CN112208547B - Safe automatic driving system - Google Patents
Safe automatic driving system Download PDFInfo
- Publication number
- CN112208547B CN112208547B CN202011047864.0A CN202011047864A CN112208547B CN 112208547 B CN112208547 B CN 112208547B CN 202011047864 A CN202011047864 A CN 202011047864A CN 112208547 B CN112208547 B CN 112208547B
- Authority
- CN
- China
- Prior art keywords
- strategy
- information
- mobile phone
- driver
- module
- 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.)
- Active
Links
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
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- 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)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automatic driving, and discloses a safe automatic driving system which comprises a starting module, a state acquisition module, an information processing module and an action execution module, wherein the starting module starts the state acquisition module after receiving control mode switching information sent by the automatic driving system, the state acquisition module acquires current driving state information of a driver and sends the driving state information to the information processing module, the information processing module compares the acquired driving state information with preset abnormal behavior information and outputs a judgment instruction, and the action execution module receives the judgment instruction and controls an execution unit to execute a behavior correction strategy according to the judgment instruction. According to the invention, the corresponding correction strategy is called and started through the action execution module to remind the driver of correcting the driving state, so that the driver is ensured to have a better driving state when taking over the vehicle, and the driving safety of the vehicle is improved.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a safe automatic driving system.
Background
With the development of technology, the automatic driving automobile is becoming an important development direction of the current automobile. The automatic driving automobile depends on the cooperation of artificial intelligence, visual calculation, radar, monitoring device and global positioning system, so that the computer can automatically and safely operate the motor vehicle to move without any active operation of human. The automatic driving vehicle can help improve the travel convenience and the travel experience of people, and can also greatly improve the travel efficiency of people and the driving comfort in long-distance travel.
However, at present, since the automatic driving technology is not mature, the automatic driving state needs to be switched to the manual driving state in a complicated road condition and a high risk area, but the state of the driver is not determined and corrected when the driving state is switched, and usually the driver is in a relaxed state after entering the automatic driving state, and even in the actual driving process, the situation that the driver operates the mobile phone to process other matters when the automatic driving state is switched to the manual driving state occurs, so that the situation that the driving danger occurs because the driver cannot immediately control the vehicle when the state is switched to the manual driving state exists.
Disclosure of Invention
In view of the defects in the prior art, an object of the present invention is to provide a safe automatic driving system, which can determine and correct the driving state of the driver when the automatic driving state is switched to the manual state, so as to ensure that the driver can maintain a good operation state when taking over the vehicle, thereby improving the driving safety of the vehicle.
In order to achieve the above purpose, the invention provides the following technical scheme:
a safe automatic driving system comprises a starting module, a state acquisition module, an information processing module and an action execution module, wherein the starting module is in communication connection with the automatic driving system and is used for receiving control mode switching information sent by the automatic driving system;
the state acquisition module comprises an image acquisition unit, and the image acquisition unit acquires driving image information of a driver;
the information processing module comprises a model configuration library, a model training information library and a judgment strategy and result sending module, wherein a three-dimensional digital model of the hand operation mobile phone is prestored in the model configuration library, a first standard quantity is prestored in the model training information library, the first standard quantity is image information of a driver when the driver uses the mobile phone at a driving position, the judgment strategy comprises a feature identification sub-strategy and a judgment sub-strategy, the feature identification sub-strategy is used for comparing the driving image information with information, stored in the model configuration library in advance, of the same feature in the three-dimensional digital model of the hand operation mobile phone, and recording the information as a first comparison quantity, the first comparison quantity is input into a preset acquaintance judgment algorithm to obtain a first similar quantity, and when the first similar quantity is larger than a preset first judgment threshold value, the judgment sub-strategy calls the first comparison quantity, compares the first comparison quantity with the first standard quantity and records a comparison result as a second similar quantity, when the second similarity is larger than a preset second standard quantity, outputting a first action result A, and sending the first action result to the action execution module by the result sending module;
the action execution module comprises a receiving unit and a control unit, and when the receiving unit receives that the first action result is A, the control unit controls the execution unit to execute a correction strategy, wherein the correction strategy is used for correcting the state of the driver. According to the scheme, when the automatic driving is switched to the manual state, whether the driver is in the state of operating the mobile phone is judged in advance, and if the driver is in the state, the driving state of the driver is reminded and corrected, so that the driver is guaranteed to have a good driving state when taking over the vehicle, and the driving safety of the vehicle is improved.
In the invention, further, the state acquisition module comprises a sign acquisition unit, and the sign acquisition unit acquires the blood pressure and heart rate information of the driver and records the information as a second comparison quantity;
first feature data are stored in the model configuration library in advance, and the first feature data are numerical ranges of heart rate and blood pressure when a driver is in a sleeping state;
the judgment sub-strategy compares a second comparison quantity with the first feature data and records a result as a second behavior result, and if the second comparison quantity falls into the first feature data, a second behavior result is output as B;
and when the receiving unit receives the first behavior result A or the second behavior result B, the control unit controls the execution unit to execute a correction strategy, and the correction strategy is used for reminding and correcting the state of the driver. In the scheme, whether the driver is in a sleeping state or not can be monitored, and the monitoring range is wider.
In the present invention, the state acquisition module includes a mobile phone operation acquisition unit, the mobile phone operation acquisition unit is configured to acquire mobile phone state information, the mobile phone state information includes whether an operation instruction is input to the mobile phone, when the mobile phone state information indicates that the operation instruction is input, a third action result is output as C, and when the action execution module receives the first action result a and/or the third action result as C, the control unit controls the execution unit to execute the correction policy. According to the scheme, whether the driver is in the state of operating the mobile phone or not can be detected by increasing the number of the acquisition mobile phone ends and inputting the operation instruction, a more accurate judgment result can be obtained by increasing the detection mode, and the identification accuracy is improved.
In the present invention, further, an update policy is configured in the information processing module, the update policy includes an update judgment sub-policy and an information supplement sub-policy, the update judgment sub-policy judges whether to trigger an update, the information supplement sub-policy is used to store new information into a model configuration library and a model training information library, a first update interval and a first judgment policy are set in the update judgment sub-policy, the first judgment policy is a ratio of times of counting a first action result a in a first identification time and is recorded as a first update comparison quantity, and when the first update comparison quantity or the first update interval reaches a threshold value, the information supplement sub-policy is started to request to re-enter current three-dimensional model information of a mobile phone, three-dimensional model information of a driver's hand, and a first standard quantity. The scheme is used for regularly updating the pre-stored information in time so as to ensure that the result is more accurate when judgment and comparison are carried out.
In the present invention, the correction strategy further includes a first correction strategy, where the first correction strategy is used to remind the driver of paying attention to the current state, and the first correction strategy is to start a player to play a prompt tone and open a music player to play music. The scheme can remind the driver in a prompt tone mode, and the state of the driver is adjusted by opening the music player to play music.
In the present invention, the correction strategy further includes a second correction strategy, the second correction strategy includes a road condition judgment sub-strategy and an inching brake sub-strategy, the road condition judgment sub-strategy is used for detecting a first safety distance, the first safety distance is a distance between the vehicle and a nearest vehicle behind the vehicle in the traveling direction of the vehicle, when the first safety distance meets a preset first safety condition, the inching brake sub-strategy is started, and the inching brake sub-strategy is used for slowing down the vehicle speed through multiple times of braking. The scheme can change the speed of the vehicle in a snub braking mode, and meanwhile, the change of the speed of the vehicle can drive the change of the riding posture of a driver to correct the state of the driver.
In the invention, further, the correcting strategy comprises a third correcting strategy, an air outlet adjusting assembly and a waking unit, the third correcting strategy is used for adjusting the air outlet direction of the air conditioner to the air inlet of the waking unit, the waking unit is detachably fixed on the outer side of the air outlet of the air conditioner, and when the air quantity enters the air inlet of the waking unit, the waking unit outputs waking spray. The scheme outputs the waking spray by changing the direction of the air outlet of the air conditioner, so that the driver is in the waking state.
In the invention, the air outlet angle adjusting assembly further comprises an air guide frame and a shielding unit, a selection air channel and an air guide fan blade are fixed in the air guide frame, the shielding unit comprises a baffle and a driving unit, and the driving unit drives the baffle to move so as to realize the opening or closing of the selection air channel. The output and the closing of the sober spray are realized by controlling the shielding and the opening of the baffle plate to the selection air channel.
In the present invention, further, the acquaintance determination algorithm is:
wherein Y is a first similar amount; n is the collected characteristic quantity of the screen when the mobile phone is awakened;u is the number of the collected appearance characteristics of the mobile phone; g is the collected characteristic quantity of the hand; k1、K2、K3Are weight coefficients. This scheme provides a set of decision algorithms for the first similarity measure, where K1、K2、K3Is a constant that characterizes the weight that an individual feature occupies in the overall algorithm, K1＝3；K2＝1；K3E is the average of the total number of features in the three-dimensional digital model of the hand-operated mobile phone at a single viewing angle.
In the present invention, it is further characterized in that the three-dimensional model information of the mobile phone includes a three-dimensional model of an individual mobile phone and a three-dimensional model when a mobile phone protective case is sleeved on the three-dimensional model information. The judgment can make the output result more accurate by adding the three-dimensional model information of the mobile phone protective sleeve.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, when the automatic driving is switched to the manual state, whether the driver is in the abnormal driving state of operating the mobile phone or sleeping is judged through the state acquisition module and the information processing module, and the driving state of the driver is corrected by calling and starting the corresponding correction strategy through the action execution module, so that the driver is ensured to have a good driving state when taking over the vehicle, and the driving safety of the vehicle is improved.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
Fig. 2 is a schematic diagram of a control strategy between the state acquisition module and the information processing module.
FIG. 3 is a logic diagram of the information processing module for identifying the operation of the mobile phone by the driver.
Fig. 4 is a flowchart for determining whether the driver is in a sleep state.
Fig. 5 is a logic diagram for determining that the driver operates the mobile phone through the mobile phone operation acquisition unit.
Fig. 6 is a schematic view of the air outlet angle adjusting assembly.
In the drawings: 1. a starting module; 2. a state acquisition module; 21. a physical sign acquisition unit; 22. an image acquisition unit; 23. a mobile phone operation acquisition unit; 3. an information processing module; 31. a model training information base; 32. a model configuration library; 33. judging a strategy; 331. a feature identification sub-strategy; 332. judging a sub-strategy; 34. a result sending module; 4. an action execution module; 51. selecting an air channel; 52. a fan blade; 53. a baffle plate; 54. a drive unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When a component is referred to as being "connected" to another component, it can be directly connected to the other component or intervening components may also be present. When a component is referred to as being "disposed on" another component, it can be directly on the other component or intervening components may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1 to 3, a preferred embodiment of the present invention provides a safe automatic driving system, including a starting module 1, a state collecting module 2, an information processing module 3, and an action executing module 4, where the starting module 1 is in communication connection with the automatic driving system, the starting module 1 is configured to receive control mode switching information sent by the automatic driving system, the starting module 1 starts the state collecting module 2 after receiving the control mode switching information, the state collecting module 2 obtains current driving state information of a driver, and sends the driving state information to the information processing module 3, the information processing module 3 compares the obtained driving state information with preset abnormal behavior information and outputs a decision instruction, and the action executing module 4 receives the decision instruction and controls an executing unit to execute a behavior correcting strategy according to the decision instruction; the correction strategy is provided with a plurality of corresponding correction strategies which can be started according to the state of the driver determined by the information processing module 3, if the driver is determined to be reminded through voice prompt when operating a mobile phone, the driver can also be reminded through changing the vehicle speed, if the driver is determined to be in a sleep state, the selection air channel 51 can be opened to enable the driver to be awake through outputting awake spray or change the vehicle speed to remind the driver of correcting the riding posture of the driver, meanwhile, the execution module can be connected with the adjustment module of the electric adjustment seat, and the driver can be reminded through adjusting the posture of the seat.
The state acquisition module 2 comprises an image acquisition unit 22, and the image acquisition unit 22 acquires driving image information of a driver;
as shown in fig. 2 and 3, the information processing module 3 includes a model configuration library 32, a model training information library 31, a determination policy 33, and a result transmission module 34, where the model configuration library 32 stores a three-dimensional digital model of a hand-operated mobile phone in advance, the three-dimensional digital model of the hand-operated mobile phone may be pre-established and stored in the model configuration library 32, or the three-dimensional digital model information may be established in a later stage specifically for a mobile phone used by a driver of a corresponding vehicle and information of the hand of the driver. The model training information base 31 stores a first standard quantity in advance, the first standard quantity is image information of a common posture of a driver when the driver is located at a driving position and uses a mobile phone, each frame of image information input into the model training information base 31 is processed by the feature identification sub-strategy 331, namely, each frame of image information is compared with a three-dimensional digital model of a hand-operated mobile phone stored in the model configuration base 32 in advance, compared information with the same features and counted information with the same features are stored in a single frame data packet, and then the single frame data packet is stored in the model training information base 31, so that an image acquired by the image acquisition unit 22 can be compared with each group of single frame data packets in the first standard quantity in the later period, and the accuracy of a judgment result is further improved. The judgment strategy 33 comprises a feature identification sub-strategy 331 and a judgment sub-strategy 332, wherein the feature identification sub-strategy 331 is used for comparing the rider image information collected by the camera with the information of the same feature in the three-dimensional digital model of the hand-operated mobile phone pre-stored in the model configuration library 32 and recording the information as a first comparison quantity, the first comparison quantity is input into a preset identification degree judgment algorithm to obtain a first similarity quantity, and when the first similarity quantity is larger than a preset first judgment threshold (60%), the judgment sub-strategy 332 is called to call the first comparison quantity and compare the first comparison quantity with the first standard quantity and record a comparison result as a second similarity quantity. The detailed comparison method in the comparison between the first comparison quantity and the first standard quantity is to compare the image feature information recorded in the first comparison quantity with a single frame data packet of each frame image in the first standard quantity pre-stored in the model training information base 31, and when the ratio between the same feature quantity and the total feature quantity in a certain single frame data packet is greater than a preset second standard quantity (e.g. 50%), output the first behavior result as a, and the value of the second standard quantity can be adjusted.
The acquaintance determination algorithm is as follows:
wherein Y is a first similar amount; n is the collected characteristic quantity of the screen when the mobile phone is awakened; u is the number of the collected appearance characteristics of the mobile phone; g is the collected characteristic quantity of the hand; k1、K2、K3E is the average value of the total number of features in the three-dimensional digital model of the hand-operated mobile phone at a single visual angle, the average value is obtained by defining the placing visual angles of a plurality of three-dimensional models, and the plurality of groups of pendulumsThe viewing angle may be set according to a photographing angle formed between the posture of the driver when operating the mobile phone and the image capturing unit 22, and the total number of features at each viewing angle is counted and then averaged. This scheme provides a set of decision algorithms for the first similarity measure, where K1、K2、K3Is a constant that characterizes the weight that each feature quantity occupies in the whole algorithm, K1＝3；K2＝1；K 32. The screen features are pattern features of the screen, a plurality of sampling areas are divided in advance in the screen part of the mobile phone in the three-dimensional digital model of the hand-operated mobile phone, and if the pattern features can be identified in one sampling area, the number of the features of one screen is recorded. The mobile phone appearance characteristics and the characteristics of the hand are the shape characteristics of the mobile phone in the three-dimensional digital model of the hand operation mobile phone and the positions of a plurality of acquisition points arranged in the hand.
The action execution module 4 includes a receiving unit and a control unit, and when the receiving unit receives that the first action result is a, the control unit controls the execution unit to execute a correction strategy, and the correction strategy is used for correcting the state of the driver. Whether the driver is in the state of operating the mobile phone or not is judged in advance when the automatic driving is switched to the manual state, and if the driver is in the state, the driving state of the driver is reminded and corrected, so that the driver is guaranteed to have a good driving state when taking over the vehicle, and the driving safety of the vehicle is improved.
As shown in fig. 4, the state acquisition module 2 includes a sign acquisition unit 21, and the sign acquisition unit 21 acquires blood pressure and heart rate information of the driver and records the information as a second contrast amount; this sign acquisition unit 21 is current wearing formula bracelet, and this bracelet no longer complains here for prior art, and driver's blood pressure and rhythm of the heart characteristic can be gathered in real time to this wearing formula bracelet to in sending this data to the information processing module 3 in this system through LAN or bluetooth module, in order to be prepared for the characteristic contrast in later stage.
The model configuration library 32 is pre-stored with first feature data, wherein the first feature data is a numerical range of heart rate and blood pressure when the driver is in a sleeping state; the range of heart rate and blood pressure values can be values collected by the driver during sleeping at ordinary times or values of heart rate and blood pressure values of the driver in a sleeping state detected from a hospital.
The judgment sub-strategy 332 compares the second comparison quantity with the first feature data and records the result as a second behavior result, if the second comparison quantity falls into the first feature data, the second behavior result is output as B, otherwise, the first behavior result is output as 0;
when the receiving unit receives the first behavior result A or the second behavior result B, the control unit controls the execution unit to execute a correction strategy, and the correction strategy is used for reminding and correcting the state of the driver. When the receiving unit receives the first action result A and the second action result is 0, the correction strategy executed by the execution unit is used for reminding the driver to turn off the mobile phone and adjusting the state to take over the driving of the vehicle. When the receiving unit receives the first action result 0 and the second action result is B, the execution unit executes the correction strategy for enabling the sleeping driver to be awake and the adjustment state is ready for taking over the driving of the vehicle. When the first behavior result 0 and the second behavior result 0 are received, the execution unit does not execute any correction strategy, and the driver is in a normal driving state and can take over the vehicle in time without correction.
As shown in fig. 5, the state collection module 2 includes a mobile phone operation collection unit 23, the mobile phone operation collection unit 23 is configured to collect mobile phone state information, application software capable of detecting whether the mobile phone has an instruction input is pre-installed in the mobile phone, and when it is detected that the mobile phone has the instruction input, the information is sent to the result sending module 34, the result sending module 34 outputs a third behavior result as C, and when the action execution module 4 receives the first behavior result as a and/or the third behavior result as C, the control unit controls the execution unit to execute the correction policy. Whether the driver is in the state of operating the mobile phone is detected by additionally arranging whether the acquisition mobile phone end has operation instruction input, and the accuracy of identifying the result of using the mobile phone by the driver can be higher by additionally arranging the detection mode.
The information processing module 3 is configured with an update strategy, the update strategy comprises an update judgment sub-strategy and an information supplement sub-strategy, the update judgment sub-strategy judges whether to trigger update, the information supplement sub-strategy is used for storing new information into the model configuration library 32 and the model training information library 31, a first update interval and a first judgment strategy 33 are arranged in the update judgment sub-strategy, the first judgment strategy 33 is used for counting the ratio of times of a first action result A in the first identification times and recording the ratio as a first update contrast quantity, and when the first update contrast quantity is lower than 10% or the first update interval reaches 30 days, the information supplement sub-strategy is started to request to record the current three-dimensional model information of the mobile phone, the three-dimensional model information of the driver hand and the first standard quantity again. The result is more accurate when judging and comparing in the follow-up driving process by regularly updating the pre-stored information in time. The mobile phone three-dimensional model information comprises a three-dimensional model of an independent mobile phone and a three-dimensional model when a mobile phone protective sleeve is sleeved on the three-dimensional model. The judgment can make the output result more accurate by adding the three-dimensional model information of the mobile phone protective sleeve.
The correction strategy comprises a first correction strategy, the first correction strategy is used for reminding a driver of paying attention to the current state, and the first correction strategy is used for starting a player to play a prompt tone and opening a music player to play music. The scheme can remind the driver in a prompt tone mode, the music player is turned on to play music to adjust the atmosphere in the vehicle so as to adjust the state of the driver, and the correction strategy can be used for reminding the driver who operates the mobile phone or is in a sleepy state.
The correction strategy comprises a second correction strategy, the second correction strategy comprises a road condition judgment sub-strategy and an inching brake sub-strategy, the road condition judgment sub-strategy is used for detecting a first safety distance, the first safety distance is the distance between the vehicle and the nearest vehicle behind the vehicle in the traveling direction of the vehicle, when the first safety distance meets a preset first safety condition, the inching brake sub-strategy is started, and the inching brake sub-strategy is used for slowing down the vehicle speed through multiple times of braking. The speed of the vehicle can be changed by the method of point braking, meanwhile, the change of the speed of the vehicle can drive the change of the riding posture of a driver to correct the state of the driver, the correction strategy is mainly used for waking up the driver in a sleeping state, and the correction strategy has a higher execution calling level when executing the correction strategy due to the fact that the change of the speed of the vehicle possibly affects other vehicles and the driving safety of the vehicle in the actual setting, and can be executed only when the regulation meeting the first safety distance is set.
As shown in fig. 6, the correction strategy includes a third correction strategy, an air outlet adjusting assembly and a waking unit, the third correction strategy is used for adjusting the air outlet direction of the air conditioner to the air inlet of the waking unit, the waking unit is detachably fixed outside the air outlet of the air conditioner, and when the air amount enters the air inlet of the waking unit, the waking unit outputs waking spray. The sobering unit is a container which is internally provided with a substance capable of making people sober, the air outlet of the container can spray sobering spray after air is blown in from the air inlet, and the container can be internally provided with essential oil or clean water and other existing substances capable of making people sober. The waking unit structure can be an existing vehicle-mounted incense or humidifier, the power supply of the humidifier is switched on when the third correction strategy is executed, and the air blown out from the air outlet of the air conditioner sends the moisture to the head of the driver so as to wake the driver. The air outlet angle adjusting assembly comprises an air guide frame and a shielding unit, a selection air channel 51 and an air guide fan 52 are fixed in the air guide frame, the shielding unit comprises a baffle 53 and a driving unit 54, and the driving unit 54 drives the baffle 53 to move so as to realize the opening or closing of the selection air channel 51. The scheme outputs the waking spray by changing the direction of the air outlet of the air conditioner, so that the driver is in the waking state. The output and the closing of the waking spray are realized by controlling the shielding and the opening of the baffle plate 53 on the selection air channel 51. The correction strategy is used for waking the driver in the sleeping state.
The above description is intended to describe in detail the preferred embodiments of the present invention, but the embodiments are not intended to limit the scope of the claims of the present invention, and all equivalent changes and modifications made within the technical spirit of the present invention should fall within the scope of the claims of the present invention.
Claims (10)
1. A safe automatic driving system is characterized by comprising a starting module (1), a state acquisition module (2), an information processing module (3) and an action execution module (4), the starting module (1) is in communication connection with the automatic driving system, the starting module (1) is used for receiving control mode switching information sent by the automatic driving system, the starting module (1) starts the state acquisition module (2) after receiving the control mode switching information, the state acquisition module (2) acquires the current driving state information of the driver, and the driving state information is sent to an information processing module (3), the information processing module (3) compares the acquired driving state information with preset abnormal behavior information and outputs a judgment instruction, the action execution module (4) receives the judgment instruction and controls the execution unit to execute the action correction strategy according to the judgment instruction;
the state acquisition module (2) comprises an image acquisition unit (22), and the image acquisition unit (22) acquires driving image information of a driver;
the information processing module (3) comprises a model configuration library (32), a model training information library (31), a judgment strategy (33) and a result sending module (34), wherein a three-dimensional digital model of a hand-operated mobile phone is stored in the model configuration library (32) in advance, a first standard quantity is stored in the model training information library (31) in advance, the first standard quantity is image information of a driver when the driver is located at a driving position and uses the mobile phone, the judgment strategy (33) comprises a feature identifier strategy (331) and a judgment sub-strategy (332), the feature identifier strategy (331) is used for comparing the driving image information with information, stored in the model configuration library (32) in advance, of the same feature in the three-dimensional digital model of the hand-operated mobile phone and recording the information as a first comparison quantity, and the first comparison quantity is input into a preset acquaintance judgment algorithm to obtain a first similar quantity, when the first similarity is larger than a preset first judgment threshold value, the judgment sub-strategy (332) calls the first comparison quantity, compares the first comparison quantity with the first standard quantity and records that the comparison result is a second similarity, when the second similarity is larger than the preset second standard quantity, the first action result is output as A, and the result sending module (34) sends the first action result to the action execution module (4);
the action execution module (4) comprises a receiving unit and a control unit, and when the receiving unit receives that the first action result is A, the control unit controls the execution unit to execute a correction strategy, wherein the correction strategy is used for correcting the state of the driver.
2. A safety automatic driving system according to claim 1, wherein the status acquisition module (2) comprises a sign acquisition unit (21), the sign acquisition unit (21) acquires the blood pressure and heart rate information of the driver and records the information as a second contrast quantity;
first feature data are stored in the model configuration library (32) in advance, and the first feature data are numerical ranges of heart rate and blood pressure when a driver is in a sleeping state;
the judgment sub-strategy (332) compares the second comparison quantity with the first characterization data and records the result as a second behavior result, and if the second comparison quantity falls into the first characterization data, the second behavior result is output as B;
and when the receiving unit receives the first behavior result A or the second behavior result B, the control unit controls the execution unit to execute a correction strategy, and the correction strategy is used for reminding and correcting the state of the driver.
3. The automatic safety driving system according to claim 1 or 2, wherein the state acquisition module (2) comprises a mobile phone operation acquisition unit (23), the mobile phone operation acquisition unit (23) is configured to acquire mobile phone state information, the mobile phone state information includes whether an operation instruction is input to the mobile phone, when the mobile phone state information indicates that the operation instruction is input, a third behavior result is output as C, and when the action execution module (4) receives that the first behavior result is a and/or the third behavior result is C, the control unit controls the execution unit to execute the correction strategy.
4. The system according to claim 1, wherein the information processing module (3) is configured with an update strategy, the update strategy includes an update determination sub-strategy and an information supplement sub-strategy, the update determination sub-strategy determines whether to trigger an update, the information supplement sub-strategy is used to store new information into the model configuration library (32) and the model training information library (31), the update determination sub-strategy is provided with a first update interval and a first determination strategy (33), the first determination strategy (33) is used to count a ratio of times of a first behavior result a in a first recognition times and record the ratio as a first update contrast quantity, and when the first update contrast quantity or the first update interval reaches a threshold value, the information supplement sub-strategy is started to request to re-enter current three-dimensional model information of the mobile phone, The driver hand three-dimensional model information and a first standard quantity.
5. The system of claim 1, wherein the correction strategy comprises a first correction strategy for alerting the driver to the current status, the first correction strategy being activating a player to play a warning tone and turning on a music player to play music.
6. The system according to claim 5, wherein the correction strategy includes a second correction strategy, the second correction strategy includes a road condition judgment sub-strategy and an inching brake sub-strategy, the road condition judgment sub-strategy is configured to detect a first safe distance, the first safe distance is a distance between the host vehicle and a nearest vehicle behind the host vehicle in a traveling direction of the host vehicle, the inching brake sub-strategy is activated when the first safe distance meets a preset first safe condition, and the inching brake sub-strategy is configured to slow down a vehicle speed by multiple braking.
7. The system of claim 2, wherein the correction strategy comprises a third correction strategy, an air outlet adjusting assembly and a waking unit, the third correction strategy is used for adjusting the air outlet direction of the air conditioner to the air inlet of the waking unit, the waking unit is detachably fixed outside the air outlet of the air conditioner, and when the air amount enters the air inlet of the waking unit, the waking unit outputs waking spray.
8. The system according to claim 7, wherein the air outlet angle adjusting assembly includes an air guiding frame and a shielding unit, the air guiding frame is internally fixed with a selection air duct (51) and an air guiding fan (52), the shielding unit includes a baffle (53) and a driving unit (54), and the driving unit (54) drives the baffle (53) to move so as to open or close the selection air duct (51).
9. A safety autopilot system according to claim 1 wherein the degree of identity determination algorithm is:
wherein Y is a first similar amount; n is the collected characteristic quantity of the screen when the mobile phone is awakened; u is the number of the collected appearance characteristics of the mobile phone; g is the collected characteristic quantity of the hand; k1、K2、K3And E is the average value of the total number of the features in the three-dimensional digital model of the hand-operated mobile phone at a single visual angle.
10. A safety automatic driving system according to claim 4, wherein the three-dimensional model information of the mobile phone comprises a three-dimensional model of the mobile phone alone and a three-dimensional model of the mobile phone when the mobile phone is sleeved with a protective sleeve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011047864.0A CN112208547B (en) | 2020-09-29 | 2020-09-29 | Safe automatic driving system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011047864.0A CN112208547B (en) | 2020-09-29 | 2020-09-29 | Safe automatic driving system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112208547A CN112208547A (en) | 2021-01-12 |
| CN112208547B true CN112208547B (en) | 2021-10-01 |
Family
ID=74051450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011047864.0A Active CN112208547B (en) | 2020-09-29 | 2020-09-29 | Safe automatic driving system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112208547B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112960001A (en) * | 2021-04-19 | 2021-06-15 | 北京七鑫易维信息技术有限公司 | Driving mode switching method and device, vehicle and storage medium |
| CN114426028B (en) * | 2022-03-03 | 2023-12-22 | 一汽解放汽车有限公司 | Intelligent driving control method, intelligent driving control device, computer equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105966405A (en) * | 2015-03-13 | 2016-09-28 | 哈曼国际工业有限公司 | Driver distraction detection system |
| CN109552332A (en) * | 2018-12-06 | 2019-04-02 | 电子科技大学 | A kind of automatic driving mode intelligent switching system based on driver status monitoring |
| CN110301921A (en) * | 2018-03-27 | 2019-10-08 | 香港生产力促进局 | System and method for carrying out drowsiness detection and intervention |
| US10569650B1 (en) * | 2014-05-05 | 2020-02-25 | State Farm Mutual Automobile Insurance Company | System and method to monitor and alert vehicle operator of impairment |
| CN110872992A (en) * | 2018-08-30 | 2020-03-10 | 丰田自动车株式会社 | Control device and control method |
| DE102018219672A1 (en) * | 2018-11-16 | 2020-05-20 | Zf Friedrichshafen Ag | Method and system for detecting a driver's distraction in a vehicle |
| CN111547062A (en) * | 2020-04-28 | 2020-08-18 | 中国第一汽车股份有限公司 | Automatic driving control method and device and vehicle |
| CN111661069A (en) * | 2019-03-07 | 2020-09-15 | 矢崎总业株式会社 | Passenger assistance system |
| CN111661059A (en) * | 2019-03-08 | 2020-09-15 | 虹软科技股份有限公司 | Method and system for monitoring distracted driving and electronic equipment |
-
2020
- 2020-09-29 CN CN202011047864.0A patent/CN112208547B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10569650B1 (en) * | 2014-05-05 | 2020-02-25 | State Farm Mutual Automobile Insurance Company | System and method to monitor and alert vehicle operator of impairment |
| CN105966405A (en) * | 2015-03-13 | 2016-09-28 | 哈曼国际工业有限公司 | Driver distraction detection system |
| CN110301921A (en) * | 2018-03-27 | 2019-10-08 | 香港生产力促进局 | System and method for carrying out drowsiness detection and intervention |
| CN110872992A (en) * | 2018-08-30 | 2020-03-10 | 丰田自动车株式会社 | Control device and control method |
| DE102018219672A1 (en) * | 2018-11-16 | 2020-05-20 | Zf Friedrichshafen Ag | Method and system for detecting a driver's distraction in a vehicle |
| CN109552332A (en) * | 2018-12-06 | 2019-04-02 | 电子科技大学 | A kind of automatic driving mode intelligent switching system based on driver status monitoring |
| CN111661069A (en) * | 2019-03-07 | 2020-09-15 | 矢崎总业株式会社 | Passenger assistance system |
| CN111661059A (en) * | 2019-03-08 | 2020-09-15 | 虹软科技股份有限公司 | Method and system for monitoring distracted driving and electronic equipment |
| CN111547062A (en) * | 2020-04-28 | 2020-08-18 | 中国第一汽车股份有限公司 | Automatic driving control method and device and vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112208547A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112208547B (en) | Safe automatic driving system | |
| US8823792B2 (en) | Wakefulness level estimation apparatus | |
| US7821409B2 (en) | Drowsiness alarm apparatus and program | |
| CN110319545A (en) | Environment management method and device and air conditioner | |
| US9105172B2 (en) | Drowsiness-estimating device and drowsiness-estimating method | |
| CN106335432A (en) | Smart rearview mirror with driving assistant system, control system and processing method | |
| CN110319544A (en) | Environment management method and device and air conditioner | |
| US20190265699A1 (en) | Concentration degree determination device, concentration degree determination method, and program for determining concentration degree | |
| CN105652767A (en) | Adjustment method and adjustment system for intelligent bathroom | |
| JP5668410B2 (en) | Vehicle control system | |
| CN110454918A (en) | A kind of air conditioner intelligent temperature control system and method based on recognition of face | |
| CN109367479A (en) | A kind of fatigue driving monitoring method and device | |
| CN108592324A (en) | Enter the wind flow control methods, air inlet flow-control equipment and airhandling equipment | |
| CN109190600A (en) | A kind of driver's monitoring system of view-based access control model sensor | |
| CN106155621A (en) | The key word voice of recognizable sound source position wakes up system and method and mobile terminal up | |
| CN113685992A (en) | Air conditioner control method and device for preventing quilt kicking | |
| CN107719065A (en) | A kind of dangerous driving prevention and intelligent driving environment adjustment method and system | |
| CN109801475A (en) | Method for detecting fatigue driving, device and computer readable storage medium | |
| WO2023087677A1 (en) | Air conditioner sitting posture auxiliary control method, control device, and air conditioner | |
| KR101326954B1 (en) | Sneeze detecting device for vehicle and drive assistance device | |
| CN109635851A (en) | A kind of smart television human fatigue detection system and method based on face multiple features fusion | |
| CN109606376A (en) | A kind of safe driving Activity recognition system based on vehicle intelligent terminal | |
| CN108302694A (en) | Air conditioner control method and device | |
| CN112971764A (en) | Method and system for detecting waking state and sleeping state of respiratory disease patient | |
| CN112572293A (en) | Vehicle-mounted control system, control method thereof and vehicle |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |