CN114162119A - Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system - Google Patents
Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system Download PDFInfo
- Publication number
- CN114162119A CN114162119A CN202111254715.6A CN202111254715A CN114162119A CN 114162119 A CN114162119 A CN 114162119A CN 202111254715 A CN202111254715 A CN 202111254715A CN 114162119 A CN114162119 A CN 114162119A
- Authority
- CN
- China
- Prior art keywords
- driver
- eyes
- vehicle
- assistance system
- opening
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 230000008859 change Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004313 glare Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000013016 damping Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 210000004709 eyebrow Anatomy 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004438 eyesight Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000638 stimulation Effects 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
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0019—Control system elements or transfer functions
- B60W2050/0028—Mathematical models, e.g. for simulation
Abstract
The invention provides a lateral control method of an advanced driving assistance system of an automobile, which comprises the following steps: the method comprises the steps of matching human face characteristic points, calculating the opening and closing degree of eyes, identifying the driving capability, establishing a vehicle dynamic model, establishing an operation model and providing auxiliary torque. The invention can detect the dazzling of the driver when driving at night and identify the driving ability through the fuzzy logic algorithm, thereby solving the problems of dazzling detection of the driver and the analysis and evaluation of the corresponding driving ability. According to the invention, through the established vehicle dynamics model, the driver control model and the advanced driving assistance system model, the assistance torque can be effectively provided for the driver in the dazzling state of the driver, the driver is helped to carry out transverse control, lane keeping is effectively carried out, and the driving safety is ensured to the maximum extent.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a transverse control method, equipment, a medium and a product of an advanced driving auxiliary system of an automobile.
Background
When the automobile runs at night, the long-time strong light irradiation of the automobile lamps on the road easily causes visual fatigue and dazzling of a driver, so that traffic accidents are easily caused, and the life safety of the driver is seriously threatened. Especially, with the development of automobile lamp technology, the lighting effect is enhanced, the lighting visual field area is enlarged, strong light irradiation is generated to the far-reaching headlamp of the oncoming automobile during meeting, and strong stimulation, even dizziness and short blindness are generated to the eyes of a driver. In the case where the driver of the bicycle is not open to the eyes, it is very easy to lose the normal steering ability of the steering wheel. In such night driving scenes, not only is a danger caused to the normal driving of the vehicle, but also the life safety of other traffic participants is threatened.
The Driver Monitoring System (DMS) can detect the mental state of the Driver, acquire a state signal of the Driver through various sensors when the Driver is fatigued or distracted, and perform early warning in time when dangerous behaviors are detected, so as to improve the active safety of the driving of the vehicle. Currently, the detection of the facial features of a driver by using a camera micro-sensor and a vision algorithm becomes a hot spot of related research. Eyes are one of important features in a human face detection process based on a visual algorithm, and under the strong light irradiation of automobile headlamps in the night driving process, the eyes can generate unconditional reflection, so that the opening degree is reduced. Therefore, the degree of opening of the eyes can be detected and calculated by a vision algorithm to recognize and judge the glare condition and the driving ability of the driver.
At present, an Advanced Driving Assistance System (ADAS) is widely applied, so that an automobile with Advanced Driving Assistance System capability can provide steering Assistance for a driver in time, and effectively provide an Assistance torque for steering in a Driving process. Therefore, under the condition that the driver is detected to be dazzled, the advanced driving assistance system provides assistance torque in time, so that the automobile can keep a lane, which is necessary for guaranteeing the safety of the driver.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a transverse control method of an advanced driving assistance system of an automobile, and the advanced driving assistance system provides an assistance torque in time under the condition that the driver is detected to be dazzled, so that the automobile can keep lanes and the safety of the driver is guaranteed.
The invention provides a lateral control method of an advanced driving assistance system of an automobile, which comprises the following steps:
matching the human face characteristic points, detecting the human face characteristics of the driver by a visual sensor through a human face matching algorithm, and marking key characteristic points of the whole face;
calculating the opening and closing degree of eyes, extracting key feature points of the eyes from the key feature points of the whole face, marking the eyes by the key feature points of the eyes, and calculating the opening and closing degree of the eyes and the change rate of the opening and closing degree of the eyes along with time;
identifying the driving ability, and identifying the driving ability of the driver under the dazzling condition through the opening and closing degree of the eyes and the change rate of the opening and closing degree of the eyes along with the time;
establishing a vehicle dynamic model, and establishing the vehicle dynamic model by taking the transverse control accuracy and the transverse control stability of the vehicle as control targets;
establishing a control model, determining an equation of the operation torque of a driver according to the vehicle dynamics model, and obtaining a state space model controlled by the driver of the advanced driving assistance system through the equation of the operation torque;
and providing an auxiliary torque, designing a PID controller, determining parameters, and providing the auxiliary torque through the PID controller to provide corresponding assistance for a driver.
Further, in the step of matching the face feature points, a camera is used as a visual sensor, the face feature of the driver is detected based on a face matching algorithm of a deep learning method, and the key feature points of the whole face include eye key feature points, eyebrow key feature points, nose key feature points, mouth key feature points and outer contour key feature points of the face of the driver.
Further, in the step of calculating the opening and closing degree of the eyes, the eyes are marked by using the circumscribed rectangle of each key feature point of the eyes, and the formula for calculating the opening and closing degree of the eyes is as follows:
wherein, OeyeDegree of opening or closing of eyes, HeyeFor detecting the pixel height of the circumscribed rectangle of the current frame, HmaxThe average value H of the heights of n frames which are sequentially ranked according to the maximum pixel height values of the rectangles circumscribed to the eyes in all the frames within the first second of the driver is detected for the vehicle to start runningiThe n frames with the largest pixel height value of the circumscribed rectangle are sequentially arranged from large to small, and i is 1,2, 3, …, n;
the formula for calculating the rate of change of the degree of opening and closing of the eye with time is:
wherein, OcIs the rate of change of the degree of opening and closing of the eye with time,. DELTA.OeyeThe average value of the opening and closing degrees of eyes of all frames is detected within 1 second, and the delta t takes 1 second.
Further, in the driving ability identifying step, the driving ability of the driver in the dazzling state is identified and calculated through a fuzzy logic algorithm, the opening and closing degree of the eyes is used as a first input of the fuzzy logic algorithm, a fuzzy subset is { minimum, small, medium, large and maximum }, the change rate of the opening and closing degree of the eyes along with time is used as a second input of the fuzzy logic algorithm, the fuzzy subset is { negative large, negative small, zero, positive small and positive large }, the output of the fuzzy logic algorithm is the driving ability of the driver in the dazzling state, the fuzzy subset is { extremely low, common, high and high }, and the output result of the driving ability of the driver in the dazzling state identified by the fuzzy logic algorithm is the value of the DA in the subsequent step.
Further, in the step of establishing a vehicle dynamics model, the vehicle dynamics model under the common action of the steering torque of the driver and the assist torque of the advanced driving assist system is established, and the state space of the vehicle dynamics model is as follows:
x(t)Tis [ v ]yrψLyLδ],vyIs the lateral velocity of the vehicle, r is the yaw rate of the vehicle; psiLIs the course angle error, yLFor lateral displacement, delta is the steering wheel angle,is the steering wheel angular velocity; in the state space:
Cf、Crfor the cornering stiffness of the front and rear wheels of the vehicle,/f、lrThe distance from the center of mass to the front axle and the rear axle of the vehicle, m is the mass of the whole vehicle, vxAs transverse velocity, IzThe moment of inertia of the vehicle about a z-axis perpendicular to the ground;
lsis the distance, eta, from the center of mass of the vehicle to the point of preview ahead of the vehicletLength of contact of the tire with the ground, IsMoment of inertia of steering wheel, RsTo the steering gear ratio, BsDamping the steering system;
B=[0 0 0 0 0 1/(ISRS)]T (12)
Bw=[1/m lw/I z 0 0 0 0]T (13)。
further, in the step of establishing the control model, the operation torque of the driver is as follows:
Md=Gc+Ga (14)
wherein:
Ga=Kd2(θ1vy+θ2r+θ3δRs) (16)
Tptime to near preview point at longitudinal velocity, τaTo anticipate the time of arrival at the far preview point, Kd1And Kd2A gain factor;
Md=Md1vy+Md2r+Kd1ψL+Md3yL+Md4δ (20)
substituting the calculated formula (20), formula (21), formula (22), formula (23) and formula (24) into formula (4) to obtain the state space of the advanced driving assistance system as follows:
wherein:
further, in the step of providing the auxiliary torque, u is used as a control input, and the transverse error e is used as a control inputyLFor the control target, obtaining a PID controller according to a formula (30), and testing and debugging to determine Kp、KiAnd Kd,
Calculating the moment M of the lateral control of the advanced driving assistance system by the formula (31)c:
Ma=μ(θd)u (31)
Where u is the control input, μ (θ)d) Weight coefficient, mu (theta), for providing driving assistance in dependence on the driver's glare statusd) Minimum is equal to muminThe value is 0.2, the maximum value is 1, and the calculation is obtained by the formula (32):
μ(θd)=ω1(θd-ω2)2+μmin (32)
where the required parameter omega is calculated1Value of 3.2, omega2The value is 0.5, sigma1Has a value of 2, sigma2And σ3The value of (A) is 3, the value of DA is the driving ability output result of the driver in the dazzling state identified by the fuzzy logic algorithm, MdmaxMaximum torque for the driver; the advanced driving assistance system model is obtained according to the formula (25) and the formula (31) as follows:
wherein, Bu T=[0 0 0 0 0 λμ(θd)]And the advanced driving assistance system obtained through calculation provides assistance torque to provide corresponding assistance for a driver, and the advanced driving assistance system jointly perform transverse control to realize lane keeping and driving safety.
An electronic device, comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for executing an automotive advanced driving assistance system lateral control method.
A computer-readable storage medium having stored thereon a computer program for executing by a processor a lateral control method for an advanced driving assistance system of a vehicle.
A computer program product comprising a computer program/instructions which, when executed by a processor, implements an automotive advanced driving assistance system lateral control method.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a transverse control method of an advanced driving auxiliary system of an automobile, which can detect the dazzling of a driver during driving at night and identify the driving ability through a fuzzy logic algorithm, thereby solving the problems of dazzling detection of the driver and the analysis and evaluation of the corresponding driving ability. According to the invention, through the established vehicle dynamics model, the driver control model and the advanced driving assistance system model, the assistance torque can be effectively provided for the driver in the dazzling state of the driver, the driver is helped to carry out transverse control, lane keeping is effectively carried out, and the driving safety is ensured to the maximum extent.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings. The detailed description of the present invention is given in detail by the following examples and the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a lateral control method of an advanced driving assistance system of an automobile according to the present invention;
FIG. 2 is a graph of the degree of openness O of the first input eye of the fuzzy logic algorithm of the present inventioneyeA membership function graph;
fig. 3 is a graph of the rate of change over time, O, of the second input eye opening and closing degree of the fuzzy logic algorithm of the present invention.eyeA membership function graph;
FIG. 4 is a graph of the membership function DA for the ability to drive in glare as the output of the fuzzy logic algorithm of the present invention;
FIG. 5 is a diagram of an inference surface of the fuzzy logic algorithm of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
The lateral control method of the advanced driving assistance system of the automobile, as shown in fig. 1, comprises the following steps:
and matching the human face characteristic points, detecting the human face characteristics of the driver by a visual sensor through a human face matching algorithm, and marking the key characteristic points of the whole face. In this embodiment, a camera is used as a visual sensor, a face matching algorithm based on a deep learning method is used to detect the face features of a driver, and 68 key feature points of the whole face are marked. The 68 key feature points of the whole face are respectively: eyes are represented by 12 key feature points, eyebrows are represented by 10 key feature points, the nose is represented by 9 key feature points, the mouth is depicted by 20 key feature points, and the outer contour of the face of the driver is represented by 17 key feature points to represent the shape of the whole face.
Calculating the degree of opening and closing of eyes, extracting eye key feature points from the key feature points of the whole face after detecting 68 key feature points of the whole face, wherein 6 eye key feature points are provided, marking the eyes through the eye key feature points, and calculating the degree of opening and closing of the eyes and the change rate of the degree of opening and closing of the eyes along with time. Specifically, the eye is marked by the circumscribed rectangle of each key feature point of the eye, and the formula for calculating the opening and closing degree of the eye is as follows:
wherein, OeyeDegree of opening or closing of eyes, HeyeFor detecting the pixel height of the circumscribed rectangle of the current frame, HmaxDetecting the average value of the heights of n frames (such as 10 frames) in which the pixel height values of the circumscribed rectangle of the eyes in all the frames within the first second of the driver are arranged in sequence to the maximum for the vehicle to start running, HiThe n frames with the largest pixel height value of the circumscribed rectangle are sequentially arranged from large to small, and i is 1,2, 3, …, n;
the formula for calculating the rate of change of the degree of opening and closing of the eye with time is:
wherein, OcIs the rate of change of the degree of opening and closing of the eye with time,. DELTA.OeyeIs detected within 1 secondThe average value of the opening and closing degrees of the eyes with frames, and delta t takes 1 second.
And identifying the driving ability of the driver under the dazzling condition through the degree of opening and closing of the eyes and the change rate of the degree of opening and closing of the eyes with time. As shown in fig. 2 to 5, the driving ability of the driver under dazzling is identified and calculated through a fuzzy logic algorithm, the opening and closing degree of the eyes is used as a first input of the fuzzy logic algorithm, the fuzzy subsets are { minimum, small, medium, large and maximum }, the change rate of the opening and closing degree of the eyes along with time is used as a second input of the fuzzy logic algorithm, the fuzzy subsets are { negative large, negative small, zero, positive small and positive large }, the output of the fuzzy logic algorithm is the driving ability of the identified driver under dazzling, the fuzzy subsets are { minimum, low, general, high and high }, and an inference rule of the fuzzy logic is formulated, as shown in table 1. And the driving capacity output result of the driver in the dazzling state identified by the fuzzy logic algorithm is the value of DA in the subsequent step.
TABLE 1 inference rules for fuzzy logic
And establishing a vehicle dynamic model by taking the transverse control accuracy and stability of the vehicle as control targets. Establishing a vehicle dynamic model under the common action of the steering torque of a driver and the auxiliary torque of an advanced driving auxiliary system, wherein the state space of the vehicle dynamic model is as follows:
vyis the lateral velocity of the vehicle, r is the yaw rate of the vehicle; psiLIs the course angle error, yLFor lateral displacement, delta is the steering wheel angle,is the steering wheel angular velocity; in the state space:
Cf、Crfor the cornering stiffness of the front and rear wheels of the vehicle,/f、lrThe distance from the center of mass to the front axle and the rear axle of the vehicle, m is the mass of the whole vehicle, vxAs transverse velocity, IzThe moment of inertia of the vehicle about a z-axis perpendicular to the ground;
lsis the distance, eta, from the center of mass of the vehicle to the point of preview ahead of the vehicletLength of contact of the tire with the ground, IsMoment of inertia of steering wheel, RsTo the steering gear ratio, BsDamping the steering system;
B=[0 0 0 0 0 1/(ISRS)]T (12)
Bw=[1/m lw/Iz 0 0 0 0]T (13)。
and establishing a control model, determining the relation among various parameters such as a preview point, a preview angle, speed and the like according to the vehicle dynamics model, and determining an equation of the operation moment of the driver. And substituting the equation of the operation moment of the driver into the state space of the transverse control of the vehicle to obtain a state space model controlled by the driver of the advanced driving assistance system. The operating torque of the driver is:
Md=Gc+Ga (14)
wherein:
Ga=Kd2(θ1vy+θ2r+θ3δRs) (16)
Tptime to near preview point at longitudinal velocity, τaTo anticipate the time of arrival at the far preview point, Kd1And Kd2A gain factor;
Md=Md1vy+Md2r+Kd1ψL+Md3yL+Md4δ (20)
substituting the calculated formula (20), formula (21), formula (22), formula (23) and formula (24) into formula (4) to obtain the state space of the advanced driving assistance system as follows:
wherein:
providing an auxiliary torque, designing a PID controller and determining parameters. Determining the control input and control target of PID controller, and testing and debugging to determine Kp、KiAnd KdThe parameter values. Determining driving ability in glare conditionProportional to the required advanced driving assistance system assistance torque. And finally, providing an auxiliary torque through a PID controller to provide corresponding assistance for a driver, so as to realize stable lane keeping.
Specifically, with u as the control input, the lateral error eyLFor the control target, obtaining a PID controller according to a formula (30), and testing and debugging to determine Kp、KiAnd Kd,
Calculating the moment M of the lateral control of the advanced driving assistance system by the formula (31)c:
Ma=μ(θd)u (31)
Where u is the control input, μ (θ)d) Weight coefficient, mu (theta), for providing driving assistance in dependence on the driver's glare statusd) Minimum is equal to muminThe value is 0.2, the maximum value is 1, and the calculation is obtained by the formula (32):
μ(θd)=ω1(θd-ω2)2+μmin (32)
where the required parameter omega is calculated1Value of 3.2, omega2The value is 0.5, sigma1Has a value of 2, sigma2And σ3The value of (A) is 3, the value of DA is the driving ability output result of the driver in the dazzling state identified by the fuzzy logic algorithm, MdmaxMaximum torque for the driver; the advanced driving assistance system model is obtained according to the formula (25) and the formula (31) as follows:
wherein, Bu T=[0 0 0 0 0 λμ(θd)]And the advanced driving assistance system obtained through calculation provides assistance torque to provide corresponding assistance for a driver, and the advanced driving assistance system jointly perform transverse control to realize lane keeping and driving safety.
The invention provides a transverse control method of an advanced automobile driving assistance system. And calculating by combining a driving capability result deduced in real time by fuzzy logic and combining the established vehicle dynamics model, the driver control model and the advanced driving assistance system model, and providing corresponding assistance torque for the driver so as to realize lane keeping and guarantee the safety of people and vehicles.
An electronic device, comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for executing the automotive advanced driving assistance system lateral control method.
A computer-readable storage medium having stored thereon a computer program for execution by a processor of a lateral control method for an advanced driving assistance system of a vehicle.
A computer program product comprising a computer program/instructions which, when executed by a processor, implements an automotive advanced driving assistance system lateral control method.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner; those skilled in the art can readily practice the invention as shown and described in the drawings and detailed description herein; however, those skilled in the art should appreciate that they can readily use the disclosed conception and specific embodiments as a basis for designing or modifying other structures for carrying out the same purposes of the present invention without departing from the scope of the invention as defined by the appended claims; meanwhile, any changes, modifications, and evolutions of the equivalent changes of the above embodiments according to the actual techniques of the present invention are still within the protection scope of the technical solution of the present invention.
Claims (10)
1. The lateral control method of the advanced driving assistance system of the automobile is characterized by comprising the following steps:
matching the human face characteristic points, detecting the human face characteristics of the driver by a visual sensor through a human face matching algorithm, and marking key characteristic points of the whole face;
calculating the opening and closing degree of eyes, extracting key feature points of the eyes from the key feature points of the whole face, marking the eyes by the key feature points of the eyes, and calculating the opening and closing degree of the eyes and the change rate of the opening and closing degree of the eyes along with time;
identifying the driving ability, and identifying the driving ability of the driver under the dazzling condition through the opening and closing degree of the eyes and the change rate of the opening and closing degree of the eyes along with the time;
establishing a vehicle dynamic model, and establishing the vehicle dynamic model by taking the transverse control accuracy and the transverse control stability of the vehicle as control targets;
establishing a control model, determining an equation of the operation torque of a driver according to the vehicle dynamics model, and obtaining a state space model controlled by the driver of the advanced driving assistance system through the equation of the operation torque;
and providing an auxiliary torque, designing a PID controller, determining parameters, and providing the auxiliary torque through the PID controller to provide corresponding assistance for a driver.
2. A lateral control method of an advanced driving assistance system for automobiles according to claim 1, characterized in that: in the step of matching the face characteristic points, a camera is used as a visual sensor, the face characteristic of the driver is detected by a face matching algorithm based on a deep learning method, and the key characteristic points of the whole face comprise eye key characteristic points, eyebrow key characteristic points, nose key characteristic points, mouth key characteristic points and driver face outline key characteristic points.
3. A lateral control method of an advanced driving assistance system for automobiles according to claim 1, characterized in that: in the step of calculating the opening and closing degree of the eyes, the eyes are marked by the circumscribed rectangle of each key feature point of the eyes, and the formula for calculating the opening and closing degree of the eyes is as follows:
wherein, OeyeDegree of opening or closing of eyes, HeyeFor detecting the pixel height of the circumscribed rectangle of the current frame, HmaxThe average value H of the heights of n frames which are sequentially ranked according to the maximum pixel height values of the rectangles circumscribed to the eyes in all the frames within the first second of the driver is detected for the vehicle to start runningiThe n frames with the largest pixel height value of the circumscribed rectangle are sequentially arranged from large to small, and i is 1,2, 3, …, n;
the formula for calculating the rate of change of the degree of opening and closing of the eye with time is:
wherein, OcIs the rate of change of the degree of opening and closing of the eye with time,. DELTA.OeyeThe average value of the opening and closing degrees of eyes of all frames is detected within 1 second, and the delta t takes 1 second.
4. A lateral control method of an advanced driving assistance system for automobiles according to claim 1, characterized in that: in the driving capacity identifying step, the driving capacity of the driver in the dazzling state is identified and calculated through a fuzzy logic algorithm, the opening and closing degree of the eyes is used as a first input of the fuzzy logic algorithm, a fuzzy subset is { minimum, small, medium, large and maximum }, the change rate of the opening and closing degree of the eyes along with time is used as a second input of the fuzzy logic algorithm, the fuzzy subset is { negative large, negative small, zero, positive small and positive large }, the output of the fuzzy logic algorithm is the driving capacity of the driver in the dazzling state, the fuzzy subset is { minimum, low, common, higher and high }, and the driving capacity output result of the driver in the dazzling state identified by the fuzzy logic algorithm is the value of DA in the subsequent step.
5. A lateral control method of an advanced driving assistance system for automobiles according to claim 1, characterized in that: in the step of establishing the vehicle dynamics model, the vehicle dynamics model under the common action of the steering moment of the driver and the auxiliary moment of the advanced driving auxiliary system is established, and the state space of the vehicle dynamics model is as follows:
x(t)Tis composed ofvyIs the lateral velocity of the vehicle, r is the yaw rate of the vehicle; psiLIs the course angle error, yLFor lateral displacement, delta is the steering wheel angle,is the steering wheel angular velocity; in the state space:
Cf、Crfor the cornering stiffness of the front and rear wheels of the vehicle,/f、lrCentroid to front of vehicleDistance between axle and rear axle, m is vehicle mass, vxAs transverse velocity, IzThe moment of inertia of the vehicle about a z-axis perpendicular to the ground;
lsis the distance, eta, from the center of mass of the vehicle to the point of preview ahead of the vehicletLength of contact of the tire with the ground, IsMoment of inertia of steering wheel, RsTo the steering gear ratio, BsDamping the steering system;
B=[0 0 0 0 0 1/(ISRS)]T (12)
Bw=[1/m lw/Iz 0 0 0 0]T (13)。
6. the lateral control method of an advanced driving assistance system for automobiles according to claim 5, characterized in that: in the step of establishing the control model, the operation torque of the driver is as follows:
Md=Gc+Ga (14)
wherein:
Ga=Kd2(θ1vy+θ2r+θ3δRs) (16)
Tptime to near preview point at longitudinal velocity, τaTo anticipate the time of arrival at the far preview point, Kd1And Kd2A gain factor;
Md=Md1vy+Md2r+Kd1ψL+Md3yL+Md4δ (20)
substituting the calculated formula (20), formula (21), formula (22), formula (23) and formula (24) into formula (4) to obtain the state space of the advanced driving assistance system as follows:
wherein:
7. a lateral control method of an advanced driving assistance system for automobiles according to claim 1, characterized in that: in the step of providing the auxiliary torque, u is used as a control input, and the transverse error eyLFor the control target, obtaining a PID controller according to a formula (30), and testing and debugging to determine Kp、KiAnd Kd,
Calculating the moment M of the lateral control of the advanced driving assistance system by the formula (31)c:
Ma=μ(θd)u (31)
Where u is the control input, μ (θ)d) Weight coefficient, mu (theta), for providing driving assistance in dependence on the driver's glare statusd) Minimum is equal to muminThe value is 0.2, the maximum value is 1, and the calculation is obtained by the formula (32):
μ(θd)=ω1(θd-ω2)2+μmin (32)
where the required parameter omega is calculated1Value of 3.2, omega2The value is 0.5, sigma1Has a value of 2, sigma2And σ3The value of (A) is 3, the value of DA is the driving ability output result of the driver in the dazzling state identified by the fuzzy logic algorithm, MdmaxMaximum torque for the driver; the advanced driving assistance system model is obtained according to the formula (25) and the formula (31) as follows:
wherein, Bu T=[0 0 0 0 0 λμ(θd)]And the advanced driving assistance system obtained through calculation provides assistance torque to provide corresponding assistance for a driver, and the advanced driving assistance system jointly perform transverse control to realize lane keeping and driving safety.
8. An electronic device, characterized by comprising: a processor;
a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, the program comprising instructions for carrying out the method according to any one of claims 1-7.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program is executed by a processor for performing the method according to any of claims 1-7.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the method according to any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111254715.6A CN114162119A (en) | 2021-10-27 | 2021-10-27 | Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111254715.6A CN114162119A (en) | 2021-10-27 | 2021-10-27 | Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114162119A true CN114162119A (en) | 2022-03-11 |
Family
ID=80477421
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111254715.6A Pending CN114162119A (en) | 2021-10-27 | 2021-10-27 | Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114162119A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102022207904B3 (en) | 2022-08-01 | 2023-11-30 | Volkswagen Aktiengesellschaft | Operating procedures for a vehicle |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007245911A (en) * | 2006-03-15 | 2007-09-27 | Omron Corp | Monitoring device and method, recording medium and program |
JP2011043961A (en) * | 2009-08-20 | 2011-03-03 | Toyota Motor Corp | Driver monitoring device |
CN103150545A (en) * | 2011-09-02 | 2013-06-12 | 沃尔沃汽车公司 | Method for classification of eye closures |
CN109271875A (en) * | 2018-08-24 | 2019-01-25 | 中国人民解放军火箭军工程大学 | A kind of fatigue detection method based on supercilium and eye key point information |
CN110291478A (en) * | 2016-12-22 | 2019-09-27 | 斯坦福国际研究院 | Driver's monitoring and response system |
US20200065596A1 (en) * | 2019-08-21 | 2020-02-27 | Lg Electronics Inc. | Control method of autonomous vehicle |
CN111626272A (en) * | 2020-07-28 | 2020-09-04 | 长沙超创电子科技有限公司 | Driver fatigue monitoring system based on deep learning |
JP2021086161A (en) * | 2019-11-25 | 2021-06-03 | オムロン株式会社 | Risk estimation device, on-vehicle device, risk estimation method, and risk estimation program |
DE102020102700A1 (en) * | 2020-02-04 | 2021-08-05 | Bayerische Motoren Werke Aktiengesellschaft | Method and control unit for supporting a driver of a vehicle in poor visibility conditions |
-
2021
- 2021-10-27 CN CN202111254715.6A patent/CN114162119A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007245911A (en) * | 2006-03-15 | 2007-09-27 | Omron Corp | Monitoring device and method, recording medium and program |
JP2011043961A (en) * | 2009-08-20 | 2011-03-03 | Toyota Motor Corp | Driver monitoring device |
CN103150545A (en) * | 2011-09-02 | 2013-06-12 | 沃尔沃汽车公司 | Method for classification of eye closures |
CN110291478A (en) * | 2016-12-22 | 2019-09-27 | 斯坦福国际研究院 | Driver's monitoring and response system |
CN109271875A (en) * | 2018-08-24 | 2019-01-25 | 中国人民解放军火箭军工程大学 | A kind of fatigue detection method based on supercilium and eye key point information |
US20200065596A1 (en) * | 2019-08-21 | 2020-02-27 | Lg Electronics Inc. | Control method of autonomous vehicle |
JP2021086161A (en) * | 2019-11-25 | 2021-06-03 | オムロン株式会社 | Risk estimation device, on-vehicle device, risk estimation method, and risk estimation program |
DE102020102700A1 (en) * | 2020-02-04 | 2021-08-05 | Bayerische Motoren Werke Aktiengesellschaft | Method and control unit for supporting a driver of a vehicle in poor visibility conditions |
CN111626272A (en) * | 2020-07-28 | 2020-09-04 | 长沙超创电子科技有限公司 | Driver fatigue monitoring system based on deep learning |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102022207904B3 (en) | 2022-08-01 | 2023-11-30 | Volkswagen Aktiengesellschaft | Operating procedures for a vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108819951B (en) | Man-machine common driving transverse driving right distribution method considering driver driving skill | |
CN106564495B (en) | The intelligent vehicle safety for merging space and kinetic characteristics drives envelope reconstructing method | |
CN111775949B (en) | Personalized driver steering behavior auxiliary method of man-machine co-driving control system | |
US9090285B2 (en) | Method for providing a lanekeeping assistance based on modifying mechanical sources of steering torques | |
CN110001782A (en) | Automatic lane-change method, system and computer readable storage medium | |
CN105857306A (en) | Vehicle autonomous parking path programming method used for multiple parking scenes | |
CN104494600B (en) | A kind of Driver intention recognition method based on SVM algorithm | |
US8670905B2 (en) | Vehicle stability control method and system | |
US20170021812A1 (en) | Vehicle acceleration and deceleration control device | |
CN109760677A (en) | A kind of lane keeps householder method and system | |
CN111332362B (en) | Intelligent steer-by-wire control method integrating individual character of driver | |
CN105882749A (en) | Driver state determination system | |
CN106740873A (en) | One kind rollover early warning system and its method for early warning | |
CN108717268A (en) | Automatic Pilot minimum time maneuver control system and its control method based on optimum control and safe distance | |
CN113291286B (en) | Auxiliary driving system based on curve yaw stability and control method thereof | |
JP6547791B2 (en) | Vehicle driving support device and method thereof | |
CN110356398A (en) | A kind of speed method of adjustment, device, controller and automobile | |
CN110641465A (en) | Lane keeping system and method based on vehicle speed | |
CN109080627A (en) | A kind of lateral force control method when automatic driving vehicle turning driving | |
CN114162119A (en) | Lateral control method, equipment, medium and product of automobile advanced driving auxiliary system | |
CN109677403A (en) | A kind of intelligent vehicle avoidance obstacle method based on differential flat | |
CN108407803A (en) | A kind of automatic parking control algolithm based on driving experience | |
CN116495002A (en) | Vehicle running control method and device, electronic equipment, storage medium and vehicle | |
Jiang et al. | Shared-control for the lateral motion of vehicles | |
JP2020523248A (en) | Method and apparatus for operating a driver assistance system for a motorcycle |
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 |