Method, computing unit and computer program for executing a driver assistance function during the operation of a rail vehicle

Abstract

The invention relates to a method (200) for executing a driver assistance function during the operation of a rail vehicle (10), comprising receiving at least one setting signal (210) containing information regarding an assistance function configuration (231, 232, 233, 234, 235, 236) to be applied, selecting the assistance function configuration (220) to be applied from a set of assistance function configurations (231, 232, 233, 234, 235, 236) based on the at least one setting signal (210), executing the driver assistance function depending on the selected assistance function configuration to determine an assistance measure, and executing the assistance measure.

Description

[0001] The invention relates to a method for carrying out a driver assistance function during operation of a rail vehicle, as well as a computing unit, a driver assistance system and a rail vehicle for carrying out the method, as well as a corresponding computer program and a storage medium. Background of the invention

[0002] Collision warning systems for light rail vehicles and trams can be used to detect critical driving situations. Such a system can consist, for example, of a camera, a radar sensor, and a control unit. Such systems can, for example, record the track layout and thus also obstacles in front of the rail vehicle in real time. If the system detects a potential collision hazard, a warning can be issued to the driver. If the driver fails to react or reacts too late, some collision warning systems can initiate automatic braking. An example of such a collision warning system is shown in the subsequently published DE 10 2022 210 974. Disclosure of the invention

[0003] According to the invention, a method, in particular a computer-implemented method, for executing a driver assistance function during operation of a rail vehicle, as well as a computing unit and a computer program for implementing the method, as well as a collision warning system and a rail vehicle with such a driver assistance system, are proposed, having the features of the independent patent claims. Advantageous embodiments are the subject of the dependent claims and the following description.

[0004] The invention utilizes the measure of receiving a setting signal containing information regarding an assistance function configuration to be used, and adapting and executing the assistance function accordingly to this required assistance function configuration. This allows a driver assistance system for a rail vehicle to be designed adaptively to respond flexibly to different application scenarios.

[0005] In detail, a method according to the invention for executing a driver assistance function during operation of a rail vehicle comprises receiving at least one setting signal containing information regarding an assistance function configuration to be applied, selecting the assistance function configuration to be applied from a set of assistance function configurations based on the at least one setting signal, executing the driver assistance function depending on the selected assistance function configuration to determine an assistance measure, and executing the assistance measure. This can, for example, reduce the frequency of incorrectly performed assistance measures, for example false warnings, and possibly increase the frequency of useful assistance measures, for exampleBenefit warnings, which leads overall to greater acceptance of the system and thus to greater operational safety of the affected rail vehicle.

[0006] In at least one embodiment, the at least one setting signal comprises a signal received based on a user specification. For example, a user (driver) of the rail vehicle can select a desired warning strategy to increase acceptance of the system and avoid a blunting effect. For example, drivers who generally rate their own driving and reaction ability highly ("aggressive drivers") can specify a later intervention of the assistance measure, while drivers who have a greater need for safety ("defensive drivers") can select a lower trigger threshold (an earlier intervention of the assistance measure). In particular, an information signal containing information about the received setting signal can be output in this case or in response to the received setting signal.For example, a corresponding display can be provided in the control station of the rail vehicle so that the driver can check whether the input was recorded correctly. Alternatively or additionally, a corresponding information signal can be transmitted to a fleet management system to enable central monitoring.

[0007] In at least one embodiment, different types of assistance measures can be determined by different assistance function configurations, wherein the different types of assistance measures can include, in particular, issuing a warning, in particular an acoustic and / or visual warning, to a person in the rail vehicle, in particular a driver of the rail vehicle, and / or a person outside the rail vehicle, in particular in an area in front of the rail vehicle in the direction of travel, and / or automated deceleration, in particular braking. This makes safety-relevant measures available, in particular. A warning of the surroundings can, in particular, be made dependent on the type of object that has been detected (object classification), since only moving objects (e.g.Animals, vehicles or people) may even be able to leave the track area when warned.

[0008] Alternatively or additionally, different assistance function configurations can determine different times, in particular for the execution of the assistance measure. In particular, the different times can be selected depending on a type of assistance measure, in particular as defined above, and / or depending on a current speed of the rail vehicle and / or depending on a maximum target deceleration and / or depending on a current and / or minimum acceptable distance from an object located in front of the rail vehicle in the direction of travel. As a result, the assistance measure can be carried out in such a way that intervention occurs in a timely manner, but is not perceived as disruptive or patronizing, in particular by the driver, which increases the acceptance of the assistance system.For example, it can be provided that a warning is triggered in time for the driver to be able to stop by his own intervention, and / or that an automatic braking request is triggered in time for the rail vehicle to avoid colliding with a detected obstacle.

[0009] In at least one embodiment, as an alternative or in addition to the procedures described so far, it can be provided that different triggers of the assistance measure are determined by different assistance function configurations, wherein the different triggers include, in particular, a risk of collision with an object, in particular with a person and / or an animal and / or a vehicle and / or another rail vehicle and / or an immovable object and / or an impassable component of the rail infrastructure. For example, in a rail vehicle depot orOn a company premises, warning the surrounding area when the presence of people is detected can be omitted because, on the one hand, it can be assumed that people in such an environment are already aware of the danger, and, on the other hand, very frequent warnings can be expected, since people often work in the track area in such an environment. The fact that the rail vehicle is in a depot can be communicated, for example, via a setting signal. Similar assistance function adaptations can also be applied to other trigger events or other deployment scenarios.

[0010] Furthermore, it can be provided that an assistance function configuration (in particular including triggering event(s) and / or a scope of assistance functions and / or the assistance measure(s)) is defined manually and / or on the basis of dedicated, predefined input parameters. Such input parameters can include, for example, a desired and / or maximum possible braking deceleration, a driver reaction time to be taken into account, a desired stopping distance (safety distance between the rail vehicle after standstill and the obstacle that triggers the brake), a reaction time of the rail vehicle or the driver assistance system, and desired triggers for the respective assistance function.

[0011] A computing unit according to the invention, e.g., a control unit of a rail vehicle, is configured, in particular in terms of programming, to carry out a method according to the invention. A driver assistance system according to the invention comprises such a computing unit and, in particular, at least one sensor, in particular a radar unit and / or a camera unit, wherein the sensor unit is configured to detect an environment of the rail vehicle and to provide the computing unit with sensor data relating to the detected environment. Furthermore, a rail vehicle with such a driver assistance system is proposed.

[0012] The implementation of a method according to the invention in the form of a computer program or computer program product with program code for carrying out all method steps is also advantageous, since this entails particularly low costs, in particular if an executing control unit is also used for other tasks and is therefore already present. Finally, a machine-readable storage medium is provided with a computer program stored thereon, as described above. Suitable storage media or data carriers for providing the computer program are, in particular, magnetic, optical and electrical memories, such as hard disks, flash memories, EEPROMs, DVDs, and others. Downloading a program via computer networks (Internet, intranet, etc.) is also possible. Such a download can be wired or cable-based or wireless (e.g. via a WLAN network, a 3G, 4G, 5G or 6G connection, etc.).Preferably, the computer program comprises commands which, when executed by the driver assistance system, cause the driver assistance system to execute the proposed method.

[0013] Further advantages and embodiments of the invention will become apparent from the description and the accompanying drawings.

[0014] The invention is illustrated schematically in the drawing using exemplary embodiments and is described below with reference to the drawing. Short description of the drawings Fig. 1 shows a rail vehicle as it can be used in embodiments of the invention, in a schematic representation. Fig. 2 schematically shows a method according to the invention in the form of a highly simplified flow chart. Fig. 3 schematically shows an application situation as it may occur within the scope of embodiments of the invention. Embodiment(s) of the invention

[0015] In the following, a driver assistance system (or a corresponding method) according to one embodiment of the invention is explained using the scenario of determining a collision risk as an example. This example serves merely as an illustration and is in no way intended to exclude the possibility that other assistance functions, in particular assistance functions that are not related to a possible collision of the rail vehicle with another object, may also be enabled by the invention.

[0016] In Fig. 1, a rail vehicle, as can be used within the scope of this invention, is schematically illustrated and designated overall by 10. The rail vehicle 10 is designed as a tram and comprises a driver assistance system 12 with two sensor units 14, 16, which according to this embodiment are designed as a radar unit 14 and a camera unit 16, as well as a computing unit designed as a control unit 18.

[0017] The radar unit 14 and the camera unit 16 are arranged in a front region 20 of the rail vehicle 10 and aligned along a direction of travel 22 of the rail vehicle 10. The radar unit 14 and the camera unit 16 are configured to detect the surroundings of the rail vehicle 10 ahead of the rail vehicle along the direction of travel 22 in order to provide the computing unit 18 with sensor data, i.e., radar data and image data, regarding the surroundings ahead. The sensor data may include information regarding an object 24, e.g., a pedestrian, in the surroundings of the rail vehicle 10.

[0018] The radar unit 14 and the camera unit 16 as well as the control unit 18 are connected to each other by means of a wireless or wired connection, e.g. a CAN connection.

[0019] According to one embodiment, the camera unit 16 is configured to determine or detect rail tracks and / or objects in the image data. The camera unit 16 is further configured to map a rail path onto a clothoid function using the detected rail tracks and to transmit this or its parameters, in particular cyclically, to the radar unit 14 via the CAN connection.

[0020] The camera unit 16 is also configured to determine one or more object properties or attributes, such as a distance in the longitudinal and / or lateral direction, for the detected or determined objects. The camera unit 16 is configured to transmit the determined object attributes to the radar unit 14, particularly cyclically, via the CAN connection.

[0021] The radar unit 14 is configured to read the transmitted information, i.e., the transmitted CAN messages, particularly cyclically. Furthermore, the radar unit 14 is configured to determine or detect objects in the radar data. Furthermore, the radar unit 14 is configured to determine one or more object properties or object attributes for the detected or determined objects.

[0022] A further computing unit assigned to the radar unit 14 or included in the radar unit 14 is configured to merge the objects detected in the radar data with the objects detected in the camera data. In this case, objects detected on the basis of the radar data can each be assigned to a corresponding object determined on the basis of the camera data or identified with this object, so that each object is ideally assigned a radar and a camera data set. The further computing unit is configured to check whether a particularly merged object is an obstacle (and not, for example, a driveable ground object) with a predetermined or predeterminable probability. The further computing unit is also configured to check whether the object is located within a trajectory of the rail vehicle in order to detect a possible collision.Furthermore, the further computing unit is configured to transmit a CAN message regarding the detected possible collision, e.g. in the form of a warning, to the computing unit 18.

[0023] In alternative embodiments, the camera unit 16 and / or radar unit 14 can also be configured only to provide sensor data and the processing of the sensor data (e.g. object detection / object classification) can take place in the computing unit 18.

[0024] The computing unit 18 is configured to receive the CAN message of the further computing unit and, in response to the received warning, to output an analog or digital signal for controlling an acoustic or optical warning unit, e.g. a light, of the rail vehicle and / or a drive unit and / or brake unit of the rail vehicle.

[0025] According to the present embodiment, the computing unit 18 is configured to read in object information relating to a position and / or speed of the object 24, wherein the object information is or has been determined based on the sensor data of the sensor units 14, 16 of the driver assistance system 12 of the rail vehicle 10 containing the information relating to the object 24. The computing unit 18 is further configured to receive at least one setting signal containing information relating to an assistance function configuration to be applied. For example, such a setting signal can be generated by a driver using an operating unit of the rail vehicle 10, at which a desired assistance function configuration (e.g., warning strategy) can be selected.Furthermore, such a setting signal can originate from a driving service center, whereby, for example, information regarding the time of day, season, current weather conditions, and the like can be taken into account when specifying the assistance function configuration to be applied (e.g., corresponding to a trigger threshold for an assistance measure). Furthermore, the computing unit 18 is configured to determine classification information (object classification) regarding an assignment of the object 24 to one of at least two predetermined object classes based on the read-in object information and, if applicable, the received setting signal (in particular if this contains information that allows conclusions to be drawn about the probability of the presence of objects of certain object classes). Furthermore, the computing unit 18 is configured to carry out an assistance measure in accordance with the assistance function configuration.For example, the assistance measure may include determining the collision probability between the rail vehicle 10 and the object 24 based on the determined object classification and initiating a corresponding countermeasure if the collision probability exceeds a predetermined threshold.

[0026] For this purpose, the computing unit 18 comprises a processor, a storage medium with a computer program, and at least one communication interface. The computer program comprises instructions which, when executed by the processor, cause the assistance measure to be carried out (e.g., by determining the collision probability between the rail vehicle 10 and the object 24 according to the claimed method and issuing a warning message and / or performing automatic emergency braking).

[0027] It should be expressly noted here that in some embodiments, sensor data from only one of the sensor units 14, 16 can be used to implement the method. Furthermore, the method is not limited to the sensor types mentioned (camera or radar).

[0028] In Fig. 2 schematically shows an embodiment of a method according to the invention in the form of a highly simplified flow chart and is designated overall by 200.

[0029] In Fig. Figure 3 schematically shows an application situation as it may occur within the scope of embodiments of the invention.

[0030] Within the scope of the method 200, one or more setting signals 210 are first received, each containing information about an assistance function configuration to be used. Such a setting signal 210 can, for example, be generated by a driver 316 using an operating unit 312 (e.g., selector lever, control knob, etc.) in a control station 310 of the rail vehicle 10. As feedback for the selection, an information signal can be displayed by means of a display unit 314, so that the driver 316 can check whether the selection was correctly recorded. In the simplest case, a light can provide information about the selected assistance function configuration (options, e.g., early, medium, late for an intervention time in the event of a collision warning), for example in the form of a color coding. Such a preference of the driver 316 can, if necessary, also be indicated by means of an identification of the driver (e.g.,by means of a key or driver card) if the driver 316 has stored a corresponding preference centrally (e.g., within the framework of vehicle fleet management) or locally (e.g., in a data memory, in particular the computing unit 18, in the rail vehicle 10 or the key). Alternatively or additionally, such a setting signal 210 can be received from an external location, e.g., a train dispatch center, a rail infrastructure unit, or the like, and can contain, for example, information relating to one or more of the time, time of day, season, brightness, weather conditions, accident hotspots, geographical position, currently taking place events (e.g., sporting event, festival, trade fair, etc.), and the like.

[0031] Based on the received setting signal 210 or the received setting signals 210, a collision probability threshold is determined, for example, in accordance with the assistance function configuration. Based on the collision probability threshold (and possibly additional information contained in the at least one received setting signal 210), one of a number of assistance function configurations (e.g. warning strategies) 331, 332, 333, 334, 335, 336 is selected. Such an assistance function configuration in the form of a warning strategy comprises at least the collision probability threshold and at least one assistance measure that is to be carried out if the collision probability threshold is reached. If necessary, an assistance function configuration (orThe warning strategy may also include multiple collision probability thresholds for different assistance measures, so that, for example, a corresponding threshold for issuing a warning message to the driver 316 may be lower than a threshold for initiating automated emergency braking. Thus, an escalation can occur as needed. The determination of the required assistance measure in each case and its respective implementation is also referred to as an assistance function.

[0032] In Fig. 3, the effects of such different assistance function configurations are schematically illustrated using the example of warning strategies, in particular based on different preferences of the driver 316. For example, when approaching an obstacle 330 in an environment 320 that includes a preceding rail section, emergency braking can be initiated automatically if the collision probability, which is based on the sensor data (as described above with regard to Fig. 1 described as an example) exceeds the relevant collision probability threshold. Fig.3 shows scenarios for three different user specifications from which the driver 316 can choose. A defensive driver 316 will, for example, specify a low collision probability level (and thus a high sensitivity or an early point in time for the intervention of the assistance measure). In such a case, for example, automated braking can take place from a position 342 that is relatively far away from the obstacle 330, wherein the assistance function configuration or warning strategy can, in particular, provide for calculating a negative acceleration to be applied such that the rail vehicle comes to a stop at a predeterminable minimum distance, for example a distance of one meter, from the obstacle 330. In such a case, for example, a starting point for braking can be selected such that a deceleration of 1.2 m / s 2is sufficient to come to a stop with the required safety distance. If, however, the driver 316 selects a medium collision probability level to be applied (a medium time for intervention of the assistance measure), the braking (with otherwise constant boundary conditions) will only be applied at a later time, for example, upon reaching position 344, and with a correspondingly increased deceleration (negative acceleration), e.g. 1.4 m / s 2 , initiated. An aggressive driver 316 could select an even higher collision probability level (i.e., an even later intervention time), which would lead to the initiation of emergency braking upon reaching position 344 with a correspondingly high deceleration (e.g., 1.6 m / s 2 ) would lead to.

[0033] Different assistance function configurations (warning strategies) 331, ..., 336 can include, for example: Warning strategy in pedestrian zones, e.g. by means of geofencing via GPS coordinates or via entry and exit signals in a predeterminable track area: in the city center, an external bell of the rail vehicle 10 can be controlled to warn pedestrians, while outside the city center only the driver 316 in the control station 310 is warned; In the area around a building with an increased probability of pedestrians, e.g. a stadium during a sporting event or in the area of ​​a fair and during the days of the fair, an earlier intervention time or an increased sensitivity (reduced collision probability threshold) can be used to take into account the increased probability of pedestrians staying there and / or the comparatively low level of attention of pedestrians; For trams and during approach (e.g. GPS and speed signals), a warning strategy with an external bell can be chosen to alert pedestrians, especially in the vicinity of a stop, to the approaching tram; In certain areas, a warning strategy can be selected only for certain obstacles (certain triggers of the assistance function), e.g. in the depot only for trams and buffer stops (depending on object classification); Different, customized warning strategies can be selected depending on the time of day, season, brightness, or weather conditions. The goal can be to increase useful warnings and reduce false warnings, as well as to respond particularly sensitively to specific accident hotspots.

[0034] This allows for the selection of assistance function configurations (warning strategies) with adaptive parameter sets to respond specifically to different objects and / or situations. For example, in pedestrian zones, a warning can be issued even when the (sensor-based) probability of pedestrians' presence is lower than when driving outside of town, since the basic probability of pedestrians' presence is significantly higher in urban areas than in suburban railway areas. This, in turn, can prevent false warnings and increase driver acceptance. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] DE 10 2022 210 974

[0002]

Claims

[1] Method (200) for executing a driver assistance function during operation of a rail vehicle (10) in order to carry out an assistance measure, comprising - receiving at least one setting signal (210) containing information regarding an assistance function configuration (231, 232, 233, 234, 235, 236) to be used, - selecting the assistance function configuration (220) to be used from a set of assistance function configurations (231, 232, 233, 234, 235, 236) based on the at least one setting signal (210), - Executing the driver assistance function depending on the selected assistance function configuration to determine an assistance measure, and - Carrying out the assistance measure. [2] The method (200) of claim 1, wherein the at least one setting signal (210) comprises a setting signal received based on a user specification (312). [3] Method (200) according to claim 1 or 2, comprising outputting an information signal (314) containing information regarding the at least one setting signal (210). [4] Method (200) according to one of the preceding claims, wherein different types of assistance measures are determined by different assistance function configurations (231, 232, 233, 234, 235, 236), in particular wherein the different types of assistance measures - issuing a warning, in particular an acoustic and / or visual warning, to a person in the rail vehicle, in particular a driver of the rail vehicle and / or a person (24) outside the rail vehicle, in particular in an area (320) in front of the rail vehicle (10) in the direction of travel (22), and / or - include automated deceleration, in particular braking. [5] Method (200) according to one of the preceding claims, wherein different times (340, 342, 344), in particular of execution, of the assistance measure are determined by different assistance function configurations (231, 232, 233, 234, 235, 236). [6] Method (200) according to claim 5, wherein the different times (340, 342, 344) are selected as a function of a type of assistance measure, in particular as defined in claim 4, and / or as a function of a current speed of the rail vehicle (10) and / or as a function of a maximum target deceleration and / or as a function of a current and / or minimum acceptable distance from an object (24, 330) located in front of the rail vehicle (10) in the direction of travel. [7] Method (200) according to one of the preceding claims, wherein different triggers of the assistance measure are determined by different assistance function configurations (231, 232, 233, 234, 235, 236), wherein the different triggers in particular comprise a risk of collision with an object (24, 330), in particular with a person (24) and / or an animal and / or a vehicle and / or another rail vehicle and / or an immovable object and / or an impassable component of the rail infrastructure. [8] Method (200), wherein an assistance function configuration (231, 232, 233, 234, 235, 236), in particular with a respective trigger, as defined in claim 7, and / or an assistance function scope and / or the assistance measure(s), in particular as defined in claim 4, is defined manually and / or on the basis of dedicated, predefined input parameters. [9] Computing unit (18) which is configured to carry out all method steps of a method (200) according to one of the preceding claims. [10] Driver assistance system (12) for a rail vehicle (10) - with a computing unit (18) according to claim 9, and - in particular with at least one sensor (14, 16), preferably a radar unit and / or a camera unit, wherein the sensor (14, 16) is designed to detect an environment of the rail vehicle (10) and to provide the computing unit (18) with sensor data relating to the detected environment. [11] Rail vehicle (10) with a driver assistance system according to claim 10. [12] Computer program which causes a computing unit (18) to carry out all method steps of a method (200) according to one of claims 1 to 8 when it is executed on the computing unit (18). [13] A machine-readable storage medium having stored thereon a computer program according to claim 12.

Images