Authentication method and device of advanced driving assistance system, medium and product

Abstract

The invention discloses a security method and device of an advanced driving assistance system, a medium and a product, and relates to the technical field of reinforcement learning, and the method comprises the steps: constructing a security framework of the advanced driving assistance system; describing a safety specification of the advanced driving assistance system based on a signal tense logic language; acquiring a current-moment system state of the advanced driving assistance system; inputting the system state and the safety specification at the current moment into a robustness semantic value calculation module to obtain a robustness semantic value; inputting the robustness semantic value and the system state at the current moment into a trained security module to obtain an interference signal; inputting the interference signal into an advanced driving assistance system to generate a system state at the next moment; and judging whether the advanced driving assistance system is in a fault state or not based on the system state at the next moment, and completing the security of the advanced driving assistance system according to the judgment result. According to the invention, long-term interference signals can be effectively searched and the security of the advanced driving assistance system can be completed.

Description

Technical Field

[0001] The present application relates to the field of reinforcement learning technology, and in particular to a falsification method, device, medium and product for an advanced driver assistance system. Background Art

[0002] The "falsification" of Advanced Driving Assistance System (ADAS) usually refers to the questioning or criticism of the safety and effectiveness of ADAS functions, which may come from accident cases in actual use, research findings or evaluation reports from regulatory agencies.

[0003] With the rapid development of ADAS technology, such as Adaptive Cruise Control (ACC) and Lane Keeping Assist (LKA), the degree of vehicle automation and intelligence has been continuously improved, so that the safety of vehicles has attracted more attention. However, ensuring the safety of vehicles is a hugely challenging task. For example, even in seemingly simple scenarios such as vehicle following, vehicles equipped with adaptive cruise control systems can be easily affected by the driving behavior of the vehicle in front, and various acceleration and deceleration behaviors of the vehicle in front may cause serious traffic accidents.

[0004] The method of evaluating whether a vehicle equipped with an advanced driver assistance system meets safety requirements is usually to simulate the vehicle under test using a large number of test cases and traffic scenarios. However, this type of method has a significant disadvantage. Even with a large number of tests, there may still be some unknown risk scenarios in the advanced driver assistance system. In contrast, formal verification methods can provide strong safety guarantees through rigorous mathematical proofs to verify whether each input of the vehicle meets safety requirements. However, formal verification methods are difficult to extend to continuous and complex advanced driver assistance systems. For example, model checking is only applicable to advanced driver assistance systems with simple and discrete state spaces.

[0005] In order to efficiently conduct safety assessment of advanced driver assistance systems, falsification technology based on black box sampling optimization is currently widely used in safety assessment of advanced driver assistance systems. Falsification technology based on black box sampling optimization searches for the optimal interference signal by minimizing the robustness semantic value of the advanced driver assistance system. The robustness semantic value can effectively guide the falsification technology to generate interference signals that force the advanced driver assistance system to produce a fault state, thereby more effectively and automatically detecting the state of the advanced driver assistance system that does not meet the safety specifications.

[0006] Existing falsification techniques based on black-box sampling optimization use various random global optimization algorithms, such as simulated annealing and cross-entropy optimization, to minimize the robustness semantic value of advanced driver assistance systems. However, such methods cannot effectively search for long-term interference signals, and therefore, in many cases it is difficult to effectively falsify the system. Summary of the invention

[0007] The purpose of this application is to provide a method, device, medium and product for falsification of an advanced driver assistance system, which can effectively search for interference signals and complete the falsification of the advanced driver assistance system, thereby efficiently realizing the safety assessment of the advanced driver assistance system.

[0008] To achieve the above objectives, this application provides the following solutions:

[0009] In a first aspect, the present application provides a method for falsification of an advanced driver assistance system, comprising:

[0010] Constructing an advanced driver assistance system falsification framework; the advanced driver assistance system falsification framework comprises: an advanced driver assistance system, a robustness semantic value calculation module and a falsification module;

[0011] Describing the safety specification of the advanced driver assistance system based on a signal temporal logic language;

[0012] Obtaining the current system status of the advanced driver assistance system;

[0013] Inputting the current system state and the safety specification into the robustness semantic value calculation module to obtain a robustness semantic value; the robustness semantic value represents the degree to which the advanced driver assistance system meets the safety specification;

[0014] Inputting the robustness semantic value and the current system state into the trained falsification module to obtain an interference signal; wherein the interference signal is used as an optimal test case for the advanced driver assistance system to test the fault state of the advanced driver assistance system in an unsafe state;

[0015] The interference signal is input into the advanced driving assistance system to generate the system state at the next moment; based on the system state at the next moment, it is determined whether the advanced driving assistance system is in a fault state, and the advanced driving assistance system is falsified according to the determination result.

[0016] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the falsification method of the advanced driver assistance system.

[0017] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the falsification method of the advanced driver assistance system.

[0018] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the falsification method of the advanced driver assistance system.

[0019] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0020] The present application provides a method, device, medium and product for falsification of an advanced driver assistance system. By constructing an advanced driver assistance system falsification framework, the advanced driver assistance system is used as a system under test, and the safety specification of the advanced driver assistance system is described. The safety specification and the current system state output by the advanced driver assistance system are used as inputs of a robustness semantic value calculation module to obtain a robustness semantic value, which is used to calculate the degree to which the current system state of the advanced driver assistance system meets the safety specification. Furthermore, the current system state and robustness semantic value of the advanced driver assistance system are processed by the falsification module to obtain an interference signal for testing the advanced driver assistance system. Among them, the robustness semantic value can effectively guide the falsification module to generate interference signals that force the advanced driving assistance system to produce a fault state, and the interference signal can more effectively and automatically detect the fault state of the advanced driving assistance system that does not meet the safety specifications. That is to say, the falsification module is used to generate the optimal test case that can cause the advanced driving assistance system to have a fault state. Furthermore, the interference signal is input into the advanced driving assistance system to obtain the safety state at the next moment. Based on the system state at the next moment, it is determined whether the advanced driving assistance system is in a fault state, thereby effectively realizing the falsification of the advanced driving assistance system and efficiently completing the safety assessment of the advanced driving assistance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of a flow chart of a falsification method of an advanced driver assistance system in one embodiment of the present application;

[0023] Figure 2 A falsification framework diagram of an advanced driver assistance system according to a falsification method of an advanced driver assistance system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0026] Reference Figure 1 , a falsification method for an advanced driver assistance system, comprising:

[0027] Step 101: construct an advanced driver assistance system falsification framework; the advanced driver assistance system falsification framework includes: an advanced driver assistance system, a robustness semantic value calculation module and a falsification module.

[0028] Among them, the construction of an advanced driver assistance system falsification framework based on reinforcement learning can be applied to a variety of different systems under test, such as automatic lane keeping systems and automatic parking systems.

[0029] For example, the Adaptive Cruise Control (ACC) in the advanced driver assistance system is used as the system under test. The function of the ACC system is to maintain a safe distance between the main vehicle (equipped with an adaptive cruise control system) and the vehicle in front by adjusting the acceleration of the main vehicle. When the relative distance is greater than the safe distance, the speed of the main vehicle will be maintained at the speed set by the driver. The system under test of this application is an ACC system based on a model predictive controller (MPC).

[0030] Step 102: Describe the safety specification of the advanced driver assistance system based on signal temporal logic language.

[0031] For example, taking the ACC system as an example, the safety specification ψ of the ACC system is described using the signal temporal logic language, which describes the safety requirements for the ACC system state, such as the relative distance between the main vehicle and the front vehicle must always be greater than a specific threshold.

[0032] In some embodiments, the safety specification is obtained based on a preset specification system, and the safety specification includes hard safety, stability and activity.

[0033] The formula for the safety specification is:

[0034]

[0035] Wherein, [0, i] represents the preset time interval of the signal, i represents time; d_rel represents the relative distance between the host vehicle and the front vehicle; d_safe represents the preset safety distance; v_ego represents the speed of the host vehicle; ψ1 represents hard safety, which means that the relative distance between the host vehicle equipped with the advanced driving assistance system and the front vehicle must be greater than the preset safety distance d_safe in the interval [0, i]; ψ2 represents stability, which means that the proposition that the relative distance between the host vehicle equipped with the advanced driving assistance system and the front vehicle in a given interval [0, j] is always greater than the preset safety distance will eventually hold true in [0, i], j≤i; ψ3 represents activity, which means that in the preset time interval [0, i], the speed of the host vehicle equipped with the advanced driving assistance system will eventually be greater than 1; It means "always"; ◇ means "eventually".

[0036] Step 103: Obtain the current system state of the advanced driver assistance system.

[0037] Exemplarily, the system state at the current moment may be the relative distance and relative speed between the host vehicle and the preceding vehicle.

[0038] Step 104: Input the current system state and the safety specification into the robustness semantic value calculation module to obtain a robustness semantic value; the robustness semantic value represents the degree to which the advanced driver assistance system meets the safety specification.

[0039] Exemplarily, taking the ACC system as an example, the robustness semantic value of the ACC system, that is, the degree to which the ACC system meets the safety specifications, is calculated in an online manner based on the system state signal and the safety specifications.

[0040] In some embodiments, the calculation formula of the robustness semantic value is:

[0041] ρ(ψ1,d_rel [0,t] ,τ)=inf t∈τ+I (ρ(ψ1,d_rel [0,t] ,t))

[0042] ρ(ψ2,d_rel [0,t] ,τ)=sup t∈τ+I inf t∈τ+I (ρ(ψ 2_1 ,d_rel [0,t] ,t)));

[0043] ρ(ψ3,v_ego [0,t] ,τ)=sup t∈τ+I(ρ(ψ3,v_ego [0,t] ,t))

[0044] In the formula, d_rel [0,t] represents the relative distance between the advanced driver assistance system and the preceding vehicle in the time interval [0, t]; ρ represents the robustness semantic value of the advanced driver assistance system; t represents the current moment; I represents the time interval; τ represents the future moment; τ+I represents the future time interval. ψ 2_1 is a sub-proposition of ψ2, ψ 2_1 = [0,i] (d_rel>d_safe+0.2).

[0045] Step 105: Input the robustness semantic value and the current system state into the trained falsification module to obtain an interference signal; wherein the interference signal is used as an optimal test case for the advanced driver assistance system to test the fault state of the advanced driver assistance system in an unsafe state.

[0046] Among them, by using the trained falsification module, through the robustness semantic value and the current system state as input, long-term interference signals can be effectively searched, that is, the optimal test case that can detect that the advanced driver assistance system is in a fault state.

[0047] Exemplarily, the current system state output by the tested system is the relative distance and relative speed between the main vehicle and the preceding vehicle, and the interference signal output by the trained falsification module is the acceleration of the preceding vehicle.

[0048] In some embodiments, the training process of the falsification module specifically includes: the falsification module includes an Actor module and a Critic module; the Actor module is used to generate the interference signal according to the system state at the current moment; the Critic module is used to evaluate the interference signal and output a state value; the Actor module is used to interact with the advanced driver assistance system to generate input data of the advanced driver assistance system; the input data includes: the system state at each moment, the interference signal output by the Actor module at each moment, and the robustness semantic value at each moment; based on the Critic module, the state value error of the state value is determined according to the system state at the current moment and the system state at the next moment; the falsification module is trained according to the state value error until a preset iteration threshold is reached.

[0049] Among them, this application uses a reinforcement learning algorithm to train the falsification module.

[0050] In some embodiments, the calculation formula of the state value error is:

[0051]

[0052] Among them, δ t represents the state value error at time t; γ represents the discount factor, γ∈[0,1]; x t+1 represents the system state at time t+1; x t represents the system state at time t; r t represents the robustness semantic value at time t; π θ Indicates interference signal; Indicates that the agent is executing π θ When x t The state value of the following; Indicates that the agent is executing π θ When x t+1 The value under; w represents the parameter of the state value function of the Critic module, and the calculation formula of the value function is: θ represents the parameters of the strategy function of the Actor module.

[0053] The calculation formula of the strategy function is: Among them, x1 represents the initial system state at the initial time t = 1; Indicates that the agent is executing π θ The state value under x1.

[0054] In some implementation cases, the method further includes: updating a parameter w of the value function according to the value function gradient of the Critic module; the calculation formula of the parameter w is:

[0055]

[0056] Among them, a w Represents the learning rate of the Critic module; Represents the gradient of the Critic module with respect to the parameter w.

[0057] Update the parameter θ of the strategy function according to the strategy function gradient of the Actor module; the calculation formula of the parameter θ is:

[0058]

[0059] Among them, a θ Indicates the learning rate of the Actor module; represents the gradient of the Actor module with respect to the parameter θ; π θ (a t |x t ) represents the policy function, a t Indicates an interference signal.

[0060] Among them, the trained falsification module continuously interacts with the advanced driver assistance system (ADAS system) and trains the falsification module according to the received system state and robustness semantic values. In the training of the falsification module by the above system state and robustness semantics, the falsification module continuously iterates and optimizes the interference signal to the system under test (ADAS system), and then discovers the fault state of the ADAS system. In other words, the advanced driver assistance system is falsified using the reinforcement learning algorithm to improve the falsification efficiency of the advanced driver assistance system.

[0061] Step 106: Input the interference signal to the advanced driver assistance system to generate the next system state. Based on the next system state, determine whether the advanced driver assistance system is in a fault state, and complete the falsification of the advanced driver assistance system according to the determination result.

[0062] For example, the current system state of the falsification output of the advanced driver assistance system is the relative distance and relative speed between the main vehicle and the front vehicle, and the interference signal output by the trained falsification module is the acceleration of the front vehicle. The next system state is the action of the main vehicle at the next moment according to the acceleration of the front vehicle.

[0063] Inspired by the good decision-making performance of deep reinforcement learning in complex systems (such as games), this application constructs the falsification problem of advanced driver assistance systems as a reinforcement learning problem, and uses deep reinforcement learning to solve long-term interference signals, thereby exploring the fault state of the ADAS system that does not meet safety regulations. This effectively improves the success rate and efficiency of falsification.

[0064] The present application also provides an application scenario, which applies the above-mentioned advanced driving assistance system falsification method. Specifically: The advanced driving assistance system falsification method provided in this embodiment can be applied in the automatic driving scenario of a vehicle equipped with an advanced driving assistance system. Through the speed of the front vehicle in the traffic scene obtained by the vehicle at the current moment and the relative distance between the two vehicles, the acceleration of the front vehicle is obtained as an interference signal, and then the next moment action of the vehicle (that is, the system state at the next moment) is obtained. Based on the system state at the next moment, it is determined whether the advanced driving assistance system is in a fault state, thereby effectively realizing the falsification of the advanced driving assistance system and efficiently completing the safety assessment of the advanced driving assistance system.

[0065] In the advanced driver assistance system falsification framework, Figure 2As shown in Figure 1, first, it is necessary to establish a system under test, which is used as the object of the falsification module based on reinforcement learning. Secondly, it is necessary to describe the safety specification of the advanced driver assistance system (ADAS system). The safety specification is output by the system safety specification module, and the safety specification and the output state of the ADAS system are used as the input of the system robustness calculation module. The robustness calculation module iteratively calculates the degree to which the system state meets the safety specification according to the safety specification. This degree is also called the robustness semantic value, that is, the system robustness semantic value, which is expressed by r. t Finally, a falsification module based on the AC (Actor-Critic) algorithm is built, and the output of the ADAS system and the robustness semantic value calculation module (i.e., the robustness semantic value calculation module) is used as the input of the falsification module, and the output of the falsification module is optimized. The output is the interference signal of the ADAS system. Taking the ACC system as the system under test as an example, the system state output by the system under test (i.e., the system state at the current moment, represented by S t ) is the relative distance and relative speed between the main vehicle and the front vehicle, and the system interference (i.e., interference signal, represented by a) output by the falsification module based on the AC algorithm t ) is the acceleration of the front vehicle.

[0066] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0067] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0068] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0070] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0071] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0072] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for falsification of an advanced driver assistance system, characterized in that: The falsification method of the advanced driver assistance system comprises: Constructing an advanced driver assistance system falsification framework; the advanced driver assistance system falsification framework comprises: an advanced driver assistance system, a robustness semantic value calculation module and a falsification module; Describing the safety specification of the advanced driver assistance system based on a signal temporal logic language; Obtaining the current system status of the advanced driver assistance system; Inputting the current system state and the safety specification into the robustness semantic value calculation module to obtain a robustness semantic value; the robustness semantic value represents the degree to which the advanced driver assistance system meets the safety specification; Inputting the robustness semantic value and the current system state into the trained falsification module to obtain an interference signal; wherein the interference signal is used as an optimal test case for the advanced driver assistance system to test the fault state of the advanced driver assistance system in an unsafe state; The interference signal is input into the advanced driving assistance system to generate the system state at the next moment; based on the system state at the next moment, it is determined whether the advanced driving assistance system is in a fault state, and the advanced driving assistance system is falsified according to the determination result.

2. The falsification method of the advanced driver assistance system according to claim 1, characterized in that: Acquiring the safety specification based on a preset specification system, wherein the safety specification includes hard safety, stability and activity; The formula for the safety specification is: Wherein, [0, i] represents the preset time interval of the signal, i represents time; d_rel represents the relative distance between the main vehicle and the front vehicle; d_safe represents the preset safety distance; v_ego represents the speed of the main vehicle; ψ1 represents hard safety, which means that the relative distance between the main vehicle equipped with the advanced driving assistance system and the front vehicle must be greater than the preset safety distance d_safe in the interval [0, i]; ψ2 represents stability, which means that the proposition that the relative distance between the main vehicle equipped with the advanced driving assistance system and the front vehicle in a given interval [0, j] is always greater than the preset safety distance will eventually hold true in [0, i], where j≤i; ψ3 represents activity, which means that in the preset time interval [0, i], the speed of the main vehicle equipped with the advanced driving assistance system will eventually be greater than 1 m / s; It means "always"; Indicates "finally".

3. The falsification method of the advanced driver assistance system according to claim 1, characterized in that: The calculation formula of the robustness semantic value is: ρ(ψ1,d_rel [0,t] ,τ)=inf t∈τ+I (ρ(ψ1,d_rel [0,t] ,t)) ρ(ψ2,d_rel [0,t] ,τ)=supt ∈τ+I inf t∈τ+I (ρ(ψ 2_1 ,d_rel [0,t] ,t))); ρ(ψ3,v_ego [0,t] ,τ)=sup t∈τ+I (ρ(ψ3,v_ego [0,t] ,t)) In the formula, d_rel [0,t] represents the relative distance between the advanced driver assistance system and the preceding vehicle in the time interval [0, t]; ρ represents the robustness semantic value of the advanced driver assistance system; t represents the current moment; I represents the preset time interval [0, i]; τ represents the future moment; τ+I represents the future time interval. ψ 2_1 is a sub-proposition of ψ2, ψ 2_1 = [0，i] (d_rel>d_safe+0.2).

4. The falsification method of the advanced driver assistance system according to claim 1, characterized in that: The training process of the falsification module specifically includes: the falsification module includes an Actor module and a Critic module; the Actor module is used to generate the interference signal according to the current system state; the Critic module is used to evaluate the interference signal and output the state value; Using the Actor module to interact with the advanced driver assistance system to generate input data of the advanced driver assistance system; the input data includes: the system state at each moment, the interference signal output by the Actor module at each moment, and the robustness semantic value at each moment; Based on the Critic module, determining a state value error of the state value according to the system state at a current moment and the system state at a next moment; The falsification module is trained according to the state value error until a preset iteration threshold is reached.

5. The falsification method of the advanced driver assistance system according to claim 4, characterized in that: The calculation formula of the state value error is: Among them, δ t represents the state value error at time t; γ represents the discount factor, γ∈[0,1]; x t+1 represents the system state at time t+1; x t represents the system state at time t; r t represents the robustness semantic value at time t; π θ Indicates interference signal; Indicates that the agent is executing π θ When x t The state value of the following; Indicates that the agent is executing π θ When x t+1 The value under; w represents the parameter of the state value function of the Critic module, and the calculation formula of the value function is: θ represents the parameters of the strategy function of the Actor module. The calculation formula of the strategy function is: Among them, x1 represents the initial system state at the initial time t = 1; Indicates that the agent is executing π θ The state value under x1.

6. The falsification method of the advanced driver assistance system according to claim 5, characterized in that: Also includes: Update the parameter w of the value function according to the value function gradient of the Critic module; the calculation formula of the parameter w is: Among them, a w Represents the learning rate of the Critic module; Represents the gradient of the Critic module with respect to the parameter w. Update the parameter θ of the strategy function according to the strategy function gradient of the Actor module; the calculation formula of the parameter θ is: Among them, a θ Indicates the learning rate of the Actor module; represents the gradient of the Actor module with respect to the parameter θ; π θ (a t |x t ) represents the policy function, a t Indicates an interfering signal.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the falsification method of the advanced driver assistance system according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the falsification method of the advanced driver assistance system according to any one of claims 1 to 6 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the falsification method of the advanced driver assistance system according to any one of claims 1 to 6 is implemented.

Images