CN111857340A - Multi-factor fusion man-machine co-driving right distribution method - Google Patents

Multi-factor fusion man-machine co-driving right distribution method Download PDF

Info

Publication number
CN111857340A
CN111857340A CN202010690235.3A CN202010690235A CN111857340A CN 111857340 A CN111857340 A CN 111857340A CN 202010690235 A CN202010690235 A CN 202010690235A CN 111857340 A CN111857340 A CN 111857340A
Authority
CN
China
Prior art keywords
driving
driver
formula
muscle
calculating
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.)
Granted
Application number
CN202010690235.3A
Other languages
Chinese (zh)
Other versions
CN111857340B (en
Inventor
张自宇
王春燕
刘利锋
赵万忠
秦亚娟
王展
刘晓强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN202010690235.3A priority Critical patent/CN111857340B/en
Publication of CN111857340A publication Critical patent/CN111857340A/en
Application granted granted Critical
Publication of CN111857340B publication Critical patent/CN111857340B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0055—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements
    • G05D1/0061—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots with safety arrangements for transition from automatic pilot to manual pilot and vice versa
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Neurosurgery (AREA)
  • Algebra (AREA)
  • Health & Medical Sciences (AREA)
  • Neurology (AREA)
  • General Health & Medical Sciences (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Computational Mathematics (AREA)
  • Dermatology (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Biomedical Technology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a multi-factor integrated man-machine co-driving right distribution method, which comprises the following steps of: collecting driver related information, vehicle state information and environmental information; calculating the cognitive load of a driver, and outputting a driving weight value which is corresponding to the current cognitive load and is to be distributed; calculating the recovery degree of the muscle driving ability of the driver, and outputting a driving weight value to be distributed corresponding to the muscle driving ability at the current moment; establishing a driving safety field model, and outputting a driving weight value to be distributed corresponding to a safety field force value of the current position of the automobile; and weighting to obtain the driving weight distribution value at the current moment. According to the invention, the influence of the cognitive load, the recovery degree of the muscle driving ability and the surrounding environment of the vehicle on the driving right taking over is considered, and the driving right distribution values corresponding to all the factors are finally weighted and fused by calculating the driving right value which is corresponding to the cognitive load, the recovery degree of the muscle driving ability and the surrounding environment of the vehicle at the current moment to obtain the final driving right distribution value.

Description

Multi-factor fusion man-machine co-driving right distribution method
Technical Field
The invention belongs to the technical field of man-machine co-driving, and particularly relates to a multi-factor integrated man-machine co-driving right distribution method.
Background
In recent years, the automatic driving technology of automobiles is rapidly developed, and various large enterprises are striving to research the automatic driving technology. However, autodrive technology has many problems with driving safety and driver acceptance of the system, and many investigations have shown that the safety of autodrive for most drivers is questionable. Therefore, the automated driving still requires a long transition period, namely a man-machine driving period in which manual driving and automated driving are cooperated.
Man-machine co-driving refers to a stage in which both a driver and an intelligent automobile control system can control an automatically-driven automobile under the condition of incomplete automatic driving, which means that a machine and the driver share the decision and control right on the automobile. Under the environment of man-machine driving, the dynamic driving task is changed into a discrete process of alternating automatic driving and manual driving from a traditional continuous process. In the process of switching the control right from the machine driving to the human driving, whether the driver can effectively recognize and evaluate the current driving state so as to take over the vehicle operation and finally avoid risks is the key to ensure the safety of the machine-machine driving and reduce the automatic driving accident rate.
At present, certain research has been carried out on the driving right distribution in the management process, for example, the driving right transfer method provided in the Chinese invention patent application number of 201810253686.3 and the patent name of 'driving right transfer method in alternating man-machine common driving' can improve the driving safety, reduce the occurrence of accidents and comprehensively improve the performance of an intelligent traffic system while reducing the burden of a driver; the Chinese invention has the patent application number of 201810846175.2, and the patent name of the method for distributing the human-computer co-driving transverse driving right considering the driving skill of the driver, wherein the driving skill of the driver is considered to distribute the driving right, so that the driving comfort can be improved, the safe driving of the vehicle can be ensured, the human-computer conflict can be reduced, and meanwhile, the difference value between the expected turning angle of the driver and the expected turning angle of a lane departure controller is considered as one of the weight distribution factors, so that the driver can feel that the vehicle runs according to the driving intention of the driver; the Chinese patent application No. 201910126135.5, entitled "a vehicle driving control right distribution system in man-machine driving", provides a global man-machine driving control right distribution scheme, and realizes the driving control right distribution between a human driver and an automatic driving system by comprehensively considering the external environment condition, the vehicle motion state and the driver comprehensive state.
In summary, although some research has been conducted on the driving right assignment, in the existing driving right assignment method, consideration is not comprehensive when designing the driving right assignment method, but any influence factor is neglected, which may cause a danger in the driving right switching process. On the other hand, although the conventional driving right distribution system involves a problem of driving right distribution and takes many aspects into consideration, a specific driving right distribution method is lacking.
Disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, an object of the present invention is to provide a multi-factor integrated driving right allocation method for human-machine co-driving, so as to solve the problems that the driving right allocation in the conventional driving right allocation method is not comprehensive enough, and various driving right allocation methods are too fuzzy and difficult to implement and the allocation methods are few. The method provided by the invention considers the cognitive load when the driver takes over, the recovery degree of the muscle driving ability and the influence of the surrounding environment of the vehicle on the driving right taking over in the taking over process, and finally performs weighted fusion on the obtained driving right distribution values corresponding to all factors by calculating the driving weight values which are corresponding to the three at the current moment to obtain the final driving right distribution value, and performs driving right distribution by the distribution method obtained after multi-factor fusion to further ensure the driving safety of the vehicle when the driver takes over.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention discloses a multi-factor integrated man-machine co-driving right distribution method, which comprises the following steps of:
(1) collecting driver related information, vehicle state information and environmental information;
(2) calculating the cognitive load of the driver according to the information collected in the step (1), and outputting a driving weight value which is corresponding to the current cognitive load and is to be distributed;
(3) calculating the recovery degree of the muscle driving ability of the driver according to the information collected in the step (1), and outputting a driving weight value which is to be distributed and corresponds to the muscle driving ability at the current moment;
(4) establishing a driving safety field model according to the information collected in the step (1), and outputting a driving weight value to be distributed corresponding to a safety field force value of the current position of the automobile;
(5) and (4) weighting according to the driving weight values calculated in the steps (1), (2) and (3) to obtain a driving weight distribution value at the current moment.
Further, the driver related information in the step (1) is the attention concentration degree of the driver and the included angle between the upper arm and the lower arm of the left arm and the right arm of the driver in the driving process; the vehicle state information comprises actual output torque of a driver, a steering wheel angle, a steering wheel angular speed and a vehicle speed; the environment information is surrounding vehicle position information, surrounding vehicle speed information and self-vehicle position information.
Further, the specific steps of the step (2) are as follows:
(21) calculating the cognitive load of the driver:
Figure BDA0002589067960000021
wherein k is the cognitive load; e is a natural constant; lambda [ alpha ]1And λ2And λ3To adjust the parameters; τ is a weighting factor; AS is the driver attention concentration;
Figure BDA0002589067960000022
is a normalized torque parameter; t isrealSteering torque, T, actually input for the current driverneedThe steering torque required to be input by a driver in the current motion state of the vehicle during normal driving;
(22) according to the current cognitive load of the driver, calculating the corresponding driving weight value to be distributed:
Qk＝Qmax-ξ1(k-ξ2)2(2)
in the formula, QkA driver driving weight (i.e., driver control authority) determined by the driver cognitive load; qmaxThe maximum value of the driving right control authority is obtained; xi1And xi2Represents an adjustment factor; k is a cognitive load value.
Further, the specific steps of the step (3) are as follows:
(31) selecting input variables for logic recursion;
(32) estimating the included angle of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver:
the included angle between the upper arm and the lower arm of the left arm and the right arm when the driver steers (clockwise is positive):
Figure BDA0002589067960000031
Figure BDA0002589067960000032
Figure BDA0002589067960000033
Figure BDA0002589067960000034
in the formula IsIs as followsThe length of the arm; lxThe lower arm length; lsxThe distance between the upper end point of the upper arm and the lower end point of the lower arm; d is half shoulder width; b is the steering wheel radius; e is the distance between the steering wheel and the driver; theta clIs the included angle of the upper arm and the lower arm of the left arm; thetacrIs the included angle of the upper arm and the lower arm of the right arm; thetawIs a steering wheel corner;
(33) using a logical recursive approach, muscle activation is estimated:
Figure BDA0002589067960000035
in the formula (I), the compound is shown in the specification,
Figure BDA0002589067960000038
is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is the muscle activation degree;
(34) calculating the recovery degree of the muscle driving ability of the driver:
Figure BDA0002589067960000036
in the formula, mdThe recovery degree of the muscle driving ability of the driver; alpha is alpharealIs the actual degree of activation of the muscle; alpha is alphaneedThe degree of muscle activation required for normal operation;
(35) according to the recovery degree of the muscle driving ability of the current driver, calculating the corresponding driving weight value to be distributed:
Figure BDA0002589067960000037
in the formula (I), the compound is shown in the specification,
Figure BDA0002589067960000039
the driving weight of the driver is determined by the muscle recovery degree of the driver; a and b are respectively adjustment parameters.
Further, the specific steps of the step (4) are as follows:
(41) modeling a potential energy field of a road static object;
(411) classifying static objects:
dividing the static objects into two types, wherein the first type is a static object which is collided with a vehicle and causes great loss; the second type is a stationary object, which cannot actually collide, but which has constraints on the behavior of the driver;
(412) modeling a first stationary object potential energy field:
Figure BDA0002589067960000041
in the formula, ER_aj_oIs at (x) a,ya) The object at (x)j,yj) The direction and r of the formed potential energy field vectorajThe same; g and k1A undetermined constant greater than zero; maIs the virtual quality of target a; raIs at (x)a,ya) Influence factors of the road; r isaj＝(xj-xa,yj-ya) Is a distance vector;
the above virtual quality expression is:
Figure BDA0002589067960000042
in the formula, TaIs a type, in particular a ratio of a collision loss of the type to a collision loss of a standard type; m isaIs the actual mass of target a; alpha is alphak、βkIs a undetermined constant; v. ofaIs the speed of target a;
the expression of the road influence factor is as follows:
Figure BDA0002589067960000043
in the formula (I), the compound is shown in the specification,ais (x)a,ya) The visibility of the site; mu.saIs (x)a,ya) Road attachment coefficient of (d); rhoaIs (x)a,ya) The road curvature of (d); tau isaIs (x)a,ya) Road grade of position; gamma ray1、γ2、γ3、γ4Is a undetermined coefficient, gamma1,γ2＜0；γ3,γ4＞0；*、μ*、ρ*、τ*Is a standard value of the parameter;
(413) modeling the potential energy field of the second type of static object:
Figure BDA0002589067960000044
in the formula, ER_aj_LIs (x)a,ya) Field intensity vector, direction and r of road marking aajThe same; LT (LT)aIs a road marking type; d is the road width; k is a radical of2A undetermined constant greater than zero; r isaj＝(xj-xa,yj-ya) As a distance vector
Figure BDA0002589067960000045
(42) Modeling a kinetic energy field:
Figure BDA0002589067960000046
in the formula, EV_bjIs at (x)b,yb) At (x) moving the objectj,yj) The vector of the formed kinetic energy field, the direction and rbjThe same; k is a radical of1、k3And G is a undetermined constant greater than zero; rbIs at (x)b,yb) Influence factors of the road; m bIs the virtual quality of target b; r isbj＝(xj-xb,yj-yb) Is a distance vector; v. ofbIs the speed of target b; thetabIs v isbAnd rbj(iv) angle (clockwise is positive);
(43) modeling a behavior field:
ED_cj＝EV_cj.DRc(15)
in the formula, ED_cjIs at (x)c,yc) C driver at (x)j,yj) The formed action field vector, the direction and EV_cjThe same; eV_cjIs at (x)c,yc) At (x) moving the objectj,yj) The kinetic energy field vector formed; DR (digital radiography)cA driver risk factor associated with the driver of car c;
(44) modeling a driving safety field:
ES_j＝ER_j+EV_j+ED_j(16)
in the formula, ES_jIs (x)j,yj) A driving safety field; eR_jIs (x)j,yj) A potential energy field of (a); eV_jIs (x)j,yj) A kinetic energy field vector of (d); eD_jIs (x)j,yj) A line field vector of (d);
then the above can be derived at (x)j,yj) The safe field force is:
Figure BDA0002589067960000051
in the formula, FjIs at (x)j,yj) The safety field force vector, the direction and E ofjThe same; ejIs (x)j,yj) The security field vector of (2); mjIs (x)j,yj) The virtual mass of the vehicle at j; rjIs at (x)j,yj) Influence factor of the road; k is a radical of3Is a undetermined coefficient greater than zero; v. ofjIs (x)j,yj) The speed of the vehicle at j; thetajIs v isjAnd Ej(iv) angle (clockwise is positive); DR (digital radiography)jA driver risk factor for a j car driver;
(45) according to the current driving safety field force value of the vehicle, calculating the corresponding driving weight value to be distributed: and (3) allocating the driving right by adopting a table look-up method according to a certain allocation principle, and adjusting table parameters according to different actual conditions.
Further, the final driving right calculation method in the step (5) is as follows:
calculating the driving weight Q to be distributed at the current moment according to the stepsk、
Figure BDA0002589067960000052
And QFAnd calculating to obtain a final output driving weight Q:
Figure BDA0002589067960000053
in the formula, Q is a final driving weight value distribution result; w is a1、w2And w3Is a weighting factor.
The invention has the beneficial effects that:
the distribution method solves the problems of incompleteness and fuzzy concept of the driving right distribution method in the process of taking over by the driver in man-machine co-driving;
the allocation method can realize safe and smooth handover of the driving right, and improves the safety and comfort of the takeover process;
the method has strong practicability and is beneficial to promoting the development of the man-machine co-driving technology.
Drawings
FIG. 1 is a schematic block diagram of a driving right distribution method of the present invention;
FIG. 2 is a graph of driver cognitive load;
FIG. 3 is a graph of driver cognitive load versus driving authority;
FIG. 4 is a graph showing the relationship between the recovery degree of the driving ability of the driver's muscles and the driving right;
fig. 5 is a schematic view of a traffic safety station.
Detailed Description
In order to facilitate understanding of those skilled in the art, the present invention will be further described with reference to the following examples and drawings, which are not intended to limit the present invention.
Referring to fig. 1, the multi-factor integrated man-machine co-driving right distribution method of the invention comprises the following steps:
(1) collecting driver related information, vehicle state information and environmental information;
wherein the driver related information is the attention concentration degree of the driver and the included angle between the upper arm and the lower arm of the left arm and the right arm of the driver in the driving process; the vehicle state information comprises actual output torque of a driver, a steering wheel angle, a steering wheel angular speed and a vehicle speed; the environment information is surrounding vehicle position information, surrounding vehicle speed information and self-vehicle position information.
(2) Calculating the cognitive load of the driver according to the information collected in the step (1), and outputting a driving weight value which is corresponding to the current cognitive load and is to be distributed; referring to fig. 2, it is embodied as:
(21) calculating the cognitive load of the driver:
Figure BDA0002589067960000061
wherein k is the cognitive load; e is a natural constant; lambda [ alpha ]1And λ2And λ3To adjust the parameters; τ is a weighting factor; AS is the driver attention concentration;
Figure BDA0002589067960000062
is a normalized torque parameter; t isrealSteering torque, T, actually input for the current driverneedThe steering torque required to be input by a driver in the current motion state of the vehicle during normal driving;
(22) According to the current driver cognitive load, referring to fig. 3, the corresponding driving weight value to be assigned is calculated:
Qk＝Qmax-ξ1(k-ξ2)2(2)
in the formula, QkA driver driving weight determined by the driver cognitive load; qmaxThe maximum value of the driving right control authority is obtained; xi1And xi2Represents an adjustment factor; k is a cognitive load value.
(3) Calculating the recovery degree of the muscle driving ability of the driver according to the information collected in the step (1), and outputting a driving weight value which is to be distributed and corresponds to the muscle driving ability at the current moment; the concrete expression is as follows:
(31) selecting input variables for logic recursion;
(32) estimating the included angle of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver:
the included angle between the upper arm and the lower arm of the left arm and the right arm when the driver steers (clockwise is positive):
Figure BDA0002589067960000071
Figure BDA0002589067960000072
Figure BDA0002589067960000073
Figure BDA0002589067960000074
in the formula IsThe upper arm length; lxThe lower arm length; lsxThe distance between the upper end point of the upper arm and the lower end point of the lower arm; d is half shoulder width; b is the steering wheel radius; e is the distance between the steering wheel and the driver; thetaclIs the included angle of the upper arm and the lower arm of the left arm; thetacrIs the included angle of the upper arm and the lower arm of the right arm; thetawIs a steering wheel corner;
(33) using a logical recursive approach, muscle activation is estimated:
Figure BDA0002589067960000075
in the formula (I), the compound is shown in the specification,
Figure BDA0002589067960000078
is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is the muscle activation degree;
(34) Calculating the recovery degree of the muscle driving ability of the driver:
Figure BDA0002589067960000076
in the formula, mdThe recovery degree of the muscle driving ability of the driver; alpha is alpharealIs the actual degree of activation of the muscle; alpha is alphaneedThe degree of muscle activation required for normal operation;
(35) according to the current recovery degree of the muscle driving ability of the driver, referring to fig. 4, the corresponding driving weight value to be assigned is calculated:
Figure BDA0002589067960000077
in the formula (I), the compound is shown in the specification,
Figure BDA0002589067960000079
the driving weight of the driver is determined by the muscle recovery degree of the driver; a and b are respectively adjustment parameters.
(4) Establishing a driving safety field model according to the information collected in the step (1), and outputting a driving weight value to be distributed corresponding to a safety field force value of the current position of the automobile;
(41) modeling a potential energy field of a road static object;
(411) classifying static objects:
dividing the static objects into two types, wherein the first type is a static object which is collided with a vehicle and causes great loss; the second type is a stationary object, which cannot actually collide, but which has constraints on the behavior of the driver;
(412) modeling a first stationary object potential energy field:
Figure BDA0002589067960000081
in the formula, ER_aj_oIs at (x)a,ya) The object at (x)j,yj) The direction and r of the formed potential energy field vectorajThe same; g and k1A undetermined constant greater than zero; MaIs the virtual quality of target a; raIs at (x)a,ya) Influence factors of the road; r isaj＝(xj-xa,yj-ya) Is a distance vector;
the above virtual quality expression is:
Figure BDA0002589067960000082
in the formula, TaIs a type, in particular a ratio of a collision loss of the type to a collision loss of a standard type; m isaIs the actual mass of target a; alpha is alphak、βkIs a undetermined constant; v. ofaIs the speed of target a;
the expression of the road influence factor is as follows:
Figure BDA0002589067960000083
in the formula (I), the compound is shown in the specification,ais (x)a,ya) The visibility of the site; mu.saIs (x)a,ya) Road attachment coefficient of (d); rhoaIs (x)a,ya) The road curvature of (d); tau isaIs (x)a,ya) Road grade of position; gamma ray1、γ2、γ3、γ4Is a undetermined coefficient, gamma1,γ2＜0；γ3,γ4＞0；*、μ*、ρ*、τ*Is a standard value of the parameter;
(413) modeling the potential energy field of the second type of static object:
Figure BDA0002589067960000084
in the formula, ER_aj_LIs (x)a,ya) Field intensity vector, direction and r of road marking aajThe same; LT (LT)aIs a road marking type; d is the road width; k is a radical of2A undetermined constant greater than zero; r isaj＝(xj-xa,yj-ya) As a distance vector
Figure BDA0002589067960000085
(42) Modeling a kinetic energy field:
Figure BDA0002589067960000086
in the formula, EV_bjIs at (x)b,yb) At (x) moving the objectj,yj) The vector of the formed kinetic energy field, the direction and rbjThe same; k is a radical of1、k3And G is a undetermined constant greater than zero; rbIs at (x)b,yb) Influence factors of the road; mbIs the virtual quality of target b; r isbj＝(xj-xb,yj-yb) Is a distance vector; v. ofbIs the speed of target b; thetabIs v isbAnd rbj(iv) angle (clockwise is positive);
(43) Modeling a behavior field:
ED_cj＝EV_cj.DRc(15)
in the formula, ED_cjIs at (x)c,yc) C driver at (x)j,yj) The formed action field vector, the direction and EV_cjThe same; eV_cjIs at (x)c,yc) At (x) moving the objectj,yj) The kinetic energy field vector formed; DR (digital radiography)cA driver risk factor associated with the driver of car c;
(44) modeling a driving safety field:
referring to fig. 5, the driving safety field can be expressed as:
ES_j＝ER_j+EV_j+ED_j(16)
in the formula, ES_jIs (x)j,yj) A driving safety field; eR_jIs (x)j,yj) A potential energy field of (a); eV_jIs (x)j,yj) OfA kinetic energy field vector; eD_jIs (x)j,yj) A line field vector of (d);
then the above can be derived at (x)j,yj) The safe field force is:
Figure BDA0002589067960000091
in the formula, FjIs at (x)j,yj) The safety field force vector, the direction and E ofjThe same; ejIs (x)j,yj) The security field vector of (2); mjIs (x)j,yj) The virtual mass of the vehicle at j; rjIs at (x)j,yj) Influence factor of the road; k is a radical of3Is a undetermined coefficient greater than zero; v. ofjIs (x)j,yj) The speed of the vehicle at j; thetajIs v isjAnd Ej(iv) angle (clockwise is positive); DR (digital radiography)jA driver risk factor for a j car driver;
(45) according to the current driving safety field force value of the vehicle, calculating the corresponding driving weight value to be distributed: and (3) allocating the driving right by adopting a table look-up method according to a certain allocation principle, and adjusting table parameters according to different actual conditions.
The allocation principle in the step (45) is as follows:
the distribution principle for normal take-over is shown in table 1 below:
TABLE 1
Figure BDA0002589067960000092
Figure BDA0002589067960000101
The allocation principle in case of a dangerous situation is shown in table 2 below:
TABLE 2
Figure BDA0002589067960000102
The final driving right calculation method in the step (5) is as follows:
calculating the driving weight Q to be distributed at the current moment according to the stepsk、
Figure BDA0002589067960000103
And QFAnd calculating to obtain a final output driving weight Q:
Figure BDA0002589067960000104
in the formula, Q is a final driving weight value distribution result; w is a1、w2And w3The weighting factors can be adjusted according to real-time driving weight distribution values of various factors.
While the invention has been described in terms of its preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims (6)

1. A multi-factor fused man-machine co-driving right distribution method is characterized by comprising the following steps:
(1) collecting driver related information, vehicle state information and environmental information;
(2) calculating the cognitive load of the driver according to the information collected in the step (1), and outputting a driving weight value which is corresponding to the current cognitive load and is to be distributed;
(3) Calculating the recovery degree of the muscle driving ability of the driver according to the information collected in the step (1), and outputting a driving weight value which is to be distributed and corresponds to the muscle driving ability at the current moment;
(4) establishing a driving safety field model according to the information collected in the step (1), and outputting a driving weight value to be distributed corresponding to a safety field force value of the current position of the automobile;
(5) and (4) weighting according to the driving weight values calculated in the steps (1), (2) and (3) to obtain a driving weight distribution value at the current moment.
2. The multi-factor fused human-computer co-driving right distribution method according to claim 1, wherein the driver-related information in the step (1) is the concentration degree of the driver and the included angles of the upper and lower arms of the left and right arms in the driving process of the driver; the vehicle state information comprises actual output torque of a driver, a steering wheel angle, a steering wheel angular speed and a vehicle speed; the environment information is surrounding vehicle position information, surrounding vehicle speed information and self-vehicle position information.
3. The multi-factor fused human-computer co-driving right distribution method according to claim 2, wherein the specific steps of the step (2) are as follows:
(21) Calculating the cognitive load of the driver:
Figure FDA0002589067950000011
wherein k is the cognitive load; e is a natural constant; lambda [ alpha ]1And λ2And λ3To adjust the parameters; τ is a weighting factor; AS is the driver attention concentration;
Figure FDA0002589067950000012
is a normalized torque parameter; t isrealSteering torque, T, actually input for the current driverneedThe steering torque required to be input by a driver in the current motion state of the vehicle during normal driving;
(22) according to the current cognitive load of the driver, calculating the corresponding driving weight value to be distributed:
Qk＝Qmax-ξ1(k-ξ2)2(2)
in the formula, QkA driver driving weight determined by the driver cognitive load; qmaxThe maximum value of the driving right control authority is obtained; xi1And xi2Represents an adjustment factor; k is a cognitive load value.
4. The multi-factor fused human-computer co-driving right distribution method according to claim 3, wherein the specific steps of the step (3) are as follows:
(31) selecting input variables for logic recursion;
(32) estimating the included angle of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver:
the included angle of the upper and lower arms of the left and right arms when the driver turns:
Figure FDA0002589067950000021
Figure FDA0002589067950000022
Figure FDA0002589067950000023
Figure FDA0002589067950000024
in the formula IsThe upper arm length; lxThe lower arm length; lsxThe distance between the upper end point of the upper arm and the lower end point of the lower arm; d is half shoulder width; b is the steering wheel radius; e is the distance between the steering wheel and the driver; theta clIs the included angle of the upper arm and the lower arm of the left arm; thetacrIs the included angle of the upper arm and the lower arm of the right arm; thetawIs a steering wheel corner;
(33) using a logical recursive approach, muscle activation is estimated:
Figure FDA0002589067950000025
in the formula (I), the compound is shown in the specification,
Figure FDA0002589067950000026
is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is the muscle activation degree;
(34) calculating the recovery degree of the muscle driving ability of the driver:
Figure FDA0002589067950000027
in the formula, mdThe recovery degree of the muscle driving ability of the driver; alpha is alpharealIs the actual degree of activation of the muscle; alpha is alphaneedThe degree of muscle activation required for normal operation;
(35) according to the recovery degree of the muscle driving ability of the current driver, calculating the corresponding driving weight value to be distributed:
Figure FDA0002589067950000028
in the formula, QmdThe driving weight of the driver is determined by the muscle recovery degree of the driver; a and b are respectively adjustment parameters.
5. The multi-factor fused human-computer co-driving right distribution method according to claim 4, wherein the specific steps of the step (4) are as follows:
(41) modeling a potential energy field of a road static object;
(411) classifying static objects:
dividing the static objects into two types, wherein the first type is a static object which is collided with a vehicle and causes great loss; the second type is a stationary object, which cannot actually collide, but which has constraints on the behavior of the driver;
(412) Modeling a first stationary object potential energy field:
Figure FDA0002589067950000031
in the formula, ER_aj_oIs at (x)a,ya) The object at (x)j,yj) The direction and r of the formed potential energy field vectorajThe same; g and k1A undetermined constant greater than zero; maIs the virtual quality of target a; raIs at (x)a,ya) Influence factors of the road; r isaj＝(xj-xa,yj-ya) Is a distance vector;
the above virtual quality expression is:
Figure FDA0002589067950000032
in the formula, TaIs a type, in particular a ratio of a collision loss of the type to a collision loss of a standard type; m isaIs the actual mass of target a; alpha is alphak、βkIs a undetermined constant; v. ofaIs the speed of target a;
the expression of the road influence factor is as follows:
Figure FDA0002589067950000033
in the formula (I), the compound is shown in the specification,ais (x)a,ya) The visibility of the site; mu.saIs (x)a,ya) Road attachment coefficient of (d); rhoaIs (x)a,ya) The road curvature of (d); tau isaIs (x)a,ya) Road grade of position; gamma ray1、γ2、γ3、γ4Is a undetermined coefficient, gamma1,γ2＜0；γ3,γ4＞0；*、μ*、ρ*、τ*Is a standard value of the parameter;
(413) modeling the potential energy field of the second type of static object:
Figure FDA0002589067950000034
in the formula, ER_aj_LIs (x)a,ya) Field intensity vector, direction and r of road marking aajThe same; LT (LT)aIs a road marking type; d is the road width; k is a radical of2A undetermined constant greater than zero; r isaj＝(xj-xa,yj-ya) Is a vector of the distance between the two objects,
Figure FDA0002589067950000035
(42) modeling a kinetic energy field:
Figure FDA0002589067950000036
in the formula, EV_bjIs at (x)b,yb) At (x) moving the objectj,yj) The vector of the formed kinetic energy field, the direction and rbjThe same; k is a radical of 1、k3And G is a undetermined constant greater than zero; rbIs at (x)b,yb) Influence factors of the road; mbIs the virtual quality of target b; r isbj＝(xj-xb,yj-yb) Is a distance vector; v. ofbIs the speed of target b; thetabIs v isbAnd rbjThe included angle of (A);
(43) modeling a behavior field:
ED_cj＝EV_cj·DRc(15)
in the formula, ED_cjIs at (x)c,yc) C driver at (x)j,yj) The formed action field vector, the direction and EV_cjThe same; eV_cjIs at (x)c,yc) At (x) moving the objectj,yj) The kinetic energy field vector formed; DR (digital radiography)cA driver risk factor associated with the driver of car c;
(44) modeling a driving safety field:
ES_j＝ER_j+EV_j+ED_j(16)
in the formula, ES_jIs (x)j,yj) A driving safety field; eR_jIs (x)j,yj) A potential energy field of (a); eV_jIs (x)j,yj) A kinetic energy field vector of (d); eD_jIs (x)j,yj) A line field vector of (d);
then the above can be derived at (x)j,yj) The safe field force is:
Figure FDA0002589067950000041
in the formula, FjIs at (x)j,yj) The safety field force vector, the direction and E ofjThe same; ejIs (x)j,yj) The security field vector of (2); mjIs (x)j,yj) The virtual mass of the vehicle at j; rjIs at (x)j,yj) Influence factor of the road; k is a radical of3Is a undetermined coefficient greater than zero; v. ofjIs (x)j,yj) The speed of the vehicle at j; thetajIs v isjAnd Ej(iv) angle (clockwise is positive); DR (digital radiography)jA driver risk factor for a j car driver;
(45) according to the current driving safety field force value of the vehicle, calculating the corresponding driving weight value to be distributed: and (3) allocating the driving right by adopting a table look-up method according to a certain allocation principle, and adjusting table parameters according to different actual conditions.
6. The multi-factor fused human-computer co-driving right distribution method according to claim 5, wherein the final driving right calculation method in the step (5) is as follows:
calculating the driving weight Q to be distributed at the current moment according to the stepsk、QmdAnd QFAnd calculating to obtain a final output driving weight Q:
Q＝w1Qk+w2Qmd+w3QF(18)
in the formula, Q is a final driving weight value distribution result; w is a1、w2And w3Is a weighting factor.
CN202010690235.3A 2020-07-17 2020-07-17 Multi-factor fusion man-machine co-driving right allocation method Active CN111857340B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010690235.3A CN111857340B (en) 2020-07-17 2020-07-17 Multi-factor fusion man-machine co-driving right allocation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010690235.3A CN111857340B (en) 2020-07-17 2020-07-17 Multi-factor fusion man-machine co-driving right allocation method

Publications (2)

Publication Number Publication Date
CN111857340A true CN111857340A (en) 2020-10-30
CN111857340B CN111857340B (en) 2024-04-16

Family

ID=72983690

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010690235.3A Active CN111857340B (en) 2020-07-17 2020-07-17 Multi-factor fusion man-machine co-driving right allocation method

Country Status (1)

Country Link
CN (1) CN111857340B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112644486A (en) * 2021-01-05 2021-04-13 南京航空航天大学 Intelligent vehicle obstacle avoidance trajectory planning method based on novel driving safety field
CN112644498A (en) * 2021-01-05 2021-04-13 南京航空航天大学 Intelligent vehicle safety decision-making method based on novel driving safety field
CN113101079A (en) * 2021-05-20 2021-07-13 南京邮电大学 Intelligent wheelchair based on multiple constraint conditions, and dynamic sharing control method and system
CN113341730A (en) * 2021-06-28 2021-09-03 上海交通大学 Vehicle steering control method under remote man-machine cooperation
CN113359688A (en) * 2021-05-28 2021-09-07 重庆交通大学 Man-machine driving-sharing robust control method based on NMS (network management System) characteristics of driver

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104239741A (en) * 2014-09-28 2014-12-24 清华大学 Travelling risk field-based automobile driving safety assistance method
CN108469806A (en) * 2018-03-26 2018-08-31 重庆邮电大学 Alternative expression is man-machine to drive middle driving power transfer method altogether
CN110949407A (en) * 2019-12-25 2020-04-03 清华大学 Dynamic man-machine co-driving right distribution method based on real-time risk response of driver

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104239741A (en) * 2014-09-28 2014-12-24 清华大学 Travelling risk field-based automobile driving safety assistance method
CN108469806A (en) * 2018-03-26 2018-08-31 重庆邮电大学 Alternative expression is man-machine to drive middle driving power transfer method altogether
CN110949407A (en) * 2019-12-25 2020-04-03 清华大学 Dynamic man-machine co-driving right distribution method based on real-time risk response of driver

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112644486A (en) * 2021-01-05 2021-04-13 南京航空航天大学 Intelligent vehicle obstacle avoidance trajectory planning method based on novel driving safety field
CN112644498A (en) * 2021-01-05 2021-04-13 南京航空航天大学 Intelligent vehicle safety decision-making method based on novel driving safety field
CN112644498B (en) * 2021-01-05 2022-04-08 南京航空航天大学 Intelligent vehicle safety decision-making method based on driving safety field
CN113101079A (en) * 2021-05-20 2021-07-13 南京邮电大学 Intelligent wheelchair based on multiple constraint conditions, and dynamic sharing control method and system
CN113359688A (en) * 2021-05-28 2021-09-07 重庆交通大学 Man-machine driving-sharing robust control method based on NMS (network management System) characteristics of driver
CN113341730A (en) * 2021-06-28 2021-09-03 上海交通大学 Vehicle steering control method under remote man-machine cooperation

Also Published As

Publication number Publication date
CN111857340B (en) 2024-04-16

Similar Documents

Publication Publication Date Title
CN111857340A (en) Multi-factor fusion man-machine co-driving right distribution method
CN109765820B (en) A kind of training system for automatic Pilot control strategy
CN111750887B (en) Unmanned vehicle track planning method and system for reducing accident severity
CN106671982B (en) Driverless electric automobile automatic overtaking system system and method based on multiple agent
CN111746539B (en) Intelligent network-connected automobile strict and safe lane-changing enqueueing control method
CN105857306A (en) Vehicle autonomous parking path programming method used for multiple parking scenes
CN104933876B (en) A kind of control method of adaptive smart city intelligent traffic signal
CN107804315A (en) It is a kind of to consider to drive people's car collaboration rotating direction control method that power is distributed in real time
CN108819951A (en) It is a kind of to consider that the man-machine of driver's driving efficiency drives transverse driving power distribution method altogether
CN106218638A (en) Intelligent network-connected automobile cooperative lane change control method
CN107298103A (en) A kind of automatic lane-change hierarchy system of intelligent electric automobile and method
CN105083266B (en) A kind of automobile autocontrol method and automobile is man-machine double drives system
CN105279981A (en) Tidal lane driving direction dynamic control method
CN108682184A (en) A kind of vehicle cut-ins auxiliary control method and system applied to two-way two track
CN111338353A (en) Intelligent vehicle lane change track planning method under dynamic driving environment
CN205381159U (en) Novel energy resource vehicle
CN106843210A (en) One kind is based on bionic automatic driving vehicle progress control method
CN110320916A (en) Consider the autonomous driving vehicle method for planning track and system of occupant's impression
WO2021233602A1 (en) Method and device for the automated driving mode of a vehicle, and vehicle
Guo et al. Multi-objective adaptive cruise control strategy based on variable time headway
EP3007952A1 (en) Method and device for operating a vehicle
CN109774713A (en) A kind of pure electric automobile VCU control method in slope
CN204915669U (en) Car automatic control system
DE102022102501B3 (en) Method, system and computer program product for determining an assessment of the functionality of a component of a motor vehicle
DE102022108677B3 (en) Method, system and computer program product for determining objective parameters for predicting a subjective evaluation of a driver assistance system and/or an automated driver assistance function

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