Method and system for improved acoustic emergency vehicle detection

Abstract

A method (2) for acoustic emergency vehicle detection is presented, in which a processing device (10) of a vehicle (3) performs the following steps: detecting (21) a traffic situation in which the probability that an emergency vehicle will appear near the vehicle (3) is increased; and controlling (22) an automatic window lifter (12) to open a window (31) of the vehicle (3) depending on the detection (21) of the traffic situation.

Description

The invention relates to a system and a computer-implemented method for improved acoustic emergency vehicle detection. Furthermore, the invention relates to a computer program for carrying out such a method and to a computer-readable storage medium on which such a computer program is stored.Modern motor vehicles are frequently equipped with automated driving functions, occasionally already up to conditionally automated driving (so-called SAE level 3). In particular for a level 3 operation, a situation-inadequate reaction to emergency vehicles is required. Accordingly, providers of level 3 functions require emergency vehicle detection, which can be performed partially optically, but partially also based on acoustic detection of a martinshorn (siren). Insofar as no external microphone is provided in affected vehicles, an internal microphone arranged in the vehicle is used for acoustic detection of the emergency vehicle.One challenge in optical emergency vehicle recognition is that it must be based on very good camera systems and algorithms. These cameras are not always installed directed to the rear, which is necessary for the optical detection of emergency vehicles approaching from behind. In addition, the cameras have difficulties, especially at night and in the tunnel, in distinguishing a pulsating blue light on a emergency vehicle from other (disturbing) lights. The number of false positive detections is therefore high, especially at night and in the tunnel.Acoustic emergency vehicle detection systems operate in darkness and in brightness, but have the disadvantage that they can only poorly locate the emergency vehicle and are also limited by disturbing noises (e.g. telephone occupants, look movies, listen to music). In addition, an acoustic insulation, in particular of vehicles in the premium segment, is usually very good, as a result of which only a relatively late acoustic detection is possible.DE 10 2009 043 774 A1 discloses a special signal transmission device and a corresponding method for transmitting special signals into a motor vehicle interior. The device has an acoustic signal recording device for recording a special signal generated outside the motor vehicle, an acoustic analysis device for analyzing the special signal, a control device which is coupled to the acoustic analysis device, and an acoustic signal output device which is suitable for outputting the special signal into the motor vehicle interior and which is controlled by the control device coupled to the acoustic analysis device. The transmission device may actuate a window lift electronic device via its control device coupled to the acoustic analysis device. As a result, if it has been determined that a special signal is present, a window can be automatically opened. This is intended to provide the advantage that, as a result of the additional transmission of sound into the motor vehicle interior through the window, a driver of the motor vehicle can acoustically determine from which direction the vehicle which generates the special signal approaches. However, a disadvantage of this solution is that it presupposes the presence of a suitable acoustic signal recording device, for example in the form of one or more external microphones, for the initial detection of the special signal.Proceeding from this, it is an object of the present invention to specify an improved method and a corresponding system for acoustic emergency vehicle detection.The object is achieved by the subject matters of the independent claims. Advantageous embodiments are set forth in the dependent claims.A first aspect of the invention relates to a method for emergency vehicle detection, in which a (data) processing device of a vehicle carries out the following steps:In a step, a traffic situation is detected (i.e. it is detected that such a traffic situation exists), in which the probability that a emergency vehicle will appear in the vicinity of the vehicle in the next time (and an acoustic emergency vehicle signal will accordingly be sounded) is increased. The indication that the probability is increased can be understood in this context to mean that the probability of the occurrence of an emergency vehicle is higher than in normal or average traffic situations. In particular, this can be established on the detection of the presence of predetermined emergency vehicle-relevant scenarios, as is explained below by way of example.In a further step, depending on the detection of the traffic situation (in particular in response to the detection of the traffic situation), a window lifter automatic system is then actuated for (at least partially) opening a window of the vehicle. This activation or opening of the window can take place proactively, in particular, i.e. before an emergency vehicle signal has actually been detected.Preferably, the control of the window lifter automatic system takes place in such a way that the window is opened only very slightly, namely just so far that external noises can be perceived better by one or more interior microphones of the vehicle. For example, the window can be opened only to such an extent that external noises can already penetrate significantly better into the vehicle interior, but that an opening gap of the window is not visually recognizable to a vehicle occupant. Temporarily reduced driving comfort due to an increased noise gate can be accepted here, especially since the driving speed of the vehicle is already low in typical emergency vehicle-relevant traffic scenarios (e.g. traffic jams or congested traffic in front of an accident site) and the driving noises of the vehicle are accordingly comparatively quiet.According to one specific embodiment, the traffic situation is recognized at least partially on the basis of information received from a backend, which may include one or more servers situated outside the vehicle. This information can be provided, for example, as real-time traffic information such as so-called RTTI (real-time traffic information) from a central service. Such information can relate in particular to RTTI events such as accidents or jams.Generally, detecting the traffic situations may include detecting one or more indicators of a traffic accident. In other words, one or more indicators may be detected that a location of an accident is in the vicinity of the vehicle and / or on a planned route of the vehicle. It is also conceivable that an indicator is detected that there is an accident site to which a emergency vehicle would likely choose a route that the emergency vehicle leads to the vicinity of the vehicle. For example, it can be recognized that a probable route of an emergency vehicle partially overlaps a planned route of the vehicle.Alternatively or additionally, the detection of the traffic situation can comprise the detection of one or more indicators for the presence of a traffic jam or congested traffic, in particular in connection with a traffic accident. Traffic jams or jamming traffic can be signs of a traffic accident that has occurred, which in turn can indicate an increased probability of an emergency vehicle occurring. Alternatively or in addition to the above-mentioned real-time traffic information, traffic jams or congested traffic can be detected on the basis of vehicle odometry (e.g. average speed over a certain period of time) or on the basis of a surroundings sensor system of the vehicle (e.g. scene detection by means of a camera).It is also within the scope of the invention that the detection of the traffic situation comprises the detection of a formed or already formed rescue corridor in the environment of the vehicle. In this case, the emergency corridor can be detected, for example, on the basis of scene detection by means of a camera of the vehicle. For example, it can be recognized on the basis of a particularly pronounced (i.e. particularly wide) emergency corridor behind and / or in front of the vehicle that the probability of soon occurring an emergency vehicle in the vicinity of the vehicle is increased.It is also possible that two or more of the aforementioned criteria for detecting the traffic situation, which relate to the presence of a traffic accident, a traffic jam or a congested traffic or a rescue corridor, are logically combined with one another in order to form a fused criterion for detecting a traffic situation with an increased probability of an emergency vehicle occurring.Alternatively or in combination with one or more of the aforementioned criteria, it is also possible to use further environmental conditions as criteria as indicators of the presence of a traffic situation relevant to emergency vehicles, such as poor visibility, in particular due to darkness (e.g. night) or fog, or the presence of a tunnel situation (i.e. the determination that the vehicle is currently in a tunnel). This is based on the idea that, in the case of poor visibility and / or in tunnels, it is generally possible to assume an increased probability of a traffic accident and, accordingly, of the occurrence of an emergency vehicle. Moreover, as mentioned at the beginning, under such conditions, an optical emergency vehicle detection can be made more difficult, so that the acoustic emergency vehicle detection is of increased importance. It can therefore be useful to react more sensitively in the case of poor visibility and / or in the case of tunnel travel and, for example, to lower a reaction threshold for opening a vehicle window within the scope of the method according to the invention.According to one specific embodiment, the method includes, as a further step, a detection of an acoustic emergency vehicle signal by means of at least one interior microphone of the vehicle.Furthermore, it can be provided that an automated driving function of the vehicle is controlled as a function of the detected emergency vehicle signal.Generally, the term "automated driving function" as used herein refers to a vehicle function that enables automated driving. The term "automated driving" is understood here to mean driving with automated longitudinal and / or transverse guidance. This can be, for example, a longer time driving on the freeway or a limited time driving in the context of parking. The term "automated driving" includes automated driving with an arbitrary degree of automation. Exemplary degrees of automation are assisted, partially automated, conditionally automated, highly automated and fully automated driving (with increasing degrees of automation in each case). The five automation levels mentioned above correspond to SAE levels 1 to 5 of the standard SAE J3016 (SAE-Society of Automotive Engineering) according to the state of April 30, 2021. In assisted driving (SAE level 1), the system performs longitudinal or lateral guidance in certain driving situations, with the expectation that the driver takes over all remaining aspects of the dynamic driving tasks. In partially automated driving (SAE level 2), the system assumes longitudinal and lateral guidance in certain driving situations, the driver having to monitor the system permanently, as in assisted driving. In conditionally automated driving (SAE level 3), the system assumes longitudinal and lateral guidance in certain driving situations without the driver having to monitor the system permanently; however, the driver must be able to assume vehicle guidance at the request of the system in a certain time. In highly automated driving (SAE level 4), the system assumes the guidance of the vehicle in certain driving situations, even if the driver does not react to a request for intervention, so that the driver is omitted as a fallback level. In fully automated driving (SAE level 5), all aspects of the dynamic driving task can be carried out by the system under any roadway and environmental condition that are also controlled by a human driver.For example, the vehicle may be configured to execute an automated driving function according to SAE level 3 or higher, wherein the automated driving function is executable taking into account the detected emergency vehicle signal. In general, the vehicle can be configured to automatically execute a situation-inadequate reaction to the detected emergency vehicle signal within the scope of the level 3 function. In this context, for example, an automatic control of a combined longitudinal and transverse guide for forming a rescue corridor in response to the detected emergency vehicle signal is conceivable.In addition or as an alternative to the above-mentioned example, one or more of the following measures are possible, for example, as situation-adequate reactions of the vehicle to a detected emergency vehicle signal:a takeover request to the driver and, if appropriate, in a further step, a deactivation or degradation of an automated driving function, such as a level 3 function;displaying an informative pop with a request for increased attention directed to the driver;transmitting information regarding the detected emergency vehicle into a backend from which following vehicles can benefit by a previous warning.A second aspect of the invention is a (data) processing device which has at least one processor and is configured (in particular programmed) for carrying out the method according to the first aspect of the invention by means of the at least one processor. According to some embodiments, the processing device may also be a processing device distributed spatially (for example via a plurality of processors or microcontrollers spaced apart from one another).For example, the processing device can be a control unit or a part of a control unit of the vehicle. In particular, this can be a control device for controlling an automated driving function, which enables an at least partially automated longitudinal guidance of the vehicle.A third aspect of the invention is a system for acoustic emergency vehicle detection, comprising: at least one interior microphone which is arranged and configured to detect sounds in an interior (such as, for example, in a passenger compartment) of a vehicle; at least one window of the vehicle which can be opened by means of a window lifter automatic system; and a processing device according to the second aspect of the invention. The processing device is configured to actuate the window lifter automatic system for (at least partially) opening the window of the vehicle as a function of the detection of the traffic situation explained above in connection with the first aspect of the invention; and to receive information about a detected acoustic emergency vehicle signal from the interior microphone.According to a development, the processing device of the system is furthermore configured to control an automated driving function of the vehicle on the basis of the information about the captured acoustic emergency vehicle signal, as was explained above by way of example with reference to the method according to the first aspect of the invention.A fourth aspect of the invention is a vehicle equipped with a system according to the third aspect of the invention. The vehicle can be a motor vehicle in particular. The term motor vehicle is to be understood here in particular as a land vehicle which is moved by machine power without being bound to railway tracks. A motor vehicle in this sense can be designed, for example, as a passenger car, motorcycle or tractor.A fifth aspect of the invention is a computer program comprising instructions which, when the computer program is executed by a processing device, such as a processing device of a system according to the third aspect of the invention, cause the processing device to execute a method according to the third aspect of the invention. The computer program can also be divided into a plurality of separate subprograms, which can be executed by different processing devices (such as a plurality of separate processors), which may be spatially remote from one another.A processing device according to the second aspect of the invention can be configured (in particular programmed) to execute a computer program according to the fifth aspect of the invention.A sixth aspect of the invention is a computer-readable storage medium comprising instructions which, when executed by a processing device, cause the processing device to execute a method according to the third aspect of the invention. In other words, a computer program according to the fifth aspect of the invention can therefore be stored on the computer-readable storage medium.The invention will now be explained in more detail on the basis of exemplary embodiments and with reference to the appended drawings. FIG. 1 illustrates, by way of example and schematically, a vehicle having a system for acoustic emergency vehicle detection. FIG. 2 illustrates, by way of example and schematically, steps of a method for acoustic emergency vehicle detection.The vehicle 3 shown in FIG. 1 has a system 1 for acoustic emergency vehicle detection. The system 1 comprises an interior microphone 11 arranged in a passenger compartment of the vehicle 3 for detecting noises in the interior of the vehicle 3. Furthermore, the system 1 comprises a window 31 of the vehicle 3 which can be opened by means of a window lifter automatic system 12. Furthermore, a (data) processing device 10 is provided as part of the system 1, which is connected by signal technology to the automatic window lifter system 12 and the interior microphone 11.The processing device 10 can be, for example, a control unit of a system for conditionally automated driving (SAE level 3) of the vehicle 3. Processing device 10 may be connected in terms of signal technology to a surroundings sensor system of vehicle 3, which is not shown separately in FIG. 1. Such a surroundings sensor system may include, for example, one or more radar sensors, one or more ultrasonic sensors, and / or one or more cameras. Furthermore, the processing device 10 can be connected to a longitudinal and / or lateral guidance actuator system of the vehicle 3, not shown in FIG. 1, in order to actuate the latter within the scope of automated driving functions.The system 1 is advantageously configured to minimally open the rear windows 31 of the vehicle, in particular, depending on the traffic situation, in order to improve the acoustic detection of emergency vehicles via the interior microphone 11. It is sufficient to open the window or windows 31 only minimally.The situations in which such a window control is expedient can be defined depending on the quality of the acoustic or optical emergency vehicle detection system and automatically detected on the basis of defined criteria. Some examples of criteria at which an emergency vehicle relevant situation can be detected are explained further below with reference to the method 2 schematically illustrated in FIG. 2.In order to provide the above-explained function of the system 1, the processing device 10 is programmed to,detecting that a traffic situation exists in which the probability that a emergency vehicle will appear in the vicinity of the vehicle 3 in the next time is increased;controlling the window lifter automatic system 12 to open the window 31 of the vehicle 3 as a function of the detection 21 of the traffic situation; andreceiving information about a detected acoustic emergency vehicle signal from the interior microphone 11.In accordance with the above, the processing device 10 is configured to execute the method steps 21, 22 according to FIG. 2 mentioned below:In a method step 21, it is recognized that a traffic situation exists in which the probability that a emergency vehicle will appear in the vicinity of the vehicle in the next time is increased.In this case, such emergency vehicle-relevant traffic situations can be detected on the basis of one or more indicators for a traffic accident. In other words, one or more indicators may be detected that a location of an accident is in the vicinity of the vehicle and / or on a planned route of the vehicle.For example, detecting a emergency vehicle-relevant traffic situation can comprise detecting one or more indicators for the presence of a traffic jam or congested traffic. Traffic jams or jamming traffic can be signs of a traffic accident that has occurred, which in turn can indicate an increased probability of an emergency vehicle occurring.A emergency vehicle relevant traffic situation may be detected at least partially based on real-time traffic information received from a backend by the processing device 10. Such information can relate in particular to RTTI events such as accidents or jams. Alternatively or in addition to real-time traffic information, traffic jams or congested traffic can be detected on the basis of a vehicle odometry (e.g. average speed over a certain period of time) or on the basis of a surroundings sensor system of the vehicle 3 (e.g. scene detection by means of a camera).It is also possible that a emergency vehicle-relevant traffic situation is recognized on the basis of a forming or already formed emergency corridor in the environment of the vehicle. In this case, the emergency corridor can be detected, for example, on the basis of scene detection by means of a camera of the vehicle. For example, it can be recognized on the basis of a particularly pronounced (i.e. particularly wide) emergency corridor behind and / or in front of the vehicle 3 that the probability of soon occurring an emergency vehicle in the vicinity of the vehicle 3 is increased.It is also possible that two or more of the aforementioned criteria for detecting the traffic situation, which relate to the presence of a traffic accident, a traffic jam or a congested traffic or a rescue corridor, are combined with one another in order to form a fused criterion for detecting a traffic situation with an increased probability of an emergency vehicle occurring. In this case, further criteria can also be used as indicators for the presence of a traffic situation relevant to emergency vehicles, such as poor visibility, in particular due to darkness or fog, or the presence of a tunnel situation (i.e. the determination that the vehicle 3 is currently in a tunnel).A further method step 22 is that of the automatic window lifter system 12 for opening the window 31 of the vehicle 3 as a function of the detection 21 of the traffic situation.Preferably, the window 31 is opened only very slightly, namely only so far that external noises can be better perceived by the interior microphone 11 of the vehicle 3. For example, the window 31 can be opened to such an extent that external noises can already penetrate significantly better into the vehicle interior, but that an opening gap of the window 31 is not visually recognizable to a vehicle occupant.As an optional method step 23 (illustrated in FIG. 1 with dashed lines), it can further be provided that an acoustic emergency vehicle signal is detected by means of the interior microphone 11.In a further optional method step 24 (illustrated in FIG. 1 with dashed lines), the processing device 10 generates control signals in response to the detected emergency vehicle signal for controlling an automated driving function, in particular according to SAE level 3. For example, the adapted vehicle guidance can comprise an automatic formation of a rescue corridor.References included in the specificationThis list of documents cited by the applicant has been produced in an automated manner and is only included for the better information of the reader. The list is not part of the German patent application or utility model application. The DPMA does not take any adhesion for any faults or omissions.Patent Literature citedDE 10 2009 043 774 A1

[0005]

Claims

Method (2) for acoustic emergency vehicle detection, in which a processing device (10) of a vehicle (3) carries out the following steps: - detection (21) of a traffic situation in which the probability that an emergency vehicle will appear in the vicinity of the vehicle (3) is increased; and - actuation (22) of a window lifter automatic system (12) for opening a window (31) of the vehicle (3) as a function of the detection (21) of the traffic situation.Method (2) according to claim 1, wherein the traffic situation is detected at least partially on the basis of information received from a backend, in particular as real-time traffic information.The method (2) according to claim 1 or 2, wherein detecting the traffic situation comprises detecting one or more indicators of a traffic accident.The method (2) according to any of the preceding claims, wherein detecting the traffic situation comprises detecting one or more indicators of the presence of a traffic jam or congestion traffic.Method (2) according to one of the preceding claims, wherein the detection of the traffic situation comprises the detection of a rescue corridor in the environment of the vehicle (3).Method (2) according to one of the preceding claims, wherein the actuation (23) of the automatic window lifter mechanism (12) is effected in such a way that the window (31) is opened only to such an extent that an opening gap of the window (31) cannot be seen by a vehicle occupant.Method (2) according to one of the preceding claims, further comprising: - detecting (23) an acoustic emergency vehicle signal by means of at least one interior microphone (11) of the vehicle (3).Method (2) according to Claim 7, further comprising: - controlling (24) an automated driving function of the vehicle (3) as a function of the detected emergency vehicle signal.Processing device (10) for a vehicle (3), wherein the processing device (10) has at least one processor and is configured to carry out a method (2) according to one of the preceding claims by means of the processor.System (1) for acoustic emergency vehicle detection, comprising - at least one interior microphone (11) which is arranged and configured to detect sounds in an interior of a vehicle (3); - at least one window (31) of the vehicle (3) which can be opened by means of a window lifter automatic system (12); and - a processing device (10) according to Claim 9, wherein the processing device (10) is configured ◯ to actuate the window lifter automatic system (12) to open the window (31) of the vehicle (3) as a function of the detection (21) of the traffic situation; and ◯ to receive information about a detected acoustic emergency vehicle signal from the interior microphone (11).The system (1) according to claim 10, wherein the processing device (10) is further configured to control an automated driving function of the vehicle (3) depending on the information about the detected acoustic emergency vehicle signal.A computer program comprising instructions which, when the computer program is executed by a processing device (10), cause the computer program to execute a method (2) according to any one of claims 1 to 8.A computer readable storage medium comprising a computer program according to claim 12.

Images