CN111857340B - Multi-factor fusion man-machine co-driving right allocation method - Google Patents

Abstract

The present invention discloses a multi-factor fusion human-machine co-driving driving rights allocation method, comprising the following steps: collecting driver-related information, vehicle status information and environmental information; calculating the driver's cognitive load, and outputting the driving weight value to be allocated corresponding to the current cognitive load; calculating the degree of recovery of the driver's muscle driving ability, and outputting the driving weight value to be allocated corresponding to the muscle driving ability at the current moment; establishing a driving safety field model, outputting the driving weight value to be allocated corresponding to the safety field force value of the current position of the car; and weighting to obtain the driving right allocation value at the current moment. The present invention takes into account the cognitive load of the driver when taking over, the degree of recovery of the muscle driving ability and the influence of the vehicle's surrounding environment on the takeover of driving rights, and calculates the driving weight value to be allocated at the current moment corresponding to the three, and finally weights and fuses the driving right allocation values corresponding to each factor to obtain the final driving right allocation value.

Description

A multi-factor fusion method for allocating driving rights for human-machine co-driving

Technical Field

The present invention belongs to the technical field of human-machine co-driving, and specifically relates to a method for allocating driving rights for human-machine co-driving integrating multiple factors.

Background technique

In recent years, the technology of autonomous driving has developed rapidly, and major companies are competing to research autonomous driving technology. However, there are still many problems with autonomous driving technology in terms of driving safety and driver acceptance of the system, and many surveys show that most drivers are skeptical about the safety of autonomous driving. It can be seen that large-scale application of autonomous driving still requires a long transition period, that is, the stage of human-machine co-driving in which manual driving and autonomous driving collaborate.

Human-machine co-driving refers to the stage in which both the driver and the intelligent vehicle control system can control the autonomous vehicle under non-fully autonomous driving conditions, which means that the machine and the driver share the decision-making and control rights over the vehicle. In the human-machine co-driving environment, the dynamic driving task is transformed from a traditional continuous process to a discrete process of alternating between autonomous driving and manual driving. Among them, in the process of switching control from machine driving to human driving, whether the driver can effectively recognize and evaluate the current driving state, and then take over the vehicle operation and ultimately avoid risks is the key to ensuring the safety of human-machine co-driving and reducing the accident rate of autonomous driving.

At present, there have been some studies on the allocation of driving rights during the takeover process. For example, the Chinese invention patent application number is 201810253686.3, and the patent name is "A method for transferring driving rights in alternating human-machine co-driving". The driving rights transfer method proposed in the patent can reduce the burden on the driver while improving driving safety, reducing accidents, and comprehensively improving the performance of the intelligent transportation system; the Chinese invention patent application number is 201810846175.2, and the patent name is "A method for allocating lateral driving rights in human-machine co-driving considering the driver's driving skills". The driving rights are allocated by considering the driver's driving skills, which can improve the driving safety. Comfort can ensure the safe driving of the vehicle and reduce human-machine conflicts. At the same time, the difference between the driver's expected turning angle and the lane departure controller's expected turning angle is considered as one of the factors for weight distribution, which can make the driver feel that the vehicle is driving according to his own driving intention; the Chinese invention patent application number is 201910126135.5, and the patent name is "A vehicle driving control rights allocation system in human-machine co-driving", which provides a global human-machine driving control rights allocation scheme, which realizes the driving control rights allocation between the human driver and the automatic driving system by comprehensively considering the external environment conditions, the vehicle's motion state and the driver's comprehensive state.

In summary, although there has been some research on driving rights allocation, the existing driving rights allocation methods do not take comprehensive considerations into account when designing driving rights allocation methods. However, any factor that is ignored will cause danger during the driving rights switching process. On the other hand, in the existing driving rights allocation system, although the driving rights allocation problem is involved and many aspects are considered, there is a lack of specific driving rights allocation methods.

Summary of the invention

In view of the deficiencies of the above-mentioned prior art, the purpose of the present invention is to provide a multi-factor fusion method for allocating driving rights for human-machine co-driving, so as to solve the problems that the factors considered in the existing human-machine co-driving driving rights allocation methods are not comprehensive enough, and the various driving rights allocation methods are too vague to be implemented and there are few allocation methods. The method proposed by the present invention considers the cognitive load of the driver when taking over, the degree of recovery of muscle driving ability, and the influence of the vehicle's surrounding environment on the takeover of driving rights during the takeover process. By calculating the driving weight value that should be allocated at the current moment corresponding to the three, the driving rights allocation values corresponding to each factor are finally weighted and fused to obtain the final driving rights allocation value. The driving rights are allocated by the allocation method obtained after multi-factor fusion, which further ensures the driving safety of the vehicle when the driver takes over.

To achieve the above object, the technical solution adopted by the present invention is as follows:

A multi-factor integrated human-machine co-driving driving rights allocation method of the present invention comprises the following steps:

(1) Collect driver-related information, vehicle status information, and environmental information;

(2) calculating the driver's cognitive load based on the information collected in step (1), and outputting the driving weight value to be allocated corresponding to the current cognitive load;

(3) calculating the degree of recovery of the driver's muscle driving ability based on the information collected in step (1), and outputting the driving weight value to be allocated corresponding to the muscle driving ability at the current moment;

(4) establishing a driving safety field model based on the information collected in step (1), and outputting the driving weight value to be allocated corresponding to the safety field force value at the current position of the vehicle;

(5) According to the driving rights calculated in steps (1), (2), and (3), weighted addition is performed to obtain the driving rights allocation value at the current moment.

Furthermore, the driver-related information in step (1) includes the driver's concentration level and the angle between the upper and lower arms of the driver's left and right arms during driving; the vehicle status information includes the driver's actual output torque, steering wheel angle, steering wheel angular velocity and vehicle speed; and the environmental information includes surrounding vehicle position information, surrounding vehicle speed information and the vehicle's own position information.

Furthermore, the specific steps of step (2) are as follows:

(21) Calculate the driver’s cognitive load:

Where, k is cognitive load; e is a natural constant; λ ₁ , λ ₂ and λ ₃ are adjustment parameters; τ is a weighting factor; AS is the driver's concentration level; is the normalized torque parameter; T _real is the steering torque actually input by the current driver; T _need is the steering torque that the driver needs to input under the current motion state of the vehicle during normal driving;

(22) According to the current cognitive load of the driver, the corresponding driving weight to be allocated is calculated:

Q _k =Q _max -ξ ₁ (k-ξ ₂ ) ² (2)

Where _Qk is the driver's driving right value (i.e., driver control authority) determined by the driver's cognitive load; _Qmax is the maximum value of driving right control authority; _ξ1 and _ξ2 represent adjustment factors; and k is the cognitive load value.

Furthermore, the specific steps of step (3) are as follows:

(31) Selecting input variables for logical recursion;

(32) Estimation of the angle between the upper and lower arms of the driver’s left and right arms during driving:

The angle between the upper and lower arms of the driver's left and right arms when steering (clockwise is positive):

Where, l _s is the length of the upper arm; l _x is the length of the lower arm; l _sx is the distance between the upper end of the upper arm and the lower end of the lower arm; d is the half shoulder width; b is the radius of the steering wheel; e is the distance between the steering wheel and the driver; θ _cl is the angle between the upper and lower arms of the left arm; θ _cr is the angle between the upper and lower arms of the right arm; θ _w is the steering wheel angle;

(33) Using a logical recursive method, muscle activation was estimated:

In the formula, is the input variable; β is the regression coefficient; T is the transposition sign; α is the muscle activation degree;

(34) Calculate the degree of recovery of the driver's muscle driving ability:

Where _md is the degree of recovery of the driver's muscle driving ability; _αreal is the actual muscle activation; _αneed is the muscle activation required for normal operation;

(35) According to the current recovery degree of the driver's muscle driving ability, the corresponding driving weight to be allocated is calculated:

In the formula, is the driver's driving weight determined by the driver's muscle recovery degree; a and b are adjustment parameters.

Furthermore, the specific steps of step (4) are as follows:

(41) Modeling of potential energy field of stationary objects on the road;

(411) Classification of stationary objects:

The stationary objects are divided into two categories: the first category is the immovable objects that can cause significant damage by colliding with the vehicle; the second category is the immovable objects that cannot actually collide with the vehicle but have constraints on the driver's behavior;

(412) Modeling of the potential energy field of the first type of stationary object:

Where, E _{R_aj_o} is the potential energy field vector formed by the object at ( _xa , _ya ) at ( _xj , _yj ), and its direction is the same as that _{of raj} ; G and _k1 are unknown constants greater than zero; _Ma is the virtual mass of target a; _Ra is the influence factor of the road at ( _xa , _ya ); _raj = ( _xj - _xa , _yj - _ya ) is the distance vector;

The above virtual mass expression is:

Wherein, Ta _is the type, specifically the ratio of the collision loss of this type to the collision loss of the standard type; _ma is the actual mass of target a; _αk and _βk are constants to be determined; _va is the velocity of target a;

The above road impact factor expression is:

Wherein, _δa is the visibility at ( _xa , _ya ); _μa is the road adhesion coefficient at ( _xa , _ya ); _ρa is the road curvature at ( _xa , _ya ); _τa is the road slope at ( _xa , _ya ); _γ1 , _γ2 , _γ3 , _γ4 are unknown coefficients, _γ1 , _γ2 <0; _γ3 , _γ4 >0; δ ^* , μ ^* , ρ ^* , τ ^* are the standard values of the parameters;

(413) Modeling of the potential energy field of the second type of stationary object:

Where, _ERajL is the field intensity vector of road marking a at ( _xa , _ya ), with the same direction as _raj ; _LTa is the road marking type; D is the road width; _k2 is a constant greater than zero to be determined; _raj = ( _xj - _xa , _yj - _ya ) is the distance vector

(42) Kinetic energy field modeling:

Wherein, _{EV_bj} is the kinetic energy field vector formed by the moving object at ( _xb , _yb ) at ( _xj , _yj ), and its direction is the same as that of _rbj ; _k1 , _k3 and G are unknown constants greater than zero; _Rb is the influence factor of the road at ( _xb , _yb ); _Mb is the virtual mass of target b; _rbj = ( _xj - _xb , _yj - _yb ) is the distance vector; _vb is the speed of target b; _θb is the angle between _vb and _rbj (clockwise is positive);

(43) Behavioral Field Modeling:

_{ED_cj} = _{EV_cj} .DR _c (15)

Wherein, _{ED_cj} is the behavior field vector formed by the driver of car c at (x _c ,y _c ) at (x _j ,y _j ), and its direction is the same as _{EV_cj} ; _{EV_cj} is the kinetic energy field vector formed by the moving object at (x _c ,y _c ) at (x _j ,y _j ); DR _c is the driver risk factor related to the driver of car c;

(44) Driving safety field modeling:

E _{S_j} = E _{R_j} + E _{V_j} + E _{D_j} (16)

Wherein, _{ES_j} is the driving safety field at (x _j ,y _j ); _{ER_j} is the potential energy field at (x _j ,y _j ); _{EV_j} is the kinetic energy field vector at (x _j ,y _j ); _{ED_j} is the behavior field vector at (x _j ,y _j );

According to the above, the safety field force at (x _j ,y _j ) can be derived as:

Wherein, _Fj is the safety field force vector at ( _xj , _yj ), with the same direction as _Ej ; _Ej is the safety field vector at ( _xj , _yj ); _Mj is the virtual mass of vehicle j at ( _xj , _yj ); _Rj is the influence factor of the road at ( _xj , _yj ); _k3 is an undetermined coefficient greater than zero; _vj is the speed of vehicle j at ( _xj , _yj ); _θj is the angle between _vj and _Ej (clockwise is positive); _DRj is the driver risk factor of the driver of vehicle j;

(45) According to the current driving safety field force value of the vehicle, the corresponding driving right value to be allocated is calculated: the driving right is allocated according to a certain allocation principle using a table lookup method, and the table parameters are adjusted according to different actual conditions.

Furthermore, the final driving right calculation method in step (5) is as follows:

The driving weight Q _k that should be allocated at the current moment calculated according to the above steps, And Q _F calculate the final output driving weight Q:

Where Q is the final driving weight allocation result; w ₁ , w ₂ and w ₃ are weighting factors.

Beneficial effects of the present invention:

The allocation method of the present invention solves the problem of imperfect allocation method and vague concept of driving rights during the driver taking over process in human-machine co-driving;

The allocation method of the present invention can realize safe and smooth handover of driving rights, and improve the safety and comfort of the takeover process;

The method of the present invention has strong practicability and is conducive to promoting the development of human-machine co-driving technology.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a block diagram of the driving rights allocation method of the present invention;

Figure 2 is a graph showing driver cognitive load;

Figure 3 is a diagram showing the relationship between driver cognitive load and driving rights;

FIG4 is a graph showing the relationship between the degree of recovery of the driver's muscle driving ability and driving rights;

Figure 5 is a schematic diagram of a driving safety field.

Detailed ways

In order to facilitate the understanding of those skilled in the art, the present invention is further described below in conjunction with embodiments and drawings. The contents mentioned in the implementation modes are not intended to limit the present invention.

1 , a multi-factor integrated human-machine co-driving driving rights allocation method of the present invention includes the following steps:

(1) Collect driver-related information, vehicle status information, and environmental information;

Among them, the driver-related information includes the driver's concentration level and the angle between the upper and lower arms of the left and right arms during the driving process; the vehicle status information includes the driver's actual output torque, steering wheel angle, steering wheel angular velocity and vehicle speed; the environmental information includes the surrounding vehicle position information, surrounding vehicle speed information and the vehicle's own position information.

(2) Calculating the driver's cognitive load based on the information collected in step (1) and outputting the driving weight value to be allocated corresponding to the current cognitive load; as shown in FIG. 2 , this is specifically performed as follows:

(21) Calculate the driver’s cognitive load:

Where, k is cognitive load; e is a natural constant; λ ₁ , λ ₂ and λ ₃ are adjustment parameters; τ is a weighting factor; AS is the driver's concentration level; is the normalized torque parameter; T _real is the steering torque actually input by the current driver; T _need is the steering torque that the driver needs to input under the current motion state of the vehicle during normal driving;

(22) According to the current driver's cognitive load, as shown in FIG3 , the corresponding driving weight to be allocated is calculated:

Q _k =Q _max -ξ ₁ (k-ξ ₂ ) ² (2)

Where _Qk is the driver's driving right value determined by the driver's cognitive load; _Qmax is the maximum value of driving right control authority; _ξ1 and _ξ2 represent adjustment factors; and k is the cognitive load value.

(3) Calculating the degree of recovery of the driver's muscle driving ability based on the information collected in step (1), and outputting the driving weight value to be allocated corresponding to the muscle driving ability at the current moment; specifically, as follows:

(31) Selecting input variables for logical recursion;

(32) Estimation of the angle between the upper and lower arms of the driver’s left and right arms during driving:

The angle between the upper and lower arms of the driver's left and right arms when steering (clockwise is positive):

Where, l _s is the length of the upper arm; l _x is the length of the lower arm; l _sx is the distance between the upper end of the upper arm and the lower end of the lower arm; d is the half shoulder width; b is the radius of the steering wheel; e is the distance between the steering wheel and the driver; θ _cl is the angle between the upper and lower arms of the left arm; θ _cr is the angle between the upper and lower arms of the right arm; θ _w is the steering wheel angle;

(33) Using a logical recursive method, muscle activation was estimated:

In the formula, is the input variable; β is the regression coefficient; T is the transposition sign; α is the muscle activation degree;

(34) Calculate the degree of recovery of the driver's muscle driving ability:

Where _md is the degree of recovery of the driver's muscle driving ability; _αreal is the actual muscle activation; _αneed is the muscle activation required for normal operation;

(35) According to the current recovery degree of the driver's muscle driving ability, as shown in FIG4 , the corresponding driving weight to be allocated is calculated:

In the formula, is the driver's driving weight determined by the driver's muscle recovery degree; a and b are adjustment parameters.

(4) establishing a driving safety field model based on the information collected in step (1), and outputting the driving weight value to be allocated corresponding to the safety field force value at the current position of the vehicle;

(41) Modeling of potential energy field of stationary objects on the road;

(411) Classification of stationary objects:

The stationary objects are divided into two categories: the first category is the immovable objects that can cause significant damage by colliding with the vehicle; the second category is the immovable objects that cannot actually collide with the vehicle but have constraints on the driver's behavior;

(412) Modeling of the potential energy field of the first type of stationary object:

Wherein, E _{R_aj_o} is the potential energy field vector formed by the object at ( _xa , _ya ) at ( _xj , _yj ), and its direction is the same as that of _raj ; G and _k1 are unknown constants greater than zero; _Ma is the virtual mass of target a; _Ra is the influence factor of the road at ( _xa , _ya ); _raj = ( _xj - _xa , _yj - _ya ) is the distance vector;

The above virtual mass expression is:

Wherein, Ta _is the type, specifically the ratio of the collision loss of this type to the collision loss of the standard type; _ma is the actual mass of target a; _αk and _βk are constants to be determined; _va is the velocity of target a;

The above road impact factor expression is:

Wherein, _δa is the visibility at ( _xa , _ya ); _μa is the road adhesion coefficient at ( _xa , _ya ); _ρa is the road curvature at ( _xa , _ya ); _τa is the road slope at ( _xa , _ya ); _γ1 , _γ2 , _γ3 , _γ4 are unknown coefficients, _γ1 , _γ2 <0; _γ3 , _γ4 >0; δ ^* , μ ^* , ρ ^* , τ ^* are the standard values of the parameters;

(413) Modeling of the potential energy field of the second type of stationary object:

Where, _ERajL is the field intensity vector of road marking a at ( _xa , _ya ), with the same direction as _raj ; _LTa is the road marking type; D is the road width; _k2 is a constant greater than zero to be determined; _raj = ( _xj - _xa , _yj - _ya ) is the distance vector

(42) Kinetic energy field modeling:

Wherein, _{EV_bj} is the kinetic energy field vector formed by the moving object at ( _xb , _yb ) at ( _xj , _yj ), and its direction is the same as that of _rbj ; _k1 , _k3 and G are unknown constants greater than zero; _Rb is the influence factor of the road at ( _xb , _yb ); _Mb is the virtual mass of target b; _rbj = ( _xj - _xb , _yj - _yb ) is the distance vector; _vb is the speed of target b; _θb is the angle between _vb and _rbj (clockwise is positive);

(43) Behavioral Field Modeling:

_{ED_cj} = _{EV_cj} .DR _c (15)

Wherein, _{ED_cj} is the behavior field vector formed by the driver of car c at (x _c ,y _c ) at (x _j ,y _j ), and its direction is the same as _{EV_cj} ; _{EV_cj} is the kinetic energy field vector formed by the moving object at (x _c ,y _c ) at (x _j ,y _j ); DR _c is the driver risk factor related to the driver of car c;

(44) Driving safety field modeling:

As shown in FIG5 , the driving safety field can be expressed as:

E _{S_j} = E _{R_j} + E _{V_j} + E _{D_j} (16)

Wherein, _{ES_j} is the driving safety field at (x _j ,y _j ); _{ER_j} is the potential energy field at (x _j ,y _j ); _{EV_j} is the kinetic energy field vector at (x _j ,y _j ); _{ED_j} is the behavior field vector at (x _j ,y _j );

According to the above, the safety field force at (x _j ,y _j ) can be derived as:

Wherein, _Fj is the safety field force vector at ( _xj , _yj ), with the same direction as _Ej ; _Ej is the safety field vector at ( _xj , _yj ); _Mj is the virtual mass of vehicle j at ( _xj , _yj ); _Rj is the influence factor of the road at ( _xj , _yj ); _k3 is an undetermined coefficient greater than zero; _vj is the speed of vehicle j at ( _xj , _yj ); _θj is the angle between _vj and _Ej (clockwise is positive); _DRj is the driver risk factor of the driver of vehicle j;

(45) According to the current driving safety field force value of the vehicle, the corresponding driving right value to be allocated is calculated: the driving right is allocated according to a certain allocation principle using a table lookup method, and the table parameters are adjusted according to different actual conditions.

The allocation principle in step (45) is as follows:

The allocation principle during normal takeover is shown in Table 1 below:

Table 1

The allocation principles in dangerous situations are shown in Table 2 below:

Table 2

The final driving right calculation method in step (5) is as follows:

The driving weight Q _k that should be allocated at the current moment calculated according to the above steps, And Q _F calculate the final output driving weight Q:

Wherein, Q is the final driving weight allocation result; _w1 , _w2 and _w3 are weighting factors, which can be adjusted according to the real-time driving weight allocation values of various factors.

The present invention has many specific application paths. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements can be made without departing from the principle of the present invention. These improvements should also be regarded as the protection scope of the present 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.