CN119920092A - Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment - Google Patents
Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment Download PDFInfo
- Publication number
- CN119920092A CN119920092A CN202411981305.5A CN202411981305A CN119920092A CN 119920092 A CN119920092 A CN 119920092A CN 202411981305 A CN202411981305 A CN 202411981305A CN 119920092 A CN119920092 A CN 119920092A
- Authority
- CN
- China
- Prior art keywords
- risk
- driver
- driving
- target vehicle
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
本发明提供一种基于人车路环境多模态数据的行车风险评估方法及设备，所述方法包括获取目标车辆的驾驶人的多种驾驶人风险因子，根据多种驾驶人风险因子建立行车风险评估模型；获取行车风险评估模型中每种驾驶人风险因子对应的权重系数；根据多种驾驶人因风险因子以及每种驾驶人因风险因子对应的权重系数确定驾驶人在驾驶目标车辆时的风险值；根据风险值确定驾驶人在驾驶目标车辆时的行车风险等级。
The present invention provides a driving risk assessment method and device based on multimodal data of a human-vehicle-road environment. The method comprises obtaining a plurality of driver risk factors of a driver of a target vehicle, establishing a driving risk assessment model according to the plurality of driver risk factors; obtaining a weight coefficient corresponding to each driver risk factor in the driving risk assessment model; determining a risk value of the driver when driving the target vehicle according to the plurality of driver risk factors and the weight coefficient corresponding to each driver risk factor; and determining a driving risk level of the driver when driving the target vehicle according to the risk value.
Description
Technical Field
The invention relates to the technical field of safe driving, in particular to a driving risk assessment method based on multi-mode data of a man-vehicle road environment, a driving risk assessment device based on multi-mode data of the man-vehicle road environment, electronic equipment and a computer readable storage medium.
Background
With the increasing complexity of traffic environment, the existing driving risk assessment technology is difficult to apply, cannot effectively describe complex human-vehicle-road interrelationships and action mechanisms, and cannot accurately predict human-vehicle-road states in space-time variation. Therefore, there is a need to develop a more comprehensive and accurate driving risk assessment method to cope with the challenges of the current and future traffic environments.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, a first object of the present invention is to provide a driving risk assessment method based on multi-modal data of a man-vehicle road environment, which can achieve accurate assessment of driving risk by comprehensively considering multiple risk factors of a driver and dynamic and static factors in road and traffic environments.
The second object of the present invention is to provide a driving risk assessment device based on multi-modal data of a man-vehicle road environment.
A third object of the present invention is to propose an electronic device.
A fourth object of the present invention is to propose a computer readable storage medium.
In order to achieve the above objective, an embodiment of the present invention provides a driving risk assessment method based on multi-modal data of a man-vehicle road environment, including:
Acquiring multiple driver risk factors of a driver of a target vehicle, and establishing a driving risk assessment model according to the multiple driver risk factors;
acquiring a weight coefficient corresponding to each driver risk factor in the driving risk assessment model;
determining a risk value of a driver when driving a target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor;
And determining the driving risk level of the driver when driving the target vehicle according to the risk value.
In addition, the driving risk assessment method based on the man-vehicle road environment multi-mode data according to the embodiment of the invention can also have the following additional technical characteristics:
As an alternative embodiment, the plurality of driver factor risk factors includes real-time driving state, real-time driving behavior, cognitive ability, and personality traits of the driver.
As an alternative embodiment, the driving risk assessment model is built according to a plurality of risk factors of drivers, including:
determining a coupling relationship between a plurality of driver risk factors;
And establishing a driving risk assessment model according to the coupling relation among each driver risk factor, the coupling relation among a plurality of driver risk factors and the driving risk.
As an optional embodiment, determining a risk value of the driver when driving the target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor includes:
Dri＝β1Dri_1+β2Dri_2+β3Dri_3+β4Dri_4
Wherein D ri is a risk value, β 1 is a weight corresponding to a real-time driving state, D ri_1 is a real-time driving state, β 2 is a weight corresponding to a real-time driving behavior, D ri_2 is a real-time driving behavior, β 3 is a weight corresponding to cognitive ability, D ri_3 is cognitive ability, β 4 is a weight corresponding to character characteristics, and D ri_4 is character characteristics.
As an alternative embodiment, determining a driving risk level of the driver when driving the target vehicle according to the risk value includes:
Comparing the risk value with a preset risk threshold value;
Determining that the driving risk level of the driver when driving the target vehicle is a first risk level in response to the risk value being higher than a preset risk threshold;
And determining that the driving risk level of the driver when driving the target vehicle is a second risk level in response to the risk value being lower than a preset risk threshold, wherein the first risk level is higher than the second risk level.
As an alternative embodiment, the method further comprises:
And determining a kinetic energy field generated by non-static objects around the target vehicle, wherein the non-static objects are moving objects which can practically collide with the target vehicle and cause great loss, and the kinetic energy field represents the potential dangerous degree of the non-static objects to the surrounding environment under certain road conditions.
As an alternative embodiment, the method further comprises:
And determining a potential energy field generated by static objects around the target vehicle, wherein the static objects can be in actual collision with the target vehicle and can cause great loss, and the potential energy field represents the potential danger degree of the static objects to the surrounding environment under certain road conditions.
As an alternative embodiment, the method further comprises:
And determining the potential danger degree of the driver to the surrounding environment under a certain road condition when the driver drives the target vehicle according to the kinetic energy field, the potential energy field and the risk value of the driver when the driver drives the target vehicle.
According to the driving risk assessment method based on the multi-mode data of the road environment of the person, multiple driver risk factors of a driver of a target vehicle are obtained firstly, a driving risk assessment model is built according to the multiple driver risk factors, further, weight coefficients corresponding to each driver risk factor in the driving risk assessment model are obtained, further, risk values of the driver when the driver drives the target vehicle are determined according to the multiple driver risk factors and the weight coefficients corresponding to each driver risk factor, and finally, driving risk grades of the driver when the driver drives the target vehicle are determined according to the risk values. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
In order to achieve the above object, an embodiment of a second aspect of the present invention provides a driving risk assessment device based on multi-modal data of a man-vehicle environment, the device comprising:
the first acquisition module is configured to acquire multiple driver risk factors of a target vehicle driver, and establish a driving risk assessment model according to the multiple driver risk factors;
the second acquisition module is configured to acquire weight coefficients corresponding to each driver risk factor in the driving risk assessment model;
the weight calculation module is configured to determine a risk value of a driver when driving a target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor;
and the evaluation module is configured to determine the driving risk level of the driver when driving the target vehicle according to the risk value.
According to the driving risk assessment device based on the multi-mode data of the road and human environment, multiple driving risk factors of a driver of a target vehicle are firstly obtained, a driving risk assessment model is built according to the multiple driving risk factors, further, weight coefficients corresponding to each driving risk factor in the driving risk assessment model are obtained, further, risk values of the driver when the driver drives the target vehicle are determined according to the multiple driving risk factors and the weight coefficients corresponding to each driving risk factor, and finally, driving risk grades of the driver when the driver drives the target vehicle are determined according to the risk values. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
To achieve the above object, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the running risk assessment method is implemented by the processor when the processor executes the program.
According to the electronic equipment provided by the embodiment of the invention, firstly, various driver risk factors of a driver of a target vehicle are obtained, a driving risk assessment model is built according to the various driver risk factors, further, weight coefficients corresponding to each driver risk factor in the driving risk assessment model are obtained, further, a risk value of the driver when driving the target vehicle is determined according to the various driver risk factors and the weight coefficients corresponding to each driver risk factor, and finally, the driving risk level of the driver when driving the target vehicle is determined according to the risk value. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
To achieve the above objective, a fourth embodiment of the present invention provides a computer readable storage medium, where the computer readable storage medium stores computer instructions, where the computer instructions are configured to cause the computer to execute the above-mentioned driving risk assessment method based on the multi-modal data of the man-vehicle road environment.
According to the computer readable storage medium provided by the embodiment of the invention, firstly, various driver risk factors of a driver of a target vehicle are obtained, a driving risk assessment model is built according to the various driver risk factors, further, weight coefficients corresponding to each driver risk factor in the driving risk assessment model are obtained, further, a risk value of the driver when driving the target vehicle is determined according to the various driver risk factors and the weight coefficients corresponding to each driver risk factor, and finally, the driving risk level of the driver when driving the target vehicle is determined according to the risk value. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a driving risk assessment method based on multi-modal data of a man-vehicle road environment according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a driving risk assessment device based on multi-modal data of a man-vehicle road environment according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As described in the background section, when the current driving risk assessment technology assesses driving safety, the important influence of characteristics of the driver, psychological and physiological factors on the driving safety is often ignored, and meanwhile, factors such as complex and changeable road conditions, traffic driving environments and the like are not fully considered, so that the current driving risk assessment technology has significant limitations. Therefore, it is difficult for the related art to accurately reflect the interaction and dynamic change between the behavior characteristics of the driver, the traffic environment, and the state of the vehicle. In addition, the description of the related art is not clear enough for the coupling mechanism between the human-vehicle-road three. With the increasing complexity of traffic environment, the existing safety model is difficult to apply, and cannot effectively describe complex human-vehicle-road interrelationships and action mechanisms, and cannot accurately predict human-vehicle-road states in space-time change. Therefore, there is a need to develop a more comprehensive and accurate driving risk assessment method to address challenges of current and future traffic environments.
The technical scheme of the invention is further described in detail through specific examples.
Referring to fig. 1, a flow chart of a driving risk assessment method based on multi-modal data of a man-vehicle road environment according to an embodiment of the present invention is shown.
Step S101, acquiring multiple driver risk factors of a driver of a target vehicle, and establishing a driving risk assessment model according to the multiple driver risk factors;
As an alternative embodiment, the plurality of driver factor risk factors includes real-time driving state, real-time driving behavior, cognitive ability, and personality traits of the driver.
Drivers are in many cases the main factor causing traffic accidents, and their behavior, decision and reaction speed are directly related to the safety conditions of road traffic as key participants in traffic systems.
In practice, the real-time driving state of the driver may be affected by various factors, which may include, for example, physiological fatigue, excitement, pain, etc., such as psychological anger, anxiety, tension, etc., in terms of the condition of the driver himself. For example, prolonged continuous driving or insufficient sleep can lead to fatigue of the driver, affecting his judgment and speed of reaction, thereby increasing the risk of accidents. The driver is liable to make wrong driving decisions such as sudden braking, hit steering wheel, etc. under the negative emotional states of anger, anxiety, tension, etc., thereby causing accidents. Diseases such as heart disease, hypertension, or sudden diseases during driving may affect the driving ability and response speed of the driver.
For the acquisition of the real-time driving state of the driver, physiological data of the driver including, but not limited to, blink frequency, gaze direction, facial expression change, heart rate, etc. may be acquired in real time by a biometric sensor (e.g., eye tracker, facial expression recognition camera, heart rate monitor, etc.) mounted in the vehicle. The eye tracker can judge the gazing direction, the concentration degree and the fatigue degree of the driver by tracking the movement track of the eyeballs. When the driver's line of sight deviates from the road or is not blinking for a long time, it is determined that the driver is in a tired state. The facial expression recognition camera can recognize the emotional state of the driver, such as tension, relaxation, fatigue, etc., by analyzing the change of the facial expression. The heart rate monitor may evaluate the physiological stress level and health of the driver by monitoring the change in heart rate. When the heart rate is abnormally elevated, the system may determine that the driver may be in a stressed or anxious state.
It should be noted that the psychological emotion of the driver may be reflected by the physiological features, and thus, the psychological state of the driver may be mapped by the captured physiological data.
The real-time driving behavior of the driver is also one of factors affecting driving safety, such as speeding, illegal operation, distraction driving, etc. In particular, overspeed is one of the main causes of traffic accidents, and when the vehicle speed is too fast, the reaction time of the driver becomes short, increasing the risk of collision. Non-compliance with traffic regulations, such as red light running, reverse running, random lane changing, etc., increases the risk of collision with other vehicles or pedestrians. The distraction of using a mobile phone, eating things, talking with passengers, etc. can distract the driver, making him unable to deal with the emergency situation in time.
For the determination of the driver's real-time driving behavior, existing sensors of the vehicle (such as accelerometers, gyroscopes, pressure sensors, etc.) may be installed or utilized to record the dynamics, smoothness and accuracy of the acceleration, deceleration and steering operations. An in-vehicle camera or an external camera (on the premise of privacy compliance) may also be used to capture the driver's posture, facial expression, etc. to analyze the normalization of the driving posture. Vehicle operating state data, including speed, engine state, etc., may also be obtained through a diagnostic interface of the vehicle.
The cognitive ability of the driver can characterize the ability of the driver to accurately perceive traffic information, make reasonable decisions and decisions. For example, selection and execution of the cut-in mode requires good cognitive ability when the driver is driving on a road. For example, when a driver decides to overtake, the speed of himself, the speed of the overtaken vehicle and the speeds of other related vehicles on the road must be accurately estimated. Meanwhile, the driver also needs to control the vehicle during overtaking to meet the power characteristics of the vehicle, such as selecting a proper gear. If the driver judges inaccurately in these respects, traffic accidents may be caused. This embodies the driver's cognitive ability to control speed, distance and vehicle during a cut-in. When a driver observes the road alignment, curve illusions and ramp illusions are easy to occur, which requires the driver to have good space awareness and visual awareness. For example, in a continuous curve, because the number of direction changes is large, the driver may feel that the curve is more curved than the actual curve, which is to create the illusion of a curve. If the driver cannot accurately judge the road alignment, the vehicle is out of control or a traffic accident may occur. Similarly, if the gradient change occurs on a long downhill slope, the illusion is easily caused to people, and a driver needs to accurately judge the gradient change so as to adjust the vehicle speed and keep the vehicle stable. The driver needs to pay attention to the dead zone of the vehicle and the dead zone of the environment at any time during driving. The existence of the vehicle blind area and the environment blind area is not known, typically on a novice. The new handcraft is fearless, has no other people in mind, is free from cross-over collision, changes lanes, turns and turns around at will, and brakes and decelerates at will, which is very dangerous. While some experienced drivers, while aware of the existence of the blind area, may not be aware of the existence of vehicles, persons, obstacles, etc. in the blind area, which may also cause traffic accidents. Therefore, the driver needs to continuously improve the cognitive ability of the blind area, remind other road users through modes such as horn sounding and flashing lights, and pay attention to observe the surrounding environment at the same time, so that the driving safety is ensured. During fatigue driving, the perception capability, the reaction capability and the judgment capability of a driver are obviously reduced. For example, the driver cannot make an accurate judgment on the spatial distance, the distance of an obstacle, and the vehicle speed, which may cause the vehicle to run away or a traffic accident to occur. In addition, fatigue driving may also cause misoperation of a driver, such as untimely and inaccurate gear shifting, slow operation action and the like, which may endanger driving safety. Therefore, the driver needs to reasonably arrange driving time and rest time to avoid fatigue driving. A mature driver can find an optimal balance point between traffic regulations and common sense, namely, the driver complies with the traffic regulations and does not make ideal demands on others, and violations, unexpected behaviors and the like of other people on the road are included in the conventional driving coping operation of the driver. For example, at a railroad crossing, the driver should stop two to three to four, which is a representation that complies with the rules of traffic. Meanwhile, when an emergency is encountered in the driving process, a driver needs to quickly make a judgment and take corresponding countermeasures, such as emergency braking, avoidance and the like. This requires the driver to have good response capability and judgment capability.
The cognitive ability of the driver can be determined by implementing observation or indirect evaluation, for example, the driving behavior of the driver can be observed, the operation behaviors such as acceleration, deceleration, steering and the like of the driver are observed in the actual driving process, the strength, stability and accuracy are evaluated, and the response speed and decision capability of the driver when dealing with emergency are noticed. The driving posture and habit can be observed, such as the adjustment of the seat of the driver, the position of the hand holding the steering wheel and the like, the normalization of the driving posture is evaluated, and the driving habit of the driver is analyzed, such as whether the driver frequently changes lanes, whether the traffic rules are complied with and the like. For another example, the spatial perception, visual memory and color recognition capabilities of the driver may also be evaluated by performing psychological tests and evaluations, such as cognitive capability tests, i.e., performing tests such as pattern recognition, azimuth recognition, color recognition, etc., on the driver in advance. The mental agility and the logic judgment of the driver can be evaluated through digital calculation or logic reasoning questions. The attention and reaction degree and the reaction speed of the driver can be measured through attention and reaction test, namely using professional test tools or software, and the reaction and the coping strategy of the driver can be observed through simulation of emergency or emergency.
In addition, the personality characteristics of drivers are also one of the factors in driving risk assessment, and drivers with higher volatility tend to prefer dangerous driving, such as speeding, running red light, or not following traffic rules, which significantly increases the likelihood of traffic accidents. The driver with large emotion fluctuation can have excessive reactions such as sudden acceleration, sudden braking or out-of-control emotion when facing stress or sudden events, and the behaviors are extremely easy to cause traffic accidents. The driver with strong responsibility usually notices the driving safety, not only obeys the traffic rules, but also regularly checks the vehicle condition to ensure that the vehicle is in a good driving state. Conversely, drivers lacking responsibility may more easily ignore safety issues, thereby increasing accident risk.
Likewise, personality traits of a driver may also be comprehensively assessed by observing driving behavior, assessing driving attitudes, analyzing ways in which the driver interacts with others, or using psychological testing and assessment tools, e.g., by observing attitudes and behaviors of the driver while interacting with other drivers through relevant detection sensors. Or analyzing the communication and interaction modes between the driver and the passengers, and judging whether the driver is enthusiasm or not, wherein the enthusiasm and social capacity in the characters of the driver can be reflected.
The invention can timely find potential driving risks and give early warning to the driver by monitoring various risk factors of the driver and the surrounding environment of the vehicle in real time, thereby effectively avoiding or reducing traffic accidents. According to individual differences (such as cognitive ability, character characteristics and the like) of drivers, more personalized risk assessment results can be provided, so that the drivers can know the driving risk of the drivers more, and more effective preventive measures can be taken.
It should be noted that, before using the technical solutions disclosed in the embodiments of the present invention, the user should be informed and authorized of the type, the usage range, the usage scenario, etc. of the personal information related to the present invention by an appropriate manner according to the relevant laws and regulations.
For example, in response to receiving an active request from a user, a prompt is sent to the user to explicitly prompt the user that the operation it is requesting to perform will require personal information to be obtained and used with the user. Therefore, the user can automatically select whether to provide personal information for software or hardware such as electronic equipment, application programs, servers or storage media for executing the operation of the technical scheme according to the prompt information.
As an alternative but non-limiting implementation, in response to receiving an active request from a user, the manner in which the prompt information is sent to the user may be, for example, a popup, in which the prompt information may be presented in a text manner. In addition, a selection control for the user to select to provide personal information to the electronic device in a 'consent' or 'disagreement' manner can be carried in the popup window.
It will be appreciated that the above-described notification and user authorization acquisition process is merely illustrative and not limiting of the implementation of the present invention, and that other ways of satisfying relevant legal regulations may be applied to the implementation of the present invention.
Step S102, obtaining weight coefficients corresponding to each driver risk factor in the driving risk assessment model.
As an alternative embodiment, the driving risk assessment model is built according to multiple driver risk factors, and comprises the steps of determining the coupling relation among the multiple driver risk factors, and building the driving risk assessment model according to each driver risk factor, the coupling relation among the multiple driver risk factors and the coupling relation among the driving risks.
In specific implementation, the real-time driving state, the real-time driving behavior, the cognitive ability and the character characteristic data of the driver acquired in the aspects can be fused, and an intelligent algorithm (such as a convolutional neural network CNN, a cyclic neural network RNN and the like in a deep learning algorithm) is adopted for modeling analysis. Through learning and training the actual driving data, the internal relations between different states of the driver and the complex relation modes between the states and the driving risk are excavated, so that a risk assessment model with high accuracy and adaptability is established, and the weight corresponding to each driver risk factor in the quantification of the driving risk assessment model is calculated.
Specifically, raw data collected from multiple sensors and test tools (i.e., real-time driving state, real-time driving behavior, cognitive ability, and personality characteristics) is cleaned, denoised, and formatted to ensure accuracy and consistency of the data. And carrying out interpolation processing on the missing data, and filtering or correcting the abnormal data. Features which have significant influence on the driving risk, such as changes of driving speed, rotation angle of a steering wheel, stepping force of an accelerator pedal, concentration of attention of a driver, reaction speed, emotion stability index and the like, are extracted from the preprocessed data. Meanwhile, character feature data (such as character types, risk preferences, and the like obtained through psychological tests) is also extracted as one of the features. And fusing the extracted characteristic data to form a comprehensive data set containing multi-dimensional information. Data from different sources can be integrated into a unified framework by adopting methods of data splicing, feature mapping and the like. Further, according to the complexity of the problem and the characteristics of the data, a proper intelligent algorithm is selected for modeling analysis. In the embodiment of the present invention, a Convolutional Neural Network (CNN), a cyclic neural network (RNN), and the like in a deep learning algorithm may be used. Further, a deep learning model is constructed using the extracted feature data. For CNNs, it may be used to process image data (e.g., driver facial expressions, gestures, etc., obtained by a vehicle recorder) to extract visual features of the driver. For RNNs, it can be used to process time series data (e.g., data of driving speed, steering wheel rotation angle, etc. over time) to capture dynamic behavior characteristics of the driver. Further, the model is trained using actual driving data, enabling it to learn the inherent associations between the different states of the driver and the complex pattern of relationships between them and driving risk. In the training process, parameters and structures of the model need to be continuously adjusted to improve the prediction performance of the model. And verifying the model by the methods of cross verification, test set evaluation and the like so as to ensure the accuracy and reliability of the prediction result. And optimizing and adjusting the model according to the verification result, such as increasing the network layer number, adjusting the learning rate and the like.
Step S103, determining a risk value of the driver when driving the target vehicle according to the multiple driver factor risk factors and the weight coefficient corresponding to each driver factor risk factor.
As an optional embodiment, determining a risk value of the driver when driving the target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor includes:
Dri＝β1Dri_1+β2Dri_2+β3Dri_3+β4Dri_4
Wherein D ri is a risk value, β 1 is a weight corresponding to a real-time driving state, D ri_1 is a real-time driving state, β 2 is a weight corresponding to a real-time driving behavior, D ri_2 is a real-time driving behavior, β 3 is a weight corresponding to cognitive ability, D ri_3 is cognitive ability, β 4 is a weight corresponding to character characteristics, and D ri_4 is character characteristics.
Wherein β 1+β2+β3+β4 =1.
And scoring and grading the driving risk of the driver according to the calculated D ri value. For example, if D ri =0.25, the characterization risk level is low, scoring 25.
Each driver factor may include a plurality of grades, each grade may correspond to a respective sub-weight, when a driver factor includes a plurality of grades, the weight corresponding to the driver factor may be an accumulation of the sub-weights corresponding to the grades, for example, for a real-time driving state, when the real-time driving state includes both fatigue and distraction, the weight coefficient corresponding to the real-time driving state may be an accumulation of the sub-weights corresponding to fatigue and the sub-weights corresponding to distraction, i.e., the weight coefficient corresponding to the real-time driving state may increase in calculating a risk value of the driver when driving the target vehicle. By classifying each driver factor risk factor and distributing sub-weights for each classification, the fine-grained recognition accuracy under the condition of few data can be increased, and the risk value of the driver when driving the target vehicle can be determined more accurately according to multiple driver factor risk factors and the weight coefficient corresponding to each driver factor risk factor.
Step S104, determining the driving risk level of the driver when driving the target vehicle according to the risk value.
As an alternative embodiment, determining the driving risk level of the driver when driving the target vehicle according to the risk value comprises comparing the risk value with a preset risk threshold, determining the driving risk level of the driver when driving the target vehicle as a first risk level in response to the risk value being higher than the preset risk threshold, and determining the driving risk level of the driver when driving the target vehicle as a second risk level in response to the risk value being lower than the preset risk threshold, wherein the first risk level is higher than the second risk level.
Specifically, one or more preset risk thresholds may be set first. These thresholds may be determined based on historical data, industry standards, regulatory requirements, or expert opinion, etc., with the aim of dividing the risk values into different intervals to correspond to different risk levels. Next, the calculated risk value is compared with a preset risk threshold. This comparison is to determine in which risk interval the risk value falls, and thus further determine the driving risk level. If the risk value is higher than a preset risk threshold value, the driver is indicated to have higher running risk under the current condition, and therefore the running risk level is determined to be the first risk level. This level typically indicates that special attention is required or emergency measures are taken to reduce risk. If the risk value is lower than the preset risk threshold value, the driving risk of the driver under the current condition is relatively low, and therefore the driving risk level is determined to be a second risk level. This level generally indicates that the driving behaviour of the driver is relatively safe, but still needs to be kept alert. In the embodiment of the present invention, the first risk level is set to be higher than the second risk level, which means that when the risk value is higher, the driving risk of the driver is also higher, and the driver needs to pay more attention to and take corresponding safety measures.
It should be noted that the preset risk threshold is not a constant one, but may be dynamically adjusted according to the actual situation. For example, when new regulatory requirements or industry standards are placed, the preset risk threshold may be adjusted accordingly based on these requirements or standards. In determining the driving risk level, other factors, such as historical driving records of a driver, vehicle conditions, road conditions and the like, can be comprehensively considered besides the risk value. These factors may provide more comprehensive risk assessment information, helping to more accurately determine the driving risk level.
As an alternative embodiment, the kinetic energy field generated by the non-static object around the target vehicle can be determined, wherein the non-static object is a moving object which can practically collide with the target vehicle and can cause great loss, and the kinetic energy field represents the potential dangerous degree of the non-static object to the surrounding environment under a certain road condition.
In particular, the kinetic energy field characterizes moving objects, such as moving vehicles, pedestrians, etc., that can physically collide with the vehicle and cause significant losses. And calculating the kinetic energy risk fields of all moving objects in the driving scene through the following formulas according to the data related to the vehicle, other vehicles, pedestrians and roads acquired in real time. The danger caused by collision is not increased linearly, but the increasing speed of the driving danger degree is increased along with the decrease of the distance between the two, so that the characteristic of increasing the collision danger degree in an exponential mode is adopted. Based on the above analysis, the kinetic energy field formed around the non-stationary object i (x i,yi) has a field strength at (x j,yj) of:
The method comprises the steps of taking x j,yj as a coordinate of a mass center of a non-static object, taking an x-axis along a road line direction and taking a y-axis as a perpendicular to the road line direction, taking a vector E V_ij as a potential danger degree of the non-static object i to the surrounding environment under a certain road condition, taking the larger field intensity as a potential danger degree of the non-static object i, taking the field intensity direction as the same as R ij, taking the field intensity direction as the field intensity direction, taking the field intensity decreasing speed as the fastest, taking R ij＝(xj-xi,yj-yi) as a vector between two points, taking k 1、k2 and G as undetermined constants larger than 0, taking M i as an equivalent mass of the object i, taking R i as a road condition influence factor at (x i,yi), taking the object i to move positively along the x-axis, taking v i as the speed of the object i, taking theta i as an included angle between the speed direction of the object i and R i j, and taking the clockwise direction as positive.
Based on the analysis, multiplying the kinetic energy field of the vehicle by the risk value D ri of the risk factor of the driver to obtain the field strength of the behavior field formed by the driver of the non-static object (vehicle) i (x i,yi) around the non-static object (vehicle) at (x j,yj):
ED_ij＝EV_ijDri
Wherein E V_ij is the field strength of the kinetic energy field formed by the vehicle i at (x j,yj), and D ri is the risk value D ri of the driver risk factor.
Vector E D_ij represents the potential hazard level of a driver of vehicle i to the surrounding environment when driving a certain vehicle under certain road conditions, and the greater the field strength is, the greater the potential hazard generated by the driver is, and the field strength direction is the same as the field strength direction of the kinetic energy field formed by vehicle i.
As an alternative embodiment, the potential energy field generated by static objects around the target vehicle can be determined, wherein the static objects can be actually collided with the target vehicle and cause great loss, and the potential energy field represents the potential danger degree of the static objects to the surrounding environment under a certain road condition.
The potential energy field formed around the static object i (x i,yi) has a field strength at (x j,yj) of:
The vector E R_ij represents the potential danger degree of the static object i to the surrounding environment under certain road conditions, the larger the field strength is, the greater the potential danger of the static object i is, the field strength direction is the same as R ij, the field strength is the fastest in the field strength direction, R ij＝(xj-xi,yj-yi) represents a two-point distance vector, k 1、k2 and G are undetermined constants greater than 0, M i is the equivalent mass of the object i, and R i is the road condition influence factor at the position (x i,yi).
As an alternative embodiment, the degree of potential danger to the surrounding environment by the driver when driving the target vehicle may be determined from the kinetic energy field, the potential energy field and the risk value of the driver when driving the target vehicle.
In summary, the unified model of the driving risk field can be expressed as:
Wherein, F j represents the dangerous degree of the current driving state of the vehicle j, and the larger F j is, the more dangerous the current driving state is, and the direction of the dangerous F is the same as E j.
From the above, the driving risk assessment method based on the multi-modal data of the road and human environment provided by the invention comprises the steps of firstly obtaining multiple driving risk factors of a driver of a target vehicle, building a driving risk assessment model according to the multiple driving risk factors, further obtaining weight coefficients corresponding to each driving risk factor in the driving risk assessment model, further determining a risk value of the driver when driving the target vehicle according to the multiple driving risk factors and the weight coefficients corresponding to each driving risk factor, and finally determining the driving risk level of the driver when driving the target vehicle according to the risk value. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
It should be noted that, the method of the embodiment of the present invention may be performed by a single device, for example, a computer or a server. The method of the embodiment can also be applied to a distributed scene, and is completed by mutually matching a plurality of devices. In the case of such a distributed scenario, one of the devices may perform only one or more steps of the method of an embodiment of the present invention, the devices interacting with each other to accomplish the method.
It should be noted that the foregoing describes some embodiments of the present invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Based on the same inventive concept, the invention also provides a driving risk assessment device based on the multi-mode data of the man-vehicle road environment, which corresponds to the method provided by any embodiment.
Referring to fig. 2, a schematic diagram of a driving risk assessment device based on multi-modal data of a man-vehicle road environment according to an embodiment of the present invention is provided.
The device comprises:
A first obtaining module 201 configured to obtain a plurality of driver risk factors of a driver of a target vehicle, and establish a driving risk assessment model according to the plurality of driver risk factors;
A second obtaining module 202 configured to obtain a weight coefficient corresponding to each driver risk factor in the driving risk assessment model;
The weight calculation module 203 is configured to determine a risk value of a driver when driving the target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor;
An evaluation module 204 is configured to determine a driving risk level of the driver while driving the target vehicle based on the risk value.
Optionally, the plurality of driver factor risk factors includes real-time driving state, real-time driving behavior, cognitive ability, and personality characteristics of the driver.
Optionally, the first acquisition module 201 is further configured to:
determining a coupling relationship between a plurality of driver risk factors;
And establishing a driving risk assessment model according to the coupling relation among each driver risk factor, the coupling relation among a plurality of driver risk factors and the driving risk.
Optionally, the weight calculation module 203 is further configured to:
Dri＝β1Dri_1+β2Dri_2+β3Dri_3+β4Dri_4
Wherein D ri is a risk value, β 1 is a weight corresponding to a real-time driving state, D ri_1 is a real-time driving state, β 2 is a weight corresponding to a real-time driving behavior, D ri_2 is a real-time driving behavior, β 3 is a weight corresponding to cognitive ability, D ri_3 is cognitive ability, β 4 is a weight corresponding to character characteristics, and D ri_4 is character characteristics.
Optionally, the evaluation module 204 is further configured to:
Comparing the risk value with a preset risk threshold value;
Determining that the driving risk level of the driver when driving the target vehicle is a first risk level in response to the risk value being higher than a preset risk threshold;
And determining that the driving risk level of the driver when driving the target vehicle is a second risk level in response to the risk value being lower than a preset risk threshold, wherein the first risk level is higher than the second risk level.
Optionally, the evaluation module 204 is further configured to:
And determining a kinetic energy field generated by non-static objects around the target vehicle, wherein the non-static objects are moving objects which can practically collide with the target vehicle and cause great loss, and the kinetic energy field represents the potential dangerous degree of the non-static objects to the surrounding environment under certain road conditions.
Optionally, the evaluation module 204 is further configured to:
And determining a potential energy field generated by static objects around the target vehicle, wherein the static objects can be in actual collision with the target vehicle and can cause great loss, and the potential energy field represents the potential danger degree of the static objects to the surrounding environment under certain road conditions.
Optionally, the evaluation module 204 is further configured to:
And determining the potential danger degree of the driver to the surrounding environment under a certain road condition when the driver drives the target vehicle according to the kinetic energy field, the potential energy field and the risk value of the driver when the driver drives the target vehicle.
According to the driving risk assessment device based on the multi-mode data of the road and human environment, multiple driving risk factors of a driver of a target vehicle are firstly obtained, a driving risk assessment model is built according to the multiple driving risk factors, further, weight coefficients corresponding to each driving risk factor in the driving risk assessment model are obtained, further, risk values of the driver when the driver drives the target vehicle are determined according to the multiple driving risk factors and the weight coefficients corresponding to each driving risk factor, and finally, driving risk grades of the driver when the driver drives the target vehicle are determined according to the risk values. The invention realizes accurate assessment of the driving risk by comprehensively considering various risk factors of drivers and dynamic and static factors in road and traffic environments.
For convenience of description, the above system is described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present invention.
The system of the foregoing embodiment is configured to implement the corresponding method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same inventive concept, the present invention also provides an electronic device, corresponding to the method described in any of the above embodiments, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method described in any of the above embodiments when executing the program.
Fig. 3 shows a more specific hardware architecture of an electronic device provided by the present embodiment, which may include a processor 310, a memory 320, an input/output interface 330, a communication interface 340, and a bus 350. Wherein the processor 310, the memory 320, the input/output interface 330 and the communication interface 340 are communicatively coupled to each other within the device via a bus 350.
The processor 310 may be implemented by a general-purpose CPU (Central Processing Unit ), a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 320 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage, dynamic storage, etc. Memory 320 may store an operating system and other application programs, and when implementing the techniques provided by the embodiments of the present disclosure via software or firmware, the associated program code is stored in memory 320 and invoked for execution by processor 310.
The input/output interface 330 is used for connecting with an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown in the figure) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
The communication interface 340 is used to connect to a communication module (not shown in the figure) to enable communication interaction between the present device and other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 350 includes a path to transfer information between components of the device (e.g., processor 310, memory 320, input/output interface 330, and communication interface 340).
It should be noted that although the above device only shows the processor 310, the memory 320, the input/output interface 330, the communication interface 340, and the bus 350, in the implementation, the device may further include other components necessary to achieve normal operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The electronic device of the foregoing embodiment is configured to implement the corresponding method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same inventive concept, the present invention also provides a computer-readable storage medium storing computer instructions for causing the computer to perform the method according to any of the above embodiments.
The computer-readable storage media described above can be any available media or data storage device that can be accessed by a computer, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, nonvolatile storage (NAND FLASH), solid State Disk (SSD)), etc.
The storage medium of the above embodiments stores computer instructions for causing the computer to perform the method described in any of the above exemplary method portions, and has the advantages of the corresponding method embodiments, which are not described herein.
Furthermore, although the operations of the methods of the present invention are depicted in the drawings in a particular order, this is not required or suggested that these operations must be performed in this particular order or that all of the illustrated operations must be performed in order to achieve desirable results. Rather, the steps depicted in the flowcharts may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present invention should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used in embodiments of the present invention, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
While the spirit and principles of the present invention have been described with reference to several particular embodiments, it is to be understood that the invention is not limited to the disclosed embodiments nor does it imply that features of the various aspects are not useful in combination, nor are they useful in any combination, such as for convenience of description. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.
Claims (11)
1. A driving risk assessment method based on multi-mode data of a man-vehicle road environment is characterized by comprising the following steps:
Acquiring multiple driver risk factors of a driver of a target vehicle, and establishing a driving risk assessment model according to the multiple driver risk factors;
acquiring a weight coefficient corresponding to each driver risk factor in the driving risk assessment model;
determining a risk value of the driver when driving the target vehicle according to a plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor;
and determining the driving risk level of the driver when driving the target vehicle according to the risk value.
2. The method for evaluating the running risk of a vehicle based on the multi-modal data of the human road environment according to claim 1, wherein the plurality of driver factor risk factors includes real-time driving states, real-time driving behaviors, cognitive abilities and personality characteristics of the driver.
3. The method for evaluating the running risk based on the multi-modal data of the man-vehicle road environment according to claim 2, wherein the establishing the running risk evaluation model according to the plurality of driver risk factors comprises:
determining a coupling relationship between the plurality of driver risk factors;
and establishing the driving risk assessment model according to each driving risk factor, the coupling relation among the plurality of driving risk factors and the coupling relation among the driving risks.
4. The method for evaluating the running risk based on the multi-modal data of the road and human environment according to claim 3, wherein determining the risk value of the driver when driving the target vehicle according to the plurality of driver factor risk factors and the weight coefficient corresponding to each of the driver factor risk factors comprises:
Dri＝β1Dri_1+β2Dri_2+β3Dri_3+β4Dri_4
Wherein D ri is a risk value, β 1 is a weight corresponding to a real-time driving state, D ri_1 is a real-time driving state, β 2 is a weight corresponding to a real-time driving behavior, D ri_2 is a real-time driving behavior, β 3 is a weight corresponding to cognitive ability, D ri_3 is cognitive ability, β 4 is a weight corresponding to character characteristics, and D ri_4 is character characteristics.
5. The method for evaluating the running risk of the driver based on the multi-modal data of the man-vehicle environment according to claim 4, wherein the determining the running risk level of the driver when driving the target vehicle according to the risk value includes:
Comparing the risk value with a preset risk threshold value;
Determining that the driving risk level of the driver when driving the target vehicle is a first risk level in response to the risk value being higher than a preset risk threshold;
and determining that the driving risk level of the driver when driving the target vehicle is a second risk level in response to the risk value being lower than a preset risk threshold, wherein the first risk level is higher than the second risk level.
6. The method for evaluating the running risk based on the multi-modal data of the man-vehicle road environment according to claim 1, wherein the method further comprises:
And determining a kinetic energy field generated by non-static objects around the target vehicle, wherein the non-static objects are moving objects which can practically collide with the target vehicle and cause great loss, and the kinetic energy field represents the potential danger degree of the non-static objects to the surrounding environment under a certain road condition.
7. The method for evaluating the running risk based on the multi-modal data of the man-vehicle environment according to claim 6, wherein the method further comprises:
and determining a potential energy field generated by static objects around the target vehicle, wherein the static objects can practically collide with the target vehicle and cause great loss, and the potential energy field represents the potential danger degree of the static objects to the surrounding environment under a certain road condition.
8. The method for evaluating the running risk based on the multi-modal data of the man-vehicle environment according to claim 7, wherein the method further comprises:
And determining the potential danger degree of the driver to the surrounding environment under a certain road condition when driving the target vehicle according to the kinetic energy field, the potential energy field and the risk value of the driver when driving the target vehicle.
9. The utility model provides a driving risk assessment device based on people's vehicle road environment multimodal data which characterized in that includes:
the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is configured to acquire a plurality of driver risk factors of a target vehicle driver, and establish a driving risk assessment model according to the plurality of driver risk factors;
the second acquisition module is configured to acquire a weight coefficient corresponding to each driver risk factor in the driving risk assessment model;
The weight calculation module is configured to determine a risk value of the driver when driving the target vehicle according to the plurality of driver factor risk factors and weight coefficients corresponding to each driver factor risk factor;
And the evaluation module is configured to determine a driving risk level of the driver when driving the target vehicle according to the risk value.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for risk assessment of a vehicle based on multimodal data of the human road environment as claimed in any one of claims 1 to 8 when executing the program.
11. A computer-readable storage medium storing computer instructions for causing the computer to implement the traffic risk assessment method based on the human-vehicle environment multimodal data according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411981305.5A CN119920092A (en) | 2024-12-30 | 2024-12-30 | Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411981305.5A CN119920092A (en) | 2024-12-30 | 2024-12-30 | Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119920092A true CN119920092A (en) | 2025-05-02 |
Family
ID=95503872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411981305.5A Pending CN119920092A (en) | 2024-12-30 | 2024-12-30 | Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119920092A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239741A (en) * | 2014-09-28 | 2014-12-24 | 清华大学 | Travelling risk field-based automobile driving safety assistance method |
| CN106651162A (en) * | 2016-12-09 | 2017-05-10 | 思建科技有限公司 | Big data-based driving risk assessment method |
| CN109740840A (en) * | 2018-11-23 | 2019-05-10 | 深圳市大东车慧科技股份有限公司 | A kind of multivariate analysis driving risk evaluating system based on people, vehicle, road and environment |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | Method and device for risk assessment of human-vehicle-road coupling based on driver's cognitive perspective |
| CN117382643A (en) * | 2023-10-13 | 2024-01-12 | 湖北汽车工业学院 | Personalized lane change decision method and system based on driver psychology risk field model |
-
2024
- 2024-12-30 CN CN202411981305.5A patent/CN119920092A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239741A (en) * | 2014-09-28 | 2014-12-24 | 清华大学 | Travelling risk field-based automobile driving safety assistance method |
| CN106651162A (en) * | 2016-12-09 | 2017-05-10 | 思建科技有限公司 | Big data-based driving risk assessment method |
| CN109740840A (en) * | 2018-11-23 | 2019-05-10 | 深圳市大东车慧科技股份有限公司 | A kind of multivariate analysis driving risk evaluating system based on people, vehicle, road and environment |
| CN110414831A (en) * | 2019-07-24 | 2019-11-05 | 清华大学 | Method and device for risk assessment of human-vehicle-road coupling based on driver's cognitive perspective |
| CN117382643A (en) * | 2023-10-13 | 2024-01-12 | 湖北汽车工业学院 | Personalized lane change decision method and system based on driver psychology risk field model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lyu et al. | Using naturalistic driving data to identify driving style based on longitudinal driving operation conditions | |
| Wang et al. | Driver drowsiness detection based on non-intrusive metrics considering individual specifics | |
| US12246740B2 (en) | Coachable driver risk groups | |
| CN107031653B (en) | A Driver Identity Authorization System for Car Sharing | |
| Yin et al. | Automatic dangerous driving intensity analysis for advanced driver assistance systems from multimodal driving signals | |
| CN107832748A (en) | A kind of shared automobile driver changes system and method | |
| Wang et al. | Predicting drowsy driving in real-time situations: Using an advanced driving simulator, accelerated failure time model, and virtual location-based services | |
| CN106956591A (en) | A system for judging driver's driving authority | |
| GB2545317A (en) | Incapacitated driving detection and prevention | |
| CN110143202A (en) | A kind of dangerous driving identification and method for early warning and system | |
| CN113753059B (en) | Method for predicting takeover capacity of driver under automatic driving system | |
| CN118211479A (en) | Accurate evaluation method for simulated driving | |
| El Masri et al. | Toward self-policing: Detecting drunk driving behaviors through sampling CAN bus data | |
| CN118907118B (en) | Intelligent automobile dynamic adjustment method and system based on user experience | |
| CN113415292A (en) | Driving takeover capability evaluation method and electronic device | |
| Damousis et al. | Fuzzy fusion of eyelid activity indicators for hypovigilance-related accident prediction | |
| Wang et al. | State space model detection of driving fatigue considering individual differences and time cumulative effect | |
| CN107150690A (en) | A kind of driving fatigue method for early warning based on roadmarking | |
| Liu et al. | Identification of driver distraction based on SHRP2 naturalistic driving study | |
| Sun et al. | Extraction of optimal measurements for drowsy driving detection considering driver fingerprinting differences | |
| CN118070154B (en) | A method and device for distinguishing driving fatigue based on LSTM neural network | |
| Zhu et al. | MADFM: Multi-Layer Adaptive Driver Fatigue Monitoring Model Based on Steering Wheel Signals | |
| Saito et al. | Bringing a vehicle to a controlled stop: Effectiveness of a dual-control scheme for identifying driver drowsiness and preventing lane departures under partial driving automation requiring hands-on-wheel | |
| Hua et al. | Cognitive distraction state recognition of drivers at a nonsignalized intersection in a mixed traffic environment | |
| CN119920092A (en) | Driving risk assessment method and equipment based on multimodal data of human-vehicle-road environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |