System and method for automatically adapting a speed of a motor vehicle that is operated by means of an automated driving system

Abstract

The present disclosure relates to a system for automatically controlling the speed of a vehicle operated by an autonomous driving system. The system comprises: an autonomous driving system configured to control the speed of a vehicle in which at least one vehicle occupant is seated; and a microphone unit configured to detect conversation inside the vehicle based on a conversation indicator including the voice of the at least one vehicle occupant. The autonomous driving system is further configured to automatically control the speed of the vehicle according to the conversation indicator. Furthermore, the present invention relates to a vehicle equipped with such a system and a method for automatically controlling the speed of a vehicle operated by an autonomous driving system.

Description

Technology Field

[0001] Various embodiments of the present disclosure relate to autonomous driving systems, vehicles, and methods thereof. Background Technology

[0002] Autonomous driving systems (ADS) have become more common in recent years. These systems are broadly classified into five levels defined by the SAE J3016 standard, with levels 1 and 2 relating to more basic driver assistance and partial automation functions, and higher levels 3 through 5 relating to more advanced functions where, at least under certain conditions, a human driver no longer needs to actively monitor the driving environment.

[0003] Level 1 and 2 systems are often referred to as Advanced Driver Assistance Systems (ADAS). In this case, if the ADAS is unable to respond appropriately to the driving situation, the driver must maintain their attention and be prepared to intervene immediately. As such, in ADAS operating at Level 1 or 2, the system monitors driver attention and provides a warning to the driver as soon as a lack of attention is detected. For example, an automatic lane keeping system warns the driver by outputting an audible alert and vibrating the seat if the driver's hands are taken away from the steering wheel for longer than a predetermined amount of time.

[0004] While providing warnings to the driver was sufficient to meet the formal and legal requirements for such systems, these warning functions do not guarantee actual safety. For example, a driver who has momentarily fallen asleep may not immediately regain full situational awareness when awakened by a warning. Therefore, there may be a delay in the ability of ADAS to respond quickly if it is unable to handle the current driving situation. In fact, a driver suddenly startled awake may exhibit abnormal behavior in the moment before their situational awareness is fully restored.

[0005] The above issue remains important as more advanced Level 3 systems become available. In this case, automation is conditional, so if driving conditions change, the driver may be asked to take control back within a limited time. These vehicles, controlled by autonomous driving systems, can adjust their driving speed based on, for example, surrounding obstacles, the presence of other vehicles, road curvature, and speed limits.

[0006] Interior noise arises from a combination of various noise characteristics, such as wind noise, engine noise, and rolling noise. Noise sources contributing to the vehicle environment can be categorized in various ways and separated into different aspects. For example, vehicle interior noise can focus on vehicle subsystems and components, such as tire-road interaction noise or aerodynamic noise. It is known in the technical field that vehicle speed is strongly correlated with interior noise levels, suggesting that the most relevant noise source lies within the vehicle itself.

[0007] For example, the document WO 2021 / 244826 A1 describes a method for controlling the volume of sound generated by a speaker (HP) inside a booth.

[0008] Literature JP 2019-137167 A describes an audio output control device capable of controlling the volume of sound output from an audio generating device at the time when a passenger starts speaking, based on an image acquisition unit that acquires an image captured by an image device that photographs the face of a passenger in a vehicle. The problem to be solved

[0009] The technical problem that the present disclosure aims to solve is to provide a method for reducing interior noise by automatically adjusting the speed of a vehicle when a conversation takes place inside the vehicle. means of solving the problem

[0010] According to a first aspect of the present disclosure, a system for automatically controlling the speed of a vehicle driven by an autonomous driving system may be provided. The system may include an autonomous driving system configured to control the speed of the vehicle. At least one vehicle occupant may be seated in the vehicle. Additionally, the system may include a microphone unit configured to detect conversation inside the vehicle based on a conversation indicator. The conversation indicator may include the voice of at least one vehicle occupant. The autonomous driving system may be further configured to automatically control the speed of the vehicle according to the conversation indicator.

[0011] According to a second aspect of the present disclosure, a vehicle equipped with a system according to a first aspect of the present disclosure may be provided.

[0012] According to a third aspect of the present disclosure, a method for automatically controlling the speed of a vehicle driven by an autonomous driving system may be provided. The method may include the step of driving a vehicle by an autonomous driving system configured to control the speed of the vehicle while at least one vehicle occupant is seated in the vehicle. The method may also include the step of detecting a conversation inside the vehicle based on a conversation indicator including the voice of at least one vehicle occupant. Furthermore, the method may include the step of the autonomous driving system automatically controlling the speed of the vehicle according to the conversation indicator. In particular, a method for automatically controlling the speed of a vehicle driven by an autonomous driving system may be provided using a system according to a first aspect of the present disclosure.

[0013] According to an embodiment of the present disclosure, when a conversation occurs within a vehicle, the driver and / or passenger may desire a reduction in interior noise. Therefore, limiting the speed or driving speed may be an appropriate measure to reduce interior noise. This allows the speed of the vehicle controlled by the autonomous driving system to be reduced. The autonomous driving system may control an autonomous vehicle that provides unmanned transportation services to a user. Generally, the autonomous driving system may be installed in the autonomous vehicle. Alternatively, at least a part of the autonomous driving system may be placed outside the autonomous vehicle to control the autonomous vehicle remotely. The conversation may take place within the passenger cabin or via telephone. That is, the present disclosure may provide speed control of the vehicle controlled by the autonomous driving system in response to a conversation detected within the vehicle. The minimum speed or threshold at which speed control, particularly speed reduction, can be performed may be set by traffic regulations.

[0014] Conversation may be detected when a conversation indicator is triggered. When conversation is detected, a step to automatically adjust the speed may be performed. Of course, speed may be reduced only where relevant traffic laws do not prohibit driving slower, such as when there is a minimum speed limit for the relevant driving lane, and speed may be increased only where relevant traffic laws do not prohibit driving faster.

[0015] Accordingly, the present disclosure can address the cause in which at least one vehicle occupant, namely the driver and / or passenger, is likely to speak louder than usual. As a result of applying the present disclosure, less stressful conversation among vehicle occupants becomes possible, which can lead to a higher user experience. Since driving speed is linked to interior noise, the preferred speed may vary depending on the ongoing conversation.

[0016] When interior noise is reduced, the driver and passengers can communicate more easily. Additionally, as the vehicle can better meet the user's needs through the present disclosure, the user may be more likely to use the autonomous driving system rather than driving manually.

[0017] The present disclosure may be particularly related to vehicles, including automobiles equipped with advanced driver assistance systems and autonomous driving capabilities.

[0018] When applying the system and / or method according to the present disclosure, new or additional hardware may not be required, particularly if the vehicle is equipped with an in-vehicle microphone. The present disclosure may utilize the vehicle's existing equipment. Consequently, the present disclosure may not affect the vehicle's package, thereby saving interior space. Furthermore, the present disclosure may provide a lower total cost of ownership (TCO).

[0019] Another advantage of the present disclosure may be that this method is a fully automated process. Therefore, this method can also be applied to new mobility services, PBVs (purpose-built vehicles), and robotaxis.

[0020] As used herein, the terms “vehicle,” “vehicular,” or other similar terms encompass all automobiles, such as passenger cars, buses, trucks, and various commercial vehicles, including sports utility vehicles (SUVs), and may be understood to include hybrid vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles, and other alternative fuel vehicles (e.g., fuels derived from resources other than petroleum). A hybrid vehicle referred to herein is a vehicle having two or more power sources, such as, for example, a vehicle having both gasoline power and electric power.

[0021] In the sense of the present application, a vehicle may include a two-wheeled vehicle such as a bicycle, an automobile, a truck, or a similar thing.

[0022] According to one embodiment of the present disclosure, the system may further include a seat occupancy detection device configured to detect the presence of at least one other vehicle occupant. For example, a conversation indicator may be triggered by the seat occupancy detection device when at least one other vehicle occupant is present in a second row seat or a third row seat or both.

[0023] According to another embodiment of the present disclosure, the system may further include a camera unit configured to detect the presence of at least one other vehicle occupant. Thus, the camera unit can determine where the at least one other vehicle occupant is sitting within the vehicle and / or who is speaking within the vehicle. Furthermore, the camera unit may be configured to determine the facial features of the at least one vehicle occupant. In this way, an emotion analysis of the conversation based on the facial features of the at least one vehicle occupant can be performed by the camera unit.

[0024] According to another embodiment of the present disclosure, the system may further include a voice recognition device configured to detect the frequency of checking back between at least one vehicle occupant. The voice recognition device may also be further configured to detect the conversation of at least two vehicle occupants sitting in different rows of seats and conversing.

[0025] According to another embodiment of the present disclosure, the autonomous driving system may be further configured to limit the acceleration of the vehicle. Accordingly, noise generated by the vehicle's propulsion system during the acceleration process of the vehicle may be reduced. In particular, noise may be reduced if the propulsion system is composed of an internal combustion engine. Acceleration may be limited to a range of less than about 2 m / s².

[0026] According to another embodiment of the present disclosure, the system may further include an audio-video-navigation system configured to adjust the duration of the conversation, changes in speed, and the maximum and / or minimum speed of acceleration. The duration of the conversation of at least one vehicle occupant, serving as a trigger for conversation detection, may be adjusted by at least one vehicle occupant. Furthermore, the magnitude of the changes in speed, i.e., the decrease or increase in speed, may be adjusted by at least one vehicle occupant. Alternatively or additionally, the maximum value of acceleration may be adjusted by at least one vehicle occupant. Additionally, the minimum speed at which speed control, particularly speed reduction, may be performed may be adjusted by at least one vehicle occupant. Nevertheless, the minimum speed or threshold may be set by traffic regulations and / or user settings. Furthermore, at least one vehicle occupant may stop the speed reduction initiated by pressing a button on the vehicle's audio-video-navigation system, for example.

[0027] Optionally, the system may further include a non-transient computer-readable storage medium communicating with an autonomous driving system, wherein the storage medium may be configured to store reference values ​​for the volume of at least one vehicle occupant, facial features of at least one vehicle occupant, heart rate variability and / or skin conductivity of at least one vehicle occupant.

[0028] According to another embodiment of the present disclosure, speed may be controlled according to a predetermined speed change range, a predetermined percentage value range, and / or a reduction in interior noise of the vehicle. Since tire irritation can be a contributing factor to the generation of interior noise of the vehicle, controlling the speed, particularly reducing it, according to a predetermined speed change range—that is, the magnitude of the speed reduction or increase—or a predetermined percentage value range or both, can reduce interior noise. For example, the predetermined speed change range may be about 20 km / h or less, particularly a range of about 5 km / h to about 20 km / h. For example, the predetermined percentage value range may be a range of about 10% to about 20%. The reduction in interior noise may be a range of about 3 dB to about 8 dB.

[0029] For example, vehicle interior noise can be reduced by increasing speed so that the stimulus frequency is further away from the vehicle's natural frequency. Alternatively, or additionally, vehicle interior noise can be reduced by increasing speed and selecting a higher gear to lower the resulting engine speed. In both of the aforementioned cases, the speed can be increased slightly, particularly by speed changes of about 10 km / h or less. The percentage value may include environmental conditions such as the current road class and weather conditions.

[0030] Optionally, changing lanes may reduce interior noise depending on the road surface. Therefore, the vehicle may change lanes if permitted by driving rules. If the interior noise is lower than in the original lane, the vehicle may remain in the new lane.

[0031] According to another embodiment of the present disclosure, the conversation indicator may include the presence of at least one other vehicle occupant, the volume of at least one vehicle occupant, the facial features of at least one vehicle occupant, the duration of the conversation of at least one vehicle occupant, and / or the frequency of repeating between at least one vehicle occupant. For example, the conversation indicator may be triggered when at least one other vehicle occupant is present in the second row seat or the third row seat or both. The frequency of repeating may be detected by a voice recognition device installed in the vehicle.

[0032] According to another embodiment of the present disclosure, the conversation duration may exceed a value in the range of about 1 minute to about 3 minutes. Thus, a short conversation may not result in automatic speed adjustment. Furthermore, multiple speed changes within a few minutes can be prevented and driving comfort can be improved. Alternatively or additionally, the conversation duration may exceed a predetermined ratio of speech to silence.

[0033] According to another embodiment of the present disclosure, the conversation may include at least two vehicle occupants sitting in different rows of seats and conversing.

[0034] According to another embodiment of the present disclosure, the conversation indicator may further determine whether the detected voice corresponds to radio broadcast content. If the detected voice includes radio broadcast content, the conversation indicator may not be triggered. Therefore, when the detected voice includes radio broadcast content, the conversation may not be detected.

[0035] According to another embodiment of the present disclosure, the step of automatically controlling the speed may include limiting the acceleration of the vehicle. Accordingly, noise generated by the vehicle's propulsion system during the acceleration process of the vehicle may be reduced. In particular, noise may be reduced when the propulsion system is composed of an internal combustion engine. Acceleration may be limited to a range of about 2[TS1] m / s² or less.

[0036] According to another embodiment of the present disclosure, the method may further include the step of detecting the volume of conversation after automatically adjusting the speed, wherein the volume of conversation after automatically adjusting the speed may be compared with the volume of conversation before automatically adjusting the speed, and the step of automatically adjusting the speed may be repeated based on the comparison of the two volumes. Thus, the step of automatically adjusting the speed does not need to be repeated in the same way, and the speed may be adjusted in a different manner than before. After adjusting the speed, it may be detected whether the volume of conversation, that is, the volume of at least one vehicle occupant speaking, has decreased. If it is determined that the decrease in the volume of at least one vehicle occupant speaking is insufficient, an additional step of automatically adjusting the speed, particularly a step of further reducing the speed, may be performed.

[0037] Optionally, a signal-to-noise ratio (SNR) calculation may be performed to detect whether interior noise is the cause of speaking loudly. For example, if the difference in volume between the conversation volume and the interior noise does not change even if the interior noise level decreases due to a decrease in speed, it can be assumed that the speaking vehicle occupant intends to speak loudly.

[0038] According to another embodiment of the present disclosure, the conversation indicator may further include an emotional analysis of the conversation, wherein the emotional analysis may be based on the feature amount of the voice, facial features of at least one vehicle occupant, heart rate variability, and / or skin conductivity of at least one vehicle occupant. That is, the conversation indicator may further determine the level of arousal of the conversation. If the emotional analysis results reveal that at least one vehicle occupant has a high level of arousal, particularly a level higher than usual, it may be assumed that this is the reason for speaking loudly, rather than a high level of interior noise.

[0039] For example, a voice acquisition unit may acquire voice data from at least one vehicle occupant who is speaking. An emotion analysis unit may divide the voice data acquired by the voice acquisition unit into predetermined periods and, for example, quantify the user's emotion based on voice features within the predetermined periods. The predetermined periods may, for example, be the duration of speaking in one breath, that is, the period from one breath to the next, and this may be defined as a single sentence. Not limited thereto, the predetermined periods may be a predetermined cycle, a predetermined number of measures, or a series of words separated by punctuation when analyzing lyrics. The voice features may be at least one of the pitch, sound intensity, intonation of spoken words, and speech rate of words contained in the voice, or a variation of at least one of these.

[0040] Furthermore, the emotion analysis unit may base its analysis on the results of quantifying emotions at each of the multiple predetermined periods constituting the voice data related to the conversation. An emotional state or a transition of that state may be obtained, and the emotion of the conversation may be evaluated. The emotion may be, for example, at least one of joy, calmness, sadness, anger, and vitality. Furthermore, the evaluation may be, for example, the magnitude relationship of the emotions quantified in the conversation. To analyze the emotion, various voice data may be played back in advance, and the type of emotion expressed by the listener may be evaluated.

[0041] For example, it is possible to evaluate what type of emotion each voice data expresses, such as anger, calmness (normal), sadness, happiness, or vigor. Each voice data can be tagged with joy, normality, sadness, anger, vitality, etc. Tagged voice data can be stored in a storage unit as reference data. Then, the voice data of the conversation can be compared with the reference data, and the pitch and intensity of the sound can be compared. Subsequently, reference data similar to the voice data of the conversation can be obtained regarding features such as the intonation and speech rate of the spoken words, and the type of emotion can be determined by the tags attached to the similar reference data. The magnitude of the emotion can be quantified by the number of similar reference data. For example, if there are many data tagged as anger among the similar reference data, the anger can be evaluated as high, and if there are few similar reference data tagged as anger, the sadness can be evaluated as low.

[0042] Quantifying emotions is not limited to this, and other methods may be used. For example, machine learning (deep learning) can be performed using the above reference data as teacher data, and correlations can be created from features such as pitch, sound intensity, intonation of spoken words, and speech speed of words. A mathematical model (neural network) can be created to obtain the degree of correlation with emotion tags (magnitude of emotion) and stored in a storage unit. Furthermore, the control unit of a vehicle or autonomous driving system can be configured to input the feature quantities of the speech data of the conversation into the mathematical model to obtain the type and magnitude of the emotion.

[0043] According to another embodiment of the present disclosure, the step of automatically adjusting the conversation indicator and / or the speed may be set by the at least one vehicle occupant. For example, the duration of the conversation of the at least one vehicle occupant as a trigger for conversation detection may be adjusted by the at least one vehicle occupant. Furthermore, the magnitude of the speed change, i.e., the decrease or increase in speed, may be adjusted by the at least one vehicle occupant. Alternatively or additionally, the maximum value of acceleration may be adjusted by the at least one vehicle occupant. Also, the minimum speed at which speed adjustment, particularly speed reduction, may be performed may be adjusted by the at least one vehicle occupant. Furthermore, the at least one vehicle occupant may stop the speed reduction initiated by, for example, pressing a button on the vehicle's audio-video-navigation system.

[0044] According to another embodiment of the present disclosure, the step of automatically adjusting the speed may not be performed when the conversation indicator is not triggered. For example, if the conversation decreases significantly, the autonomous driving system may not automatically adjust according to the conversation indicator and may switch back to a normal target speed and / or acceleration. Effects of the invention

[0045] According to an embodiment of the present disclosure, if interior noise is reduced, the driver and passengers can communicate more easily. Additionally, since the vehicle can better meet the user's needs through the present disclosure, the user may be more likely to use the autonomous driving system rather than driving manually. Brief explanation of the drawing

[0046] The attached drawings may be included to provide a further understanding of the invention and may be incorporated into or constitute part of this specification. The drawings may illustrate embodiments of the invention and, together with the specification, serve to explain the principles of the invention. Other embodiments of the invention and many intended advantages may be readily recognized as they are better understood by referring to the following detailed description. The elements of the drawings may not necessarily be depicted in proportion to one another. In the drawings, the same reference numerals may represent identical or functionally similar components unless otherwise specified. FIG. 1 schematically illustrates a system for automatically controlling the speed of a vehicle driven by an autonomous driving system according to one embodiment of the present invention. FIG. 2 may show a flowchart of a method for automatically controlling the speed of a vehicle driven by an autonomous driving system according to another embodiment of the present invention. FIG. 3 may show a flowchart of the steps of a method for detecting the conversation of FIG. 2 according to another embodiment of the present invention. Specific details for implementing the invention

[0047] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0048] In the various flowcharts of this document, at least some of the steps may be omitted or their order may be changed, and at least some of the various embodiments of this document may be performed at specific points in time of each step of the flowchart.

[0049] Although specific embodiments have been illustrated and described in this specification, a person skilled in the art will recognize that various alternative and / or equivalent embodiments are possible to replace the specific embodiments illustrated and described without departing from the scope of the invention. In general, this application may be intended to include all adaptations or variations of the specific embodiments discussed in this specification.

[0050] Hereinafter, embodiments will be described in detail with reference to the attached drawings, provided that identical or corresponding components are given the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted.

[0051] FIG. 1 schematically illustrates a system (1) for automatically controlling the speed of a vehicle (V) driven by an autonomous driving system (2) according to one embodiment of the present disclosure. Specifically, FIG. 1 illustrates a vehicle (V) equipped with the system (1).

[0052] The system (1) may include an autonomous driving system (2) configured to control the speed of the vehicle (V), wherein at least one vehicle occupant may be seated in the vehicle (V).

[0053] The system (1) may further include a microphone unit configured to detect conversation inside the vehicle (V) based on a conversation indicator. The conversation indicator may include the voice of at least one vehicle occupant. The autonomous driving system (2) may be further configured to automatically adjust the speed of the vehicle (V) according to the conversation indicator.

[0054] For example, the autonomous driving system (2) may be further configured to limit the acceleration of the vehicle (V). Thus, noise generated by the propulsion system of the vehicle (V) during the acceleration process of the vehicle may be reduced. In particular, noise may be reduced if the propulsion system is composed of an internal combustion engine. Acceleration may be limited to a range of about 2 [TS1] m / s² or less.

[0055] Optionally, the system (1) may further include a seat occupancy detection device configured to detect the presence of at least one other vehicle occupant. For example, a conversation indicator may be triggered by the seat occupancy detection device when at least one other vehicle occupant is present in the second row seat or the third row seat or both.

[0056] Optionally, the system (1) may further include a camera unit (3) configured to detect the presence of at least one other vehicle occupant. Thus, the camera unit (3) can determine where at least one other vehicle occupant is sitting within the vehicle (V) and / or who is speaking within the vehicle (V). Furthermore, the camera unit (3) may be configured to determine the facial features of at least one vehicle occupant. In this way, an emotion analysis of the conversation based on the facial features of at least one vehicle occupant can be performed by the camera unit (3).

[0057] Optionally, the system (1) may further include a voice recognition device configured to detect the frequency of repeating between at least one vehicle occupant. The voice recognition device may also be further configured to detect the conversation of at least two vehicle occupants sitting in different rows of seats and conversing.

[0058] Optionally, the system (1) may further include an audio-video-navigation system configured to adjust the duration of the conversation, changes in speed, and the maximum and / or minimum speed of acceleration. The duration of the conversation of at least one vehicle occupant as a trigger for conversation detection may be adjusted by at least one vehicle occupant.

[0059] Furthermore, the magnitude of the speed change, i.e., the speed decrease or increase, can be adjusted by at least one vehicle occupant. Alternatively or additionally, the maximum value of acceleration can be adjusted by at least one vehicle occupant. Also, the minimum speed at which speed control, particularly speed reduction, can be performed can be adjusted by at least one vehicle occupant. Nevertheless, the minimum speed or threshold can be set by traffic regulations and / or user settings. Furthermore, at least one vehicle occupant can stop the speed reduction initiated by, for example, pressing a button on the vehicle's (V) audio-video-navigation (AVN) system.

[0060] Optionally, the system (1) may further include a non-transient computer-readable storage medium communicating with an autonomous driving system (2), wherein the storage medium may be configured to store reference values ​​for the volume of at least one vehicle occupant, facial features of at least one vehicle occupant, heart rate variability and / or skin conductivity of at least one vehicle occupant.

[0061] FIG. 2 may show a flowchart of a method (M) for automatically controlling the speed of a vehicle (V) driven by an autonomous driving system (2) according to another embodiment of the present invention.

[0062] The method (M) may include, for example, a step of driving a vehicle (V) (M0), a step of detecting a conversation inside the vehicle (V) (M1), a step of automatically adjusting the speed of the vehicle (V) (M2), and a step of detecting the volume of the conversation after the step of automatically adjusting the speed (M2) (M3).

[0063] In step (M0), the vehicle (V) can be driven by an autonomous driving system (2) configured to control the speed of the vehicle (V), where at least one vehicle occupant can be seated in the vehicle (V).

[0064] For example, the conversation may involve at least two vehicle occupants sitting in different rows of seats and conversing.

[0065] In step (M1), conversation can be detected inside the vehicle (V) based on a conversation indicator that includes the voice of at least one vehicle occupant. When the conversation indicator is triggered, conversation can be detected. When conversation is detected, step (M2) of automatically adjusting the speed can be performed.

[0066] Conversation indicators may include the presence of at least one other vehicle occupant, the volume of at least one vehicle occupant, the facial features of at least one vehicle occupant, the duration of the conversation of at least one vehicle occupant, and / or the frequency of questioning between at least one vehicle occupant. For example, conversation indicators may be triggered when at least one other vehicle occupant is present in the second row seat or the third row seat or both. The frequency of mutual responses (e.g., the frequency of questioning) may be detected by a voice recognition device installed in the vehicle.

[0067] In particular, the duration of the conversation may exceed a value in the range of 1 minute to about 3 minutes. Alternatively, or additionally, the duration of the conversation may exceed a standard value determined by the ratio of speaking time to pause time.

[0068] Additionally, the conversation indicator may further include an analysis of the sentiment of the conversation, wherein the analysis of sentiment may be based on voice features, facial features of at least one vehicle occupant, heart rate variability and / or skin conductivity of at least one vehicle occupant.

[0069] In other words, conversational indicators can additionally assess the arousal level of the conversation. If sentiment analysis reveals that at least one vehicle occupant has a high level of arousal, particularly higher than usual, it can be determined that they are intentionally speaking loudly rather than due to high interior noise levels. For example, a voice collection device can collect voice data from the occupant during the conversation.

[0070] In step (M2), the speed of the vehicle (V) can be automatically controlled by the autonomous driving system (2) according to the conversation indicator.

[0071] For example, speed may be controlled (M2) according to a predetermined speed change range, a predetermined percentage value range, and / or a reduction in interior noise of the vehicle. For example, the predetermined speed change range may be about 20 km / h or less, specifically from about 5 km / h to about 20 km / h. For example, the predetermined percentage value range may be from about 10% to about 20%. The reduction in interior noise may be from about 3 dB to about 8 dB. For example, the interior noise of the vehicle may be reduced by increasing the speed so that the stimulus frequency has a greater distance from the vehicle's natural frequency.

[0072] Alternatively, or additionally, the interior noise of the vehicle can be reduced by increasing the speed and selecting a higher gear to lower the resulting engine speed. In this case, the speed can be increased slightly to about 10 km / h or less.

[0073] The percentage value may include environmental conditions such as the current road class and weather conditions. Optionally, changing the driving lane based on road pavement conditions may also reduce interior noise. Therefore, the vehicle may change the driving lane if permitted by driving rules. If the interior noise is lower than in the original driving lane, the vehicle may maintain the new driving lane.

[0074] The step (M2) for automatically controlling speed may include limiting the acceleration of the vehicle (V). Thus, noise generated by the propulsion system of the vehicle (V) during the acceleration process of the vehicle may be reduced. In particular, there is a greater noise reduction effect when the propulsion system is an internal combustion engine. Acceleration may be limited to a range of about 2 m / s² or less.

[0075] The step (M2) of automatically adjusting the speed may not be performed when the conversation indicator is not triggered (e.g., activated). For example, if the conversation decreases significantly, the autonomous driving system may not automatically adjust based on the conversation indicator and may revert to the normal target speed and / or acceleration. That is, if step (M1) is insufficient or not satisfied, the speed may not be automatically adjusted (M2).

[0076] In the optional step (M3), the volume of the conversation may be detected after the step of automatically adjusting the speed (M2), where the volume of the conversation after the step of automatically adjusting the speed (M2) may be compared with the volume of the conversation before the step of automatically adjusting the speed (M2). Based on the comparison of the two volumes, the step of automatically adjusting the speed (M2) may be repeated. Thus, the step of automatically adjusting the speed (M2) does not need to be repeated in the same way, and the speed may be adjusted in a different way than before.

[0077] After speed adjustment (M2), it can be detected whether the volume of at least one passenger in conversation has been reduced (M3). If it is determined that the volume reduction is insufficient, an additional speed adjustment step, specifically an additional speed reduction, may be performed.

[0078] Optionally, a signal-to-noise ratio (SNR) calculation may be performed to detect whether interior noise is the cause of loud speaking. For example, if the difference in volume between the conversation volume and the interior noise does not change even if the interior noise level decreases due to a reduction in speed, it may be determined that the occupant is intentionally speaking loudly.

[0079] For example, the step (M2) for automatically adjusting the conversation indicator and / or speed may be set by at least one vehicle occupant. For example, the conversation duration of at least one vehicle occupant serving as a trigger for conversation detection may be adjusted by at least one vehicle occupant. Furthermore, the magnitude of the speed change, i.e., the decrease or increase in speed, may be adjusted by at least one vehicle occupant.

[0080] Alternatively or additionally, the maximum value of acceleration can be adjusted by at least one vehicle occupant. Furthermore, the minimum speed at which speed control, particularly speed reduction, can be performed can be adjusted by at least one vehicle occupant. Moreover, at least one vehicle occupant can stop the speed reduction that has already started, for example, by pressing a button on the vehicle's audio-video-navigation system.

[0081] FIG. 3 may show a flowchart of a method step (M1) for detecting the conversation of FIG. 2 according to another embodiment of the present invention. The method step (M1) may also be useful for determining whether there is an advantage to reducing speed.

[0082] When voice or sound is detected or captured (M1-1) in the passenger compartment of the vehicle, a conversation may be in progress.

[0083] Optionally, background noise can be filtered (M1-2).

[0084] Furthermore, indoor noise, particularly the filtered portion of indoor noise, can be classified (M1-3) to distinguish between human voice and other voice types.

[0085] The conversation indicator may further determine or confirm (M1-4) whether the detected voice, particularly the human voice in the conversation, corresponds to radio broadcast content. If the detected voice contains radio broadcast content, the conversation indicator may not be triggered. Therefore, when the detected voice contains radio broadcast content, the conversation may not be detected.

[0086] Additionally, the volume over time can be judged (M1-5) to determine whether to trigger a conversation indicator.

[0087] All method steps M0, M1, M1-1, M1-2, M1-3, M1-4, M2, and M3 described above may be performed in the order described or illustrated, but the order may not be limited to these examples.

[0088] In the foregoing detailed description, various features may be grouped together into one or more examples for the purpose of simplifying the disclosure. It should be understood that the foregoing description is illustrative and is not intended to be limiting. It may be intended to include all alternatives, modifications, and equivalents of other features and embodiments. A person skilled in the art will be able to clearly see many other examples by reviewing the foregoing specification. Embodiments may be selected and described to explain the principles of the invention and their practical applications, thereby enabling a person skilled in the art to utilize the invention and various embodiments by making various modifications suitable for the specific use being considered.

[0089] The term "part" as used in this embodiment refers to a software or hardware component, such as a field-programmable gate array (FPGA) or an ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Thus, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0090] Although the foregoing has been described with reference to preferred embodiments of the present disclosure, those skilled in the art will understand that various modifications and changes can be made to the present disclosure without departing from the spirit and scope of the present disclosure as set forth in the following claims. Explanation of the symbols

[0091] 1: System 2: Autonomous driving system 3: Camera Unit V: Vehicle M: Method M0: The stage of driving a car M1: Vehicle interior conversation detection M1-1: Sound Capture M1-2: Background Noise Filtering M1-3: Acoustic Classification M1-4: Verify voice source M1-5: Volume determination over time M2: Automatic vehicle speed control M3: Dialogue volume detection after automatic speed adjustment

Claims

Claim 1 A system for automatically controlling the speed of a vehicle driven by an autonomous driving system, comprising: an autonomous driving system configured to control the speed of the vehicle in which at least one vehicle occupant is seated; and a microphone unit configured to detect conversation inside the vehicle based on a conversation indicator including the voice of the at least one vehicle occupant; wherein the autonomous driving system is configured to automatically control the speed of the vehicle according to the conversation indicator. Claim 2 A system according to claim 1, characterized in that the system further comprises a seat occupancy detection device configured to detect the presence of at least one other vehicle occupant. Claim 3 A system according to claim 1, characterized in that the system further comprises a camera unit configured to detect the presence of at least one other vehicle occupant. Claim 4 A system according to claim 1, further comprising a voice recognition device configured to detect the frequency of questioning between at least one vehicle occupant. Claim 5 A system according to claim 1, characterized in that the autonomous driving system is configured to limit the acceleration of the vehicle. Claim 6 A system according to claim 1, further comprising an audio-video-navigation system configured to adjust the duration of the conversation, changes in speed, maximum and / or minimum speed of acceleration. Claim 7 A vehicle characterized by having a system according to any one of paragraphs 1 to 6. Claim 8 A method for automatically controlling the speed of a vehicle operated by an autonomous driving system, comprising: using a system according to any one of claims 1 to 6, (a) operating a vehicle in which at least one vehicle occupant is seated by an autonomous driving system configured to control the speed of said vehicle; (b) detecting a conversation inside said vehicle based on a conversation indicator including the voice of said at least one vehicle occupant; and (c) the autonomous driving system automatically controlling the speed of said vehicle according to said conversation indicator. Claim 9 A method according to claim 8, wherein the step (c) of controlling the speed is characterized by controlling according to a predetermined speed change range, a predetermined percentage value range, and / or a reduction in interior noise of the vehicle. Claim 10 A method according to claim 8, wherein the conversation indicator comprises the presence of at least one other vehicle occupant, the volume of the at least one vehicle occupant, the facial features of the at least one vehicle occupant, the duration of the conversation of the at least one vehicle occupant, and / or the frequency of questioning between the at least one vehicle occupants. Claim 11 A method according to claim 10, characterized in that the duration of the conversation exceeds a value in the range of 1 minute to about 3 minutes. Claim 12 A method according to claim 8, characterized in that the conversation includes at least two vehicle occupants sitting in different rows of seats and conversing. Claim 13 A method according to claim 8, wherein the conversation indicator further comprises determining whether the detected voice corresponds to radio broadcast content. Claim 14 A method according to claim 8, wherein the step (c) of automatically adjusting the speed includes limiting the acceleration of the vehicle. Claim 15 A method according to claim 8, further comprising: (d) a step of detecting a conversation volume after the step of automatically adjusting the speed (c); and (e) a step of comparing the conversation volume after the step of adjusting the speed (c) with the conversation volume before the step of adjusting the speed (c), and repeating the step of automatically adjusting the speed (c) based on the comparison result. Claim 16 A method according to claim 8, wherein the conversation indicator further includes an emotional analysis of the conversation, and the emotional analysis of the conversation is based on voice feature quantities, facial features of at least one vehicle occupant, heart rate variability, and / or skin conductivity of at least one vehicle occupant. Claim 17 A method according to claim 8, wherein the step (c) of automatically adjusting the conversation indicator and / or the speed is settable by at least one vehicle occupant. Claim 18 A method according to claim 8, wherein the step (c) of automatically adjusting the speed is not performed when the conversation indicator is not triggered.

Images