CN111857340B - Multi-factor fusion man-machine co-driving right allocation method - Google Patents
Multi-factor fusion man-machine co-driving right allocation method Download PDFInfo
- Publication number
- CN111857340B CN111857340B CN202010690235.3A CN202010690235A CN111857340B CN 111857340 B CN111857340 B CN 111857340B CN 202010690235 A CN202010690235 A CN 202010690235A CN 111857340 B CN111857340 B CN 111857340B
- Authority
- CN
- China
- Prior art keywords
- driving
- driver
- vehicle
- muscle
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004927 fusion Effects 0.000 title claims abstract description 9
- 210000003205 muscle Anatomy 0.000 claims abstract description 35
- 230000001149 cognitive effect Effects 0.000 claims abstract description 27
- 238000011084 recovery Methods 0.000 claims abstract description 16
- 238000005381 potential energy Methods 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 11
- 238000002601 radiography Methods 0.000 claims description 6
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000005251 gamma ray Effects 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000010924 continuous production Methods 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
- 210000001503 joint Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Dermatology (AREA)
- Mathematical Analysis (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a multi-factor fusion man-machine co-driving right distribution method, which comprises the following steps: collecting driver related information, vehicle state information and environment information; calculating the cognitive load of a driver, and outputting a driving weight value which corresponds to the current cognitive load and is to be allocated; calculating the recovery degree of the muscle driving capability of the driver, and outputting a driving weight value which corresponds to the muscle driving capability at the current moment and is to be allocated; establishing a driving safety field model, and outputting a driving weight value to be allocated corresponding to a safety field force value of the current automobile; and weighting to obtain the driving weight distribution value at the current moment. The invention considers the cognitive load, the recovery degree of muscle driving ability and the influence of the surrounding environment of the vehicle on the driving right take over when the driver takes over, and finally carries out weighted fusion on the obtained driving right distribution values corresponding to all factors by calculating the driving right values which are corresponding to the three at the current moment and are to be distributed, so as to obtain the final driving right distribution value.
Description
Technical Field
The invention belongs to the technical field of man-machine co-driving, and particularly relates to a multi-factor fusion man-machine co-driving right distribution method.
Background
In recent years, automobile autopilot technology has been rapidly developed, and various enterprises are controversially researching autopilot technology. However, the autopilot technology has many problems in terms of driving safety and driver acceptance of the system, and many surveys show that the safety of most drivers for autopilot is doubtful. It follows that autopilot wants a large-scale application or an excessive phase that takes a long time, i.e. a co-driving phase of manual driving and autopilot cooperation.
Man-machine co-driving refers to the stage where both the driver and the intelligent car control system can control the car under the condition of non-fully automatic driving, which means that the machine and the driver share decision and control rights to the car. In the man-machine co-driving environment, the dynamic driving task is changed from the traditional continuous process into a discrete process of automatic driving and manual driving alternating. In the control right switching process from the driving to the driving, whether the driver can effectively recognize and evaluate the current driving state, take over the vehicle operation and finally avoid the risk is a key for ensuring the driving safety of the man-machine co-driving and reducing the automatic driving accident rate.
At present, the driving right distribution in the process of butt joint pipe has been studied to a certain extent, for example, the driving right transfer method proposed in the Chinese patent application number 201810253686.3 and the patent name "driving right transfer method in alternating man-machine co-driving" can improve the driving safety, reduce the accident occurrence and comprehensively improve the performance of an intelligent traffic system while reducing the burden of a driver; the Chinese patent application number is 201810846175.2, the patent name is a man-machine co-driving transverse driving right distribution method considering the driving skill of a driver, the driving skill of the driver is considered to distribute the driving right, the driving comfort can be improved, the safe driving of a vehicle can be ensured, the man-machine conflict can be reduced, meanwhile, the difference between the expected rotation angle of the driver and the expected rotation angle of a lane departure controller is considered as one of the weight distribution factors, and the driver can feel that the vehicle is driven according to the driving intention of the driver; the Chinese patent application number is 201910126135.5, the patent name is a global man-machine driving control right distribution scheme provided in a vehicle driving control right distribution system in man-machine co-driving, and the driving control right distribution between a human driver and an automatic driving system is realized by comprehensively considering the external environment condition, the vehicle motion state and the comprehensive driver state.
In summary, although there is a certain research on the driving right distribution, in the existing driving right distribution method, the driving right distribution method is not fully considered when designing the driving right distribution method, however, any influence factor is ignored, which causes danger in the driving right switching process. On the other hand, in the existing driving right distribution system, although the problem of driving right distribution is involved and many aspects are considered, a specific driving right distribution method is lacking.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a multi-factor fusion human-machine co-driving right distribution method, so as to solve the problems that the factors considered in the prior human-machine co-driving right distribution method are not comprehensive enough, various driving right distribution methods are too fuzzy to realize, the distribution methods are less, and the like. According to the method, the cognitive load, the recovery degree of muscle driving capability and the influence of the surrounding environment of the vehicle on the driving right take over are considered in the take over process, the driving right distribution values corresponding to all the factors are finally weighted and fused through calculating the driving right values corresponding to the three, the final driving right distribution value is obtained, the driving right distribution is carried out through the distribution method obtained after the multi-factor fusion, and the driving safety of the vehicle when the driver takes over is further ensured.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention discloses a multi-factor fusion man-machine co-driving right distribution method, which comprises the following steps:
(1) Collecting driver related information, vehicle state information and environment information;
(2) According to the information acquired in the step (1), calculating the cognitive load of a driver, and outputting a driving weight which corresponds to the current cognitive load and is to be allocated;
(3) Calculating the recovery degree of the muscle driving capability of the driver according to the information acquired in the step (1), and outputting the driving weight which corresponds to the muscle driving capability at the current moment and is to be allocated;
(4) According to the information acquired in the step (1), a driving safety field model is established, and driving weights to be allocated corresponding to the safety field force values of the current automobile are output;
(5) And (3) weighting according to the driving weight calculated in the steps (1), (2) and (3) to obtain the driving weight distribution value at the current moment.
Further, the driver related information in the step (1) is the concentration degree of the driver and the included angles of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver; the vehicle state information is the actual output torque of a driver, steering wheel rotation angle, steering wheel angular speed and vehicle speed; the environmental information is surrounding vehicle position information, surrounding vehicle speed information, and vehicle position information.
Further, the specific steps of the step (2) are as follows:
(21) Calculating the cognitive load of the driver:
wherein k is cognitive load; e is a natural constant; lambda (lambda) 1 And lambda (lambda) 2 And lambda (lambda) 3 To adjust parameters; τ is a weighting factor; AS is the degree of driver concentration;is a normalized torque parameter; t (T) real For the steering torque actually input by the current driver, T need The steering torque which is required to be input by a driver in the current motion state of the vehicle during normal driving is obtained;
(22) According to the current cognitive load of the driver, calculating a corresponding driving weight which should be allocated:
Q k =Q max -ξ 1 (k-ξ 2 ) 2 (2)
in which Q k A driver driving authority (i.e., driver control authority) determined by the driver's cognitive load; q (Q) max The maximum value of the driving right control authority; zeta type toy 1 And xi 2 Representing 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) And estimating the included angles of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver:
the angle between the upper and lower arms of the left and right arms (clockwise positive) when the driver turns the steering wheel:
wherein, I s Is the length of the upper arm; l (L) x Is the lower arm length; l (L) sx The distance between the upper end point of the upper arm and the lower end point of the lower arm is set; d is half shoulder width; b is the radius of the steering wheel; e is the distance between the steering wheel and the driver; θ cl The included angle between the upper arm and the lower arm of the left arm; θ cr The included angle between the upper arm and the lower arm of the right arm; θ w Is the steering wheel angle;
(33) Estimating the muscle activation degree by adopting a logic recursion method:
in the method, in the process of the invention,is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is the degree of muscle activation;
(34) Calculating the recovery degree of the muscle driving ability of the driver:
wherein m is d The degree of restoration of the muscle driving ability of the driver; alpha real Is the actual degree of activation of the muscle; alpha need Is the degree of muscle activation required for normal operation;
(35) According to the current recovery degree of the muscle driving capability of the driver, calculating the corresponding driving weight to be allocated:
in the method, in the process of the invention,a driver driving weight value determined by the muscle recovery degree of the driver; a and b are tuning parameters, respectively.
Further, the specific steps of the step (4) are as follows:
(41) Modeling a potential energy field of a road stationary object;
(411) Stationary object classification:
stationary objects are classified into two categories, the first category being stationary objects that collide with the vehicle causing significant losses; the second type is an motionless object, cannot collide actually, but has a constraint on the behavior of the driver;
(412) Modeling potential energy fields of a first type of stationary object:
wherein E is R_aj_o Is within (x) a ,y a ) The object at (x) j ,y j ) Potential energy field vector formed at the position, direction and r aj The same; g and k 1 A pending constant greater than zero; m is M a Virtual quality for target a; r is R a Is within (x) a ,y a ) The influence factor of the road is located; r is (r) aj =(x j -x a ,y j -y a ) Is a distance vector;
the virtual mass expression is:
wherein T is a Is of a type, in particular the ratio of the collision losses of that type to the collision losses of the standard type; m is m a Is the actual mass of target a; alpha k 、β k Is a constant to be determined; v a Is the speed of target a;
the road impact factor expression is:
in delta a Is (x) a ,y a ) Visibility of the place; mu (mu) a Is (x) a ,y a ) Road adhesion coefficient at the location; ρ a Is (x) a ,y a ) Road curvature at; τ a Is (x) a ,y a ) Road grade at; gamma ray 1 、γ 2 、γ 3 、γ 4 For undetermined coefficients, gamma 1 ,γ 2 <0;γ 3 ,γ 4 >0;δ * 、μ * 、ρ * 、τ * Is the standard value of the parameter;
(413) Modeling potential energy fields of a second type of stationary object:
wherein E is R_aj_L Is (x) a ,y a ) Field intensity vector of road marking a, direction and r aj The same; LT (LT) a The road marking type is adopted; d is the road width; k (k) 2 A pending constant greater than zero; r is (r) aj =(x j -x a ,y j -y a ) Is a distance vector
(42) Modeling a kinetic energy field:
wherein E is V_bj Is within (x) b ,y b ) The moving object at (x) j ,y j ) The vector of the kinetic energy field formed at the position, the direction and r bj The same; k (k) 1 、k 3 And G is a pending constant greater than zero; r is R b Is within (x) b ,y b ) The influence factor of the road is located; m is M b Virtual quality for target b; r is (r) bj =(x j -x b ,y j -y b ) Is a distance vector; v b A speed of target b; θ b V is b And r bj Is positive (clockwise);
(43) Behavioral field modeling:
E D_cj =E V_cj .DR c (15)
wherein E is D_cj Is within (x) c ,y c ) C vehicle driver at (x) j ,y j ) The direction and the E of the action field vector formed at the position V_cj The same; e (E) V_cj Is within (x) c ,y c ) The moving object at (x) j ,y j ) A kinetic energy field vector formed thereat; DR (digital radiography) c For driver risk associated with c-car driversFactors;
(44) Modeling a driving safety field:
E S_j =E R_j +E V_j +E D_j (16)
wherein E is S_j Is (x) j ,y j ) Driving safety field at the place; e (E) R_j Is (x) j ,y j ) A potential energy field at the location; e (E) V_j Is (x) j ,y j ) A kinetic energy field vector at; e (E) D_j Is (x) j ,y j ) A behavior field vector at;
then the value of the sum is calculated in (x j ,y j ) The safety field force at the position is as follows:
wherein F is j Is within (x) j ,y j ) The safety field force vector, direction and E j The same; e (E) j Is (x) j ,y j ) Is a safety field vector of (2); m is M j Is (x) j ,y j ) Virtual mass of the j vehicle; r is R j Is within (x) j ,y j ) An impact factor of the road at; k (k) 3 A pending coefficient greater than zero; v j Is (x) j ,y j ) Speed of the j vehicle; θ j V is j And E is j Is positive (clockwise); DR (digital radiography) j A 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 to be allocated: the table look-up method is adopted to distribute driving rights according to a certain distribution principle, and table parameters are adjusted according to different actual conditions.
Further, the final driving right calculation method in the step (5) is as follows:
driving weight Q to be allocated at the present moment calculated according to the above steps k 、And Q F Calculating to obtain a driving weight Q which is finally output:
wherein Q is the final driving weight distribution result; w (w) 1 、w 2 And w 3 Is a weighting factor.
The invention has the beneficial effects that:
the distribution method solves the problems of unsound driving right distribution method and fuzzy concept in the process of taking over by the driver in man-machine co-driving;
the distribution method can realize safe and smooth handover of the driving right, and improves the safety and comfort of the taking over process;
the method has strong practicability and is beneficial to the development of the man-machine co-driving technology.
Drawings
FIG. 1 is a schematic block diagram of a driving right assignment 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 right;
FIG. 4 is a graph of the degree of muscle recovery of a driver versus the right of drive;
fig. 5 is a schematic view of a driving safety field.
Detailed Description
The invention will be further described with reference to examples and drawings, to which reference is made, but which are not intended to limit the scope of the invention.
Referring to fig. 1, the method for distributing the multi-factor fused man-machine co-driving right of the invention comprises the following steps:
(1) Collecting driver related information, vehicle state information and environment information;
the driver related information is the concentration degree of the driver and the included angles of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver; the vehicle state information is the actual output torque of a driver, steering wheel rotation angle, steering wheel angular speed and vehicle speed; the environmental information is surrounding vehicle position information, surrounding vehicle speed information, and vehicle position information.
(2) According to the information acquired in the step (1), calculating the cognitive load of a driver, and outputting a driving weight which corresponds to the current cognitive load and is to be allocated; referring to fig. 2, the method is specifically shown as follows:
(21) Calculating the cognitive load of the driver:
wherein k is cognitive load; e is a natural constant; lambda (lambda) 1 And lambda (lambda) 2 And lambda (lambda) 3 To adjust parameters; τ is a weighting factor; AS is the degree of driver concentration;is a normalized torque parameter; t (T) real For the steering torque actually input by the current driver, T need The steering torque which is required to be input by a driver in the current motion state of the vehicle during normal driving is obtained;
(22) Based on the current driver cognitive load, the corresponding driving weight to be assigned is calculated as shown in fig. 3:
Q k =Q max -ξ 1 (k-ξ 2 ) 2 (2)
in which Q k A driving weight value for a driver determined by the cognitive load of the driver; q (Q) max The maximum value of the driving right control authority; zeta type toy 1 And xi 2 Representing an adjustment factor; k is a cognitive load value.
(3) Calculating the recovery degree of the muscle driving capability of the driver according to the information acquired in the step (1), and outputting the driving weight which corresponds to the muscle driving capability at the current moment and is to be allocated; the concrete steps are as follows:
(31) Selecting input variables for logic recursion;
(32) And estimating the included angles of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver:
the angle between the upper and lower arms of the left and right arms (clockwise positive) when the driver turns the steering wheel:
wherein, I s Is the length of the upper arm; l (L) x Is the lower arm length; l (L) sx The distance between the upper end point of the upper arm and the lower end point of the lower arm is set; d is half shoulder width; b is the radius of the steering wheel; e is the distance between the steering wheel and the driver; θ cl The included angle between the upper arm and the lower arm of the left arm; θ cr The included angle between the upper arm and the lower arm of the right arm; θ w Is the steering wheel angle;
(33) Estimating the muscle activation degree by adopting a logic recursion method:
in the method, in the process of the invention,is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is the degree of muscle activation;
(34) Calculating the recovery degree of the muscle driving ability of the driver:
wherein m is d The degree of restoration of the muscle driving ability of the driver; alpha real Is the actual degree of activation of the muscle; alpha need Is the degree of muscle activation required for normal operation;
(35) According to the current recovery degree of the muscle driving capability of the driver, referring to fig. 4, the corresponding driving weight to be allocated is calculated:
in the method, in the process of the invention,a driver driving weight value determined by the muscle recovery degree of the driver; a and b are tuning parameters, respectively.
(4) According to the information acquired in the step (1), a driving safety field model is established, and driving weights to be allocated corresponding to the safety field force values of the current automobile are output;
(41) Modeling a potential energy field of a road stationary object;
(411) Stationary object classification:
stationary objects are classified into two categories, the first category being stationary objects that collide with the vehicle causing significant losses; the second type is an motionless object, cannot collide actually, but has a constraint on the behavior of the driver;
(412) Modeling potential energy fields of a first type of stationary object:
wherein E is R_aj_o Is within (x) a ,y a ) The object at (x) j ,y j ) Potential energy field vector formed at the position, direction and r aj The same; g and k 1 A pending constant greater than zero; m is M a Virtual quality for target a; r is R a Is within (x) a ,y a ) The influence factor of the road is located; r is (r) aj =(x j -x a ,y j -y a ) Is a distance vector;
the virtual mass expression is:
wherein T is a Is of a type, in particular the ratio of the collision losses of that type to the collision losses of the standard type; m is m a Is the actual mass of target a; alpha k 、β k Is a constant to be determined; v a Is the speed of target a;
the road impact factor expression is:
in delta a Is (x) a ,y a ) Visibility of the place; mu (mu) a Is (x) a ,y a ) Road adhesion coefficient at the location; ρ a Is (x) a ,y a ) Road curvature at; τ a Is (x) a ,y a ) Road grade at; gamma ray 1 、γ 2 、γ 3 、γ 4 For undetermined coefficients, gamma 1 ,γ 2 <0;γ 3 ,γ 4 >0;δ * 、μ * 、ρ * 、τ * Is the standard value of the parameter;
(413) Modeling potential energy fields of a second type of stationary object:
wherein E is R_aj_L Is (x) a ,y a ) Field intensity vector of road marking a, direction and r aj The same; LT (LT) a The road marking type is adopted; d is the road width; k (k) 2 A pending constant greater than zero; r is (r) aj =(x j -x a ,y j -y a ) Is a distance vector
(42) Modeling a kinetic energy field:
wherein E is V_bj Is within (x) b ,y b ) The moving object at (x) j ,y j ) The vector of the kinetic energy field formed at the position, the direction and r bj The same; k (k) 1 、k 3 And G is a pending constant greater than zero; r is R b Is within (x) b ,y b ) The influence factor of the road is located; m is M b Virtual quality for target b; r is (r) bj =(x j -x b ,y j -y b ) Is a distance vector; v b A speed of target b; θ b V is b And r bj Is positive (clockwise);
(43) Behavioral field modeling:
E D_cj =E V_cj .DR c (15)
wherein E is D_cj Is within (x) c ,y c ) C vehicle driver at (x) j ,y j ) The direction and the E of the action field vector formed at the position V_cj The same; e (E) V_cj Is within (x) c ,y c ) The moving object at (x) j ,y j ) A kinetic energy field vector formed thereat; DR (digital radiography) c Is a driver risk factor associated with the c-vehicle driver;
(44) Modeling a driving safety field:
referring to fig. 5, the driving safety field may be expressed as:
E S_j =E R_j +E V_j +E D_j (16)
wherein E is S_j Is (x) j ,y j ) Driving safety field at the place; e (E) R_j Is (x) j ,y j ) A potential energy field at the location; e (E) V_j Is (x) j ,y j ) A kinetic energy field vector at; e (E) D_j Is (x) j ,y j ) A behavior field vector at;
then the value of the sum is calculated in (x j ,y j ) The safety field force at the position is as follows:
wherein F is j Is within (x) j ,y j ) The safety field force vector, direction and E j The same; e (E) j Is (x) j ,y j ) Is a safety field vector of (2); m is M j Is (x) j ,y j ) Virtual mass of the j vehicle; r is R j Is within (x) j ,y j ) An impact factor of the road at; k (k) 3 A pending coefficient greater than zero; v j Is (x) j ,y j ) Speed of the j vehicle; θ j V is j And E is j Is positive (clockwise); DR (digital radiography) j A 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 to be allocated: the table look-up method is adopted to distribute driving rights according to a certain distribution principle, and table parameters are adjusted according to different actual conditions.
The allocation principle in the step (45) is as follows:
the allocation principle at normal take over is shown in table 1 below:
TABLE 1
The allocation principle in case of dangerous situation is shown in the following table 2:
TABLE 2
The final driving right calculation method in the step (5) is as follows:
driving weight Q to be allocated at the present moment calculated according to the above steps k 、And Q F Calculating to obtain a driving weight Q which is finally output:
wherein Q is the final driving weight distribution result; w (w) 1 、w 2 And w 3 The weighting factors can be specifically adjusted according to the driving weight distribution values of all the factors in real time.
The present invention has been described in terms of the preferred embodiments thereof, and it should be understood by those skilled in the art that various modifications can be made without departing from the principles of the invention, and such modifications should also be considered as being within the scope of the invention.
Claims (3)
1. A multi-factor fusion man-machine co-driving right distribution method is characterized by comprising the following steps:
(1) Collecting driver related information, vehicle state information and environment information;
(2) According to the information acquired in the step (1), calculating the cognitive load of a driver, and outputting a driving weight which corresponds to the current cognitive load and is to be allocated;
(3) Calculating the recovery degree of the muscle driving capability of the driver according to the information acquired in the step (1), and outputting the driving weight which corresponds to the muscle driving capability at the current moment and is to be allocated;
(4) According to the information acquired in the step (1), a driving safety field model is established, and driving weights to be allocated corresponding to the safety field force values of the current automobile are output;
(5) Weighting according to the driving weight calculated in the steps (1), (2) and (3) to obtain a driving weight distribution value at the current moment;
the driver related information in the step (1) is the concentration degree of the driver and the included angles of the upper arm and the lower arm of the left arm and the right arm in the driving process of the driver; the vehicle state information is the actual output torque of a driver, steering wheel rotation angle, steering wheel angular speed and vehicle speed; the environment information is surrounding vehicle position information, surrounding vehicle speed information and vehicle position information;
the specific steps of the step (2) are as follows:
(21) Calculating the cognitive load of the driver:
wherein k is cognitive load; e is a natural constant; lambda (lambda) 1 And lambda (lambda) 2 And lambda (lambda) 3 To adjust parameters; τ is a weighting factor; AS is the degree of driver concentration;is a normalized torque parameter; t (T) real For the steering torque actually input by the current driver, T need The steering torque which is required to be input by a driver in the current motion state of the vehicle during normal driving is obtained;
(22) According to the current cognitive load of the driver, calculating a corresponding driving weight which should be allocated:
Q k =Q max -ξ 1 (k-ξ 2 ) 2 (2)
in which Q k A driving weight value for a driver determined by the cognitive load of the driver; q (Q) max The maximum value of the driving right control authority; zeta type toy 1 And xi 2 Representing an adjustment factor; k is a cognitive load value;
the specific steps of the step (3) are as follows:
(31) Selecting input variables for logic recursion;
(32) And estimating the included angles 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 and lower arms of the left and right arms when the driver turns the steering wheel:
wherein, I s Is the length of the upper arm; l (L) x Is the lower arm length; l (L) sx The distance between the upper end point of the upper arm and the lower end point of the lower arm is set; d is half shoulder width; b is the radius of the steering wheel; e is the distance between the steering wheel and the driver; θ cl The included angle between the upper arm and the lower arm of the left arm; θ cr The included angle between the upper arm and the lower arm of the right arm; θ w Is the steering wheel angle;
(33) Estimating the muscle activation degree by adopting a logic recursion method:
in the method, in the process of the invention,is an input variable; beta is a regression coefficient; t is a transposed symbol; alpha is muscle activationA degree;
(34) Calculating the recovery degree of the muscle driving ability of the driver:
wherein m is d The degree of restoration of the muscle driving ability of the driver; alpha real Is the actual degree of activation of the muscle; alpha need Is the degree of muscle activation required for normal operation;
(35) According to the current recovery degree of the muscle driving capability of the driver, calculating the corresponding driving weight to be allocated:
in which Q md A driver driving weight value determined by the muscle recovery degree of the driver; a and b are tuning parameters, respectively.
2. The multi-factor fusion method for assigning the man-machine co-driving right according to claim 1, wherein the specific steps of the step (4) are as follows:
(41) Modeling a potential energy field of a road stationary object;
(411) Stationary object classification:
stationary objects are classified into two categories, the first category being stationary objects that collide with the vehicle causing significant losses; the second type is an motionless object, cannot collide actually, but has a constraint on the behavior of the driver;
(412) Modeling potential energy fields of a first type of stationary object:
wherein E is R_aj_o Is within (x) a ,y a ) The object at (x) j ,y j ) Potential energy field vector formed at the position, direction and r aj The same; g and k 1 A pending constant greater than zero; m is M a Virtual quality for target a; r is R a Is within (x) a ,y a ) The influence factor of the road is located; r is (r) aj =(x j -x a ,y j -y a ) Is a distance vector;
the virtual mass expression is:
wherein T is a Is of a type, in particular the ratio of the collision losses of that type to the collision losses of the standard type; m is m a Is the actual mass of target a; alpha k 、β k Is a constant to be determined; v a Is the speed of target a;
the road impact factor expression is:
in delta a Is (x) a ,y a ) Visibility of the place; mu (mu) a Is (x) a ,y a ) Road adhesion coefficient at the location; ρ a Is (x) a ,y a ) Road curvature at; τ a Is (x) a ,y a ) Road grade at; gamma ray 1 、γ 2 、γ 3 、γ 4 For undetermined coefficients, gamma 1 ,γ 2 <0;γ 3 ,γ 4 >0;δ * 、μ * 、ρ * 、τ * Is the standard value of the parameter;
(413) Modeling potential energy fields of a second type of stationary object:
wherein E is R_aj_L Is (x) a ,y a ) Field intensity vector of road marking a, direction and r aj The same; LT (LT) a The road marking type is adopted; d is the road width; k (k) 2 A pending constant greater than zero; r is (r) aj =(x j -x a ,y j -y a ) As a result of the distance vector,
(42) Modeling a kinetic energy field:
wherein E is V_bj Is within (x) b ,y b ) The moving object at (x) j ,y j ) The vector of the kinetic energy field formed at the position, the direction and r bj The same; k (k) 1 、k 3 And G is a pending constant greater than zero; r is R b Is within (x) b ,y b ) The influence factor of the road is located; m is M b Virtual quality for target b; r is (r) bj =(x j -x b ,y j -y b ) Is a distance vector; v b A speed of target b; θ b V is b And r bj Is included in the plane of the first part;
(43) Behavioral field modeling:
E D_cj =EV _cj ·DR c (15)
wherein E is D_cj Is within (x) c ,y c ) C vehicle driver at (x) j ,y j ) The direction and the E of the action field vector formed at the position V_cj The same; e (E) V_cj Is within (x) c ,y c ) The moving object at (x) j ,y j ) A kinetic energy field vector formed thereat; DR (digital radiography) c Is a driver risk factor associated with the c-vehicle driver;
(44) Modeling a driving safety field:
E S_j =E R_j +E V_j +E D_j (16)
wherein E is S_j Is (x) j ,y j ) Driving safety field at the place; e (E) R_j Is (x) j ,y j ) A potential energy field at the location; e (E) V_j Is (x) j ,y j ) A kinetic energy field vector at; e (E) D_j Is (x) j ,y j ) A behavior field vector at;
then the value of the sum is calculated in (x j ,y j ) The safety field force at the position is as follows:
wherein F is j Is within (x) j ,y j ) The safety field force vector, direction and E j The same; e (E) j Is (x) j ,y j ) Is a safety field vector of (2); m is M j Is (x) j ,y j ) Virtual mass of the j vehicle; r is R j Is within (x) j ,y j ) An impact factor of the road at; k (k) 3 A pending coefficient greater than zero; vj is (x) j ,y j ) Speed of the j vehicle; θ j V is j And E is j Is positive (clockwise); DR (digital radiography) j A 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 to be allocated: the table look-up method is adopted to distribute driving rights according to a certain distribution principle, and table parameters are adjusted according to different actual conditions.
3. The multi-factor fusion method for assigning the man-machine co-driving right according to claim 2, wherein the final driving right calculation method in the step (5) is as follows:
driving weight Q to be allocated at the present moment calculated according to the above steps k 、And Q F Calculating to obtain a driving weight Q which is finally output:
wherein Q is the final driving weight distribution result; w (w) 1 、w 2 And w 3 Is a weighting factor.
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 CN111857340A (en) | 2020-10-30 |
CN111857340B true 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) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112644486B (en) * | 2021-01-05 | 2022-04-08 | 南京航空航天大学 | Intelligent vehicle obstacle avoidance trajectory planning method based on 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 |
CN113359688B (en) * | 2021-05-28 | 2022-06-24 | 重庆交通大学 | Man-machine driving-sharing robust control method based on NMS (network management System) characteristics of driver |
CN113341730B (en) * | 2021-06-28 | 2022-08-30 | 上海交通大学 | Vehicle steering control method under remote man-machine cooperation |
Citations (3)
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 |
-
2020
- 2020-07-17 CN CN202010690235.3A patent/CN111857340B/en active Active
Patent Citations (3)
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 |
Also Published As
Publication number | Publication date |
---|---|
CN111857340A (en) | 2020-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111857340B (en) | Multi-factor fusion man-machine co-driving right allocation method | |
CN110969848B (en) | Automatic driving overtaking decision method based on reinforcement learning under opposite double lanes | |
CN106671982B (en) | Driverless electric automobile automatic overtaking system system and method based on multiple agent | |
CN111338340B (en) | Model prediction-based local path planning method for unmanned vehicle | |
CN109855639B (en) | Unmanned driving trajectory planning method based on obstacle prediction and MPC algorithm | |
WO2021073079A1 (en) | Trajectory planning method for highly coupling path and speed of autonomous vehicle | |
CN105741637B (en) | Four-wheel hub motor electric car automated steering control method | |
CN111746539B (en) | Intelligent network-connected automobile strict and safe lane-changing enqueueing control method | |
CN106184207B (en) | Four motorized wheels electric vehicle adaptive cruise control system Torque distribution method | |
CN108454623A (en) | A kind of unmanned electric vehicle Trajectory Tracking Control method of four motorized wheels | |
CN107856737B (en) | A kind of man-machine coordination rotating direction control method based on degree of danger variable weight | |
CN110162046A (en) | Unmanned vehicle path following method based on event trigger type model predictive control | |
CN106800023A (en) | Method, device and vehicle for adaptive cruise control | |
CN111338353A (en) | Intelligent vehicle lane change track planning method under dynamic driving environment | |
CN112068445B (en) | Integrated control method and system for path planning and path tracking of automatic driving vehicle | |
CN111688704A (en) | Man-machine torque cooperative steering control method based on driving state prediction | |
CN109754626B (en) | Unmanned autonomous lane change strategy | |
CN110262229A (en) | Vehicle Adaptive Path method for tracing based on MPC | |
CN113650609B (en) | Flexible transfer method and system for man-machine co-driving control power based on fuzzy rule | |
CN112644486B (en) | Intelligent vehicle obstacle avoidance trajectory planning method based on driving safety field | |
Liu et al. | A multi-objective model predictive control for vehicle adaptive cruise control system based on a new safe distance model | |
Liu et al. | Driver-automation shared steering control for highly automated vehicles | |
CN107832517A (en) | ACC lengthwise movement modeling methods based on relative motion relation | |
CN105644566B (en) | A kind of tracking of the electric automobile auxiliary lane-change track based on car networking | |
CN107272419A (en) | A kind of driver's adaptive direction control method based on improvement PSO |
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 |