Method for controlling a driving function of a movable device

Abstract

Method (100) for controlling a driving function (5) of a movable device (1), in particular a vehicle or a robot, comprising the steps: - Reading (110) parameters (6) for controlling the driving function (5), - Using (120) a card (15) wherein the card (15) has at least a first area (16) and a second area (17) wherein at least one value of a swarm behavior (9) is entered in the second area (17), - Locating (130) the device on the map (15), - Using (140) the parameters (6) to determine the driving function (5) when the movable device (1) is in the first area (16) of the map (15), - Using (150) at least one value of the swarm behavior (9) to determine the driving function (5) when the movable device (1) is in the second area (17) of the map (15), - Controlling (160) the device with the determined driving function (5). Furthermore, the invention comprises a method for creating a map for determining a driving function of a movable device, a computing unit, a computer program and a machine-readable storage medium.

Description

[0001] The invention relates to a method for controlling a driving function of a movable device. Furthermore, the invention includes a method for creating a map for controlling a driving function. The invention also comprises a computing unit, a computer program product, and a machine-readable storage medium. State of the art

[0002] Methods for controlling a driving function for a movable device are known from the prior art. Disclosure of the invention

[0003] It is therefore an object of the invention to provide an improved method for controlling a driving function of a movable device, in particular a vehicle or a robot. Furthermore, the object can be seen as providing an improved method for creating a digital map for determining a driving function of a device.

[0004] These tasks are solved using the methods described in the independent claims. Advantageous embodiments are described in the dependent claims.

[0005] According to a first aspect of the invention, a method for controlling a driving function of a movable device, in particular a vehicle or a robot, is proposed. The method comprises the following steps: - Reading parameters for controlling the driving function, - Using a map, wherein the map has at least a first area and a second area, wherein at least one value of a swarm behavior is entered in the second area, - Locating the moving device on the map, - Using the parameters to determine the driving function when the moving device is in the first area of ​​the map, - Using at least one value of the swarm behavior to determine the driving function when the moving device is located in the second area of ​​the map, - Controlling the movable device with the determined driving function.

[0006] This allows for the technical advantage of providing an improved method for controlling the driving function of a movable device. This is achieved by using a map with at least a first and a second area, where at least one value of a swarm behavior is entered in the second area. The device is located on the map. If the device is located within the first area of ​​the map, the parameters are used to determine the driving function. If the device is located within the second area of ​​the map, the at least one value of the swarm behavior is used to determine the driving function. This significantly reduces the technical effort compared to controlling a driving function solely via a behavior map.This offers the advantage that the driving function requires less frequent control of the swarm behavior from a behavior map. Using the proposed method, the driving function replicates a required driving behavior. The frequency of parameter adjustments for the driving function can thus be significantly reduced. Consequently, less data about the swarm behavior needs to be transmitted to or stored in the device.

[0007] In an advantageous embodiment, the swarm behavior values ​​of the second domain comprise a multitude of vehicle driving behavior values. These driving behavior values ​​include, for example, vehicle speeds during maneuvers, vehicle stopping points, lane change points, overtaking zones, or trajectories. In particular, an average of these vehicle driving behavior values ​​is used as the swarm behavior values.

[0008] This offers the advantage that the swarm behavior in the second areas of the map is adapted as precisely as possible to the current environmental conditions. This can therefore increase the accuracy of the method for controlling the driving function.

[0009] In another embodiment, the parameters for controlling the driving function are derived from calculations, whereby the calculations are performed based on the swarm behavior of the behavior map. Target values ​​are defined from the swarm behavior for these calculations, which are performed iteratively until the parameters provide a solution for achieving the target values, or until the parameters in a final iterative step yield the same number of achieved target values ​​as in a previously performed penultimate iterative step.

[0010] This allows, for example, the technical advantage that the control system can precisely replicate the required swarm behavior in as many areas of the map as possible using the parameters. This reduces the need for a separate behavioral map in the secondary areas of the map. Consequently, the processing effort for applying the parameters and the complex transfer of the behavioral map to the vehicle can be further reduced.

[0011] In another embodiment, the driving function controls the device, in particular the vehicle or the robot, in a semi- or fully autonomous driving mode.

[0012] According to a second aspect of the invention, a method for creating a map for determining a driving function of a device is proposed. The method comprises the following steps: - Controlling the driving function of the device using predefined parameters, wherein the driving function controls the device in a semi- or fully autonomous driving mode, - Locating the device within a behavior map, wherein the behavior map contains information about a swarm behavior of moving devices, wherein the swarm behavior has values ​​with a predefinable tolerance field, - Determining measured values ​​of the device's driving function, - Comparing the measured values ​​and the values ​​of the swarm behavior of the behavior map, - Creation of a map with at least a first area and a second area, wherein the first area of ​​the map is defined as the one in which the comparison between the measured values ​​and the values ​​of the swarm behavior lies within the predefinable tolerance field, wherein the second area is defined as the one in which the comparison between the measured values ​​and the values ​​of the swarm behavior lies outside the predefinable tolerance field, and wherein the values ​​of the swarm behavior of the behavior map are entered for the second area.

[0013] This allows, for example, the technical advantage that a map for determining a driving function contains as much and as precise information as possible about the control of that driving function using predefined parameters. By creating the first and second sections, the map thus provides information on whether the driving function, using the predefined parameters, represents the swarm behavior within or outside a predefined tolerance range. This ensures that the map contains precise information about the control of the driving function using the predefined parameters.

[0014] In an advantageous embodiment, the swarm behavior of the behavior map is derived from swarm behavior data, wherein the swarm behavior data contains a multitude of information about the driving behavior of vehicles, wherein the information particularly includes speeds of vehicles during driving maneuvers, and wherein the swarm behavior of the behavior map describes an average of the information from the swarm behavior.

[0015] This allows, for example, the technical advantage that the created map describes the swarm behavior of a large number of vehicles with particular accuracy.

[0016] In an advantageous embodiment, the parameters for controlling the driving function are derived from calculations, wherein the calculations are performed based on the swarm behavior of the behavior map. For the calculations, target values ​​are defined from the swarm behavior, and the calculations are performed iteratively until the parameters provide a solution for achieving the target values, or until the parameters in a final iterative step yield the same number of achieved target values ​​as in a previously performed penultimate iterative step.

[0017] This allows, for example, the technical advantage that the parameters are adapted as precisely as possible to the swarm behavior from the behavior map, thus achieving as many defined target values ​​as possible. This can lead to improved performance of the driving function.

[0018] According to a third aspect, a computing unit is proposed which is configured to execute the method according to one of the preceding claims.

[0019] According to a fourth aspect of the invention, a computer program comprising the instructions which, when executed by a computer, cause it to execute a method according to one of the independent claims.

[0020] A fifth aspect proposes a machine-readable storage medium on which the computer program is stored.

[0021] The invention is explained in more detail below with reference to exemplary figures and embodiments. These show: - Fig. 1 a schematic flowchart of a procedure according to a first aspect; - Fig. 2 a schematic flowchart of a procedure according to a second aspect; - Fig. Figure 3 shows an example of a movable device on a road section and a behavior map for creating a map; - Fig. Figure 4 shows an example map for determining a driving function of a device; - Fig. Figure 5 shows an example of a movable device on a section of road and a map; - Fig. Figure 6 shows an example of a movable device on a section of road and a map; - Fig. Figure 7 schematically shows a computing unit according to a third aspect; - Fig. Figure 8 shows a machine-readable storage medium according to a fifth aspect.

[0022] Fig. Figure 1 shows a schematic flowchart of a procedure 100 according to a first aspect.

[0023] Method 100 is used to control a driving function of a movable device, in particular a vehicle or a robot. Method 100 comprises the following steps: In a first step, parameters for controlling the driving function are read in.

[0024] The parameters for controlling the driving function can, for example, be used to control the device in autonomous or semi-autonomous operation. These parameters provide the driving function with information on how the device should be controlled. For instance, the parameters can contain information for the driving function such as acceleration duration, acceleration height, braking distance, or braking duration. Furthermore, it is also conceivable that the driving function receives information about when to steer the device through a curve and when to drive straight ahead.

[0025] Advantageously, the parameters for controlling the driving function are derived from calculations. These calculations are advantageously performed based on the swarm behavior of a behavior map. Target values ​​for the calculations are defined from the swarm behavior of the behavior map. The calculations are then performed iteratively until the parameters yield a solution for the defined target values. Alternatively, the calculations are performed iteratively until the parameters in a final iteration yield the same number of target values ​​as in a previously performed penultimate iteration. Thus, the parameters for controlling the driving function are advantageously adapted as precisely as possible to the driving behavior of a behavior map.

[0026] In a second step 120, a map is used, wherein the map has at least a first area and a second area, wherein at least one value of a swarm behavior is entered in the second area.

[0027] Advantageously, the swarm behavior values ​​in the second area encompass a wide range of vehicle driving behavior data. These values ​​can include, for example, vehicle speeds during maneuvers. Particularly preferred are swarm behavior values ​​that represent an average of the vehicle driving behavior data. The swarm behavior datasets preferably originate from manually driven vehicles, not those controlled by driver assistance systems or automated driving functions. Swarm behavior preferably describes situations in which drivers of manually driven vehicles can freely choose their speed, such as when following a truck or tractor. It is also beneficial to use a large number of datasets for swarm behavior. This means the datasets should be representative and cover a wide range of different behaviors.

[0028] In a third step (130), the device is located within the map. Based on the device's location, a decision is made between a fourth step (140) and a fifth step (150).

[0029] The device can be located within the map using common satellite location technologies, such as GPS.

[0030] In a fourth step 140, the parameters for determining the driving function are used when locating the device in the first area of ​​the map.

[0031] In a fifth step 150, at least one value of the swarm behavior is used to determine the driving function when locating the vehicle or robot in the second area of ​​the map.

[0032] In a sixth step 160, the device is controlled with the determined driving function.

[0033] By using method 100, the driving function can map the required driving behavior for controlling the device. Using the first and second sections of the map reduces the number of parameter applications for the driving function. Advantageously, there is no need for constant transfer from a behavior map to the device's back end. The behavior map, or swarm behavior, is only used in the second sections of the map. In the first sections of the map, the driving function can be controlled using the read parameters.

[0034] Fig. Figure 2 shows a schematic flowchart of a procedure 200 according to a second aspect.

[0035] Method 200 is used to create a map for determining the driving function of a device. Method 200 comprises the following steps: In a first step 200, the driving function of the device is controlled using predefined parameters, whereby the driving function controls the device in a semi- or fully autonomous driving mode.

[0036] Preferably, the parameters for the driving function are derived from calculations. These calculations are performed based on the swarm behavior of a behavior map. Target values ​​are defined from the swarm behavior, and the calculations are performed iteratively until the parameters provide a solution for achieving the target values. Alternatively, the calculations are performed until, in a final iterative step, the parameters yield the same number of achieved target values ​​as in a previously performed penultimate iterative step.

[0037] In a second step 220, the device is located within a behavior map, wherein the behavior map contains information about a swarm behavior of moving devices, wherein the swarm behavior has values ​​with a predefinable tolerance field.

[0038] The swarm behavior of the behavior map is preferably derived from swarm behavior data. This data contains a wealth of information about the driving behavior of devices, particularly vehicles. For example, the swarm behavior data may include vehicle speeds during maneuvers. Preferably, the swarm behavior is determined from a large number of swarm behavior data points and can be calculated as the average of different vehicle speeds during the same maneuver. Predefinable tolerance fields are defined for the target values ​​of the swarm behavior. For example, the tolerance field could represent a deviation from an average speed of the swarm behavior. Thus, an average speed of 100 km / h could be represented by a tolerance field of ± 1 km / h.

[0039] In a third step 230, measured values ​​of the driving function of the device are determined.

[0040] The measured values ​​obtained from the driving function include, for example, the device's speeds achieved at defined locations or areas using the parameter-controlled driving function. Thus, during device control via the driving function, the actual speeds achieved by the device in semi- or fully autonomous driving mode are recorded.

[0041] In a fourth step, the measured values ​​and the values ​​of the swarm behavior of the behavior map are compared.

[0042] Each value of the swarm behavior with its associated tolerance field is compared with the corresponding measured value from the journey.

[0043] In a fifth step 250, a map with at least one first area and at least one second area is created. The first area of ​​the map is defined as the one in which the comparison between the measured values ​​and the values ​​of the swarm behavior lies within the tolerance field, and the second area is defined as the one in which the comparison between the measured values ​​and the values ​​of the swarm behavior lies outside the tolerance field, with the values ​​of the swarm behavior from the behavior map being entered for the second area.

[0044] Consequently, the proposed method provides a map containing precise information about the control of a device with a driving function based on predefined parameters. The map indicates in which areas the control of the driving function, using the predefined parameters, falls within a defined tolerance range. In the second area, the map indicates that the control of the driving function, using the parameters, falls outside the predefined tolerance range, meaning it inadequately represents the desired driving behavior. The map thus created can then be used to determine the driving function of a device. Preferably, the created map is used for the method described in the first aspect.

[0045] In the following Fig. 3 and Fig. Figure 4 shows by way of example how the procedure 200 can be used to create a map for determining a driving function.

[0046] Fig. Figure 3 shows an example of a movable device 1 on a road section 7 and a behavior map 8 for creating a map.

[0047] A movable device 1, in particular a vehicle, is located on a road section 7. The movable device 1 can be any type of movable device, including, in particular, a robot. The movable device 1 is controlled by a driving function 5 and predefinable parameters 6 to operate semi-autonomously or fully autonomously on the road section 7.

[0048] Furthermore, a behavior map 8 with information about swarm behavior 9 is shown. The behavior map 8 is highly simplified and shows only a small part of a complete behavior map as an example. The behavior map 8, for instance, depicts a road in the form of a winding road. Road segment 7 is part of the road shown in the behavior map 8. The movable device 1 is located, for example, via a GPS signal within the behavior map 8 using a localization point 18.

[0049] The behavior map 8 is stored, for example, on an external computing unit or in the cloud. The parameters 6 for controlling the vehicle's driving function 5 preferably originate from calculations performed by an external computing unit based on the behavior map 8. The swarm behavior 9 from the behavior map 8 is preferably used for these calculations.

[0050] The swarm behavior 9 from the behavior map 8 is derived from various vehicle test runs and describes, for example, a multitude of speeds during different driving maneuvers. Preferably, average speeds of manually controlled vehicles are used. Furthermore, the swarm behavior 9 can also include stopping points, lane change points, overtaking zones, and trajectories.

[0051] Target values ​​10, 11, 12, and 13 are defined based on the swarm behavior 9. Four target values ​​10, 11, 12, and 13 are shown as examples. Calculations for the parameters 6 can be performed based on the target values ​​10, 11, 12, and 13. Preferably, the calculations are performed in iterative steps until the parameters 6 provide a solution for achieving the target values ​​10, 11, 12, and 13, or until the parameters 6, in a final iterative step, yield the same number of achieved target values ​​10, 11, 12, and 13 as in a previously performed penultimate iterative step.

[0052] During autonomous or semi-autonomous operation of the moving device 4, measured values ​​14 are recorded using sensors. These measured values ​​14 include, for example, the speeds of the moving device 4 at the determined localization point 18 in the behavior map 8. Measured values ​​14 of the moving device are recorded for several target values ​​10, 11, 12, 13. Subsequently, a comparison is made between the target values ​​10, 11, 12, 13 and the measured values ​​14. A tolerance range is also specified for each target value. For example, a first target value 10 might have a tolerance range of ± 1 km / h. Furthermore, a second target value 11 might have a tolerance range of ± 2 km / h. The third target value 12 and the fourth target value 13 might, for example, again have a tolerance range of ± 1 km / h.By comparing the measured values ​​14 and the target values ​​10, 11, 12, 13, a statement can then be made as to whether the movable device 4 meets the defined requirements through the use of the driving function 5. A map is then created from the comparison of the measured values ​​14 and the target values ​​10, 11, 12, 13. An example of such a map is shown below. Fig. 4 described.

[0053] Fig. Figure 4 shows an example of a map 15 created for determining a driving function of a moving device.

[0054] Map 15 has a first area 16 and a second area 17. The creation of these areas is based on the results of comparing the measured values ​​and target values ​​from Fig. 3. The first area 16 of the map is defined as the area in which the comparison between the measured values ​​and the target values ​​from the swarm behavior lies within the specified tolerance field. Thus, in this example, the lower area of ​​map 15 was defined as the first area 16. In other words, this means that in the first area 16, the driving function, using the parameters, adequately replicates the required swarm behavior.

[0055] In the second area 17, the swarm behavior is represented by the first target value 10 and the second target value 11, as shown on map 15. These values ​​were entered because the recorded measurements for target values ​​10 and 11 were outside the specified tolerance range. In other words, this means that in the second area 17, the target values ​​10 and 11 could not be replicated with sufficient accuracy using the control of the driving function and the parameters.

[0056] The resulting map 15 can be used to carry out a procedure according to the first aspect. The following serve as an exemplary description of the use of such a map 15. Fig. 5 and Fig. 6.

[0057] Fig. Figure 5 shows, by way of example, a movable device 1 on a road section 7 and a map 15.

[0058] The movable device 1 on road section 7 is, by way of example, a vehicle. The vehicle has map 15, a driving function 5, and parameters 6 for controlling the driving function 5. Map 15 was created with a previously described and in Fig. 3 and Fig. The map 15 is created according to the procedures described in section 4. It is stored online in the mobile device 1. During travel on road segment 7, the mobile device 1 is located in the map 15 via a localization point 18, for example, via a GPS signal. The map 15 has a first area 16 and a second area 17.

[0059] In this example, the movable device 1 is located in the first area 16 using the localization point 18. Therefore, the movable device 1 receives the information from the map 15 to use the parameters 6 to determine the driving function 5 and to control it via the determined driving function 5.

[0060] Fig. Figure 6 shows, by way of example, a movable device 1 on a road section 7 and a map 15.

[0061] The movable device 1, or the vehicle, is again located on a road segment 7 and has the driving function 5. Furthermore, the map 15 with the first area 16 and the second area 17 is again stored in the movable device 1. The movable device 1 on the road segment 7 is located via the localization point 18. In this embodiment, the movable device 1 is located in the second area 17 of the map. Since the localization, unlike in Fig. Since the parameters for determining driving function 5 are now located in the second area 17 of the map, they are not used. In this case, driving function 5 accesses the first target value 10 and the second target value 11, which are stored in the second area 17 of the map. In this embodiment, driving function 5 is therefore determined and controlled via the values ​​of the swarm behavior, in particular the target values ​​10 and 11. Thus, the movable device 1 also replicates the required swarm behavior when passing through road section 7.

[0062] Based on Fig. 5 and Fig. Section 6 thus illustrates how the driving function 5 for a moving device 1, for example during a curve, can be determined using map 15. Depending on which area the moving device 1, or the location point 18 for the device, is in, the correct driving function 5 is determined. This significantly reduces the need for frequent access to a behavior map or frequent adjustments of the parameters 6 for controlling the driving function 5. This offers the advantage that a moving device 1 can be controlled efficiently and with the desired performance in all areas of map 15 using map 15.

[0063] Fig. 7 shows a calculation unit 4 according to a third aspect.

[0064] The computing unit 4 is configured to perform all steps of the previously described procedures, including advantageous embodiments. The computing unit 4 can, in particular, be a computer.

[0065] Fig. Figure 8 shows a machine-readable storage medium 3 according to a fifth aspect.

[0066] A computer program 2 according to the fourth aspect is stored on the machine-readable storage medium 3. The computer program 2 comprises instructions which, when executed by a computer, cause the computer program 2 to execute a method according to the independent claims. The machine-readable storage medium 3 can, for example, be provided by the computing unit 4. Fig. 7 can be read.

[0067] Although the invention has been described here with reference to specific embodiments, the person skilled in the art can also realize embodiments that have not been disclosed or have only been partially disclosed, without deviating from the core of the invention.

Claims

[1] Method (100) for controlling a driving function (5) of a movable device (1), in particular a vehicle or a robot, comprising the steps: - Reading (110) parameters (6) for controlling the driving function (5), - Using (120) a card (15) wherein the card (15) has at least a first area (16) and a second area (17) wherein at least one value of a swarm behavior (9) is entered in the second area (17), - Locating (130) the device on the map (15), - Using (140) the parameters (6) to determine the driving function (5) when the movable device (1) is in the first area (16) of the map (15), - Using (150) at least one value of the swarm behavior (9) to determine the driving function (5) when the movable device (1) is in the second area (17) of the map (15), - Controlling (160) the device with the determined driving function (5). [2] Method (100) according to claim 1, wherein the swarm behavior value (9) of the second area (17) comprises a plurality of values ​​of the driving behavior of vehicles, wherein the values ​​include in particular speeds of vehicles during driving maneuvers, wherein the swarm behavior value is an average of the values ​​of the driving behavior of vehicles. [3] Method (100) according to claim 1 or 2, wherein the parameters (6) for controlling the driving function (5) are derived from calculations, wherein the calculations are performed on the basis of the swarm behavior (9) of a behavior map (8), wherein target values ​​(10, 11, 12, 13) are defined from the swarm behavior (9) for the calculations, wherein the calculations are performed in iterative steps until the parameters (6) provide a solution for achieving the target values ​​(10, 11, 12, 13), or until the parameters (6) in a final iterative step provide the same number of achieved target values ​​(10, 11, 12, 13) as in a previously performed penultimate iterative step. [4] Method (100) according to one of the preceding claims, wherein the driving function controls the movable device (1), in particular the vehicle or the robot, in a semi- or fully autonomous driving mode. [5] Method (200) for creating a map (15) for determining a driving function (5) of a movable device (1) for a method (100) according to one of the preceding claims comprising the steps: - Controlling (210) the driving function (5) of the movable device (1) using predefined parameters (6), wherein the driving function (5) controls the movable device (1) in a semi- or fully autonomous driving mode, - Locating (220) the moving device (1) within a behavior map (8), wherein the behavior map (8) contains information about a swarm behavior (9) of moving devices, wherein the swarm behavior (9) contains values ​​with a predefinable tolerance field, - Determining (230) measured values ​​(14) of the driving function (5) of the moving device (1), - Comparing (240) the measured values ​​(14) and the values ​​of the swarming behavior (9) from the behavior map (8), - Creating (250) a map (15) with at least one first area (16) and a second area (17), wherein the first area (16) of the map (15) is defined as the one in which the comparison between the measured values ​​(14) and the values ​​of the swarm behavior (9) lies within the tolerance field, wherein the second area (17) is defined as the one in which the comparison between the measured values ​​(14) and the values ​​of the swarm behavior (9) lies outside the tolerance field, wherein at least one value of the swarm behavior (9) from the behavior map (8) is entered for the second area (17). [6] Method (200) according to claim 5, wherein the swarm behavior (9) of the behavior map (8) is derived from swarm behavior data, wherein the swarm behavior data includes a multitude of information about the driving behavior of vehicles, wherein the information includes in particular speeds of vehicles during driving maneuvers, wherein the swarm behavior (9) of the behavior map (8) describes an average of the information from the swarm behavior data. [7] Method (200) according to claim 5 or 6, wherein the parameters (6) for controlling the driving function (5) are derived from calculations, wherein the calculations are performed on the basis of the swarm behavior (9) of the behavior map (8), wherein target values ​​(10, 11, 12, 13) are defined from the swarm behavior (9) for the calculations, wherein the calculations are performed in iterative steps until the parameters (6) provide a solution for achieving the target values ​​(10, 11, 12, 13), or until the parameters (6) in a final iterative step provide the same number of achieved target values ​​(10, 11, 12, 13) as in a previously performed penultimate iterative step. [8] Computing unit (4) which is configured to perform the method according to any of the preceding claims. [9] Computer program (2) comprising the instructions which, when the computer program (2) is executed by a computer, cause it to execute a method according to any one of claims 1 to 7. [10] Machine-readable storage medium (3) on which the computer program (2) according to claim 9 is stored.

Images