CN113341730A - Vehicle steering control method under remote man-machine cooperation - Google Patents
Vehicle steering control method under remote man-machine cooperation Download PDFInfo
- Publication number
- CN113341730A CN113341730A CN202110718353.5A CN202110718353A CN113341730A CN 113341730 A CN113341730 A CN 113341730A CN 202110718353 A CN202110718353 A CN 202110718353A CN 113341730 A CN113341730 A CN 113341730A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- machine
- driver
- driving
- potential energy
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a vehicle steering control method under remote man-machine cooperation, which relates to the field of intelligent vehicle remote driving and is characterized by comprising the following steps of: step 1, calculating a comprehensive safety potential field value in a traffic flow where a self vehicle is located; step 2, predicting a short-term expected track of the driver; step 3, considering the moment of a driver and the safety risk degree in the traffic flow where the driving vehicle is located, designing different fuzzy controllers, and obtaining dynamic authority factors between the human and the machine; and 4, designing a remote cooperative driving vehicle steering control strategy and establishing a remote man-machine cooperative controller. According to the invention, the dynamic authority factor between the human machine and the machine is calculated by comparing the sum of the driving safety potential fields of the predicted track of the driving vehicle and the track planned by the machine, the steering control authority between the human machine and the machine is reasonably distributed, the transverse state control of the vehicle is realized, the conflict between the human machine and the machine is reduced, and the driving safety and the driving comfort are improved.
Description
Technical Field
The invention relates to the field of intelligent vehicle remote driving, in particular to a vehicle steering control method under remote man-machine cooperation.
Background
In recent years, with the support of technologies such as computer vision, 5G communication, internet of vehicles, artificial intelligence and the like, many companies have introduced automobile products equipped with intelligent driving systems, and two kinds of future development resultant force of vehicles, namely, intelligent automatic driving of a single vehicle and intelligent internet connection depending on advanced internet, are formed. The intelligent internet vehicle cooperation technology is a new generation internet technology, realizes dynamic real-time information interaction of vehicles and vehicles on all directions, develops a vehicle-road cooperation safety technology on the basis of full-time dynamic traffic information acquisition and fusion, fully realizes effective cooperation of people, vehicles and roads, and improves the driving safety and comfort of vehicles. With the popularization of 5G networks, the transmission delay of video signals and the like is reduced to be within 10ms due to the large bandwidth and the low time delay, and the remote driving practical application of vehicles can be landed on the ground. Compared with the traditional automatic driving implementation method, the man-vehicle-road cooperative driving in the remote driving environment is a new technical route different from completely unmanned driving, the dependence on a high-precision sensor and intelligent driving software and hardware can be effectively reduced through the man-vehicle-road cooperative driving in the remote driving environment, an actual driver on a vehicle can be cancelled, the riding space of the vehicle is improved, the effect similar to that of the unmanned driving is achieved, and the intelligent driving comprehensive solution is controllable, low in cost, high in reliability and capable of being timely implemented.
[ 201810253686.3 ] A method for driving right transfer in interactive man-machine co-driving is provided. According to the invention, the driving right transfer in man-machine driving is realized by extracting the current key factors influencing the driving safety and analyzing the safety of the current driving state. However, the driving right cannot be dynamically adjusted in a ring by man-machine at the same time, and meanwhile, the end-to-end transfer of the driving right between man-machine requires some time, which easily brings driving potential safety hazard.
[ 201710784806.8 ] provides a man-machine cooperation driving method of an automatic driving vehicle. The remote control terminal is applied to a remote driving environment, the vehicle can realize a certain automatic driving function, and the remote control terminal needs to control the vehicle to bypass a barrier and realize the switching between automatic driving and manual remote driving. The method realizes automatic driving of the vehicle by combining manual remote control and automatic driving, and can deal with more complex driving scenes, namely complex driving scenes which cannot be processed by automatic driving originally. However, the method simplifies the human and the machine, namely, the automatic driving function works in a part of time, and a part of time is intervened by a remote control personnel, so that the organic integration of the human and the machine cannot be realized, and the method is in a unilateral control mode.
Therefore, those skilled in the art have made efforts to develop a man-vehicle cooperative control method suitable for a remote driving environment in consideration of the driver's will and traffic safety evaluation. The method improves a calculation method of a driving safety potential field to evaluate the safety risk degree of a vehicle in a traffic flow, and because the telepresence of a driver is influenced to a certain extent in a remote driving environment, the method calculates dynamic authority factors between human machines based on three human-machine target consistency modes by comparing the sum of the driving safety potential field of a predicted track of the driving vehicle and a track planned by a machine, reasonably distributes steering control authorities between the human machines, realizes the transverse state control of the vehicle, and reduces the conflict between the human machines in the driving process of the vehicle so as to improve the driving safety and comfort.
Disclosure of Invention
In view of the above defects in the prior art, the technical problem to be solved by the present invention is how to reasonably allocate steering control authority between human and machine under the remote driving environment of the intelligent vehicle, so as to realize the lateral state control of the vehicle.
In order to achieve the above object, the present invention provides a method for controlling steering of a vehicle under remote human-machine cooperation, the method comprising the steps of:
step 3, considering the torque of a driver and the safety risk degree in the traffic flow where the driving vehicle is located, designing different fuzzy controllers based on a human-computer target consistency mode, and obtaining dynamic authority factors between human and computers;
and 4, designing a remote cooperative driving vehicle steering control strategy, and establishing a remote man-machine cooperative controller to obtain the final input torque of the vehicle.
Further, in step 1, the integrated safety potential field values comprise a potential energy field characterizing a risk from a non-moving object, a kinetic energy field and a behavioral field, the potential energy field being expressed as:
wherein k is1Is a proportionality coefficient, R, associated with the lane line1Are road condition influencing factors, (x, y) and (x)l,yl) Respectively represent the position of the own vehicle and the lane line nearest to the own vehicle, rl=(x-xl,y-yl);
The kinetic energy field represents a risk that the own vehicle is subjected to a force from a moving vehicle, and is represented as:
wherein M isvIs the mass of the obstacle vehicle, RvIs a scale factor, r0=((x-x0)/c,(y-y0) D) represents a vector distance between the own vehicle and the obstacle vehicle, thetaeRepresenting the velocity vOVDirection and r0Angle of direction, c and d are offset factors, vOVRepresenting a speed of the own vehicle;
the behavior field represents the safety risk of the driver's own behavior on the own vehicle, and is represented as:
Eb=k3Ev;
wherein k is3Is a coefficient related to the driver state.
Further, in step 1, the integrated safety potential field value further includes a risk factor function, the risk factor function characterizes the azimuth condition of the obstacle vehicle in the self-vehicle, and the functional relationship between the risk factor and the angle is expressed as:
where s is a risk factor, θsIs the speed direction and vector r of the vehicle0The included angle of (a).
Further, in step 1, the potential energy sum of the own vehicle includes the potential energy field, the kinetic energy field, the behavior field and the risk factor function, and is characterized in that:
wherein M and N represent the number of lanes and the obstacle vehicles;
in the running process of the vehicle, the change rate of the potential energy sum of the vehicle represents the change trend of the risk of the vehicle, and the comprehensive safety potential field value is characterized as follows:
CDS=Es+dEs/dt;
wherein CDS represents the integrated safety potential field value.
Further, in the step 2, the model based on the constant turning rate and the acceleration is expressed as:
xC=(x,y,ψ,v,a,ω);
wherein x, y represent longitudinal and lateral coordinates of the driven vehicle, ψ represents a heading angle of the driven vehicle, v represents a vehicle speed of the driven vehicle, a represents an acceleration of the driven vehicle, and ω represents a yaw rate of the driven vehicle, respectively;
assuming that the driven vehicle maintains a constant turn rate and a constant acceleration for a future period of time, the future equation of state of the driven vehicle is:
xt+Δt=xt+ΔF(t);
wherein, Δ t is a time step, and Δ f (t) is a state variation;
iterating the future equation of state of the driven vehicle by NpStep (c), an expected trajectory [ (x) of the driven vehicle within T time can be obtained1,y1),(x2,y2)…(xT,yT)]The planned track of the machine is planned in advance asAnd substituting the predicted track point of the driver and the machine planning track point into the comprehensive safe potential field value to sum to obtain the predicted track potential energy sum of the vehicleAnd machine planning trajectory potential energy and
further, in the step 3, the fuzzy controller includes a target uniform mode fuzzy controller in which a driver and a machine are in a normal control state, a driver priority mode fuzzy controller in which the driver is assigned more driving authorities than the machine, and a machine priority mode fuzzy controller in which the machine is assigned more driving authorities than the driver.
Further, in the step 3, whenOr Then, the fuzzy controller of the target consistent mode is adopted(ii) a When the potential energy of the predicted trajectory of the driver is lower than 0.9 times the potential energy of the planned trajectory of the machine, i.e. the predicted trajectory of the driver is less than the potential energy of the planned trajectory of the machineThen, adopting the driver priority mode fuzzy controller; when the potential energy value of the planned trajectory of the machine is lower than 0.9 times the potential energy of the predicted trajectory of the driver, i.e. when the projected trajectory of the machine is a factor of twoThe machine priority mode is used.
Further, in the step 3, the input value of the fuzzy controller is the intervention torque and driving risk assessment quantity of the driver, and the output value of the fuzzy controller is the dynamic authority factor between the human machine and the machine.
Further, in step 4, the final input torque of the vehicle couples the input torque of the driver and the input torque of the machine, the allocation strategy is determined according to the dynamic authority factor K between the human machines obtained in step 3, and the final input torque of the vehicle is determined by the following formula:
τ=Kτd+(1-K)τc;
where τ represents the vehicle final input torque, τdRepresenting the input torque, τ, of the drivercRepresenting an input torque of the machine.
Further, the transmission of signals between the driver and the driven vehicle is via a 5G network.
Because the telepresence of the driver in the remote driving environment can be influenced to a certain extent, the safety degree of the track is determined by comparing and predicting the safety potential energy of the future driving track of the driver and the safety potential energy sum of the future driving track planned by the machine, so that the method determines who the 'man' and the 'machine' distribute more driving authorities, and the method is divided into three control modes according to different situations: a human-machine target consistent mode, a driver priority control mode and a machine priority control mode.
In the human-computer target consistent mode, a human and a machine are in a normal control state;
the driver is assigned more driving authority in the driver priority control mode;
the machine is assigned more driving authority in the machine priority control mode.
Through the arrangement of the three control modes, the invention can reduce the conflict in the man-machine steering control process, and gives greater freedom degree to the driver in a safe driving scene, thereby improving the safety and comfort of driving the vehicle, and having the following effects:
1. the invention provides an improved and optimized traffic flow safety risk assessment method, which takes the distance between a self vehicle and a target vehicle and the speed direction into consideration by combining safety risk factors and is closer to the safety assessment of a real driving scene;
2. the method determines the mode of consistency of the human-computer target by predicting the driving track of a driver and comprehensively comparing the tracks of the machines, and under the scene, more control authorities are distributed to a main body which is safe relative to the human and the machine, and less control authorities are distributed to the other main body;
3. the invention designs three fuzzy controllers which are used under the conditions of different man-machine target consistencies and comprise a target consistence mode, a driver priority mode and a machine priority mode, aims to reduce the contradiction between man machines and ensure that more authorities are distributed to the driver as far as possible under the condition of safety, realizes the remote man-machine cooperative driving and running, and simultaneously keeps the function that the driver can completely control the steering of the vehicle, namely the driver can completely control the motion of the vehicle by paying a moment more than 4Nm, and K is 1;
4. according to the method, under the condition that the automatic vehicle driving controller and the remote driver are controlled together, the steering control right of the automatic vehicle driving controller and the steering control right of the remote driver can be distributed through the driving right which is dynamically adjusted, so that the automatic vehicle driving controller and the driver can cooperatively control the remote vehicle.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a flow chart of a design method of a preferred embodiment of the present invention;
FIG. 2 is a schematic diagram of a vehicle position correlation in a traffic flow scenario according to a preferred embodiment of the present invention;
FIG. 3 is a schematic illustration of a remote co-driver vehicle steering control strategy in accordance with a preferred embodiment of the present invention;
FIG. 4 is a schematic diagram of the target consistent mode fuzzy controller rule in accordance with a preferred embodiment of the present invention;
FIG. 5 is a schematic view of the driver priority mode fuzzy controller rule of a preferred embodiment of the present invention;
FIG. 6 is a schematic diagram of the rules of the fuzzy controller for the machine priority mode in accordance with a preferred embodiment of the present invention.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
The size and thickness of each component shown in the drawings are arbitrarily illustrated, and the present invention is not limited to the size and thickness of each component. The thickness of the components may be exaggerated where appropriate in the figures to improve clarity.
The invention provides a man-vehicle cooperative control method which is applicable to a remote driving environment and takes the intention of a driver and traffic flow safety evaluation into consideration, the calculation method of a driving safety potential field is improved to evaluate the safety risk degree of the vehicle in a traffic flow, and the method calculates dynamic permission factors between human machines and reasonably distributes steering control permission between the human machines by comparing the driving safety potential field of a predicted track of the driving vehicle with the driving safety potential field of a planned track of a machine based on three human-machine target consistency modes because the telepresence of the driver in the remote driving environment is influenced to a certain extent, thereby realizing the transverse state control of the vehicle. As shown in fig. 1, the specific steps are as follows:
step 3, considering the torque of a driver and the safety risk degree in the traffic flow where the driving vehicle is located, designing three fuzzy controllers based on a human-computer target consistency mode, and obtaining dynamic authority factors between human and computers;
and 4, designing a remote cooperative driving vehicle steering control strategy and establishing a remote man-machine cooperative controller.
1. Calculation of integrated safety potential field values
(1) Potential energy of each part is calculated as follows, and the coordinate relationship is shown in fig. 2.
The potential energy field is primarily indicative of risks from non-moving objects, such as lane lines, traffic markers, etc. The closer the host vehicle is to these immobile objects, the higher the risk level. Therefore, the potential field experienced by the own vehicle at the coordinates (x, y) is represented as:
in the formula: k is a radical of1Is a proportionality coefficient associated with the lane line; r1Is a road condition influence factor; (x, y) and (x)l,yl) Respectively showing the position of the own vehicle and the position of a lane line closest to the own vehicle; r isl=(x-xl,y-yl)。
The kinetic energy field represents the risk of the own vehicle being exposed to the motion from the moving vehicle. The closer the distance from the host vehicle to the obstacle vehicle, the higher the risk of collision. Therefore, the kinetic energy field generated by the obstacle vehicle at the own vehicle (x, y) is:
in the formula: mvIs the mass of the obstacle vehicle; rvIs a scale factor; r is0=((x-x0)/c,(y-y0) D) represents a vector distance between the own vehicle and the obstacle vehicle; thetaeRepresenting the velocity vOVDirection and r0The included angle of the direction; c and d are bias factors; v. ofOVIndicating the speed of the vehicle.
The behavior field characterizes the safety risk of the driver's own behavior for driving the vehicle. The magnitude of the value is related to the fatigue state of the driver, the driving skill, the driving mood, and the like. For example, in the same scenario, a driver with a skilled driving skill may experience a lower driving risk than a driver with an unsophisticated driving skill. Regardless of monitoring the real-time state of the driver, the behavior bias degree of the driver is related to the state of the vehicle in the traffic flow, and the behavior field energy is expressed as a linear relation of the kinetic energy field for simplifying calculation.
Eb=k3Ev (3)
In the formula, k3Is a coefficient related to the driver state.
(2) Risk factor function definition
In the past, the speed direction and the vector r of the vehicle are rarely considered0Included angle thetasThe influence of the safety potential field distribution of the vehicle is considered, namely the azimuth condition of the obstacle vehicle in the self vehicle. A risk factor s and an angle theta are presented hereinsFunctional relationship between:
the position correlation of the vehicles in the traffic flow scene is shown in fig. 2.
(3) Comprehensive driving safety potential energy design
The potential energy sum of the self vehicle comprises a potential energy field, a kinetic energy field and a behavior field, and the influence of a risk factor function is considered, and the potential energy sum is characterized in that:
in the formula, M and N represent the number of lanes and obstacle vehicles.
During the running process of the vehicle, the change rate of the potential energy represents the change trend of the risks suffered by the vehicle. Therefore, herein, considering comprehensively the driving safety potential field value of the vehicle and the rate of change of the potential field value, a comprehensive safety potential field (CDS) is proposed:
CDS=Es+dEs/dt (6)
2. driver trajectory prediction
To quantify the safety of the vehicle over a future period of time, the present document predicts the trajectory of the vehicle over the future period of time based on a constant turn rate constant acceleration model (CTRA). Predicting potential energy value of track by calculationThe safety degree of the vehicle in a future period is obtained. The CTRA model can be expressed as:
xC=(x,y,ψ,v,a,ω) (7)
in the formula: x and y respectively represent longitudinal and transverse coordinates of the vehicle; ψ represents a heading angle of the vehicle; v represents a vehicle speed of the vehicle; a represents the acceleration of the vehicle; ω represents the yaw rate of the vehicle; x is the number ofCRepresenting the set of parameters.
Assuming that the vehicle maintains a constant turning rate and constant acceleration for a future period of time, the future state of the vehicle can be predicted as:
xt+Δt=xt+ΔF(t) (8)
in the formula: Δ t is the time step; Δ f (t) is a state change amount.
Iterating equation (8) by NpStep(s), an expected trajectory [ (x) of the vehicle within T time can be obtained1,y1),(x2,y2)…(xT,yT)]The planned track of the machine is planned in advance asThe predicted track potential energy sum of the vehicle can be obtained by summing the predicted track point of the driver and the machine planning track point (6)And machine planning trajectory potential energy and
3. designing a fuzzy controller to obtain the authority factor of driver
The invention provides three man-machine target consistency models(s) based on a fuzzy controller, wherein the models are a target consistency mode fuzzy controller (s is 1), a driver priority mode fuzzy controller (s is 2) and a machine priority mode fuzzy controller (s is 3).
And when the potential energy value of the predicted track of the driver is closer to the potential energy value of the planned track of the machine, namely the following relation exists, adopting the target consistent mode fuzzy controller.
When the potential energy value of the predicted track of the driver is lower than 0.9 times of the potential energy value of the planned track of the machine, the controller is in a driver priority mode at the moment, namely the driver priority mode fuzzy controller is adopted when the following relation exists.
When the potential energy value of the planned track of the machine is lower than 0.9 times of the potential energy of the predicted track of the driver, the controller is in a machine priority mode at the moment, namely the fuzzy controller of the machine priority mode is adopted when the following relation exists.
The fuzzy controller can combine with expert experience and has good generalization capability for processing unknown nonlinear systems. Therefore, in the present invention, the driver's intervention torque and driving risk assessment are used as two inputs to the fuzzy controller, and the output is the driver dynamic authority factor K.
The fuzzy controller can be widely applied to the design of the controller by virtue of the advantages that the fuzzy controller can be fused with expert experience rules, the output control quantity is smooth, and the like, the dynamic authority distribution factor is solved by utilizing the fuzzy controller, and aiming at three different target consistency models, the fuzzy controller designs three corresponding fuzzy controllers, the input and the output of the three fuzzy controllers are the same, the fuzzy rules are different, the fuzzy rule of the target consistency mode fuzzy controller is shown in figure 4, the fuzzy rule of the driver priority mode fuzzy controller is shown in figure 5, and the fuzzy rule of the machine priority mode fuzzy controller is shown in figure 6. The fuzzy controller contains two control inputs, respectively the driver torque τdAnd an output K of the integrated safety potential field CDS, fuzzy controller.
The CDS has 5 semantic variables: very Safe (VVS), general safe (VS), safe (S), general (M), dangerous (L), general dangerous (VL), very dangerous (VVL), variable Range [0,600](ii) a Driver torque taudThere are 5 semantic variables: very Small (VVS), generally small (VS), small (S), medium (M), large (L), generally large (VL), very large (VVL), variable range [0,4 ]](ii) a K has 5 semantic variables: generally small (VS), small (S), medium (M), large (L), generally large (VL), very large (VVL), variable range [0,1]。
The fuzzy controller converts the fuzzy output into the fuzzy control quantity by using a gravity center method, in addition, the fuzzy controller performs fuzzy calculation by using a amantani reasoning method to obtain the output value of the fuzzy controller, and the reasoning form is characterized as follows:
if CDS is A, τdIf B, K is C. (14)
In the formula: a, B and C are the two input values and one output value of the fuzzy controller, respectively.
4. Establishing a remote cooperative driving vehicle steering control strategy
As shown in fig. 3, the remote cooperative driving vehicle steering control strategy comprises two parts, namely a remote driver and a controlled vehicle, wherein the signal transmission between the remote driver and the controlled vehicle is transmitted through a 5G network, the dotted line in the figure represents the transmission through the 5G network, and the solid line represents the actual physical wired transmission. The final driving input torque of the remote driving vehicle is the control input coupled with the control input of the driver and the control input of the machine, the specific allocation strategy is based on the dynamic authority factor K of the driver calculated by the fuzzy controller in the step 3, meanwhile, the invention keeps the function that the driver can completely control the vehicle steering, namely, the driver can completely control the vehicle to move when paying the torque more than 4Nm, and K is 1.
τ=Kτd+(1-K)τc (15)
In the formula: τ represents the final input torque of the vehicle, τdIndicating the moment, τ, of the drivercRepresenting the moment of the machine.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A vehicle steering control method under remote man-machine cooperation is characterized by comprising the following steps:
step 1, calculating a comprehensive safety potential field value in a traffic flow where a self vehicle is located based on a driving safety potential field theory;
step 2, predicting a short-term expected track of the driver based on the constant turning rate and the acceleration model;
step 3, considering the torque of a driver and the safety risk degree in the traffic flow where the driving vehicle is located, designing different fuzzy controllers based on a human-computer target consistency mode, and obtaining dynamic authority factors between human and computers;
and 4, designing a remote cooperative driving vehicle steering control strategy, and establishing a remote man-machine cooperative controller to obtain the final input torque of the vehicle.
2. The remote human-computer cooperative vehicle steering control method according to claim 1, wherein in the step 1, the integrated safety potential field value includes a potential energy field, a kinetic energy field and a behavior field, the potential energy field characterizes risks from non-moving objects, and the potential energy field is expressed as:
wherein k is1Is a proportionality coefficient, R, associated with the lane line1Are road condition influencing factors, (x, y) and (x)l,yl) Respectively represent the position of the own vehicle and the lane line nearest to the own vehicle, rl=(x-xl,y-yl);
The kinetic energy field represents a risk that the own vehicle is subjected to a force from a moving vehicle, and is represented as:
wherein M isvIs the mass of the obstacle vehicle, RvIs a scale factor, r0=((x-x0)/c,(y-y0) D) represents a vector distance between the own vehicle and the obstacle vehicle, thetaeRepresenting the velocity vOVDirection and r0Angle of direction, c and d are offset factors, vOVRepresenting a speed of the own vehicle;
the behavior field represents the safety risk of the driver's own behavior on the own vehicle, and is represented as:
Eb=k3Ev;
wherein k is3Is a coefficient related to the driver state.
3. The method for controlling steering of vehicle under remote human-machine cooperation as claimed in claim 2, wherein in step 1, said integrated safety potential field value further includes a risk factor function, said risk factor function characterizes the orientation of said obstacle vehicle in said own vehicle, and the functional relationship between risk factor and angle is expressed as:
where s is the risk factor, θsIs the speed direction and vector r of the vehicle0The included angle of (a).
4. The method for controlling steering of a vehicle under remote human-machine cooperation according to claim 3, wherein in the step 1, the potential energy sum of the host vehicle comprises the potential energy field, the kinetic energy field, the behavior field and the risk factor function, and is characterized in that:
wherein M and N represent the number of lanes and the obstacle vehicles;
in the running process of the vehicle, the change rate of the potential energy sum of the vehicle represents the change trend of the risk of the vehicle, and the comprehensive safety potential field value is characterized as follows:
CDS=Es+dEs/dt;
wherein CDS represents the integrated safety potential field value.
5. The method for controlling steering of a vehicle under remote human-machine cooperation according to claim 1, wherein in the step 2, the model based on constant turning rate and acceleration is expressed as:
xC=(x,y,ψ,v,a,ω);
wherein x, y represent longitudinal and lateral coordinates of the driven vehicle, ψ represents a heading angle of the driven vehicle, v represents a vehicle speed of the driven vehicle, a represents an acceleration of the driven vehicle, and ω represents a yaw rate of the driven vehicle, respectively;
assuming that the driven vehicle maintains a constant turn rate and a constant acceleration for a future period of time, the future equation of state of the driven vehicle is:
xt+Δt=xt+ΔF(t);
wherein, Δ t is a time step, and Δ f (t) is a state variation;
iterating the future equation of state of the driven vehicle by NpStep (c), an expected trajectory [ (x) of the driven vehicle within T time can be obtained1,y1),(x2,y2)…(xT,yT)]The planned track of the machine is planned in advance asAnd substituting the predicted track point of the driver and the machine planning track point into the comprehensive safe potential field value to sum to obtain the predicted track potential energy sum of the vehicleAnd machine planning trajectory potential energy and
6. the remote human-machine cooperation vehicle steering control method according to claim 5, wherein in the step 3, the fuzzy controller includes a target consistent mode fuzzy controller in which a driver and a machine are in a normal control state, a driver priority mode fuzzy controller in which the driver is assigned more driving authority than the machine, and a machine priority mode fuzzy controller in which the machine is assigned more driving authority than the driver.
7. The method as claimed in claim 6, wherein in step 3, when the vehicle steering control is executed in cooperation with a remote human-machine interactionOrThen, the target consistent mode fuzzy controller is adopted; when the potential energy of the predicted trajectory of the driver is lower than 0.9 times the potential energy of the planned trajectory of the machine, i.e. the predicted trajectory of the driver is less than the potential energy of the planned trajectory of the machineThen, adopting the driver priority mode fuzzy controller; when the potential energy value of the planned trajectory of the machine is lower than 0.9 times the potential energy of the predicted trajectory of the driver, i.e. when the projected trajectory of the machine is a factor of twoThe machine priority mode is used.
8. The method as claimed in claim 1, wherein in step 3, the input values of the fuzzy controller are the intervention torque and driving risk assessment of the driver, and the output value of the fuzzy controller is the dynamic authority factor between the human machines.
9. A method as claimed in claim 1, wherein in step 4, the final input torque of the vehicle is coupled with the input torque of the driver and the input torque of the machine, the allocation strategy is determined according to the dynamic authority factor K between the human machines obtained in step 3, and the final input torque of the vehicle is determined by the following formula:
τ=Kτd+(1-K)τc;
where τ represents the vehicle final input torque, τdRepresenting the input torque, τ, of the drivercRepresenting an input torque of the machine.
10. The method as claimed in claim 1, wherein the signal transmission between the driver and the driving vehicle is via a 5G network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110718353.5A CN113341730B (en) | 2021-06-28 | 2021-06-28 | Vehicle steering control method under remote man-machine cooperation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110718353.5A CN113341730B (en) | 2021-06-28 | 2021-06-28 | Vehicle steering control method under remote man-machine cooperation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113341730A true CN113341730A (en) | 2021-09-03 |
CN113341730B CN113341730B (en) | 2022-08-30 |
Family
ID=77479201
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110718353.5A Active CN113341730B (en) | 2021-06-28 | 2021-06-28 | Vehicle steering control method under remote man-machine cooperation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113341730B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113619563A (en) * | 2021-09-06 | 2021-11-09 | 厦门大学 | Intelligent electric vehicle transverse control system and method based on man-machine sharing |
CN115071758A (en) * | 2022-06-29 | 2022-09-20 | 杭州电子科技大学 | Man-machine common driving control right switching method based on reinforcement learning |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110329255A (en) * | 2019-07-19 | 2019-10-15 | 中汽研(天津)汽车工程研究院有限公司 | A kind of deviation auxiliary control method based on man-machine coordination strategy |
CN110435671A (en) * | 2019-07-31 | 2019-11-12 | 武汉理工大学 | It is man-machine to drive the driving permission switching system that driver's state is considered under environment altogether |
CN110509926A (en) * | 2019-08-06 | 2019-11-29 | 武汉理工大学 | One kind man-machine drive altogether drives driver's abnormal condition monitoring system in permission handoff procedure under environment |
CN111489588A (en) * | 2020-03-30 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Vehicle driving risk early warning method and device, equipment and storage medium |
CN111717207A (en) * | 2020-07-09 | 2020-09-29 | 吉林大学 | Cooperative steering control method considering human-vehicle conflict |
CN111857340A (en) * | 2020-07-17 | 2020-10-30 | 南京航空航天大学 | Multi-factor fusion man-machine co-driving right distribution method |
CN111976723A (en) * | 2020-09-02 | 2020-11-24 | 大连理工大学 | Lane keeping auxiliary system considering dangerous state of vehicle under man-machine cooperative control |
CN112356852A (en) * | 2020-11-12 | 2021-02-12 | 北京石油化工学院 | Driver and intelligent vehicle unit cooperative driving control right switching method |
CN112562405A (en) * | 2020-11-27 | 2021-03-26 | 山东高速建设管理集团有限公司 | Radar video intelligent fusion and early warning method and system |
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 |
-
2021
- 2021-06-28 CN CN202110718353.5A patent/CN113341730B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110329255A (en) * | 2019-07-19 | 2019-10-15 | 中汽研(天津)汽车工程研究院有限公司 | A kind of deviation auxiliary control method based on man-machine coordination strategy |
CN110435671A (en) * | 2019-07-31 | 2019-11-12 | 武汉理工大学 | It is man-machine to drive the driving permission switching system that driver's state is considered under environment altogether |
CN110509926A (en) * | 2019-08-06 | 2019-11-29 | 武汉理工大学 | One kind man-machine drive altogether drives driver's abnormal condition monitoring system in permission handoff procedure under environment |
CN111489588A (en) * | 2020-03-30 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Vehicle driving risk early warning method and device, equipment and storage medium |
CN111717207A (en) * | 2020-07-09 | 2020-09-29 | 吉林大学 | Cooperative steering control method considering human-vehicle conflict |
CN111857340A (en) * | 2020-07-17 | 2020-10-30 | 南京航空航天大学 | Multi-factor fusion man-machine co-driving right distribution method |
CN111976723A (en) * | 2020-09-02 | 2020-11-24 | 大连理工大学 | Lane keeping auxiliary system considering dangerous state of vehicle under man-machine cooperative control |
CN112356852A (en) * | 2020-11-12 | 2021-02-12 | 北京石油化工学院 | Driver and intelligent vehicle unit cooperative driving control right switching method |
CN112562405A (en) * | 2020-11-27 | 2021-03-26 | 山东高速建设管理集团有限公司 | Radar video intelligent fusion and early warning method and system |
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 |
Non-Patent Citations (7)
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113619563A (en) * | 2021-09-06 | 2021-11-09 | 厦门大学 | Intelligent electric vehicle transverse control system and method based on man-machine sharing |
CN113619563B (en) * | 2021-09-06 | 2022-08-30 | 厦门大学 | Intelligent electric vehicle transverse control system and method based on man-machine sharing |
CN115071758A (en) * | 2022-06-29 | 2022-09-20 | 杭州电子科技大学 | Man-machine common driving control right switching method based on reinforcement learning |
Also Published As
Publication number | Publication date |
---|---|
CN113341730B (en) | 2022-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Path tracking control for autonomous vehicles based on an improved MPC | |
Suh et al. | Stochastic model-predictive control for lane change decision of automated driving vehicles | |
CN110187639B (en) | Trajectory planning control method based on parameter decision framework | |
Guo et al. | Nonlinear coordinated steering and braking control of vision-based autonomous vehicles in emergency obstacle avoidance | |
Chen et al. | Simultaneous path following and lateral stability control of 4WD-4WS autonomous electric vehicles with actuator saturation | |
Shakouri et al. | Nonlinear model predictive control approach in design of adaptive cruise control with automated switching to cruise control | |
CN113341730B (en) | Vehicle steering control method under remote man-machine cooperation | |
CN110703754B (en) | Path and speed highly-coupled trajectory planning method for automatic driving vehicle | |
Zha et al. | A survey of intelligent driving vehicle trajectory tracking based on vehicle dynamics | |
Mohammadzadeh et al. | A robust fuzzy control approach for path-following control of autonomous vehicles | |
Laurense et al. | Long-horizon vehicle motion planning and control through serially cascaded model complexity | |
Chiang et al. | Embedded driver-assistance system using multiple sensors for safe overtaking maneuver | |
Wang et al. | Longitudinal and lateral control of autonomous vehicles in multi‐vehicle driving environments | |
Benloucif et al. | A new scheme for haptic shared lateral control in highway driving using trajectory planning | |
CN113619574A (en) | Vehicle avoidance method and device, computer equipment and storage medium | |
Liu et al. | Moving horizon shared steering strategy for intelligent vehicle based on potential‐hazard analysis | |
Guo et al. | Adaptive non‐linear coordinated optimal dynamic platoon control of connected autonomous distributed electric vehicles on curved roads | |
Seo et al. | Robust mode predictive control for lane change of automated driving vehicles | |
Dai et al. | A bargaining game-based human–machine shared driving control authority allocation strategy | |
Yang et al. | Vehicle local path planning and time consistency of unmanned driving system based on convolutional neural network | |
CN116198534A (en) | Method, device and equipment for controlling intention fusion of co-driving of man and machine and storage medium | |
Zhang et al. | A novel simultaneous planning and control scheme of automated lane change on slippery roads | |
Nilsson et al. | Automated highway lane changes of long vehicle combinations: A specific comparison between driver model based control and non-linear model predictive control | |
Wang et al. | Integrated control of steering and braking for effective collision avoidance with autonomous emergency braking in automated driving | |
Skrickij et al. | Review of integrated chassis control techniques for automated ground vehicles |
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 |