Method and evaluation device for evaluating an intervention of at least one driver assistance system of a vehicle
By combining sensors and machine learning methods, the intervention perceptibility of the driver assistance system is measured and feedback, which solves the problem of drivers' unaware of intervention and improves driving safety.
Patent Information
- Application Number
- CN202210070419.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2021-01-22
- Filing Date
- 2022-01-21
- Publication Date
- 2025-08-08
- Estimated Expiration
- 2042-01-21
AI Technical Summary
In the prior art, the intervention of the driver assistance system when the vehicle is driving is often not perceived by the driver and passengers, resulting in the inability to effectively improve driving safety.
The evaluation device determines whether the intervention of the driver assistance system is perceived, and uses driving mechanism sensors, surrounding environment sensors, passenger monitoring devices and prior knowledge, combined with machine learning methods, to provide users with perceptible feedback on the intervention.
It improves drivers and passengers' awareness of driver assistance system intervention, enhances driving safety, and informs unperceived interventions through output signals, helping users adjust driving behavior to prevent potential dangers.
Smart Images

Figure CN114872723B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a method and an evaluation device for evaluating an intervention of at least one driver assistance system of a vehicle during driving operation of the vehicle. Background Art
[0002] Driver assistance systems are known from the prior art for supporting a user of a vehicle while the vehicle is being driven, for example for improving driving safety and / or for avoiding and / or mitigating accidents.
[0003] Modern vehicles are equipped with numerous accident avoidance systems. Many of these systems develop silently—that is, drivers pay for them but are not always aware that they are supporting them while driving or even preventing accidents. An example of this is ESC (short for "Electronic Stability Control," German for Elektronische Stabilitätskontrolle, often also referred to as the Electronic Stability Program ("ESP")), a driver assistance system for controlling driving dynamics that, in particular, counteracts vehicle roll by selectively braking individual wheels of the vehicle.
[0004] ESC intervention prevents a skid when the vehicle oversteers or understeers. During an ESC intervention, the driver only notices a brief "judder" at the wheel and usually doesn't connect the dots—he might think he's driving over a rock or a sill. In this case, ESC might actually save his life.
[0005] A similar situation exists in computer virus scanners in a different technical field. These virus scanners make this visible to the user / customer by reporting "Virus attack blocked" after each virus attack and generating, for example, monthly statistics on how often viruses were scanned and blocked. In the automotive industry, this or similar solutions are not known or used.
[0006] US Pat. No. 9,773,281 B1 describes an accident recognition device for a vehicle, which is configured to determine the occurrence of an accident in which the vehicle is involved. After determining the occurrence of the accident, characteristics of the accident can be determined, and vehicle data and data on vehicle passengers can be obtained.
[0007] US Pat. No. 9,487,138 B2 discloses a method for outputting a warning for a driver assistance system in a vehicle, in which data about the vehicle's movement and data about the risk of an accident in the vehicle's surroundings are detected. The detected data is evaluated and associated with a specific accident risk level. A warning is output based on the associated accident risk level. For example, if a critical collision situation occurs, the driver is informed of the start of automatic vehicle control so that he or she understands the corresponding revocation of the driving task.
[0008] US Pat. No. 8,766,846 B2 describes a vehicle system for preventing accidents, which has an object recognition device. When an object is detected, an accident prevention response signal is transmitted to the vehicle's braking system, which then brakes the vehicle independently of the vehicle driver. Summary of the Invention
[0009] The object of the present invention is to overcome the disadvantages known from the prior art and to provide a method and an evaluation device for evaluating the intervention of at least one driver assistance system of a vehicle during vehicle operation, by means of which the user is also informed of the intervention while ensuring greater driving safety through the intervention of the driver assistance system.
[0010] According to the present invention, this object is achieved by a method for evaluating an intervention of at least one driver assistance system of a vehicle during driving operation of the vehicle.
[0011] In a method according to the present invention for evaluating an intervention of at least one driver assistance system of a vehicle during driving operation of the vehicle, a driver assistance system for supporting a user of the vehicle while the vehicle is traveling, particularly with respect to driving safety, is adapted and provided for intervention in the driving operation. The user may be the driver of the vehicle and / or another passenger.
[0012] According to the present invention, the evaluation device determines, during at least one intervention of the driver assistance system, whether this intervention is (and / or was) an intervention perceptible per se to the user.
[0013] An intervention that is perceptible (or should be perceptible) to the user is understood, in particular, to mean that the user can, in principle (independently, solely through their own sensory perceptions) perceive the intervention itself in the driving operation (e.g., through irregularities occurring in the driving operation, such as jolts), and can perceive and / or associate this perception, in particular substantially unambiguously and / or with a predetermined probability, as an effect of the driver assistance system's intervention in the driving operation. Preferably, the user can distinguish an intervention that is perceptible to the user from other irregularities in the driving operation that arise from other causes (e.g., a road sill).
[0014] The driver assistance system is preferably a driver assistance system for improving driving safety, and particularly preferably a driver assistance system for avoiding and / or mitigating accidents. Preferably, the driver assistance system is an electronically controlled driver assistance system.
[0015] Preferably, at least one driver assistance system of a vehicle and in particular a plurality of driver assistance systems of a vehicle are (in each case) accident avoidance systems.
[0016] A plurality of driver assistance systems, in particular a plurality of accident avoidance systems, are preferably installed in the vehicle. Preferably, these driver assistance systems report their interventions to the evaluation device, in particular via a data bus, and preferably to an evaluation algorithm (of the evaluation device).
[0017] In particular, the evaluation device is suitable and provided for determining whether an intervention performed and / or executed and / or triggered by a driver assistance system (or multiple driver assistance systems) of the vehicle is an intervention that should be perceptible to and is preferably perceptible to a user of the vehicle.
[0018] Preferably, the evaluation device determines whether the intervention is an intervention that is not perceptible to the user (in particular per se).
[0019] In other words, the evaluation device or evaluation algorithm determines, for example, via an evaluation of system data (e.g. data of at least one or more driver assistance systems) whether an intervention of a driver assistance system (in particular an accident avoidance system) is not immediately recognizable to a user (e.g. the driver) or cannot itself be associated with the user (e.g. the driver).
[0020] This offers the advantage that the user can be informed of unnoticed and / or imperceptible interventions. Advantageously, the user can be informed of the activities carried out by the driver assistance system. Advantageously, the user is thus given the possibility to analyze the driving situation and / or (their) driving behavior and / or environmental conditions (e.g., weather conditions) in view of their potential dangers and to adapt or change future driving behavior.
[0021] By reporting an intervention that is not perceptible per se, for example to the user, the importance of the driver assistance system can be demonstrated to the user on the one hand, and similar dangerous situations in the future can be prevented or mitigated on the other hand by adapting the user's driving behavior.
[0022] Preferably, (in particular each) driver assistance system that carries out and / or triggers an intervention triggers (simultaneously or with a time offset) activation of an evaluation device in order to determine the perceptibility of this intervention for a user.
[0023] Preferably, the evaluation device determines the perceptibility of the respective intervention for a plurality of interventions and in particular for each intervention (eg of a journey).
[0024] In a preferred method, the perceptibility of the intervention is determined based on an evaluation of data from a driver assistance system or multiple driver assistance systems. This offers the advantage that the perceptibility of the intervention (in particular itself) to the user can be inferred from the data from the driver assistance system or multiple driver assistance systems.
[0025] The data of a driver assistance system or a plurality of driver assistance systems preferably include information about the type and / or duration of an intervention of the (corresponding) driver assistance system, the action carried out, the required intensity of the intervention, and at least one state.
[0026] In a further preferred method, the perceptibility of the intervention is determined based on previously known and / or past similar interventions of the driver assistance system. Preferably, the evaluation device or evaluation algorithm utilizes a priori knowledge. For example, an intervention of an ESC system may be less likely to be associated by the user or driver with accident avoidance than an intervention of an emergency braking system for collision avoidance.
[0027] Preferably, the connection between the intervention and its perceptibility known and / or determined from a priori knowledge is stored in a memory device which is accessible to the evaluation device and / or is a component of the vehicle and in particular the evaluation device.
[0028] In a further (alternatively or additionally) preferred method, the perceptibility of an intervention (per se) is determined based on the intensity and / or type of intervention by the driver assistance system. This offers the advantage that some of the interventions can be classified as perceptible or imperceptible, for example, without a high evaluation or computational complexity. Thus, for example, the execution of an emergency brake by an emergency brake system can (usually) be classified as a (per se) perceptible intervention without further evaluation.
[0029] Preferably, the driver assistance system that carried out or executed the intervention is taken into account when determining the perceptibility of the intervention. For example, the vehicle's central computer and / or the corresponding driver assistance system can report to the evaluation device the intervention intensity and the intervention that is to be executed and / or has been (already) executed.
[0030] In a further preferred method, the perceptibility of the (own) intervention is determined based on at least one (measured) value detected and / or determined by at least one chassis sensor device and / or surroundings sensor device.
[0031] Preferably, the evaluation device and / or the evaluation algorithm utilizes information from chassis sensors (or chassis sensor devices), such as inertial, height and wheel speed sensors, as well as information from surrounding sensors, such as camera, radar, laser or ultrasonic sensors. Preferably, the algorithm compares the vehicle behavior before and during the intervention in order to assess how strongly the intervention is perceptible to the driver compared to normal driving.
[0032] The chassis sensor device is preferably selected from the group of sensor devices comprising at least one inertial sensor device, at least one height sensor device, at least one wheel speed sensor device, etc. and combinations thereof.
[0033] Taking into account the value(s) detected and / or determined by the chassis sensor device offers the advantage that movements and / or jerks of the chassis and / or vehicle can be determined very precisely. In particular, the evaluation device can advantageously determine very precise movements and / or jerks that are or have been caused by an intervention of the driver assistance system and that are perceptible and / or (physically) perceptible to the driver.
[0034] Preferably, the determination of the perceptibility of the intervention (itself) is based on the following (measured) values of at least one chassis sensor device and / or at least one surroundings sensor device, at least one of which is detected (or recorded) and / or determined before the intervention and at least one other of which is detected (or recorded) and / or determined during the intervention.
[0035] Preferably, the comparison of the vehicle behavior before and during the intervention is performed, in particular by the evaluation device. This advantageously allows an assessment of how strongly the intervention is perceptible to the user compared to normal driving or previous driving.
[0036] In a further preferred method, the user's reaction to the intervention is detected by means of a passenger monitoring device, and the perceptibility of the intervention is determined based on the user's detected reaction. This offers the advantage that the user's perceptibility is not indirectly inferred, for example, from (measured) values of a chassis sensor system, but rather can be directly observed by the user themselves as to whether they perceive and / or have perceived the intervention. This offers the advantage that individually relevant perception thresholds can be taken into account.
[0037] Preferably, the passenger monitoring device optically observes the user and / or the user's behavior (at least temporarily and in particular before and / or during the intervention). Preferably, the passenger monitoring device thereby determines the user's perception of the intervention. Preferably, the passenger monitoring device has an image capture device, such as a camera, in particular an in-vehicle camera. Preferably, the passenger monitoring device is a (in-vehicle) camera.
[0038] It is also conceivable that the passenger monitoring device monitors the user by tracking the gaze path (at least temporarily and in particular before and / or during an intervention).
[0039] Preferably, the passenger monitoring device and / or the evaluation device is suitable and provided for determining a passenger's state of alarm and / or a state of increased attention from an optical image that at least partially includes the user, for example by a withdrawal and / or change in body posture and / or a change in gaze path and / or pupil dilation.
[0040] Preferably, the passenger monitoring device determines the perception of the intervention (and thus the perceptibility of the intervention) by means of haptic and / or tactile elements of the passenger monitoring device and / or the vehicle. The haptic and / or tactile elements may be, for example, operating elements of the vehicle, such as a steering wheel and / or a accelerator pedal and / or a brake pedal. Preferably, the passenger monitoring device determines the user's reaction to the intervention from the operation of the operating element and / or a change in the intensity and / or movement dynamics of the user at the haptic and / or tactile element (in particular at the operating element).
[0041] Preferably, the passenger monitoring device and / or the evaluation device determines whether the user is in a state of panic and / or increased attention in a temporally related manner to the intervention. Temporally related means, in particular, the user's reaction time. Typical reaction times can be stored, for example, on a storage device, in particular, of the evaluation device and / or the vehicle. It is also conceivable to store user-specific reaction times on the storage device, which are used to assess the user's perceptibility and / or perception of the intervention, taking into account the driver's reaction to the intervention.
[0042] Furthermore, the (evaluation) algorithm and / or evaluation device preferably utilizes information from an in-vehicle camera and / or operating elements (e.g., the steering wheel, accelerator pedal, and brake pedal). The (evaluation) algorithm observes the driver's reaction to the intervention and evaluates this reaction based on this information. For this purpose, the driver's reaction is preferably classified as, for example, weak, medium, or strong.
[0043] Preferably, the user's reaction detected by the passenger monitoring device is classified into one of a plurality of preset categories of different reaction intensities (eg into (four) categories: no reaction | weak reaction | medium reaction | strong reaction), in particular by the evaluation device.
[0044] Preferably, it can be determined from the category to which the reaction is assigned and / or the intensity of the intervention and / or a variable characteristic of the intervention whether the user has consciously and / or unconsciously perceived the intervention and / or whether the user can (has) perceived the intervention itself.
[0045] Preferably, data from different sources (a priori knowledge, chassis and / or surroundings sensors, and / or interior cameras and / or operating elements) are fused together, particularly preferably data from the domains of a priori knowledge, chassis and / or surroundings sensors, and interior cameras and / or operating elements. Machine learning methods, such as neural networks, deep learning, or even Bayesian networks, can be used for this purpose.
[0046] Preferably, the evaluation device is able to determine the perceptibility of the intervention and / or the perception of the intervention by the user via modern algorithms (KI, i.e. artificial intelligence, machine learning, neural networks, deep learning, Bayesian networks, etc.), preferably by means of evaluating multiple data, in particular multiple data of past interventions and associated detected surroundings data and / or vehicle data and / or user reaction data.
[0047] In a further preferred method, the evaluation device provides an output signal for output to a user based on the result of the determination of the perceptibility of the intervention. This offers the advantage of increasing the user's awareness of the driver assistance system's operating mode and / or the frequency and / or significance and / or intensity of the intervention. For example, this can indicate to the user that an accident could be prevented or (significantly) mitigated by the intervention.
[0048] If the algorithm detects that the intervention is not recognizable or relevant to the driver, it requests a text message via the data bus in an existing display unit in the vehicle, such as "ESC has just prevented a skid." For this purpose, existing displays, such as the speedometer or navigation display, can be used. Whether this display should take place can be determined by the driver in a suitable menu, for example by clicking on "Show intervention statistics." " box (e.g. by ticking a box).
[0049] Preferably, the evaluation device provides an output signal when the result of the evaluation results in an intervention that is not (per se) perceptible to the user and / or the intervention is not perceived by the user (eg due to strong distraction of the user).
[0050] Preferably, a threshold value (storable and / or stored in a memory device) for the perceptibility of the intervention is predeterminable and / or predeterminable, based on which the evaluation device determines or determines the perceptibility of the intervention.
[0051] Preferably, the output signal is output to the user by at least one output device. The output device may be an output device of the vehicle. However, additionally or alternatively, the output device may also be an output device of the user and / or an output device external to the vehicle.
[0052] The output device of the vehicle can be an output device fixedly (especially not detachable without destruction) installed in the vehicle. Preferably, it is a vehicle speed display, a navigation display and / or a (graphic) HMI (human-machine interface).
[0053] However, it is also conceivable that it is an output device that is mobile and / or movable within the vehicle.
[0054] Preferably, the output device is a terminal (e.g., of a user), in particular a mobile terminal. Thus, it can be, for example, a display device connected to a stationary computer. However, the terminal can also be a smartphone, tablet computer, laptop computer, etc.
[0055] Preferably, the output device is an optical or visual output device.Preferably, the output device is a graphics display.
[0056] Additionally or alternatively, it is also possible that the output device is an acoustic output device, in which the user is informed of the intervention, for example by a noise or a speech output.
[0057] It is also conceivable that the output device via which the output signal is output can be predefined and / or selected, in particular by a user (in particular optionally).
[0058] Preferably, the evaluation device is suitable and provided for providing an output signal for output via an output device (of the vehicle and / or user and / or external device), which output signal includes, in particular within the scope of statistics about a preset time period and / or a preset journey, information about at least one or more interventions that occurred, in particular, in this preset time period and / or preset journey.
[0059] The information to be outputted regarding the intervention can be selected from the group consisting of time and / or location and / or type of intervention and / or type of driver assistance system and / or intensity of intervention as well as variables characteristic of the intervention and combinations thereof.
[0060] Preferably, statistics regarding a plurality of interventions (which, for example, occurred within a predetermined time period and / or route section and / or within a predetermined journey) can be output graphically, for example, within the scope of a bar graph and / or in table form.
[0061] For example, the time period may be a time period of at least one hour, preferably at least one day, preferably at least one week, preferably at least one month and particularly preferably at least one year. Preferably, the evaluation is performed in relation to the user.
[0062] Preferably, the output signal is provided for output to the user and / or (by the output device) in a temporally linked manner, for example within five minutes, preferably within three minutes, and particularly preferably within two minutes after the intervention has been carried out. The user receives direct feedback about the intervention event via the time reference.
[0063] Preferably, the output signal is output via the output device automatically and / or without an instruction for output by a user.
[0064] However, it is also possible that the user can input (e.g. via a human-machine interface) an instruction to output all and / or some of the above-mentioned information related to one or more interventions and / or intervention statistics. This can be supported, for example, via a menu guide of the human-machine interface.
[0065] Preferably, statistics of interventions of one or more accident avoidance systems in the vehicle are displayed via an output device.
[0066] In a further preferred method, the perceptibility of an intervention is determined for a plurality of interventions, and information about a selection of these interventions is provided for output as a function of the respective perceptibility.
[0067] Preferably, the driver assistance system is selected from the following group, which includes (at least) one ESC system (Electronic Stability Control), ABS (Anti-lock Braking System), Avoidance Assist System, Emergency Brake Assist System, Lane Departure Warning System, Fatigue Warning System, etc. and combinations thereof.
[0068] A driver assistance system can (in each case) be a system that at least partially automatically prepares to take over the driving. It is also conceivable that it is a driver assistance system that is suitable (and intended) for (in particular within defined limits) to completely take over (in particular independently) the driving of the vehicle at least temporarily (for example during a dangerous situation).
[0069] The present invention further relates to an evaluation device, in particular for a vehicle with at least one driver assistance system, for evaluating interventions of at least one driver assistance system of the vehicle during the driving operation of the vehicle. In this case, the driver assistance system, in particular for supporting a user of the vehicle while the vehicle is traveling, in particular with regard to driving safety, is suitable and intended for intervention in the driving operation (of the vehicle).
[0070] According to the invention, the evaluation device is suitable and provided for and configured to determine, during at least one intervention of the driver assistance system, whether this intervention is (and / or was) an intervention perceptible per se to the user.
[0071] In other words, within the scope of the evaluation device according to the invention, it is proposed to evaluate data related to interventions by a driver assistance system, in particular data of a central computer of the driver assistance system and / or of the vehicle and / or a chassis sensor device and / or a surroundings sensor device and / or a driver monitoring device, in order to determine whether the intervention of the driver assistance system is not (immediately or directly) perceptible or recognizable to the user or cannot itself be associated with the user and / or is not associated with the user.
[0072] Preferably, the evaluation device is designed, suitable and / or intended for carrying out the above-described method and all the method steps described above in conjunction with the method, either individually or in combination. Conversely, the method can be equipped with all the features described within the scope of the evaluation device, either individually or in combination.
[0073] The present invention further relates to a vehicle, in particular a motor vehicle, comprising the above-described evaluation device for a vehicle according to one embodiment. In particular, the present invention can be used or applied to all vehicles and platforms, in particular as a purely software solution, preferably without new or additional hardware. The vehicle can in particular be a (motor-driven) road vehicle.
[0074] The vehicle preferably has an output device, by means of which an output signal provided by the evaluation device is output with information about one or more interventions of the driver assistance system.
[0075] The vehicle can be a motor vehicle, in particular a motor vehicle controlled by the driver himself ("driver only"), a semi-autonomous, autonomous (for example, autonomy level 3, 4, or 5 (SAE J3016 standard)) or a self-driving motor vehicle. Autonomy level 5 refers to fully automated vehicles. The vehicle can also be a driverless transport system. The vehicle can be controlled by a driver or can be driven autonomously. In addition to road vehicles, the vehicle can also be a flying taxi, an airplane, another means of transport, or other vehicle types, such as an aircraft, a ship, or a rail vehicle.
[0076] The present invention, which concerns a method for evaluating interventions of at least one driver assistance system of a vehicle during the driving operation of the vehicle, has been described in conjunction with a vehicle and a driver assistance system, wherein the driver assistance system, which is used to support a user of the vehicle while the vehicle is in motion, particularly with regard to driving safety, is suitable and intended for interventions in the driving operation. However, the present invention can also be applied to other devices and / or devices and / or systems for automation, for example in the field of home automation. Thus, an evaluation and output of (e.g., statistical) information can be implemented and / or provided, such as when and how a heating system is adjusted, blinds are opened and / or closed, etc. The applicant reserves the right to also claim protection for the method and evaluation device related thereto.
[0077] The present invention further relates to a computer program or a computer program product comprising a program medium, in particular a program code, which represents or encodes at least one of the method steps and preferably one of the preferred embodiments of the method according to the invention and is designed to be executed by a processing device.
[0078] The present invention further relates to a data memory on which at least one embodiment of the computer program according to the invention or a preferred embodiment of the computer program is stored. BRIEF DESCRIPTION OF THE DRAWINGS
[0079] Further advantages and embodiments can be seen from the accompanying drawings:
[0080] in:
[0081] Figure 1 A schematic diagram of a vehicle with an evaluation device according to the invention is shown;
[0082] Figure 2a A first embodiment of an output object outputted by an output device is shown;
[0083] Figure 2b Another embodiment of an output object outputted by an output device is shown;
[0084] Figure 3 Another embodiment of an output product outputted by an output device is shown; and
[0085] Figure 4 Another embodiment of an output material outputted via an output device is shown. DETAILED DESCRIPTION
[0086] Figure 1 A schematic diagram of a vehicle 1 with an evaluation device 20 according to the present invention is shown according to one embodiment. The evaluation device 20 can be a component of the vehicle 1. At least one and preferably multiple accident avoidance systems or driver assistance systems 35 (system 1, system 2, ..., system n) are installed in the vehicle 1.
[0087] A driver assistance system 35 or accident avoidance system can, for example, (automatically) intervene in the driving operation of the vehicle in potentially dangerous situations in order to prevent or at least mitigate the occurrence of a dangerous situation (eg, an accident) as far as possible.
[0088] The evaluation device can execute an evaluation algorithm which evaluates data as to whether an intervention of driver assistance system 35 or of an accident avoidance system is not immediately recognizable to the driver or cannot itself be attributed to the driver.
[0089] The evaluation device 20 is connected to a driver assistance system 35 of the vehicle 1 via at least one communication connection for data exchange. Figure 1 , a plurality of systems, system 1, system 2, ..., system n, are schematically shown as driver assistance systems 35 (or accident avoidance systems), each of which is connected to the evaluation device 20 via a communication connection 36 (here a data bus) for data exchange. These (driver assistance) systems preferably report their interventions to the evaluation device 20 or to the evaluation algorithm via the data bus.
[0090] In order to determine whether the intervention itself is recognizable or perceptible to the driver or user and / or cannot itself be associated with the driver or user, the evaluation device or the evaluation algorithm (1) uses a priori knowledge. For example, an intervention of an ESC system may be more difficult for the driver or user to associate as an accident avoidance than an intervention of an emergency brake system for collision avoidance.
[0091] Preferably, the (evaluation) algorithm or evaluation device 20 utilizes (measured) values detected by the detection device 10 of the vehicle 1, such as (2), information from the chassis sensors 16 (e.g., inertial, height, and wheel speed sensors), and information from the surroundings sensors 12 (e.g., camera, radar, laser, or ultrasonic sensors). To this end, the (evaluation) algorithm preferably compares the vehicle behavior before and during the intervention in order to assess how strongly the intervention is perceived by the driver compared to normal driving.
[0092] Furthermore, the (evaluation) algorithm preferably utilizes (3) information from the interior camera 14 and / or the operating elements 12 (e.g., the steering wheel, the accelerator pedal, and / or the brake pedal). The (evaluation) algorithm observes the driver's reaction to the intervention and evaluates this reaction based on this information. In particular, the driver's reaction is graded, for example, as weak, medium, and strong.
[0093] Data from various sources, including (1) prior knowledge, (2) chassis and surrounding sensors, and (3) in-vehicle cameras and operating elements, are combined. Machine learning methods such as neural networks, deep learning, or Bayesian networks can be used for this purpose.
[0094] If the (evaluation) algorithm detects that the intervention is not recognizable or relevant for the driver or user, the algorithm requests a text message, such as "ESC has just prevented a skid" via a communication connection 34 (here a data bus) to an output device 30 present in particular (in the vehicle 1), such as a display (unit) in the vehicle, such as a speedometer or navigation display. The driver can determine whether this display should take place, for example, by clicking on "Show intervention statistics" in a suitable menu. " box to select.
[0095] Figure 2a A first embodiment of an output A1 outputted via an output device is shown. The (evaluation) algorithm or evaluation device 20 preferably generates an intervention statistic A1 of a driver assistance system 35 or accident avoidance system. This intervention statistic preferably indicates which driver assistance system 35 ("system 1, system 2, ..., system n") intervened most frequently in a time period t. Figure 2a The output A1 shown in FIG is displayed in the form of a bar graph.
[0096] Figure 2b Another embodiment of the output A2 outputted by the output device is shown. Figure 2a As in the embodiment shown in , intervention statistics are also output here, which indicate which driver assistance system 35 (“system 1 , system 2 , . . . , system n”) intervened and how often in a time period t. Figure 2b The output A2 shown in FIG is displayed in a tabular form.
[0097] Figure 3 Another embodiment of the output A3 outputted by the output device is shown. Preferably, the driver or user can input (for example, click on the bar graph of the output A1) Figure 2a When the system bar is displayed, or when you click on the output A2 table Figure 2b ) to display additional data of the intervention, such as the location, date, time and intensity of the intervention of the driver assistance system 35 or the accident avoidance system, as in Figure 3 The output is shown in A3.
[0098] Figure 4 Another embodiment of an output A4 outputted via an output device is shown. The driver or user can preferably (in addition) navigate to this location on the map M by inputting (e.g. by clicking on a location of an intervention displayed via the output device 30) together with further information 50 about the intervention, such as the date and time of the intervention and / or the intensity of the intervention. Figure 4 In the output shown in , the location position P of the intervention selected by the user is marked by a fill point in the navigation map M. Additional information related to the selected intervention is associated with the marked location P, which is framed here by a rectangular frame and thus highlighted.
[0099] Above Figure 2a 、 Figure 2b 、 Figure 3 and Figure 4The statistics and data described in the foregoing can preferably be selected by the driver or user via menu guidance in the vehicle 1 and viewed via the aforementioned display unit 30. Alternatively, these statistics and data can also be sent via a particularly wireless communication connection 38, such as a radio network (W-LAN, Bluetooth, etc.), to a (mobile) terminal 40, such as a smartphone 42 or a home PC 44 of the driver or user, and can be viewed there by the driver or user, such as Figure 1 As shown in .
[0100] The applicant reserves the right to claim all features disclosed in the application documents as essential to the present invention, provided that they are novel individually or in combination compared to the prior art. Furthermore, it is noted that features that can be advantageous in themselves are depicted in the various figures. Those skilled in the art will recognize that a feature depicted in a figure can be advantageous without the use of other features in that figure. Furthermore, those skilled in the art will recognize that advantages can also be derived from combining multiple features depicted in individual or different figures.
[0101] Reference Signs List
[0102] 1 vehicle
[0103] 10 Testing equipment
[0104] 12 operating elements
[0105] 14In-car cameras
[0106] 16 Travel mechanism sensor equipment
[0107] 18 ambient sensor devices
[0108] 20 evaluation devices
[0109] 30 output devices
[0110] 32 communication connections
[0111] 34 communication connections
[0112] 35 Driver Assistance Systems
[0113] 36 communication connections
[0114] 38 communication connections
[0115] 40 terminals
[0116] 42 smartphones
[0117] 44 Home PC
[0118] 50 information
[0119] A1, A2, A3 output
[0120] N quantity
[0121] M Map
[0122] P position
[0123] tThe time period from... to...
Claims
1. A method for evaluating an intervention of at least one driver assistance system (35) of a vehicle (1) during driving operation of the vehicle (1), wherein: The driver assistance system (35) for supporting a user of the vehicle (1) while the vehicle is moving is suitable and intended for intervening in the driving operation, and is characterized in that an evaluation device (20) determines, in at least one intervention of the driver assistance system (35), whether the intervention is perceptible to the user per se, wherein the evaluation device provides an output signal for output to the user based on the result of the determination of the perceptibility of the intervention, and wherein the evaluation device provides the output signal when the result of the evaluation results in an intervention that is not perceptible to the user and / or the intervention is not perceived by the user.
2. The method according to claim 1, characterized in that This support is provided in the area of driving safety.
3. The method according to claim 1 or 2, characterized in that The perceptibility of the intervention is determined based on an evaluation of data of the driver assistance system (35) and / or the perceptibility of the intervention is determined based on previously known and / or past similar interventions of the driver assistance system (35) and / or based on the intensity and / or type of intervention of the driver assistance system (35).
4. The method according to claim 1 or 2, characterized in that The perceptibility of the intervention is determined based on at least one value detected by at least one chassis sensor device (16) and / or a surroundings sensor device (18).
5. The method according to claim 1 or 2, characterized in that The user's reaction to the intervention is detected by means of an occupant monitoring device, and the perceptibility of the intervention is determined based on the detected reaction of the user.
6. The method according to claim 1 or 2, characterized in that The evaluation device (20) provides an output signal for output to the user as a function of the result of the determination of the perceptibility of the intervention.
7. The method according to claim 1 or 2, characterized in that The perceptibility of the intervention is determined for each of a plurality of interventions, and information about a selection of the intervention is provided for output as a function of the respective perceptibility.
8. An evaluation device (20) for a vehicle (1) having at least one driver assistance system (35), for evaluating an intervention of the driver assistance system (35) in a driving operation of the vehicle (1), wherein: The driver assistance system (35) for supporting a user of the vehicle (1) while the vehicle is moving is suitable and intended for intervening in the driving operation, and is characterized in that the evaluation device (20) is suitable and intended for and is configured to determine, in at least one intervention of the driver assistance system (35), whether the intervention is perceptible to the user per se, wherein the evaluation device is suitable and intended for providing an output signal for output to the user based on a result of the determination of the perceptibility of the intervention and for providing the output signal when the result of the evaluation results in an intervention that is not perceptible to the user and / or the intervention is not perceived by the user.
9. The evaluation device (20) according to claim 8, characterized in that This support is provided in the area of driving safety.
10. A vehicle (1) comprising an evaluation device (20) according to claim 8 or 9.
11. The vehicle (1) according to claim 10, characterized in that The vehicle (1) is a motor vehicle.
Citation Information
Patent Citations
Accident prevention system and a vehicle including the accident prevention system
US8766846B2
Method for outputting alert messages of a driver assistance system and associated driver assistance system
US9487138B2
Accident detection and recovery
US9773281B1
Method and control unit for adapting a vehicle that is at least partially automated to a user
DE102018126834A1