Pre-collision information acquisition method, emergency rescue method, driving equipment and cloud platform

Abstract

The invention relates to the field of intelligent driving, particularly provides a pre-collision information acquisition method, an emergency rescue method, driving equipment and a cloud platform, and aims to solve the problem that key information is lost after a vehicle is collided, and the rescue efficiency is influenced. The pre-collision information acquisition method comprises the following steps: acquiring perception data of current driving equipment; judging whether the current driving equipment is about to collide or not based on the sensing data; if the collision is about to occur, generating a collision early warning signal, and obtaining pre-collision information based on the sensing data; and sending the pre-collision information to a cloud platform, so that the cloud platform sends collision confirmation information to the current driving equipment based on the pre-collision information, and selectively starts emergency rescue based on feedback information of the user. Through the above implementation mode, the pre-collision information can be uploaded to the cloud platform before the collision of the driving equipment occurs, the cloud platform confirms whether the real collision occurs with the vehicle owner, emergency rescue is started according to the demand of the vehicle owner, and the rescue efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and particularly relates to a method for obtaining pre-collision information, an emergency rescue method, a driving device and a cloud platform. Background Art

[0002] At present, the vehicle safety guarantee system has become increasingly perfect. Especially the application of the emergency call system eCall provides important support for the rescue after a traffic accident. eCall can upload key data after a vehicle collision, helping rescue personnel quickly understand the accident situation, so as to implement efficient rescue.

[0003] However, in actual collision accidents, in some extreme working conditions, the 12V low-voltage small battery or the low-voltage power supply harness may be damaged, resulting in the loss of some key information (Minimum Set of Data, MSD) of eCall after the collision, and it cannot be uploaded to the system background in time, affecting the efficiency of accident rescue. Although adding a backup power redundancy design can solve the power supply problem, it will greatly increase the cost.

[0004] Correspondingly, a new technical solution is needed in this field to solve the above problems. Summary of the Invention

[0005] In order to overcome the above defects, the present application is proposed to provide a method for obtaining pre-collision information, an emergency rescue method, a driving device and a cloud platform that can solve or at least partially solve the technical problem that key information is lost after a vehicle collision, affecting the efficiency of accident rescue.

[0006] In a first aspect, a method for obtaining pre-collision information is provided, which is applied to a driving device, and the driving device is communicatively connected to a cloud platform; the method includes:

[0007] Obtain the perception data of the current driving device; the perception data includes cockpit perception data, vehicle body perception data and environmental perception data;

[0008] Based on the perception data, determine whether the current driving device is about to collide;

[0009] If a collision is about to occur, generate a collision warning signal, and obtain pre-collision information based on the perception data;

[0010] Send the pre-collision information to the cloud platform, so that the cloud platform sends a collision confirmation information to the current driving device based on the pre-collision information, and selectively starts emergency rescue based on the feedback information of the user.

[0011] In one technical solution of the above pre-collision information acquisition method, the cockpit perception data includes at least one of the number of occupants in the cockpit and the seating position;

[0012] The vehicle body perception data includes at least one of the position information, driving trajectory, and driving speed of the current driving device;

[0013] The environment perception data includes at least one of the position information, driving speed, driving direction of the target driving device existing within a preset range around the current driving device, and the distance between the target driving device and the current driving device.

[0014] In one technical solution of the above pre-collision information acquisition method, determining whether the current driving device is about to collide based on the perception data includes:

[0015] Obtaining the predicted driving trajectories of the current driving device and the target driving device based on the perception data;

[0016] Based on the perception data, the predicted driving trajectories of the current driving device and the target driving device, obtaining the probability of an inevitable collision of the current driving device;

[0017] When the probability is greater than a preset collision threshold, it is determined that the current driving device is about to collide.

[0018] In one technical solution of the above pre-collision information acquisition method, obtaining the probability of an inevitable collision of the current driving device based on the perception data, the predicted driving trajectories of the current driving device and the target driving device includes:

[0019] Inputting the perception data, the predicted driving trajectories of the current driving device and the target driving device into a collision prediction model to obtain the possibility of collision, collision severity, predicted collision time, and collision risk level in each direction between the current driving device and the target driving device;

[0020] Based on the possibility of collision, collision severity, predicted collision time, and collision risk level in each direction, obtaining the probability of an inevitable collision of the current driving device.

[0021] In one technical solution of the above pre-collision information acquisition method, obtaining pre-collision information based on the perception data includes:

[0022] Obtaining a predicted collision direction based on the collision risk level in each direction;

[0023] Take the cockpit perception data, vehicle body perception data, and environmental perception data, as well as the target driving device, the predicted collision direction, the collision severity, and the predicted collision time as the pre-collision information.

[0024] In one technical solution of the above pre-collision information acquisition method, the sending the pre-collision information to the cloud platform includes:

[0025] Based on the collision warning signal, send the pre-collision information to the cloud platform.

[0026] In a second aspect, the present application provides an emergency rescue method, which is applied to a cloud platform. The cloud platform is communicatively connected to multiple driving devices; the method includes:

[0027] In response to the pre-collision information sent by the driving device, determine whether the actual collision signal of the driving device is received within a first preset time period;

[0028] If so, send a collision confirmation information to the driving device, and selectively start emergency rescue based on the feedback information of the user.

[0029] In one technical solution of the above emergency rescue method, the sending the collision confirmation information to the driving device and selectively starting emergency rescue based on the feedback information of the user includes:

[0030] Send the collision confirmation information to the driving device, and determine whether the feedback information is received within a second preset time period to determine whether an actual collision has occurred;

[0031] If the feedback information is received within the second preset time period and it is determined that an actual collision has occurred, continue to send a rescue confirmation information to the driving device to determine whether the user needs rescue;

[0032] If the feedback information is not received within the second preset time period, start the emergency rescue.

[0033] In one technical solution of the above emergency rescue method, the continuing to send the rescue confirmation information to the driving device to determine whether the user needs rescue includes:

[0034] Send the rescue confirmation information to the driving device, and determine whether the feedback information is received within a third preset time period;

[0035] If the feedback information is received within the third preset time period and it is determined that the user needs rescue, start the emergency rescue;

[0036] If the feedback information is not received within the third preset time period, start the emergency rescue;

[0037] If the feedback information is received within the third preset duration and it is determined that the user does not need rescue, the emergency rescue is not initiated.

[0038] In a third aspect, an electronic device is provided. The electronic device includes a processor and a memory. The memory is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the pre-collision information acquisition method described in any one of the technical solutions of the above pre-collision information acquisition method.

[0039] In a fourth aspect, a driving device is provided. The driving device includes a driving domain, a cockpit domain, a control domain, and the electronic device described in the technical solution of the above electronic device. The driving domain and the cockpit domain include sensing sensors;

[0040] The sensing sensors are configured to acquire sensing data of the current driving device;

[0041] The driving domain is configured to generate a collision warning signal when the current driving device is about to collide, and send the collision warning signal to the control domain;

[0042] The control domain is configured to acquire pre-collision information based on the sensing data, and send the pre-collision information to the cloud platform based on the collision warning signal;

[0043] Wherein, the sensing sensors include cockpit sensors, vehicle body sensors, and environmental sensors, and the sensing data includes cockpit sensing data, vehicle body sensing data, and environmental sensing data.

[0044] In a fifth aspect, a cloud platform is provided. The cloud platform includes a processor and a memory. The memory is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the emergency rescue method described in any one of the technical solutions of the above emergency rescue method.

[0045] In a sixth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores multiple program codes, and the program codes are adapted to be loaded and run by a processor to execute the pre-collision information acquisition method described in any one of the technical solutions of the above pre-collision information acquisition method, or the emergency rescue method described in any one of the technical solutions of the above emergency rescue method.

[0046] Solution 1. A pre-collision information acquisition method is applied to a driving device. The driving device is communicatively connected to a cloud platform. The method includes:

[0047] Obtain the perception data of the current driving device; the perception data includes cockpit perception data, vehicle body perception data, and environmental perception data;

[0048] Based on the perception data, determine whether the current driving device is about to collide;

[0049] If a collision is about to occur, generate a collision warning signal and obtain pre-collision information based on the perception data;

[0050] Send the pre-collision information to the cloud platform so that the cloud platform sends collision confirmation information to the current driving device based on the pre-collision information and selectively activates emergency rescue based on the user's feedback information.

[0051] Solution 2. The pre-collision information acquisition method according to Solution 1, wherein the cockpit perception data includes at least one of the number of occupants in the cockpit and the seating position;

[0052] The vehicle body perception data includes at least one of the position information, driving trajectory, and driving speed of the current driving device;

[0053] The environmental perception data includes at least one of the position information, driving speed, driving direction of the target driving device existing within a preset range around the current driving device, and the distance between the target driving device and the current driving device.

[0054] Solution 3. The pre-collision information acquisition method according to Solution 2, wherein the determining whether the current driving device is about to collide based on the perception data includes:

[0055] Obtain the predicted driving trajectories of the current driving device and the target driving device based on the perception data;

[0056] Based on the perception data, the predicted driving trajectories of the current driving device and the target driving device, obtain the probability of an inevitable collision of the current driving device;

[0057] When the probability is greater than a preset collision threshold, determine that the current driving device is about to collide.

[0058] Solution 4. The pre-collision information acquisition method according to Solution 3, wherein the obtaining the probability of an inevitable collision of the current driving device based on the perception data, the predicted driving trajectories of the current driving device and the target driving device includes:

[0059] Input the perception data, the predicted driving trajectories of the current driving device and the target driving device into a collision prediction model to obtain the likelihood of a collision between the current driving device and the target driving device, the severity of the collision, the predicted collision time, and the collision risk level in each direction;

[0060] Based on the likelihood of the collision, the severity of the collision, the predicted collision time, and the collision risk level in each direction, obtain the probability of an inevitable collision for the current driving device.

[0061] Solution 5. The pre-collision information acquisition method according to Solution 4, characterized in that the obtaining of pre-collision information based on the perception data includes:

[0062] Based on the collision risk level in each direction, obtain the predicted collision direction;

[0063] Use the cockpit perception data, the vehicle body perception data, the environmental perception data, as well as the target driving device, the predicted collision direction, the severity of the collision, and the predicted collision time as the pre-collision information.

[0064] Solution 6. The pre-collision information acquisition method according to Solution 3, characterized in that the sending of the pre-collision information to the cloud platform includes:

[0065] Based on the collision warning signal, send the pre-collision information to the cloud platform.

[0066] Solution 7. An emergency rescue method applied to a cloud platform, characterized in that the cloud platform is communicatively connected to multiple driving devices; the method includes:

[0067] In response to pre-collision information sent by a driving device, determine whether an actual collision signal of the driving device is received within a first preset time period;

[0068] If so, send a collision confirmation message to the driving device and selectively initiate emergency rescue based on the user's feedback information.

[0069] Solution 8. The emergency rescue method according to Solution 7, characterized in that the sending of the collision confirmation message to the driving device and selectively initiating emergency rescue based on the user's feedback information includes:

[0070] Send the collision confirmation message to the driving device and determine whether the feedback information is received within a second preset time period to determine whether an actual collision has occurred;

[0071] If the feedback information is received within the second preset duration and an actual collision is determined, continue to send a rescue confirmation message to the driving device to determine whether the user needs rescue;

[0072] If the feedback information is not received within the second preset duration, start the emergency rescue.

[0073] Solution 9. The emergency rescue method according to Solution 8, wherein the continuing to send a rescue confirmation message to the driving device to determine whether the user needs rescue includes:

[0074] Send the rescue confirmation message to the driving device and determine whether the feedback information is received within a third preset duration;

[0075] If the feedback information is received within the third preset duration and it is determined that the user needs rescue, start the emergency rescue;

[0076] If the feedback information is not received within the third preset duration, start the emergency rescue;

[0077] If the feedback information is received within the third preset duration and it is determined that the user does not need rescue, do not start the emergency rescue.

[0078] 10. An electronic device, including a processor and a memory, the memory being adapted to store multiple program codes, wherein the program codes are adapted to be loaded and run by the processor to execute the pre-collision information acquisition method according to any one of Solutions 1 to 6.

[0079] Solution 11. A driving device, wherein the driving device includes a driving domain, a cockpit domain, a control domain, and the electronic device according to Solution 10, and the driving domain and the cockpit domain include sensing sensors;

[0080] The sensing sensors are configured to acquire sensing data of the current driving device;

[0081] The driving domain is configured to generate a collision warning signal when the current driving device is about to collide and send the collision warning signal to the control domain;

[0082] The control domain is configured to acquire pre-collision information based on the sensing data and send the pre-collision information to the cloud platform based on the collision warning signal;

[0083] Wherein, the sensing sensors include cockpit sensors, vehicle body sensors, and environmental sensors, and the sensing data includes cockpit sensing data, vehicle body sensing data, and environmental sensing data.

[0084] Solution 12. A cloud platform includes a processor and a memory. The memory is adapted to store multiple program codes. It is characterized in that the program codes are adapted to be loaded and run by the processor to execute the emergency rescue method described in any one of Solutions 7 to 9.

[0085] Solution 13. A computer-readable storage medium stores multiple program codes. It is characterized in that the program codes are adapted to be loaded and run by a processor to execute the pre-collision information acquisition method described in any one of Solutions 1 to 6, or the emergency rescue method described in any one of Solutions 7 to 9.

[0086] One or more of the above technical solutions of the present application have at least one or more of the following Beneficial effects:

[0087] In implementing the technical solution of the present application, the pre-collision information acquisition method is applied to a driving device, and the driving device is communicatively connected to a cloud platform; first, the perception data of the current driving device is acquired, and the perception data includes cockpit perception data, vehicle body perception data, and environmental perception data; then, based on the perception data, it is determined whether the current driving device is about to collide; if a collision is about to occur, a collision warning signal is generated, and pre-collision information is acquired based on the perception data; the pre-collision information is sent to the cloud platform so that the cloud platform sends a collision confirmation information to the current driving device based on the pre-collision information, and selectively activates emergency rescue based on the feedback information of the user. Through the above implementation method, key pre-collision information can be timely uploaded to the cloud platform before the driving device is about to collide, the cloud platform can confirm with the vehicle owner whether a real collision has occurred, and selectively activate emergency rescue according to the vehicle owner's needs, avoiding the failure of collision information transmission caused by low-voltage power supply failure, avoiding the omission of collision accidents being reported to the cloud platform, and improving the accident rescue efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Referring to the accompanying drawings, the disclosure of the present application will become more readily understood. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the protection scope of the present application. Among them:

[0089] Figure 1 is a schematic flowchart of the main steps of the pre-collision information acquisition method according to an embodiment of the present application;

[0090] Figure 2 is a schematic flowchart of the main steps of the emergency rescue method according to an embodiment of the present application;

[0091] Figure 3 is a schematic diagram of the main steps of the pre-collision information and emergency rescue method according to an embodiment of the present application;

[0092] Figure 4 It is a schematic diagram of the main structure of an electronic device according to an embodiment of the present application;

[0093] Figure 5 It is a schematic diagram of the main structure of a cloud platform according to an embodiment of the present application. Detailed implementation manners

[0094] Some embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.

[0095] In the description of the present application, the "processor" may include hardware, software, or a combination of both. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, in hardware, or in a combination of both. The non-transitory computer-readable storage medium includes any suitable medium for storing program code, such as magnetic disks, hard disks, optical discs, flash memories, read-only memories, random access memories, and so on. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "this" may also include the plural form.

[0096] As described in the background art, the vehicle safety guarantee system has become increasingly perfect. In particular, the application of the emergency call system eCall provides important support for the rescue after traffic accidents. eCall can upload key data after a vehicle collision, helping rescue personnel quickly understand the accident situation and thus implement efficient rescue.

[0097] However, in actual collision accidents, in some extreme working conditions, the 12V low-voltage small battery or the low-voltage power supply harness may be damaged, resulting in the loss of some key MSD information (such as collision direction, airbag deployment status, number of occupants in the cabin, high-voltage power-off situation, vehicle location, etc.) after the collision and being unable to be uploaded to the system background in time, affecting the efficiency of accident rescue. Although adding a redundant design of the backup power supply can solve the power supply problem, it will greatly increase the cost.

[0098] To solve the above problems, that is, the technical problem that key information is lost after a vehicle collision, affecting the efficiency of accident rescue, the present application provides a pre-collision information acquisition method, an emergency rescue method, an electronic device, a driving device, a cloud platform, and a storage medium.

[0099] Refer to the appendixFigure 1 , Figure 1 is a schematic diagram of the main steps of a pre-collision information acquisition method according to an embodiment of the present application, which is applied to a driving device, and the driving device is communicatively connected to a cloud platform. As Figure 1 shown, the pre-collision information acquisition method in the embodiment of the present application mainly includes the following steps S101 to S104.

[0100] Step S101: Obtain the perception data of the current driving device;

[0101] Among them, the perception data includes cockpit perception data, vehicle body perception data, and environment perception data.

[0102] Step S102: Based on the perception data, determine whether the current driving device is about to collide;

[0103] Further, if a collision is about to occur, then execute step S103, otherwise return to step S101.

[0104] Step S103: Generate a collision warning signal, and obtain pre-collision information based on the perception data;

[0105] Step S104: Send the pre-collision information to the cloud platform, so that the cloud platform sends a collision confirmation information to the current driving device based on the pre-collision information, and selectively activates emergency rescue based on the user's feedback information.

[0106] Based on the method described in the above steps S101 to S104, it is possible to upload key pre-collision information to the cloud platform in time before the driving device is about to collide. The cloud platform confirms with the vehicle owner whether a real collision has occurred, and selectively activates emergency rescue according to the vehicle owner's needs, avoiding the failure of collision information transmission caused by low-voltage power supply failure, and avoiding the omission of collision accidents reported to the cloud platform, thereby improving the accident rescue efficiency.

[0107] The following further explains the above steps S101 to S104.

[0108] In some embodiments of the above step S101, the perception data of the driving device can be obtained through various perception sensors in the Autonomous Driving (AD) domain and the Driver Cockpit Domain (DC) domain of the driving device, including cockpit perception data, vehicle body perception data, and environment perception data, etc.

[0109] Specifically, the cockpit perception data can be obtained through the cockpit sensors in the DC domain, and the vehicle body perception data and environment perception data can be obtained through the vehicle body sensors and environment sensors in the AD domain.

[0110] For example, perception data such as the number of occupants in the cockpit and their seating positions are obtained through in-cabin cameras, the status of seat belt buckles at each seating position, seat cushion occupant detection sensors, etc. Location information of the driving device is obtained through GPS, Beidou positioning systems, etc.; perception data such as the driving trajectory and driving speed of the driving device are obtained through wheel speed sensors and steering angle sensors; road condition information within a preset range around the current driving device is collected through devices such as lidar, high-definition cameras, and millimeter-wave radars, and the data collected by the sensors is processed through algorithms such as computer vision and machine learning to detect and track information on target driving devices existing within the preset range around the current driving device, including but not limited to perception data such as the location information, driving speed, driving direction of the target driving device, and the distance between the target driving device and the current driving device.

[0111] It should be noted that the above examples of cockpit perception data, vehicle body perception data, and environmental perception data are only illustrative. In actual applications, those skilled in the art can obtain the perception data of the driving device according to specific scenarios, and it can also include data such as vehicle model information and vehicle identification, which are not limited here.

[0112] The above is the description of step S101. Next, step S102 will be further described.

[0113] In some embodiments of the above step S102, it can be determined based on the perception data whether the current driving device and the target driving device are about to collide. Among them, if there are multiple target driving devices within the preset range around the current driving device, it is determined separately whether the current driving device and each target driving device are about to collide.

[0114] Specifically, step S102 may include the following steps S1021 to S1023.

[0115] Step S1021: Obtain the predicted driving trajectories of the current driving device and the target driving device based on the perception data;

[0116] In some embodiments, the obtained perception data can be analyzed based on prediction methods such as physical kinematic models and machine learning, and the future driving trajectories of the current driving device and the target driving device can be predicted according to the current states, historical motion data, etc. of the current driving device and the target driving device.

[0117] Among them, the physical kinematic model is constructed by describing the relationships between the basic physical quantities (such as displacement, velocity, acceleration, etc.) of an object's motion based on physical principles such as Newton's laws of motion. When predicting the driving trajectory, the driving device can be regarded as an object that moves in accordance with physical laws. For example, if the driving device maintains a uniform linear motion for a period of time, its position at a future moment can be predicted based on its current speed and driving time using the uniform linear motion formula (such as displacement = velocity × time) to obtain the predicted driving trajectory; if the driving device has an acceleration, the uniformly variable linear motion formula (such as displacement = initial velocity × time + 0.5 × acceleration × time 2 ) can be used for calculation to obtain the predicted driving trajectory of the driving device.

[0118] By analyzing the current speed, acceleration, driving direction and other data of the driving device through the above physical kinematic model and combining with the physical kinematic formula, the driving trajectories of the current driving device and the target driving device in the short term in the future can be deduced.

[0119] The machine learning prediction method is to let the computer automatically mine the potential patterns and rules in the data by learning a large amount of historical data, so as to realize the prediction of future data. When predicting the driving trajectory, a large amount of historical data containing information such as the motion state of the driving device and the surrounding environment can be collected first, such as the speed change, steering angle, and distance from the surrounding driving devices of the driving device in different scenarios. Then, machine learning algorithms such as decision trees, neural networks, and support vector machines are used to train these data.

[0120] Taking the neural network as an example, it can simulate the structure of human brain neurons, construct a multi-layer network, take the collected perceptual data as input, and output the predicted driving trajectories of the current driving device and the target driving device after complex weight calculations and non-linear transformations inside the network.

[0121] The machine learning method can handle complex non-linear relationships and has better adaptability to various complex scenarios and uncertainty factors. For example, in the case of complex traffic conditions and variable vehicle driving behaviors, it can learn the rules that are difficult to accurately describe by physical models from a large amount of data, so as to more accurately predict the future driving trajectory of the driving device.

[0122] In practical applications, a prediction method combining a physical kinematic model and machine learning is usually adopted. The physical kinematic model can provide a preliminary prediction based on basic physical principles, providing basic kinematic constraints for the machine learning model. The machine learning model, on the other hand, can utilize its powerful learning ability to model complex environmental factors and uncertain driving behaviors, making up for the deficiencies of the physical kinematic model in dealing with complex situations, thereby more accurately predicting the driving trajectories of the current driving device and the target driving device, and providing a reliable basis for subsequent collision risk judgment.

[0123] The above is the description of step S1021.

[0124] Step S1022: Based on the perception data, the predicted driving trajectories of the current driving device and the target driving device, obtain the probability that an inevitable collision will occur to the current driving device.

[0125] In some embodiments, the perception data, the predicted driving trajectories of the current driving device and the target driving device can be input into a collision prediction model to obtain the possibility of collision, the severity of the collision, the predicted collision time, and the collision risk level in each direction between the current driving device and the target driving device; and based on the possibility of collision, the severity of the collision, the predicted collision time, and the collision risk level in each direction, obtain the probability that an inevitable collision will occur to the current driving device.

[0126] Specifically, the collision prediction model will comprehensively analyze these input data. For example, by using mathematical models and probability analysis methods, it calculates the possibility of collision between the current driving device and the target driving device. During the calculation process, factors such as the motion states of the two vehicles, the relative speed, the intersection of the driving trajectories, and the surrounding environmental factors are considered.

[0127] The assessment of the severity of the collision involves factors such as the speeds, masses, and collision angles of the two vehicles. For example, a high-speed head-on collision between two vehicles is usually more severe than a low-speed side collision.

[0128] The predicted collision time (Time-To-Collision, TTC) is a key parameter, which represents the remaining time from the current state to the occurrence of a collision between the current driving device and the target driving device that may cause a collision. The TTC value can be calculated based on the motion state information (such as speed, acceleration) and position and distance information of the current driving device and the target driving device. For example, when the current driving device and the target driving device are traveling in the same direction, the collision prediction model will accurately calculate the TTC value according to the speed difference and the current distance between the two vehicles, combined with the respective acceleration changes. If the vehicle speed of the target driving device in front of the current driving device is slow and the distance is close, the TTC value will be small, indicating a high collision risk.

[0129] The collision prediction model also calculates the collision risk levels for each direction, such as in front of, to the side of, and behind the current driving device. Specifically, it can be determined by comparing the relative positions, speed differences, distances, and intersection situations of the driving trajectories with the target driving device in different directions. For example, if the distance between the current driving device and the driving device in front is relatively close and the speed difference is large, and there is an obvious trend of intersection in the driving trajectories, then the front collision risk level will be relatively high.

[0130] Furthermore, after obtaining the probability of a collision occurring, the severity of the collision, the predicted collision time, and the collision risk levels for each direction, the collision prediction model will further synthesize this information. Through complex algorithms, considering the mutual relationships and weights among various factors, it calculates the probability of an inevitable collision occurring for the current driving device.

[0131] For example, if the probability of a collision is very high, but the severity of the collision is relatively low, and although the collision risk level in a certain direction is high but there is still some room for avoidance, then the probability of an inevitable collision may not be very high; on the contrary, if the probability of a collision is high, the severity is high, and the collision risk levels in all directions are high with almost no room for avoidance, then the probability of an inevitable collision will be high. This probability is the result of a comprehensive assessment, which reflects the likelihood of an inevitable collision occurring for the driving device under the current circumstances.

[0132] Among them, the above-mentioned collision prediction model can be a machine learning model such as a random forest collision prediction model, an AdaBoost-based collision prediction model, etc., or a prediction model improved based on deep learning models such as convolutional neural networks and Transformers. There is no limitation here.

[0133] The above is the description of step S1022.

[0134] Step S1023: When the probability is greater than the preset collision threshold, it is determined that the current driving device is about to have a collision.

[0135] In practical applications, the preset collision threshold can be set according to specific scenarios. For example, 60%. When the calculated probability of an inevitable collision reaches the preset collision threshold, it will be determined that the current driving device is about to have a collision.

[0136] The above is the description of step S103.

[0137] Further, in some embodiments of the above step S104, if a collision is about to occur, a collision warning signal may be generated to trigger a corresponding warning mechanism. For example, warning information is sent from the AD domain to the vehicle CAN network. After the vehicle safety assurance (SA) control domain of the driving device receives the collision warning signal from the AD domain, pre-collision information can be obtained based on the perception data.

[0138] Specifically, the predicted collision direction can be obtained based on the collision risk level in each direction; then, the cockpit perception data, body perception data, and environmental perception data, as well as the target driving device, predicted collision direction, collision severity, and predicted collision time are used as pre-collision information.

[0139] Further, in some embodiments of the above step S105, the SA domain may use the collision warning signal provided by the AD domain as the decision basis for triggering the upload of pre-collision information. After receiving the collision warning signal sent by the AD domain, the pre-collision information is sent to the cloud platform, so that the cloud platform sends a collision confirmation message to the current driving device based on the pre-collision information and selectively activates emergency rescue based on the user's feedback information.

[0140] The above is an explanation of the method for obtaining pre-collision information applied to a driving device.

[0141] Further, the present application also provides an emergency rescue method applied to a cloud platform. Among them, the cloud platform may be a background system communicatively connected to multiple driving devices, such as the NIO Control Tower (NCT) system, which is not limited here.

[0142] Refer to the appendix Figure 2 , Figure 2 is a schematic diagram of the main step flow of the emergency rescue method according to an embodiment of the present application. As Figure 2 shown, the emergency rescue method in the embodiment of the present application mainly includes the following steps S201 to step S202.

[0143] Step S201: In response to the pre-collision information sent by the driving device, determine whether an actual collision signal of the driving device is received within a first preset time period;

[0144] In some embodiments, when an actual collision occurs to the driving device, an actual collision signal is generated and sent to the cloud platform.

[0145] Among them, the actual collision signal may be a collision detection signal of the airbag controller of the airbag control module (ACM).

[0146] Specifically, the ACM airbag controller detects whether a collision occurs in the driving device through various sensors such as acceleration sensors and pressure sensors. When a collision occurs in the driving device, these sensors detect abnormalities in physical quantities such as the instantaneous acceleration change and pressure change of the driving device. For example, when the acceleration or pressure change exceeds a preset threshold, the ACM airbag controller determines that a collision has occurred and generates a corresponding collision detection signal.

[0147] In addition, the basis for judging the actual collision signal may not only be the signal of the ACM airbag controller, but may also include feedback information from other driving device systems, such as the comprehensive judgment of the vehicle body structure deformation monitoring system and the safety system, which is not limited here.

[0148] Therefore, the cloud platform can, in response to the pre-collision information sent by the driving device, determine whether it receives the actual collision signal of the driving device within the first preset time period.

[0149] Among them, the first preset time period can be within a short time after the cloud platform receives the pre-collision information sent by the driving device, such as 0.5 to 1 second, which is not limited here.

[0150] Furthermore, if the cloud platform receives the actual collision signal of the driving device within the first preset time period, it executes step S202; otherwise, it returns to step S201.

[0151] Step S202: Send collision confirmation information to the driving device and selectively initiate emergency rescue based on the feedback information of the user.

[0152] In some embodiments, the cloud platform can send collision confirmation information to the driving device and determine whether it receives feedback information within the second preset time period to determine whether an actual collision has occurred.

[0153] Among them, the collision confirmation information can be presented to the user in various forms, such as a prompt on the in-vehicle display screen, a voice query, etc., and the user can respond by pressing a button, voice, etc.

[0154] The collision confirmation information can verify with the vehicle owner or passenger whether a real collision has occurred in the driving device. At the same time, the cloud platform sets a second preset time period (such as 10 seconds) and waits for the feedback information of the driving device within this time range.

[0155] Among them, the setting of the second preset time period is to balance the needs of timely response and ensuring information accuracy. If the second preset time period is too short, the driving device may not have time to give feedback; if the second preset time period is too long, the rescue opportunity will be delayed.

[0156] Further, in some embodiments of step S202, if the cloud platform receives feedback information within the second preset duration and determines that an actual collision has occurred, it continues to send a rescue confirmation message to the driving device to determine whether the user needs rescue.

[0157] Specifically, the cloud platform can send a rescue confirmation message to the driving device and determine whether feedback information is received within the third preset duration. If feedback information is received within the third preset duration and it is determined that the user needs rescue, emergency rescue is initiated; if feedback information is not received within the third preset duration, emergency rescue is initiated; if feedback information is received within the third preset duration and it is determined that the user does not need rescue, emergency rescue is not initiated.

[0158] Among them, the third preset duration can be the same as or different from the second preset duration, and no limitation is made here.

[0159] Specifically, if feedback information from the driving device is received within the third preset duration and it is determined that the user needs rescue, the cloud platform will immediately initiate emergency rescue and notify relevant rescue personnel to go to the scene. If no feedback information is received within the third preset duration, considering that there may be situations where the people in the cockpit are injured and unable to respond, the system will also initiate emergency rescue to ensure that the people can be rescued in a timely manner. If feedback information is received within the third preset duration and it is determined that the user does not need rescue, the cloud platform will not initiate emergency rescue, but will record this event for subsequent query and analysis.

[0160] Further, in some other embodiments of step S202, if the cloud platform does not receive feedback information within the second preset duration, it initiates emergency rescue.

[0161] Specifically, if the cloud platform does not receive feedback information from the driving device within the second preset time, there may be various situations, such as serious damage to the driving device resulting in communication failure, or the people in the cockpit being injured and unable to operate the device. To ensure the safety of the people in the cockpit, the cloud platform will directly initiate emergency rescue, such as automatically contacting rescue agencies (such as traffic police, ambulances, etc.) and providing information such as the location of the driving device and possible damage conditions to improve the efficiency of accident rescue.

[0162] The above is the description of the emergency rescue method applied to the cloud platform.

[0163] Refer to the appendix Figure 3 , Figure 3 is a schematic diagram of the main steps of the pre-collision information and emergency rescue method according to an embodiment of the present application.

[0164] Such as Figure 3As shown in the figure, the AD domain of the driving device obtains vehicle body perception data (including data such as the position information, driving trajectory, and driving speed of the current driving device) and environmental perception data (including data such as whether it is the target driving device, the position information, driving speed, driving direction, and the distance between the current driving device and the target driving device) through the perception sensor, and the DC domain obtains cockpit perception data (including data such as the number of occupants in the cockpit and their seating positions) through the perception sensor;

[0165] Further, based on the perception data, it is determined whether the current driving device is about to collide. If a collision is about to occur, the AD domain generates a collision warning signal and sends it to the SA domain, and obtains pre-collision information based on the perception data;

[0166] Further, after receiving the collision warning signal sent by the AD domain, the SA domain sends the pre-collision information to the cloud platform NCT. In response to the pre-collision information sent by the driving device, NCT determines whether it receives the actual collision signal of the driving device sent by the SA domain within the first preset duration, and sends a collision confirmation information to the driving device after receiving the actual collision signal, and selectively activates emergency rescue based on the user's feedback information.

[0167] Through the above implementation manner, it is possible to use the pre-collision signal of "inevitable collision" provided by the AD domain before the collision of the current driving device as a trigger source. Before the driving device collides, key MSD information such as the predicted collision direction, the number of occupants in the cockpit, the position information of the current driving device, the relative speed of the two vehicles at the time of collision, the target driving device, the severity of the collision, and the predicted collision time is uploaded to the cloud platform in advance to provide corresponding warning reminders, so that the cloud platform combines the real collision event after the warning reminder, and timely confirms with the car owner or passenger whether rescue is needed and activates the emergency response.

[0168] In this application, the pre-collision signal of the AD domain can be used to improve the accuracy of pre-collision prediction through algorithm optimization, so that the TTC value of the pre-collision signal is between the automatic emergency braking (AEB) brake signal and the real collision signal, and the pre-judgment accuracy is higher than that of the AEB brake signal, thereby improving the confidence level of the collision warning. Further, triggering the MSD information of the driving device to be sent to the cloud platform in advance according to this pre-collision signal with a relatively high confidence level can avoid the low-voltage power supply failure caused by the 12V small battery and the power supply harness being damaged in the collision, avoid the failure to upload key MSD information, and at the same time avoid the collision accident being missed from being reported to the cloud platform, improving the efficiency of accident rescue.

[0169] The above is a further description of the pre-collision information acquisition method and the emergency rescue method provided by this application.

[0170] It should be noted that although the steps are described in a specific order in the above embodiments, those skilled in the art can understand that in order to achieve the effects of this application, it is not necessary to execute different steps in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are within the protection scope of this application.

[0171] Those skilled in the art can understand that all or part of the processes in the method of implementing the above-mentioned embodiment of this application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc., that can carry the computer program code.

[0172] Furthermore, this application also provides an electronic device. Refer to the attached Figure 4 , Figure 4 is a schematic diagram of the main structure of an electronic device according to an embodiment of this application. As Figure 4 shown, the electronic device in the embodiment of this application mainly includes a processor 41 and a memory 42. The memory 42 can be configured to store a program for executing the pre-collision information acquisition method of the above-mentioned method embodiment. The processor 41 can be configured to execute the program in the memory 42, and the program includes but is not limited to the program for executing the pre-collision information acquisition method of the above-mentioned method embodiment. For the sake of convenience of description, only the parts related to the embodiment of this application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of this application.

[0173] In some possible implementation manners of this application, the electronic device may include multiple processors 41 and multiple memories 42. The program for executing the pre-collision information acquisition method of the above-mentioned method embodiment can be divided into multiple sub-programs, and each sub-program can be loaded and run by the processor 41 respectively to execute different steps of the pre-collision information acquisition method of the above-mentioned method embodiment. Specifically, each sub-program can be stored in different memories 42 respectively, and each processor 41 can be configured to execute the program in one or more memories 42 to jointly implement the pre-collision information acquisition method of the above-mentioned method embodiment, that is, each processor 41 respectively executes different steps of the pre-collision information acquisition method of the above-mentioned method embodiment to jointly implement the pre-collision information acquisition method of the above-mentioned method embodiment.

[0174] The above-mentioned multiple processors 41 may be processors deployed on the same device. For example, the above-mentioned electronic device may be a high-performance device composed of multiple processors, and the above-mentioned multiple processors 41 may be the processors configured on the high-performance device. In addition, the above-mentioned multiple processors 41 may also be processors deployed on different devices. For example, the above-mentioned electronic device may be a server cluster, and the above-mentioned multiple processors 41 may be the processors on different servers in the server cluster, or the above-mentioned computer device may be a driving device cluster, and the above-mentioned multiple processors 41 may be the processors on different driving devices in the driving device cluster.

[0175] Furthermore, the present application also provides a driving device. In an embodiment of a driving device according to the present application, the driving device may include a driving domain, a cockpit domain, a control domain, and the electronic device described in the above-mentioned electronic device embodiment. Among them, the driving domain and the cockpit domain include sensing sensors.

[0176] In some embodiments, the sensing sensors are configured to obtain sensing data of the current driving device.

[0177] Among them, the sensing sensors include cockpit sensors, vehicle body sensors, and environmental sensors, and the sensing data includes cockpit sensing data, vehicle body sensing data, and environmental sensing data.

[0178] In some embodiments, the driving domain is configured to generate a collision warning signal when a collision is about to occur to the current driving device, and send the collision warning signal to the control domain;

[0179] In some embodiments, the control domain is configured to obtain pre-collision information based on the sensing data, and send the pre-collision information to the cloud platform based on the collision warning signal.

[0180] Furthermore, the present application also provides a cloud platform. Refer to the attached Figure 5 , Figure 5 is a schematic diagram of the main structure of the cloud platform according to an embodiment of the present application. As Figure 5 shown, the cloud platform in the embodiment of the present application mainly includes a processor 51 and a memory 52. The memory 52 may be configured to store a program for executing the emergency rescue method in the above-mentioned method embodiment. The processor 51 may be configured to execute the program in the memory 52, and the program includes but is not limited to the program for executing the emergency rescue method in the above-mentioned method embodiment. For the sake of convenience of description, only the parts related to the embodiment of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of the present application.

[0181] In some possible embodiments of the present application, the cloud platform may include a plurality of processors 51 and a plurality of memories 52. The program for executing the emergency rescue method of the above method embodiments can be divided into multiple sub-programs, and each sub-program can be loaded and run by the processor 51 respectively to execute different steps of the emergency rescue method of the above method embodiments. Specifically, each sub-program can be stored in a different memory 52 respectively, and each processor 51 can be configured to execute the program in one or more memories 52 to jointly implement the emergency rescue method of the above method embodiments, that is, each processor 51 respectively executes different steps of the emergency rescue method of the above method embodiments to jointly implement the emergency rescue method of the above method embodiments.

[0182] The above-mentioned plurality of processors 51 can be processors deployed on the same device. For example, the above-mentioned cloud platform can be a high-performance device composed of a plurality of processors, and the above-mentioned plurality of processors 51 can be the processors configured on the high-performance device. In addition, the above-mentioned plurality of processors 51 can also be processors deployed on different devices. For example, the above-mentioned cloud platform can be a server cluster, and the above-mentioned plurality of processors 51 can be the processors on different servers in the server cluster.

[0183] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium can be configured to store a program for executing the pre-collision information acquisition method or the emergency rescue method of the above method embodiments, and this program can be loaded and run by the processor to implement the above pre-collision information acquisition method or the emergency rescue method. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0184] It should be noted that the relevant user personal information that may be involved in the embodiments of the present application is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, for reasonable purposes based on business scenarios, and processes the personal information actively provided by users during the use of products / services or generated due to the use of products / services, as well as the personal information obtained with the authorization of users.

[0185] The user personal information processed by the present application will vary according to the specific product / service scenarios, and it is necessary to be subject to the specific scenarios of users using products / services. It may involve the user's account information, device information, driving information, vehicle information, or other relevant information. The present application will treat the user's personal information and its processing with a high degree of diligence.

[0186] This application attaches great importance to the security of users' personal information and has taken security protection measures that meet industry standards and are reasonable and feasible to protect users' information, preventing personal information from being accessed, publicly disclosed, used, modified, damaged or lost without authorization.

[0187] So far, the technical solution of this application has been described in conjunction with an embodiment shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of this application is obviously not limited to these specific embodiments. Without departing from the principle of this application, those skilled in the art can make equivalent changes or substitutions to relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of this application.

Claims

1. A pre-collision information acquisition method, applied to a driving device, characterized in that, The driving device is communicatively connected to the cloud platform; the method includes: Obtain the perception data of the current driving device; the perception data includes cockpit perception data, vehicle body perception data, and environmental perception data; Based on the perception data, determine whether the current driving device is about to collide; If a collision is about to occur, generate a collision warning signal and obtain pre-collision information based on the perception data; Send the pre-collision information to the cloud platform so that the cloud platform sends a collision confirmation information to the current driving device based on the pre-collision information and selectively activates emergency rescue based on the user's feedback information.

2. The pre-collision information acquisition method according to claim 1, wherein The cockpit perception data includes at least one of the number of occupants in the cockpit and the seating position; The vehicle body perception data includes at least one of the position information, driving trajectory, and driving speed of the current driving device; The environmental perception data includes at least one of the position information, driving speed, driving direction of a target driving device existing within a preset range around the current driving device, and the distance between the target driving device and the current driving device.

3. The pre-collision information acquisition method according to claim 2, wherein The determining whether the current driving device is about to collide based on the perception data includes: Obtain the predicted driving trajectories of the current driving device and the target driving device based on the perception data; Based on the perception data, the predicted driving trajectories of the current driving device and the target driving device, obtain the probability of an inevitable collision of the current driving device; When the probability is greater than a preset collision threshold, determine that the current driving device is about to collide.

4. The pre-collision information acquisition method according to claim 3, characterized in that, The obtaining the probability of an inevitable collision of the current driving device based on the perception data, the predicted driving trajectories of the current driving device and the target driving device includes: Input the perception data, the predicted driving trajectories of the current driving device and the target driving device into a collision prediction model to obtain the possibility of collision, collision severity, predicted collision time, and collision risk level in each direction between the current driving device and the target driving device; Based on the possibility of collision, collision severity, predicted collision time, and collision risk level in each direction, obtain the probability of an inevitable collision of the current driving device.

5. The pre-collision information acquisition method according to claim 4, wherein The obtaining pre-collision information based on the perception data includes: Obtain the predicted collision direction based on the collision risk level in each direction; Use the cockpit perception data, vehicle body perception data, and environmental perception data, as well as the target driving device, the predicted collision direction, the collision severity, and the predicted collision time as the pre-collision information.

6. The pre-collision information acquisition method according to claim 3, wherein The sending the pre-collision information to the cloud platform includes: Based on the collision warning signal, send the pre-collision information to the cloud platform.

7. An emergency rescue method, applied to a cloud platform, characterized in that, The cloud platform is communicatively connected to multiple driving devices; the method includes: In response to the pre-collision information sent by a driving device, determine whether an actual collision signal of the driving device is received within a first preset time period; If so, send a collision confirmation information to the driving device and selectively activate emergency rescue based on the user's feedback information.

8. The emergency rescue method according to claim 7, characterized in that, Sending the collision confirmation information to the driving device and selectively initiating emergency rescue based on the feedback information of the user includes: Sending the collision confirmation information to the driving device and determining whether the feedback information is received within a second preset duration to determine whether an actual collision has occurred; If the feedback information is received within the second preset duration and it is determined that an actual collision has occurred, continue to send a rescue confirmation information to the driving device to determine whether the user needs rescue; If the feedback information is not received within the second preset duration, initiate the emergency rescue.

9. The emergency rescue method according to claim 8, characterized in that, The continuing to send the rescue confirmation information to the driving device to determine whether the user needs rescue includes: Sending the rescue confirmation information to the driving device and determining whether the feedback information is received within a third preset duration; If the feedback information is received within the third preset duration and it is determined that the user needs rescue, initiate the emergency rescue; If the feedback information is not received within the third preset duration, initiate the emergency rescue; If the feedback information is received within the third preset duration and it is determined that the user does not need rescue, do not initiate the emergency rescue.

10. An electronic device, comprising a processor and a memory, the memory being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to execute the pre-collision information acquisition method according to any one of claims 1 to 6.

Images