Instrument panel light control method and system based on risk estimation and man-machine credibility

Abstract

The invention discloses an instrument panel light control method and system based on risk estimation and man-machine credibility, and the method comprises the following steps: collecting and extracting the behavior information of a driver, including the state information of the eyes, hands and feet of the driver; collecting a road traffic environment image, and obtaining a driving environment and traffic event information; taking the behavior information of the driver as an input pre-constructed credibility evaluation model, and outputting a credibility evaluation value of the driver on the automatic driving system at the current moment; the current automatic driving risk is evaluated according to the driving environment and the traffic event information, and an automatic driving system risk evaluation result is obtained; and according to the credibility evaluation value of the driver at the current moment and the automatic driving risk evaluation result, the adaptation degree between the credibility and the automatic driving system risk is calculated, the threshold value interval of the adaptation degree is judged, and light prompts of different colors are correspondingly controlled according to different threshold value intervals. According to the invention, the coordination of man-machine co-driving cooperation can be optimized, and the traffic safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving, and in particular to a method and system for controlling instrument panel lighting based on risk estimation and human-machine trust. Background Art

[0002] As a medium for information exchange between the driver and the vehicle, the human-computer interaction system provides the driver with crucial information during the driving process, including vehicle status, environmental perception, and operational intent. This information forms a crucial foundation for the driver's perception of risk situations and driving behavior decisions, directly impacting driving safety. Currently, human-computer interaction is developing in a multimodal manner, providing richer information content and transmitting information from a wider range of sensory channels and combinations. However, this also introduces negative consequences, such as increased cognitive load and driving distraction. Therefore, human-computer interaction significantly impacts driving safety, necessitating research into how to optimize human-computer interaction systems to enhance driver trust in shared driving environments.

[0003] At present, the information prompts about autonomous driving on the human-computer interaction interface are relatively simple, which cannot enable drivers to quickly and accurately understand the risk response capabilities of the autonomous driving system, resulting in excessive or insufficient trust, which in turn affects safe driving; on the one hand, most of the current smart connected vehicles use LCD instrument panels to display autonomous driving information, requiring drivers to actively identify information. This method is not eye-catching and lacks intuitiveness, which will increase the driver's cognitive load. Summary of the Invention

[0004] The main purpose of the present invention is to provide an instrument panel lighting control method and system based on risk assessment and human-machine trust, to achieve intuitive and dynamic automatic driving information prompts, to adapt to the dynamic changes in the driver's attention, trust, and ability to predict risk events during driving, which can significantly reduce the driver's cognitive load, optimize the coordination of human-machine co-driving, and thus improve traffic safety.

[0005] The technical solution adopted in the present invention is:

[0006] A method for controlling instrument panel lighting based on risk assessment and human-machine trust is provided, comprising the following steps:

[0007] Collect and extract driver behavior information, including the driver's eye, hand, and foot status information;

[0008] Collect road traffic environment images and obtain driving environment and traffic event information;

[0009] The driver's behavior information is input into a pre-built trust assessment model, which then processes the information and outputs the driver's trust assessment value for the autonomous driving system at the current moment.

[0010] Evaluate the current autonomous driving risk based on the driving environment and traffic incident information to obtain the autonomous driving system risk assessment results, including the risk assessment coefficient of the autonomous driving system's technical capabilities, the risk assessment coefficient of the driving environment, and the risk assessment coefficient of traffic incidents;

[0011] The degree of compatibility between the driver's trustworthiness and the risk of the autonomous driving system is calculated based on the driver's trustworthiness assessment value at the current moment and the autonomous driving risk assessment results. Different colors of light prompts are controlled accordingly based on the threshold range of the compatibility.

[0012] Following the above technical solution, the trust evaluation model calculates each risk assessment coefficient through the Kalman filter algorithm.

[0013] Following the above technical solution, the trust evaluation value is calculated based on the probability of the driver's hands being ready to take over, the probability of the driver's feet being ready to take over, and the probability of the driver's eyes being ready to take over.

[0014] Following the above technical solution, the state of the driver's hands ready to take over is specifically: the grip sensor installed on the steering wheel detects the state of the driver's hands touching the steering wheel with one or both hands, resting on the steering wheel, or lightly touching the bottom edge of the steering wheel. Assuming that during unmanned driving, the driver is in a state of trust and his hands do not touch the steering wheel. Only when the driver is in a state of distrust and touches the steering wheel, the grip sensor will detect the corresponding contact signal. If the force detected by the grip sensor is less than a preset threshold, it is considered that the driver has not taken over the steering wheel, but is in a state of the driver's hands ready to take over.

[0015] Following the above technical solution, the state of the driver's foot ready to take over is specifically: through the pressure sensors installed on the accelerator and brake pedals, the state of the driver's toes lightly resting on the brake pedal is detected. Assuming that during the unmanned driving process, the driver is in a state of trust and his feet do not touch the accelerator or brake pedal. Only when the driver's foot touches the accelerator or brake pedal, the pressure sensor will detect the corresponding contact signal. If the applied pressure detected by the pressure sensor is less than a preset threshold, it is considered that the driver has not taken over the accelerator or brake pedal, but is in a state of the driver's foot ready to take over.

[0016] Following the above technical solution, the driver's eye gaze points collected by the eye tracker are specifically divided into the dashboard, the road ahead, the interactive vehicle on the right, and other areas. The state where the eye gaze point is in the dashboard area is the eye ready to take over state.

[0017] Following the above technical solution, if it is determined based on the driver's behavior information that the driver has not paid attention to the driving environment or the dashboard for a certain period of time, the driver is judged to be in a distracted state and the red light is controlled to flash continuously; if it is determined based on the risk assessment results of the autonomous driving system that there is a dangerous event in the driving environment or the vehicle is in a dangerous driving environment, the red light is controlled to flash continuously.

[0018] According to the above technical solution, if the value of the adaptability is in the first range, the driver is in an abnormally over-trusting state, and the red light is turned on;

[0019] If the adaptability value is in the second range, the driver is in a state of significant over-trust, and the orange light is turned on;

[0020] If the value of the adaptability is in the third interval, the driver is in a general over-trust state and the yellow light is turned on;

[0021] If the adaptability value is in the fourth interval, the driver is in a slightly over-trust state and the green light is turned on;

[0022] If the adaptability value is in the fifth interval, the driver is in a state of slight over-trust and the blue light is turned on.

[0023] The present invention also provides an instrument panel lighting control system based on risk assessment and human-machine trust, comprising:

[0024] Driver behavior information collection module, used to collect and extract driver behavior information, including driver's eye, hand, and foot status information;

[0025] Traffic environment information acquisition module, used to collect road traffic environment images and obtain driving environment and traffic event information;

[0026] A trust evaluation module is used to input the driver's behavior information into a pre-built trust evaluation model, and after processing by the trust evaluation model, output the driver's trust evaluation value in the autonomous driving system at the current moment;

[0027] The risk assessment module is used to evaluate the current autonomous driving risk based on the driving environment and traffic incident information, and obtain the risk assessment results of the autonomous driving system, including the risk assessment coefficient of the autonomous driving system's technical capabilities, the risk assessment coefficient of the driving environment, and the risk assessment coefficient of traffic incidents;

[0028] A compatibility calculation module is used to calculate the compatibility between the trust level and the risk of the autonomous driving system based on the current driver's trust evaluation value and the autonomous driving risk assessment result;

[0029] The lighting control module is used to control lighting prompts of different colors according to the threshold range of the adaptability.

[0030] The present invention also provides a computer storage medium storing a computer program executable by a processor, wherein the computer program executes the instrument panel lighting control method based on risk assessment and human-computer trust as described in the above technical solution.

[0031] The beneficial effects of the present invention are as follows: the present invention collects driver behavior information parameters and environmental parameters around the vehicle, and comprehensively considers the driver's driving psychology and risk factors in the traffic environment, calculates the driver's trust evaluation value of the automatic driving system and the automatic driving system risk assessment result, thereby calculating the adaptability between the trust and the automatic driving system risk, and controls light prompts of different colors accordingly by judging the different threshold intervals of the adaptability, thereby providing the driver with intuitive and efficient information prompts and improving the safety of automatic driving.

[0032] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is a flow chart of a method for controlling instrument panel lighting based on risk assessment and human-machine trust in an embodiment of the present invention;

[0035] Figure 2 This is an overall structural diagram of an instrument panel lighting control system according to an embodiment of the present invention;

[0036] Figure 3 1 is a three-view diagram of an instrument panel lighting control system according to an embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of the use of an instrument panel lighting control system according to an embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the structure of an instrument panel lighting control system based on risk assessment and human-machine trust in an embodiment of the present invention;

[0039] Figure numerals: 1. LCD instrument panel; 2. Reflector; 3. Light guide groove; 4. Flexible light guide; 5. Sunshade cap; 6. RGB lamp head; 7. Circuit board. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0041] It should be noted that the illustrations provided in the embodiments of the present invention are only schematic illustrations of the basic concept of the present invention. Therefore, the drawings only show components related to the present invention and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0042] In the present invention, it should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" and the like are used to indicate positions or locations based on those shown in the accompanying drawings. These terms are intended solely to facilitate the description of the present application and to simplify the description. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used solely for descriptive and distinguishing purposes and should not be construed as indicating or implying relative importance.

[0043] In addition, it should be noted that the features of the various embodiments of the present invention may be combined or coupled in part or in whole, and, as will be appreciated by those skilled in the art, may interact and operate in different ways. Each embodiment may be implemented independently of one another or in an associated relationship.

[0044] Example 1

[0045] like Figure 1 As shown, the instrument panel lighting control method based on risk assessment and human-machine trust in an embodiment of the present invention mainly includes the following steps:

[0046] S1. Collect and extract driver behavior information, including driver's eye, hand, and foot status information;

[0047] S2. Collect road traffic environment images and obtain driving environment and traffic event information;

[0048] S3. Inputting the driver's behavior information into a pre-built trust assessment model, and after processing by the trust assessment model, outputting the driver's trust assessment value for the autonomous driving system at the current moment;

[0049] S4. Evaluate the current autonomous driving risk based on the driving environment and traffic incident information to obtain an autonomous driving system risk assessment result, including a risk assessment coefficient for the autonomous driving system's technical capabilities, a risk assessment coefficient for the driving environment, and a risk assessment coefficient for traffic incidents;

[0050] S5. Calculate the degree of compatibility between the driver's trustworthiness and the risk of the autonomous driving system based on the current driver's trustworthiness assessment value and the autonomous driving risk assessment result, and control light prompts of different colors accordingly based on the threshold range of the compatibility.

[0051] Among them, the trust evaluation model can calculate various risk assessment coefficients through the Kalman filtering algorithm.

[0052] The trust evaluation value can be specifically calculated based on the probability that the driver's hands are ready to take over, the probability that the feet are ready to take over, and the probability that the eyes are ready to take over.

[0053] The state of the driver's hands ready to take over is specifically: the grip force sensor installed on the steering wheel detects the state of the driver's hands touching the steering wheel with one or both hands, resting on the steering wheel or lightly touching the bottom edge of the steering wheel. Assuming that during unmanned driving, the driver is in a state of trust and his hands do not touch the steering wheel. Only when the driver is in a state of distrust and touches the steering wheel, the grip force sensor will detect the corresponding contact signal. If the force detected by the grip force sensor is less than a preset threshold, it is considered that the driver has not taken over the steering wheel, but is in a state of the driver's hands ready to take over.

[0054] The state of the driver's foot ready to take over is specifically: the state of the driver's toes lightly resting on the brake pedal is detected by the pressure sensors installed on the accelerator and brake pedals. Assuming that during the unmanned driving process, the driver is in a state of trust and his feet do not touch the accelerator or brake pedal. Only when the driver's feet touch the accelerator or brake pedal will the pressure sensor detect the corresponding contact signal. If the applied pressure detected by the pressure sensor is less than a preset threshold, it is considered that the driver has not taken over the accelerator or brake pedal, but is in the state of the driver's foot ready to take over.

[0055] Furthermore, the driver's eye gaze points collected by the eye tracker are specifically divided into the dashboard, the road ahead, the interactive vehicle on the right, and other areas. The state where the eye gaze point is in the dashboard area is the eye ready to take over state.

[0056] Specifically, if it is determined based on the driver's behavior information that the driver has not paid attention to the driving environment or the instrument panel for a certain period of time, the driver is judged to be in a distracted state and the red light is controlled to flash continuously.

[0057] If the risk assessment results of the autonomous driving system determine that there is a dangerous event in the driving environment or the vehicle is in a dangerous driving environment, the red light will be controlled to flash continuously.

[0058] In step S5, if the value of the adaptability is in the first range, the driver is in an abnormally over-trusting state, and the red light is controlled to turn on;

[0059] If the adaptability value is in the second range, the driver is in a state of significant over-trust, and the orange light is turned on;

[0060] If the value of the adaptability is in the third interval, the driver is in a general over-trust state and the yellow light is turned on;

[0061] If the adaptability value is in the fourth interval, the driver is in a slightly over-trust state and the green light is turned on;

[0062] If the adaptability value is in the fifth interval, the driver is in a state of slight over-trust and the blue light is turned on.

[0063] This embodiment collects driver behavior information parameters and environmental parameters around the vehicle, and comprehensively considers the driver's driving psychology and risk factors in the traffic environment to calculate the driver's trust assessment value in the automatic driving system and the automatic driving system risk assessment result, thereby calculating the adaptability between the trust and the automatic driving system risk. By judging the different threshold intervals where the adaptability lies, different colors of light prompts are controlled accordingly, thereby realizing intuitive and dynamic automatic driving information prompts, adapting to the dynamic changes in the driver's attention, trust, and ability to predict risk events during driving, significantly reducing the driver's cognitive load, optimizing the coordination of human-machine co-driving, and thus improving traffic safety.

[0064] Example 2

[0065] This embodiment is based on embodiment 1 and provides a specific calculation example.

[0066] The specific calculation process of the driver's trust evaluation value is as follows:

[0067] Establishing an objective trust equation:

[0068] T(t k+1 )=f(t k ,T(t k ),L(t k ),M(t k ),N(t k ))

[0069] Among them, T(t k+1 ) is t k+1 The trust degree at the moment is the true value to be estimated, T(tk ) is t k The trust level at the moment, L(t k ),M(t k ), N(t k ) represents the Boolean value of the human-computer interaction scheme. k For a smart connected car in motion, if the human-computer interaction solution is to display the current risk events and response measures on the dashboard at the same time, then L(t k )=1,M(t k )=0,N(t k )=0; If the human-computer interaction solution is to only display the current risk event on the dashboard, then L(t k )=0,M(t k )=1,N(t k )=0; If the human-computer interaction solution is to only display on the dashboard how the system is prepared to respond to risk events, then L(t k )=0,M(t k )=0,N(t k )=1. Therefore, for f, we have f:

[0070] [t0, t f ]×[T min ,T max ]×{0,1} 3 →[T min ,T max ]

[0071] The observed variables and trust satisfy the equation:

[0072]

[0073] Among them, h(t k ) is t k The probability that the driver's hands are ready to take over at any time is specifically detected by the grip sensor installed on the steering wheel, which detects the state of the driver's one or both hands touching the steering wheel, resting on the steering wheel, or lightly touching the bottom edge of the steering wheel. Assume that during unmanned driving, when the driver is in a state of trust, his hands are usually placed on his legs and do not touch the steering wheel. Only when the driver is not in a state of trust and touches the steering wheel, the grip sensor will detect the corresponding contact signal. When the driver does not apply enough grip force, although the grip sensor can detect the contact state, due to the small force, it is not enough to affect the rotation state of the steering wheel, that is, if the force F detected by the grip sensor is h (t k ) is less than a preset threshold F threshold , the driver is not considered to have taken over the steering wheel, but is in a state of preparing to take over.

[0074] f(t k ) is t k The probability that the driver's feet are ready to take over at any time, specifically, the state where the driver's toes are lightly placed on the accelerator or brake pedal is detected by the pressure sensors installed on the accelerator and brake pedals. Assuming that during unmanned driving, when the driver is in a state of trust, his feet usually do not touch the accelerator or brake pedal, but are placed outside the accelerator and pedal, such as under the pedal, under the seat, and near the door panel area. Only when the driver's feet touch the accelerator or brake pedal, the pressure sensor will detect the corresponding contact signal. When the driver's foot does not apply enough pressure, the pressure sensor can detect the contact state, but because the applied pressure is small, it is not enough to change the opening and closing degree of the brake pedal or accelerator, that is, if the applied pressure P detected by the pressure sensor is f (t k ) is less than a preset threshold P threshold , it is not considered that the driver has taken over the accelerator or brake pedal, but is in a state of preparing to take over.

[0075] The driver's eye gaze points collected by the eye tracker are divided into the instrument panel, the road ahead, the interactive vehicle on the right, and other areas, e(t k ) is t k The probability that the driver's eye gaze is in the instrument panel area at any given moment.

[0076] Therefore, for have

[0077]

[0078] Furthermore, assuming that f and The function is linear, time-invariant, and contains random terms based on individual driver differences. Furthermore, the observed variables are assumed to follow a Gaussian distribution and are independent of events and each other. Considering the discreteness of the observed variables and trust, the LT1 system state space equation is used to represent the driver's trust:

[0079]

[0080] Among them, A, B, H are the coefficient matrices to be determined, and there is w(t k ) is the process noise, with covariance Q, and obeys Gaussian distribution: w(t k )~N(0,Q);v(t k ) is the process noise, with covariance R, and obeys Gaussian distribution: v(t k )~N(0,R).

[0081] Furthermore, based on the Kalman filter solution algorithm, the confidence and covariance are initialized:

[0082]

[0083] in, Refers to the initial trust, C refers to the coefficient matrix to be determined, and C = [c 11 c 21 c 31 ] T , h(t0) refers to the frequency of the driver's hand movements indicating the state of preparation for takeover at the initial moment; f(t0) refers to the frequency of the driver's foot movements indicating the state of preparation for takeover at the initial moment; e(t0) refers to the frequency of the driver's eye gaze on the instrument panel at the initial moment; refer to The covariance of . Calculate the Kalman gain:

[0084]

[0085] Where K refers to the Kalman gain; Refers to ∑T(t k ) is the covariance of the observation noise; ∑v refers to the standard deviation of the observation noise.

[0086] Furthermore, the observation error is calculated:

[0087]

[0088] in, Finger k The frequency with which the driver's hand movements indicate a state of readiness to take over; Finger k The frequency with which the driver's foot movements indicate a readiness to take over; Finger k The frequency of the driver's eye gaze on the instrument panel at any given moment; Finger k The prior estimate of the moment is the estimated trust of the subject.

[0089]

[0090] Where u refers to the error between the estimated observation value and the actual observation value;

[0091] Furthermore, the posterior state estimate is calculated:

[0092]

[0093] Among them, T(t k ) refers to t k The posterior estimate of the posterior estimate is the optimal estimate of the subject's trust; ∑T(t k) refers to T(t k ), update the prior estimate at the next moment:

[0094]

[0095] in, Finger k+1 The prior trust at the moment, that is, the estimated trust of the driver at the current moment; refer to covariance of σ w Refers to the standard deviation of the estimated process noise.

[0096] Furthermore, according to the driver's trust level T(t k+i ), and the various risk assessment coefficients calculated by the risk assessment module, including system technical capability R1, driving environment R2, and traffic events R3, the following calculation steps are used to obtain the adaptability M(T(t k+1 ),R):

[0097]

[0098] Among them, R refers to the multi-dimensional risk assessment vector of the system, which expands the trust into a three-dimensional risk assessment vector:

[0099]

[0100] Construct the covariance matrix S:

[0101]

[0102] in Refers to the variance of the three risk factors, σ 12 , σ 13 , σ 23 Refers to the covariance between different risk factors, reflecting their correlation. Substitute the trust vector T′, the system risk assessment vector R, and the covariance matrix S into the following formula:

[0103]

[0104] Furthermore, the color space and flashing period of the lamp head RGB are controlled according to the value of the adaptability. One of the control decision schemes for the instrument panel lighting is:

[0105] If there are dangerous events in the driving environment, including but not limited to slope collapse, traffic accidents, sudden braking of the vehicle in front, speeding, and side overtaking, the control light head will turn red and flash continuously;

[0106] If the intelligent connected vehicle is in a dangerous driving environment, including but not limited to heavy snow, fog, heavy rain, or mountain roads, the headlight will be controlled to flash red continuously.

[0107] The driver is in a distracted state, and the driver does not pay attention to the driving environment or the instrument panel for more than 20 minutes, that is, T distract >20min, the control lamp will be red and flash continuously;

[0108] The driver is in an abnormal over-trust state, specifically τ1≤M(T(t k+1 ),R)<τ0 and the trust is greater than the risk assessment, there is no dangerous event or dangerous environment, then the light head is controlled to be red. The trust is greater than the risk assessment, that is, the driver's trust at the current moment T(t k+1 ) is higher than the risk assessment vector R in comprehensive evaluation. Specifically, the trust T(t k+1 ) must be greater than the weighted sum of the risk assessment vector R: T(t k+1 )>α1·R1+α2·R2+α2·R2, where α1, α2, and α3 are weighted coefficients of each dimension;

[0109] The driver is in a state of significant over-trust, specifically τ2≤M(T(t k+1 ),R)<τ1 and the trust level is greater than the risk assessment, and there is no dangerous event or dangerous environment, then the lamp head is controlled to orange;

[0110] The driver is in a general over-trust state, specifically τ3≤M(T(t k+1 ),R)<τ2 and the trust level is greater than the risk assessment, and there is no dangerous event or dangerous environment, then the lamp head is controlled to yellow;

[0111] The driver is in a slightly over-trust state, specifically τ4≤M(T(t k+1 ),R)<τ3 and the trust level is greater than the risk assessment, and there is no dangerous event or dangerous environment, then the light head is controlled to green;

[0112] The driver is in a state of slight over-trust, specifically τ5≤M(T(t k+1 ),R)<τ4 and the trust level is greater than the risk assessment, and there is no dangerous event or dangerous environment, then the lamp head is controlled to be blue;

[0113] In a safe driving environment, the distance d from the vehicle in front of the left is left-front ≥230m, distance d to the vehicle in front of the right rig h t-front ≥230m, distance d to the vehicle behind the left left-rear ≥230m, right rear vehicle distance d rig h t-rear ≥230m, distance d to the vehicle directly aheadfront ≥200m, distance d to the vehicle directly behind rear ≥200m, the lamp head will be controlled to light up in blue and in breathing mode at a specific frequency;

[0114] Among them, τ0, τ1, τ2, τ3, τ4, and τ5 are preset thresholds, and satisfy the following size relationship: τ0>τ1>τ2>τ3>τ4>τ5, that is, each threshold decreases in sequence.

[0115] Example 3

[0116] This embodiment is a dashboard lighting control system based on risk assessment and human-machine trust for implementing a method embodiment, such as Figure 5 As shown, it includes:

[0117] Driver behavior information collection module, used to collect and extract driver behavior information, including driver's eye, hand, and foot status information;

[0118] Traffic environment information acquisition module, used to collect road traffic environment images and obtain driving environment and traffic event information;

[0119] A trust evaluation module is used to input the driver's behavior information into a pre-built trust evaluation model, and after processing by the trust evaluation model, output the driver's trust evaluation value in the autonomous driving system at the current moment;

[0120] The risk assessment module is used to evaluate the current autonomous driving risk based on the driving environment and traffic incident information, and obtain the risk assessment results of the autonomous driving system, including the risk assessment coefficient of the autonomous driving system's technical capabilities, the risk assessment coefficient of the driving environment, and the risk assessment coefficient of traffic incidents;

[0121] A compatibility calculation module is used to calculate the compatibility between the trust level and the risk of the autonomous driving system based on the current driver's trust evaluation value and the autonomous driving risk assessment result;

[0122] The lighting control module is used to control lighting prompts of different colors according to the threshold range of the adaptability.

[0123] Specifically, the trust assessment module is connected to the driver behavior information collection module to process the real-time eye, hand and foot status data received to obtain the driver's trust level; the traffic environment information collection module is used to collect road traffic environment information; the risk assessment module is connected to the traffic environment information collection module to process the captured road condition images, identify the safety risk sources of the highway driving environment, and evaluate the risk response capabilities of the autonomous driving system; the adaptability calculation module is connected to the trust assessment module and the risk assessment module, and determines the degree of adaptability of the trust and the risk of the autonomous driving system based on the results of the trust and risk assessment; the lighting control module adjusts the RGB color space and flashing period of the lamp head according to the output results of the adaptability calculation module.

[0124] Among them, road traffic environment information includes vehicles, pedestrians, road obstacles, weather conditions, etc.

[0125] The risk assessment module is equipped with a fusion algorithm to analyze images obtained by cameras and different types of radar sensors to achieve environmental perception and risk assessment.

[0126] Furthermore, several acquisition modules collect data from the eye tracker, the grip force sensor installed on the steering wheel, and the pressure sensors installed on the accelerator and brake pedals, and extract eye movement trajectory features and hand and foot status information.

[0127] Furthermore, the trust evaluation module uses the information extracted by the driver behavior information collection module as input variables, a trust model based on the Kalman filter algorithm as an evaluation method, and objective trust as an output result.

[0128] Among them, the lighting control module is mainly used to control the display of the LCD instrument panel, such as Figure 2-4 As shown, the LCD instrument panel 1 mainly includes a liquid crystal display screen, a reflector 2 is provided at the bottom of the LCD screen, a light guide groove 3 is provided at the bottom of the LCD screen, a flexible light guide 4 is provided inside the light guide groove 3, and the two ends of the flexible light guide 4 are respectively connected to a light shielding cap 5 and an RGB lamp head 6, and the RGB lamp head 6 is connected to a circuit board 7 provided at the bottom of the display screen through a line.

[0129] Furthermore, a light shield 5 prevents unnecessary light leakage, improving light efficiency and reducing glare. The RGB lamp head 6 provides an adjustable color light source. This RGB lamp head 6 is connected to a circuit board 7 mounted at the bottom of the LCD screen via an electrical circuit. This circuit board 7 provides power and control signals to the RGB lamp head 6. The programs for the adaptability calculation module and the lighting control module are burned into this circuit board.

[0130] Furthermore, the reflector 2 has a curved surface and is made of a high-reflectivity reflective material to maximize light reflection and improve illumination uniformity. The reflector 2 and the flexible light guide 4 are installed inwardly relative to the outer contour of the LCD screen at equal distances.

[0131] The above-mentioned instrument panel lighting control system is installed in a vehicle with autonomous driving capabilities and has the characteristics and functions of a non-autonomous driving vehicle, such as the steering system and braking system required to complete driving tasks. Autonomous driving vehicles can drive automatically in all road environments without driver intervention by controlling actuators such as the accelerator, brake pedal, and steering wheel. When encountering an emergency, the driver is required to intervene. In non-emergency situations, the driver can also take the initiative to take over. The instrument panel lighting control system collects driver behavior information parameters and environmental parameters around the vehicle, and comprehensively considers the driver's driving psychology and risk factors in the traffic environment to provide the driver with intuitive and efficient information prompts.

[0132] The specific working steps of the instrument panel lighting control system are as follows:

[0133] (1) The eye tracker, grip sensor, and pressure sensor in the driver behavior information collection module collect data and extract the driver's eye, hand, and foot status information respectively, h(t k )=0.20,f(t k )=0.135,e(t k )=0.07;

[0134] (2) The camera and radar sensor in the traffic environment information acquisition module collect road traffic environment images and obtain driving environment and traffic event information;

[0135] (3) The trust evaluation module uses the information extracted by the driver behavior information collection module as input variables, executes the driver's trust evaluation model for the autonomous driving system, and outputs the driver's trust evaluation value at the current moment, including:

[0136] First, obtain the Boolean value of the human-computer interaction solution provided by the system: L(t k )=1、M(t k )=0、N(t k )=0, indicating that the current risk events and response measures are displayed on the dashboard at the same time;

[0137] Furthermore, the model parameters are selected, assuming that the trust level T(t k)=0.65; the influence weight of the trust degree at the previous moment on the trust degree at the current moment A=[0.8]; the influence coefficient matrix of sound, vision, and tactile prompts on trust degree B=[0.2,0.1,0.05]; the influence coefficient matrix of hand, foot, and eye movement frequency on trust degree C=[0.3,0.2,0.1]; process noise w(t k )~N(0,Q), covariance Q=0.01, assuming w(t k )=-0.02;process noise v(t k )~N(0,R), covariance R=0.01, assuming v(t k )=0.005, according to the coefficient matrix C:

[0138]

[0139] Furthermore, the new trust level is calculated based on human-computer interaction and the trust level at the previous moment:

[0140]

[0141] After calculation, the driver's trustworthiness at the current moment is 0.7;

[0142] (4) Using the built-in algorithm of the risk assessment module, extract the technical capabilities of the autonomous driving system, the driving environment, and the traffic incident information respectively, and use the built-in processing rules to assess the current autonomous driving risk. Assume that the risk assessment coefficient of the system technical capabilities is R1 = 0.8, the risk assessment coefficient of the driving environment is R2 = 0.5, and the risk assessment coefficient of the traffic incident is R3 = 0.6;

[0143] (5) The adaptability calculation module uses the current driver trust evaluation value calculated by the trust evaluation module, the risk assessment coefficient R1 of the system technical capability, the risk assessment coefficient R2 of the driving environment, and the risk assessment coefficient R3 of the traffic incident as input variables, executes the adaptability calculation model, and outputs the adaptability of the trust and the risk of the autonomous driving system:

[0144] First, the covariance matrix S is calculated as:

[0145]

[0146] Calculate the inverse matrix S of the covariance -1 , and bring it into the formula to calculate the adaptability of trust and autonomous driving system risk:

[0147]

[0148] (6) The lighting control module will adapt the degree M(T(t k+1),R),The information extracted by the driver behavior information collection module and the traffic environment information collection module is used as input variables to execute the instrument panel lighting control decision plan and adjust the color space and flashing period of the lamp head RGB:

[0149] First, select the thresholds τ0 = 1, τ1 = 0.7, τ2 = 0.5, τ3 = 0.3, τ4 = 0.1, and τ5 = 0. At this time, the adaptation degree M(T(t k+1 ),R) is between τ3 and τ2;

[0150] Furthermore, it is determined whether there is a dangerous driving environment or dangerous situation. If so, the RGB light head is controlled to be red and flash continuously; if not, the driver's distraction time T is further determined. distract Is it greater than 20 minutes? If so, the RGB light head is controlled to be red and flash continuously; if not, the distance d to the vehicle in front of the left is further determined. left-front , the distance d to the vehicle in front of the right right-front , the distance d to the vehicle behind the left left-rear , the distance d to the vehicle behind the right right-rear Is the distance d to the vehicle directly ahead greater than or equal to 230m? front , the distance to the vehicle directly behind d rear Is it greater than or equal to 200m? If so, control the RGB lamp head to be blue and flash at a breathing rate; if not, perform adaptation M(T(t k+1 ), R) is compared with each threshold value to control the RGB lamp head to output the corresponding color.

[0151] In this embodiment, there is a moving car 50m to the right front, 155m to the rear, and 300m to the front. The driving environment is safe and no dangerous driving incidents occur. τ3≤M(T(t k+1 ),R)<τ2, it is determined that the driver is in a general over-trust state, so the RGB lamp head is controlled to be yellow and always on.

[0152] The above specific case implementation process reflects that the invention has the following technical advantages and beneficial effects:

[0153] (1) A mathematical model is used to quantitatively measure the driver's trust in the human-machine co-driving car, and the driver's objective trust can be continuously estimated;

[0154] (2) Through a fitness calculation function, the multi-dimensional influencing factors of driver trust, system technical capabilities, driving environment and traffic events are comprehensively considered, and the fitness quantification of trust and risk assessment is achieved;

[0155] (3) Through a signal light control scheme, guide the driver to adjust the trust level of the automated driving system to achieve optimal human-machine collaboration and improve driving safety;

[0156] (4) Through a signal light installation plan, intuitive driving information prompts are provided to drivers, reducing the driver's cognitive load.

[0157] Example 4

[0158] The present application also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App store, etc., on which a computer program is stored, and when the program is executed by a processor, a corresponding function is implemented. When the computer-readable storage medium of this embodiment is executed by a processor, the instrument panel lighting control method based on risk assessment and human-computer trust in the method embodiment is implemented.

[0159] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0160] The size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0161] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A dashboard lighting control method based on risk estimation and human-machine trust, characterized in that: The following steps are involved: Collect and extract driver behavior information, including driver's eye, hand, and foot status information; Collect road traffic environment images and obtain driving environment and traffic event information; The driver's behavior information is input into a pre-built trust evaluation model, and after being processed by the trust evaluation model, the driver's trust evaluation value for the autonomous driving system at the current moment is output; Evaluate the current autonomous driving risk based on the driving environment and traffic incident information to obtain the risk assessment results of the autonomous driving system, including the risk assessment coefficient of the autonomous driving system's technical capabilities, the risk assessment coefficient of the driving environment, and the risk assessment coefficient of traffic incidents; The degree of compatibility between the driver's trustworthiness and the risk of the autonomous driving system is calculated based on the driver's trustworthiness assessment value at the current moment and the result of the autonomous driving risk assessment. Different colors of light prompts are controlled accordingly based on the threshold range of the degree of compatibility.

2. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 1 is characterized in that: The trust evaluation model calculates each risk assessment coefficient through the Kalman filter algorithm.

3. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 1 is characterized in that: The trust evaluation value is specifically calculated based on the probability that the driver's hands are ready to take over, the probability that the feet are ready to take over, and the probability that the eyes are ready to take over.

4. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 3 is characterized in that: The state of the driver's hands ready to take over is specifically: the grip force sensor installed on the steering wheel detects the state of the driver's one hand or both hands touching the steering wheel, resting on the steering wheel or lightly touching the bottom edge of the steering wheel. Assuming that during unmanned driving, the driver is in a state of trust, his hands do not touch the steering wheel. Only when the driver is in a state of distrust and touches the steering wheel, the grip force sensor will detect the corresponding contact signal. If the force detected by the grip force sensor is less than a preset threshold, it is considered that the driver has not taken over the steering wheel, but is in a state of the driver's hands ready to take over.

5. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 3 is characterized in that: The state of the driver's foot ready to take over is specifically: through the pressure sensors installed on the accelerator and brake pedals, the state of the driver's toes lightly resting on the brake pedal is detected. Assuming that during the unmanned driving process, the driver is in a state of trust and his feet do not touch the accelerator or brake pedal. Only when the driver's feet touch the accelerator or brake pedal, the pressure sensor will detect the corresponding contact signal. If the applied pressure detected by the pressure sensor is less than a preset threshold, it is considered that the driver has not taken over the accelerator or brake pedal, but is in a state of the driver's foot ready to take over.

6. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 3 is characterized in that: Specifically, the driver's eye gaze points collected by the eye tracker are divided into the dashboard, the road ahead, the interactive vehicle on the right and other areas. The state where the eye gaze point is in the dashboard area indicates that the eyes are ready to take over.

7. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 1 is characterized in that: If it is determined based on the driver's behavior information that the driver has not paid attention to the driving environment or the dashboard for a certain period of time, the driver is considered to be in a distracted state and the red light is controlled to flash continuously; if it is determined based on the risk assessment results of the autonomous driving system that there is a dangerous event in the driving environment or the vehicle is in a dangerous driving environment, the red light is controlled to flash continuously.

8. The instrument panel lighting control method based on risk estimation and human-machine trust according to claim 1 is characterized in that: If the value of the adaptability is in the first interval, the driver is in an abnormally over-trust state, and the red light is controlled to turn on; If the value of the adaptability is in the second interval, the driver is in a state of significant over-trust, and the orange light is turned on; If the value of the adaptability is in the third interval, the driver is in a general over-trust state, and the yellow light is turned on; If the value of the adaptability is in the fourth interval, the driver is in a slightly over-trust state, and the green light is turned on; If the adaptability value is in the fifth interval, the driver is in a state of slight over-trust and the blue light is turned on.

9. A dashboard lighting control system based on risk estimation and human-machine trust, characterized in that: include: The driver behavior information collection module is used to collect and extract the driver's behavior information, including the driver's eye, hand, and foot status information; Traffic environment information collection module, used to collect road traffic environment images and obtain driving environment and traffic event information; A trust evaluation module is used to input the driver's behavior information into a pre-built trust evaluation model, and output the driver's trust evaluation value of the automatic driving system at the current moment after being processed by the trust evaluation model; The risk assessment module is used to assess the current autonomous driving risk based on the driving environment and traffic incident information, and obtain the risk assessment results of the autonomous driving system, including the risk assessment coefficient of the autonomous driving system's technical capabilities, the risk assessment coefficient of the driving environment, and the risk assessment coefficient of traffic incidents; A fitness calculation module, used to calculate the fitness between the trust and the risk of the autonomous driving system according to the trust evaluation value of the driver at the current moment and the autonomous driving risk assessment result; The lighting control module is used to control lighting prompts of different colors according to the threshold range of the adaptability.

10. A computer storage medium, characterized in that: A computer program executable by a processor is stored therein, and the computer program executes the instrument panel lighting control method based on risk estimation and human-machine trust as described in any one of claims 1-8.

Images