Automobile driving risk early warning method and device considering carsickness factor

Abstract

The invention discloses an automobile driving risk early warning method and system considering a carsickness factor, and belongs to the technical field of safe driving, and the method comprises the steps: when detecting that a current driving mode is automatic driving, obtaining slave factors which influence driving and include the carsickness frequency in an automatic driving state; calculating a driving risk score in an automatic driving state according to the slave person factor and the corresponding weight; when it is monitored that the current driving mode is switched from automatic driving to manual driving, a slave vehicle factor and a slave person factor which influence driving in the manual driving state are obtained; a driving risk scoring model of network hierarchy analysis is utilized to analyze the slave vehicle factor and the slave person factor which influence driving in the manual driving state, and a driving risk score in the manual driving state is obtained; and according to the driving risk score in the automatic driving state and the driving risk score in the manual driving state, an automobile driving comprehensive scoring result is obtained. According to the invention, the safety coefficient of driving risk early warning is improved.

Description

Technical Field

[0001] The present invention relates to the field of safe driving technology, and more particularly to a method and device for early warning of automobile driving risks taking motion sickness factors into consideration. Background Art

[0002] As autonomous driving technology becomes increasingly widespread, the core of driving risks is shifting from traditional manual control to complex scenarios involving human-machine collaboration. First, drivers, due to their long-term reliance on the system to monitor the vehicle, may develop "automation fatigue," leading to a decrease in alertness. Research shows that after 30 minutes of continuous system monitoring, drivers' reaction time to emergencies can be delayed by over 40%. This fatigue stems from the continuous depletion of neural resources, directly impacting their ability to reconstruct the situation when taking over.

[0003] Autonomous driving below Level 3 still requires human supervision, but drivers can easily lose continuous awareness of road conditions due to distraction using electronic devices or cognitive disengagement. A survey by the Insurance Institute for Highway Safety (IHIS) shows that drivers are 3.2 times more likely to use their mobile phones while using autonomous driving features, and when distraction leads to an emergency takeover request, the average time to regain effective control increases to 4.5 seconds.

[0004] The passive riding mode brought about by the transfer of control of autonomous vehicles may induce motion sickness. The difference between the vehicle's acceleration and deceleration strategies and human driving habits increases the lateral acceleration fluctuation rate by 15%, causing the incidence of motion sickness to rise from 12% to 38%. Visual-vestibular perception conflicts (such as the vehicle turning while looking down at a mobile phone) will further aggravate physiological discomfort and weaken the ability to take over operations.

[0005] Therefore, how to consider motion sickness factors and thus improve driving safety has become one of the technical problems that those skilled in the art urgently need to solve. Summary of the Invention

[0006] In view of this, the present invention provides a car driving risk warning method and device taking motion sickness factors into consideration, which are used to at least solve some of the technical problems in the background technology.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] The present invention first discloses a car driving risk warning method considering motion sickness factors, comprising the following steps:

[0009] Detect current driving mode;

[0010] When it is detected that the current driving mode is automatic driving, the human factors affecting driving, including the number of motion sickness, are obtained in the automatic driving state;

[0011] Calculating a driving risk score in an autonomous driving state based on the human factors and corresponding weights;

[0012] When it is detected that the current driving mode is switched from automatic driving to manual driving, the vehicle-related factors and the human-related factors affecting driving in the manual driving state are obtained;

[0013] Using the network hierarchical analysis driving risk scoring model, the vehicle factors and human factors that affect driving in manual driving conditions are analyzed to obtain the driving risk score in manual driving conditions.

[0014] Based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state, a comprehensive car driving score result is obtained.

[0015] Furthermore, the human factors that affect driving in the autonomous driving state, including the number of motion sickness, include:

[0016] The number of times the driver closes his eyes, yawns, nods, answers or makes phone calls, does not look forward for a long time, is not in the driving position, smokes, reaction time to take over, and the number of times he gets carsick due to switching driving modes.

[0017] Furthermore, the vehicle-related factors and human-related factors that affect driving in the manual driving state include the following:

[0018] The following vehicle factors include the number of sudden accelerations, sudden decelerations, sharp turns, speeding, and driving time during driving;

[0019] The human factors include the number of times the driver closes his eyes, yawns, nods, answers or makes phone calls, does not look forward for a long time, is not in the driving position, smokes, and takes both hands off the steering wheel during driving.

[0020] Furthermore, the driving risk scoring model of the network hierarchical analysis is used to analyze the vehicle factors and human factors that affect driving in the manual driving state, and obtain the driving risk score in the manual driving state, which specifically includes:

[0021] Determine the influence weights of vehicle factors and human factors on driving status as the main criteria;

[0022] Get factor group E i Factor e in ij As a secondary criterion, the factor e was obtained using the satty1-9 scale method. ij For factor group E i The influence degree of other factors is obtained ij The submatrix W ij , factor group Ei The subscript i is 1 or 2. When i is 1, it indicates the vehicle factor group, and when i is 2, it indicates the human factor group. The sub-matrices of all factors are combined into a super matrix W.

[0023] Compare the importance of each factor in factor group E1 to each factor in factor group E2, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j …a nj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A;

[0024] Use matrix A to weight the super matrix W to obtain a weighted super matrix;

[0025] The weighted supermatrix is ​​taken to the limit to obtain the limit supermatrix ∞, where the column vector of the matrix is ​​the global weight of each factor;

[0026] The original assessment of each factor is multiplied by the corresponding global weight to obtain the final risk score of each factor.

[0027] Furthermore, based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state, a comprehensive driving score result is obtained, which specifically includes:

[0028] The driving risk score in the automatic driving state and the driving risk score in the manual driving state are weighted and summed to obtain the comprehensive driving score result.

[0029] Furthermore, the above method also includes obtaining a risk assessment level based on the comprehensive vehicle driving score, specifically including:

[0030] The comprehensive car driving score results are divided according to the set threshold to obtain the corresponding risk assessment level, including low risk, medium risk and high risk.

[0031] Furthermore, the above method also includes, according to the corresponding risk assessment level, using a corresponding risk warning module to issue an early warning, and the risk warning module includes a vibration seat cushion early warning module and an odor generator module.

[0032] The present invention also discloses a car driving risk warning device taking motion sickness factors into consideration, comprising:

[0033] A driving mode detection module is used to detect and determine the current driving mode;

[0034] The autonomous driving data acquisition module obtains human factors that affect driving, including the number of motion sickness episodes, during autonomous driving.

[0035] An autonomous driving risk assessment module, configured to calculate a driving risk score in an autonomous driving state based on the human factors and corresponding weights;

[0036] The manual driving data acquisition module, when detecting that the current driving mode switches from automatic driving to manual driving, obtains the vehicle-related factors and human-related factors that affect driving in the manual driving state;

[0037] The manual driving risk assessment module is used to analyze the vehicle factors and human factors that affect driving in the manual driving state using the driving risk scoring model of the network hierarchical analysis to obtain the driving risk score in the manual driving state;

[0038] The driving risk comprehensive assessment module is used to obtain a comprehensive driving score result of the car based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state.

[0039] Preferably, a driving risk scoring model based on network hierarchical analysis is used to analyze vehicle factors and human factors that affect driving in a manual driving state, and obtain a driving risk score in a manual driving state, specifically including:

[0040] Determine the influence weights of vehicle factors and human factors on driving status as the main criteria;

[0041] Get factor group E i Factor e in ij As a secondary criterion, the factor e was obtained using the satty1-9 scale method. ij For factor group E i The influence degree of other factors is obtained ij The submatrix W ij , factor group E i The subscript i is 1 or 2. When i is 1, it indicates the vehicle factor group, and when i is 2, it indicates the human factor group. The sub-matrices of all factors are combined into a super matrix W.

[0042] Compare the importance of each factor in factor group E1 to each factor in factor group E2, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j …a nj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A;

[0043] Use matrix A to weight the super matrix W to obtain a weighted super matrix;

[0044] The weighted supermatrix is ​​taken to the limit to obtain the limit supermatrix ∞, where the column vector of the matrix is ​​the global weight of each factor;

[0045] The original assessment of each factor is multiplied by the corresponding global weight to obtain the final risk score of each factor.

[0046] Preferably, the above system also includes a risk assessment level classification module, which is used to classify the comprehensive vehicle driving score results according to set thresholds to obtain corresponding risk assessment levels, including low risk, medium risk and high risk.

[0047] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a method and device for warning of automobile driving risks taking motion sickness factors into consideration, which has the following beneficial effects:

[0048] The present invention can switch the driving state, and in particular can capture the influence of the dizziness factor on the driving risk during the manual takeover of the automatic state.

[0049] This invention uses the Analytic Hierarchy Network Process (AHP) to establish a scoring model for manual driving. This model calculates a comprehensive risk score based on the driver's behavior and status during driving. A controller analyzes the comprehensive score and triggers a vibrating seat cushion and odor generator to provide early warnings, further ensuring driver safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0051] Figure 1 This is a schematic diagram of the overall process of the automobile driving risk warning method provided by an embodiment of the present invention.

[0052] Figure 2 A schematic diagram of the composition of vehicle-related factors and human-related factors that affect driving in a manual driving state provided by an embodiment of the present invention.

[0053] Figure 3 A schematic diagram of the mutual influence between vehicle factors and human factors that affect driving in a manual driving state provided by an embodiment of the present invention.

[0054] Figure 4 A schematic diagram of the vibration seat cushion warning workflow provided by an embodiment of the present invention.

[0055] Figure 5This is a schematic diagram of the seat cushion structure provided by an embodiment of the present invention, in which 1 is the seat cushion body, 2 is the power interface, 3 is 12 vibration motors, and 4 is the circuit board.

[0056] Figure 6 Schematic diagram of the warning workflow of the odor generator module provided in an embodiment of the present invention.

[0057] Figure 7 This is a schematic diagram of the structure of the odor generator provided in an embodiment of the present invention, wherein 5 is the fragrance chamber, 6 is the injection port, 7 is the fragrance spray port, 8 is the power interface, and 9 is the atomizer. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] refer to Figure 1 The embodiment of the present invention discloses a car driving risk warning method considering motion sickness factors, which mainly includes the following steps:

[0060] Detect current driving mode;

[0061] When it is detected that the current driving mode is automatic driving, the human factors affecting driving, including the number of motion sickness, are obtained in the automatic driving state;

[0062] Calculating a driving risk score in an autonomous driving state based on the human factors and corresponding weights;

[0063] When it is detected that the current driving mode is switched from automatic driving to manual driving, the vehicle-related factors and the human-related factors affecting driving in the manual driving state are obtained;

[0064] Using the network hierarchical analysis driving risk scoring model, the vehicle factors and human factors that affect driving in manual driving conditions are analyzed to obtain the driving risk score in manual driving conditions.

[0065] Based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state, a comprehensive car driving score result is obtained.

[0066] In the present invention, the current driving mode is detected to determine whether the current driving mode is automatic driving or manual driving. A comprehensive judgment can be made based on the driver's behavior, vehicle status, and system operation status. For example, when the driver's hands are away from the steering wheel, and his feet are away from the brake or accelerator, and the vehicle is in a relatively stable operating state, it can be determined that the current driving mode is automatic driving. It can also be determined by whether the automatic driving mode on the driving vehicle is activated.

[0067] When the current driving mode is detected as autonomous, the human factors that influence driving under autonomous driving conditions, including the number of motion sickness episodes, are obtained. Based on these human factors and their corresponding weights, a driving risk score for the autonomous driving state is calculated. Furthermore, when the current driving mode switches from autonomous driving to manual driving, the vehicle and human factors that influence driving under manual driving conditions are obtained. Using a network analytic hierarchy process driving risk scoring model, these vehicle and human factors that influence driving under manual driving conditions are analyzed to obtain a driving risk score for the manual driving state.

[0068] The specific steps of the present invention are described in detail below:

[0069] In an embodiment of the present invention, the human factors that affect driving in the automatic driving state, including the number of motion sickness, specifically include: the number of times the driver closes his eyes, yawns, nods, answers or makes phone calls, does not look forward for a long time, is not in the driving position, smokes, takes time to react, and the number of motion sickness caused by switching driving modes. The above factors are used to evaluate the driving risk in the automatic driving state. Specifically, the driving risk score in the automatic driving state can be calculated based on the human factors and the corresponding weights.

[0070] During the specific implementation process, for the human factors in the autonomous driving state, refer to the autonomous driving risk scoring factor criteria table and the autonomous driving risk factor weight table.

[0071] Table 1. Criteria for autonomous driving risk scoring factors

[0072]

[0073]

[0074] Table 2. Weights of risk factors for autonomous driving risks

[0075]

[0076] The calculation formula for the comprehensive score S1 of autonomous driving risk is:

[0077] S1=S′1W′1

[0078] In the formula: W′1 is the global weight of the indicator during autonomous driving, and S′1 is the score of each factor of the driver during autonomous driving.

[0079] refer to Figure 2 、 Figure 3 In an embodiment of the present invention, the vehicle factors and human factors that affect driving in a manual driving state include the following contents: the vehicle factors include the number of sudden accelerations, sudden decelerations, sharp turns, speeding times and driving time during driving; the human factors include the number of times the eyes are closed, the number of times the driver yawns, the number of times the head is nodded, the number of times the phone is answered or made, the number of times the driver does not look forward for a long time, the number of times the driver is not in the driving position, the number of times the driver smokes and the number of times both hands are off the steering wheel at the same time during driving.

[0080] Table 3 Manual driving risk scoring factors

[0081]

[0082] Table 4 Manual driving risk scoring factor criteria

[0083]

[0084]

[0085]

[0086] In the manual driving model, the present invention uses a driving risk scoring model based on network hierarchical analysis to analyze the vehicle factors and human factors that affect driving in the manual driving state, and obtains a driving risk score in the manual driving state, specifically including:

[0087] Determine the influence weights of vehicle factors and human factors on driving status as the main criteria;

[0088] Get factor group E i Factor e in ij As a secondary criterion, the factor e was obtained using the satty1-9 scale method. ij For factor group E i The influence degree of other factors is obtained ij The submatrix W ij , factor group E i The subscript i is 1 or 2. When i is 1, it indicates the vehicle factor group, and when i is 2, it indicates the human factor group. The sub-matrices of all factors are combined into a super matrix W.

[0089] Compare the importance of each factor in factor group E1 to each factor in factor group E2, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j …anj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A;

[0090] Use matrix A to weight the super matrix W to obtain a weighted super matrix;

[0091] The weighted supermatrix is ​​taken to the limit to obtain the limit supermatrix ∞, where the column vector of the matrix is ​​the global weight of each factor;

[0092] The original assessment of each factor is multiplied by the corresponding global weight to obtain the final risk score of each factor.

[0093] The driving risk scoring model based on the network analysis method adopted in the present invention is further explained below.

[0094] The construction of the network analysis hierarchy process algorithm mainly includes the following steps:

[0095] ① Establish network structure

[0096] The construction of network structure requires the determination of various factors ij (i=1,2,3,…,n; j=1,2,3,…,n n ), which can be systematically determined through expert discussions or researcher brainstorming.

[0097] ②Construct a super matrix

[0098] In the main criterion P m Next, factor group E j A factor e among (j=1, 2, 3, ..., n) jl (l=1,2,3,…,n j ) as a secondary criterion, for factor group E i All effects in jl The importance of the factors is compared pairwise, and the scaling method of Table 4satty1-9 is used to compare and assign values, construct a judgment matrix, and then use the characteristic root method to calculate each column of the judgment matrix to obtain the normalized eigenvector: To ensure the rationality and credibility of the judgment matrix, the matrix must be checked for consistency:

[0099]

[0100] In the formula: when CR is less than 0.1, it indicates that the inconsistency of the judgment matrix is ​​within the allowable range and passes the consistency test, where RI represents the average consistency index, which can be obtained by looking up the table.

[0101] Table 5 Satty1-9 scale table

[0102]

[0103] Factor group E i Each factor e i For factor E j Each factor e jl The normalized eigenvector permutation and combination of the influence degree is recorded as matrix W ij , where i = 1, 2, ... n, j = 1, 2, ... n, repeat this step for all n factor groups to obtain the super matrix, denoted as W:

[0104]

[0105] ③Construct weighted super matrix

[0106] According to each criterion, a super matrix can be calculated, so that m super matrices are obtained, and each super matrix W ij The sub-matrices in W are all normalized, but ij No normalization operation has been performed. Therefore, in the analysis of each super matrix, the factor E i (i=1,2,3,…,n) and the subcriteria E j (j=1, 2, 3, ..., n) to compare the importance of each pair, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j …a nj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A:

[0107]

[0108] The supermatrix W is weighted by the matrix A to obtain the weighted supermatrix:

[0109]

[0110] ④Calculate the extreme super matrix and the weight of each factor

[0111] The weighted supermatrix is ​​taken to the limit, that is, its self-multiplication reaches a convergent and stable extreme value, that is, the value will be fixed and no longer change. This matrix is ​​called the limit supermatrix. At this time, the column vector of the matrix is ​​the global weight W' of each factor.

[0112] The present invention adopts the network analytic hierarchy process to construct a driving risk scoring model under the manual driving mode. The driving risk scoring index weights in the model are compared and assigned using the satty1-9 scaling method and calculated using the yaanp software.

[0113] In the specific implementation, with the help of the opinions and suggestions of passenger car drivers and university experts, the judgment matrix can be constructed according to formulas (1)-(6) and the effective weights can be determined after completing a one-time test. The results of the human factor indicator weights and consistency test are shown in Table 6.

[0114] Table 6 Human factor index weights and consistency test results under manual driving mode

[0115]

[0116] As shown in Table 6, the consistency test value of the human factor judgment matrix is ​​0.0899 (<0.1), indicating that it has passed the test and meets the requirements. The vehicle factor indicators in this model are processed using the same method to obtain the final weight results, as shown in Table 7.

[0117] Table 7 Weights of the driving risk scoring index system in manual driving mode

[0118]

[0119]

[0120] In summary, the calculation formula for the comprehensive score of manual driving risk S2 is:

[0121] S2=S′2W′2

[0122] Where: W2′ is the global weight of the indicator during manual driving, and S2′ is the driver's score for each factor during manual driving.

[0123] Finally, the driving risk score S1 in the automatic driving state and the driving risk score S2 in the manual driving state are weighted and summed to obtain the comprehensive driving score S of the car.

[0124] After obtaining the comprehensive car driving score results, they can be graded into three risk levels: low, medium, and high.

[0125] Specifically, S represents the comprehensive driving risk score, with a score range of [0-100]. According to the scoring criteria of the secondary indicators, the higher the frequency of risky behaviors, the lower the score. The comprehensive score naturally forms a continuous distribution from high to low. The interval is set by the quartile method to achieve the division of three risk levels: low, medium, and high, as shown in Table 8.

[0126] Table 8 Comprehensive scoring level classification

[0127]

[0128] The Driving Risk Warning System consists of comprehensive risk scoring software, a vibrating seat cushion, and an odor generator. Each warning module is interconnected via a controller, allowing the driver to make timely adjustments based on feedback from each module, ensuring a safe driving environment.

[0129] The early warning device may include a vibration seat cushion module and an odor generating module. The vibration seat cushion module and the odor generating module are respectively described below through specific embodiments.

[0130] The workflow of the vibration seat cushion module is as follows Figure 4 As shown in FIG, in a specific embodiment, the vibration seat cushion is composed of a seat cushion cover, a vibration unit, a control unit and a signal receiving module. Twelve vibration motors are installed in the seat cushion cover and are evenly distributed. The control unit controls the vibration intensity of the motors. A receiving module is integrated into the vibration seat cushion, which can receive signals from the risk scoring system. The controller analyzes the risk level based on the received signal and triggers the corresponding response mechanism. The partial structure of the vibration seat cushion module is shown in FIG. Figure 5 As shown, the seat cushion includes a seat cushion body 1, a power interface 2, 12 vibration motors 3 and corresponding circuit boards 4.

[0131] The design of the seat cushion must meet ergonomic requirements, with materials, dimensions, and vibration frequencies suitable for human wear. The vibration frequency will affect the driver's mood and physical changes. The three evaluation indicators of human vibration perception ratio, vertical fourth power vibration dose value, and annoyance rate affect the comfort of human exposure to whole-body vibration. In the frequency range of 4-8Hz, internal organs are prone to resonance effects, and in the frequency range of 8-12.5Hz, the biomechanical effects of vibration energy on the spinal system are particularly significant.

[17] Therefore, the vibration frequency range is selected as 0-3Hz, which is reasonably distributed to each risk level. At the same time, the vibration intensity level is also set to 3 levels, as shown in Table 9.

[0132] Table 9 Correspondence between vibration frequency and vibration intensity at different risk levels

[0133]

[0134] like Figure 6 As shown in the figure, when the driver is detected to be engaging in dangerous driving, the odor generator releases a pungent odor to warn the driver to drive safely. The odor generator consists of a liquid storage container, an atomizer, a signal receiving module, and a controller. The receiver module integrated into the odor generator can receive signals from the risk scoring system. The controller analyzes the risk level based on the received signals and triggers the corresponding response mechanism.

[0135] In one specific implementation, in-car fragrances can be used. Research on the effects of in-car fragrances on user olfactory preferences and fatigue awakening methods found that an 80% concentration of mint fragrance is most effective in invigorating spirits and increasing alertness. Therefore, the scent generator continuously blows out 80% mint gas for 0-10 seconds based on the driving risk level. To ensure regional effectiveness and timeliness of scent transmission, the scent generator is designed to be located in the driver's headrest. The schematic diagram of the scent generator is shown below. Figure 7 As shown, the scent generator includes a fragrance chamber 5, an injection port 6, a fragrance spray port 7, a power interface 8 and an atomizer 9.

[0136] This paper, considering that driver status and behavior directly impact driving safety, proposes a driving risk warning method and designs a related warning device. It also constructs a driving risk scoring system and establishes a comprehensive driving risk scoring model using the analytic network hierarchy process. This model calculates a comprehensive risk score based on the driver's behavior and status during driving. A controller analyzes the comprehensive score and triggers a vibrating seat cushion and an odor generator to issue warnings, further ensuring driver safety. The next step is to continuously optimize the functional mechanisms of the existing system architecture, significantly enhancing driver and passenger safety by improving risk identification accuracy and adaptive learning capabilities. It is hoped that this paper will provide valuable insights into the research and implementation of driving safety warning systems.

[0137] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0138] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A car driving risk warning method considering motion sickness factors, characterized in that: include: Detect current driving mode; When it is detected that the current driving mode is automatic driving, the human factors affecting driving, including the number of motion sickness, are obtained in the automatic driving state; Calculating a driving risk score in an autonomous driving state based on the human factors and corresponding weights; When it is detected that the current driving mode is switched from automatic driving to manual driving, the vehicle-related factors and the human-related factors affecting driving in the manual driving state are obtained; Using the network hierarchical analysis driving risk scoring model, the vehicle factors and human factors that affect driving in manual driving conditions are analyzed to obtain the driving risk score in manual driving conditions. Based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state, a comprehensive car driving score result is obtained.

2. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 1, characterized in that: Human factors that affect driving in an autonomous driving state, including the number of motion sickness episodes, include: The number of times the driver closes his eyes, yawns, nods, answers or makes phone calls, does not look forward for a long time, is not in the driving position, smokes, reaction time to take over, and the number of times he gets carsick due to switching driving modes.

3. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 1, characterized in that: The vehicle factors and human factors that affect driving in manual driving state include the following: The following vehicle factors include the number of sudden accelerations, sudden decelerations, sharp turns, speeding, and driving time during driving; The human factors include the number of times the driver closes his eyes, yawns, nods, answers or makes phone calls, does not look forward for a long time, is not in the driving position, smokes, and takes both hands off the steering wheel during driving.

4. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 1, characterized in that: The driving risk scoring model based on network analysis is used to analyze the vehicle factors and human factors that affect driving in manual driving conditions, and obtain the driving risk score in manual driving conditions, including: Determine the influence weights of vehicle factors and human factors on driving status as the main criteria; Get factor group E i Factor e in ij As a secondary criterion, the factor e was obtained using the satty1-9 scale method. ij For factor group E i The influence degree of other factors is obtained ij The submatrix W ij , factor group E i The subscript i is 1 or 2. When i is 1, it indicates the vehicle factor group, and when i is 2, it indicates the human factor group. The sub-matrices of all factors are combined into a super matrix W. Compare the importance of each factor in factor group E1 to each factor in factor group E2, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j … a nj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A; Use matrix A to weight the super matrix W to obtain a weighted super matrix; The weighted supermatrix is ​​taken to the limit to obtain the limit supermatrix ∞, where the column vector of the matrix is ​​the global weight of each factor; The original assessment of each factor is multiplied by the corresponding global weight to obtain the final risk score of each factor.

5. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 1, characterized in that: Based on the driving risk scores in the automatic driving state and the manual driving state, the comprehensive driving score results are obtained, including: The driving risk score in the automatic driving state and the driving risk score in the manual driving state are weighted and summed to obtain the comprehensive driving score result.

6. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 5, characterized in that: It also includes obtaining a risk assessment level based on the comprehensive car driving score, including: The comprehensive car driving score results are divided according to the set threshold to obtain the corresponding risk assessment level, including low risk, medium risk and high risk.

7. The method for early warning of automobile driving risk taking motion sickness factors into consideration according to claim 1, characterized in that: It also includes using a corresponding risk warning module to issue an early warning according to the corresponding risk assessment level, and the risk warning module includes a vibration seat cushion early warning module and an odor generator module.

8. A car driving risk warning device taking motion sickness factors into consideration, characterized in that: include: A driving mode detection module is used to detect and determine the current driving mode; The autonomous driving data acquisition module obtains human factors that affect driving, including the number of motion sickness episodes, during autonomous driving. An autonomous driving risk assessment module, configured to calculate a driving risk score in an autonomous driving state based on the human factors and corresponding weights; The manual driving data acquisition module, when detecting that the current driving mode switches from automatic driving to manual driving, obtains the vehicle-related factors and human-related factors that affect driving in the manual driving state; The manual driving risk assessment module is used to analyze the vehicle factors and human factors that affect driving in the manual driving state using the driving risk scoring model of the network hierarchical analysis to obtain the driving risk score in the manual driving state; The driving risk comprehensive assessment module is used to obtain a comprehensive driving score result of the car based on the driving risk score in the automatic driving state and the driving risk score in the manual driving state.

9. The car driving risk warning device considering motion sickness factors according to claim 8, characterized in that: The driving risk scoring model based on network analysis is used to analyze the vehicle factors and human factors that affect driving in manual driving conditions, and obtain the driving risk score in manual driving conditions, including: Determine the influence weights of vehicle factors and human factors on driving status as the main criteria; Get factor group E i Factor e in ij As a secondary criterion, the factor e was obtained using the satty1-9 scale method. ij For factor group E i The influence degree of other factors is obtained ij The submatrix W ij , factor group E i The subscript i is 1 or 2. When i is 1, it indicates the vehicle factor group, and when i is 2, it indicates the human factor group. The sub-matrices of all factors are combined into a super matrix W. Compare the importance of each factor in factor group E1 to each factor in factor group E2, establish a judgment matrix, and then perform normalization to obtain the normalized eigenvector (a 1j a 2j … a nj ) T If a factor group does not affect E j , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix A; Use matrix A to weight the super matrix W to obtain a weighted super matrix; The weighted supermatrix is ​​taken to the limit to obtain the limit supermatrix ∞, where the column vector of the matrix is ​​the global weight of each factor; The original assessment of each factor is multiplied by the corresponding global weight to obtain the final risk score of each factor.

10. The car driving risk warning device considering motion sickness factors according to claim 8, characterized in that: It also includes a risk assessment level division module, which is used to divide the comprehensive car driving score results according to the set threshold value to obtain the corresponding risk assessment level, including low risk, medium risk and high risk.

Images