Method for functional improvement of environment modeling in a vehicle assistance system

Abstract

The invention relates to a method (100) for functionally improving an environment model in an assistance system (2) of a vehicle (1), comprising the following steps: - Providing (101) at least two calculation paths (3) of the assistance system (2), wherein the calculation paths (3) comprise a respective environmental detection, wherein an analysis and a fusion (4) of sensor data (5a) is carried out within the scope of the environmental detection, wherein the sensor data (5a) result from a detection of at least one sensor (5) of the vehicle (1), - determining (102) at least one action option for the vehicle (1) from each of the at least two calculation paths (3) on the basis of the respective environmental detection, - exchanging (103) a respective result of the environment detection between the respective calculation paths (3), - modifying (104) the at least one action option of at least one of the calculation paths (3) on the basis of the respective exchanged result of the environment detection, wherein at least one safety requirement, in particular all safety requirements, of the respective calculation path (3) are taken into account in order to provide the functional improvement of the environment modeling in the assistance system (2), - determining (105) a target action option for the assistance system (2) on the basis of a result of the modification (104). Furthermore, the invention relates to a computer program, a device and a storage medium for this purpose.

Description

[0001] The invention relates to a method for functionally improving environment modeling in a vehicle assistance system. Furthermore, the invention relates to a computer program, a device, and a storage medium for this purpose. State of the art

[0002] The correct detection of the environment, including all relevant road users, obstacles, and boundaries, is a key component of a driver assistance system. Various environmental sensors, such as cameras, radar, lidar, or ultrasonic sensors, are used for this purpose. These sensors have different advantages and disadvantages due to their physical properties, installation location, different algorithms, or aging. Therefore, today's assistance systems usually employ several, sometimes different, sensors. A fusion algorithm based on this algorithm combines the sensor data, taking into account the various advantages and disadvantages of the sensors, with the goal of creating the most accurate image of the real environment with all relevant object properties. Such a combination is referred to as environmental detection in the context of the present invention.The requirements for environmental sensing increase with the complexity of the automated driving system in terms of functional safety (FuSa) and the safety of the intended function (SOTIF). For higher levels of automation, various implementations are often provided to meet the safety requirements, as is the case with the aforementioned fusion algorithm. While various state-of-the-art approaches provide multiple paths, the paths are kept completely separate. This can, for example, lead to errors with the same cause. Disclosure of the invention

[0003] The invention relates to a method having the features of claim 1, a computer program having the features of claim 8, a device having the features of claim 9, and a computer-readable storage medium having the features of claim 10. Further features and details of the invention emerge from the respective subclaims, the description, and the drawings. Features and details described in connection with the method according to the invention naturally also apply in connection with the computer program according to the invention, the device according to the invention, and the computer-readable storage medium according to the invention, and vice versa, so that reciprocal reference is always possible with regard to the disclosure of the invention.

[0004] The invention particularly relates to a method for functionally improving environmental modeling in a vehicle assistance system, comprising the following steps, wherein the steps can be performed repeatedly and / or sequentially. The assistance system is, in particular, a multi-path assistance system, i.e., an assistance system that has at least two redundant calculation paths. The assistance system can be designed for at least partially automated control of the vehicle or provision of at least one vehicle function and, for this purpose, can use, for example, a processor for calculation and have various software modules.

[0005] In a first step, preferably at least two calculation paths of the assistance system are provided. The at least two calculation paths are in particular two redundant calculation paths and provide the same vehicle function for the vehicle, for example a control or distance control. The calculation paths in particular comprise a respective environmental detection, wherein an analysis and a fusion of sensor data is carried out as part of the environmental detection. During the fusion of the sensor data, a representation of the vehicle's environment is generated, in particular based on the analyzed sensor data. The sensor data preferably result from a detection by at least one sensor of the vehicle. The at least one sensor can be, for example, a camera, a radar sensor, an ultrasonic sensor and / or a LiDAR sensor.

[0006] In a further step, preferably at least one action option for the vehicle is determined from each of the at least two calculation paths based on the respective environmental detection. The action option includes, in particular, a specific control of the vehicle or a manner in which a vehicle function is executed, for example, values ​​for parameters of the vehicle function. The environmental detection is taken into account or used as a basis, for example, by steering the vehicle into an open space based on the action option, which is determined based on the environmental detection.

[0007] In a further step, a respective result of the environmental detection is preferably exchanged between the respective calculation paths. In particular, a one-way exchange can also be provided, so that only one calculation path makes the respective result of the environmental detection available to the at least one further calculation path. It is also conceivable for each calculation path to make its respective result of the environmental detection available to all further calculation paths. The exchange can, for example, be a data exchange between corresponding software modules. The result of the environmental detection can, for example, be a representation of the environment generated based on the fusion of the analyzed sensor data.

[0008] In a further step, the at least one action option of at least one of the calculation paths is preferably modified based on the respective exchanged result of the environment detection, wherein at least one safety requirement, in particular all safety requirements, of the respective calculation path are taken into account in order to provide the functional improvement of the environment modeling in the assistance system. The safety requirement can, for example, be a distance to a vehicle ahead or a distance to a guardrail or compliance with a speed limit. The modification can, for example, be an adaptation of parameter values ​​of a vehicle function, in particular an adaptation of a trajectory if the action option is implemented as a trajectory. Furthermore, as part of the modification, an acceleration or braking process of the vehicle can be varied, for example.At the end of the modification, the at least one course of action can be validated, whereby it is determined and indicated whether the at least one course of action meets the at least one safety requirement, in particular all safety requirements.

[0009] In a further step, a target course of action for the assistance system is preferably determined based on the result of the modification. The result of the modification can, for example, indicate a course of action validated with regard to the at least one safety requirement. When determining the target course of action, a balance can also be struck between at least two course of action options, and one of the at least two course of action options can be selected, taking the at least one safety requirement into account.

[0010] It can further advantageously be provided that one of the at least two calculation paths is a main path and the at least one further calculation path is an auxiliary path, wherein the main path is used with priority for controlling the vehicle. The auxiliary path is thus in particular a substitute path which can be used, for example, if an error is detected in the main path. In this case, the exchange is preferably carried out from the at least one auxiliary path to the main path, in particular exclusively from the at least one auxiliary path to the main path. In an alternative, the exchange can be carried out from the main path to the at least one auxiliary path if an error is detected in the main path.

[0011] It is also advantageous if the respective environmental detections of the calculation paths differ from one another with regard to the processing of the sensor data and / or the sensors used. Thus, in particular, there is no homogeneous redundancy between the at least two calculation paths. This advantageously expands the database used for modifying the at least one action option and for determining the target action option, since at least two calculation paths, or their respective environmental detections, are taken into account.

[0012] In a further embodiment, the at least one action option can describe a trajectory to be followed by the vehicle. The trajectory is, in particular, a planned movement of the vehicle through space and can further include a planning of an acceleration and / or braking process of the vehicle.

[0013] Furthermore, within the scope of the invention, it is conceivable for the at least two calculation paths to each process at least two data inputs, with each data input being provided for a respective environmental detection. Preferably, only one environmental detection associated with the respective calculation path is used to determine the at least one action option for the vehicle. Thus, advantageously, the at least one action option can initially be determined independently by the at least two calculation paths.

[0014] It is also advantageous if, within the scope of the invention, the modification comprises the following step: - Checking the at least one determined course of action on the basis of an analysis of the exchanged respective result of the environmental detection, taking into account the at least one safety requirement, in particular all safety requirements, of the respective calculation path.

[0015] Testing can also be referred to as validation and may include, for example, an analysis of a determined trajectory, ie the course of action, with regard to a distance to a vehicle ahead, ie the safety requirement.

[0016] It can be provided within the scope of the invention that the determination comprises the following step: - Selecting one of the at least two calculation paths based on a result of the check in order to determine the target action option for the assistance system using the selected calculation path.

[0017] For example, if one of the calculation paths is the main path, it can be provided that this is selected by default. However, if, for example, an error is detected in the main path based on the environmental detection, the at least one additional calculation path can be selected. It can be provided that, despite the error in the main path, this additional calculation path uses the environmental detection of the main path, taking the error into account, to determine the target action option for the assistance system.

[0018] It is possible for the method according to the invention to be used in a vehicle. The vehicle can be designed, for example, as a motor vehicle and / or passenger vehicle and / or as an at least partially autonomous or automated vehicle. The vehicle can have a vehicle device, for example, for providing an at least partially autonomous or automated driving function and / or an assistance system. The vehicle device can be designed to control the vehicle at least partially automatically and / or to accelerate and / or decelerate and / or steer it.

[0019] The invention also relates to a computer program, in particular a computer program product, comprising instructions that, when executed by a computer, cause the computer to carry out the method according to the invention. Thus, the computer program according to the invention provides the same advantages as those described in detail with reference to a method according to the invention.

[0020] The invention also relates to a data processing device configured to carry out the method according to the invention. The device can be, for example, a computer that executes the computer program according to the invention. The computer can have at least one processor for executing the computer program. A non-volatile data memory can also be provided, in which the computer program is stored and from which the computer program can be read by the processor for execution.

[0021] The invention may also provide a computer-readable storage medium that contains the computer program according to the invention and / or includes instructions that, when executed by a computer, cause the computer to carry out the method according to the invention. The storage medium is designed, for example, as a data storage device such as a hard disk and / or a non-volatile memory and / or a memory card. The storage medium can, for example, be integrated into the computer.

[0022] Furthermore, the method according to the invention can also be implemented as a computer-implemented method.

[0023] Further advantages, features, and details of the invention will become apparent from the following description, which describes embodiments of the invention in detail with reference to the drawings. The features mentioned in the claims and in the description may be essential to the invention individually or in any combination. They show: Fig. 1 a schematic visualization of a method, a vehicle with an assistance system and a sensor, a device, a storage medium and a computer program according to embodiments of the invention, Fig. 2 a schematic representation of a method according to embodiments of the invention.

[0024] In Fig. 1 schematically shows a method 100, a vehicle 1 with an assistance system 2 and a sensor 3, a device 10, a storage medium 15 and a computer program 20 according to embodiments of the invention.

[0025] Fig. 1 shows, in particular, a method 100 for functionally improving environmental modeling in an assistance system 2 of a vehicle 1. In a first step 101, at least two calculation paths 3 of the assistance system 2 are provided, wherein the calculation paths 3 comprise a respective environmental detection, wherein, as part of the environmental detection, an analysis and a fusion 4 of sensor data 5a is carried out. The provision can comprise retrieving from a data storage device and executing at least one software module of the assistance system 2. The sensor data 5a result from a detection by at least one sensor 5 of the vehicle 1. In a second step 102, at least one action option for the vehicle 1 is determined by each of the at least two calculation paths 3 based on the respective environmental detection, in particular by executing at least one software module by a processor of the assistance system 2.In a third step 103, a respective result of the environmental detection is exchanged between the respective calculation paths 3, in particular by executing at least one software module by a processor of the assistance system 2. In a fourth step 104, the at least one action option of at least one of the calculation paths 3 is modified based on the respective exchanged result of the environmental detection, wherein at least one safety requirement, in particular all safety requirements, of the respective calculation path 3 are taken into account in order to provide the functional improvement of the environmental modeling in the assistance system 2. This is carried out in particular by executing at least one software module by a processor of the assistance system 2.In a fifth step 105, a target action option for the assistance system 2 is determined based on a result of the modification 104, in particular by executing at least one software module by a processor of the assistance system 2.

[0026] Fig.2 schematically shows a method according to exemplary embodiments of the invention. In the two illustrated calculation paths 3, the environmental detection is initially provided based on sensor data 5a and a fusion step 4. This result of the environmental detection is exchanged between the calculation paths 3. In a further step 103, at least one action option is determined from each calculation path 3 by a planner module 6, taking both environmental detections into account. In a further step 105, a target action option is selected by the planner module 6. The planner module 6 can be a software module and executed by a processor of the assistance system 2.

[0027] The present invention describes, according to embodiments, a method for merging fusion approaches of calculation paths 3 or for using an alternative fusion approach of a calculation path 3, for example, in order to increase security with regard to SOTIF while simultaneously avoiding "common causes".

[0028] A prerequisite for the method according to exemplary embodiments is, in particular, a security architecture with two functional calculation paths 3, both of which include different environmental detection, comprising a sensor system 2 and fusion 4. Such multi-path systems are already known, particularly for L3 and L4 approaches with a wide range of functions.

[0029] The differences in environmental detection can include a different sensor configuration, different processing, or both. For the SOTIF benefit, a certain difference must preferably exist, i.e., there must not be purely homogeneous redundancy. One aspect of the invention according to exemplary embodiments is, in particular, the use of the results of environmental detection from one calculation path 3 in the other in order to reduce the frequency or risk of an incorrect reaction. At the same time, this can advantageously exclude errors that occur simultaneously in both calculation paths 3 and therefore render the overall system, or the assistance system 2, no longer operational. This can guarantee that an error in one calculation path 3 does not simultaneously negatively affect the other calculation path 3.

[0030] A basic prerequisite for using the method is two redundant calculation paths 3. For reasons of functional safety, this can often be the case for L3 / L4 systems or vehicles 1. Even in the event of a fault, continued operation should preferably be ensured until a safe state is reached. Various calculation paths 3 can help to rule out common cause errors. If this is the case, the method according to exemplary embodiments can be particularly advantageous. Another aspect of safety is, in particular, the safety of the intended function (SOTIF). In short, the system, i.e. in particular vehicle 1, must preferably function sufficiently well to be able to master even critical situations (in the absence of functional safety errors).In order to function sufficiently well, it may be desirable to use the results of the various environmental detections of the at least two calculation paths 3 when executing a nominal function (in normal operation).

[0031] According to exemplary embodiments, the invention thus provides that the results of the environmental detections of the calculation paths 3 are each made available to the other calculation path. In order to exclude "common cause" errors, a simple merging of the results is preferably not possible. The calculation paths 3 that use the results must therefore preferably be capable of handling two inputs. The input of their own calculation path 3 preferably enjoys priority. This alone is preferably used to determine the at least one course of action, for example, by generating a trajectory bundle. The possible course of action is preferably checked with the second input. Course of action that is considered safe with both inputs is preferred.If, in extreme situations, no calculated course of action satisfies the constraints of the second input, this can be interpreted as the first sign of an error. Since the same procedure is performed in parallel in the second calculation path 3, in such a case, calculation path 3 can be changed if a trajectory is found in the second calculation path 3 that is considered safe based on environmental detection.

[0032] The above explanation of the embodiments describes the present invention exclusively by way of examples. Of course, individual features of the embodiments can be freely combined with one another, provided they are technically feasible, without departing from the scope of the present invention.

Claims

[1] Method (100) for functionally improving an environment model in an assistance system (2) of a vehicle (1), comprising the following steps: - Providing (101) at least two calculation paths (3) of the assistance system (2), wherein the calculation paths (3) comprise a respective environmental detection, wherein an analysis and a fusion (4) of sensor data (5a) is carried out within the scope of the environmental detection, wherein the sensor data (5a) result from a detection of at least one sensor (5) of the vehicle (1), - determining (102) at least one action option for the vehicle (1) from each of the at least two calculation paths (3) on the basis of the respective environmental detection, - exchanging (103) a respective result of the environment detection between the respective calculation paths (3), - modifying (104) the at least one action option of at least one of the calculation paths (3) on the basis of the respective exchanged result of the environment detection, wherein at least one safety requirement, in particular all safety requirements, of the respective calculation path (3) are taken into account in order to provide the functional improvement of the environment modeling in the assistance system (2), - determining (105) a target action option for the assistance system (2) on the basis of a result of the modification (104). [2] Method (100) according to claim 1, characterized by , that one of the at least two calculation paths (3) is a main path and the at least one further calculation path (3) is an auxiliary path, wherein the main path is used with priority for controlling the vehicle (1), wherein the exchange (103) is performed from the at least one auxiliary path to the main path. [3] Method (100) according to one of the preceding claims, characterized by that the respective environmental detection of the calculation paths (3) differ from one another with regard to processing of the sensor data (5a) and / or with regard to the sensors used. [4] Method (100) according to one of the preceding claims, characterized by that the at least one action option describes a trajectory to be driven by the vehicle (1). [5] Method (100) according to one of the preceding claims, characterized by that the at least two calculation paths (3) each process at least two data inputs, wherein a respective data input is provided for a respective environmental detection, wherein only one environmental detection assigned to the respective calculation path (3) is used for determining (102) the at least one action option for the vehicle (1). [6] Method (100) according to one of the preceding claims, characterized bythat the modifying (104) comprises the following step: - Checking the at least one determined course of action on the basis of an analysis of the exchanged respective result of the environmental detection, taking into account the at least one safety requirement, in particular all safety requirements, of the respective calculation path (3). [7] Method (100) according to claim 6, characterized by that the determining (105) comprises the following step: - Selecting one of the at least two calculation paths (3) based on a result of the check in order to determine the target action option for the assistance system (2) using the selected calculation path (3). [8] Computer program (20) comprising instructions which, when the computer program (20) is executed by a computer (10), cause the computer (10) to carry out the method (100) according to one of the preceding claims. [9] Device (10) for data processing, which is arranged to carry out the method (100) according to one of claims 1 to 7. [10] A computer-readable storage medium (15) comprising instructions which, when executed by a computer (10), cause the computer (10) to carry out the steps of the method (100) according to any one of claims 1 to 7.

Images