Safety control method for vehicle, electronic equipment and storage medium

Abstract

The invention provides a safety control method for a vehicle, electronic equipment and a storage medium, the safety control method is applied to an object vehicle, the object vehicle comprises a main driving system and a standby driving system, and the safety control method comprises the following steps: controlling an acquisition module to acquire environment data in the driving process of the object vehicle, and transmitting the environment data to a monitoring module, the monitoring module judges whether the object vehicle is in an early warning state or not according to the environment data; if the object vehicle is in the early warning state, the main driving system is controlled to enter a pre-switching mode; the control monitoring module monitors the running condition of the vehicle and judges whether the main driving system breaks down or not; if yes, it is judged that the control system of the vehicle is switched from the main driving system to the standby driving system. The technical problems that in the prior art, due to the fact that the decision-making ability of a double-driving system is insufficient, when a main driving system is switched to a standby driving system, response time is long, and the vehicle is prone to being out of control in the period are solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a safety control method, electronic device, and storage medium for a vehicle. Background Art

[0002] With the rapid development of autonomous driving technology and advanced driver assistance systems, vehicle safety and reliability have become key industry concerns. Modern vehicles are typically equipped with multiple sensors to perceive their surroundings and implement autonomous or assisted driving functions through complex decision-making algorithms. To further enhance the fault tolerance of autonomous driving, vehicles are equipped with dual-pilot systems, allowing for a backup system to be used in the event of a failure in the primary driver's system.

[0003] However, there is at least one of the following problems in the related art: the decision-making ability of the dual-driving system in the existing technology is insufficient, resulting in a long reaction time when the main driving system switches to the backup driving system, during which the vehicle is prone to loss of control. Summary of the Invention

[0004] The technical problem solved by the present invention is that the decision-making ability of the dual-driving system in the existing technology is insufficient, resulting in a long reaction time when the main driving system switches to the backup driving system, during which the vehicle is prone to loss of control.

[0005] To solve the above problems, the present invention provides a safety control method for a vehicle, which is applied to a target vehicle, wherein the target vehicle includes a main driving system and a backup driving system. The safety control method includes: controlling an acquisition module of the target vehicle to collect environmental data during the driving process of the target vehicle, and transmitting the environmental data to a monitoring module, so that the monitoring module determines whether the target vehicle is in a warning state based on the environmental data; if the target vehicle is in the warning state, controlling the main driving system to enter a pre-switching mode to prepare for switching from the main driving system to the co-driving system; controlling the monitoring module to monitor the operating status of the target vehicle and determine whether the main driving system has a fault; if so, controlling the control system of the vehicle to switch from the main driving system to the backup driving system.

[0006] Compared with the existing technology, the technical effect achieved by adopting this technical solution is as follows: the environment in which the target vehicle is located is analyzed through the vehicle's surrounding environment data, and then it is determined whether the target vehicle is in a warning state that is prone to failure, thereby activating the pre-switching mode of the main driving system to prepare for possible system switching and reduce reaction time; when the main driving system fails, the control system of the target vehicle is switched from the main driving system to the backup driving system, thereby ensuring the continuity of the target vehicle's driving in the failure scenario.

[0007] In one embodiment of the present invention, the monitoring module determines whether the target vehicle is in a warning state according to the environmental data, including: calculating the uncertainty parameter σ and the dynamic uncertainty threshold σ of the main driving system according to the environmental data th , determine whether the uncertainty parameter σ is greater than the dynamic uncertainty threshold σ th If so, the target vehicle is determined to be in a warning state; if not, the target vehicle is determined to be controlled by the main driving system.

[0008] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: by calculating the uncertainty parameter σ and the dynamic uncertainty threshold σ th , quantifies the operating risk of the main driving system; when the operating risk reaches a certain level, the pre-switching mode of the main driving system is activated to reduce unnecessary system operations, lower the misjudgment rate, and thus optimize the system's operating efficiency.

[0009] In one embodiment of the present invention, the environmental data includes traffic density D, vehicle speed change rate V, weather conditions T, and road characteristics W; the uncertainty parameter σ and dynamic uncertainty threshold σ of the main driving system are calculated based on the environmental data. th , including: calculating the environmental complexity C based on traffic density D, vehicle speed change rate V, weather conditions T and road characteristics W; calculating the dynamic uncertainty threshold σ based on the environmental complexity C th , and follow the following formula 3: Formula 3: ; Among them, σ base is the baseline uncertainty threshold, which is used to replace the dynamic uncertainty threshold σ in simple scenarios th Use, P human is the probability that the driver takes over the target vehicle, σ total is the total uncertainty of multimodal fusion, k1, k2 and α are proportional coefficients.

[0010] Compared with the existing technology, the technical effect achieved by adopting this technical solution is as follows: by calculating the environmental complexity, comprehensively considering the environmental characteristics of the target vehicle, and adaptively adjusting the operating risks of the target vehicle when facing different environmental characteristics, it not only ensures the efficiency of the main driving system during normal operation, but also enhances the safety of the target vehicle when facing abnormal situations.

[0011] In one embodiment of the present invention, the main driving system adopts a first decision algorithm to handle driving tasks under normal circumstances; the backup driving system adopts a second decision algorithm to handle driving tasks under emergency circumstances; wherein the predictability of the second decision algorithm is higher than the predictability of the first decision algorithm.

[0012] Compared with the existing technology, the technical effects achieved by adopting this technical solution are as follows: by adopting the first decision algorithm and the second decision algorithm for processing different tasks in the main driving system and the backup driving system, the overlap between the main driving system and the backup driving system is reduced, and the possibility of the main driving system and the backup driving system failing due to the same reason is reduced; in addition, by improving the predictability of the second decision algorithm, the safety of the target vehicle when controlled by the backup driving system is improved.

[0013] In one example of the present invention, the acquisition module includes a laser radar, a camera, a millimeter-wave radar and an ultrasonic radar; the acquisition module of the target vehicle is controlled to collect environmental data during the driving process of the target vehicle, including: controlling the laser radar to collect point cloud data; controlling the camera to collect image data; controlling the millimeter-wave radar to collect target detection data; and controlling the ultrasonic radar to collect near-field detection data.

[0014] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: by collecting multiple data through multiple sensors, the target vehicle's perception of the surrounding environment is enriched, and multiple sensors working together can make up for the shortcomings of specific sensors under specific weather conditions, thereby improving the integrity and reliability of environmental data.

[0015] In one example of the present invention, an acquisition module that controls a target vehicle collects environmental data during the driving process of the target vehicle, including: calculating the environmental data through a Kalman filter algorithm based on point cloud data, image data, target detection data, and near-field detection data; wherein, the weight ratio of the point cloud data, image data, target detection data, and near-field detection data in the Kalman filter algorithm is determined by the vehicle position, speed, and obstacle information of the target vehicle.

[0016] Compared with the existing technology, the technical effects achieved by adopting this technical solution are: by fusing multimodal data through the Kalman filter algorithm, sensor noise interference is reduced, and the accuracy and consistency of environmental data are improved; in addition, the weight of each sensor data is dynamically adjusted based on vehicle position, speed and obstacle information, optimizing the applicability of data processing in different scenarios.

[0017] In one embodiment of the present invention, the environmental data is calculated by the Kalman filter algorithm based on the point cloud data, image data, target detection data and near field detection data, including: initializing the state vector x k , the state vector x k It is used to describe the speed and position coordinates of the target vehicle and the number and position coordinates of obstacles in the environment; the state transfer function f(·) is used to perform the state prediction step to obtain the predicted state vector and the forecast error covariance matrix ; Perform the update step and calculate the observation value z of the acquisition module s according to the acquisition module s s and the corresponding observation matrix H s , according to the observed value z s and the observation matrix H s Calculate the Kalman gain ; Calculate the confidence w of the acquisition module s s , and follow the following formula: ; in, is the uncertainty measure of the acquisition module s, is the reference uncertainty level, Is the sensitivity parameter, used to adjust the steepness of the confidence curve; according to the confidence w of the acquisition module s s Kalman gain Perform weighted averaging to obtain the adaptive Kalman gain ; According to the adaptive Kalman gain , predicted state vector and the forecast error covariance matrix Calculate the updated state vector and update the error covariance matrix .

[0018] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: by introducing an adaptive weight adjustment mechanism based on the uncertainty of the acquisition module, the main driving system can automatically adjust the contribution ratio of each sensor in different driving environments, thereby improving the accuracy and robustness of the fusion results.

[0019] In one embodiment of the present invention, the target vehicle includes a critical module and a non-critical module, and the priority of computing power allocation of the target vehicle to the critical module is higher than that to the critical module.

[0020] Compared with existing technologies, the technical effects achieved by adopting this technical solution are: computing power is allocated first to key modules to ensure the stable operation of core functions under high-load scenarios; non-critical modules adopt time-sharing multiplexing to optimize computing resource utilization and reduce system power consumption and hardware costs.

[0021] On the other hand, the present invention also provides an electronic device, which includes: a processor, a memory, and a program or instruction stored in the memory and runnable on the processor, wherein when the program or instruction is executed by the processor, a security control method as in any of the above examples is implemented.

[0022] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: it can achieve the technical effect corresponding to any of the above examples, which will not be repeated here.

[0023] On the other hand, the present invention also provides a storage medium storing a program or instruction, which implements the security control method as described in any of the above examples when the program or instruction is executed by a processor.

[0024] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: it can achieve the technical effect corresponding to any of the above examples, which will not be repeated here.

[0025] After adopting the technical solution of the present invention, the following technical effects can be achieved: (1) Analyze the environment of the target vehicle through the vehicle's surrounding environment data, and then determine whether the target vehicle is in a warning state that is prone to failure, thereby activating the pre-switching mode of the main driving system to prepare for the possible system switch and reduce the reaction time; when the main driving system fails, the control system of the target vehicle is switched from the main driving system to the backup driving system, thereby ensuring the continuity of the target vehicle's driving in the failure scenario; (2) By calculating the uncertainty parameter σ and the dynamic uncertainty threshold σ th , quantifying the operational risk of the main driving system; when the operational risk reaches a certain level, the pre-switching mode of the main driving system is activated, reducing unnecessary system operations, lowering the misjudgment rate, and thus optimizing the system's operational efficiency; (3) By calculating the environmental complexity, the environmental characteristics of the target vehicle are comprehensively considered, and the operating risks of the target vehicle when facing different environmental characteristics are adaptively adjusted. This not only ensures the efficiency of the main driving system during normal operation, but also enhances the safety of the target vehicle when facing abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings to be used in describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts. Figure 1 A flowchart of a vehicle safety control method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] See also Figure 1, which is a flow chart of a vehicle safety control method provided by an embodiment of the present invention. The present invention provides a vehicle safety control method, which is applied to a target vehicle, the target vehicle including a primary driving system and a backup driving system, and includes: S100: controlling a collection module of the target vehicle to collect environmental data during the driving process of the target vehicle, and transmitting the environmental data to a monitoring module, so that the monitoring module determines whether the target vehicle is in a warning state based on the environmental data; S200: If the target vehicle is in a warning state, controlling the main driving system to enter a pre-switching mode for preparing to switch from the main driving system to the co-pilot system; S300: The control monitoring module monitors the operating status of the target vehicle and determines whether a fault occurs in the main driving system; S400: If yes, the control system of the vehicle is switched from the main driving system to the backup driving system.

[0029] The environment of the target vehicle is analyzed by using the vehicle's surrounding environment data to determine whether the target vehicle is in a warning state that is prone to failure, thereby activating the pre-switching mode of the main driving system to prepare for possible system switching and reduce reaction time. When the main driving system fails, the control system of the target vehicle is switched from the main driving system to the backup driving system, thereby ensuring the continuity and safety of the target vehicle in the failure scenario.

[0030] Preferably, when the target vehicle is in adverse conditions such as dangerous weather or complex road conditions, the main driving system on the target vehicle is prone to malfunction. When the adverse conditions accumulate to a certain extent, an alarm can be issued to determine that the target vehicle is in a warning state.

[0031] Preferably, the pre-switching mode indicates that the subject vehicle is in a state of being ready to switch from the primary driving system to the backup driving system, so as to reduce a reaction time required for switching when the subject vehicle fails.

[0032] Preferably, the monitoring module is disposed inside the target vehicle for monitoring the operating conditions inside the target vehicle, and the collection module is disposed around the target vehicle for collecting environmental data around the target vehicle.

[0033] Preferably, the subject vehicle described in the present invention is an autonomous driving car with at least two driving systems, and is normally driven automatically by the subject vehicle.

[0034] Furthermore, S100 includes: S110: Calculate the uncertainty parameter σ and dynamic uncertainty threshold σ of the main driving system based on the environmental data th , determine whether the uncertainty parameter σ is greater than the dynamic uncertainty threshold σth ; S120: If yes, then determine that the target vehicle is in a warning state; S130: If not, it is determined that the target vehicle is controlled by the main driving system.

[0035] The prior art discloses a method and system for controlling the operation of an unmanned vehicle, wherein the vehicle's driving is mainly controlled by a main driving system. If there is a problem with the vehicle's driving status, the system switches to a backup driving system. When judging whether the main driving system is operating normally, the system mainly collects status signals emitted by the main driving system at predetermined time intervals to determine whether they are normal, or whether there is a fault in the software or hardware inside the vehicle. Both of these judgment methods require a certain reaction time to be reserved. However, the reaction time that can actually be reserved when a fault occurs is very short, and the reaction time needs to be further shortened.

[0036] By calculating the uncertainty parameter σ and the dynamic uncertainty threshold σ th , which can quantify the operating risk of the main driving system; when the operating risk of the vehicle accumulates to a certain level, the pre-switching mode of the main driving system will be activated, and when problems occur in the main driving system, the response space of the monitoring module will be reduced.

[0037] Preferably, the main driving system adopts an end-to-end autonomous driving algorithm based on a deep neural network (DNN), and calculates the uncertainty parameter σ and the dynamic uncertainty threshold σ based on the uncertainty quantification method. th ; The main driving system can be regarded as a complex mapping function f by building a model DNN , so that the acquisition module input X is mapped to the control output Y and follows the following formula 1: Formula 1: ; Among them, θ represents the deep neural network parameters of the model. Furthermore, the uncertainty σ of the prediction results is estimated by Bayesian deep learning technology. 2 , so that the output of the model changes from a single value to a normal distribution and follows the following formula 2: Formula 2: ; When the uncertainty parameter σ exceeds the dynamic uncertainty threshold σ th We believe that the main driving system may face the risk of failure.

[0038] Furthermore, the environmental data includes traffic density D, vehicle speed change rate V, weather conditions T, and road characteristics W; S110 includes: S111: Calculate the environment complexity C based on the traffic density D, the vehicle speed change rate V, the weather conditions T, and the road characteristics W; S112: Calculate the dynamic uncertainty threshold σ of the primary driving system based on the environmental complexity C th , and follow the following formula 3: Formula 3: ; Among them, σ base is the baseline uncertainty threshold, which is used to replace the dynamic uncertainty threshold σ in simple scenarios th Use, P human is the probability that the driver takes over the target vehicle, σ total is the total uncertainty of sensor multimodal fusion, k1, k2 and α are proportional coefficients.

[0039] By calculating the environmental complexity and comprehensively considering the environmental characteristics of the target vehicle, the operating risks of the target vehicle when facing different environmental characteristics are adaptively adjusted. This not only ensures the efficiency of the main driving system during normal operation, but also enhances the safety of the target vehicle when facing abnormal situations.

[0040] Preferably, when calculating the environmental complexity C based on the traffic density D, the vehicle speed change rate V, the weather conditions T, and the road characteristics W, the following formula 4 is followed: Formula 4: ; Preferably, w1, w2, w3 and w4 are weight coefficients.

[0041] Preferably, the three proportional coefficients k1, k2 and α are used to adjust the environmental complexity, total uncertainty and driver behavior for the dynamic uncertainty threshold σ th impact.

[0042] Specifically, the present invention provides the uncertainty parameter σ in the real scene is greater than the dynamic uncertainty threshold σ th Example 1. The specific scenario is that the target vehicle is driving on a mountain highway in foggy weather and encounters a sudden traffic jam. The specific values of each parameter in this scenario can be exemplified in Table 1.

[0043] Table 1 Parameter values of the target vehicle when driving in the example 1 scenario Specifically, in Example 1, the traffic density D is 0.92, indicating extremely high density (the traffic density D ranges from 0 to 1, with 1 indicating complete congestion), the vehicle speed change rate V is 0.85 (indicating frequent sudden braking, with a value range of 0 to 1, with 1 indicating drastic changes), the weather condition T is 0.95 (indicating dense fog, visibility <50 meters), and the road feature W is 0.88 (indicating continuous steep slopes and sharp turns).

[0044] Specifically, in the first example scenario, the specific method of obtaining the model output is: through Bayesian deep learning (Monte Carlo Dropout sampling 200 times), it can be measured that Y = 0.18 rad and the uncertainty parameter σ = 0.26 rad.

[0045] Specifically, by substituting traffic density D, vehicle speed change rate V, weather conditions T, and road characteristics W into Formula 4, we can obtain the environmental complexity C=0.9075; Specifically, the environmental complexity C, the benchmark uncertainty threshold σ base , driver takeover probability P human And the total uncertainty σ of sensor multimodal fusion total Substituting into formula 3, we can get the dynamic uncertainty threshold σ th is 0.0298rad; 0.26rad>0.0298rad, the uncertainty parameter σ is greater than the dynamic uncertainty threshold σ th , it is determined that the target vehicle is in a warning state.

[0046] Specifically, the meaning and impact of each factor in the example scenario are as follows: (1-k1·C) is the environmental complexity term, with a value of 0.36475. Due to the high complexity of the environment, the dynamic uncertainty threshold σ th is compressed to the reference uncertainty threshold σ base 36.5%; (1+α·P human ) is the driver takeover item, with a value of 1.125, which is affected by the possibility of driver takeover and is the dynamic uncertainty threshold σ th Provides a small cushion; exp(-k2·σ total ) is the multimodal fusion term, and its value is about 0.6042. Due to the interference of dense fog, the uncertainty of the multimodal fusion term of the sensor is high, which further suppresses the dynamic uncertainty threshold σ th .

[0047] Preferably, when it is determined that the target vehicle is in the warning state, the sound and light alarm on the target vehicle is activated to prompt the driver to take over, and the speed of the target vehicle is limited to 40 km / h.

[0048] Furthermore, the main driving system adopts a first decision algorithm to handle driving tasks under normal circumstances; the backup driving system adopts a second decision algorithm to handle driving tasks under emergency circumstances; wherein the second decision algorithm has higher predictability than the first decision algorithm.

[0049] By using the first decision algorithm and the second decision algorithm to handle different tasks for the primary driving system and the backup driving system, the overlap between the primary driving system and the backup driving system is reduced, and the possibility of the primary driving system and the backup driving system failing due to the same reason is reduced; in addition, by improving the predictability of the second decision algorithm, the safety of the target vehicle when controlled by the backup driving system is improved.

[0050] Preferably, the backup driving system adopts a traditional rule-based decision-making algorithm, which usually makes decisions according to a set of predefined logical rules R. Assuming that these rules are deterministic, there is Formula 5: Formula 5: ; The function g(·) is composed of a series of conditional statements based on traffic regulations and safety standards, such as the MPC (Model Predictive Control) control algorithm. Because this method does not involve complex parameter optimization, its behavior is more predictable and easy to understand.

[0051] Furthermore, the acquisition module includes a laser radar, a camera, a millimeter-wave radar and an ultrasonic radar; the acquisition module of the target vehicle is controlled to collect environmental data during the driving process of the target vehicle, including: controlling the laser radar to collect point cloud data; controlling the camera to collect image data; controlling the millimeter-wave radar to collect target detection data; and controlling the ultrasonic radar to collect near-field detection data.

[0052] By collecting a variety of data through multiple sensors, the target vehicle's ability to perceive the surrounding environment is enriched. The coordinated operation of multiple sensors can make up for the shortcomings of specific sensors in specific weather conditions, thereby improving the integrity and reliability of environmental data.

[0053] Preferably, the laser radar model is Velodyne VLP-16, with a horizontal field of view of 360 degrees and a vertical field of view of 30 degrees; the camera is a 1080P high-definition camera, the millimeter wave radar is the Continental ARS408 model with an operating frequency of 77GHz; the ultrasonic radar is the Continental Automotive 3TX model.

[0054] Furthermore, the acquisition module of the control object vehicle collects environmental data during the driving process of the object vehicle, including: calculating the environmental data through the Kalman filter algorithm based on the point cloud data, image data, target detection data and near-field detection data; wherein, the weight ratio of the point cloud data, image data, target detection data and near-field detection data in the Kalman filter algorithm is determined by the vehicle position, speed and obstacle information of the object vehicle.

[0055] By fusing multimodal data through the Kalman filter algorithm, sensor noise interference is reduced and the accuracy and consistency of environmental data are improved. In addition, the weight of each sensor data is dynamically adjusted based on vehicle position, speed and obstacle information to optimize the applicability of data processing in different scenarios.

[0056] Furthermore, the environmental data is calculated using the Kalman filter algorithm based on the point cloud data, image data, target detection data, and near-field detection data, including: initializing the state vector x k , the state vector x k It is used to describe the speed and position coordinates of the target vehicle and the number and position coordinates of obstacles in the environment, and follows the following formula 6: Formula 6: ; Among them, p x , p y represents the position of the vehicle on the two-dimensional plane; v x , v y Represents the velocity component of the vehicle; o xi , o yi represents the position coordinates of the i-th obstacle; n is the number of obstacles in the environment, and T represents the transpose of the matrix; the state transfer function f(·) is used to perform the state prediction step to obtain the predicted state vector and the forecast error covariance matrix , and follow the following formulas 7-8: Formula 7: ; Formula 8: ; in, is the predicted state vector; is the predicted error covariance matrix; and is the prior state estimate, expressed as a predicted value, without integrating the current measurement; and is the posterior state estimate, expressed as an updated value that incorporates the current measurement; f(·) refers to the state transfer function; is the control input; is the Jacobian matrix; refers to the process noise covariance matrix; k represents the current moment, and k-1 represents the previous moment; Perform the update step and calculate the observation value z of the acquisition module s according to the acquisition module s s and the corresponding observation matrix H s , according to the observed value z s and the observation matrix H s Calculate the Kalman gain , and then according to the Kalman gain , predicted state vector and the forecast error covariance matrix Calculate the updated state vector and update the error covariance matrix , and follow the following formulas 9-13: Formula 9: ; Formula 10: ; Formula 11: ; Formula 12: ; Formula 13: ; in, is the observation noise covariance matrix, is the Kalman gain, h s (·) is the observation function, is the measurement noise covariance matrix; calculate the confidence w of the acquisition module s s , and follow the following formula 14: Formula 14: ; in, is the uncertainty measure of the acquisition module s, is the reference uncertainty level, is a sensitivity parameter used to adjust the steepness of the confidence curve; Among them, in the update step, according to the confidence w of the acquisition module s s Kalman gain Perform weighted averaging to calculate the adaptive Kalman gain , according to the adaptive Kalman gain , predicted state vector and the forecast error covariance matrix Calculate the updated state vector and update the error covariance matrix And follow the following formulas 15-17: Formula 15: ; Formula 16: ; Formula 17: ; Where z is the total number of observations , h(·) is the comprehensive observation function.

[0057] By introducing an adaptive weight adjustment mechanism based on the uncertainty of the acquisition module, the main driving system can automatically adjust the contribution ratio of each sensor in different driving environments, thereby improving the accuracy and robustness of the fusion results.

[0058] Preferably, in the acquisition module s, lider represents a laser radar; camer represents a camera; rader represents a millimeter-wave radar; and ultrasonic represents an ultrasonic radar.

[0059] Furthermore, the target vehicle includes critical modules and non-critical modules, and the priority of computing power allocation for the target vehicle to the critical modules is higher than that for the non-critical modules.

[0060] Prioritize computing power allocation for key modules to ensure stable operation of core functions under high-load scenarios; non-critical modules adopt time-sharing multiplexing to optimize computing resource utilization and reduce system power consumption and hardware costs.

[0061] Preferably, the key modules include an environmental perception module, a decision-making and planning module, and a control execution module, and the non-key modules include a human-computer interaction module, an in-vehicle multimedia module, etc.

[0062] Preferably, the key modules run on an eight-core ARM processor with a main frequency of 3.0GHz to process sensor data and make decision instructions in real time; the non-critical modules run on a quad-core ARM processor with a main frequency of 2.0GHz and use a priority-based preemptive scheduling algorithm for time-sharing multiplexing.

[0063] On the other hand, the present invention also provides an electronic device, which includes: a processor, a memory, and a program or instruction stored in the memory and runnable on the processor, wherein when the program or instruction is executed by the processor, a security control method as in any of the above examples is implemented.

[0064] The technical effects corresponding to any of the above examples can be achieved and will not be repeated here.

[0065] On the other hand, the present invention also provides a storage medium storing a program or instruction, which implements the security control method as described in any of the above examples when the program or instruction is executed by a processor.

[0066] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: it can achieve the technical effect corresponding to any of the above examples, which will not be repeated here.

[0067] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A safety control method for a vehicle, characterized in that: The safety control method is applied to a target vehicle, the target vehicle including a primary driving system and a backup driving system, and the safety control method includes: Controlling a collection module of the target vehicle to collect environmental data during the driving process of the target vehicle, and transmitting the environmental data to a monitoring module, so that the monitoring module determines whether the target vehicle is in a warning state according to the environmental data; If the target vehicle is in a warning state, controlling the main driving system to enter a pre-switching mode for preparing to switch from the main driving system to the co-pilot system; controlling the monitoring module to monitor the operating status of the target vehicle and determine whether a failure occurs in the main driving system; If so, the control system for controlling the vehicle is switched from the main driving system to the backup driving system.

2. The safety control method according to claim 1, characterized in that: The step of enabling the monitoring module to determine whether the target vehicle is in a warning state according to the environmental data includes: Calculate the uncertainty parameter σ and dynamic uncertainty threshold σ of the main driving system according to the environmental data th , determine whether the uncertainty parameter σ is greater than the dynamic uncertainty threshold σ th ; If so, it is determined that the target vehicle is in a warning state; If not, it is determined that the target vehicle is controlled by the main driving system.

3. The safety control method according to claim 2, characterized in that: The environmental data includes traffic density D, vehicle speed change rate V, weather conditions T and road characteristics W; The uncertainty parameter σ and the dynamic uncertainty threshold σ of the main driving system are calculated according to the environmental data th ,include: Calculating the environment complexity C based on the traffic density D, the vehicle speed change rate V, the weather conditions T and the road characteristics W; Calculate the dynamic uncertainty threshold σ according to the environmental complexity C th , and follow the following formula 3: Formula 3: ; Among them, σ base is the baseline uncertainty threshold, which is used to replace the dynamic uncertainty threshold σ in simple scenarios th Use, P human is the probability that the driver takes over the target vehicle, σ total is the total uncertainty of multimodal fusion, k1, k2 and α are proportional coefficients.

4. The safety control method according to claim 1, characterized in that: The main driving system adopts a first decision-making algorithm to handle driving tasks under normal circumstances; The backup driving system adopts a second decision algorithm for handling driving tasks in emergency situations; The predictability of the second decision algorithm is higher than that of the first decision algorithm.

5. The safety control method according to claim 1, characterized in that: The acquisition module includes a laser radar, a camera, a millimeter-wave radar and an ultrasonic radar; The collecting module for controlling the target vehicle to collect environmental data during the driving process of the target vehicle includes: Controlling the laser radar to collect point cloud data; Controlling the camera to collect image data; Controlling the millimeter-wave radar to collect target detection data; Control the ultrasonic radar to collect near-field detection data.

6. The safety control method according to claim 5, characterized in that: The collecting module for controlling the target vehicle to collect environmental data during the driving process of the target vehicle includes: Calculating environmental data using a Kalman filter algorithm based on the point cloud data, the image data, the target detection data, and the near-field detection data; The weights of the point cloud data, the image data, the target detection data, and the near-field detection data in the Kalman filter algorithm are determined by the vehicle position, speed, and obstacle information of the object vehicle.

7. The safety control method according to claim 6, characterized in that: The calculating of environmental data by a Kalman filter algorithm based on the point cloud data, the image data, the target detection data, and the near-field detection data includes: Initialize the state vector x k , the state vector x k Used to describe the speed and position coordinates of the target vehicle and the number and position coordinates of obstacles in the environment; Use the state transfer function f(·) to perform the state prediction step and obtain the predicted state vector and the forecast error covariance matrix ; Perform the update step, calculate the observation value z of the acquisition module s according to the acquisition module s s and the corresponding observation matrix H s , according to the observed value z s and the observation matrix H s Calculate the Kalman gain ; Calculate the confidence w of the acquisition module s s , and follow the following formula: ； in, is the uncertainty measure of the acquisition module s, is the reference uncertainty level, is a sensitivity parameter used to adjust the steepness of the confidence curve; According to the confidence w of the acquisition module s s The Kalman gain Perform weighted averaging to obtain the adaptive Kalman gain ; According to the adaptive Kalman gain , the predicted state vector and the forecast error covariance matrix Calculate the updated state vector and update the error covariance matrix .

8. The safety control method according to claim 1, characterized in that: The target vehicle includes a critical module and a non-critical module, and the priority of computing power allocation of the target vehicle to the critical module is higher than that to the critical module.

9. An electronic device, characterized in that: The electronic device includes: a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the security control method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the security control method according to any one of claims 1 to 8 are implemented.

Images