Elastic event triggering method for network attack of intelligent automobile control system
By employing a flexible event triggering method and utilizing modules and adaptive threshold functions in the intelligent vehicle control system, the problem of network attacks on the intelligent vehicle control system under limited communication resources is solved, achieving resource conservation and enhanced security.
Patent Information
- Application Number
- CN202510904558.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-01
- Publication Date
- 2025-10-31
AI Technical Summary
Intelligent vehicle control systems are vulnerable to cyberattacks due to limited communication resources, leading to wasted communication resources and congestion, which affects safety and reliability.
An elastic event triggering method is adopted, which includes an initialization module, a network attack signal detection module, an elastic event triggering module, a data caching module, and a controller module. It designs a switching adaptive threshold function and elastic event triggering conditions to control the update of status signals in order to save communication resources and reduce the impact of network attacks.
It effectively saves communication resources, avoids communication congestion, improves the safety and reliability of intelligent vehicles, and ensures safe and reliable operation even under cyberattacks.
Smart Images
Figure CN120871808A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent vehicle control technology, and in particular to a resilient event triggering method for network attacks on intelligent vehicle control systems. Background Technology
[0002] Intelligent vehicle control systems, equipped with various in-vehicle communication networks, are essentially networked control systems. Their communication bandwidth is limited, meaning communication resources are inherently finite. Traditional intelligent vehicle control systems update transmitted status signals and control commands at each sampling moment, wasting significant communication resources and potentially leading to communication congestion, ultimately causing the vehicle to malfunction. The status signals refer to lateral speed, yaw rate, lateral error, heading angle error, and speed error; the control commands refer to front wheel steering angle, throttle, or braking signals. Furthermore, due to the open interconnection between in-vehicle communication networks and the intelligent vehicle's hardware, malicious attackers can easily launch attacks between in-vehicle sensors and controller modules, and between controller modules and actuator modules. This can cause the intelligent vehicle to lose control, potentially threatening life and property. Summary of the Invention
[0003] To address the aforementioned problems in the existing technology, the present invention aims to provide a flexible event triggering method for network attacks on intelligent vehicle control systems. This method effectively conserves communication resources and reduces performance losses caused by network attacks on intelligent vehicle control systems under conditions of limited in-vehicle communication network resources, thereby enabling intelligent vehicles to operate safely and reliably.
[0004] To achieve the above objectives, the technical solution of the present invention is as follows:
[0005] A resilient event triggering method for network attacks on intelligent vehicle control systems is disclosed. The method utilizes the intelligent vehicle control system for control, which includes an initialization module, a network attack signal detection module, a resilient event triggering module, a data caching module, a controller module, and an actuator module.
[0006] The initialization module is used to check whether the signal transmission and reception of the on-board sensors, planning module, and actuator module are normal; to check whether the network attack signal detection module and data cache module are operating normally; to check whether the loading of reference path information is normal, the reference path information including reference position, reference road curvature, reference heading angle, reference speed, and reference acceleration; to load the parameters of the intelligent vehicle control model; to load the parameters of the elastic event triggering module; and to load the parameters of the intelligent vehicle state feedback controller.
[0007] The network attack signal detection module obtains the security status of the vehicle communication network by monitoring the data stream transmission in real time. The security status is either an attack-affected state or an attack-free state. The elastic event triggering module consists of elastic event triggering conditions, which are designed based on a switching adaptive threshold function and the state signals of the intelligent vehicle control model. The switching adaptive threshold function is designed based on the security status of the vehicle communication network and the state signals. The elastic event triggering module determines whether the state signals are updated in the controller module. The elements of the state signals include lateral velocity, yaw rate, lateral error, heading angle error, and velocity error. The lateral error refers to the difference between the current position and the reference position of the intelligent vehicle, and the heading angle error refers to the difference between the current heading angle and the reference heading angle of the intelligent vehicle. The current state information of the intelligent vehicle includes position information, heading angle, longitudinal velocity, lateral velocity, and yaw rate. The data caching module is used to cache the state signals triggered at the previous moment when the elastic event triggering conditions are not met.
[0008] The intelligent vehicle control model is obtained by mathematical calculations based on the current state information of the intelligent vehicle and the reference path information, and modeled in the form of mathematical equations. The controller module consists of an intelligent vehicle state feedback controller, which is designed based on the intelligent vehicle control model. The intelligent vehicle state feedback controller uses the state signals to solve for control commands.
[0009] The elastic event triggering method includes the following steps:
[0010] Step 1: Initialization
[0011] The initialization module checks whether the signal transmission and reception of the on-board sensors, planning module, and actuator module are normal; checks whether the network attack signal detection module and data cache module are operating normally; and checks whether the loading of reference path information is normal. The on-board sensor information, planning module information, and actuator module information respectively refer to environmental obstacle information, current status information of the intelligent vehicle, reference path information, and status signals of the intelligent vehicle actuators. The reference path information includes reference position, reference road curvature, reference heading angle, reference speed, and reference acceleration. The intelligent vehicle actuator signals include the front wheel steering angle, throttle opening, and braking pressure actually executed by the actuators.
[0012] The initialization module loads parameters for the intelligent vehicle control model; loads parameters for the elastic event triggering module; and loads parameters for the intelligent vehicle state feedback controller. The intelligent vehicle control model parameters include the vehicle's mass, the distance from the center of the front and rear axles to the center of mass, and the lateral stiffness and moment of inertia of the front and rear axle tires. The elastic event triggering module parameters include the weight matrix for elastic event triggering and preset constants in the adaptive threshold function. The intelligent vehicle state feedback controller parameters include the maximum constraint value of the control command, the preview distance, the maximum and minimum values of the network-induced delay, and the sampling period.
[0013] Step 2: Establish an intelligent vehicle control model
[0014] Based on the current state information of the intelligent vehicle obtained in real time in step 1 and the reference path information, mathematical calculations are performed, and the following intelligent vehicle control model is established in the form of mathematical equations:
[0015]
[0016] In the formula: x(t) is the state signal of the intelligent vehicle control model, and u(t) is the control command calculated by the intelligent vehicle state feedback controller. Let A be the first differential of x(t), A be the coefficient matrix of x(t), and B be the coefficient matrix of u(t).
[0017] Step 3: Design the adaptive threshold function for switching
[0018] Based on the security status of the vehicle communication network and the state signals of the intelligent vehicle control model obtained in step 2, a switching adaptive threshold function is designed, and its mathematical equation expression is as follows:
[0019]
[0020] In the formula: λ(i k h s ) is the adaptive threshold function; λ2, λ1, λ0, γ are all preset constants λ2>0, λ1>0, λ0>0, γ>0; π is pi; exp() is the exponential function; || is the sign for calculating the norm; arctan() is the arctangent function; x(i k h s ) is the i-th k h s The state signal sampled at each moment; d k (t) represents the network-induced time delay. Error induced by elastic events. θ i (i k h s ) represents the security status of the vehicle-mounted communication network, θ i (ik h s ) = 1 represents the state of no attack, θ i (i k h s i = 0 indicates an attack state, i = 1 indicates an attack state between the vehicle sensor and the controller module, and i = 2 indicates an attack state between the controller module and the actuator module.
[0021] Step 4: Determine if the elastic event triggering conditions are met.
[0022] The elastic event triggering module is composed of elastic event triggering conditions. These conditions are designed based on the switching adaptive threshold function in step 3 and the state signals of the intelligent vehicle control model calculated in step 2. Their mathematical expression is:
[0023]
[0024] Where: h s Where t is the period length, l is the number of sampling periods, and t is the number of sampling periods. k The sampling time is when the k-th event triggers, t k+1 The sampling time is triggered by the (k+1)th event, i k h s Refers to the i-th k Each sampling time. Let x(td) be the weight matrix for the elastic event triggering conditions, and it is positive definite. k (t) is the tdth time k The state signal triggered at time (t).
[0025] Before calculating each control command, the intelligent vehicle state feedback controller determines whether the elastic event triggering condition is met. If the condition is met, the state signal of the intelligent vehicle control model is updated in the intelligent vehicle state feedback controller to calculate the control command; if the condition is not met, no update is made, that is, the control command of the previous moment is saved in the data cache module.
[0026] Step 5: Solve for control commands
[0027] Based on the state signal of the intelligent vehicle control model triggered in step 4, the control command of the intelligent vehicle state feedback controller is calculated as follows:
[0028]
[0029] In the formula: K is the gain matrix of the intelligent vehicle state feedback controller.
[0030] Step 6: Implement elastic event triggering control
[0031] The control command determined in step 5 is sent to the actuator module. If there is no attack signal between the controller module and the actuator module, the control command is updated to the actuator module. If there is an attack signal between the controller module and the actuator module, the control command from the previous moment is used. Further, it is determined whether the intelligent vehicle has reached its destination. If so, the control task is completed; otherwise, proceed to step 1.
[0032] The present invention has the following beneficial effects:
[0033] This invention fully considers the limited communication resources and network attack problems existing in the intelligent vehicle control system. It designs a flexible event triggering condition to determine whether the state signal of the intelligent vehicle control model is updated to the intelligent vehicle state feedback controller, thereby avoiding communication congestion problems, saving a lot of communication resources and improving the safety of intelligent vehicles in the control process. Attached Figure Description
[0034] Figure 1 This is a schematic diagram of the present invention.
[0035] Figure 2 This is a schematic diagram of the intelligent vehicle control system of the present invention. Detailed Implementation
[0036] The following is for reference Figure 1-2 The present invention will be further described below.
[0037] Figure 1 The diagram shown illustrates the principle of this invention, which utilizes an intelligent vehicle state feedback controller and a flexible event triggering module to achieve safe control and communication resource conservation in intelligent vehicles. The flexible event triggering module determines whether the flexible event triggering conditions are met based on a switching adaptive threshold function and the state signal of the intelligent vehicle control model, thereby deciding whether to update the state signal. The intelligent vehicle state feedback controller calculates control commands based on the state signal triggered by the flexible event triggering module and the gain matrix of the intelligent vehicle state feedback controller.
[0038] Before each calculation of a control command, the intelligent vehicle state feedback controller needs to determine whether the elastic event triggering condition in step 4 is met. If it is met, the state signal of the intelligent vehicle control model is updated in the intelligent vehicle state feedback controller to calculate the control command; if it is not met, it is not updated, and the control command of the previous moment is saved in the data cache module.
[0039] Before the control command is sent to the actuator module, if there is no attack between the controller module and the actuator module, the control command is updated to the actuator module; if there is an attack between the controller module and the actuator module, the control command from the previous moment is used; ultimately, safe control of the intelligent vehicle is achieved.
[0040] This invention utilizes Figure 2 The intelligent vehicle control system shown below performs the following steps:
[0041] Step 1: Initialization;
[0042] Step 2: Establish an intelligent vehicle control model;
[0043] Step 3: Design the switching adaptive threshold function;
[0044] Step 4: Determine if the conditions for triggering the elastic event are met;
[0045] Step 5: Solve for the control commands;
[0046] Step 6: Implement elastic event triggering control.
[0047] The content of each step in this embodiment is consistent with the content of the steps in the invention.
[0048] This invention is not limited to the details of the above embodiments. Any equivalent concept or modification within the technical scope disclosed in this invention shall be included within the protection scope of this invention.
Claims
1. A resilient event triggering method for network attacks on intelligent vehicle control systems, characterized in that: Controlling a vehicle using an intelligent vehicle control system includes the following steps: Step 1: Initialization; Step 2: Establish an intelligent vehicle control model; Step 3: Design the switching adaptive threshold function; Step 4: Determine if the conditions for triggering the elastic event are met; Step 5: Solve for the control commands; Step 6: Implement elastic event triggering control.
2. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The intelligent vehicle control system includes an initialization module, a network attack signal detection module, a flexible event triggering module, a data caching module, a controller module, and an actuator module. The initialization module is used to check whether the signal transmission and reception of the vehicle-mounted sensors, planning module, and actuator module are normal; to check whether the network attack signal detection module and data cache module are operating normally; and to check whether the loading of reference path information is normal. The reference path information includes reference position, reference road curvature, reference heading angle, reference speed, and reference acceleration. Load the parameters of the intelligent vehicle control model; load the parameters of the elastic event triggering module; load the parameters of the intelligent vehicle state feedback controller; The network attack signal detection module obtains the security status of the vehicle communication network by monitoring the data stream transmission status of the vehicle communication network in real time. The security status is either an attack-affected state or an attack-free state. The elastic event triggering module consists of elastic event triggering conditions, which are designed based on a switching adaptive threshold function and the state signals of the intelligent vehicle control model. The switching adaptive threshold function is designed based on the security status of the vehicle communication network and the state signals. The elastic event triggering module determines whether the state signals are updated in the controller module. The elements of the state signals include lateral velocity, yaw rate, lateral error, heading angle error, and speed error. The lateral error refers to the difference between the current position and the reference position of the intelligent vehicle, and the heading angle error refers to the difference between the current heading angle and the reference heading angle of the intelligent vehicle. The current state information of the intelligent vehicle includes position information, heading angle, longitudinal velocity, lateral velocity, and yaw rate. The data caching module is used to cache the state signals triggered at the previous moment when the elastic event triggering conditions are not met. The intelligent vehicle control model is obtained by performing mathematical calculations on the current state information of the intelligent vehicle and the reference path information, and modeling it in the form of mathematical equations. The controller module consists of an intelligent vehicle state feedback controller, which is designed based on an intelligent vehicle control model. The intelligent vehicle state feedback controller uses the state signal to solve for control commands.
3. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The initialization method described in step 1 is as follows: The initialization module checks whether the signal transmission and reception of the on-board sensors, planning module, and actuator module are normal; checks whether the network attack signal detection module and data cache module are operating normally; and checks whether the loading of reference path information is normal. The on-board sensor information, planning module information, and actuator module information respectively refer to environmental obstacle information, current status information of the intelligent vehicle, reference path information, and status signals of the intelligent vehicle actuators. The reference path information includes reference position, reference road curvature, reference heading angle, reference speed, and reference acceleration. The intelligent vehicle actuator signals include the front wheel steering angle, throttle opening, and braking pressure actually executed by the actuator. The initialization module loads the parameters of the intelligent vehicle control model; loads the parameters of the elastic event triggering module; and loads the parameters of the intelligent vehicle state feedback controller. The intelligent vehicle control model parameters include the mass of the intelligent vehicle, the distance from the center of the front and rear axles to the center of mass, the lateral stiffness of the front and rear axle tires, and the moment of inertia. The parameters of the elastic event triggering module include the weight matrix of the elastic event triggering and the preset constant in the switching adaptive threshold function. The parameters of the intelligent vehicle state feedback controller include the maximum value of the control command constraint, the preview distance, the maximum and minimum values of the network-induced delay, and the sampling period.
4. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The method for establishing the intelligent vehicle control model in step 2 is as follows: Based on the current state information of the intelligent vehicle obtained in real time in step 1 and the reference path information, mathematical calculations are performed, and the following intelligent vehicle control model is established in the form of mathematical equations: In the formula: x(t) is the state signal of the intelligent vehicle control model, and u(t) is the control command calculated by the intelligent vehicle state feedback controller. Let A be the first differential of x(t), A be the coefficient matrix of x(t), and B be the coefficient matrix of u(t).
5. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The method for designing and switching adaptive threshold functions described in step 3 is as follows: Based on the security status of the vehicle communication network and the state signals of the intelligent vehicle control model obtained in step 2, a switching adaptive threshold function is designed, and its mathematical equation expression is as follows: In the formula: λ(i k h s ) is the adaptive threshold function for switching; λ2, λ1, λ0, γ are all preset constants λ2>0, λ1>0, λ0>0, γ>0; π is pi; exp() is the exponential function; |||| is the sign for calculating the norm; arctan() is the arctangent function; x(i k h s ) is the i-th k h s The state signal sampled at each moment; d k (t) represents the network-induced time delay. Errors induced by elastic events; For the security status of the vehicle communication network, Refers to a state of no attack. The term "attack state" refers to the state where an attack is occurring. i=1 indicates an attack state between the vehicle sensor and the controller module, while i=2 indicates an attack state between the controller module and the actuator module.
6. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The method for determining whether the elastic event triggering conditions are met in step 4 is as follows: The elastic event triggering module is composed of elastic event triggering conditions. These conditions are designed based on the switching adaptive threshold function in step 3 and the state signals of the intelligent vehicle control model calculated in step 2. Their mathematical expression is: Where: h s Where t is the period length, l is the number of sampling periods, and t is the number of sampling periods. k The sampling time is when the k-th event triggers, t k+1 The sampling time is triggered by the (k+1)th event, i k h s Refers to the i-th k Each sampling time; x(td) is the weight matrix for the elastic event triggering condition, and it is positive definite; k (t) is the tdth time k The state signal triggered at time (t); Before calculating each control command, the intelligent vehicle state feedback controller determines whether the elastic event triggering condition is met. If the condition is met, the state signal of the intelligent vehicle control model is updated in the intelligent vehicle state feedback controller to calculate the control command; if the condition is not met, no update is made, that is, the control command of the previous moment is saved in the data cache module.
7. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: The method for solving the control commands described in step 5 is as follows: Based on the state signal of the intelligent vehicle control model triggered in step 4, the control command of the intelligent vehicle state feedback controller is calculated as follows: In the formula: K is the gain matrix of the intelligent vehicle state feedback controller.
8. The resilient event triggering method for network attacks on intelligent vehicle control systems according to claim 1, characterized in that: Step 6 describes the implementation of elastic event triggering control. The control command determined in step 5 is sent to the actuator module. If there is no attack signal between the controller module and the actuator module, the control command is updated to the actuator module. If an attack signal exists between the controller module and the actuator module, the control command from the previous moment is used; further, it is determined whether the intelligent vehicle has reached its destination. If so, the control task is completed; otherwise, proceed to step 1.