CN113415292A - Driving takeover capability evaluation method and electronic device - Google Patents
Driving takeover capability evaluation method and electronic device Download PDFInfo
- Publication number
- CN113415292A CN113415292A CN202110721376.1A CN202110721376A CN113415292A CN 113415292 A CN113415292 A CN 113415292A CN 202110721376 A CN202110721376 A CN 202110721376A CN 113415292 A CN113415292 A CN 113415292A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- sample data
- driving
- attribute
- data
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 190
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 33
- 238000003066 decision tree Methods 0.000 claims description 14
- 231100000279 safety data Toxicity 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000001815 facial effect Effects 0.000 description 7
- 238000001914 filtration Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000036387 respiratory rate Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011157 data evaluation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000035790 physiological processes and functions Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/005—Handover processes
- B60W60/0053—Handover processes from vehicle to occupant
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/005—Handover processes
- B60W60/0059—Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/0872—Driver physiology
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
- B60W2520/105—Longitudinal acceleration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/28—Wheel speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/10—Accelerator pedal position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/12—Brake pedal position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/18—Steering angle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2540/00—Input parameters relating to occupants
- B60W2540/221—Physiology, e.g. weight, heartbeat, health or special needs
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a driving takeover capacity evaluation method and an electronic device, which can effectively evaluate the vehicle takeover capacity of a driver and improve the driving safety of an intelligent vehicle. The method comprises the following steps: when the vehicle is switched from automatic driving to manual driving, vehicle driving data and physiological characteristic data of a driver are obtained. And inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information. And determining the driving takeover capability evaluation result of the driver according to the evaluation attribute information.
Description
Technical Field
The application relates to the technical field of intelligent driving, in particular to a driving takeover capacity evaluation method and an electronic device.
Background
The intelligent vehicle is a comprehensive system integrating functions of environmental perception, planning decision, multi-level auxiliary driving and the like, intensively applies technologies such as computer, modern sensing, information fusion, communication, artificial intelligence, automatic control and the like, and is a typical high and new technology complex. The technical level of part of current intelligent vehicles has not yet completely transited to a full-automatic driving stage, and the driving behavior problem derived from the man-machine driving process gradually becomes a hot spot of international research.
At present, in the process of man-machine driving, the technical supervision for the drivers to take over the intelligent vehicles is still lacked, so that some non-standard and even wrong vehicle taking over modes are easily caused, and the driving safety of the intelligent vehicles is not facilitated.
Disclosure of Invention
The present application is directed to solving at least one of the problems in the prior art. Therefore, the driving takeover capacity evaluation method and the electronic device can effectively evaluate the vehicle takeover capacity of a driver and improve the driving safety of the intelligent vehicle.
According to a first aspect embodiment of the application, a driving takeover capability evaluation method comprises the following steps:
when the vehicle is switched from automatic driving to manual driving, vehicle driving data and physiological characteristic data of a driver are obtained; inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information; and determining the driving taking over capability evaluation result of the driver according to the evaluation attribute information.
According to the driving takeover capability evaluation method provided by the embodiment of the application, the following beneficial effects are at least achieved:
in the embodiment of the application, when the driver takes over the vehicle, the vehicle running data and the physiological characteristic data of the driver are obtained. The vehicle driving data and the physiological characteristic data are input into a pre-constructed evaluation prediction model, so that evaluation attribute information can be obtained, and the evaluation attribute information realizes qualitative or quantitative evaluation on the vehicle taking-over capability of a driver and is used for matching a corresponding driving taking-over capability evaluation result. Therefore, the vehicle taking over capability of the driver is effectively evaluated by combining the driving condition of the vehicle and the physiological state of the driver, an effective evaluation standard can be provided for supervision and intervention of the vehicle taking over behavior, and the driving safety of the intelligent vehicle is favorably improved.
According to some embodiments of the application, the training of the predetermined assessment prediction model comprises:
acquiring a plurality of acquisition sample data when a vehicle is in a preset working condition, wherein the acquisition sample data comprises driving sample data acquired for the vehicle and physiological characteristic sample data acquired for a driver, and the preset working condition comprises that the vehicle is in a dangerous driving scene and is driven manually; performing takeover capability evaluation on a plurality of acquisition sample data, and determining evaluation attribute sample data corresponding to each acquisition sample data; and carrying out classification and regression training by using the plurality of the acquisition sample data and the plurality of the evaluation attribute sample data to construct an evaluation prediction model.
According to some embodiments of the present application, the plurality of the acquisition sample data includes sample data corresponding to a plurality of characteristic attributes, and the plurality of the evaluation attribute sample data includes sample data corresponding to a plurality of evaluation attributes; the classifying and regression training is performed by using the plurality of the acquisition sample data and the plurality of the evaluation attribute sample data, and an evaluation prediction model is constructed, including:
combining a plurality of the collected sample data and a plurality of the evaluation attribute sample data, performing importance level sorting on a plurality of characteristic attributes, and screening out the characteristic attributes for evaluation prediction; taking the characteristic attribute for evaluation prediction and a plurality of evaluation attributes as decision factors; acquiring sample data corresponding to the decision factor aiming at a plurality of acquisition sample data and a plurality of evaluation attribute sample data to serve as target sample data; and carrying out classification and regression training by combining a plurality of target sample data to construct an evaluation prediction model.
According to some embodiments of the present application, the sorting of importance levels of the plurality of feature attributes by combining the plurality of the collection sample data and the plurality of the evaluation attribute sample data to screen out feature attributes for evaluation prediction includes:
calculating the total information entropy of the evaluation attributes in combination with the sample data of the evaluation attributes; calculating a first conditional entropy of each feature attribute relative to all the evaluation attributes by combining a plurality of acquisition sample data and a plurality of evaluation attribute sample data; obtaining a first information gain corresponding to each characteristic attribute according to the total information entropy and the first conditional entropy of each characteristic attribute; and based on the first information gain corresponding to each kind of the characteristic attributes, carrying out importance level sorting on the plurality of kinds of the characteristic attributes to obtain the characteristic attributes of N before sorting as the characteristic attributes for evaluating and predicting, wherein N is a positive integer.
According to some embodiments of the present application, the sorting of importance levels of the plurality of feature attributes by combining the plurality of the collection sample data and the plurality of the evaluation attribute sample data to screen out feature attributes for evaluation prediction includes:
calculating the total information entropy of the evaluation attributes in combination with the sample data of the evaluation attributes; combining the multiple characteristic attributes to obtain multiple characteristic attribute combinations; calculating a second conditional entropy of each feature attribute combination relative to all the evaluation attributes by combining a plurality of acquisition sample data and a plurality of evaluation attribute sample data; obtaining a second information gain corresponding to each characteristic attribute combination according to the total information entropy and the second conditional entropy of each characteristic attribute combination; and taking the characteristic attribute combination with the maximum second information gain, and taking the characteristic attribute included in the characteristic attribute combination with the maximum second information gain as the characteristic attribute for evaluation prediction.
According to some embodiments of the present application, the classifying and regression training with reference to a plurality of target sample data to construct an evaluation prediction model includes:
dividing a plurality of target sample data into a training set with a first proportion and a testing set with a second proportion; constructing a decision tree by using the training set to obtain an evaluation prediction model; verifying the accuracy of the evaluation prediction model by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; and if the accuracy is less than the preset accuracy, continuing to execute the training step again.
According to some embodiments of the application, the method further comprises:
determining driving safety data matched with the driving takeover evaluation result by combining the driving takeover evaluation result, the vehicle driving data and the physiological characteristic data; and carrying out safety early warning processing by combining the driving safety data.
An electronic device according to an embodiment of a second aspect of the present invention includes:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring vehicle running data and physiological characteristic data of a driver when the vehicle is switched from automatic driving to manual driving;
the evaluation module is used for inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information; and determining the driving taking over evaluation result of the driver according to the evaluation attribute information.
An electronic device according to an embodiment of the third aspect of the present invention comprises a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for enabling connection communication between the processor and the memory, the program, when executed by the processor, implementing the steps of the aforementioned method.
A storage medium according to an embodiment of the fourth aspect of the invention for computer readable storage stores one or more programs executable by one or more processors to perform the steps of the aforementioned method.
Additional aspects and advantages of the present application 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 present application.
Drawings
The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a block diagram of a driving takeover capability evaluation system applied in an embodiment of the present application;
FIG. 2 is a block diagram of an electronic device according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of a driving takeover capability evaluation method disclosed in an embodiment of the present application;
FIG. 4 is a flow chart of another driving takeover capability assessment method disclosed in the embodiments of the present application;
FIG. 5 is a schematic diagram of a data structure of sample data collection and attribute sample data evaluation in an embodiment of the present application;
fig. 6 is a block diagram of another electronic device applied in the embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, suffixes such as "module", "part", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no peculiar meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
The invention provides a driving takeover capability evaluation method which can be applied to a driving takeover capability evaluation system. Specifically, the driving taking-over capability evaluation system is applied to an intelligent vehicle, and the intelligent vehicle can be a vehicle with an automatic driving function. Referring to fig. 1, fig. 1 is a block diagram illustrating a driving takeover capability evaluation system according to an embodiment of the present disclosure. As shown in fig. 1, the driving takeover capability evaluation system may include an electronic device 10, a physiological data acquisition system 20, and a driving data acquisition system 30.
In this embodiment, the electronic device 10 may be a vehicle-mounted terminal having an operation function, such as a vehicle body controller, a central control large screen, or a vehicle event data recorder, or may be a terminal device for controlling the vehicle-mounted terminal, such as a cloud server, without specific limitations. Referring to fig. 2, fig. 2 is a block diagram of an electronic device according to an embodiment of the disclosure. As shown in fig. 2, the electronic device 10 may include: memory 11, processor 12, network interface 13, and communication bus 14.
The memory 11 includes at least one type of readable storage medium, which may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory, and the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 10, such as a hard disk of the electronic device 10. In other embodiments, the readable storage medium may be an external memory of the electronic device 10, such as a plug-in hard disk provided on the electronic device 10, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like.
In the present embodiment, the readable storage medium of the memory 11 is generally used for storing a driving taking over capability evaluation program installed in the electronic device 10, a sample database, a pre-trained evaluation prediction model, and the like. The memory 11 may also be used to temporarily store data that has been output or is to be output.
The processor 12 may be a Central Processing Unit (CPU), a microprocessor or other data Processing chip in some embodiments, and is used for executing program codes stored in the memory 11 or Processing data, such as executing a driving taking-over capability evaluation program.
The network interface 13 is generally used to establish a communication connection between the electronic device 10 and other devices (such as a physiological data acquisition device and a driving data acquisition device), and the network interface 13 may include a standard wired interface, a wireless interface (such as bluetooth, WI-FI interface), and is not limited thereto.
The communication bus 14 is used to enable connection communication between these components.
Fig. 1 only shows an electronic device 10 having components 11-14, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
In the present embodiment, the physiological data acquisition system 20 is used for acquiring physiological characteristic data of the driver and transmitting the physiological characteristic data to the electronic device 10 for data processing by the processor 12. The physiological data acquisition system 20 can include, but is not limited to, the following physiological data acquisition devices: the system comprises a camera device, a photoelectric acquisition device, a sound acquisition device, an infrared sensing device and the like which are arranged in a vehicle; a unit or module in the electronic device 10 having a physiological characteristic acquisition function; wearable equipment (such as intelligent bracelet, wrist-watch or glasses etc.) that the driver wore, and be equipped with physiological characteristics collection module such as rhythm of the heart sensor, contact temperature sensor and respiratory rate sensor in the wearable equipment, do not specifically limit to this.
In the present embodiment, the driving data collecting system 30 is used for collecting vehicle driving data when the driver drives the vehicle, and transmitting the vehicle driving data to the electronic device 10 for data processing by the processor 12. The driving data collection system 30 may include, but is not limited to, at least one of the following driving data collection devices: the vehicle speed sensor, the wheel rotation angle measuring device, the steering wheel rotation angle sensor, the inertia measuring unit, the acceleration sensor, the brake pedal travel sensor, the accelerator pedal position sensor, the camera device (such as a monocular camera, a binocular camera or a depth camera), the ultrasonic radar device, the positioning device (such as a GPS positioning module or a Beidou positioning module) and the like are not limited specifically.
Optionally, the driving takeover capability evaluation system may further include an operation panel, and the operation panel may be disposed on the electronic device 10, or may be a separate display device in the vehicle, such as an on-board head-up display. In some embodiments, the operation panel may be an LED display, a liquid crystal display, an Organic Light-Emitting Diode (OLED) display, and the like. The operation panel is used to display information processed in the electronic device and to display a visualized user interface. Optionally, the operation panel may be stacked with the touch sensor to form a touch display screen, so that the electronic device 10 may detect a touch operation triggered by a user based on the touch display screen.
The following specifically describes a driving takeover capability evaluation method disclosed in the embodiment of the present application. It is understood that the driving takeover capability evaluation system described above is applicable to the driving takeover capability evaluation method in the embodiment of the present application.
As shown in fig. 3, fig. 3 is a flowchart of a driving takeover capability evaluation method disclosed in an embodiment of the present application. Based on the electronic device shown in fig. 2, the processor 12 implements the following steps:
300. when the vehicle is switched from automatic driving to manual driving, vehicle driving data and physiological characteristic data of a driver are obtained.
In this embodiment, when the vehicle is in autonomous driving, the driver can take over the vehicle actively, and the vehicle ends autonomous driving and switches to manual driving. Or when the vehicle judges that the current driving scene is not suitable for automatic driving, the vehicle prompts the driver, and the driver takes over the vehicle passively and then switches from automatic driving to manual driving. It is understood that the driving takeover capability evaluation method of the present application is applicable to the entire process from the start of automatic driving to manual driving until the end of manual driving.
In this embodiment, different driving data collecting devices are used in cooperation, and corresponding vehicle driving data can be collected, so the vehicle driving data may include but is not limited to: vehicle speed, wheel angle, steering wheel angle, vehicle yaw angle, vehicle acceleration, braking signal, braking depth, throttle depth, and the like.
In some implementations, the vehicle driving data may further include road condition information of the surroundings of the vehicle, the road condition information may be road information (such as lane lines, road signs, etc.) of the surroundings of the vehicle and surrounding vehicle movement information (such as the speed of the surrounding vehicle and the distance from the current vehicle) detected by at least one of a camera device provided on the vehicle body, an ultrasonic radar device provided on the vehicle body, and a positioning device, and the driving scene where the vehicle is located may be determined according to the road information, such as urban roads, expressways, ascending/descending roads, winding mountain roads, and elevated roads; and the running vehicle distance can be determined according to the motion information of the surrounding vehicles. Therefore, considering that the driver can show different takeover behavior abilities when dealing with different traffic road conditions, the takeover behavior analysis and supervision can be carried out in combination with specific traffic road conditions.
In this embodiment, different physiological data acquisition devices are used in cooperation, and corresponding physiological characteristic data can be acquired for the driver, so the physiological characteristic data can include but is not limited to: facial features (such as eye openness and facial expression), body posture features, blood volume pulses, respiratory rate, heart rate, and the like.
301. And inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information.
In this embodiment, the evaluation attribute information may specifically be a classification attribute, which is used to indicate categories to which different takeover capabilities belong, for example, the classification attribute includes excellent, good, general, poor, extremely poor, and the like; the evaluation attribute information may also be a numerical attribute for indicating a specific numerical level, for example, the numerical attribute includes X (X is a positive integer, such as 3) levels, and the lower (or higher) the level is, the more excellent the takeover capability is; this is not limitative.
In some optional implementations, the training step of the predetermined evaluation prediction model may specifically be:
firstly, a plurality of sample data are acquired when a vehicle is in a preset working condition. The collected sample data comprises driving sample data collected for the vehicle and physiological characteristic sample data collected for the driver. The preset working conditions comprise that the vehicle is in a dangerous driving scene and the vehicle is in manual driving. The dangerous driving scenes may include, but are not limited to, urban roads, expressways, curved mountain roads, and the like.
And then, performing takeover capability evaluation on the plurality of acquisition sample data, and determining evaluation attribute sample data corresponding to each acquisition sample data. The evaluation criterion for taking over the capability evaluation of the plurality of collected sample data may be determined based on human experience, which is not limited. It can be understood that the evaluation attribute sample data corresponds to the acquisition sample data one to one, and each evaluation attribute sample data is used for representing the evaluation attribute corresponding to the corresponding acquisition sample data.
And finally, carrying out classification and regression training by using a plurality of collected sample data and a plurality of evaluation attribute sample data to construct an evaluation prediction model. Specifically, the classification and regression training mode may adopt a decision tree algorithm, a naive bayes algorithm or a convolutional neural network algorithm, etc.
It is understood that the sample data for training the estimation and prediction model may be derived from the simulated driving training process of the driver, or may be derived from the actual driving process of the vehicle, so as to continuously optimize the estimation and prediction model. Optionally, in the process of driving training simulation, the vehicle may refer to a driving simulator, and the driving simulator may operate according to working parameters corresponding to different dangerous driving scenes. A driver operates an accelerator pedal, a brake pedal, a steering wheel, buttons and the like of the driving simulator according to the vehicle driving state and the simulated environment change presented by the driving simulator so as to simulate vehicle driving, so that sample data under various driving scenes can be flexibly collected.
Therefore, the physiological characteristics and the driving sample data of the manual driving of the driver in different dangerous driving scenes are collected, and the evaluation prediction model is trained continuously, so that the output result of the evaluation prediction model can reflect the driving taking over capability of the driver in response to emergency situations.
In some optional implementation manners, both the vehicle driving data and the physiological characteristic data can be preprocessed to obtain preprocessed data, and then the preprocessed data are input into a predetermined evaluation prediction model to obtain evaluation attribute information. The preprocessing method may include, but is not limited to, averaging, filtering, data synchronization, and fusion processing. The filtering process can adopt signal filtering modes such as low-pass filtering, band-pass filtering or complementary filtering and the like, and the effect of improving the signal-to-noise ratio of the signal is achieved. The data synchronization is used for synchronizing the data of different acquisition devices in time or space, for example, taking a specified acquisition frequency as a reference, and performing timestamp alignment on the data of different acquisition devices; for another example, the position data acquired by different acquisition devices is subjected to coordinate conversion based on a specified coordinate reference system. Moreover, the data fusion processing can adopt Kalman filtering or Bayesian estimation method, etc., and can reduce redundant information between data of different acquisition devices.
Therefore, the data are preprocessed and then input into the evaluation prediction model, and a more accurate and reliable evaluation result can be obtained.
302. And determining the driving takeover capability evaluation result of the driver according to the evaluation attribute information.
For example, if the evaluation attribute information adopts a numerical attribute, the driving takeover capability evaluation result can be determined according to the matching relationship between different numerical attributes and the driving takeover capability. For example, the numerical attribute is 0 level, and the evaluation result is good; the numerical attribute is level 1, and the evaluation result is poor; the numerical attribute was level 2, and the evaluation result was the worst.
As shown in fig. 4, fig. 4 is a flowchart of another driving takeover capability evaluation method disclosed in the embodiment of the present application. Based on the electronic device shown in fig. 2, the processor 12 implements the following steps:
400. the method comprises the steps of obtaining a plurality of collected sample data when a vehicle is in a preset working condition.
In this embodiment, the collected sample data includes driving sample data collected for the vehicle and physiological characteristic sample data collected for the driver, and the preset working condition includes that the vehicle is in a dangerous driving scene and is driven manually. From another perspective, the multiple collected sample data includes sample data corresponding to multiple characteristic attributes, where the multiple characteristic attributes include characteristic attributes corresponding to driving sample data and characteristic attributes corresponding to physiological characteristic sample data, and the characteristic attributes are used to represent data types.
401. And performing takeover capability evaluation on the plurality of acquisition sample data, and determining evaluation attribute sample data corresponding to each acquisition sample data.
In this embodiment, the sample data of the plurality of evaluation attributes includes sample data corresponding to the plurality of evaluation attributes.
For example, please refer to fig. 5, fig. 5 is a schematic diagram of a data structure of sample data collection and attribute sample data evaluation in an embodiment of the present application. As shown in fig. 5, taking the sample data of the collection with the number 1 as an example, the driving sample data corresponds to 6 characteristic attributes, that is, the vehicle speed, the wheel angle, the steering wheel angle, the vehicle yaw angle, the braking depth, and the accelerator depth. The physiological characteristic sample data corresponds to 4 characteristic attributes, namely facial characteristics, blood volume pulse, respiratory rate and heart rate. Therefore, the collected sample data includes the sample data corresponding to the 10 characteristic attributes, which are a1 to J1. Correspondingly, the evaluation attribute sample data corresponding to the collected sample data is determined to be level 0.
402. Combining a plurality of collected sample data and a plurality of evaluation attribute sample data, performing importance level sequencing on a plurality of characteristic attributes, and screening out the characteristic attributes for evaluation prediction; the above-described characteristic attributes for evaluation prediction and various evaluation attributes are used as decision factors.
In some optional implementations, the ranking of importance levels for the plurality of feature attributes may specifically include steps S1-S4:
and S1, calculating the total information entropy of various evaluation attributes by combining a plurality of evaluation attribute sample data. Specifically, the calculation formula (1) of the total information entropy may be:
(1)
wherein H (Y) is total information entropy, M is number of categories of evaluation attributes in multiple evaluation attribute sample data, pkThe probability of occurrence of the k-th evaluation attribute in all the evaluation attribute sample data.
And S2, combining a plurality of acquisition sample data and a plurality of evaluation attribute sample data, and calculating a first conditional entropy of each characteristic attribute relative to all evaluation attributes. Specifically, the calculation formulas (2) and (3) of the first conditional entropy of each feature attribute may be:
(2)
(3)
wherein H (Y | x)ij) The conditional entropy, P (y), of the jth sample data value corresponding to the ith characteristic attribute relative to all the evaluation attributesk|xij) The occurrence probability of the k-th evaluation attribute H (Y | x) when the j-th sample data corresponding to the known i-th characteristic attribute is taken as a valuei) First conditional entropy, P (x), for the ith characteristic attributeij) And the occurrence probability of the jth sample data value corresponding to the ith characteristic attribute in a plurality of collected sample data is set, and w is the number of the sample data values corresponding to the ith characteristic attribute.
Optionally, when the characteristic attribute is a numerical attribute, all sample data values of the numerical attribute in the multiple collected sample data may be classified to obtain multiple value intervals. And then classifying the sample data values of the numerical attribute in the plurality of collected sample data into corresponding value intervals, and calculating the number of the sample data values classified into the value intervals to obtain the occurrence probability of the value intervals. And finally, taking the value intervals as a plurality of sample data values corresponding to the numerical attributes again.
Wherein, still optionally, the discretization treatment specifically may be: and taking the maximum sample data value max and the minimum sample data value min based on all the sample data values of the numerical attribute in the plurality of the collected sample data, and dividing the value range between max and min into a plurality of value ranges according to the range, wherein the range is (max-min)/the number of the types of all the sample data values of the numerical attribute in the plurality of the collected sample data.
Illustratively, the characteristic attribute is a numerical attribute when the characteristic attribute is a vehicle speed. Assuming that the sample data values of the vehicle speed in the multiple collected sample data comprise: 40 km/hr, 65 km/hr, 75 km/hr and 80 km/hr, the interval range is (80-40)/4 is 10, and further 4 value intervals [40,50 ], [50,60 ], [60,70 ], [70,80] are obtained. Wherein, the sample data values classified in the value range [40,50) are 1 (40 km/h), the sample data values classified in the value range [50,60) are 0, the sample data values classified in the value range [60,70) are 1 (65 km/h), and the sample data values classified in the value range [70,80] are 2 (75 km/h and 80 km/h). Therefore, the sample data values corresponding to the vehicle speed are reclassified into value intervals [40,50 ], [60,70 ] and [70,80], the occurrence probability of the value interval [40,50 ] is 1/4, the occurrence probability of the value interval [60,70) is 1/4, and the occurrence probability of the value interval [70,80] is 1/2.
And S3, obtaining a first information gain corresponding to each characteristic attribute according to the total information entropy and the first conditional entropy of each characteristic attribute. Specifically, the calculation formula (4) for solving the first information gain may be:
(4)Gain(Y|xi)＝H(Y)-H(Y|xi)，Gain(Y|xi) And obtaining a first information gain corresponding to the ith characteristic attribute.
And S4, based on the first information gain corresponding to each characteristic attribute, performing importance level sorting on the multiple characteristic attributes to obtain N characteristic attributes before sorting as the characteristic attributes for evaluation and prediction, wherein N is a positive integer. N is a parameter set and adjusted manually, and is not limited.
In other alternative implementations, the ranking of importance levels for the plurality of feature attributes may specifically include steps S5-S9:
and S5, calculating the total information entropy of the multiple evaluation attributes by combining the sample data of the multiple evaluation attributes.
And S6, combining the multiple characteristic attributes to obtain multiple characteristic attribute combinations.
In particular, in some implementations, R (R is a positive integer, and R > N) features can be attributedPerforming permutation and combination to obtain
Each feature attribute combination is such that each feature attribute combination comprises N different feature attributes. In other implementation manners, the R kinds of feature attributes include a kind of feature attributes corresponding to the driving sample data and b kinds of feature attributes corresponding to the physiological feature sample data, or a first weight Qa and a second weight Qb may be set, and then the R kinds of feature attributes are arranged and combined, so that each feature attribute combination includes n kinds of feature attributes corresponding to the driving sample dataaN corresponding to the species characteristic attribute and the physiological characteristic sample databA seed characteristic attribute, and na+nb＝N,na＝Qa·N,nb＝QbN, so as to ensure that the characteristic attributes screened out according to the characteristic attribute combination for evaluating and predicting always cover the vehicle driving behavior characteristics and the physiological characteristics of the driver at the same time. Optionally, Qa＝na/N,Qb＝nband/N. In some implementations, the R feature attributes may be randomly combined without limitation.
And S7, calculating a second conditional entropy of each characteristic attribute combination relative to all the evaluation attributes by combining the plurality of acquisition sample data and the plurality of evaluation attribute sample data.
And S8, obtaining a second information gain corresponding to each characteristic attribute combination according to the total information entropy and the second conditional entropy of each characteristic attribute combination.
And S9, taking the characteristic attribute combination with the maximum second information gain, and taking the characteristic attribute included in the characteristic attribute combination with the maximum second information gain as the characteristic attribute for evaluation prediction.
The steps S5 and S7-S8 may refer to the above calculation formulas (1) - (4), and are not described in detail. For example, assuming that there are 4 feature attributes "vehicle speed", "brake depth", "facial feature" and "heart rate", and N takes a value of 3, the 4 feature attributes can be divided into 4 feature attribute combinations, namely: x is the number of1X ═ vehicle speed, brake depth, facial features ═ x2The speed of the vehicle (vehicle speed, braking depth,heart rate), x3Vehicle speed, facial features, heart rate, x4Not (depth of arrest, facial features, heart rate). If the second information gain of the 4 feature attribute combinations satisfies: gain (x)1)＞Gain(x2)＞Gain(x3)＞Gain(x4) Then the 3 characteristic attributes of vehicle speed, brake depth and facial features are taken as the characteristic attributes for evaluation prediction.
Therefore, by ranking the importance of various characteristic attributes and preferably selecting the characteristic attributes with larger information gain to add the decision factors for training the evaluation prediction model, the rationality of determining the decision factors can be improved, and the accuracy of analyzing the takeover capacity of the driver through the evaluation prediction model is further improved.
403. And acquiring sample data corresponding to the decision factor aiming at the plurality of the collected sample data and the plurality of the evaluation attribute sample data to be used as target sample data.
404. And carrying out classification and regression training by combining a plurality of target sample data to construct an evaluation prediction model.
In some optional implementations, step 404 may specifically be:
the method comprises the steps of dividing a plurality of target sample data into a training set with a first proportion and a testing set with a second proportion. Constructing a decision tree by using a training set to obtain an evaluation prediction model; verifying and evaluating the accuracy of the prediction model by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; and if the accuracy is less than the preset accuracy, continuing to execute the training step again.
The first ratio, the second ratio and the preset accuracy may be parameters set and adjusted based on human experience, and are not particularly limited. The algorithm used for the decision tree construction may be a C4.5 algorithm, an ID3 algorithm, or a CART algorithm, and the like, and is not particularly limited.
Specifically, in the process of constructing the decision tree by using the training set, the information division amount and the information gain rate of each decision factor can be calculated, and the tree nodes of the decision tree are selected by comparing the information gain rates of the decision factors until the processes of feature selection, decision tree generation and decision tree pruning are completed. The calculation formula (5) of the split information amount and the calculation formula (6) of the information gain ratio may be as follows:
(5)
(6)
wherein, the SplitInformation (S, D) is the division information quantity of the decision factor D, PkThe method comprises the steps of obtaining the occurrence probability of a kth sample data value corresponding to a decision factor D in a plurality of target sample data, obtaining the number of sample data values corresponding to the decision factor D in the plurality of target sample data, obtaining the information Gain of the decision factor D relative to the plurality of target sample data by Gain (S, D), and obtaining the information Gain rate of the decision factor D by Gain (S, D).
It can be understood that, in the decision tree-based evaluation prediction model, the decision tree nodes are each decision factor, and different branches of the decision tree nodes correspond to different data values of the decision factor. More specifically, leaf nodes in the decision tree nodes correspond to different evaluation attributes to be output as prediction results of the evaluation prediction model. Therefore, the decision tree is constructed based on the sample data corresponding to the decision factors, the classification precision and the generalization capability are good, a better fitting effect exists on the training set, and model verification and optimization can be performed through the verification set, so that the reliability of model construction is further improved.
405. When the vehicle is switched from automatic driving to manual driving, vehicle driving data and physiological characteristic data of a driver are obtained.
406. And inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information.
407. And determining the driving takeover capability evaluation result of the driver according to the evaluation attribute information.
It is understood that, in the embodiment, the specific implementation manner of steps 405 and 407 can also refer to the description of step 300 and 302 in the embodiment of the method shown in fig. 3, and is not described herein again.
408. And determining the driving safety data matched with the driving takeover evaluation result by combining the driving takeover evaluation result, the vehicle driving data and the physiological characteristic data.
In this embodiment, specifically, for the vehicle driving data and the physiological characteristic data, target characteristic attributes included in the vehicle driving data and the physiological characteristic data may be determined, and then, a safety data value of each target characteristic attribute is determined by combining the driving takeover evaluation result to serve as driving safety data, so that the driving safety data conforms to the actual takeover capability of the driver, and the method is flexibly applicable to safe driving scenes of different drivers. More specifically, the driving safety data may further include a warning time and a safe vehicle distance.
409. And carrying out safety early warning processing by combining the driving safety data.
In some embodiments, step 409 may specifically be: and aiming at each target characteristic attribute, matching the actual data value of the target characteristic attribute in the vehicle driving data (or physiological characteristic data) with the safety data value in the driving safety data to obtain unmatched target characteristic attributes, and outputting early warning information to the unmatched target characteristic attributes through the vehicle-mounted terminal, wherein the output mode of the early warning information can include but is not limited to voice warning, video playing, interface popup window output or prompt lamp lighting. For example, the vehicle voice alerts "vehicle speed too fast", "driver heart rate too fast", etc.
Optionally, if the unmatched target characteristic attribute belongs to the physiological characteristic, the driving state of the driver may be determined according to the unmatched target characteristic attribute, and the working parameter of the control system in the vehicle may be adjusted according to the driving state. In-vehicle control systems include, but are not limited to, audio systems, air conditioning systems, and the like. For example, if the driving state of the driver is determined to be fatigue driving, the sound system can be controlled to play dynamic and cheerful music; if the driving state is judged to be the existence of the anxiety, the sound system can be controlled to play relaxing music, and the air conditioning system is controlled to lower the temperature of the air conditioner in the vehicle.
Therefore, safety warning is carried out by combining the physiological characteristics of the driver and the vehicle running characteristics, intervention and supervision can be carried out on invalid and irregular taking-over behaviors, driving safety is improved, and theoretical guidance is conveniently provided for driver quality training.
The embodiment of the application also provides an electronic device. Referring to fig. 6, fig. 6 is a block diagram of another electronic device according to an embodiment of the disclosure. As shown in fig. 6, the electronic device 600 includes:
the acquiring module 610 is used for acquiring vehicle running data and physiological characteristic data of a driver when the vehicle is switched from automatic driving to manual driving.
The evaluation module 620 is used for inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information; and determining a driving takeover evaluation result of the driver according to the evaluation attribute information.
It should be noted that, for the specific implementation process of this embodiment, reference may be made to the specific implementation process described in the foregoing method embodiment, and details are not described again.
By implementing the driving taking-over capacity evaluation method and the electronic device provided by the embodiment of the application, the driving taking-over capacity of the driver is effectively evaluated by combining the driving condition of the vehicle and the physiological state of the driver, an effective evaluation standard can be provided for supervision and intervention of the vehicle taking-over behavior, and the driving safety of the intelligent vehicle is favorably improved.
One of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not to be construed as limiting the scope of the invention. Any modifications, equivalents and improvements which may occur to those skilled in the art without departing from the scope and spirit of the present invention are intended to be within the scope of the claims.
Claims (10)
1. A driving takeover capability evaluation method, characterized by comprising:
when the vehicle is switched from automatic driving to manual driving, vehicle driving data and physiological characteristic data of a driver are obtained;
inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information;
and determining the driving taking over capability evaluation result of the driver according to the evaluation attribute information.
2. The method of claim 1, wherein the step of training the predetermined assessment prediction model comprises:
acquiring a plurality of acquisition sample data when a vehicle is in a preset working condition, wherein the acquisition sample data comprises driving sample data acquired for the vehicle and physiological characteristic sample data acquired for a driver, and the preset working condition comprises that the vehicle is in a dangerous driving scene and is driven manually;
performing takeover capability evaluation on a plurality of acquisition sample data, and determining evaluation attribute sample data corresponding to each acquisition sample data;
and carrying out classification and regression training by using the plurality of the acquisition sample data and the plurality of the evaluation attribute sample data to construct an evaluation prediction model.
3. The method according to claim 2, wherein the plurality of the collection sample data includes sample data corresponding to a plurality of characteristic attributes, and the plurality of the evaluation attribute sample data includes sample data corresponding to a plurality of evaluation attributes; the classifying and regression training is performed by using the plurality of the acquisition sample data and the plurality of the evaluation attribute sample data, and an evaluation prediction model is constructed, including:
combining a plurality of the collected sample data and a plurality of the evaluation attribute sample data, performing importance level sorting on a plurality of characteristic attributes, and screening out the characteristic attributes for evaluation prediction;
taking the characteristic attribute for evaluation prediction and a plurality of evaluation attributes as decision factors;
acquiring sample data corresponding to the decision factor aiming at a plurality of acquisition sample data and a plurality of evaluation attribute sample data to serve as target sample data;
and carrying out classification and regression training by combining a plurality of target sample data to construct an evaluation prediction model.
4. The method according to claim 3, wherein said combining a plurality of said sample data for collection and a plurality of said sample data for evaluation attributes, ranking a plurality of feature attributes according to importance, and screening out feature attributes for evaluation prediction comprises:
calculating the total information entropy of the evaluation attributes in combination with the sample data of the evaluation attributes;
calculating a first conditional entropy of each feature attribute relative to all the evaluation attributes by combining a plurality of acquisition sample data and a plurality of evaluation attribute sample data;
obtaining a first information gain corresponding to each characteristic attribute according to the total information entropy and the first conditional entropy of each characteristic attribute;
and based on the first information gain corresponding to each kind of the characteristic attributes, carrying out importance level sorting on the plurality of kinds of the characteristic attributes to obtain the characteristic attributes of N before sorting as the characteristic attributes for evaluating and predicting, wherein N is a positive integer.
5. The method according to claim 3, wherein said combining a plurality of said sample data for collection and a plurality of said sample data for evaluation attributes, ranking a plurality of feature attributes according to importance, and screening out feature attributes for evaluation prediction comprises:
calculating the total information entropy of the evaluation attributes in combination with the sample data of the evaluation attributes;
combining the multiple characteristic attributes to obtain multiple characteristic attribute combinations;
calculating a second conditional entropy of each feature attribute combination relative to all the evaluation attributes by combining a plurality of acquisition sample data and a plurality of evaluation attribute sample data;
obtaining a second information gain corresponding to each characteristic attribute combination according to the total information entropy and the second conditional entropy of each characteristic attribute combination;
and taking the characteristic attribute combination with the maximum second information gain, and taking the characteristic attribute included in the characteristic attribute combination with the maximum second information gain as the characteristic attribute for evaluation prediction.
6. The method of claim 3, wherein the performing classification and regression training in combination with a plurality of the target sample data to construct an evaluation prediction model comprises:
dividing a plurality of target sample data into a training set with a first proportion and a testing set with a second proportion;
constructing a decision tree by using the training set to obtain an evaluation prediction model;
verifying the accuracy of the evaluation prediction model by using the test set, and finishing training if the accuracy is greater than or equal to a preset accuracy; and if the accuracy is less than the preset accuracy, continuing to execute the training step again.
7. The method according to any one of claims 1 to 6, further comprising:
determining driving safety data matched with the driving takeover evaluation result by combining the driving takeover evaluation result, the vehicle driving data and the physiological characteristic data;
and carrying out safety early warning processing by combining the driving safety data.
8. An electronic device, comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring vehicle running data and physiological characteristic data of a driver when the vehicle is switched from automatic driving to manual driving;
the evaluation module is used for inputting the vehicle driving data and the physiological characteristic data into a predetermined evaluation prediction model to obtain evaluation attribute information; and determining the driving taking-over evaluation result of the driver according to the evaluation attribute information.
9. An electronic device, characterized in that the electronic device comprises a memory, a processor, a program stored on the memory and executable on the processor, and a data bus for realizing connection communication between the processor and the memory, the program, when executed by the processor, realizing the steps of the driving takeover capability evaluation method according to any one of claims 1 to 7.
10. A storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs executable by one or more processors to implement the steps of the driving takeover capability assessment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110721376.1A CN113415292A (en) | 2021-06-28 | 2021-06-28 | Driving takeover capability evaluation method and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110721376.1A CN113415292A (en) | 2021-06-28 | 2021-06-28 | Driving takeover capability evaluation method and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113415292A true CN113415292A (en) | 2021-09-21 |
Family
ID=77717810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110721376.1A Pending CN113415292A (en) | 2021-06-28 | 2021-06-28 | Driving takeover capability evaluation method and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113415292A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970705A (en) * | 2022-05-20 | 2022-08-30 | 深圳市有一说一科技有限公司 | Driving state analysis method, device, equipment and medium based on multi-sensing data |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170066452A1 (en) * | 2015-09-04 | 2017-03-09 | Inrix Inc. | Manual vehicle control notification |
| CN207190754U (en) * | 2017-09-22 | 2018-04-06 | 华东交通大学 | A kind of motorcar electric sun shield |
| CN109398229A (en) * | 2018-08-11 | 2019-03-01 | 华东交通大学 | A kind of highway turns around alarm set and based reminding method |
| US20190204826A1 (en) * | 2017-12-28 | 2019-07-04 | Automotive Research & Testing Center | Safe warning system for automatic driving takeover and safe warning method thereof |
| CN110371132A (en) * | 2019-06-18 | 2019-10-25 | 华为技术有限公司 | Driver's adapter tube appraisal procedure and device |
| GB2574877A (en) * | 2018-06-22 | 2019-12-25 | Jaguar Land Rover Ltd | Apparatus and methods for controlling a transition between driving modes |
| CN111016914A (en) * | 2019-11-22 | 2020-04-17 | 华东交通大学 | Dangerous driving scene identification system based on portable terminal information and identification method thereof |
| US20200319635A1 (en) * | 2019-04-04 | 2020-10-08 | International Business Machines Corporation | Semi-autonomous vehicle driving system, and method of operating semi-autonomous vehicle |
| CN111915159A (en) * | 2020-07-15 | 2020-11-10 | 北方工业大学 | Personalized takeover early warning method and system based on dynamic time budget |
| CN112406882A (en) * | 2020-11-11 | 2021-02-26 | 中汽研汽车检验中心（天津）有限公司 | Device for monitoring state of driver in man-machine co-driving process and method for evaluating pipe connection capability |
| CN112693469A (en) * | 2021-01-05 | 2021-04-23 | 中国汽车技术研究中心有限公司 | Method and device for testing vehicle taking over by driver, electronic equipment and medium |
-
2021
- 2021-06-28 CN CN202110721376.1A patent/CN113415292A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170066452A1 (en) * | 2015-09-04 | 2017-03-09 | Inrix Inc. | Manual vehicle control notification |
| CN207190754U (en) * | 2017-09-22 | 2018-04-06 | 华东交通大学 | A kind of motorcar electric sun shield |
| US20190204826A1 (en) * | 2017-12-28 | 2019-07-04 | Automotive Research & Testing Center | Safe warning system for automatic driving takeover and safe warning method thereof |
| GB2574877A (en) * | 2018-06-22 | 2019-12-25 | Jaguar Land Rover Ltd | Apparatus and methods for controlling a transition between driving modes |
| CN109398229A (en) * | 2018-08-11 | 2019-03-01 | 华东交通大学 | A kind of highway turns around alarm set and based reminding method |
| US20200319635A1 (en) * | 2019-04-04 | 2020-10-08 | International Business Machines Corporation | Semi-autonomous vehicle driving system, and method of operating semi-autonomous vehicle |
| CN110371132A (en) * | 2019-06-18 | 2019-10-25 | 华为技术有限公司 | Driver's adapter tube appraisal procedure and device |
| CN111016914A (en) * | 2019-11-22 | 2020-04-17 | 华东交通大学 | Dangerous driving scene identification system based on portable terminal information and identification method thereof |
| CN111915159A (en) * | 2020-07-15 | 2020-11-10 | 北方工业大学 | Personalized takeover early warning method and system based on dynamic time budget |
| CN112406882A (en) * | 2020-11-11 | 2021-02-26 | 中汽研汽车检验中心（天津）有限公司 | Device for monitoring state of driver in man-machine co-driving process and method for evaluating pipe connection capability |
| CN112693469A (en) * | 2021-01-05 | 2021-04-23 | 中国汽车技术研究中心有限公司 | Method and device for testing vehicle taking over by driver, electronic equipment and medium |
Non-Patent Citations (2)
| Title |
|---|
| 严利鑫: "智能辅助驾驶***模式决策建模与安全性评价研究", 《工程科技Ⅱ辑》 * |
| 安玉等: "考虑多因素的驾驶行为安全评价与风险等级预测", 《***仿真学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114970705A (en) * | 2022-05-20 | 2022-08-30 | 深圳市有一说一科技有限公司 | Driving state analysis method, device, equipment and medium based on multi-sensing data |
| CN114970705B (en) * | 2022-05-20 | 2024-05-07 | 深圳市有一说一科技有限公司 | Running state analysis method, device, equipment and medium based on multi-sensing data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10346888B2 (en) | Systems and methods to obtain passenger feedback in response to autonomous vehicle driving events | |
| US11900738B2 (en) | Systems and methods to obtain feedback in response to autonomous vehicle failure events | |
| CN107492251B (en) | Driver identity recognition and driving state monitoring method based on machine learning and deep learning | |
| US9676395B2 (en) | Incapacitated driving detection and prevention | |
| CN101389521B (en) | Drive behavior estimating device, drive supporting device, vehicle evaluating system | |
| US7444311B2 (en) | System and method for real-time recognition of driving patterns | |
| CN110329271A (en) | A kind of multisensor vehicle driving detection system and method based on machine learning | |
| CN109388130A (en) | The security control of the automotive vehicle of networking | |
| CN109670970B (en) | Driving behavior scoring method and device and computer readable storage medium | |
| CN110119714B (en) | Driver fatigue detection method and device based on convolutional neural network | |
| US10528833B1 (en) | Health monitoring system operable in a vehicle environment | |
| CN111275249A (en) | Driving behavior optimization method based on DQN neural network and high-precision positioning | |
| CN109084992A (en) | Method based on engine bench test unmanned vehicle intelligence | |
| CN105930771A (en) | Driving behavior grading method and device | |
| CN111152788A (en) | Method and system for preventing mistaken stepping of accelerator pedal of vehicle | |
| CN109664894A (en) | Fatigue driving safety pre-warning system based on multi-source heterogeneous data perception | |
| US20220018906A1 (en) | Predicting An Outcome Associated With A Driver Of A vehicle | |
| CN110175654A (en) | A kind of update method and system of track road sign | |
| CN110263836B (en) | Bad driving state identification method based on multi-feature convolutional neural network | |
| CN113415292A (en) | Driving takeover capability evaluation method and electronic device | |
| CN111626905A (en) | Passenger safety monitoring method and device and computer readable storage medium | |
| CN112462759B (en) | Evaluation method, system and computer storage medium of rule control algorithm | |
| CN115635982A (en) | Automatic driving method and system based on driving efficiency and comfort | |
| CN112706776B (en) | Method and device for determining road calibration data, electronic equipment and storage medium | |
| GB2564563A (en) | Vehicle driver workload management |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210921 |
|
| RJ01 | Rejection of invention patent application after publication |