Ermitteln, dass die vorgegebene Umfelderfassungssituation innerhalb eines vorgegebenen Zeitraums, insbesondere im Sekundenbereich, eintreten wird;
• - Ermitteln der Steuerungsinformation zum Ansteuern des Sensorsystems des Fahrzeugs in Abhängigkeit von der erkannten, vorgegebenen Umfelderfassungssituation und zumindest einer Zeitinformation, auf die sich diese bezieht;
• - Variieren des Sensorsystems des Fahrzeugs oder einer mit dem Sensorsystem zusammenhängenden Fahrzeugfunktion abhängig von der Steuerungsinformation und der Zeitinformation.

One step in which the following additional steps are performed:

• Determining that the given environment detection situation will occur within a predetermined time period, in particular in the seconds range;
• - Determining the control information for driving the sensor system of the vehicle in dependence on the detected, predetermined environment detection situation and at least one time information to which it refers;
• Vary the sensor system of the vehicle or a vehicle function related to the sensor system depending on the control information and the time information.

The determination that the predetermined environment detection situation within a predetermined period of time can be made from information about a specific maneuver of the vehicle that is currently being performed or whose implementation is intended. A particular maneuver may be detected by the vehicle operator by the driver, such as the engagement of the reverse gear, the steering angle, a control sequence, etc.

As a result of this embodiment, the control parameter for activating the sensor system can be determined before the surroundings detection situation occurs. The applied measuring method can be carried out according to the planning, which includes a time information or a time sequence.

The 2 illustrates again the above method for machine learning.

The trajectory pattern TM of the first vehicle 10 is determined when driving on a route section. In addition, the parameter becomes P representing a sensing artifact in the first vehicle 10 in connection with the determined trajectory pattern TM , determined.

The determined parameter P of the sensation artifact becomes the trajectory pattern TM associated and assigned data ZD are stored.

Subsequently, when recognizing at least one Trajektorienmusters TM , in particular during repeated driving on the route section, an activation of at least one sensor, and / or adaptation of at least one environment detection measurement based on one or more sensors and / or a processed measurement of the sensor system of at least the first and / or a second vehicle 10 . 20 ,

The steps may be from a device of the first vehicle 10 and / or the second vehicle 20 and / or from a mobile user device 14 . 14 ' be executed.

Furthermore, the assigned data ZD to a backend 15 and / or to the second vehicle 20 be transmitted so that in the respective vehicle 10 . 20 the control and / or adjustment can be done.

It can also have two or more than two first vehicles 10 be present and used for the procedure.

Claims (16)

A machine learning method for a sensor system of a vehicle, comprising: Determining a trajectory pattern of a first vehicle when driving on a route section, Determining a parameter representing a sensing artifact in the first vehicle in association with the determined trajectory pattern, and Assigning the determined parameter of the sensing artifact to the trajectory pattern and storing the associated data, Upon detection of at least one trajectory pattern, in particular during repeated driving on the route section, activation of at least one sensor, and / or adaptation of at least one surroundings detection measured value based on one or more sensors and / or a processed measured value of the sensor system of at least the first and / or one second vehicle. Method according to Claim 1 in which an environment detection situation, in particular a scene which is associated with the appearance of the sensation artifact, is recognized, in particular classified and processed when determining the assigned data. Method according to one of the preceding claims, in which a control information dependent on the stored data, in particular learning data, is determined, which causes a change in the properties of a sensor and / or the applied sensing method, in particular to a certain quantitative extent, in particular the emission of light or waves and / or interpretation of the received light reflection or wave echo by the sensor system of the first and / or second vehicle. Method according to Claim 3 in which the sensor system with the determined control information is controlled such that the adaptation relates to: one or more wavelengths in which a sensing is performed, and / or a pulse sequence or pulse sequence, in particular a combination and / or time dependence of or between at least two measurement processes, and / or a change in the phase of one or more measurement pulses or consideration each changed phase of the received pulses. Method according to Claim 3 or 4 in which the control information causes an alternating, in particular temporally alternating change in the properties of a sensor and / or the applied Sensierungsverfahrens. Method according to one of the preceding claims, also comprising: Detecting a trajectory pattern corresponding to at least one local position in relation to at least one lane marking, lane boundary or guardrail of the lane, in connection with said sensing artifact, preferably also comprising: Detecting a global position associated with the occurrence of the sensing artifact by the first vehicle, Determining mapping data representative of matching the detected local position to at least one of a lane marker, guardrail, or lane edge to a global location associated with the occurrence of said sensing artifact. Method according to one of the preceding claims, in which the trajectory pattern is determined on the basis of a sequence of vehicle coordinates, in particular global coordinates of the movement of the vehicle in connection with the occurrence of a sensing artifact, in particular of the sensing artifact of a specific type. Method according to one of the preceding claims, wherein the associated data are linked to one or more specific conditions of use, wherein the one or more conditions of use are taken into account during repeated driving of the lane section through at least the first and / or second vehicle. Method according to one of the preceding claims, wherein the sensor system also comprises means or methods for performing a sensor fusion, wherein depending on a detected environment sensing situation and / or determined control information, the fusion of the sensor data is varied by at least two sensors. Method according to one of the preceding claims, in which a prediction for the occurrence of a specific scene in the surroundings detection is determined for the near future, and a, in particular anticipatory, planning for the control of the sensor system and / or the vehicle function based thereon is determined. Method according to one of the preceding claims, wherein in the first and / or second vehicle, depending on the stored data, a weighting between a map information and surroundings detection data for operating at least one vehicle function, in particular a driver assistance function, takes place. Method according to one of the preceding claims, comprising: Recognition, in particular prediction of a trajectory pattern, Predicting a sensing artifact, in particular a sensing artifact having a certain parameter, in the near future depending on the trajectory pattern, Determining control information for activating the sensor system of the first and / or second vehicle as a function of the identified specific surroundings fouling situation, further preferably comprising: Determining at least one time information and / or position information to which the control information relates, - Driving the sensor system of the first and / or second vehicle or related to the sensor system vehicle function depending on the control information, preferably departing from the Trajektorienmuster. Method according to one of the preceding claims, in which a prediction of a specific sensing artifact, in particular a sensing artifact with a specific parameter, is determined in a near future, dependent on the data about a current and / or predicted position information of the first and / or second vehicle for the near future, and or - Is carried out or intended, depending on the information about a particular scene in the Umfeldfassung in question, in particular in connection with a particular maneuver. Method according to one of the preceding claims, in which a control information for controlling at least one sensor of another vehicle is determined based on the one or more associated data of the first vehicle, wherein in particular a comparison: - the associated data based on a multiple driving on the route section, and / or - the associated data is executed by a plurality of first vehicles. A mobile user device configured to perform a machine learning method for a sensor system of a vehicle together with a first vehicle and / or a second vehicle, the mobile user device configured to include at least a portion of the method for determining or providing the same the assignment of based data and / or a part of the method for determining the information to control the sensor system of at least one second vehicle perform. Computer program, in particular a computer program product comprising a computer program, wherein the computer program is designed, when executed on a computing unit of the first vehicle, the second vehicle or a mobile user device carried in a first vehicle or in a second vehicle, the method according to one of Claims 1 - 14 perform.

Images