Local traffic safety assessment method and system based on visual angle of automatic driving vehicle

Abstract

The invention relates to a local traffic safety assessment method and system based on a visual angle of an automatic driving vehicle, and the method comprises the following steps: constructing a mechanical simulation system of the automatic driving vehicle in a driving process; establishing a virtual force system from the perspective of an automatic driving vehicle; modeling the action quantity of the virtual force system, and constructing a local traffic safety instantaneous evaluation index; and designing a dangerous scene to carry out a simulation experiment, and evaluating the safety of the automatic driving vehicle in the driving process. According to the method, the local traffic safety assessment method is constructed through the perspective of the autonomous vehicle, and the safety of the autonomous vehicle in the driving process can be assessed more comprehensively by calculating the absolute value of the action quantity borne by the autonomous vehicle in different scenes and the local traffic safety instantaneous assessment index; and the driving safety of the automatic driving vehicle can be improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a local traffic safety assessment method and system based on the perspective of an autonomous driving vehicle. Background Art

[0002] Autonomous vehicles are affected by a combination of factors including people, vehicles, and roads (driven by the driver's driving goals, the impact of the dynamic traffic environment, and the constraints of traffic rules). Due to the complex and changeable road traffic environment, the complex vehicle system, and the coupled performance, the driving risks of autonomous vehicles are time-varying, complex, and coupled. A study published in Nature Communications conducted an in-depth analysis of data from 2,100 autonomous vehicle accidents and 35,133 human-driven car accidents that occurred between 2016 and 2022, and found that autonomous vehicles have a higher accident rate in dim or overly bright environments and on curved roads. The probability of an autonomous vehicle accident at sunrise or sunset is five times that of a human driver, and the accident rate on curved roads is twice that of a human driver. It can be seen that different environments have different risk characteristics, and these risk characteristics are difficult to quantify with a unified standard.

[0003] Therefore, in order to solve the problem of difficulty in uniformly quantifying risks in different driving scenarios of autonomous driving, it is urgent to provide a new assessment method and system to solve this technical problem. Summary of the invention

[0004] In view of this, the present invention provides a local traffic safety assessment method and system based on the perspective of an autonomous driving vehicle, which provides a local traffic safety assessment method based on the principle of minimum action, accurately assessing driving risks, and enhancing the ability of autonomous driving vehicles to respond to and mitigate potential dangers have become issues that urgently need to be addressed by personnel in the current technical field.

[0005] The first aspect of the present invention discloses a local traffic safety assessment method based on the perspective of an autonomous driving vehicle, comprising the following steps:

[0006] Construct a mechanical simulation system for autonomous vehicles during driving, including a virtual driving force used to represent the self-driving vehicle, a virtual risk force affected by the dynamic traffic environment, and a virtual traffic constraint force imposed by traffic rules on the autonomous vehicle.

[0007] According to the mechanical simulation system, a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle is constructed and obtained, including a virtual driving force model, a virtual risk force model and a virtual traffic regulation constraint force model;

[0008] Based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle is calculated respectively to obtain the total potential energy to which the autonomous driving vehicle is subjected;

[0009] Based on the principle of minimum action, the driving process action equation of the virtual force system centered on the autonomous driving vehicle is constructed;

[0010] Based on the driving process action, construct the local traffic safety instantaneous evaluation index;

[0011] For different traffic hazard scenarios, the absolute value of the driving action on the autonomous driving vehicle and the change process of the local traffic safety instantaneous evaluation index over time are calculated to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenarios.

[0012] In the above implementation process, the autonomous driving process of the autonomous driving vehicle is described as the process of a sphere rolling down from the top of the scene matrix (e.g., a U-shaped groove). During the rolling process, it will be subject to the virtual driving force driven by the autonomous driving vehicle itself, the virtual risk external force affected by the dynamic traffic environment, and the virtual constraint resistance generated by traffic rules, that is, the virtual driving force, the virtual risk force, and the virtual traffic rule constraint force. Among them, the inclination angle θ of the U-shaped groove is i It is related to the driver's expected speed or expectation of maneuverability. In the longitudinal direction, θ i,x ≠0, the ball moves longitudinally, and in the horizontal direction, θ i,y When ≠0, the ball will move laterally, which corresponds to the lane-changing behavior of the vehicle. The angle θ between the scene base (i.e., the U-shaped groove) and the XOY horizontal plane (i.e., the XOY plane in the scene coordinates) is i Reflects the driver's overall pursuit of efficiency, θ i,x and θ i,y They correspond to the driver's pursuit of efficiency in the longitudinal and lateral directions during driving. According to the Euler angle coordinate system conversion principle, the relationship between the three satisfies the following formula:

[0013] θ i =arccos(cosθ i,x ·cosθ i,y ).

[0014] Define the virtual driving force as G i , let G i =m i gsinθ i The small protrusions in the U-shaped groove as the scene matrix can be regarded as risk scenarios that the autonomous driving vehicle may face during driving, such as obstacles in front and forced entry of neighboring vehicles, and the virtual risk force F jiIndicates that due to the existence of traffic rules, the driving process of the autonomous vehicle will also be subject to virtual constraint resistance R i .

[0015] That is, in the present invention, based on the scenario model as described above, a mechanical simulation system suitable for the driving process of the autonomous driving vehicle is constructed, that is, a physical model of the driving process is constructed. After the mechanical simulation system is constructed based on the scenario model, the virtual forces to which the autonomous driving vehicle is subjected in the actual driving scenario are modeled to obtain a virtual driving force model, a virtual risk force model, and a virtual traffic regulation constraint force model, respectively. Then, based on the models of each virtual force, the potential energy of each virtual force on the autonomous driving vehicle is calculated, and the driving process action quantity equation of the virtual force system centered on the autonomous driving vehicle is constructed based on the total potential energy. Then, based on the driving process action quantity, a local traffic safety instantaneous evaluation index is constructed, so that for different traffic hazard scenarios, the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenario can be evaluated by calculating the absolute value of the driving process action quantity to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time.

[0016] The present invention provides a relatively unified driving safety assessment method and system for different traffic hazard scenarios, thereby forming a unified and quantifiable assessment standard. Compared with the prior art method of extracting different risk features for different traffic hazard scenarios and assessing them separately, the present invention can accurately assess driving risks in different scenarios based on the principle of minimum action, thereby effectively enhancing the ability of autonomous driving vehicles to cope with and mitigate potential dangers.

[0017] According to the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention, the driving process action equation of the virtual force system centered on the autonomous driving vehicle is:

[0018]

[0019] Where S is the driving action of the autonomous driving vehicle i. Since the virtual force system is centered on the autonomous driving vehicle i, T i = 0, Lagrangian l = T i -U i =-U i , U i Represents the total potential energy of the autonomous vehicle, T i represents the total kinetic energy of the autonomous vehicle, t0, t f They represent the time of starting position and the time of arriving at destination respectively.

[0020] According to the local traffic safety assessment method based on the perspective of an autonomous driving vehicle disclosed in the first aspect of the present invention, the equation of the local traffic safety instantaneous assessment index is:

[0021] D=2-a |S| ;

[0022] Where a is a constant, and So that when S=0, D=1, and when S<0, D∈[0,1].

[0023] According to the local traffic safety assessment method based on the perspective of an autonomous driving vehicle disclosed in the first aspect of the present invention, in the virtual risk force model, the virtual risk force is described by the risk field force of other vehicles to the autonomous driving vehicle, and the construction process of the virtual risk force model is:

[0024] The other car is regarded as the road user relative to the autonomous vehicle, where the autonomous vehicle and the other car are represented by v i and v j The relative speed of the two vehicles is v ji ;

[0025] Taking the coordinates of the other car as the origin, along the relative speed v of the two cars ji Direction establishes the coordinate axis x j , perpendicular to x j Axis direction establishes the coordinate axis y j , forming x j jy j Coordinate system;

[0026] Based on the formed coordinate system, construct and obtain the risk field force F of other vehicles to the autonomous driving vehicle ji The formula is:

[0027]

[0028] in,

[0029]

[0030] In the formula, i represents the autonomous driving vehicle, j represents other vehicles, and M ji V represents the reduced mass of the autonomous vehicle i and other vehicles j; ji represents the velocity term of the two-vehicle system; r′ ji Represents the relative distance between the two vehicles; m i and m j are the masses of the autonomous vehicle i and other vehicle j respectively; v ji represents the relative speed of the two vehicles; is the average speed of the autonomous vehicle i and other vehicles j; r0 is the following distance; r eRepresents the unit length, i.e. r e =1m;k x and k y are the longitudinal and transverse gradient coefficients respectively; x′ i and y′ i They are respectively the autonomous vehicle i at x j jy j Coordinates in the coordinate system; r max is the maximum vertical impact range of the risk, r min Represents the minimum vertical impact range of the risk.

[0031] According to the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention, the virtual driving force includes a longitudinal virtual driving force and a lateral virtual driving force;

[0032] In the virtual driving force model, when the autonomous driving vehicle is in a straight-moving state without changing lanes, it is only subjected to the longitudinal virtual driving force. The virtual driving force model is as follows:

[0033] G i,x =m i gsinθ i,x ;

[0034] Among them, G i,x is the longitudinal driving force; m i is the mass of autonomous vehicle i; g is the acceleration of gravity; θ i is the angle between the scene matrix and the horizontal plane in the mechanical simulation system; θ i,x Represents the longitudinal angle with the XOY plane during driving.

[0035] When the autonomous driving vehicle changes lanes, it is subject to longitudinal virtual driving force and lateral virtual driving force respectively. The virtual driving force model is as follows:

[0036] G i,x =m i gsinθ i ·cosθ i,x

[0037] G i,y =m i gsinθ i sinθ i,y ;

[0038] Among them, G i,y is the lateral virtual driving force; θ i,y Represents the lateral angle with the XOY plane during driving.

[0039] According to the local traffic safety assessment method based on the perspective of an autonomous driving vehicle disclosed in the first aspect of the present invention, in the virtual traffic regulation constraint model, the longitudinal virtual traffic regulation constraint is described by the road speed limit, and the lateral virtual traffic regulation constraint is described by the road traffic markings;

[0040] Among them, the longitudinal virtual traffic regulation constraint force is shown as follows:

[0041]

[0042] Where v i is the speed of the autonomous vehicle; v l Set speed limits for roads;

[0043] The lateral virtual traffic regulation constraint force caused by road traffic markings on autonomous driving vehicles is shown in the following formula:

[0044]

[0045] Among them, k m is a constant coefficient, take k m =0.1; k y is the lateral gradient adjustment coefficient; E i represents the kinetic energy of car i; y mi represents the lateral distance between the autonomous driving vehicle i and the lane line m. When the vehicle is driving on the center line of the lane, it is not affected by the traffic markings. p Indicates the offset, take

[0046] According to the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention, based on the virtual risk force model, the virtual risk potential energy U generated by the virtual risk force of a single other vehicle to the autonomous driving vehicle Fji The calculation formula is:

[0047]

[0048] When there are n other vehicles in the traffic scene, the total virtual risk potential energy U generated for the autonomous driving vehicle is F for:

[0049]

[0050] Among them, based on the virtual driving force model, the virtual driving force generates a virtual driving potential energy U G The calculation formula is:

[0051]

[0052] Where t e is the unit time;

[0053] Among them, based on the virtual traffic regulation constraint model, based on the lateral virtual traffic regulation constraint, the virtual traffic regulation constraint potential energy U generated by the virtual traffic regulation constraint on the autonomous driving vehicle R for:

[0054]

[0055] Then, in the virtual force system centered on the autonomous driving vehicle, the total potential energy of the autonomous driving vehicle in any scenario is:

[0056] U i =U F +U G +U R .

[0057] The second aspect of the present invention further discloses a local traffic safety assessment system based on the perspective of an autonomous driving vehicle, comprising:

[0058] A mechanical simulation construction unit, which is used to construct a mechanical simulation system of the autonomous driving vehicle during driving, including a virtual driving force used to represent the autonomous driving vehicle's own driving force, a virtual risk force affected by the dynamic traffic environment on the autonomous driving vehicle, and a virtual traffic regulation constraint force generated by traffic rules on the autonomous driving vehicle;

[0059] A virtual force system construction unit is configured to construct and obtain a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle according to the mechanical simulation system, including a virtual driving force model, a virtual risk force model and a virtual traffic regulation constraint force model;

[0060] A potential energy calculation unit is constructed to calculate the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, so as to obtain the total potential energy received by the autonomous driving vehicle;

[0061] An action equation construction unit, which is constructed by constructing an action equation of a driving process of a virtual force system centered on an autonomous driving vehicle based on the principle of minimum action;

[0062] An evaluation index construction unit is constructed by constructing a local traffic safety instantaneous evaluation index based on the driving process action amount;

[0063] The evaluation unit is constructed to calculate the absolute value of the driving process action amount to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time for different traffic hazard scenarios, so as to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenarios.

[0064] The third aspect of the present invention discloses an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention.

[0065] The fourth aspect of the present invention further discloses a computer-readable storage medium storing computer instructions. When the computer instructions in the computer-readable storage medium are executed by a computing device, the computing device executes the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention, or enables the computing device to implement the functions of the system disclosed in the second aspect of the present invention.

[0066] Beneficial effects: The method and system of the present invention provide a local traffic safety assessment method based on the principle of minimum action, which can accurately assess driving risks. Enhancing the ability of autonomous driving vehicles to respond to and mitigate potential dangers has become an urgent problem that workers in the current technical field need to solve.

[0067] The local traffic safety assessment method and system based on the perspective of an autonomous driving vehicle of the present invention are disclosed in detail below in conjunction with the embodiments shown in the accompanying drawings and the accompanying figure numerals. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A flowchart of the steps of the local traffic safety assessment method based on the perspective of an autonomous driving vehicle of the present invention is shown.

[0069] Figure 2 The figure shows the mechanical simulation system, i.e., the physical model, of an autonomous vehicle during driving.

[0070] Figure 3 A virtual force system based on the autonomous vehicle's perspective is shown;

[0071] Figure 4 A diagram showing the interaction relationship between the autonomous driving vehicle and other vehicles (i.e., vehicle-to-vehicle);

[0072] Figure 5 —10 are scene diagrams of rear-end collision scenario, deceleration collision avoidance scenario, lane change collision avoidance scenario, cut-in scenario, intersection collision scenario, and intersection braking collision avoidance scenario.

[0073] Figure 11-16 Corresponding to Figure 5-Figure 10 A plot of instantaneous simulation results for the scenario shown. DETAILED DESCRIPTION

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0076] Figure 1 The flowchart of the steps of the local traffic safety assessment method based on the perspective of the autonomous driving vehicle of the present invention is shown. Figure 1 As shown, the present invention discloses a local traffic safety assessment method based on the perspective of an autonomous driving vehicle, comprising the following steps:

[0077] Step S1, constructing a mechanical simulation system of the autonomous driving vehicle during driving, including a virtual driving force for representing the autonomous driving vehicle's own driving, a virtual risk force of the dynamic traffic environment on the autonomous driving vehicle, and a virtual traffic regulation constraint force on the autonomous driving vehicle caused by traffic rules;

[0078] Step S2, constructing and obtaining a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle according to the mechanical simulation system, including a virtual driving force model, a virtual risk force model, and a virtual traffic regulation constraint force model;

[0079] Step S3, based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, respectively calculating the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle, so as to obtain the total potential energy received by the autonomous driving vehicle;

[0080] Step S4, constructing a driving process action equation of a virtual force system centered on the autonomous driving vehicle based on the principle of minimum action;

[0081] Step S5, constructing a local traffic safety instantaneous evaluation index based on the driving process action;

[0082] Step S6, for different traffic hazard scenarios, calculate the absolute value of the driving process action amount to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time, so as to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenario.

[0083] In step S1 of constructing a mechanical simulation system of an autonomous driving vehicle during driving, the autonomous driving process of the autonomous driving vehicle is described as a process in which a sphere rolls downward from the top of a scene base (e.g., a U-shaped groove), such as Figure 2 As shown in the figure, during the rolling process, the vehicle will be subject to the virtual driving force driven by the autonomous driving vehicle itself, the virtual risk force affected by the dynamic traffic environment, and the virtual constraint resistance generated by traffic rules, namely, the virtual driving force, the virtual risk force, and the virtual traffic rule constraint force. i It is related to the driver's expected speed or expectation of maneuverability. In the longitudinal direction, θ i,x ≠0, the ball moves longitudinally, and in the horizontal direction, θ i,y When ≠0, the ball will move laterally, which corresponds to the lane-changing behavior of the vehicle. The angle θ between the scene base (i.e., the U-shaped groove) and the XOY horizontal plane (i.e., the XOY plane in the scene coordinates) is i Reflects the driver's overall pursuit of efficiency, θ i,x and θ i,y They correspond to the driver's pursuit of efficiency in the longitudinal and lateral directions during driving. According to the Euler angle coordinate system conversion principle, the relationship between the three satisfies the following formula:

[0084] θ i =arccos(cosθ i,x ·cosθ i,y ) (1).

[0085] Define the virtual driving force as G i , let G i =m i gsinθ i The small protrusions in the U-shaped groove as the scene matrix can be regarded as risk scenarios that the autonomous driving vehicle may face during driving, such as obstacles in front and forced entry of neighboring vehicles, and the virtual risk force F ji Indicates that due to the existence of traffic rules, the driving process of the autonomous vehicle will also be subject to virtual constraint resistance R i .

[0086] That is, in the present invention, based on the scenario model as described above, a mechanical simulation system suitable for the driving process of the autonomous driving vehicle is constructed, that is, a physical model of the driving process is constructed. After the mechanical simulation system is constructed based on the scenario model, the virtual forces to which the autonomous driving vehicle is subjected in the actual driving scenario are modeled to obtain a virtual driving force model, a virtual risk force model, and a virtual traffic regulation constraint force model, respectively. Then, based on the models of each virtual force, the potential energy of each virtual force on the autonomous driving vehicle is calculated, and the driving process action quantity equation of the virtual force system centered on the autonomous driving vehicle is constructed based on the total potential energy. Then, based on the driving process action quantity, a local traffic safety instantaneous evaluation index is constructed, so that for different traffic hazard scenarios, the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenario can be evaluated by calculating the absolute value of the driving process action quantity to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time.

[0087] The present invention provides a relatively unified driving safety assessment method and system for different traffic hazard scenarios, thereby forming a unified and quantifiable assessment standard. Compared with the prior art method of extracting different risk features for different traffic hazard scenarios and assessing them separately, the present invention can accurately assess driving risks in different scenarios based on the principle of minimum action, thereby effectively enhancing the ability of autonomous driving vehicles to cope with and mitigate potential dangers.

[0088] In step S2, the steps of constructing a virtual driving force model, constructing a virtual risk force model and constructing a virtual traffic regulation constraint force model are included. Figure 3 is the virtual force system from the perspective of the autonomous vehicle, where the white vehicle is the autonomous vehicle i. The virtual risk forces caused by the four other vehicles to vehicle i are The virtual driving force corresponding to the driving expectation of vehicle i is G i , the virtual constraint of the road speed limit rule on the behavior of vehicle i is R si , the constraints of the lane lines on both sides on vehicle i are and

[0089] Specifically, in the first part, the virtual risk force analyzes the relationship between the work done by the force and the energy conversion during the collision process. In order to quantify the risk between any two moving objects in space, this embodiment analyzes the vehicle-vehicle interaction relationship such as Figure 4 As shown, vehicle i and vehicle j are respectively i and v j The relative speed of the two vehicles is v ji , if the coordinate of vehicle j is taken as the origin, along the relative speed v of the two vehicles ji Direction establishes the coordinate axis x j , perpendicular to xj Axis direction establishes the coordinate axis y j ,θ ji Indicates v ji The connection line d between vehicles j and i ji The angle between them is obviously θ ji The smaller the risk of vehicle i being affected by vehicle j, the greater the risk of vehicle i being affected by vehicle j, θ ji It depends on the position and speed of the two vehicles.

[0090] That is, in the virtual risk force model, the virtual risk force is described by the risk field force of other vehicles on the autonomous driving vehicle. Then the construction process of the virtual risk force model is:

[0091] The other car is regarded as the road user relative to the autonomous vehicle, where the autonomous vehicle and the other car are represented by v i and v j The relative speed of the two vehicles is v ji ;

[0092] Taking the coordinates of the other car as the origin, along the relative speed v of the two cars ji Direction establishes the coordinate axis x j , perpendicular to x j Axis direction establishes the coordinate axis y j , forming x j jy j Coordinate system;

[0093] In order to achieve F ji =-F ij , introducing the reduced mass, based on the formed coordinate system, construct and obtain the risk field force F of other vehicles to the autonomous driving vehicle ji The formula is:

[0094]

[0095] in,

[0096]

[0097] In the formula, i represents the autonomous driving vehicle, j represents other vehicles, and M ji V represents the reduced mass of the autonomous vehicle i and other vehicles j; ji represents the velocity term of the two-vehicle system; r j ' i Represents the relative distance between the two vehicles; m i and m j are the masses of the autonomous vehicle i and other vehicle j respectively; v ji represents the relative speed of the two vehicles; is the average speed of the autonomous vehicle i and other vehicles j; r0 is the following distance; r eRepresents the unit length, i.e. r e =1m;k x and k y are the longitudinal and transverse gradient coefficients respectively; x′ i and y′ i They are respectively the autonomous vehicle i at x j jy j Coordinates in the coordinate system; r max is the maximum vertical impact range of the risk, r min Represents the maximum horizontal impact of the risk.

[0098] In addition, if the actual geodetic coordinates of vehicle j and vehicle i are (x j ,y j ) and (x i ,y i ), θ j is the angle of rotation of the coordinate system, then vehicle i is at x j jy j The coordinates in the coordinate system are:

[0099]

[0100] Additionally, in the step of constructing a virtual driving force model, the virtual driving force includes a longitudinal virtual driving force and a lateral virtual driving force; in the virtual driving force model, when the autonomous driving vehicle is in a straight-moving state without lane change, it is only subjected to the longitudinal virtual driving force, and the virtual driving force model is as follows:

[0101] G i,x =m i gsinθ i,x (7)

[0102] Among them, θ i,x Represents the angle between the longitudinal direction and the XOY plane during driving, G i,x is the longitudinal driving force; m i is the mass of autonomous vehicle i; g is the acceleration of gravity; θ i is the angle between the scene matrix and the horizontal plane in the mechanical simulation system, which is related to the pursuit of driving speed by vehicle i, and is defined as i Satisfying formula (8):

[0103]

[0104] Wherein, k is a constant, and in this embodiment, k=0.2; v der is the expected speed of vehicle i; v l Set a speed limit for the lane.

[0105] When the autonomous driving vehicle changes lanes, it is subject to longitudinal virtual driving force and lateral virtual driving force respectively. The virtual driving force model is as follows:

[0106] G i,x =m i gsinθ i ·cosθ i,x (9)

[0107] G i,y =m i gsinθ i sinθ i,y (10)

[0108] Among them, G i,y is the lateral virtual driving force; θ i,y Represents the angle between the lateral and upward direction and the XOY plane during driving. θ i,x is related to the driving expectation of vehicle i in the longitudinal direction. Similarly, θ i,y It is related to the lateral lane-changing behavior of vehicle i. When the driver has the intention to change lanes, he first breaks through the constraint imposed by the lane line on the vehicle and drives towards the center line of the target lane. Therefore, similar to formula (8), the definition is:

[0109]

[0110] Among them, d i,aim is the distance between vehicle i and the center line of the target lane; l w is the lane width, take l w =3.5m; k ic is a constant.

[0111] In addition, in the step of constructing the virtual traffic regulation constraint model, in the third part, the virtual traffic regulation constraint is the constraint caused by the road traffic rules on the vehicle, wherein the road traffic rules such as traffic lights, pedestrian crossings, road traffic speed limit signs and road traffic markings will constrain the movement of the vehicle. This embodiment temporarily only considers the longitudinal constraint of the road traffic speed limit sign on the vehicle movement and the lateral constraint of the road traffic marking on the vehicle movement.

[0112] Since the road speed limit rules are valid everywhere on the roads they refer to, they only depend on the speed. i = 0, the restraining resistance R i =0; if vehicle i accelerates to the road speed limit, that is, v i =v limit When the virtual constraint resistance is equal to the virtual driving force, that is, R i =G i .

[0113] That is, in the virtual traffic regulation constraint model, the longitudinal virtual traffic regulation constraint is described by the road speed limit, and the lateral virtual traffic regulation constraint is described by the road traffic markings;

[0114] Among them, the longitudinal virtual traffic regulation constraint force is shown as follows:

[0115]

[0116] Where v i is the speed of the autonomous vehicle; v l is the road speed limit; from formula (2), we can see that the closer the vehicle speed is to the road speed limit, the greater the constraint resistance.

[0117] Generally, road traffic markings are considered to be able to generate lateral virtual constraints (such as lane keeping) during the driving process of the vehicle. Then, the lateral virtual traffic constraint force caused by road traffic markings on the autonomous driving vehicle is as follows:

[0118]

[0119] Among them, k m is a constant coefficient, take k m =0.1; k y is the lateral gradient adjustment coefficient; E i represents the kinetic energy of car i; y mi represents the lateral distance between the autonomous driving vehicle i and the lane line m. When the vehicle is driving on the center line of the lane, it is not affected by the traffic markings. p Indicates the offset, take

[0120] By modeling the local road traffic environment where the autonomous vehicle is located through virtual force, the vehicle's movement, traffic regulations, and other vehicle risks are integrated and modeled to form a virtual force system. This facilitates the subsequent calculation of safety assessment indicators for the local road traffic environment under the virtual force system architecture.

[0121] In the next step S3, based on the virtual force system architecture from the perspective of the autonomous driving vehicle established in step S2, the potential energy generated by the virtual risk force, virtual driving force and virtual traffic regulation constraint force on the vehicle is calculated, and the sum of these potential energies is used to indicate the safety of the vehicle's driving process.

[0122] Specifically, based on formula (2), for any other road user, the single virtual risk potential energy caused by the other road user to the autonomous driving vehicle can be calculated, that is, based on the virtual risk force model, the virtual risk potential energy caused by the virtual risk force of a single other vehicle to the autonomous driving vehicle is: The calculation formula is:

[0123]

[0124] When there are n other vehicles in the traffic scene, the total virtual risk potential energy U generated for the autonomous driving vehicle is F for:

[0125]

[0126] Furthermore, for the virtual driving force in the longitudinal direction and the virtual traffic regulation constraint force, the virtual driving potential energy U G The modeling of i and θ ix The difference is small. For the convenience of calculation, consider θ i ≈θ ix , combining equations (7) and (12) we can get:

[0127]

[0128] That is, based on the virtual driving force model, the virtual driving force generates a virtual driving potential energy U G The calculation formula of is as above formula (16), where t e As unit time.

[0129] At the same time, in the horizontal direction, ignoring G i,y Based on the virtual traffic regulation constraint model, the virtual traffic regulation constraint potential energy U generated by the virtual traffic regulation constraint on the autonomous driving vehicle is R for:

[0130]

[0131] Then, in the virtual force system centered on the autonomous driving vehicle, the total potential energy of the autonomous driving vehicle in any scenario is:

[0132] U i =U F +U G +U R (18).

[0133] Further, in step S4, the driving process action equation of the virtual force system centered on the autonomous driving vehicle is:

[0134]

[0135] Where S is the driving action of the autonomous driving vehicle i. Since the virtual force system is centered on the autonomous driving vehicle i, T i = 0, Lagrangian L = T i -U i =-U i , U iRepresents the total potential energy of the autonomous vehicle, T i represents the total kinetic energy of the autonomous vehicle, t0, t f They represent the time of starting position and the time of arriving at destination respectively.

[0136] From the above embodiments, the lower the total potential energy of vehicle i, the safer and more efficient it is. F =U G =U R =0, at this time, the action is S=0, taking the extreme value. That is, the driving state of the vehicle is the safest and most efficient at this time. However, in most cases, vehicle i will be affected by the virtual risk force of other vehicles during driving, and it is impossible to always drive at the road speed limit. Therefore, under normal circumstances, the action S<0. Therefore, in step S5, the present invention designs the local traffic safety instantaneous evaluation index D as shown in formula (20), so that when S=0, D=1, and when S<0, D∈[0,1].

[0137] D=2-a |S| (20)

[0138] Where a is a constant, and

[0139] In step S6, based on the local traffic safety instantaneous evaluation index from the perspective of the autonomous driving vehicle, various dangerous scenarios from the perspective of the autonomous driving vehicle are designed, including: rear-end collision scenario, rear-end collision (deceleration to avoid collision) scenario, rear-end collision (lane change to avoid collision) scenario, cut-in scenario, intersection collision scenario. By calculating the absolute value of the amount of action on the autonomous driving vehicle in different scenarios and the local traffic safety instantaneous evaluation index, the safety of the autonomous driving vehicle during driving is simulated and analyzed.

[0140] Specifically, this simulation experiment uses the Driving Scenario Designer in Matlab to design scenarios and perform simulation calculations. Figure 5 For the rear-end scene, Figure 5 In the example, the autonomous driving vehicle i and another vehicle j are in the same lane, 120 meters apart. Vehicle i is traveling at a speed of 30 m / s. If the vehicle remains in motion, the two vehicles will have a rear-end collision in 4 seconds. Fig.11 From the results, as time goes by, the absolute value of the action |S| gradually increases, the local traffic safety instantaneous evaluation index D gradually decreases, and a collision occurs at 4 seconds, and an accident occurs. If the autonomous driving vehicle i recognizes the risk from the front vehicle j during this process and brakes or changes lanes to avoid the risk, the absolute value of the action |S| will not continue to increase, that is, the risk will not continue to increase.

[0141] Furthermore, if Figure 6 For deceleration and collision avoidance scenarios, 3 decelerations are designed - 4m / s 2 , -6m / s 2 , -8m / s 2 , let vehicle i brake from gentle to emergency, and the position when stopping is the same. The results are as follows Fig.12 As shown, Fig.12 EB-1, EB-2, and EB-3 correspond to deceleration of -4m / s respectively. 2 , -6m / s 2 , -8m / s 2 As can be seen from the figure, due to the braking of vehicle i, the driving time changes from 4s to 5.6s, 6.3s, and 7.5s respectively. Compared with the absolute value of the action amount in the rear-end collision scenario, |S| has been significantly reduced, and the local traffic safety instantaneous evaluation index D value has been significantly improved. At the same time, the greater the deceleration |S|, the greater the risk, which is consistent with the actual situation.

[0142] Furthermore, to avoid rear-end collision, lane changing can be adopted. Therefore, a lane changing collision avoidance scenario is designed, such as Figure 7 As shown in Figure 2. It is designed that vehicle i starts changing lanes at a distance of 80m, 60m, and 40m from vehicle j, and the curvature of the lane-changing trajectory is consistent. The results are shown in Figure 2. Fig.13 As shown, Fig.13 LC-1, LC-2, and LC-3 in the figure correspond to lane change starting distances of 80m, 60m, and 40m, respectively. As can be seen from the figure, compared with the absolute value of the action amount in the rear-end collision scenario, |S| has been significantly reduced, and the local traffic safety instantaneous evaluation index D value has been significantly improved. At the same time, it can be seen from the results that the longer the lane change starting distance, the safer it is, which is consistent with the actual situation.

[0143] Furthermore, if a vehicle is too close to other vehicles on the lane on the side of the lane it is changing, the risk will increase. Therefore, the design of the entry scenario, such as Figure 8 As shown in Figure 2. The design is that vehicle j starts to cut in at a distance of 5m, 7.5m, and 10m from vehicle i, and the curvature of the cutting trajectory is consistent. The results are shown in Figure 2. Fig.14 As shown, Fig.14 CI-1, CI-2, and CI-3 in the figure correspond to the starting distances of 10m, 15m, and 20m, respectively. As can be seen from the figure, the smaller the starting distance between the two vehicles when cutting in, the greater the risk, which is consistent with the actual situation. At the same time, the results show that before preparing to change lanes, the vehicle should ensure that it maintains a sufficient longitudinal distance from the vehicle on the lane on the lane to be changed.

[0144] Furthermore, if Fig. 9For the intersection collision scenario, vehicles i and j travel at a constant speed of 20 m / s along their respective lanes. If they remain in motion, they will collide at point C(2, -2) after 2.5 seconds. The results are as follows Fig.15 As shown in the figure, it can be seen from the results that as time goes by, the absolute value of the action |S| gradually increases, the local traffic safety instantaneous evaluation index D gradually decreases, and a collision occurs at 2.5s, and an accident occurs. If the autonomous driving vehicle i recognizes the risk from the front vehicle j during this process and brakes to avoid the risk, the absolute value of the action |S| will not continue to increase, that is, the risk will not continue to increase.

[0145] Furthermore, if Fig.10 For the intersection braking collision avoidance scenario, the autonomous driving vehicle i is designed to find vehicle j when it is 10m away from the collision point and start braking. The speed of vehicle i when passing through the intersection of the trajectories of vehicles i and j is set to 18m / s, 16m / s, and 14m / s respectively. The results are as follows Fig.16 As shown in the figure, NSI-1, NSI-2, and NSI-3 correspond to the speeds of vehicle i passing through the intersection of the trajectories of vehicles i and j, which are 18m / s, 16m / s, and 14m / s, respectively. From the results, it can be seen that since vehicle i starts braking at point (2, -12), that is, after the simulation time t = 2s, the absolute value of the action |S| gradually decreases, and the local traffic safety instantaneous evaluation index D gradually increases. In addition, the lower the speed of vehicle i passing the intersection of the trajectories, the smaller the absolute value of the action |S|, and the higher the local traffic safety instantaneous evaluation index D, which is consistent with the actual situation.

[0146] So far, the simulation results of 6 scenarios have been obtained. From the results, we can see that the absolute value of the action amount |S| on the autonomous driving vehicle and the local traffic safety instantaneous evaluation index D measure the safety of the autonomous driving vehicle's driving process.

[0147] The second aspect of the present invention further discloses a local traffic safety assessment system based on the perspective of an autonomous driving vehicle, comprising:

[0148] A mechanical simulation construction unit, which is used to construct a mechanical simulation system of the autonomous driving vehicle during driving, including a virtual driving force used to represent the autonomous driving vehicle's own driving force, a virtual risk force affected by the dynamic traffic environment on the autonomous driving vehicle, and a virtual traffic regulation constraint force generated by traffic rules on the autonomous driving vehicle;

[0149] A virtual force system construction unit is configured to construct and obtain a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle according to the mechanical simulation system, including a virtual driving force model, a virtual risk force model and a virtual traffic regulation constraint force model;

[0150] A potential energy calculation unit is constructed to calculate the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, so as to obtain the total potential energy received by the autonomous driving vehicle;

[0151] An action equation construction unit, which is constructed by constructing an action equation of a driving process of a virtual force system centered on an autonomous driving vehicle based on the principle of minimum action;

[0152] An evaluation index construction unit is constructed by constructing a local traffic safety instantaneous evaluation index based on the driving process action amount;

[0153] The evaluation unit is constructed to calculate the absolute value of the driving process action amount to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time for different traffic hazard scenarios, so as to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenarios.

[0154] The third aspect of the present invention discloses an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention.

[0155] The fourth aspect of the present invention further discloses a computer-readable storage medium storing computer instructions. When the computer instructions in the computer-readable storage medium are executed by a computing device, the computing device executes the local traffic safety assessment method based on the perspective of the autonomous driving vehicle disclosed in the first aspect of the present invention, or enables the computing device to implement the functions of the system disclosed in the second aspect of the present invention.

[0156] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0157] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0158] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0159] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A local traffic safety assessment method based on the perspective of an autonomous driving vehicle, characterized in that: The following steps are involved: Construct a mechanical simulation system for autonomous vehicles during driving, including a virtual driving force used to represent the self-driving vehicle, a virtual risk force affected by the dynamic traffic environment, and a virtual traffic constraint force imposed by traffic rules on the autonomous vehicle. According to the mechanical simulation system, a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle is constructed and obtained, including a virtual driving force model, a virtual risk force model and a virtual traffic regulation constraint force model; Based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle is calculated respectively to obtain the total potential energy to which the autonomous driving vehicle is subjected; Based on the principle of minimum action, the driving process action equation of the virtual force system centered on the autonomous driving vehicle is constructed; Based on the driving process action, construct the local traffic safety instantaneous evaluation index; For different traffic hazard scenarios, the absolute value of the driving action on the autonomous driving vehicle and the change process of the local traffic safety instantaneous evaluation index over time are calculated to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenarios.

2. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 1 is characterized in that: in, The driving process action equation of the virtual force system centered on the autonomous driving vehicle is: Where S is the driving action of the autonomous driving vehicle i. Since the virtual force system is centered on the autonomous driving vehicle i, T i = 0, Lagrangian L = T i -U i =-U i , U i Represents the total potential energy of the autonomous vehicle, T i represents the total kinetic energy of the autonomous vehicle, t0, t f They represent the time of starting position and the time of arriving at destination respectively.

3. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 2 is characterized in that: The equation of the local traffic safety instantaneous evaluation index is: D=2-a |S| ; Where a is a constant, and So that when S=0, D=1, and when S<0, D∈[0,1].

4. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 1, characterized in that: in, In the virtual risk force model, the virtual risk force is described by the risk field force of other vehicles on the autonomous driving vehicle. The construction process of the virtual risk force model is: The other car is regarded as the road user relative to the autonomous vehicle, where the autonomous vehicle and the other car are represented by v i and v j The relative speed of the two vehicles is v ji ; Taking the coordinates of the other car as the origin, along the relative speed v of the two cars ji Direction establishes the coordinate axis x j , perpendicular to x j Axis direction establishes the coordinate axis y j , forming x j jy j Coordinate system; Based on the formed coordinate system, construct and obtain the risk field force F of other vehicles to the autonomous driving vehicle ji The formula is: in, In the formula, i represents the autonomous driving vehicle, j represents other vehicles, and M ji V represents the reduced mass of the autonomous vehicle i and other vehicles j; ji represents the velocity term of the two-vehicle system; r′ ji Represents the relative distance between the two vehicles; m i and m j are the masses of the autonomous vehicle i and other vehicle j respectively; v ji represents the relative speed of the two vehicles; is the average speed of the autonomous vehicle i and other vehicles j; r0 is the following distance; r e Represents the unit length, i.e. r e =1m;k x and k y are the longitudinal and transverse gradient coefficients respectively; x′ i and y′ i They are respectively the autonomous vehicle i at x j jy j Coordinates in the coordinate system; r max is the maximum vertical impact range of the risk, r min Represents the minimum vertical impact range of the risk.

5. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 1, characterized in that: in, The virtual driving force includes longitudinal virtual driving force and lateral virtual driving force; In the virtual driving force model, when the autonomous driving vehicle is in a straight-moving state without changing lanes, it is only subjected to the longitudinal virtual driving force. The virtual driving force model is as follows: G i，x =m i g sinθ i，x ; Among them, G i，x is the longitudinal driving force; m i is the mass of autonomous vehicle i; g is the acceleration of gravity; θ i is the angle between the scene matrix and the horizontal plane in the mechanical simulation system; θ i，x Represents the longitudinal angle with the XOY plane during driving. When the autonomous driving vehicle changes lanes, it is subject to longitudinal virtual driving force and lateral virtual driving force respectively. The virtual driving force model is as follows: G i，x =m i g sinθ i ·cosθ i，x G i,y =m i gsinθ i ·sinθ i,y ; Among them, G i,y is the lateral virtual driving force; θ i,y Represents the lateral angle with the XOY plane during driving.

6. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 1, characterized in that: In the virtual traffic regulation constraint model, the longitudinal virtual traffic regulation constraint is described by the road speed limit, and the lateral virtual traffic regulation constraint is described by the road traffic markings; Among them, the longitudinal virtual traffic regulation constraint force is shown as follows: Where v i is the speed of the autonomous vehicle; v l Set speed limits for roads; The lateral virtual traffic regulation constraint force caused by road traffic markings on autonomous driving vehicles is shown in the following formula: Among them, k m is a constant coefficient, take k m =0.1; k y is the lateral gradient adjustment coefficient; E i represents the kinetic energy of car i; y mi represents the lateral distance between the autonomous driving vehicle i and the lane line m. When the vehicle is driving on the center line of the lane, it is not affected by the traffic markings. p Indicates the offset, take Among them l w Represents the width of the lane.

7. The local traffic safety assessment method based on the perspective of an autonomous driving vehicle according to claim 4, characterized in that: in, Based on the virtual risk force model, the virtual risk potential energy generated by the virtual risk force of a single other car on the autonomous driving vehicle The calculation formula is: When there are n other vehicles in the traffic scene, the total virtual risk potential energy U generated for the autonomous driving vehicle is F for: Among them, based on the virtual driving force model, the virtual driving force generates a virtual driving potential energy U G The calculation formula is: Where t e is the unit time; Among them, based on the virtual traffic regulation constraint model, based on the lateral virtual traffic regulation constraint, the virtual traffic regulation constraint potential energy U generated by the virtual traffic regulation constraint on the autonomous driving vehicle R for: Then, in the virtual force system centered on the autonomous driving vehicle, the total potential energy of the autonomous driving vehicle in any scenario is: IN i =U F +U G +U R 。 8. A local traffic safety assessment system based on the perspective of an autonomous driving vehicle, characterized in that: include: A mechanical simulation construction unit, which is used to construct a mechanical simulation system of the autonomous driving vehicle during driving, including a virtual driving force used to represent the autonomous driving vehicle's own driving force, a virtual risk force affected by the dynamic traffic environment on the autonomous driving vehicle, and a virtual traffic regulation constraint force generated by traffic rules on the autonomous driving vehicle; A virtual force system construction unit is configured to construct and obtain a virtual force system of the autonomous driving vehicle in a set multi-vehicle driving scenario based on the perspective of the autonomous driving vehicle according to the mechanical simulation system, including a virtual driving force model, a virtual risk force model and a virtual traffic regulation constraint force model; A potential energy calculation unit is constructed to calculate the potential energy generated by the virtual risk force, the virtual driving force and the virtual traffic regulation constraint force on the autonomous driving vehicle based on the virtual risk force model, the virtual driving force model and the virtual traffic regulation constraint force model, so as to obtain the total potential energy received by the autonomous driving vehicle; An action equation construction unit, which is constructed by constructing an action equation of a driving process of a virtual force system centered on an autonomous driving vehicle based on the principle of minimum action; An evaluation index construction unit is constructed by constructing a local traffic safety instantaneous evaluation index based on the driving process action amount; The evaluation unit is constructed to calculate the absolute value of the driving process action amount to which the autonomous driving vehicle is subjected during driving and the change process of the local traffic safety instantaneous evaluation index over time for different traffic hazard scenarios, so as to evaluate the driving safety of the autonomous driving vehicle in the corresponding traffic hazard scenarios.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the local traffic safety assessment method based on the perspective of an autonomous driving vehicle as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: It stores computer instructions. When the computer instructions in the computer-readable storage medium are executed by a computing device, the computing device executes the method according to any one of claims 1 to 7, or the computing device implements the functions of the system according to claim 8.

Images