Vehicle emergency braking method, device, system and vehicle

Abstract

The application provides a vehicle emergency braking method, device, system and vehicle, comprising: in response to monitoring that the vehicle executes an automatic parking function, collecting audio signals, vibration signals and elastic wave signals generated by an outside target user interfering with the vehicle, performing feature analysis on the audio signals, vibration signals and elastic wave signals, determining a confidence degree of the audio signals, a probability value of the vibration signals and a similarity of the elastic wave signals, fusing and calculating to obtain a credibility of an emergency parking event, generating an emergency braking instruction according to the credibility of the emergency parking event and current state information of the vehicle, and controlling the vehicle to execute a braking operation and stop parking according to the emergency braking instruction. The application increases an emergency braking mechanism directly triggered by an outside user, fuses multi-modal sensor signals, accurately evaluates the credibility of the emergency parking event, improves the overall emergency processing capability of the automatic parking system, and guarantees the safety and reliability of the automatic parking in a complex dangerous scene.

Description

Technical Field

[0001] This invention relates to the field of automatic parking technology, and in particular to a vehicle emergency braking method, device, system, and vehicle. Background Technology

[0002] As the automotive industry continues to move towards intelligence, automatic parking technology has become a key area of ​​research and development for many automakers and research institutions. Current automatic parking systems are mainly based on a series of onboard sensors and complex control algorithms to achieve autonomous parking and exit operations.

[0003] Currently, when vehicles perform automatic parking, they face some complex emergency dangerous situations that are not detected by the vehicle's sensors (millimeter-wave radar, cameras). For example, if a vehicle accidentally slides into a dangerous area such as a pond or cliff due to slippery ground, system failure, or other unforeseen factors, the automatic parking system cannot respond quickly and effectively because the vehicle cannot receive timely intervention from the driver. This further affects the safety and reliability of automatic parking in complex and dangerous scenarios. Summary of the Invention

[0004] In view of this, the present invention aims to provide a vehicle emergency braking method, device, system and vehicle to solve the problem that the vehicle cannot receive timely human intervention measures, which makes it difficult for the automatic parking system to respond quickly and effectively, affecting the safety and reliability of automatic parking in complex and dangerous scenarios.

[0005] According to a first aspect of the present invention, a vehicle emergency braking method is provided, applied to a vehicle emergency braking system, the method comprising:

[0006] In response to the detection that the vehicle is performing an automatic parking function, audio signals, vibration signals, and elastic wave signals generated by the intervention of a target user outside the vehicle are collected; wherein, the audio signals, vibration signals, and elastic wave signals are used to identify emergency parking events;

[0007] Feature analysis is performed on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0008] The credibility of the emergency stop event is calculated based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0009] An emergency braking command is generated based on the credibility of the emergency braking event and the vehicle's current status information.

[0010] According to the emergency braking command, control the vehicle to perform braking operation and stop parking.

[0011] Optionally, the vehicle emergency braking system includes external sensors, including an external microphone, a vibration sensor, and an elastic wave sensor. The feature is that, in response to detecting that the vehicle is performing an automatic parking function, the acquisition of audio signals, vibration signals, and elastic wave signals generated by an external user intervening in the vehicle's operation includes:

[0012] In response to detecting that the vehicle is performing an automatic parking function, the system uses the external microphone to collect audio signals generated by the external target user's intervention in the vehicle, the vibration sensor to collect vibration signals generated by the external target user's intervention in the vehicle, and the elastic wave sensor to collect elastic wave signals generated by the external target user's intervention in the vehicle.

[0013] Optionally, the step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes:

[0014] The audio signal is subjected to feature analysis to obtain the audio content and audio features corresponding to the audio signal, and it is determined whether the audio signal is valid.

[0015] If the audio signal is emitted by the target user and the audio content contains a preset emergency stop command, then the audio signal is determined to be a valid audio signal.

[0016] The confidence level of a valid audio signal is calculated based on its audio characteristics.

[0017] Optionally, the step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes:

[0018] The vibration signal is subjected to feature analysis to obtain its time-domain and frequency-domain features; wherein, the time-domain features include duration and signal variance, and the frequency-domain features include signal amplitude and signal energy;

[0019] The probability value of the vibration signal is calculated based on the time-domain characteristics and the frequency-domain characteristics.

[0020] Optionally, the step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes:

[0021] The elastic wave signal is subjected to feature analysis to obtain the elastic wave characteristics of the elastic wave signal; wherein, the elastic wave characteristics include at least one of elastic wave frequency, elastic wave amplitude and elastic wave phase;

[0022] The elastic wave characteristics of the elastic wave signal are matched with a preset elastic wave template to obtain a matching result;

[0023] If the matching result is that the elastic wave signal is similar to the elastic wave template, the similarity between the elastic wave signal and the elastic wave template is calculated.

[0024] Optionally, calculating the credibility of the emergency braking event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes:

[0025] The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are obtained, and the evaluation function and weighting coefficients of the signal are determined.

[0026] The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are weighted using the evaluation function and weighting coefficients to obtain the weighted result of multimodal signal fusion.

[0027] The weighted result is used to determine the credibility of the emergency parking event.

[0028] Optionally, generating an emergency braking command based on the credibility of the emergency braking event and the vehicle's current state information includes:

[0029] If the credibility of the emergency braking event is greater than or equal to the first preset threshold and less than the second preset threshold, a braking warning command is generated.

[0030] If the credibility of the emergency braking event is greater than or equal to the second preset threshold, and the current vehicle status information meets the preset braking conditions, then an emergency braking command is generated.

[0031] According to a second aspect of the present invention, a vehicle emergency braking device is provided, applied to a vehicle emergency braking system, the device comprising:

[0032] The signal acquisition module is used to acquire audio signals, vibration signals, and elastic wave signals generated by external user intervention in response to the detection of the vehicle performing automatic parking function; wherein, the audio signals, vibration signals, and elastic wave signals are used to identify emergency parking events.

[0033] The signal processing module is used to perform feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0034] The event evaluation module is used to calculate the credibility of the emergency stop event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0035] The command generation module is used to generate an emergency braking command based on the credibility of the emergency braking event and the current vehicle status information.

[0036] The braking control module is used to control the vehicle to perform braking operations and stop parking according to the emergency braking command.

[0037] According to a third aspect of the present invention, a vehicle emergency braking system is provided, the system including external sensors and a vehicle controller, the external sensors including an external microphone, a vibration sensor and an elastic wave sensor;

[0038] The external microphone collects audio signals generated by the external target user's intervention in the vehicle; the vibration sensor collects vibration signals generated by the external target user's intervention in the vehicle; and the elastic wave sensor collects elastic wave signals generated by the external target user's intervention in the vehicle.

[0039] The vehicle controller is configured to acquire audio signals, vibration signals, and elastic wave signals collected by the external sensors, perform feature analysis on the audio signals, vibration signals, and elastic wave signals to determine the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, calculate the credibility of the emergency stopping event based on the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, generate an emergency braking command based on the credibility of the emergency stopping event and the current vehicle status information, and control the vehicle to perform braking operation and stop parking based on the emergency braking command.

[0040] According to another aspect of the present invention, a vehicle is also provided, the vehicle including the vehicle emergency braking system as described above, which, when executed, implements the steps of the vehicle emergency braking method as described above.

[0041] The vehicle emergency braking method provided in this invention responds to the detection of an automatic parking function being executed by a vehicle. It collects audio signals, vibration signals, and elastic wave signals generated by external user intervention. Feature analysis is performed on these signals to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. The confidence level of the emergency parking event is calculated by fusing these signals. Based on the confidence level of the emergency parking event and the vehicle's current state information, an emergency braking command is generated. According to the emergency braking command, the vehicle is controlled to perform braking operations and stop parking. This invention adds an emergency braking mechanism that can be directly triggered by external users, fuses multimodal sensor signals, accurately assesses the confidence level of emergency parking events, and responds to emergency interventions from external users based on both the confidence level of the emergency parking event and the vehicle's state. This avoids false triggering of the automatic parking function and enables timely and rapid response to users' emergency intervention needs in emergency scenarios. It reduces the risk of accidents caused by the inability to stop in time during automatic parking, improves the overall emergency handling capability of the automatic parking system, and further ensures the safety and reliability of automatic parking in complex and dangerous scenarios.

[0042] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0043] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0044] Figure 1 This is a flowchart of the steps of a vehicle emergency braking method provided in an embodiment of the present invention;

[0045] Figure 2 yes Figure 1 The flow chart of step 102 in the vehicle emergency braking method provided in this embodiment of the invention Figure 1 ;

[0046] Figure 3 yes Figure 1 The flow chart of step 102 in the vehicle emergency braking method provided in this embodiment of the invention Figure 2 ;

[0047] Figure 4 yes Figure 1The flow chart of step 102 in the vehicle emergency braking method provided in this embodiment of the invention Figure 3 ;

[0048] Figure 5 yes Figure 1 A flowchart of step 103 in the vehicle emergency braking method provided in this embodiment of the invention;

[0049] Figure 6 This is a schematic diagram of the structure of a vehicle emergency braking device provided in an embodiment of the present invention;

[0050] Figure 7 This is a schematic diagram of the structure of a vehicle emergency braking system provided in an embodiment of the present invention;

[0051] Figure 8 This is a schematic diagram of an external sensor in a vehicle emergency braking system provided in an embodiment of the present invention.

[0052] Figure label:

[0053] 1-External microphone, 2-Vibration sensor, 3-Elastic wave sensor. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those skilled in the art will understand that many technical details are presented in the various embodiments of the present invention to facilitate a better understanding of this application. However, the technical solutions claimed in this application can be implemented even without these technical details and various changes and modifications based on the following embodiments. The division of the various embodiments below is for ease of description and should not constitute any limitation on the specific implementation of the present invention. The various embodiments can be combined with and referenced by each other without contradiction.

[0055] Reference Figure 1 The diagram illustrates a flowchart of a vehicle emergency braking method provided by an embodiment of the present invention, which is applied to a vehicle emergency braking system. The method may include:

[0056] Step 101: In response to the detection that the vehicle is performing the automatic parking function, collect audio signals, vibration signals and elastic wave signals generated by the intervention of the target user outside the vehicle.

[0057] Among them, audio signals, vibration signals, and elastic wave signals are used to identify emergency stopping events.

[0058] In this embodiment of the invention, since current automatic parking systems rely almost entirely on onboard sensors to perceive and judge the in-vehicle environment, they neglect the crucial information and intervention capabilities that external personnel may provide in emergency situations. When external personnel discover that the vehicle is in a dangerous state, they can only indirectly stop the dangerous behavior of the vehicle by calling out to the driver inside the vehicle or receiving a response from the driver. There is a possibility that the driver inside the vehicle cannot immediately receive intervention measures from personnel and take over control of the vehicle, making it difficult for the automatic parking system inside the vehicle to respond quickly and effectively, affecting the safety and reliability of automatic parking in complex and dangerous scenarios. To solve the above problems, this embodiment adds external sensors to the outside of the vehicle to collect multimodal signals from outside the vehicle, thereby accurately identifying intervention events caused by external forces on the vehicle. After determining that it is an emergency, an emergency braking decision is immediately initiated to realize emergency braking of the vehicle in complex and dangerous situations.

[0059] It should be noted that the vehicle emergency braking system in this embodiment of the invention includes external sensors and a vehicle controller. The external sensors include an external microphone, a vibration sensor, and an elastic wave sensor. When the vehicle is detected to be performing automatic parking, the external sensors operate and collect external signals in real time. The external sensors are used to collect audio signals, vibration signals, and elastic wave signals generated by external user intervention in the vehicle. The vehicle controller is used to process the audio signals, vibration signals, and elastic wave signals to identify emergency stopping events. The external target user is a pre-recorded or identified driver or passenger. To improve identification accuracy and prevent interference sounds from falsely triggering emergency braking, this embodiment can process the audio collected by the external microphone to accurately identify the audio signals generated by the external target user's intervention in the vehicle, ensuring that parking brake is not falsely triggered by instructions from unrelated personnel or passersby. An emergency stopping event is an intervention event performed by a user when the vehicle needs to stop immediately in a complex or dangerous situation. This can be an intervention such as a voice instruction to stop, tapping or knocking on the vehicle body, etc., and is not specifically limited here.

[0060] Reference Figure 8This diagram illustrates the external sensors in the vehicle emergency braking system provided in this embodiment of the invention. External microphones (1) are evenly distributed and installed at the front, rear, and sides of the vehicle. At the front, one external microphone is marked on each side of the air intake grille; at the rear, one is marked on the upper center of the rear bumper; and at the sides, one is marked below the side mirrors. These are used to receive sound signals from different directions from all directions. The vibration sensor (2) is a piezoelectric vibration sensor that converts the mechanical vibration of the vehicle body into an electrical signal, accurately detecting the vibration signal generated by people outside the vehicle hitting the vehicle body. Specifically, it can be installed in key parts of the vehicle body, such as the four doors, the hood, and the trunk. On the four doors, one vibration sensor is marked on the inner side near the door lock; on the hood, one is marked on the inner side of the front edge. Mark a vehicle vibration sensor installation point. Mark a vehicle vibration sensor installation point on the inner side of the rear edge of the trunk lid. Fully perceive the vibration of the vehicle body. Each sensor is installed on the vehicle body by a high-strength fixed bracket. The fixed bracket is isolated from the vehicle body by a shock-absorbing rubber pad to reduce the interference of vibration caused by road bumps during normal vehicle operation. At the same time, ensure that the sensor can accurately detect the vibration signal generated by people outside the vehicle hitting or knocking the vehicle body. The elastic wave sensor (3) is installed on the main structural components of the vehicle body. It is installed in the middle section of the longitudinal beam of the frame, at the bottom of the front of the vehicle and below the rear trunk. During installation, a special adhesive is used to tightly bond the sensor to the vehicle body structure to ensure good acoustic coupling effect so that the sensor can receive elastic wave signals to the maximum extent. At the same time, a shield can be set around the sensor to reduce the influence of external electromagnetic interference on the sensor. It will not be elaborated here.

[0061] Specifically, when the vehicle enters automatic parking mode, the vehicle's emergency braking system automatically activates external sensors to begin real-time acquisition of audio signals, vibration signals, and elastic wave signals from the external environment. External microphones collect sound signals from the external environment, especially emergency stop voice commands issued by the target user. Body vibration sensors detect vibrations of the vehicle body, especially vibration signals generated by people outside the vehicle hitting the body. Elastic wave sensors detect elastic waves generated by impacts on the body and convert them into electrical signals. Through multimodal signal acquisition, the vehicle's emergency braking system can comprehensively perceive emergency stop commands in the external environment, ensuring that no possible emergency is missed. Furthermore, signal acquisition begins immediately after the automatic parking function is activated, ensuring real-time response to interventions from users outside the vehicle.

[0062] Step 102: Perform feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0063] In this embodiment of the invention, the vehicle controller in the vehicle emergency braking system receives multimodal signals collected by external sensors and performs feature analysis on audio signals, vibration signals and elastic wave signals. Based on the analysis results, the confidence level of the audio signal, the probability value of the vibration signal and the similarity of the elastic wave signal are determined respectively.

[0064] Specifically, audio signal processing includes feature analysis of the audio signal to obtain the corresponding audio content and audio features. Audio features include duration, volume, and speech clarity. First, it is determined whether the audio signal is valid, that is, whether the audio signal contains an emergency stop voice command. If the audio signal is issued by the target user and the audio content contains an emergency stop voice command, then the audio signal is determined to be a valid audio signal. Based on the audio features of the valid audio signal, the confidence level of the valid audio signal is calculated. In particular, to verify whether the command is a real and valid emergency stop command, the confidence level of the valid audio signal is calculated based on the audio features of the valid audio signal. The confidence level is used to determine the credibility of the audio signal reflecting an emergency stop command. The confidence level calculation method scores the audio features of the audio signal to obtain a confidence level value ranging from 0 to 1. If the confidence level value is close to 0, it indicates that the credibility of the emergency stop command is low; if the confidence level value is close to 1, it indicates that the credibility of the emergency stop command is high.

[0065] In this embodiment, vibration signal processing includes feature analysis of the vibration signal to obtain its time-domain and frequency-domain features. The time-domain features include duration and signal variance, while the frequency-domain features include signal amplitude and signal energy. Based on the aforementioned time-domain and frequency-domain features of the vibration signal, a probability value of the vibration signal is calculated. The probability value represents the probability that vibration exists in the external environment. Specifically, it is obtained by normalizing the characteristics of the vibration signal, such as duration, signal variance, signal amplitude, and signal energy, which will not be elaborated further here.

[0066] Specifically, elastic wave signal processing includes feature analysis of the elastic wave signal to obtain elastic wave features, which include signal frequency, signal amplitude, and signal phase. The elastic wave features of the elastic wave signal are then matched with a preset elastic wave template. If the elastic wave signal matches and is similar to the elastic wave template, the elastic wave features and the features of the elastic wave template are converted into feature vectors. A similarity algorithm between the two feature vectors is then used to calculate the similarity between the elastic wave signal and the elastic wave template.

[0067] This embodiment ensures the accuracy of identification by accurately recognizing emergency stop commands in audio signals, vibration signals, and elastic wave signals. It enables the coordinated operation of the external microphone, vehicle vibration sensor, and elastic wave sensor to ensure that the signals collected by different sensors can be accurately and timely received, processed, and comprehensively judged by the system to trigger a reliable emergency braking operation.

[0068] Step 103: Calculate the credibility of the emergency stop event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0069] In this embodiment of the invention, the processing results of the elastic wave signal are fused with the processing results of the audio signal and the vibration signal to determine the temporal correlation between the audio signal, the vibration signal and the elastic wave signal. The system calculates the credibility of the emergency stopping event by using a multimodal signal fusion method based on the confidence level of the audio signal, the probability value of the vibration signal and the similarity of the elastic wave signal.

[0070] Specifically, the system acquires the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. Based on these signal quantities, a decision model based on fuzzy weighted evidence synthesis is pre-determined. The decision model includes an evaluation function for the signal and weighting coefficients for each signal quantity in the function. The evaluation function and weighting coefficients are used to perform weighted calculations on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal to obtain the weighted result of multimodal signal fusion, which is used to determine the credibility of the existence of an emergency parking event.

[0071] Step 104: Generate an emergency braking command based on the credibility of the emergency braking event and the current vehicle status information.

[0072] In this embodiment of the invention, a braking decision is made based on the weighted result of multimodal signal fusion. If the confidence level of an emergency braking event exceeds a preset threshold, an emergency braking command is generated and sent to the vehicle braking execution module. If the confidence level of an emergency braking event is lower than the preset threshold, the signals of each sensor continue to be monitored, and the braking operation is not performed for the time being. It should be noted that when generating an emergency braking command, the current vehicle status information needs to be considered, including vehicle speed, gear, steering angle, etc. When it is determined that the current vehicle status meets the braking conditions, an emergency braking command is issued to ensure the safe and smooth braking process.

[0073] Step 105: According to the emergency braking command, control the vehicle to perform braking operation and stop parking.

[0074] In this embodiment of the invention, the vehicle controller sends the generated emergency braking command to the vehicle braking execution module. Based on the emergency braking command, the vehicle is controlled to perform braking operation and stop parking. Specifically, the vehicle braking execution module receives the emergency braking command from the vehicle controller, controls the vehicle's braking system to perform braking operation based on the received emergency braking command, and simultaneously controls the vehicle's power system to stop power output, thereby achieving effective emergency braking of the vehicle during automatic parking.

[0075] The vehicle emergency braking method provided in this invention responds to the detection of an automatic parking function being executed by a vehicle. It collects audio signals, vibration signals, and elastic wave signals generated by external user intervention. Feature analysis is performed on these signals to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. The confidence level of the emergency parking event is calculated by fusing these signals. Based on the confidence level of the emergency parking event and the vehicle's current state information, an emergency braking command is generated. According to the emergency braking command, the vehicle is controlled to perform braking operations and stop parking. This invention adds an emergency braking mechanism that can be directly triggered by external users, fuses multimodal sensor signals, accurately assesses the confidence level of emergency parking events, and responds to emergency interventions from external users based on both the confidence level of the emergency parking event and the vehicle's state. This avoids false triggering of the automatic parking function and enables timely and rapid response to users' emergency intervention needs in emergency scenarios. It reduces the risk of accidents caused by the inability to stop in time during automatic parking, improves the overall emergency handling capability of the automatic parking system, and further ensures the safety and reliability of automatic parking in complex and dangerous scenarios.

[0076] Specifically, the vehicle emergency braking system includes external sensors, including an external microphone, a vibration sensor, and an elastic wave sensor. Step 101, in response to detecting that the vehicle is performing an automatic parking function, collects audio signals, vibration signals, and elastic wave signals generated by an external user intervening in the vehicle. Specifically, this may include:

[0077] In response to the detection that the vehicle is performing automatic parking, the system uses an external microphone to collect audio signals generated by the external user's intervention in the vehicle, a vibration sensor to collect vibration signals generated by the external user's intervention in the vehicle, and an elastic wave sensor to collect elastic wave signals generated by the external user's intervention in the vehicle.

[0078] It should be noted that in this embodiment, in response to the detection of the vehicle performing the automatic parking function, an external microphone is used to collect audio signals generated by the intervention of the target user outside the vehicle. The target user outside the vehicle is a driver or passenger who has been pre-recorded or identified. In order to improve the recognition accuracy and prevent interference sounds from accidentally triggering emergency braking, this embodiment can preprocess the audio collected by the external microphone, identify the voice command of the target user outside the vehicle as the audio signal to be processed, and transmit the collected audio signal to the vehicle controller for processing through a shielded twisted pair cable. The shielded twisted pair cable can effectively reduce the influence of external electromagnetic interference on the audio signal, ensuring the integrity and accuracy of the signal. In addition, a preamplifier is also provided in the transmission line to amplify the weak audio signal for better subsequent signal analysis.

[0079] In this embodiment, a vibration sensor is used to collect vibration signals generated by the intervention of the target user outside the vehicle. The vibration sensor is a piezoelectric vibration sensor. The collected electrical signal is first preprocessed by the signal conditioning circuit in the vibration sensor. The signal conditioning circuit mainly includes a filtering circuit, an amplification circuit, and an A / D conversion circuit. The filtering circuit is used to remove high-frequency noise and low-frequency interference signals from the vibration signal, retaining only the effective frequency components related to the vibration generated by the intervention such as patting and knocking outside the vehicle. The amplification circuit amplifies the weak signal after filtering so that it can meet the input requirements of the subsequent A / D conversion circuit. The A / D conversion circuit converts the analog electrical signal into a digital signal so that the signal can be better analyzed later.

[0080] In this embodiment, an elastic wave sensor is used to collect elastic wave signals generated by external user intervention on the vehicle. The elastic wave sensor converts the elastic waves generated by the vehicle body due to the impact, slapping, or other interventions into electrical signals. The collected electrical signals are first amplified, filtered, and converted by an A / D converter through a dedicated signal processing circuit. The amplification circuit amplifies the weak elastic wave signals, the filtering circuit removes noise and interference frequency components from the signals, and the A / D conversion circuit converts the analog electrical signals into digital signals for better subsequent signal analysis.

[0081] Furthermore, refer to Figure 2 , showed Figure 1 The process of step 102 in a provided vehicle emergency braking method Figure 1 This method is basically the same as the vehicle emergency braking method provided in the first embodiment of the present invention, and step 102 may include:

[0082] Step 201: Perform feature analysis on the audio signal to obtain the audio content and audio features corresponding to the audio signal, and determine whether the audio signal is valid.

[0083] Step 202: If the audio signal is issued by the target user and the audio content contains a preset emergency stop command, then the audio signal is determined to be a valid audio signal.

[0084] Step 203: Calculate the confidence level of the valid audio signal based on the audio characteristics of the valid audio signal.

[0085] In this embodiment of the invention, the audio signal collected by the external microphone is subjected to feature analysis. First, the audio signal is divided into frames of fixed time length to ensure the precision of signal processing. Features of each frame of the audio signal are extracted to obtain the corresponding audio content and audio features. The extracted audio features can be input into a speech recognition model to accurately identify the audio content corresponding to the audio signal. If the audio signal contains clear speech content and the speech content is related to a preset emergency stop command, the audio signal is considered valid. If the audio signal is noise or irrelevant speech content, the audio signal is considered invalid. The preset emergency stop command includes speech commands with keywords such as "stop" and "stop". This embodiment can be preset according to actual braking needs, and no specific limitation is made here. It should be noted that when collecting audio signals and other data, the system mainly focuses on audio that can reflect the intervention of the target user outside the vehicle, rather than indiscriminately collecting all surrounding sound information. The purpose of collection is to determine whether there is an emergency stop requirement. For sounds unrelated to emergency braking, the system will not process or store them excessively, thereby protecting privacy to a certain extent.

[0086] To further ensure the reliability of the audio signal reflecting the emergency stop command, this embodiment can use voiceprint recognition technology to determine whether the audio signal was issued by the target user. Specifically, a voiceprint recognition model is used to extract voiceprint features (such as fundamental frequency, formants, etc.) from the audio signal. These voiceprint features are then matched with the voiceprint features of the pre-registered target user. If the voiceprint matching degree meets the requirements, the audio signal is confirmed to have been issued by the target user, ensuring that only the target user's command is received by the system, preventing false triggering. Furthermore, if the audio content matches the preset emergency stop command, the audio signal is considered valid. It should be noted that a valid audio signal includes two conditions: parking audio and the target user's voice. The system performs feature analysis on the audio signal to determine its confidence level. If a passerby shouts "Stop!" and the frequency, intensity, timbre, or other characteristics of the audio do not match or have a low match with the preset emergency braking command, the audio signal is considered invalid and will not be processed. For example, the preset audio signal for emergency braking is a high-decibel, urgent shout within a specific frequency range, while a passerby's normal shout does not have these audio signal characteristics. Therefore, the matching degree of the audio signal will not reach the trigger condition, ensuring that the parking brake will not be mistakenly triggered due to commands from irrelevant personnel or passersby.

[0087] After identifying a valid audio signal, a confidence score (score1) is calculated based on the audio characteristics of the valid audio signal. These audio characteristics include duration, volume, and clarity. The system determines whether the duration of the audio signal is within a reasonable range, whether the volume has reached the minimum threshold, and whether the clarity of the command is sufficiently high. Based on these characteristics, the confidence score (a value between 0 and 1) of the audio signal is calculated. If the audio signal has a long duration, moderate volume, and high clarity, the confidence score approaches 1. If the audio signal has a short duration, low volume, or low clarity, the confidence score approaches 0. The calculated confidence score of the audio signal is then transmitted to the vehicle controller for subsequent multimodal signal fusion and braking decisions.

[0088] This invention, through audio recognition and semantic analysis, confirms whether an audio signal is an emergency stop command issued by a target user. Based on features such as voice duration, volume, and clarity, it calculates the confidence level of the audio signal, quantifies and evaluates the credibility of the audio signal, and ensures the accuracy of the evaluation results. This achieves high-precision recognition and quantitative evaluation of emergency stop commands issued by target users outside the vehicle, accurately identifying emergency stop commands.

[0089] Furthermore, refer to Figure 3 , showed Figure 1 The process of step 102 in a provided vehicle emergency braking method Figure 2 This method is basically the same as the vehicle emergency braking method provided in the first embodiment of the present invention, and step 102 may include:

[0090] Step 301: Perform feature analysis on the vibration signal to obtain the time-domain and frequency-domain features of the vibration signal.

[0091] The time-domain features include duration and signal variance, and the frequency-domain features include signal amplitude and signal energy.

[0092] Step 302: Calculate the probability value of the vibration signal based on the time domain characteristics and frequency domain characteristics.

[0093] In this embodiment of the invention, the vibration signal collected by the vibration sensor is subjected to feature analysis to extract the time-domain features of the vibration signal. These time-domain features include duration and signal variance. Duration is the length of time the vibration signal lasts from start to finish, and signal variance is the variance of the vibration signal in the time domain, reflecting the degree of fluctuation of the vibration signal. A Fast Fourier Transform is performed on the vibration signal to convert it into a frequency-domain signal, and frequency-domain features are extracted. These frequency-domain features include signal amplitude and signal energy. Signal amplitude is the amplitude of each frequency component in the vibration signal, reflecting the intensity of the vibration signal at different frequencies. Signal energy is the energy of each frequency component in the signal, obtained by calculating the sum of the squares of the amplitudes of each frequency component in the spectrum. Through the extraction of time-domain and frequency-domain features, the system can comprehensively analyze the characteristics of the vibration signal, ensuring the accuracy of identification.

[0094] Specifically, based on actual needs, weights are assigned to each time-domain and frequency-domain feature. The weight system for each feature satisfies the condition that the sum of the weights is 1. After normalizing the time-domain and frequency-domain features, probability values ​​are calculated. Specifically, based on the time-domain and frequency-domain features, the probability value of the vibration signal is calculated. That is, the higher the calculated probability value of the vibration signal, the higher the probability that there is vibration in the external environment. This is achieved through the following calculation formula:

[0095]

[0096] Where P is the probability value of the vibration signal, representing the probability that vibration exists in the external environment; α1, α2, α3, and α4 are weighting coefficients; and V... max It is the maximum value of the signal variance, A. th T is the threshold value for the signal amplitude. th T is the threshold of signal energy. d Here, E is the threshold for duration, T is the signal energy of the vibration signal, A is the signal amplitude of the vibration signal, and V is the signal variance of the vibration signal.

[0097] The embodiments of the present invention combine time-domain and frequency-domain characteristics for comprehensive analysis, quantitatively assessing the likelihood that the vibration signal is a vehicle body vibration event, and can comprehensively evaluate the characteristics of the vibration signal, thereby improving the accuracy of the judgment.

[0098] Furthermore, refer to Figure 4 , showed Figure 1 The process of step 102 in a provided vehicle emergency braking method Figure 3 This method is basically the same as the vehicle emergency braking method provided in the first embodiment of the present invention, and step 102 may include:

[0099] Step 401: Perform feature analysis on the elastic wave signal to obtain the elastic wave characteristics of the elastic wave signal.

[0100] Among them, the elastic wave characteristics include at least one of the elastic wave frequency, elastic wave amplitude, and elastic wave phase;

[0101] Step 402: Match the elastic wave characteristics of the elastic wave signal with the preset elastic wave template to obtain the matching result.

[0102] Step 403: If the matching result is that the elastic wave signal is similar to the elastic wave template, calculate the similarity between the elastic wave signal and the elastic wave template.

[0103] In this embodiment of the invention, a fast Fourier transform is performed on the elastic wave signal to convert it into a frequency domain signal. The elastic wave features in the frequency domain are extracted. The elastic wave features include at least one of the following: elastic wave frequency, elastic wave amplitude, and elastic wave phase. The elastic wave frequency is the main frequency component of the elastic wave signal, reflecting the frequency characteristics of the impact event. The elastic wave amplitude is the amplitude of each frequency component in the elastic wave signal, reflecting the intensity of the elastic wave signal at different frequencies. The elastic wave phase is the phase information of each frequency component in the elastic wave signal, reflecting the waveform characteristics of the elastic wave signal.

[0104] It should be noted that if the matching result is that the elastic wave signal is similar to the elastic wave template, the similarity score2 between the elastic wave signal and the elastic wave template is calculated. The system pre-stores elastic wave templates corresponding to various emergency parking events. Each template contains standard values ​​of the frequency domain characteristics (frequency, amplitude, phase) of the elastic wave. The elastic wave templates are generated through experimental data or simulation data and cover the elastic wave characteristics of different impact positions, forces and materials. The acquired elastic wave signal's elastic wave characteristics are matched with a preset elastic wave template. The similarity between the main frequency of the elastic wave signal and the template frequency, the similarity between the amplitude distribution of the elastic wave signal and the template amplitude distribution, and the consistency between the phase information of the elastic wave signal and the template phase information are compared. Based on the matching results, it is determined whether the elastic wave signal is similar to a certain template. If the matching degree exceeds a preset threshold, the elastic wave signal is considered similar to the template. If the matching result shows that the elastic wave signal and the elastic wave template are similar, the similarity between the two is calculated. The similarity calculation method includes Euclidean distance or cosine similarity. The Euclidean distance between the elastic wave characteristics of the elastic wave signal and the frequency domain characteristics of the elastic wave in the template is calculated. The smaller the distance, the higher the similarity. Alternatively, the cosine similarity between the elastic wave characteristics of the elastic wave signal and the frequency domain characteristics of the elastic wave in the template is calculated. The closer the cosine similarity value is to 1, the higher the similarity.

[0105] This invention provides a quantitative assessment of the matching degree between elastic wave signals and templates. By extracting elastic wave features, it comprehensively analyzes the characteristics of elastic wave signals to ensure the accuracy of identification. Through elastic wave feature matching, it can accurately identify whether elastic wave signals are related to emergency braking events.

[0106] Furthermore, refer to Figure 5 , showed Figure 1 A flowchart of step 103 in a vehicle emergency braking method is provided. This method is basically the same as the vehicle emergency braking method provided in the first embodiment of the present invention. Step 103 may include:

[0107] Step 501: Obtain the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal, and determine the evaluation function and weighting coefficients of the signal.

[0108] Step 502: The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are weighted using an evaluation function and weighting coefficients to obtain the weighted result of multimodal signal fusion.

[0109] Step 503: Determine the weighted result as the credibility of the emergency parking event.

[0110] In this embodiment of the invention, the evaluation function is used to perform weighted calculations on multimodal signals. Common evaluation functions include linear weighting and / or nonlinear weighting functions. The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are obtained. The evaluation function of the signal is determined. According to actual needs and system design, the weighting coefficients of each signal are determined. Based on the evaluation function and weighting coefficients, the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are weighted and calculated.

[0111] Specifically, the confidence score (score1) of the audio signal, the probability value (P) of the vibration signal, and the similarity score (score2) of the elastic wave signal are used to calculate the credibility of the emergency stopping event using the evaluation function in the decision model based on fuzzy weighted evidence synthesis. The evaluation function is as follows:

[0112] S=ω1·f1(score1)+ω2·f2(P)+ω3·f3(score2)

[0113]

[0114] Where S is the confidence level of the emergency stop event, w1, w2, and w3 are weighting coefficients, score1 is the confidence level of the audio signal, P is the probability value of the vibration signal, score2 is the similarity of the elastic wave signal, f1(x) is the confidence level correction of the audio signal, f2(x) is the mapping function of the probability value of the vibration signal, and f3(x) is the similarity correction of the elastic wave signal.

[0115] This invention, through multimodal signal fusion, can comprehensively consider the characteristics of audio, vibration, and elastic wave signals, and accurately determine whether an emergency braking event exists, thereby improving the accuracy and reliability of decision-making.

[0116] Specifically, step 104 generates an emergency braking command based on the credibility of the emergency braking event and the vehicle's current status information, which may include the following steps:

[0117] If the credibility of an emergency braking event is greater than or equal to the first preset threshold and less than the second preset threshold, a braking warning command is generated.

[0118] If the credibility of the emergency braking event is greater than or equal to the second preset threshold, and the current vehicle status information meets the preset braking conditions, then an emergency braking command is generated.

[0119] In this embodiment of the invention, if the credibility of an emergency braking event is greater than or equal to a first preset threshold and less than a second preset threshold, a braking warning command is generated and a braking warning is issued, such as a voice reminder or a speed reduction warning. If the credibility of an emergency braking event is greater than or equal to the second preset threshold and the current vehicle status information meets the preset braking conditions, an emergency braking command is generated. The first preset threshold is less than the second preset threshold, and the specific setting is determined according to actual needs and is not limited here.

[0120] Reference Figure 6 The diagram illustrates a structural schematic of a vehicle emergency braking device according to an embodiment of the present invention, which is applied to a vehicle emergency braking system. The device includes:

[0121] The signal acquisition module 601 is used to acquire audio signals, vibration signals, and elastic wave signals generated by the intervention of a target user outside the vehicle when the vehicle is detected to be performing an automatic parking function; wherein, the audio signals, vibration signals, and elastic wave signals are used to identify emergency parking events.

[0122] The signal processing module 602 is used to perform feature analysis on the audio signal, vibration signal and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal and the similarity of the elastic wave signal.

[0123] The event evaluation module 603 is used to calculate the credibility of the emergency stop event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal.

[0124] The command generation module 604 is used to generate an emergency braking command based on the credibility of the emergency braking event and the current vehicle status information.

[0125] The braking control module 605 is used to control the vehicle to perform braking operations and stop parking according to the emergency braking command.

[0126] Furthermore, the vehicle emergency braking system includes external sensors, including an external microphone, a vibration sensor, and an elastic wave sensor. The signal acquisition module 601 includes:

[0127] The acquisition submodule is used to acquire audio signals generated by the external user's intervention in the vehicle when the vehicle is detected to be performing automatic parking function, acquire vibration signals generated by the external user's intervention in the vehicle, and acquire elastic wave signals generated by the external user's intervention in the vehicle, in response to the detection of the vehicle performing automatic parking function.

[0128] Furthermore, the signal processing module 602 includes:

[0129] The first analysis submodule is used to perform feature analysis on the audio signal, obtain the audio content and audio features corresponding to the audio signal, and determine whether the audio signal is valid.

[0130] The first determining submodule is used to determine that the audio signal is a valid audio signal if the audio signal is emitted by the target user and the audio content contains a preset emergency stop command.

[0131] The first calculation submodule is used to calculate the confidence level of the valid audio signal based on the audio characteristics of the valid audio signal.

[0132] Furthermore, the signal processing module 602 includes:

[0133] The second analysis submodule is used to perform feature analysis on the vibration signal to obtain the time-domain and frequency-domain features of the vibration signal; wherein, the time-domain features include duration and signal variance, and the frequency-domain features include signal amplitude and signal energy;

[0134] The second calculation submodule is used to calculate the probability value of the vibration signal based on the time domain characteristics and the frequency domain characteristics.

[0135] Furthermore, the signal processing module 602 includes:

[0136] The third analysis submodule is used to perform feature analysis on the elastic wave signal to obtain the elastic wave features of the elastic wave signal; wherein, the elastic wave features include at least one of elastic wave frequency, elastic wave amplitude and elastic wave phase;

[0137] The matching submodule is used to match the elastic wave characteristics of the elastic wave signal with a preset elastic wave template to obtain a matching result;

[0138] The third calculation submodule is used to calculate the similarity between the elastic wave signal and the elastic wave template if the matching result is that the elastic wave signal is similar to the elastic wave template.

[0139] Furthermore, the event evaluation module 603 includes:

[0140] The acquisition submodule is used to acquire the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal, and to determine the evaluation function and weighting coefficients of the signal;

[0141] The fourth calculation submodule is used to perform weighted calculations on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal using the evaluation function and the weighting coefficients, so as to obtain the weighted result of multimodal signal fusion.

[0142] The second determining submodule is used to determine the weighted result as the credibility of the emergency parking event.

[0143] Furthermore, the generation instruction module 604 includes:

[0144] The first generation submodule is used to generate a braking warning command if the credibility of the emergency braking event is greater than or equal to a first preset threshold and less than a second preset threshold.

[0145] The second generation submodule is used to generate an emergency braking command if the credibility of the emergency braking event is greater than or equal to the second preset threshold and the current vehicle status information meets the preset braking conditions.

[0146] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0147] The vehicle emergency braking device provided in this invention responds to the detection of an automatic parking function being executed by the vehicle. It collects audio signals, vibration signals, and elastic wave signals generated by external user intervention. Feature analysis is performed on these signals to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. The confidence level of the emergency parking event is then calculated. Based on the confidence level of the emergency parking event and the vehicle's current state information, an emergency braking command is generated. Following the emergency braking command, the vehicle is controlled to perform braking and stop parking. This invention adds an emergency braking mechanism that can be directly triggered by external users, integrates multimodal sensor signals, accurately assesses the confidence level of emergency parking events, and responds to emergency interventions from external users based on both the confidence level of the emergency parking event and the vehicle's state. This avoids false triggering of the automatic parking function and enables timely and rapid response to users' emergency intervention needs in emergency scenarios. It reduces the risk of accidents caused by the inability to stop in time during automatic parking, improves the overall emergency handling capability of the automatic parking system, and further ensures the safety and reliability of automatic parking in complex and dangerous scenarios.

[0148] Reference Figure 7 Based on the same inventive concept, a third aspect of the present application provides a vehicle emergency braking system for performing the above-described vehicle emergency braking method. The system includes external sensors and a vehicle controller. The external sensors include an external microphone, a vibration sensor, and an elastic wave sensor.

[0149] The external microphone collects audio signals generated by the external target user's intervention in the vehicle; the vibration sensor collects vibration signals generated by the external target user's intervention in the vehicle; and the elastic wave sensor collects elastic wave signals generated by the external target user's intervention in the vehicle.

[0150] The vehicle controller is configured to acquire audio signals, vibration signals, and elastic wave signals collected by the external sensors, perform feature analysis on the audio signals, vibration signals, and elastic wave signals to determine the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, calculate the credibility of the emergency stopping event based on the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, generate an emergency braking command based on the credibility of the emergency stopping event and the current vehicle status information, and control the vehicle to perform braking operation and stop parking based on the emergency braking command.

[0151] As the system implementation is basically similar to the method implementation, it is described in a relatively simple way. For relevant details, please refer to the description of the method implementation.

[0152] Based on the above-described vehicle emergency braking method, this embodiment of the invention also provides a vehicle, the vehicle including the vehicle emergency braking system described in the above steps, for performing the vehicle emergency braking method described in the above steps.

[0153] It should be noted that the embodiments of the present invention are described with reference to the methods and apparatus according to embodiments of the present invention. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions of the vehicle system management system. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0155] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0156] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0157] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0158] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A vehicle emergency braking method, characterized in that, The method, applied to a vehicle emergency braking system, includes: In response to the detection that the vehicle is performing an automatic parking function, audio signals, vibration signals, and elastic wave signals generated by the intervention of a target user outside the vehicle are collected; wherein, the audio signals, vibration signals, and elastic wave signals are used to identify emergency parking events; Feature analysis is performed on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal; the confidence level of the audio signal is calculated based on the audio features when the audio signal is emitted by the target user outside the vehicle and the audio content contains a preset emergency stop command. The credibility of the emergency stop event is calculated based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. An emergency braking command is generated based on the credibility of the emergency braking event and the vehicle's current status information. According to the emergency braking command, control the vehicle to perform braking operation and stop parking.

2. The method according to claim 1, wherein the vehicle emergency braking system includes external sensors, the external sensors including an external microphone, a vibration sensor, and an elastic wave sensor, characterized in that, The response to detecting that the vehicle is performing automatic parking function collects audio signals, vibration signals, and elastic wave signals generated by external user intervention in the vehicle, including: In response to detecting that the vehicle is performing an automatic parking function, the system uses the external microphone to collect audio signals generated by the external target user's intervention in the vehicle, the vibration sensor to collect vibration signals generated by the external target user's intervention in the vehicle, and the elastic wave sensor to collect elastic wave signals generated by the external target user's intervention in the vehicle.

3. The method according to claim 1, characterized in that, The step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes: The audio signal is subjected to feature analysis to obtain the audio content and audio features corresponding to the audio signal, and it is determined whether the audio signal is valid. If the audio signal is emitted by the target user outside the vehicle and the audio content contains a preset emergency stop command, then the audio signal is determined to be a valid audio signal. The confidence level of a valid audio signal is calculated based on its audio characteristics.

4. The method according to claim 1, characterized in that, The step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes: The vibration signal is subjected to feature analysis to obtain its time-domain and frequency-domain features; wherein, the time-domain features include duration and signal variance, and the frequency-domain features include signal amplitude and signal energy; The probability value of the vibration signal is calculated based on the time-domain characteristics and the frequency-domain characteristics.

5. The method according to claim 1, characterized in that, The step of performing feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes: The elastic wave signal is subjected to feature analysis to obtain the elastic wave characteristics of the elastic wave signal; wherein, the elastic wave characteristics include at least one of elastic wave frequency, elastic wave amplitude and elastic wave phase; The elastic wave characteristics of the elastic wave signal are matched with a preset elastic wave template to obtain a matching result; If the matching result is that the elastic wave signal is similar to the elastic wave template, the similarity between the elastic wave signal and the elastic wave template is calculated.

6. The method according to claim 1, characterized in that, The step of calculating the credibility of the emergency stopping event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal includes: The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are obtained, and the evaluation function and weighting coefficients of the signal are determined. The confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal are weighted using the evaluation function and the weighting coefficients to obtain the weighted result of multimodal signal fusion. The weighted result is used to determine the credibility of the emergency parking event.

7. The method according to claim 1, characterized in that, The step of generating an emergency braking command based on the credibility of the emergency braking event and the vehicle's current state information includes: If the credibility of the emergency braking event is greater than or equal to the first preset threshold and less than the second preset threshold, a braking warning command is generated. If the credibility of the emergency braking event is greater than or equal to the second preset threshold, and the current vehicle status information meets the preset braking conditions, then an emergency braking command is generated.

8. A vehicle emergency braking device, characterized in that, The device, used in a vehicle emergency braking system, includes: The signal acquisition module is used to acquire audio signals, vibration signals, and elastic wave signals generated by external user intervention in response to the detection of the vehicle performing automatic parking function; wherein, the audio signals, vibration signals, and elastic wave signals are used to identify emergency parking events. The signal processing module is used to perform feature analysis on the audio signal, vibration signal, and elastic wave signal to determine the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. The confidence level of the audio signal is calculated based on the audio features when the audio signal is emitted by the target user outside the vehicle and the audio content contains a preset emergency stop command. The event evaluation module is used to calculate the credibility of the emergency stop event based on the confidence level of the audio signal, the probability value of the vibration signal, and the similarity of the elastic wave signal. The command generation module is used to generate an emergency braking command based on the credibility of the emergency braking event and the current vehicle status information. The braking control module is used to control the vehicle to perform braking operations and stop parking according to the emergency braking command.

9. A vehicle emergency braking system, characterized in that, For performing the vehicle emergency braking method according to any one of claims 1 to 7, the system includes external sensors and a vehicle controller, the external sensors including an external microphone, a vibration sensor and an elastic wave sensor; The external microphone collects audio signals generated by the external target user's intervention in the vehicle; the vibration sensor collects vibration signals generated by the external target user's intervention in the vehicle; and the elastic wave sensor collects elastic wave signals generated by the external target user's intervention in the vehicle. The vehicle controller is configured to acquire audio signals, vibration signals, and elastic wave signals collected by the external sensors, perform feature analysis on the audio signals, vibration signals, and elastic wave signals to determine the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, calculate the credibility of the emergency stopping event based on the confidence level of the audio signals, the probability value of the vibration signals, and the similarity of the elastic wave signals, generate an emergency braking command based on the credibility of the emergency stopping event and the current vehicle status information, and control the vehicle to perform braking operation and stop parking based on the emergency braking command.

10. A vehicle, characterized in that, The vehicle includes the vehicle emergency braking system as described in claim 9.

Images