Vehicle control method and related device
By combining UWB radar and feature processing models with image analysis, the system accurately determines the water ingress of vehicles and executes rescue operations, solving the problem of accurate rescue when vehicles fall into water and improving the reliability and accuracy of rescue efforts.
Patent Information
- Application Number
- CN202411940400.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-26
- Publication Date
- 2025-10-28
- Estimated Expiration
- 2044-12-26
AI Technical Summary
When a vehicle falls into water, current technology struggles to accurately determine if anyone is inside and to carry out an effective rescue. This is especially true in areas with high humidity, where humidity sensors are prone to false detections, reducing the reliability and accuracy of rescue efforts.
Using channel impulse response data from UWB radar, the depth of water entering the vehicle is detected by Doppler effect spectrum. Combined with the vehicle location and the location of water ingress, the water ingress parameters of the vehicle are determined by feature processing model and image analysis, and preset rescue operations such as opening the windows and outputting prompt information are executed.
It improves the accuracy of vehicle submersion detection and the reliability of rescue, avoids the problem of false detection by humidity sensors in areas with high humidity, and ensures the safety of people inside the vehicle.
Smart Images

Figure CN119459581B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle control, and more specifically, to a vehicle control method and related apparatus. Background Technology
[0002] As the number of vehicles on the road increases, people are paying more and more attention to vehicle safety.
[0003] In some cases, vehicles often fall into water. How to achieve personnel rescue based on vehicle control is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0004] In view of this, this application provides a vehicle control method and related device to solve the problem of the urgent need to achieve personnel rescue based on vehicle control when a vehicle falls into water.
[0005] To solve the above-mentioned technical problems, this application adopts the following technical solution:
[0006] A vehicle control method, comprising:
[0007] Acquire channel impulse response data inside the vehicle;
[0008] Based on the channel impulse response data, the parameter values of the vehicle water ingress parameters are determined;
[0009] If there are people inside the vehicle, and the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, a preset rescue operation will be performed; the preset rescue operation includes at least opening the vehicle window.
[0010] Optionally, the vehicle water ingress parameters include water depth; determining the parameter values of the vehicle water ingress parameters based on the channel impulse response data includes:
[0011] Extract the feature data from the channel impulse response data;
[0012] The feature processing model is invoked to process the feature data to obtain the inflow depth; the feature processing model is trained based on training samples; the training samples include feature data of channel impulse response samples and depth labels corresponding to the channel impulse response samples.
[0013] Optionally, the vehicle water ingress parameters further include the water ingress location and the vehicle position; the vehicle control method further includes:
[0014] Images of the vehicle's interior are acquired and analyzed to determine the location of water ingress.
[0015] The vehicle's location information is detected using a positioning device.
[0016] Optionally, if the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, a preset rescue operation is performed, including:
[0017] When the water ingress depth is not less than the depth threshold, the vehicle is located in a designated water area, and the water ingress location is the foot pedal, open the car window and output a rescue prompt message.
[0018] When the water depth is less than the depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, output a water ingress warning message, respond to the confirmation message of the water ingress warning message, open the car window, and output a rescue warning message.
[0019] If the vehicle is located in a designated water area and the water ingress point is a window, open the window and output a rescue alert message.
[0020] Optionally, if the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, a preset rescue operation is performed, including:
[0021] Obtain the humidity value at a preset location on the vehicle;
[0022] If the humidity value is greater than the humidity threshold, and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions, a preset rescue operation is executed.
[0023] Optionally, it also includes:
[0024] Responding to the touch command of the emergency assistance button, it opens the windows and outputs emergency assistance prompts.
[0025] Optionally, it also includes:
[0026] Receive user voice messages;
[0027] If the user's voice includes key rescue information, then the car window will be opened and a rescue prompt message will be output.
[0028] A vehicle control device, comprising:
[0029] The data acquisition module is used to acquire channel impulse response data inside the vehicle;
[0030] The parameter determination module is used to determine the parameter values of the vehicle water ingress parameters based on the channel impulse response data.
[0031] The rescue control module is used to execute preset rescue operations if there are people inside the vehicle and the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue; the preset rescue operations include at least opening the vehicle windows.
[0032] An electronic device includes at least one processor and a memory connected to the processor, wherein:
[0033] The memory is used to store computer programs;
[0034] The processor is used to execute the computer program so that the electronic device can implement the vehicle control method described above.
[0035] A computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the vehicle control method described above.
[0036] This application provides a vehicle control method and related apparatus. In this application, based on the channel impulse response data inside the vehicle, the parameter values of the vehicle's water ingress parameters are determined. If the parameter values of the vehicle's water ingress parameters meet the conditions for vehicle water ingress rescue, it indicates that the vehicle may be flooded, and preset rescue operations such as opening the windows are executed to help the occupants escape and ensure their safety. Furthermore, in this invention, the channel impulse response data used to determine the water ingress parameters exhibits different spectral data when the object is moving. Therefore, this data can be used to accurately determine the parameter values of the water ingress parameters. Compared to using humidity sensors for water ingress detection, this method avoids false detection problems in areas with high humidity and improves the accuracy of water ingress detection. Attached Figure Description
[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0038] Figure 1 A flowchart of a vehicle control method provided in an embodiment of the present invention;
[0039] Figure 2 A flowchart illustrating a method for determining water inlet depth provided in an embodiment of the present invention;
[0040] Figure 3 This is a device interaction diagram of a vehicle control method provided in an embodiment of the present invention;
[0041] Figure 4 This is a schematic diagram of the structure of a vehicle control device provided in an embodiment of the present invention;
[0042] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0044] As the number of vehicles on the road increases, people are paying more and more attention to vehicle safety.
[0045] In some cases, vehicles often fall into water. How to achieve personnel rescue based on vehicle control is a technical problem that urgently needs to be solved by those skilled in the art.
[0046] In related technologies, humidity sensors can be used to detect the humidity inside or outside a vehicle. When the humidity value is high, it indicates that the vehicle may be at risk of falling into water, and a warning message is output. However, this method may result in false detections in areas with high humidity, such as southern regions, thus reducing the reliability and accuracy of rescue efforts.
[0047] Therefore, research revealed that vehicles are equipped with UWB (Ultra Wide Band) radar. Currently, UWB radar primarily uses radio communication to achieve high-precision positioning. UWB radar also possesses CIR (Channel Impulse Response) functionality. The CIR of UWB radar can detect surrounding objects and their movement. When an object is present near the UWB radar, a pulse peak will appear at the corresponding CIR location. Furthermore, when the surrounding object moves, the corresponding CIR value will change due to the Doppler effect. Therefore, the channel impulse response data output by the CIR, such as a Doppler effect spectrum, can be used to detect water ingress into the vehicle, thereby determining the depth of water ingress. In one implementation, to achieve water ingress depth detection, channel impulse response samples at different water ingress depths are pre-constructed. These samples are used to train a model, which is then used to identify the water ingress depth corresponding to the channel impulse response data. Because the model is trained on a large number of samples, the recognition accuracy is high, avoiding the problem of false detection by humidity sensors.
[0048] Based on the above, this invention provides a vehicle control method. The executing entity can be an electronic device, such as a cloud-based system or a vehicle controller (e.g., an ECU (Electronic Control Unit)). In practical scenarios, to reduce the computing power of the in-vehicle ECU and avoid overloading it, the software program for this vehicle control method can be installed in the cloud, allowing the cloud to perform rescue control operations when the vehicle falls into water. Therefore, subsequent embodiments will use the cloud-based system as an example.
[0049] Reference Figure 1 Vehicle control methods may include:
[0050] S11. Acquire channel impulse response data inside the vehicle.
[0051] In real-world scenarios, UWB radar can be installed at the key fob entrance / exit. The CIR function of this UWB radar can scan the interior of the vehicle. If the vehicle controller detects a change in CIR through the UWB radar, it can send the CIR detection data, such as channel impulse response data (specifically, a Doppler effect spectrum), to the cloud via a communication device. After receiving the Doppler effect spectrum, the cloud will perform subsequent analysis.
[0052] S12. Based on the channel impulse response data, determine the parameter values of the vehicle water ingress parameters.
[0053] In real-world scenarios, if a vehicle falls into water, water will flow into the vehicle through the windows or footwell area, causing water to enter the vehicle's interior. Therefore, detecting the amount of water inside the vehicle can help determine if it has fallen into water.
[0054] The extent of water ingress into a vehicle can be assessed using the values of the vehicle's water ingress parameters. These parameters, such as water depth, location of the ingress, and vehicle position, can be selected based on the specific circumstances of the water ingress.
[0055] Among them, the water depth and water ingress location are parameters that can directly reflect the water ingress situation inside the vehicle. The vehicle location is a parameter that helps to judge whether the vehicle has water ingress. If the vehicle is currently located near a body of water, it means that the probability of the vehicle falling into the water is relatively high when water ingress is detected inside the vehicle. If the vehicle is not currently located near a body of water, but in a dry area such as a desert, the probability of the vehicle falling into the water is relatively low. If water ingress is detected inside the vehicle, there may be a problem of false detection.
[0056] S13. If there are people inside the vehicle, and the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, execute the preset rescue operation.
[0057] Whether there are people inside the vehicle can be determined through CIR function for liveness detection, or by acquiring images and performing target recognition.
[0058] The preset rescue operation includes at least opening the vehicle windows. Normally, after a vehicle falls into water, the water pressure is too high, preventing the driver and passengers from opening the windows. Therefore, this embodiment of the invention can actively control the opening of the windows, allowing trapped personnel to escape through the opened windows.
[0059] In addition, the preset rescue operations may also include outputting rescue prompts, such as outputting prompts to the dealer system of the mobile phone used by the owner of the submerged vehicle, so that the system can call the owner to provide rescue care and introduce rescue measures to help the owner get out of danger.
[0060] Regarding the vehicle flood rescue conditions in this embodiment, they can be configured according to the actual scenario. For example, the vehicle flood rescue conditions may include at least one of the following limiting conditions: vehicle location, water depth, and water location. If there are people inside the vehicle, then when the corresponding limiting conditions are met, it indicates that the vehicle has indeed fallen into the water. At this time, preset rescue operations can be performed to help the people inside the vehicle escape danger.
[0061] In this embodiment, based on the channel impulse response data inside the vehicle, the parameter values of the vehicle water ingress parameters are determined. If the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, it indicates that the vehicle may be flooded, and preset rescue operations such as opening the windows are performed to help the occupants escape and ensure their safety. Furthermore, in this invention, the channel impulse response data used to determine the water ingress parameters exhibits different spectral data when the object is moving. Therefore, this data can be used to accurately determine the parameter values of the water ingress parameters. Compared to using a humidity sensor for water ingress detection, this method avoids false detections in areas with high humidity and improves the accuracy of water ingress detection.
[0062] In another implementation of the present invention, if the vehicle water ingress parameters include water depth, then determining the parameter values of the vehicle water ingress parameters based on the channel impulse response data may include:
[0063] S21. Extract the feature data of the channel impulse response data.
[0064] In this application, if water is present inside the vehicle, a corresponding Doppler frequency shift will appear in the channel impulse response data of the CIR, such as the Doppler effect spectrum. That is, the Doppler effect spectrum differs when there is water inside the vehicle and when there is no water. Therefore, the presence of water in the vehicle and the depth of the water can be determined using the Doppler effect spectrum.
[0065] Therefore, feature extraction is performed on the Doppler effect spectrum to obtain corresponding feature data, which is then used for ingress depth detection. Feature extraction can be performed using a feature extraction model or by using the pixel values of the Doppler effect spectrum as feature data; the specific method used depends on the actual configuration.
[0066] S22. The feature processing model is invoked to process the feature data to obtain the inflow depth.
[0067] In this embodiment, a feature processing model that can identify the depth of water ingress is pre-trained. The feature processing model can be a neural network model, a machine learning model, etc.
[0068] In real-world scenarios, the feature processing model needs to be trained first. After training, it can be used to identify the depth of water ingress.
[0069] During model training, the feature processing model is trained based on training samples, which include feature data of channel impulse response samples and depth labels corresponding to the channel impulse response samples.
[0070] Specifically, since the Doppler effect spectrum differs at different depths of water, in this embodiment of the invention, a water ingress experiment can be conducted on a vehicle. Starting with a water depth of 1 cm, the water depth increases by 1 cm increments until the vehicle is completely submerged; that is, the range of water depth is from 1 cm to full. At each water depth, the water's wave pattern is irregular. Therefore, to collect spectra of water at the same depth but with different patterns, a large number of Doppler effect spectra can be collected at a certain water depth as the water continuously changes, such as collecting 2 million Doppler effect spectra. Each Doppler effect spectrum serves as a channel impulse response sample. After collecting channel impulse response samples at a certain water depth, the water depth is increased by 1 cm, and the sampling continues at the next water depth until channel impulse response samples at all water depths are collected.
[0071] For the collected channel impulse response samples, the feature extraction method described above can be used to obtain the feature data of the channel impulse response samples. Furthermore, for each channel impulse response sample, its corresponding inflow depth can be used as its depth label.
[0072] Subsequently, the feature data including the channel impulse response samples and the training samples with the corresponding depth labels are input into the feature processing model to train the model until the number of training iterations reaches a set threshold or the loss function meets the stop training condition, thus obtaining the feature processing model.
[0073] In actual use, the feature processing model is input into the feature processing model for processing, and the feature processing model can then output the water depth.
[0074] In this embodiment, when using the feature processing model to identify the depth of water ingress, the model has high accuracy because it has been trained with a large number of training samples. It can determine whether the vehicle has water ingress and the corresponding depth of water ingress based on the CIR features.
[0075] In another implementation of this invention, relying solely on the depth of water ingress may not accurately detect whether the vehicle has actually been flooded. For example, if someone inside the vehicle accidentally spills water from a bottle, causing a detection of water ingress, it does not necessarily mean the vehicle has fallen into water. Therefore, in this embodiment of the invention, the location of the water ingress and the vehicle's location can be combined to determine whether the vehicle has actually been flooded, thereby improving the accuracy of vehicle flood detection.
[0076] In this embodiment, the vehicle water ingress parameters further include the water ingress location and the vehicle position; the vehicle control method further includes:
[0077] 1) Acquire images of the vehicle's interior and analyze these images to determine the location of the water ingress.
[0078] In this embodiment, images of the vehicle's interior can be captured using an existing camera inside the vehicle or a camera specifically configured for water ingress detection.
[0079] The cameras can be installed in various locations inside the vehicle, such as the ceiling or floor. They can also be installed in the front and rear seats, each capturing images of the vehicle's interior. In real-world scenarios, if a vehicle window (such as a sunroof) is open, water typically enters the vehicle through the foot pedals or windows. If the windows are closed, water usually enters through the foot pedals. Therefore, the camera's capture area should at least include the foot pedal area and the window area. For example, a camera can be installed in the foot pedal area to capture images of that area, and another camera can be installed in the ceiling to capture images of multiple windows.
[0080] The images of the vehicle's interior captured by the camera can be output to the cloud. The cloud uses its internal detection logic to analyze the images and determine the location of the water ingress.
[0081] When inspecting images inside a vehicle, object detection can be performed. If water is detected in the image, the location of the water ingress can be determined. For example, if object detection is performed on the image of the pedal area and water is detected, it indicates that the water ingress is located on the pedal.
[0082] 2) Use positioning devices to detect vehicle location information.
[0083] In this embodiment, the positioning device can be GPS (Global Positioning System) or the aforementioned UWB radar, which can detect the specific location of the vehicle.
[0084] This specific location allows analysis of whether the vehicle is near a body of water (such as a river or lake). For example, based on GPS positioning to determine the vehicle's latitude and longitude, a map search is performed to check for nearby bodies of water, such as within a preset range of that latitude and longitude, such as within 500 meters (considering potential errors, this range is set relatively large). If such bodies of water are found, the vehicle is near a body of water. In this case, if water enters the vehicle, the probability of water ingress is high. If the vehicle is not near a body of water, the probability of water ingress is low.
[0085] In this embodiment, by detecting the water ingress location and the vehicle location, and using these two locations for water ingress detection, it is possible to determine whether the vehicle has fallen into the water from multiple angles and aspects, thereby improving the accuracy of vehicle water ingress detection.
[0086] After detecting the water depth, water ingress location, and vehicle location through the above embodiments, the system can determine whether the vehicle has fallen into the water based on this data, and then perform corresponding rescue operations when the vehicle falls into the water.
[0087] Specifically, in another implementation of the present invention, when the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, there are three possible scenarios when performing the preset rescue operation. These three scenarios are parallel solutions and will be described separately below.
[0088] 1. The first scenario.
[0089] If the water depth is not less than a depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, open the vehicle window and output a rescue alert message.
[0090] The designated water area can be within 500 meters of a river or lake.
[0091] Specifically, the depth threshold can be set according to the actual scenario. For example, if the water depth is 2cm, it can be considered that the vehicle is likely to fall into the water, and the depth threshold can be set to 2cm.
[0092] If the water depth is not less than 2cm, it indicates that a significant amount of water has entered the vehicle. Furthermore, the vehicle's location analysis confirms it is in a specific water area, suggesting water is present around the vehicle and further indicating a high probability that it has fallen into the water.
[0093] If the water ingress point is the foot pedal, it means the vehicle is taking in water from the bottom.
[0094] If the water depth is not less than a depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, it indicates a high probability that the vehicle has fallen into the water. The cloud system can then output a command to open the windows to the vehicle's system or controller, such as to the ECU, which will then control the windows to open. Specifically, when the windows are open, all windows can be opened to help occupants escape as quickly as possible.
[0095] In addition, the cloud can also output rescue prompts, such as sending prompts to the dealer system of the mobile phone used by the owner of the submerged vehicle, so that the system can automatically call the owner to provide rescue care and introduce rescue measures to help the owner get out of danger.
[0096] 2. The second scenario.
[0097] If the water depth is less than a depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, output a water ingress warning message, respond to the confirmation message of the water ingress warning message, open the vehicle window, and output a rescue warning message.
[0098] If the water depth is less than a depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, it indicates that the vehicle may have taken in water, but the extent of the ingress is minor. This could be due to the vehicle being driven on a flooded surface (i.e., wading through water), or the vehicle having just fallen into the water. Therefore, in this situation, to avoid misoperation during rescue, a water ingress warning message can be displayed to the user, and the user's response can confirm whether water has entered the vehicle.
[0099] In real-world scenarios, when a vehicle falls into water, a water ingress warning can be issued via voice, such as asking the user, "Is the vehicle currently submerged in water?" The user can answer "yes" or "no" via voice. If the user answers "yes," it is considered that the water ingress warning has been received. In response to the confirmation of the water ingress warning, the car window is opened and a rescue prompt is issued.
[0100] In this embodiment, when the vehicle is only slightly flooded, the user is interacted with to confirm whether the vehicle has fallen into the water, thus improving the accuracy of the water-falling judgment.
[0101] 3. The third scenario.
[0102] If the vehicle is located in a designated water area and the water ingress point is a window, open the window and output a rescue alert message.
[0103] Specifically, when the vehicle is located in a designated water area, it indicates that the vehicle is near the water and has a high probability of water ingress. If the water ingress point is a window, it means that the vehicle window is open at this time. When the window gap is large, the water ingress speed is fast, which poses a high degree of danger to the people inside the vehicle. Therefore, as long as it is detected that the vehicle is located in the designated water area and the water ingress point is a window, regardless of the water depth, it is considered that the vehicle has fallen into the water. In this case, the window is opened and a rescue prompt message is output.
[0104] In this embodiment, multiple water-fall judgment scenarios are set up, which can cover a wide range of water-fall situations and improve the accuracy of water-fall judgment.
[0105] In another implementation of the present invention, errors may still occur during the water ingress judgment process described above, such as someone pouring a large amount of water into the vehicle through the window. Therefore, in this embodiment of the present invention, a humidity sensor can be used for further judgment. Specifically, the humidity value at a preset location on the vehicle is obtained. If the humidity value is greater than a humidity threshold, and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions, a preset rescue operation is executed.
[0106] To elaborate, when a vehicle falls into water, the humidity sensor inside or outside the vehicle can detect the humidity value at a preset location, i.e., the location where the humidity sensor is installed. If the humidity value is greater than the humidity threshold and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions, it indicates that the current environment of the vehicle is relatively humid and water has entered the vehicle, which can further confirm that the vehicle is in a water ingress scenario. At this time, the preset rescue operation is executed.
[0107] In this embodiment, by combining the humidity value with the conditions for vehicle water ingress rescue, false detection of vehicles falling into water can be further avoided.
[0108] In another implementation of this application, the vehicle can also respond to the touch command of the emergency rescue button, open the window, and output emergency rescue prompt information.
[0109] Specifically, a physical button (ECALL) is installed inside the vehicle. When a user encounters danger, they can press this button to request assistance. When the user presses the button, the system receives a touch command for the assistance button, responds to the command by opening the windows and displaying assistance prompts to help the user escape the predicament.
[0110] In another implementation of this application, user voice can also be received. If the user voice includes key rescue information, the car window is opened and rescue prompt information is output.
[0111] Among them, key rescue information can be words such as "help me," "save me," "fall into the water," and "danger," which indicate that someone who has fallen into the water needs rescue.
[0112] In real-world scenarios, if a vehicle falls into water, people trapped inside will shout for help. Therefore, it's possible to collect user voice recordings and identify key information within them. If this information includes crucial rescue details, it's assumed the user needs assistance. In this case, the car windows are opened and rescue prompts are displayed to help the trapped individuals escape.
[0113] In another implementation of the present invention, a specific device interaction process for the vehicle control method is provided. This process includes the following steps:
[0114] S31, UWB acquires channel impulse response data.
[0115] UWB utilizes its own CIR function to collect channel impulse response data.
[0116] S32 and UWB output channel impulse response data to the cloud.
[0117] Specifically, UWB can transmit channel impulse response data to the cloud via wireless means, TBOX (Telematics Box), or other methods.
[0118] S33. The cloud determines the parameter values of the vehicle water ingress parameters based on the channel impulse response data.
[0119] S34. The cloud determines that there are people inside the vehicle and that the parameters of the vehicle's water ingress meet the conditions for vehicle water ingress rescue.
[0120] S35: The cloud sends the command to open the car window to the vehicle system.
[0121] S36. Output rescue notification information to the dealer system.
[0122] S37, The vehicle system opens the windows.
[0123] S38, Dealer system communication with vehicle occupants.
[0124] For the specific implementation of steps S33-S38, please refer to the corresponding descriptions above.
[0125] In this embodiment, when the CIR detects that the vehicle has fallen into the water, all four windows and the sunroof can be opened to allow the driver trapped underwater to escape, and the relevant after-sales department can be notified in a timely manner to handle subsequent issues.
[0126] In addition, because this invention detects water ingress into the vehicle's interior, it avoids false alarms compared to humidity sensors. It also prevents the risk of criminals using the characteristics of humidity sensors to open car windows and steal from the vehicle.
[0127] Based on the embodiments of the above-described vehicle control method, another embodiment of the present invention provides a vehicle control device, referring to... Figure 4 ,include:
[0128] The data acquisition module 11 is used to acquire channel impulse response data inside the vehicle;
[0129] The parameter determination module 12 is used to determine the parameter values of the vehicle water ingress parameters based on the channel impulse response data.
[0130] The rescue control module 13 is used to execute a preset rescue operation if there are people inside the vehicle and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions; the preset rescue operation includes at least opening the vehicle window.
[0131] In one implementation, the vehicle water ingress parameters include water ingress depth; the parameter determination module 12 includes:
[0132] The feature extraction submodule is used to extract feature data from the channel impulse response data;
[0133] The depth determination submodule is used to call the feature processing model to process the feature data to obtain the inflow depth; the feature processing model is trained based on training samples; the training samples include feature data of channel impulse response samples and depth labels corresponding to the channel impulse response samples.
[0134] In one implementation, the vehicle water ingress parameters further include the water ingress location and the vehicle position; the vehicle control device further includes:
[0135] The first location determination module is used to acquire images of the vehicle interior and analyze the images to determine the location of water ingress.
[0136] The second location determination module is used to detect vehicle location information using a positioning device.
[0137] In one implementation, the rescue control module 13 includes:
[0138] The first control submodule is used to open the car window and output rescue prompt information when the water ingress depth is not less than the depth threshold, the vehicle is located in a designated water area, and the water ingress position is the foot pedal.
[0139] The second control submodule is used to output water ingress warning information, respond to the confirmation information of the water ingress warning information, open the car window and output rescue warning information when the water ingress depth is less than the depth threshold, the vehicle position is in the designated water area and the water ingress position is the foot pedal;
[0140] The third control submodule is used to open the window and output rescue prompt information when the vehicle is located in a designated water area and the water ingress point is the window.
[0141] In one implementation, the rescue control module 13 includes:
[0142] The fourth control submodule is used to obtain the humidity value at a preset location of the vehicle. If the humidity value is greater than the humidity threshold, and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions, a preset rescue operation is executed.
[0143] One implementation also includes:
[0144] The button response module is used to respond to emergency button touch commands, open the windows, and output emergency prompt information.
[0145] One implementation also includes:
[0146] The voice response module is used to receive user voice. If the user voice includes key rescue information, the module will open the car window and output rescue prompt information.
[0147] In this embodiment, based on the channel impulse response data inside the vehicle, the parameter values of the vehicle water ingress parameters are determined. If the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, it indicates that the vehicle may be flooded, and preset rescue operations such as opening the windows are performed to help the occupants escape and ensure their safety. Furthermore, in this invention, the channel impulse response data used to determine the water ingress parameters exhibits different spectral data when the object is moving. Therefore, this data can be used to accurately determine the parameter values of the water ingress parameters. Compared to using a humidity sensor for water ingress detection, this method avoids false detections in areas with high humidity and improves the accuracy of water ingress detection.
[0148] It should be noted that the working process of each module and sub-module in this embodiment is described in the corresponding descriptions in the above embodiments, and will not be repeated here.
[0149] This application embodiment also provides an electronic device, including at least one processor and a memory connected to the processor, wherein:
[0150] The memory is used to store computer programs;
[0151] The processor is used to execute the computer program so that the electronic device can implement the vehicle control method described above.
[0152] refer to Figure 5The diagram illustrates a structural schematic suitable for implementing the electronic device in the embodiments of this application. The electronic device in the embodiments of this application may include, but is not limited to, fixed terminals such as ECUs, cloud computing, mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0153] like Figure 5 As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, the RAM 603 also stores various programs and data required for the operation of the electronic device. The processing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0154] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, memory cards, hard drives, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.
[0155] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the vehicle control methods provided in this application.
[0156] This application also provides a computer-readable storage medium carrying one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the vehicle control methods provided in this application.
[0157] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A vehicle control method, characterized in that, include: Acquire channel impulse response data inside the vehicle; Based on the channel impulse response data, the parameter values of the vehicle water ingress parameters are determined; the vehicle water ingress parameters include water ingress depth, water ingress location, and vehicle location. If there are people inside the vehicle, and the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, a preset rescue operation is performed, including: opening the car window and outputting rescue prompt information when the water ingress depth is not less than a depth threshold, the vehicle is located in a designated water area, and the water ingress location is the foot pedal.
2. The vehicle control method according to claim 1, characterized in that, Based on the channel impulse response data, the parameter values of the vehicle water ingress parameters are determined, including: Extract the feature data from the channel impulse response data; The feature processing model is invoked to process the feature data to obtain the inflow depth; the feature processing model is trained based on training samples; the training samples include feature data of channel impulse response samples and depth labels corresponding to the channel impulse response samples.
3. The vehicle control method according to claim 2, characterized in that, The vehicle control method further includes: Images of the vehicle's interior are acquired and analyzed to determine the location of water ingress. The vehicle's location information is detected using a positioning device.
4. The vehicle control method according to claim 3, characterized in that, If the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, the preset rescue operation is executed, which also includes: When the water depth is less than the depth threshold, the vehicle is located in a designated water area, and the water ingress point is the foot pedal, output a water ingress warning message, respond to the confirmation message of the water ingress warning message, open the car window, and output a rescue warning message. If the vehicle is located in a designated water area and the water ingress point is a window, open the window and output a rescue alert message.
5. The vehicle control method according to claim 4, characterized in that, If the parameter values of the vehicle water ingress parameters meet the conditions for vehicle water ingress rescue, a preset rescue operation is executed, including: Obtain the humidity value at a preset location on the vehicle; If the humidity value is greater than the humidity threshold, and the parameter value of the vehicle water ingress parameter meets the vehicle water ingress rescue conditions, a preset rescue operation is executed.
6. The vehicle control method according to claim 1, characterized in that, Also includes: Responding to the touch command of the emergency assistance button, it opens the windows and outputs emergency assistance prompts.
7. The vehicle control method according to claim 1, characterized in that, Also includes: Receive user voice messages; If the user's voice includes key rescue information, then the car window will be opened and a rescue prompt message will be output.
8. A vehicle control device, characterized in that, include: The data acquisition module is used to acquire channel impulse response data inside the vehicle; The parameter determination module is used to determine the parameter values of the vehicle water ingress parameters based on the channel impulse response data; the vehicle water ingress parameters include water ingress depth, water ingress location, and vehicle location; The rescue control module is used to perform preset rescue operations if there are people inside the vehicle and the parameter values of the vehicle water ingress parameters meet the vehicle water ingress rescue conditions. These operations include: opening the car window and outputting rescue prompt information when the water ingress depth is not less than a depth threshold, the vehicle is located in a designated water area, and the water ingress location is the foot pedal.
9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program to enable the electronic device to implement the vehicle control method as described in any one of claims 1 to 7.
10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs that, when executed by an electronic device, enable the electronic device to implement the vehicle control method as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Vehicle control method, device and system and storage medium
CN117984893A
Driver Assistance Apparatus And Control Method For The Same
US20160339959A1