Vehicle falling-into-water escape method and system and vehicle

By combining the sensing data from sensor units and inertial measurement units to make multi-dimensional judgments, the confidence level of a vehicle falling into water is determined. This solves the problems of easy failure and false triggering in existing vehicle water escape systems, enabling fast and reliable escape operations and improving the success rate of passenger escape.

CN121697571APending Publication Date: 2026-03-20ZHEJIANG LEAPMOTOR TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202610186658.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-09
Publication Date
2026-03-20

AI Technical Summary

Technical Problem

Existing vehicle water escape systems are prone to failure after the vehicle loses power and are susceptible to false triggering, which can affect the normal use of the vehicle and may cause the best escape opportunity to be missed.

Method used

By combining the sensing data from the sensor unit and the inertial measurement unit to perform multi-dimensional trigger judgments, the confidence level of the vehicle falling into the water is determined. When the confidence level meets the preset level conditions, the falling water state is determined, and the control execution module is used to perform the escape operation.

Benefits of technology

It improves the reliability and accuracy of escape in water-related scenarios, ensures the success rate of passenger escape, avoids false triggers and missed judgments, and provides a fast and reliable escape route.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121697571A_ABST
    Figure CN121697571A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle safety, and discloses a vehicle falling-into-water escape method and system and a vehicle. The method comprises the steps that first sensing data of a sensor unit on the vehicle and second sensing data of an inertial measurement unit on the vehicle are obtained; under the condition that at least one of the first sensing data and the second sensing data meets a preset triggering condition, determining a water falling confidence coefficient according to the first sensing data and the second sensing data; determining whether the vehicle is in a drowning state based on the drowning confidence; and under the condition that the vehicle is in the water falling state, an execution module of the vehicle is controlled to execute escape operation in response to the water falling state. Triggering judgment is performed by combining the sensing data of the sensor unit and the inertial measurement unit, so that the influence of false triggering on use can be effectively avoided, quick response to escape operation when falling into water is ensured, and the reliability of the system is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of vehicle safety technology, and in particular to a method, system and vehicle for escaping from falling into water. Background Technology

[0002] Accidental falling into water during vehicle operation is one of the most dangerous scenarios. Because new energy vehicles have high-voltage circuit systems, large battery packs, and highly integrated electronic control systems, when a vehicle falls into water, the entire vehicle's circuitry may short-circuit rapidly, resulting in the loss of an active escape route.

[0003] Related technologies typically employ mechanical window-breaking tools or a single electronic window-opening function, relying on a single sensor to trigger emergency actions. However, this method is prone to failure after the vehicle loses power and cannot accurately determine the state of being submerged in water, leading to false triggering of the system, affecting normal vehicle use, and potentially causing the best escape opportunity to be missed. Summary of the Invention

[0004] This application provides a method, system, and vehicle for escaping a vehicle from falling into water. It solves the technical problems that current vehicle water escape systems are prone to failure after the vehicle loses power and are easily triggered by false triggers. It achieves the technical effect of effectively avoiding false triggers that affect use, ensuring a rapid response escape operation when the vehicle falls into water, and improving the reliability of the system.

[0005] To achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, this application provides a method for escaping a vehicle that has fallen into water, the method comprising: Acquire the first sensing data from the sensor unit on the vehicle and the second sensing data from the inertial measurement unit; If at least one of the first sensing data and the second sensing data satisfies a preset trigger condition, the confidence level of the vehicle falling into the water is determined based on the first sensing data and the second sensing data. Determine whether the vehicle is in a state of being submerged in water based on the aforementioned confidence level. When the vehicle is in a state of being submerged in water, the execution module that controls the vehicle performs an escape operation in response to the state of being submerged in water.

[0006] The vehicle submersion escape method proposed in this application triggers a judgment by combining the first sensing data from the sensor unit and the second sensing data from the inertial measurement unit. Then, based on the first and second sensing data, the confidence level of the vehicle submersion is determined. Submersion is only confirmed when the confidence level meets a preset level condition; otherwise, a third sensing data is collected for verification. Compared with related technologies, this effectively reduces false triggers caused by single data triggers. Simultaneously, the escape operation is executed in response to the submersion status by the control execution module, ensuring that the escape process is initiated promptly after the submersion determination. This ensures both the accuracy of submersion identification, avoiding impact on normal vehicle use, and the timeliness of the escape response, improving the reliability of escape in vehicle submersion scenarios and significantly increasing the passenger escape success rate.

[0007] Optionally, the sensor unit includes a pressure sensor and a water level sensor; The pressure sensor is disposed on the bottom outer surface of the vehicle, and the first sensing data of the pressure sensor represents the water pressure outside the vehicle. The water level sensor is installed on the floor of the vehicle's driver's cabin, and the first sensing data from the water level sensor represents the water level inside the vehicle.

[0008] Optionally, at least one of the first sensing data and the second sensing data may be determined to satisfy a preset trigger condition in the following manner: If the first sensing data of at least two of the pressure sensors is greater than a first preset water pressure threshold, then it is determined that the first sensing data satisfies the preset trigger condition; and / or If the first sensing data from at least one of the water level sensors indicates that water has entered the vehicle interior, then it is determined that the first sensing data satisfies the preset trigger condition; and / or If the second sensing data characterization of the inertial measurement unit detects that the vehicle is in a state of weightlessness or impact, then it is determined that the second sensing data satisfies the preset triggering condition.

[0009] This application uses a multi-dimensional trigger judgment through pressure sensors, water level sensors, and inertial measurement units, which not only avoids false triggering caused by abnormal data from a single sensor, but also ensures that subsequent water fall judgment and escape operation response processes can be accurately triggered in different water fall scenarios.

[0010] Optionally, determining the confidence level of the vehicle falling into water based on the first sensing data and the second sensing data includes: If both the first sensing data and the second sensing data satisfy the preset triggering condition, and if it is determined that the first sensing data and the second sensing data satisfy the preset timing condition, then the confidence level of falling into the water is determined to be a high confidence level. If the first sensing data satisfies the preset triggering condition and the second sensing data does not satisfy the preset triggering condition, the confidence level of falling into the water is determined to be medium confidence level. If the second sensing data meets the preset triggering condition and the first sensing data does not meet the preset triggering condition, the confidence level of falling into the water is determined to be a low confidence level.

[0011] This application determines the confidence level of falling into water based on the first and second perception data. By determining different levels of confidence level for falling into water, it can ensure the rapid and accurate identification of real falling into water scenarios, effectively avoid false triggering of falling into water states, and not miss any suspected falling into water scenarios, which is conducive to improving the reliability of the system.

[0012] Optionally, determining whether the vehicle is in a submerged state based on the submerged confidence level includes: If the confidence level of the vehicle falling into the water is high, it is determined that the vehicle is in a state of falling into the water. When the confidence level of the vehicle falling into the water is at a medium level, the third sensing data of the sensor unit is acquired, and the vehicle is determined to be in a state of falling into the water based on the third sensing data. If the confidence level for the vehicle falling into the water is low, it is determined that the vehicle is not in a state of falling into the water.

[0013] Optionally, acquiring the third sensing data from the sensor unit and determining that the vehicle is in a submerged state based on the third sensing data includes: The third sensing data output by the sensor unit is continuously collected within a preset confirmation window to form time series data based on the third sensing data; The time series data is linearly fitted to determine the rate of change and coefficient of determination of the time series data based on the fitting results; If the rate of change is greater than a preset change threshold and the coefficient of determination is greater than a preset fitting threshold, the vehicle is determined to be in a state of being submerged in water.

[0014] This application continuously collects third-sensor data within a preset confirmation window and forms time-series data. The rate of change and coefficient of determination are obtained through linear fitting. In this way, the rate of change accurately represents the trend of change of external water pressure or internal water level of the vehicle after determining a medium confidence level. At the same time, the coefficient of determination eliminates misjudgments caused by random disturbances, effectively filtering out interference from non-water-falling scenarios such as wave impact and short-term water accumulation, and further reducing the risk of missed or misjudged water-falling scenarios.

[0015] Optionally, the vehicle controls the execution module via an electronic control unit, the execution module including a power control unit, an on-board emergency backup battery, and a door and window linkage control unit; The execution module that controls the vehicle performs an escape operation in response to the water-falling state, including: The electronic control unit generates a first escape command in response to the water-falling state, causing the power control unit to cut off the high-voltage power supply of the vehicle in response to the first escape command and switch the low-voltage power supply of the vehicle to the on-board emergency backup battery. The electronic control unit generates a second escape command in response to the water-falling state, causing the door and window linkage control unit to automatically lower all windows and forcibly unlock the doors in response to the second escape command.

[0016] This application utilizes an electronic control unit in conjunction with a power control unit, an onboard emergency backup battery, and a door and window linkage control unit to execute the escape operation. This eliminates the risk of high-voltage electric shock after a new energy vehicle falls into water and prevents the escape system from failing after the main power supply of the vehicle fails, further improving system reliability. Furthermore, by automatically lowering and forcibly unlocking the windows through the door and window linkage control unit, the water pressure inside and outside the vehicle is quickly balanced, providing occupants with a direct and convenient escape route. This effectively overcomes the difficulties of manual operation after falling into water and the inability to open the escape passage in a timely manner, significantly increasing the success rate of escape in water-falling scenarios.

[0017] Optionally, the execution module further includes a door and window status detection unit and a window breaking unit, wherein the window breaking unit is distributed at the top edge of each window glass of the vehicle; The execution module that controls the vehicle performs an escape operation in response to the water-falling state, including: The electronic control unit acquires the fourth sensing data from the sensor unit in response to the water-falling state; If the window and door status detection unit fails to detect that the window and door lock have been successfully opened within a second preset time, and the fourth sensing data is greater than the second preset water pressure threshold, the electronic control unit generates a third escape command, causing the window breaking unit to directionally break the window glass in response to the third escape command.

[0018] This application utilizes a door and window status detection unit and a window-breaking unit positioned at the top edge of the vehicle window glass. When the door or window fails to open and the water pressure reaches a second preset threshold, the window-breaking unit is triggered to directionally explode. Furthermore, the window-breaking unit is positioned at the top edge of the window, which is the last part to be submerged during the initial stage of flooding. This avoids ineffective window-breaking operations when the door or window can be opened normally, and provides a rapid escape route in extreme scenarios where door and window opening fails. In addition, the window-breaking unit can precisely directionally explode, reducing the risk of flying glass shards.

[0019] Secondly, this application provides a vehicle water escape system, the system comprising: The perception module is used to acquire first perception data from the sensor units on the vehicle and second perception data from the inertial measurement unit. The confidence analysis module is used to determine the confidence level of the vehicle falling into the water based on the first sensing data and the second sensing data when at least one of the first sensing data and the second sensing data meets a preset triggering condition. The water-fall detection module is used to determine whether a vehicle is in a water-fall state based on the water-fall confidence level; An execution module is used to perform an escape operation in response to the vehicle being submerged in water.

[0020] The vehicle submersion escape system proposed in this application uses a sensing module to combine first sensing data from a sensor unit with second sensing data from an inertial measurement unit for trigger judgment. Based on the first and second sensing data, it determines the confidence level of the vehicle submersion. Submersion is only confirmed when the confidence level meets a preset level condition; otherwise, third sensing data is collected for verification. Compared with related technologies, this effectively reduces false triggers caused by single data triggers. Simultaneously, the control execution module responds to the submersion status and executes the escape operation, ensuring that the escape process is initiated promptly after submersion determination. This ensures both the accuracy of submersion identification, avoiding impact on normal vehicle use, and the timeliness of the escape response, improving the reliability of escape in vehicle submersion scenarios and significantly increasing the passenger escape success rate.

[0021] Thirdly, this application provides a vehicle that includes the aforementioned vehicle water escape system. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is one of the flowcharts illustrating a method for escaping a vehicle that has fallen into water, as provided in an embodiment of this application. Figure 2 A second schematic flowchart illustrating a method for escaping a vehicle that has fallen into water, as provided in an embodiment of this application; Figure 3 The third schematic flowchart of a method for escaping a vehicle that has fallen into water, provided as an embodiment of this application; Figure 4 This is a schematic diagram of a vehicle water escape system provided in an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0025] Accidental submersion in water during vehicle operation is an extremely dangerous scenario. In particular, new energy vehicles, which are equipped with high-voltage circuit systems and large-capacity battery packs, not only face the risk of escape routes failing after falling into water, but may also face secondary dangers due to high-voltage leakage.

[0026] Some related technologies typically employ mechanical window-breaking tools or a single electronic window-opening function, requiring occupants to search for and use them in a panic. This often results in failure to break the window due to incorrect impact angles or insufficient force, and water resistance further weakens the impact effect. In the event of a short circuit and power loss after the vehicle has fallen into the water, the control circuit and triggering mechanism of an electronic window breaker will fail due to power loss, leading to poor escape reliability.

[0027] In other related technologies, the escape system typically relies on a threshold trigger from a single sensor to activate, initiating the escape operation only upon a single data point meeting the threshold. However, this method is susceptible to external environmental interference. For example, when a vehicle drives through flooded areas, encounters wave impacts, or experiences road bumps, a single sensor may generate a false trigger signal, causing the escape system to activate erroneously. This not only affects the normal use of the vehicle but may also damage the performance of escape-related components. Furthermore, in special water-fall scenarios such as slow immersion or unilateral submersion, the system may fail to meet the threshold trigger mechanism, resulting in missed opportunities for optimal escape.

[0028] Therefore, there is an urgent need for a vehicle-to-water escape solution that balances trigger accuracy and escape reliability.

[0029] According to an embodiment of this application, a method for escaping a vehicle that has fallen into water is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a method for escaping a vehicle that has fallen into water. Figure 1 This is a flowchart of a vehicle escaping from water according to an embodiment of this application, such as... Figure 1 As shown, the process includes the following steps: Step S1: Acquire the first sensing data from the sensor unit on the vehicle and the second sensing data from the inertial measurement unit.

[0031] Specifically, the sensor unit is used to detect the vehicle's state related to falling into water. Its output first sensing data characterizes the changes in external water pressure and the state of water ingress inside the vehicle. The inertial measurement unit (IMU) is a device used to measure the vehicle's angular velocity and acceleration. Its output second sensing data characterizes the vehicle's motion acceleration and whether it is in a state of weightlessness or impact, thereby sensing abnormal postures such as vehicle falling and rolling.

[0032] In this embodiment, the sensor unit and IMU work continuously during vehicle operation, thereby sending the real-time collected first and second sensing data to the vehicle's electronic control unit (ECU). The ECU acquires all the first and second sensing data at a fixed scan cycle (e.g., 10ms) to monitor the vehicle's submersion status.

[0033] Step S3: If at least one of the first perception data and the second perception data satisfies a preset triggering condition, determine the confidence level of the vehicle falling into the water based on the first perception data and the second perception data.

[0034] Specifically, the preset trigger condition is a pre-defined critical threshold used to initially determine if a vehicle may be in a water-related scenario. If at least one of the first and second perception data satisfies the preset trigger condition, it indicates that the vehicle may be in water. Subsequently, the confidence level of the vehicle's water-related situation is determined based on the first and second perception data. This integrates two different dimensions of perception data to analyze the probability that the vehicle is in a water-related state, avoiding misjudgments caused by judging from a single data dimension.

[0035] Step S5: Determine whether the vehicle is in a state of being submerged in water based on the confidence level of the submersion.

[0036] Specifically, the likelihood of a vehicle falling into water is assessed by the water-falling confidence level. The higher the water-falling confidence level, the greater the likelihood of the vehicle falling into water. Subsequent escape operations will only be triggered when the water-falling confidence level is high, in order to prevent the system from being triggered erroneously.

[0037] Step S7: When the vehicle is in a state of being submerged in water, the execution module controlling the vehicle responds to the state of being submerged in water by performing an escape operation.

[0038] Specifically, when a vehicle is definitively determined to be in a state of submersion, the ECU will immediately send relevant escape commands to a pre-set execution module, thereby initiating a pre-set escape procedure. The execution module will complete the corresponding escape actions according to the pre-set escape procedure, thereby quickly providing a safe escape route for the occupants, while avoiding potential safety hazards after the vehicle falls into the water, ensuring that the occupants can evacuate the vehicle in a timely and safe manner, and maximizing the chances of survival for the occupants in a submersion scenario.

[0039] The vehicle submersion escape method provided in this application combines first sensing data from a sensor unit with second sensing data from an inertial measurement unit for trigger judgment. Then, based on the first and second sensing data, the confidence level of the vehicle submersion is determined. Submersion is only determined when the confidence level meets a preset level condition; otherwise, third sensing data is collected for verification. Compared with related technologies, this effectively reduces false triggers caused by single data triggers. Simultaneously, the escape operation is executed in response to the submersion status by a control execution module, ensuring that the escape process is initiated promptly after the submersion determination. This ensures both the accuracy of submersion identification, avoiding impact on normal vehicle use, and the timeliness of the escape response, improving the reliability of escape in vehicle submersion scenarios and significantly increasing the passenger escape success rate.

[0040] Furthermore, the sensor unit includes a pressure sensor and a water level sensor. The pressure sensor is located on the outer surface of the vehicle's bottom, and its initial sensing data characterizes the water pressure outside the vehicle. The water level sensor is located on the floor of the vehicle's passenger compartment, and its initial sensing data characterizes the water level inside the vehicle.

[0041] Specifically, in this embodiment, pressure sensors are distributed at the bottom of the four door panels and the chassis of the vehicle to monitor the external water pressure in real time. Water level sensors are distributed below the driver's cabin floor to monitor whether water has entered the vehicle.

[0042] In addition, in some embodiments of this application, a wading depth sensor can be installed on the vehicle, which uses ultrasonic waves to monitor the rapid rise of water levels around the vehicle.

[0043] It should be noted that, in this embodiment of the application, the vehicle is also equipped with a seat belt status sensor and a seat pressure sensor to determine whether there are occupants in the vehicle. The ECU will only start the above steps S1 to S7 when there are occupants in the vehicle.

[0044] In some embodiments of this application, at least one of the first sensing data and the second sensing data is determined to satisfy a preset trigger condition in the following manner: If the first sensing data from at least two pressure sensors is greater than a first preset water pressure threshold, then the first sensing data is determined to meet a preset trigger condition; and / or If the first sensing data from at least one water level sensor indicates that water has entered the vehicle interior, then the first sensing data is determined to meet a preset trigger condition; and / or If the second sensing data characterization of the inertial measurement unit detects that the vehicle is in a state of weightlessness or impact, then the second sensing data is determined to meet the preset triggering conditions.

[0045] Specifically, the aforementioned preset triggering conditions include at least the following three: (1) Water pressure triggering condition: In this embodiment, the first preset water pressure threshold is set to the pressure value corresponding to a water depth of 1 meter, which is approximately 10 kPa. When the water pressure detected by at least two pressure sensors is greater than 10 kPa, it is determined that the first sensing data meets the preset triggering condition; (2) Water level triggering conditions: In this embodiment, the water level sensor is a contact electrode type sensor and adopts a switch signal triggering mode. When the sensor electrode comes into contact with water, its output signal state will switch instantaneously, thereby accurately triggering the detection and judgment of water entering the vehicle, and thus determining that the first sensing data meets the preset triggering conditions. (3) Attitude triggering conditions: In this embodiment, the threshold for determining the weightlessness state is a weightlessness acceleration lasting 0.5 to 1 second to simulate an abnormal vehicle fall scenario. The threshold for determining the impact state is a longitudinal deceleration greater than 5g to simulate a vehicle falling into water. When the acceleration value corresponding to the second sensing data of the IMU is a weightlessness acceleration lasting 0.5 to 1 second, or the acceleration value corresponding to the second sensing data is a longitudinal deceleration greater than 5g, it is determined that the second sensing data meets the preset triggering conditions.

[0046] This application embodiment uses a pressure sensor, a water level sensor, and an inertial measurement unit to perform multi-dimensional trigger judgment, which not only avoids false triggering caused by abnormal data from a single sensor, but also ensures that subsequent water fall judgment and escape operation response processes can be accurately triggered in different water fall scenarios.

[0047] In some embodiments of this application, step S3 may include: If both the first and second sensing data meet the preset triggering conditions, and if it is determined that the first and second sensing data meet the preset timing conditions, then the confidence level of falling into the water is determined to be a high confidence level. If the first sensing data meets the preset triggering conditions and the second sensing data does not meet the preset triggering conditions, the confidence level of falling into the water is determined to be medium confidence level. If the second sensing data meets the preset triggering conditions and the first sensing data does not meet the preset triggering conditions, the confidence level of falling into the water is determined to be low confidence level.

[0048] Specifically, in a real-life scenario where a vehicle falls into water, the following stages are typically involved: (1) First stage: The stage when the vehicle is falling in the air or hitting the water surface. In this stage, the IMU first detects the abnormal changes in the vehicle's motion state through the second sensing data. Specifically, the weightlessness acceleration generated during the vehicle's fall and the longitudinal deceleration generated by the violent impact when the vehicle hits the water surface, thus satisfying the preset triggering conditions. (2) Second stage: When the vehicle is in the water entry stage, within a very short time after the vehicle hits the water surface, usually no more than 500 milliseconds, the first sensing data output by the external pressure sensor will show the characteristic of a sharp increase in water pressure, thus meeting the preset triggering conditions. (3) In the third stage, the vehicle is in the stage of internal water ingress. Compared with the second stage, the first sensing data output by the internal water level sensor will be delayed. The delay time is usually from hundreds of milliseconds to several seconds. After a certain delay time, the first sensing data of the internal water level sensor may meet the preset triggering conditions due to the influx of water.

[0049] Therefore, in a real-world water-fall scenario, the IMU should detect the vehicle's weightlessness or impact state earlier than or nearly simultaneously with the moment when the water pressure or level rises sharply in the first sensing data output by the external pressure sensor and internal water level sensor. If the first sensing data changes drastically before the second sensing data, it may be more consistent with a scenario where the vehicle is passing through a deep water area, rather than a real-world water-fall scenario. If only the IMU's second sensing data detects the vehicle's weightlessness or impact state, while the first sensing data from the external pressure sensor and internal water level sensor do not show any characteristics of rising water pressure or level, it may be more consistent with a scenario of a vehicle collision, rather than a real-world water-fall scenario.

[0050] Therefore, the preset timing condition in this application embodiment is that the moment when the second sensing data meets the preset trigger condition is earlier than or synchronized with the moment when the first sensing data meets the preset trigger condition, and the synchronization time difference between the two satisfying moments is less than the preset time threshold, which is usually set to 0.5 seconds.

[0051] If both the first and second perception data meet the preset triggering conditions and the preset timing conditions, the confidence level of falling into the water is determined to be high confidence level. High confidence level indicates that the probability of the vehicle being in a state of falling into the water is very high. Therefore, it is directly determined that the vehicle has fallen into the water accident so that the escape operation of the execution module can be started immediately.

[0052] If the first sensing data meets the preset triggering conditions, but the second sensing data does not, the confidence level for the vehicle falling into water is determined to be medium. Medium confidence level indicates that the possibility of the vehicle being in a state of falling into water needs further verification; it may simply be that the vehicle is slowly entering the water. Therefore, to avoid false triggering, a vehicle falling into water accident will not be immediately determined.

[0053] If the second sensing data meets the preset triggering conditions, but the first sensing data does not meet the preset triggering conditions, the confidence level of falling into the water is determined to be low. Low confidence level indicates that the probability of the vehicle being in the water is very low. The vehicle is more likely to have been involved in a crash or severe jolt. Therefore, the escape system will ignore this event and reset to step S1 for continuous monitoring.

[0054] The following table 1 illustrates the logic for determining the confidence level of falling into water in the embodiments of this application.

[0055] Table 1 The embodiments of this application determine the confidence level of falling into water based on the first perception data and the second perception data. By determining different levels of confidence level of falling into water, it can ensure the rapid and accurate identification of real falling into water scenarios, effectively avoid false triggering of falling into water states, and not miss suspected falling into water scenarios, which is conducive to improving the reliability of the system.

[0056] Furthermore, in some embodiments of this application, step S5 above includes the following steps: Under the condition that the confidence level of the vehicle falling into the water is high, it is determined that the vehicle is in the state of falling into the water. When the confidence level of the vehicle falling into the water is at a medium level, the third perception data of the sensor unit is acquired, and the vehicle is determined to be in a state of falling into the water based on the third perception data. If the confidence level for the vehicle falling into the water is low, it is determined that the vehicle is not in a state of being submerged in water.

[0057] Furthermore, such as Figure 2 As shown, under a medium confidence level of falling into water, the third sensing data of the sensor unit is acquired, and the vehicle is determined to be in a state of falling into water based on the third sensing data. Specifically, this may include the following steps: Step S51: Continuously acquire the third sensing data output by the sensor unit within the preset confirmation window to form time series data (t1, P1), (t2, P2), ..., (t... n ,P n ), where t n For the acquisition time of the third sensing data, P n For t n The third sensing data corresponding to each moment is the pressure value. This can be understood as the external water pressure detection signal of the vehicle when the confidence level of the water fall is determined to be moderate. Specifically, it represents the external water pressure value detected by the pressure sensor when the confidence level of the water fall is moderate.

[0058] Specifically, in this embodiment, the preset confirmation window is a short-term monitoring timer with a timing of 100ms to 200ms, for example, setting the preset confirmation window to 150ms, to provide a delay decision buffer. When the confidence level of falling into water is determined to be moderate, the ECU continues to acquire the third sensing data from the pressure sensor with a shorter scan cycle (e.g., 1ms). The third sensing data forms time-series data according to the acquisition time. In this way, by introducing a controllable and acceptable short-term delay, the accuracy of determining the state of falling into water is greatly improved, effectively avoiding the risk of false triggering in non-falling-in-water scenarios such as the vehicle passing through water accumulation areas or encountering wave impacts.

[0059] Step S53: Perform linear fitting on the time series data to determine the rate of change and coefficient of determination of the time series data based on the fitting results.

[0060] Specifically, for the aforementioned time series data (t1, P1), (t2, P2), ..., (t... n ,P n A linear fit was performed to obtain a fitted straight line P = a*t + b, which is the fitting result described above. Here, the slope 'a' represents the rate of change of the time series data.

[0061] In this embodiment of the application, the determination coefficient R of the fitted line is further determined based on the ratio between the sum of squared deviations between the actual pressure value at each sampling point in the time series data and the fitted pressure value at the corresponding time of the fitted line, and the sum of squared deviations between the actual pressure value at each sampling point and the mean pressure value. 2 Coefficient of determination R 2 The coefficient of determination R is a numerical characteristic representing the relationship between a random variable and multiple random variables. It is a statistical indicator used to reflect the reliability of a regression model in explaining changes in the dependent variable. It is understood that, in the embodiments of this application, the coefficient of determination R... 2 This characterizes the extent to which the fitted straight line can explain the fluctuations in pressure values.

[0062] Among them, the coefficient of determination R 2 The closer the value is to 1, the higher the reliability of the fit. Data points are closely distributed on both sides of the straight line, meaning that although there may be slight fluctuations in pressure increase, possibly due to sensor noise or minor water disturbances, the overall trend of water pressure is a linear increase, which highly matches real-world water-fall scenarios. (Coefficient of Determination R) 2 The closer the value is to 0, the lower the reliability of the fit. The data points are very scattered and have no regularity. This means that the pressure changes are random and disordered, which does not conform to the physical model of a vehicle sinking in water. It may be a false alarm scenario such as wave impact or bumps causing instantaneous force on the sensor.

[0063] Step S55: If the rate of change is greater than a preset change threshold and the coefficient of determination is greater than a preset fitting threshold, then the vehicle is determined to be in a state of being submerged in water.

[0064] Specifically, in this embodiment, the preset change threshold is determined based on the rate of change of pressure corresponding to a vehicle sinking speed greater than 0.5 m / s, and the fitting threshold is set to 0.9. If the slope 'a' of the fitted straight line is greater than the preset change threshold, the coefficient R is determined. 2 A value greater than 0.9 indicates that the vehicle is sinking rapidly, confirming that the vehicle is in a state of being submerged in water. This greatly improves the accuracy of the submersion determination and effectively avoids the risk of false triggering in various non-submersion scenarios.

[0065] This application embodiment continuously collects third-sensor data within a preset confirmation window and forms time-series data. The rate of change and coefficient of determination are obtained through linear fitting. In this way, the rate of change accurately represents the trend of change of external water pressure or internal water level of the vehicle after determining a medium confidence level. At the same time, the coefficient of determination eliminates misjudgments caused by random disturbances, effectively filtering out interference from non-water-falling scenarios such as wave impact and short-term water accumulation, and further reducing the risk of missed or misjudged water-falling scenarios.

[0066] In some embodiments of this application, the vehicle controls the execution module through an electronic control unit. The execution module includes a power control unit, an on-board emergency backup battery, a door and window linkage control unit, a door and window status detection unit, and a window breaking unit.

[0067] Furthermore, the ECU responds within 0 to 30 seconds of determining that the vehicle is in a submerged state to execute step S7. Figure 3 A flowchart of step S7 is shown, as follows. Figure 3 As shown, step S7 may include the following steps: In step S71, the electronic control unit generates a first escape command in response to the water-falling state, causing the power control unit to cut off the vehicle's high-voltage power supply in response to the first escape command and switch the vehicle's low-voltage power supply to the on-board emergency backup battery.

[0068] Specifically, the ECU sends a first escape command to the Battery Management System (BMS) via the high-speed CAN bus. This first escape command instructs the BMS to immediately disconnect the high-voltage battery main relay, achieving a complete high-voltage power cut-off and eliminating the risk of high-voltage leakage. Simultaneously, the BMS switches the vehicle's low-voltage power supply from the 12V battery to an independent onboard emergency backup battery, ensuring power supply for subsequent escape functions.

[0069] In step S73, the electronic control unit generates a second escape command in response to the water-falling state, causing the door and window linkage control unit to automatically lower all windows and forcibly unlock the doors in response to the second escape command.

[0070] Specifically, the door and window linkage control unit controls all door locks and all window motors. The ECU sends a second escape command to the door and window linkage control unit, which instructs the windows to be forcibly lowered and the doors to be forcibly unlocked. At this time, the occupants can escape directly through the lowered windows. At the same time, because the windows have been lowered, the water pressure inside and outside the vehicle is quickly balanced, making the doors easier to open.

[0071] In step S75, the electronic control unit acquires the fourth sensing data of the sensor unit in response to the water-falling state. If the door and window status detection unit fails to detect that the window and door lock are successfully opened within a second preset time, and the fourth sensing data is greater than the second preset water pressure threshold, the electronic control unit generates a third escape command, causing the window breaking unit to directionally break the window glass in response to the third escape command.

[0072] In some embodiments of this application, the fourth sensing data is the external water pressure detection signal of the vehicle when it is determined that the vehicle is in a submerged state, specifically representing the external water pressure value detected by the pressure sensor when the vehicle is in a submerged state. Specifically, the door and window status detection unit determines whether the door lock and window have been successfully opened through door switch sensors, window motor current feedback, etc., thereby indirectly determining whether any occupants are escaping through the doors and windows. If the door or window is detected to have been successfully opened, the door and window status detection unit determines that the escape operation has been initiated, and maintains the current state until the escape is successful or the vehicle sinks. If the door and window status detection unit does not detect that the door or window has been opened within a certain waiting time (e.g., 30 seconds), and the external pressure sensor shows that the water level continues to rise to a dangerous threshold, such as the fourth sensing data reaching the second preset water pressure threshold corresponding to three-quarters of the window height, it determines that the occupants may lose their mobility. At this time, the ECU generates a third escape command, which is used to send an ignition signal to the window breaking unit embedded at the top edge of each window.

[0073] In some embodiments of this application, the window-breaking unit is a miniature explosive window breaker, positioned at the top edge of the vehicle window. The top edge of the window is the area last to be submerged after the vehicle falls into water. Placing the window-breaking unit at the top edge of the window allows for some air space inside the vehicle after the window is broken, enabling occupants to consciously escape towards the water surface. Furthermore, the window-breaking unit in this embodiment employs directional explosive technology, ensuring that the window breaks out towards the outside of the vehicle, effectively preventing secondary injuries to occupants from glass fragments and protecting their safety during escape.

[0074] Furthermore, in some embodiments of this application, the aforementioned execution module may also include an audible and visual alarm unit, which forces all reading lights and dashboard lights inside the vehicle to illuminate for lighting purposes. Simultaneously, the vehicle horn sounds an urgent alarm, and the vehicle's central control screen displays an animated instruction: "Vehicle has fallen into water, escape immediately through the windows!" This helps occupants overcome panic and provides them with clear action instructions.

[0075] In some embodiments of this application, the aforementioned execution module may further include an emergency buoyancy and positioning unit, which is located on the vehicle roof or in the trunk, such as around the sunroof, and integrates a compressed gas tank and an inflatable airbag. When the vehicle is submerged in water, the ECU can trigger the compressed gas tank to rapidly inflate the airbag, forming one or more buoyant bodies on the roof. This slows the vehicle's descent, providing more time for escape. Furthermore, the inflatable airbag can be made of highly visible reflective materials such as orange and can integrate an emergency GPS beacon, thus serving as a surface beacon for the vehicle and automatically sending out a distress signal after submersion, facilitating its discovery by rescuers.

[0076] Accordingly, please refer to Figure 4 ,like Figure 4 As shown in the figure, this application provides a vehicle water escape system, which includes: The sensing module 100 is used to acquire the first sensing data from the sensor unit on the vehicle and the second sensing data from the inertial measurement unit. For details, please refer to step S1. The confidence analysis module 200 is used to determine the confidence level of the vehicle falling into the water based on the first perception data and the second perception data when at least one of the first perception data and the second perception data meets a preset triggering condition. For details, please refer to step S3. The water-falling detection module 300 is used to determine whether a vehicle is in a water-falling state based on the water-falling confidence level. For details, please refer to step S5. The execution module 400 is used to perform an escape operation in response to the vehicle being submerged in water. For details, please refer to step S7.

[0077] In some embodiments of this application, the vehicle submersion escape system further includes a trigger module 500, which is used for: If the first sensing data from at least two pressure sensors is greater than a first preset water pressure threshold, then the first sensing data is determined to meet a preset trigger condition; and / or If the first sensing data from at least one water level sensor indicates that water has entered the vehicle interior, then the first sensing data is determined to meet a preset trigger condition; and / or If the second sensing data characterization of the inertial measurement unit detects that the vehicle is in a state of weightlessness or impact, then the second sensing data is determined to meet the preset triggering conditions.

[0078] In some embodiments of this application, the confidence analysis module 200 is used for: If both the first and second sensing data meet the preset triggering conditions, and if it is determined that the first and second sensing data meet the preset timing conditions, then the confidence level of falling into the water is determined to be a high confidence level. If the first sensing data meets the preset triggering conditions and the second sensing data does not meet the preset triggering conditions, the confidence level of falling into the water is determined to be medium confidence level. If the second sensing data meets the preset triggering conditions and the first sensing data does not meet the preset triggering conditions, the confidence level of falling into the water is determined to be low confidence level.

[0079] In some embodiments of this application, the water-fall detection module 300 is used for: The third sensing data output by the sensor unit is continuously collected within the preset confirmation window to form time series data based on the third sensing data; Linear fitting is performed on time series data to determine the rate of change and coefficient of determination of the time series data based on the fitting results; If the rate of change is greater than a preset change threshold and the coefficient of determination is greater than a preset fitting threshold, the vehicle is determined to be in a state of being submerged in water.

[0080] In some embodiments of this application, the execution module 400 is used for: In response to the first escape command from the electronic control unit, the vehicle's high-voltage power supply is cut off, and the vehicle's low-voltage power supply is switched to the on-board emergency backup battery. In response to the second escape command from the electronic control unit, all windows automatically lower and the doors are forcibly unlocked; In response to the third escape command from the electronic control unit, the window breaking unit directionally breaks the vehicle window glass in response to the third escape command.

[0081] Accordingly, this application provides a vehicle that includes the aforementioned vehicle water escape system.

[0082] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0083] In this embodiment, the vehicle falling into the water escape system is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0084] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

[0085] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0086] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, 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.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable 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.

[0090] It should also be noted that 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 limitation, 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.

[0091] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. 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 in the method embodiments.

[0092] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

[0093] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for escaping a vehicle that has fallen into water, characterized in that, The method includes: Acquire the first sensing data from the sensor unit on the vehicle and the second sensing data from the inertial measurement unit; If at least one of the first sensing data and the second sensing data satisfies a preset trigger condition, the confidence level of the vehicle falling into the water is determined based on the first sensing data and the second sensing data. Determine whether the vehicle is in a state of being submerged in water based on the aforementioned confidence level. When the vehicle is in a state of being submerged in water, the execution module that controls the vehicle performs an escape operation in response to the state of being submerged in water.

2. The method according to claim 1, characterized in that, The sensor unit includes a pressure sensor and a water level sensor; The pressure sensor is disposed on the bottom outer surface of the vehicle, and the first sensing data of the pressure sensor represents the water pressure outside the vehicle. The water level sensor is installed on the floor of the vehicle's driver's cabin, and the first sensing data from the water level sensor represents the water level inside the vehicle.

3. The method according to claim 2, characterized in that, The following method is used to determine that at least one of the first sensing data and the second sensing data satisfies a preset trigger condition: If the first sensing data of at least two of the pressure sensors is greater than the first preset water pressure threshold, then it is determined that the first sensing data satisfies the preset triggering condition. and / or If the first sensing data of at least one of the water level sensors indicates that water has entered the vehicle, then it is determined that the first sensing data satisfies the preset triggering condition. and / or If the second sensing data characterization of the inertial measurement unit detects that the vehicle is in a state of weightlessness or impact, then it is determined that the second sensing data satisfies the preset triggering condition.

4. The method according to claim 1, characterized in that, Determining the confidence level of the vehicle falling into water based on the first sensing data and the second sensing data includes: If both the first sensing data and the second sensing data satisfy the preset triggering condition, and if it is determined that the first sensing data and the second sensing data satisfy the preset timing condition, then the confidence level of falling into the water is determined to be a high confidence level. If the first sensing data meets the preset triggering condition and the second sensing data does not meet the preset triggering condition, the confidence level of falling into the water is determined to be medium confidence level. If the second sensing data meets the preset triggering condition and the first sensing data does not meet the preset triggering condition, the confidence level of falling into the water is determined to be a low confidence level.

5. The method according to claim 1, characterized in that, Determining whether the vehicle is in a submerged state based on the submerged confidence level includes: If the confidence level of the vehicle falling into the water is high, it is determined that the vehicle is in a state of falling into the water. When the confidence level of the vehicle falling into the water is at a medium level, the third sensing data of the sensor unit is acquired, and the vehicle is determined to be in a state of falling into the water based on the third sensing data. If the confidence level for the vehicle falling into the water is low, it is determined that the vehicle is not in a state of falling into the water.

6. The method according to claim 5, characterized in that, The step of acquiring the third sensing data from the sensor unit and determining that the vehicle is in a submerged state based on the third sensing data includes: The third sensing data output by the sensor unit is continuously collected within a preset confirmation window to form time series data based on the third sensing data; The time series data is linearly fitted to determine the rate of change and coefficient of determination of the time series data based on the fitting results; If the rate of change is greater than a preset change threshold and the coefficient of determination is greater than a preset fitting threshold, the vehicle is determined to be in a state of being submerged in water.

7. The method according to claim 1, characterized in that, The vehicle controls the execution module via an electronic control unit, and the execution module includes a power control unit, an on-board emergency backup battery, and a door and window linkage control unit. The execution module that controls the vehicle performs an escape operation in response to the water-falling state, including: The electronic control unit generates a first escape command in response to the water-falling state, causing the power control unit to cut off the high-voltage power supply of the vehicle in response to the first escape command and switch the low-voltage power supply of the vehicle to the on-board emergency backup battery. The electronic control unit generates a second escape command in response to the water-falling state, causing the door and window linkage control unit to automatically lower all windows and forcibly unlock the doors in response to the second escape command.

8. The method according to claim 7, characterized in that, The execution module also includes a door and window status detection unit and a window breaking unit, wherein the window breaking unit is distributed at the top edge of each window glass of the vehicle; The execution module that controls the vehicle performs an escape operation in response to the water-falling state, including: The electronic control unit acquires the fourth sensing data from the sensor unit in response to the water-falling state; If the window and door status detection unit fails to detect that the window and door lock have been successfully opened within a second preset time, and the fourth sensing data is greater than the second preset water pressure threshold, the electronic control unit generates a third escape command, causing the window breaking unit to directionally break the window glass in response to the third escape command.

9. A vehicle water escape system, characterized in that, The system includes: The perception module is used to acquire first perception data from the sensor units on the vehicle and second perception data from the inertial measurement unit. The confidence analysis module is used to determine the confidence level of the vehicle falling into the water based on the first sensing data and the second sensing data when at least one of the first sensing data and the second sensing data meets a preset triggering condition. The water-fall detection module is used to determine whether a vehicle is in a water-fall state based on the water-fall confidence level; An execution module is used to perform an escape operation in response to the vehicle being submerged in water.

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

Citation Information

Patent Citations

  • Control method and system for falling-into-water protection of electric vehicle

    CN112009409A

  • Automobile rescue method, automobile and medium

    CN117048541A

  • High-altitude falling detection method and system based on mobile terminal multi-sensor fusion

    CN120974415A

  • Intelligent safety monitoring waistcoat based on multi-sensor fusion and control method

    CN121220835A

  • Method for evaluating and monitoring state of health of battery of electric vehicle

    CN121388673A