CN110298131B - Method for establishing automatic driving lane change decision model in hybrid driving environment - Google Patents

Method for establishing automatic driving lane change decision model in hybrid driving environment Download PDF

Info

Publication number
CN110298131B
CN110298131B CN201910603412.7A CN201910603412A CN110298131B CN 110298131 B CN110298131 B CN 110298131B CN 201910603412 A CN201910603412 A CN 201910603412A CN 110298131 B CN110298131 B CN 110298131B
Authority
CN
China
Prior art keywords
lane
vehicle
strategy
changing
change
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910603412.7A
Other languages
Chinese (zh)
Other versions
CN110298131A (en
Inventor
杨达
沈悦
吴悦竹
文成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN201910603412.7A priority Critical patent/CN110298131B/en
Publication of CN110298131A publication Critical patent/CN110298131A/en
Application granted granted Critical
Publication of CN110298131B publication Critical patent/CN110298131B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

The invention discloses a method for establishing an automatic driving lane changing decision model in a hybrid driving environment, which is used for establishing a multi-step dynamic game lane changing model of an automatic driving vehicle LV and a human driving vehicle RV in the hybrid driving environment and designing a set of nested game algorithm for the automatic driving vehicle. The invention firstly establishes a multi-step dynamic game framework, both vehicles can determine the next action according to the strategy selection of the other vehicle, define the potential conflict points of the lane changing vehicle and the vehicle behind the target lane, and set the starting and stopping condition criteria of the game according to the initial information, the strategy and the game step number of the vehicles, then the two vehicles carry out the dynamic game by using respective strategies and acceleration selection methods until the lane changing stopping condition is met, so that the lane changing space can be manufactured by the game of the vehicles driven by human beings under the condition that the direct lane changing condition is not met by the automatically driven vehicles, and the safe lane changing is realized.

Description

Method for establishing automatic driving lane change decision model in hybrid driving environment
Technical Field
The invention relates to a method for establishing an automatic driving lane change decision model in a hybrid driving environment.
Background
In recent years, the automatic driving technology has received more and more attention worldwide, is considered as an emerging technology capable of subverting traditional traffic, and plays an important role in solving the problems of traffic safety and traffic congestion. However, the transition from a current road with all human-driven vehicles to all autonomous driving is necessarily a long-term process where the traffic environment is a hybrid of human-driven and autonomous vehicles. Autonomous vehicles need to perform safe and efficient driving in a fully autonomous driving environment, as well as to adapt to a hybrid driving environment.
According to the existing research of the automatic driving lane change decision, the content of the lane change decision mainly comprises the following steps: lane change intent generation and evaluation of the lane change environment. When the vehicle is influenced by a preceding vehicle/obstacle during driving or must enter/exit a ramp, the vehicle generates a lane change intention to determine whether the vehicle needs to perform a lane change operation. The lane change environment evaluation is to evaluate the lane change environment of the vehicle after the lane change is determined to be needed, so as to ensure the safety and the high efficiency of the lane change, thereby determining whether the lane change of the vehicle can be carried out. Wei et al believe that the vehicle produces a lane change intent when driving efficiency is the most sought, and select the most efficient control strategy from among vehicle following, lane selection, and scenes based on prediction and a cost function algorithm. The threshold values of the left lane and the right lane are not used in the decision, the strategy cost is not directly counted, and the vehicles preferentially select the left lane switching or overtaking. A Boss simulator in DARPA Urban Chanllenge 2007 is used for testing in a forced lane changing scene, and test results show that the decision-making algorithm is good in lane selection and lane changing results. Similarly, Habenicht et al generates lane change intention when pursuing driving efficiency, establishes a vehicle lane change auxiliary system based on a cost function method of fuzzy logic, makes decisions on operations such as lane non-change, acceleration lane change, deceleration lane change, and direct lane change without changing speed, and provides lane change time, lane change direction, and required acceleration/deceleration. The system is also provided with a module which can not successfully change the lane, and when the system detects that collision exists during lane changing, a warning for giving up lane changing is provided. The system architecture and human-machine interface are described in detail herein, but there is no background description of the evaluation and decision-making algorithms for the zapping scenario. In the research of Kim and the like, a vehicle generates a lane changing intention when avoiding an obstacle, the vehicle utilizes emergency braking and lane changing to realize an obstacle avoiding process, the vehicle generates the lane changing intention to realize obstacle avoidance when decelerating and cannot realize obstacle avoidance, then a scene is evaluated, when determining that an adjacent lane can provide a comfortable lane changing environment, a transverse acceleration is set as a constant, the maximum transverse acceleration which can be accepted by people is used as a comfort judgment standard, and then the obstacle avoidance is realized by executing lane changing. In addition, the Sivaraman and the Trivedi research lane changing intentions generated in the urban vehicle lane changing and lane merging environment, the probability driving graph is used for representing the road environment, and the cost of vehicle mandatory lane changing is calculated by using the dynamic probability graph, so that the vehicle lane changing decision problem is solved. Jula et al set up safety rules for lane change/merge of vehicles, and assume that the speed of the surrounding vehicles is constant, and the lane change vehicle is traveling at a constant speed or constant acceleration, and calculate the longitudinal minimum safe distance at which the lane change vehicle does not collide with the surrounding vehicles. The minimum safe distance is used as a judgment standard for judging whether the lane change of the vehicle is feasible, but the model only considers the condition that the vehicle is not collided and is not suitable for emergency situations such as emergency braking. Kanaris et al have solved Jula et al and have not adapted to the problem of emergency, have proposed a brand-new safe judgement standard, the safety rule is when any one car takes place the emergency braking in lane changing vehicle and surrounding vehicle, and other vehicles can both brake and do not collide. The lane changing vehicle adjusts the acceleration and the speed of the lane changing vehicle, and only when the distance between all vehicles meets the minimum safety distance, the lane changing operation is executed after the lane changing environment meets the safety rules. Wan et al, based on an identifiable environment, studies an algorithm for a decision rule for automatic lane change of a vehicle, estimates and predicts the lane change speed and relative position of the vehicle by using the algorithm, and the rule requires that the vehicle must keep a proper safe distance from surrounding vehicles in the whole lane change process, and also requires that the estimated lane change transverse and longitudinal acceleration meet the vehicle performance requirements. Furda and Vlacic use a Petri network and a multi-target decision model to make real-time decision, and divide a lane changing decision into two continuous stages, wherein the first stage uses Petri to determine whether lane changing is safe and violates traffic rules, the second stage uses the multi-target decision to improve the comfort and efficiency of a vehicle, and the two stages are executed circularly to obtain a driving decision meeting the safety, comfort and efficiency. Chen et al studied the decision of automatically driving vehicles in a complex urban environment, and the decision of changing lanes was used as well, and the rule determined that the operation that could not be executed was deleted first, e.g., the operation of changing lanes to the right was deleted when the vehicle was on the rightmost lane; secondly, deleting the decision which does not comply with the traffic rules; then, an optimal driving decision is selected in consideration of efficiency and safety of driving. The lane changing safety of the vehicle is represented by the distance between the lane changing vehicle and other vehicles around, and the lane changing efficiency is represented by the time reaching the destination, so that the lane changing operation which is safe and accords with the characteristics of a driver is determined. Nie et al proposed a lane change preparation process for an autonomous vehicle in lane change decision-making studies, but did not analyze the lane change preparation process and effects, where the decision-making process for free lane change of an autonomous vehicle was analyzed using NGSIM data vehicle trajectory sets. Introducing a threshold value of the transverse speed of lane changing of the vehicle to identify a starting point of the lane changing of the vehicle, establishing an autonomous lane changing decision model based on a support vector machine classifier, evaluating a gap between front and rear vehicles according to the position and the speed of the vehicle on a target lane, and determining a lane changing execution point and execution time of the vehicle. Mccall et al establish a driver intention inference system based on sparse Bayes, take vehicle state, environmental variables and driver state as system inputs, and use sparse Bayes to calculate the probability of whether the vehicle changes lanes for lane change intention, thereby implementing vehicle lane change decision operation.
The present invention is concerned with the problem of lane changing in a hybrid driving environment for autonomous vehicles. The lane change is used as the basic driving behavior of the automatic driving vehicle, and has important significance on driving safety. How to design a reasonable vehicle lane changing algorithm and ensure the lane changing safety and efficiency of an automatic driving vehicle in actual traffic, particularly in a mixed driving environment, is a very challenging problem.
The Lane change scene of the automatic driving vehicle is shown in fig. 1, and in the Lane change process, there are four related vehicles, including an automatic driving Lane change vehicle LV (Lane-changing vehicle), a front vehicle pv (preceding vehicle) of a current Lane, a front vehicle fv (front vehicle) of a target Lane, and a rear vehicle rv (real vehicle) of the target Lane. This situation is often encountered in actual zapping: due to the fact that the safe lane changing distance is insufficient, in order to achieve lane changing, the RV of the rear vehicle of the target lane needs to be decelerated to create a safe lane changing space for the LV. In this case, the LV would expect the RV to avoid to gain a lane change benefit, however, the RV deceleration would be detrimental to its own benefits, and therefore the RV would be reluctant to select an avoidance. At this time, the benefits of the LV and the benefits of the RV conflict, and a series of games are required for the LV and the RV to finally determine the behavior strategy. In a hybrid driving environment, although the LV is an autonomous vehicle, when the RV is a human-driven vehicle, the LV still needs to dynamically perform its own policy adjustment for policy selection of the RV in real time, thereby improving lane-change safety and success rate. In this case, a lane-change control algorithm specifically designed for the autonomous vehicle is necessary.
At present, although there is a relevant research aiming at the problem, the research cannot adjust the strategy of the vehicle according to the actual strategy selection of human driving vehicles, but only makes an assumption on the behavior of the RV by evaluating the aggressiveness of the RV vehicle, and if the aggressiveness estimation has an error, the LV may change the lane without avoiding the RV, thereby causing a safety hazard.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a method for establishing an automatic driving lane changing decision model in a hybrid driving environment, which is characterized in that a multi-step dynamic game lane changing model of an automatic driving vehicle LV and a human driving vehicle RV in the hybrid driving environment is established by utilizing a game theory-kinematic coupling model method and considering strategy selection and dynamic game processes among vehicles, and a set of nested game algorithm is designed for the automatic driving vehicle. Firstly, a multi-step dynamic game framework is established, vehicles of two parties can determine the next action according to strategy selection of the other party, potential conflict points of the lane changing vehicle and a target lane rear vehicle are defined, starting and stopping condition criteria of a game are formulated according to vehicle initial information, strategies and game steps, benefits of the vehicles involved in the automatic driving lane changing process are considered, and the benefits comprise three aspects of speed benefits, safety benefits and comfort benefits, then, the LV uses a kinematic method to deduce the corresponding benefit values of the vehicles in the automatic driving nested game lane changing framework, and the strategy used by the LV and the corresponding longitudinal acceleration under the strategy are solved; and the RV compares the gains under different strategies at present, and selects the optimal strategy and the corresponding longitudinal acceleration under the strategy. And finally, the two vehicles carry out dynamic game by using respective strategies and acceleration selection methods until the track changing termination condition is met, so that the automatic driving vehicle can manufacture a track changing space through game with a human driving vehicle under the condition that the direct track changing condition is not met, and safe track changing is realized.
The technical scheme adopted by the invention for solving the technical problems is as follows: a method for establishing an automatic driving lane change decision model in a hybrid driving environment comprises the following steps:
step one, LV generates a lane change intention;
step two, judging whether the lane changing game starting condition is met: if yes, entering a third step; if not, judging whether the LV meets a lane change condition: if yes, entering the ninth step, otherwise, waiting for the next generation of a lane change intention, and then entering the first step;
step three, building a dynamic game model by the LV, and calculating earnings of two vehicles;
step four, solving the optimal strategy to be selected by the LV;
step five, judging whether the lane changing game termination condition is met: if yes, entering step ten, and if not, entering step six;
step six, turning on a steering lamp by the LV and performing tentative transverse deviation;
step seven, the LV selects lane changing acceleration;
step eight, judging whether the RV selects avoidance: if not, returning to the third step; if yes, entering the ninth step;
step nine, the LV starts to change the lane until the lane change is finished;
step ten, the LV continues to follow the original lane, and the lane changing intention is finished.
Compared with the prior art, the invention has the following positive effects:
1) the automatic driving lane changing model can enable the LV to actively create a lane changing space through a game, and safe lane changing behaviors can be carried out under the scene that a common automatic driving model cannot carry out lane changing.
2) The automatic driving vehicle makes own strategy selection according to the previous RV strategy in the actual lane changing process, and compared with the existing model, the automatic driving vehicle has higher safety.
3) The lane changing game framework has better integrity and dynamics by respectively thinking the game process from the perspective of the vehicles of the two game parties.
4) The acceleration and strategy selection of the human driving vehicle RV are modeled, the difference between the human vehicle and the automatic driving vehicle in the lane changing game process is distinguished, and the dynamic process of the lane changing game of the automatic driving lane changing vehicle and the human vehicle in the future hybrid driving environment can be predicted more reasonably.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a lane change scenario;
FIG. 2 is a lane-change model framework for an autonomous vehicle;
FIG. 3 is a lane change gaming process for autonomous driving and human driving vehicles;
FIG. 4 is a potential conflict point;
FIG. 5 is a nested game algorithm framework for autopilot;
FIG. 6 is an example solution process;
FIG. 7 is a lane change scene diagram;
FIG. 8 is a boxed graph of conflict time differences at lane change times;
FIG. 9 is a schematic diagram of a conventional model lane change;
FIG. 10 is a schematic diagram of the model lane change;
fig. 11 is a simulation analysis diagram.
Detailed Description
A method for establishing an automatic driving lane change decision model in a hybrid driving environment comprises the following steps:
1. model frame
The invention provides a vehicle lane change model in a manual-automatic hybrid driving environment, and designs a set of complete mechanism for automatically driving a lane change vehicle so as to complete a lane change game process with human vehicles. As shown in fig. 2, first, the lane-change vehicle LV generates a lane-change intention; then, the lane changing vehicle LV judges whether a game relation exists between the two vehicles according to the position and speed information of the lane changing vehicle LV and the position and speed information of the rear vehicle RV of the target lane, and if the lane changing condition can be met by the LV under the condition that the game starting condition is not met, the lane changing can be executed by the LV; secondly, aiming at the condition that the game starting condition is met, the LV starts an automatic driving nested lane-changing game algorithm, a dynamic game model frame of the LV and the RV is firstly established, the whole game process is simulated through a general rule in the driving process of a human vehicle, the income of each stage of the LV and RV game is predicted, and the strategy of the current stage of the LV is solved; and finally, according to the strategy selection of the RV, the LV and the RV perform multiple dynamic games until the game termination condition is met.
2. Lane changing game analysis
(1) Multi-step dynamic lane-change game
According to the lane changing game method and the lane changing game system, a game in the lane changing process of the vehicles in the human driving environment and the characteristics of the automatic driving vehicles are analyzed, a model of a complete lane changing dynamic game between the automatic driving vehicles and the human driving vehicles in the manual-automatic hybrid driving environment is established, and the dynamic process of the lane changing game between the human driving vehicles and the automatic driving vehicles in the future manual-automatic hybrid driving environment can be reflected.
The analysis of the hand-automatic driving vehicle lane changing game process is shown in fig. 3, in the figure, a lane changing vehicle LV is an automatic driving vehicle, a rear vehicle RV of a target lane is a human driving vehicle, the lane changing vehicle LV can generate a lane changing intention before lane changing starts, and the target lane and a target gap are determined. And then under the condition that the lane changing vehicle LV judges that the lane changing game condition is met, the lane changing vehicle LV plays a game with the rear vehicle RV of the target lane, the lane changing vehicle LV performs strategy selection, if lane changing is selected, a turn lamp is turned on and transverse displacement is used for probing, if lane changing is not performed, the rear vehicle RV of the target lane continues to drive the front vehicle FV of the target lane, and the game is ended. Then, when the target lane rear vehicle RV observes the LV selection lane change strategy, the gains of the next strategy of the target lane rear vehicle RV are compared, and strategy selection is performed. Similarly, when the lane changing vehicle LV observes that the vehicle RV behind the target lane selects an avoidance strategy, the lane changing vehicle LV selects the lane changing, the two vehicles reach the same, the lane changing vehicle LV can cooperatively change the lane, and the game is ended. And if the RV of the rear vehicle of the target lane selects a non-avoidance strategy, the game of the two vehicles continues. When the number of steps of the lane changing vehicle LV game reaches the set number, the automatic driving vehicle is subjected to game again, so that a large risk exists, the lane changing vehicle LV actively exits the game, namely when the vehicle behind the target lane selects the avoidance-free strategy again, the lane changing vehicle LV directly selects the lane-free strategy.
(2) Potential conflict point
The game between the vehicles LV and RV in lane change decision is generated because there is a spatial conflict between the two vehicles. As shown in fig. 4, the driving curve of the LV lane change and the driving route of the RV continuing straight will meet at a certain point on the target lane, which is defined as the potential conflict point of the two vehicles. Assuming that the LV makes a lane change immediately after the lane change intention is generated and the RV travels forward at the current speed and the selected acceleration, a Difference between times at which the two vehicles reach the potential conflict point is defined as a Time Difference of conflict (TDTC), and the smaller the Difference of conflict Time means the lower the lane change safety of the two vehicles. When the time difference of reaching the potential conflict point reaches a certain threshold value, the two vehicles need to play a game, so that the final driving strategy, such as whether the LV needs to change the lane or not and whether the RV needs to avoid or not, is determined. Therefore, the potential conflict points of the LV and RV need to be calculated first.
Let the coordinates of the potential conflict point be (x)c,yc) Wherein, ycThe calculation formula of (a) is as follows:
yc＝ye-wcar (1)
wherein, yeFor the ordinate, w, of the end point of the track-changing curvecarIndicating the width of the vehicle.
Assuming that the vehicle is normally running along the center of the lane, yeCan be directly acquired. So at ycWhen known, xcIs obtained by the track changing curve function of the automatic driving vehicle. The most common polynomial curve for the lane change trajectory curve of an autonomous vehicle is shown in the following formula,
y(x)＝a0+a1x+a2x2+a3x3 (2)
wherein x and y are the transverse and longitudinal positions of the left end of the LV head, a0，a1，a2，a3Are all parameters to be determined.
A in formula (2)0，a1，a2，a3Is the unknown quantity of the track-changing trajectory curve equation and needs to be solved. The trajectory equation is designed by taking a lane-changing vehicle as a main body, so that a coordinate system used by the trajectory equation in the text takes the left end of the LV headstock as a coordinate origin. After derivation and solving the unknown parameters in the above formula, the track-changing trajectory equation in this document is as follows,
Figure BDA0002120026760000091
wherein x and y are the transverse and longitudinal positions of the left end of the LV head, and xeAnd yeThe lateral and longitudinal coordinates of the end of the track switch track (ending).
Will ycBy substituting the value of (c) into the above trajectory curve equation (3), the abscissa x of the potential conflict point can be obtainedcThe location of the potential conflict point may eventually be obtained.
(3) Lane change game start-stop condition
1) Lane change game start condition
In the lane changing process of the vehicles, not all lane changing vehicles and the vehicles behind the target lane are required to play games. The lane changing game has two conditions, wherein the first condition is that the lane changing vehicle keeps a safe distance with the front vehicle of the current lane, and the second condition is that the conflict time difference between the lane changing vehicle and the rear vehicle of the target lane does not exceed a certain threshold value. The first condition is to ensure safety with the PV during the lane change, and the second condition states that there is a conflict between the LV and the RV if the lane change is performed directly.
The safe distance calculation of the vehicle LV from the PV uses the classic Gipps safe distance formula, as shown below,
Figure BDA0002120026760000092
wherein G islFor the safe distance, x, of the lane-changing vehicle LV from the vehicle PV ahead of the current lanel(t) the LV position, x, of the lane-changing vehicle at time tp(t) the PV position of the front vehicle of the current lane at time t,/pThe length of the body of the vehicle PV ahead of the current lane, blMaximum deceleration of LV, τlReaction time of LV, vl(t) the velocity at time LV, vp(t) is the velocity at time PV.
Calculating the difference in collision time between the LV and RV requires calculating the time to reach the potential conflict point for both vehicles separately. The distance traveled by the LV in the process of reaching the potential conflict point from the lane change starting point is the arc length of the trajectory curve equation, and the calculation formula is as follows,
Figure BDA0002120026760000101
wherein L islFor the distance the LV traveled from the current position lane to the potential conflict point,
the distance the RV travels from the current location to the potential conflict point is,
Lr＝xc+d (6)
wherein L isrRepresents the distance traveled by the RV from the current position to the potential conflict point, xcRepresents the longitudinal distance of the lane change vehicle's front left corner from the potential conflict point, and d represents the locomotive separation of the LV from the RV in the longitudinal direction.
Therefore, the game conditions for the LV and RV are as follows,
Figure BDA0002120026760000102
wherein, TMThe critical conflict time difference of the two cars for playing games is shown, and is also the critical point that the RV influences the LV lane change safety, vr(t) and vl(t) represents the velocity of the RV and LV at the current time t, respectively.
2) Lane change game termination condition
In the lane changing game process of the automatic driving vehicle and the human driving vehicle, potential safety hazards exist in both vehicles, the more the game times are, the larger the potential safety hazards caused by the game times are, and the driving efficiency of both vehicles can be influenced. The need for setting the game termination condition is also a non-negligible problem.
In the normal lane changing game process, only one of the two vehicles chooses to yield, if the lane changing vehicle LV chooses not to change the lane and the rear vehicle RV of the target lane chooses to yield, the lane changing game is terminated at the moment, and the other vehicle chooses not to yield. Therefore, one of the game termination conditions is that one of the two parties of the game gives way to actively quit the game.
In addition, the automatic driving vehicle is controlled by a computer and is not as flexible as a human driving vehicle, so strict conditions are required to be set to ensure the safety of the automatic driving vehicle in the lane changing game process with the human driving vehicle. In the invention, the lane change termination condition for the automatic driving lane change vehicle is as follows:
a. when the game steps of the automatic driving lane changing vehicle LV reach n times (the times can be adjusted along with different lane changing scenes), if the human driving vehicle RV does not avoid, the automatic driving vehicle actively exits the game.
b. When the automatic driving vehicle LV and the vehicle PV in front of the current lane do not satisfy the safe following condition in the formula (4) in the lane changing process, the automatic driving vehicle LV should give up the lane changing actively and search for the next lane changing opportunity.
(4) Lane changing game element and type
1) Lane changing game element
In the game model, three essential elements which need to be specified are game objects, strategies and benefits respectively. The three elements of the lane-change game herein are as follows,
a. game object: an automatic driving lane-changing vehicle LV and a manual driving target lane rear vehicle RV.
b. Strategy: the lane changing vehicle LV has two strategies of lane changing and lane non-changing in the game, and the rear vehicle RV of the target lane has two strategies of avoidance and non-avoidance. When the LV selects a lane change strategy, the LV can move to a target lane from the center line of the current lane to complete a lane change process; when the LV selects a non-lane change strategy, the LV needs to give up lane change temporarily and continue to drive in the current lane to search the next lane change opportunity. When the RV selects an avoidance strategy, the RV can actively create a lane changing condition for the LV and complete lane changing in cooperation with the LV; when the RV selects a non-avoidance strategy, the lane change behavior of the LV can be prevented.
c. And (4) yield: when the LV and the RV carry out the lane changing game, three income indexes are adopted when the strategy is evaluated, namely speed income, safety income and comfort income.
2) Lane changing game type
The lane changing game type is determined according to the information and the action sequence of the two sides of the game. First, the autonomous vehicle can have a relatively clear view of the benefits and strategies of its own and its counterpart vehicles. The human vehicle can only know partial information and can not make a relatively clear judgment on the income of the opposite party, so that the game is an incomplete information game; secondly, in the manual and automatic lane changing game process, communication does not exist among vehicles, and after lane changing vehicles LV generate lane changing intentions, RV needs to judge the strategy of LV and then make the next reaction. The game is a multi-step dynamic game because the driver and the vehicles have reaction time, the two vehicles decide to have a precedence order, and the game is terminated only when one vehicle actively exits the game.
3. Revenue analysis
In the lane changing process, the lane changing vehicle LV changes lanes in order to pursue higher benefits, and the lane changing behavior of the lane changing vehicle LV affects the normal running of the rear vehicle RV of the target lane, so that the benefits of the RV are damaged, and the lane changing vehicle LV and the rear vehicle RV of the target lane are also the root cause of the conflict. Therefore, the benefits of the lane change vehicle LV and the target lane rear vehicle RV in the lane change process need to be analyzed, and the benefits of the vehicle in the lane change process include speed benefits, safety benefits and comfort benefits, which are shown in the following specific cases.
(1) Speed gain
1) Speed gain of lane-change vehicle LV
The reason for the lane change of the lane change vehicle LV is that a higher speed gain is obtained by reaching the target lane by the lane change, so the speed gain is an indispensable gain index for the LV.
a. Without changing the track
When the lane changing vehicle LV selects the strategy of not changing lanes, the vehicle continuously follows the vehicle PV in front of the current lane, the speed of the LV is restricted by the PV, so that the difference between the speed of the PV and the speed of the LV is the speed gain under the strategy of not changing lanes of the LV, as shown in the following formula:
Figure BDA0002120026760000121
wherein the content of the first and second substances,
Figure BDA0002120026760000122
indicates the velocity gain, v, of the LV under a no-lane-change strategyp(t) represents the velocity of the PV at time t, vl(t) represents the velocity of the LV at time t.
b. Situation of changing lanes
When the lane change strategy is selected by the lane change vehicle LV, the vehicle that the LV expects to follow is the front vehicle FV of the target lane, so the speed of the FV is the expected speed of the LV, and the difference between the speed of the FV and the speed of the LV is the speed gain under the lane change strategy, as shown in the following formula:
Figure BDA0002120026760000131
wherein the content of the first and second substances,
Figure BDA0002120026760000132
indicates the velocity gain, v, of the LV under the lane-change strategyf(t) velocity of FV at time t, vl(t) represents the velocity of the LV at time t.
2) Speed gain of rear vehicle RV of target lane
The speed gain is an important index selected by the RV strategy of a rear vehicle of a target lane, the RV can adopt the strategy to prevent the LV from changing the lane, the main reason is that the LV needs deceleration cooperation of the RV to change the lane, normal running of the RV is interfered, the RV vehicle has avoidance strategies and non-avoidance strategies, and the speed gain of the RV under the two strategies is analyzed.
a. Avoidance situation
Assuming that the lane change vehicle LV performs lane change immediately, the RV has an expected avoidance speed under an avoidance strategy, and the RV can just ensure the safety of the LV lane change by using the speed to continue running. The expected escape velocity of the RV should satisfy the following equation,
Figure BDA0002120026760000133
wherein the content of the first and second substances,
Figure BDA0002120026760000134
representing the expected avoidance velocity, T, of the RVlIndicating the travel time of the LV to the potential conflict point for performing a lane change from the current position.
The expected speed under the RV avoidance strategy can be found from equation (10):
Figure BDA0002120026760000135
wherein T islIs derived as follows, assuming that the LV vehicle is at a speed v at time tl(t) and acceleration al(t) making a lane change, the LV is at a distance L from the potential conflict point on the predicted lane change execution tracklSatisfies the following formula:
Figure BDA0002120026760000136
wherein v isl(t) represents the velocity of LV at time t, al(t) represents acceleration of LV selection. T isl(t) represents the time required for the LV to reach the potential conflict point.
The time T required for the LV to reach the potential conflict point can be obtained by the derivation of the formulal(t) tableThe expression is as follows:
Figure BDA0002120026760000141
the difference between the expected avoidance speed of the RV vehicle and the RV speed is the speed gain under the RV avoidance strategy, which is shown as the following formula:
Figure BDA0002120026760000142
wherein the content of the first and second substances,
Figure BDA0002120026760000143
and representing the speed gain under the RV avoidance strategy.
b. Not avoiding situation
Under the strategy that the RV behind the target lane selects no avoidance, the RV can continue to drive the front vehicle FV of the target lane, and the speed difference between the front vehicle FV and the RV of the target lane is the speed gain of the RV under the strategy of no avoidance, as shown in the following formula:
Figure BDA0002120026760000144
wherein the content of the first and second substances,
Figure BDA0002120026760000145
and representing the speed gain under the RV non-avoidance strategy.
(2) Comfort benefits
Comfort is also an important factor to consider for an autonomous vehicle, and the driving comfort is affected by the variation range of the vehicle acceleration during the running of the vehicle. The change in acceleration between adjacent steps is used herein to describe the comfort benefit of the vehicle, as shown in the following equation:
Figure BDA0002120026760000146
wherein the content of the first and second substances,
Figure BDA0002120026760000147
indicating a comfort benefit of the LV, al(t- λ) represents the acceleration of the previous step length LV.
Like the LV vehicle, the comfort benefit of the RV vehicle is also expressed in terms of the difference between the accelerations of adjacent steps, as shown in the following equation:
Figure BDA0002120026760000148
wherein the content of the first and second substances,
Figure BDA0002120026760000149
shows the comfort gain of RV, ar(t- λ) represents the acceleration of the previous step RV.
(3) Safety benefits
Vehicle safety is a critical factor in a hybrid driving environment, and the safety gains of the LV and RV during a lane change will be elaborated upon below.
The safety gains of two vehicles can be calculated by the conflict time difference. Suppose RV is at velocity vr(t) and acceleration ar(T) forward driving, if RV reaches potential conflict point from current position for driving time Tr(t), then RV travels to the distance L of the potential conflict pointrComprises the following steps:
Figure BDA0002120026760000151
t can be derived from the formula (18)rThe expression of (a) is as follows,
Figure BDA0002120026760000152
wherein, Tr(t) represents the travel time of the RV from the current position to the potential conflict point.
Time T for LV to reach potential conflict pointl(t) isEquation (13), the collision time difference between the RV vehicle and the LV vehicle is shown as follows:
ΔT＝Tr(t)-Tl(t) (20)
where Δ T represents a collision time difference between the vehicle RV behind the target lane and the lane change vehicle LV.
When Δ T >0, it indicates that the LV reached the potential conflict point before the RV, and when Δ T <0, it indicates that the RV reached the potential conflict point before the LV.
1) LV safety benefits
LV lane change
The safety gains when the LV selects the lane change strategy are related to the conflict time difference Δ T. In view of the importance of safety to autonomous vehicles, the range of values for the safety gain function is not limited to the range of-1 to 1, as is the speed gain and comfort gain, when the safety gain function is designed. When Δ T<At 0, the LV reaches the conflict point after the RV, and at this time, there is a great safety hazard in the lane change behavior, and the safety gain of the LV in this case is regarded as negative infinity. When Δ T>At 0, at this time, the collision time difference when the LV reaches the conflict point before the RV and the safety gain are not in a linear relationship, and as the collision time difference Δ T increases, the safety gain also increases, but the increasing rate gradually decreases; when the value of Δ T continues to increase to the safety critical point TMAnd meanwhile, the safety gain reaches the maximum, the gain value is 0, and then the safety gain is kept stable. Since the two cars do not have a conflict relationship before the lane changing game occurs, the driving state is safe, the safety profit cannot be positive, and the maximum value of the safety profit is 0. This process can be described as a logarithmic function, then the expression for the security benefits is as follows,
Figure BDA0002120026760000161
wherein the content of the first and second substances,
Figure BDA0002120026760000162
indicating the safety gains in the LV in selecting the lane-change strategy.
b LV changing lane
Under the condition that the LV does not change lanes, the two vehicles do not have conflict relation, potential safety hazards do not exist, the safety of the LV is not affected, and therefore the safety income of the LV is still kept at the maximum value.
Figure BDA0002120026760000163
Wherein the content of the first and second substances,
Figure BDA0002120026760000164
indicating the safety gains of the LV in choosing a no-change strategy.
2) RV safety gain
LV lane change RV non-avoidance
When the LV is changed, the safety gain of the RV adopting a non-avoidance strategy is also related to delta T. Delta T>And when 0, the RV reaches a potential conflict point after the LV, and the continuous selection of the non-avoidance strategy under the condition has great potential safety hazard, so the safety gain of the RV is negative infinite under the condition. When Δ T<0, when the RV reaches the potential conflict point before the LV. The safety benefit of RV at this time is that as Δ T decreases, the safety is higher and the rate gradually decreases. When Δ T reaches-TMThen, the safety gain reaches the highest, and then the safety gain is kept stable. The expression of the security benefits is as follows,
Figure BDA0002120026760000171
wherein the content of the first and second substances,
Figure BDA0002120026760000172
and when the LV is changed, the RV selects the safety gain of the non-avoidance strategy.
LV lane changing RV avoidance
When the LV is changed, the safety gain of the RV adopting the avoidance strategy is opposite to the formula. Delta T<When 0, the RV adopts the avoidance strategy and still reaches the potential conflict point before the LV, and under the condition, the RV selects the avoidance strategy unreasonably and is also unsafe, so that the safe yield of the RV is negative infinityIs large. Delta T>At 0, the RV reaches a potential conflict point after the LV, where the safety benefit of the RV increases with Δ T, the higher the safety. When Δ T reaches TMThe security gains are then maximized. As will be shown below, in the following,
Figure BDA0002120026760000173
wherein the content of the first and second substances,
Figure BDA0002120026760000174
and when the LV is changed, the RV selects the safety gain of the avoidance strategy.
LV do not change lanes
In the case of an LV that is not being rerouted, the safety of the RV is likewise unaffected, so the safety gains of the RV remain at a maximum.
Figure BDA0002120026760000175
Wherein the content of the first and second substances,
Figure BDA0002120026760000176
indicating the safety benefit of the RV when the LV is not rerouting.
(4) Total profit
After the speed, safety and comfort benefits of the LV and RV are determined, the total vehicle benefit is then calculated from these three benefits. The LV and RV total profit expressions are shown below,
Figure BDA0002120026760000177
wherein the content of the first and second substances,
Figure BDA0002120026760000181
the velocity gain of the LV is represented,
Figure BDA0002120026760000182
indicating the safety benefits of the LV in the area,
Figure BDA0002120026760000183
indicates the comfort benefit of LV, α1，β1，γ1The weights between the three benefits of the LV are respectively represented, and f (×) represents a function normalized for each benefit.
Figure BDA0002120026760000184
Wherein the content of the first and second substances,
Figure BDA0002120026760000185
the speed gain of the RV is expressed,
Figure BDA0002120026760000186
the safety gain of the RV is represented,
Figure BDA0002120026760000187
representing the comfort benefit, α, of RV2，β2，γ2And delta represents a random number of benefits of the human-driven vehicle RV.
4. Model solution
The final solution in the invention comprises two parts of final strategy and acceleration selection. Firstly, the LV and the RV respectively calculate the vehicle acceleration corresponding to the four strategy combinations, then the total profit value of the LV and the RV under the four strategy combinations is determined through the acceleration, and finally the final strategy of each of the two vehicles and the acceleration of the two vehicles under the strategy combination are obtained through the profit matrix.
(1) Acceleration selection
1) Lane change vehicle acceleration selection
The lane change vehicle LV is not only influenced by the RV vehicle when the acceleration is selected, but also has a relationship with both the PV and FV vehicles, and because the conflict between the lane change vehicle LV and the RV of the rear vehicle of the target lane is mainly researched, only the influence of the RV on the LV is considered in the LV safety income, the acceleration cannot be calculated through the income value. Therefore, LV calculates the gain after calculating the selected acceleration under the two strategies of lane change and lane non-change. The following describes the acceleration selection of the lane-change vehicle LV under both lane-change and lane-not-change strategies.
LV lane selection switch strategy
Under the track changing strategy, the longitudinal acceleration selection of the LV is simultaneously influenced by two vehicles, namely the FV and the RV, and when the LV selects the track changing strategy and prepares for changing tracks, the safety between the LV and the vehicles, namely the FV and the RV, is ensured at the same time. A lane change acceleration model based on the expected headway is introduced, the model considers that the selection of the LV acceleration in the lane change process is the process that the LV seeks to keep the expected headway with the vehicle FV and RV, and the acceleration is determined by the difference between the real headway and the expected headway of the LV and the FV and the RV. The model expression is as follows:
Figure BDA0002120026760000191
Figure BDA0002120026760000192
Figure BDA0002120026760000193
wherein the content of the first and second substances,
Figure BDA0002120026760000194
representing acceleration of the LV under a lane-change strategy, hf(t) represents the time headway of LV and FV at time t, hr(t) represents the headway of LV to RV at time t,
Figure BDA0002120026760000195
representing the driver's desired FV at time t from the LV lead time,
Figure BDA0002120026760000196
representing the time interval of RV and LV expected by a driver at t moment, and k represents the time interval of the lane change vehicle to the vehicle ahead of the target lane in the total accelerationDegree of consideration, a1，b1，c1，a2，b2，c2Is a parameter.
LV selection lane change-free strategy
When the lane changing vehicle LV selects a lane changing strategy, namely when the LV runs on the PV before the original lane continues to follow, the vehicles LV and the PV keep a safe distance in the following process, and the distance can ensure that the LV and the PV do not have rear-end collision accidents when the PV performs emergency braking. Therefore, Gipps' safe distance rule was introduced to calculate acceleration. According to the Gipps model, the safe following speed that the LV needs to maintain in order not to collide with the PV is as follows:
Figure BDA0002120026760000197
wherein the content of the first and second substances,
Figure BDA0002120026760000198
is the longitudinal safe speed of the LV vehicle relative to the vehicle PV, bpAnd blIs the respective maximum braking acceleration of the vehicles PV and LV. x is the number ofl(t) is the longitudinal position of the lane-change vehicle LV at time t, xp(t) is the longitudinal position of the leading car PV at time t, τ is the reaction time.
Then the acceleration of the LV under the lane-change-free strategy is shown as follows:
Figure BDA0002120026760000199
wherein the content of the first and second substances,
Figure BDA00021200267600001910
indicating the acceleration that the LV will select under the no-lane-change strategy.
2) Target lane rear vehicle acceleration selection
RV selection avoidance strategy
The expected avoidance velocity of the acceleration under the avoidance strategy of the RV vehicle can be obtained by the formula (11)
Figure BDA0002120026760000201
And (4) obtaining. Starting from the moment when the RV vehicle selects the avoidance strategy, the RV vehicle needs to ensure that the avoidance strategy is not more than
Figure BDA0002120026760000202
The average speed of the game is driven to the potential conflict point, so that the safety of the vehicles of the two parties of the game can be ensured. The RV reaches the potential collision point at a rate,
Figure BDA0002120026760000203
in the formula (I), the compound is shown in the specification,
Figure BDA0002120026760000204
representing the speed, v, of the RV vehicle to a potential conflict pointr(t) represents the speed of the RV vehicle at time t,
Figure BDA0002120026760000205
representing the expected escape velocity of the RV.
Therefore, through a kinematic formula, the avoidance acceleration of the RV vehicle under an avoidance strategy is shown as the following formula,
Figure BDA0002120026760000206
in the formula (I), the compound is shown in the specification,
Figure BDA0002120026760000207
representing the avoidance acceleration, L, of the RVrRepresenting the distance of the RV from the potential conflict point.
RV selection non-avoidance strategy
When the RV vehicle adopts a non-avoidance strategy, the RV vehicle continues to drive with the front vehicle FV, a safe distance is kept between the RV vehicle and the front vehicle in the following process, and the safe following speed which needs to be kept by the RV is solved according to a Gipps model:
Figure BDA0002120026760000208
wherein the content of the first and second substances,
Figure BDA0002120026760000209
is the longitudinal safe speed of the RV vehicle relative to the vehicle FV, brAnd bfIs the respective maximum braking acceleration of the vehicles RV and FV. x is the number ofr(t) is the longitudinal position of the lane-change vehicle RV at time t, xf(t) is the longitudinal position of the preceding vehicle FV at time t.
The acceleration of the RV under the no-avoidance strategy is shown as follows,
Figure BDA00021200267600002010
wherein the content of the first and second substances,
Figure BDA00021200267600002011
and representing the acceleration of the RV under the avoidance strategy.
(2) Autonomous vehicle strategy selection
After the acceleration selection models under the strategies of the lane changing vehicle LV and the target lane rear vehicle RV are completed, the strategy selection problem of the automatic driving vehicle in the lane changing becomes a key problem to be solved.
In the invention, the automatic driving vehicle firstly constructs an automatic driving vehicle nested lane changing game framework which can reflect the lane changing game process between the automatic driving vehicle LV and the human driving vehicle RV. Then, the automatic driving vehicle simulates the game process of the two vehicles by using the acceleration selection algorithm of the lane changing vehicle LV and the target lane rear vehicle RV, so that vehicle information of each game stage in the automatic driving vehicle embedded lane changing game frame is obtained, and the total income of the vehicles of both sides in each game stage in the future is predicted. And finally, the automatic driving vehicle obtains the optimal strategy which is selected at the current stage by utilizing the two-vehicle income in the nested lane-changing game framework through a reverse induction method. The specific process is shown in fig. 5.
The process of solving the optimal strategy by the LV inverse induction method of the automatic driving lane changing vehicle is described in detail below. Fig. 6 simulates the game process between an autonomous vehicle LV and a human-driven vehicle RV, and for ease of explanation of the algorithm, the vehicle gains are given in specific values at various stages of the game.
When the RV selects the non-avoidance strategy at STEP2, the LV is taken as an automatic driving vehicle at STEP3, yield is made actively, the non-lane-changing strategy is selected, and the yield of the LV is 3 at the moment. When the LV selects the lane change strategy at STEP2, the gain of the LV selecting the lane change strategy at STEP2 is 3, and the gain of the LV selecting the lane change strategy at STEP2 is 5, considering that the RV vehicle selects the non-avoidance strategy which makes the STEP2 gain larger, so the strategy at STEP2 is the lane change-free strategy, and the gain is 5. Similarly, when the LV selects the lane-change strategy at STEP1, the benefit of the LV selecting the lane-change strategy at STEP1 is to consider that the RV vehicle will select the non-avoidance strategy that makes its benefit greater at STEP 1: when the RV chooses not to avoid at STEP2, the LV strategy and gain at STEP2 (i.e. LV does not switch channels, gain is 5). The LV elects the no-lane-change strategy at STEP1 with a profit of 2, so the final strategy for the LV is to elect no-lane-change at STEP 2. The autonomous vehicle LV predicts that it will fail to change lanes in this lane change game, so the optimal strategy for the autonomous vehicle is not to change lanes.
(3) Human-driven vehicle strategy selection
The human-driven vehicle is different from the automatic-driven vehicle, and the automatic-driven vehicle can simulate the whole lane-changing game process by modeling the general rule of the driving behavior of the human-driven vehicle and by a lane-changing nested game algorithm, so that the optimal strategy of the automatic-driven vehicle is selected. When the human driving vehicle selects the strategy, the profits of the strategy to be selected in the current stage of the game are only compared, and the strategy with larger profits is selected from the profits.
5. Simulation verification of technical effects
First, a simulation scenario is introduced. Then, the model is compared with the existing model, the difference between the two models is explained, the safety of the model is subjected to simulation analysis, and the model is verified to have enough safety. And finally, simulation analysis is carried out on the model, and the model is statistically analyzed for the conflict time difference, the lane changing success rate, the game times and the strategy acceleration under various scenes, so that the rationality of the model is verified.
(1) Simulation scenario
Before the model is simulated, a scene needs to be constructed, as shown in fig. 7, a lane changing vehicle LV is an automatic driving vehicle, and a rear vehicle RV of a target lane is a human driving vehicle. Assuming that the highest speed limit of a current lane is 100km/h, the highest speed limit of a target lane is 120km/h, the initial state of a vehicle is constant-speed driving, the LV initial speed is 90km/h, the RV initial speed is 110km/h, the PV initial speed is 90km/h, the FV initial speed is 120km/h, the x-axis coordinate corresponding to the RV initial position is 0m, the x-axis coordinate corresponding to the PV and FV initial positions is 120m, and different lane changing scenes are simulated through the change of the LV initial position. The speed gain weight α for LV and RV vehicles is 0.3, the safety gain weight β is 0.5, and the comfort gain weight γ is 0.2. Critical safety conflict time difference TM＝3s。
(2) Model comparison
In the existing research of the opponent-automatic hybrid driving lane changing environment, the model cannot reflect the actual lane changing game process of the human vehicle RV and the automatic driving vehicle LV, and the game theory idea is combined in the automatic driving strategy selection algorithm of the LV, so that the strategy selection process of the RV is predicted. In the actual lane changing game process, the strategy of the RV vehicle is not considered at all by the LV, and the value of the income is calculated only by calculating the aggressiveness of the previous step of the RV and introducing the aggressiveness as a parameter into the strategy selection model of the automatic driving vehicle. Although the method is likely to be more accurate in the judgment of the human vehicle income value, because the human vehicle has great randomness and the aggressiveness is only used as a parameter of a vehicle income function, under the condition that the estimated aggressiveness of the human is estimated to have an error or under the control of other income, the LV is likely to change the road under the condition that the human vehicle does not make an avoidance, thereby causing the potential safety hazard.
The lane changing game process of the automatic driving vehicle and the human vehicle is deeply analyzed, and a multi-step dynamic game framework of the LV and the RV is established for the RV. The framework embodies the strategy selection process of the LV and the RV in the actual lane changing game. The automatic driving vehicle and the human vehicle can make self strategy selection according to the strategy selected by the other vehicle in one step, the lane changing game can be ended only under the condition that one vehicle gives way, the other vehicle can directly select the strategy which does not give way, and in addition, the strategy which does not give way before the vehicle judges that the game is ended is tentative. Therefore, the automatic driving vehicle in the model can select whether to directly change lanes or continue the game according to the strategy of the human vehicle in the last step, and the safety is higher.
The following is a simulation analysis of the security of the model and the existing models. The safety is analyzed by adopting the conflict time difference between the LV and the RV at the lane changing time, 100 times of simulation is respectively carried out on different lane changing scenes, and finally, the conflict time difference between the two model lane changing times is counted, and a box-shaped graph is drawn as shown in fig. 8. As can be seen from FIG. 8, the upper edge, the upper quartile and the median of the existing model and the model herein are all relatively close and are all larger than the critical collision time difference TM. However, the lower edge and the lower quartile of the existing model are both between 0 and 1s, which indicates that if the LV switches lanes at this time, two vehicles almost reach the potential conflict point at the same time, and the RV does not make an avoidance behavior, but the strategy of the LV in the existing model is determined as direct lane switching. And the lower edge of the model is slightly lower than 3s, and the lower quartile is at the position of 4s, which shows that the safety of both vehicles can be ensured at the moment of LV lane change selection.
The lane change of the two models corresponding to the edge collision time difference under the box chart is shown in fig. 9 and 10. Fig. 9 shows that when the LV changes lanes, the RV does not make an avoidance strategy, the time difference between two vehicles conflict is very small, and when the LV reaches a potential conflict point, the following distance of the RV is very small, so that two vehicles have relatively large potential safety hazards. In fig. 10, after the LV judges that the RV selects an avoidance strategy, a lane change behavior is selected, so that the time difference between two vehicle conflicts is large, and the RV and the LV keep a relatively safe following distance from the lane change time to the lane change end. Therefore, the model has higher safety.
(3) Model analysis
Selecting 15 different lane changing scenes in the LV initial positions 0-80m, simulating each lane changing scene for 100 times, outputting related data including conflict time difference between game starting time and the lane changing time, a lane changing success rate, game times and strategy acceleration, and drawing a simulation analysis chart as shown in FIG. 11. Fig. 11(a) reflects the collision time differences of the game start time and the lane change times LV and RV, and it can be seen that the collision time differences at the game start time are all very small, and if the lane is directly changed, there is a great potential safety hazard. After the game is finished, the conflict time difference of the lane changing time is much higher than the game starting time, and the selected lane changing behavior is safe after the LV passes through the game. Fig. 11(b) and 11(c) reflect the relationship between the change in LV initial position and the lane change success rate and the number of games, respectively. When the initial position of the LV is between 0 and 20m, the distance between the two vehicles is very close, the lane changing success rate is 0 percent, the vehicle game times are all 1 time, and the LV actively selects a lane changing-free strategy in the primary game. When the initial position of the LV is between 20 and 60m, the lane changing success rate of the LV is about 80%, and the situation that a small part of games are carried out for 2 times also occurs, so that the LV selects a lane changing strategy in the first games under the lane changing scenes, and the RV is a human vehicle, so that the LV cannot be avoided under the influence of random factors in some situations, and the LV lane changing failure is caused. When the initial position of the LV is between 60 and 80m, the lane changing success rate of the LV is about 100 percent, the game times are 1 time and 2 times, and the minimum part of the game times is 3 times and 4 times, which shows that the LV has larger lane changing space along with the increasing distance between the LV and the RV when the game starts, so that the LV has more and more advantages in the game, the LV can play games for more times, and the lane changing success rate of the LV is greatly improved. FIG. 11(d) reflects the relationship between the change in LV home position and the strategic acceleration of the first game of two cars. The LV lane changing acceleration shows a gradually rising trend, the LV lane changing-free acceleration shows a descending trend along with the reduction of the distance between the LV and the PV, the RV avoidance acceleration shows a rising trend along with the increase of the distance between the LV and the RV, and the RV avoidance acceleration is related to the distance between the RV and the FV, so that the trend is not changed.

Claims (4)

1. A method for establishing an automatic driving lane change decision model in a hybrid driving environment is characterized by comprising the following steps: the method comprises the following steps:
step one, a lane changing vehicle LV generates a lane changing intention;
step two, judging whether the lane changing game starting condition is met: if yes, entering a third step; if not, judging whether the LV meets a lane change condition: if yes, entering the ninth step, otherwise, waiting for the next generation of a lane change intention, and then entering the first step;
step three, building a dynamic game model by the LV, and calculating the income of the two cars: firstly, vehicle accelerations respectively corresponding to the LV and the RV under the four strategy combinations are calculated, and then the total benefit values of the LV and the RV under the four strategy combinations are determined through the accelerations; wherein: the method for calculating the acceleration of the vehicle corresponding to the LV and the RV under the four strategy combinations comprises the following steps:
(1) calculating the acceleration under the LV selection lane change strategy:
Figure FDA0003021718190000011
Figure FDA0003021718190000012
Figure FDA0003021718190000013
wherein the content of the first and second substances,
Figure FDA0003021718190000014
representing acceleration of the LV under a lane-change strategy, hf(t) represents the time headway of LV and FV at time t, hr(t) represents the headway of LV to RV at time t,
Figure FDA0003021718190000015
representing the driver's desired FV at time t from the LV lead time,
Figure FDA0003021718190000016
representing the RV-to-LV headway, v, desired by the driver at time tr(t) and vl(t) the velocities at the current time t of RV and LV respectively, k the degree of consideration of the lane-change vehicle to the vehicle ahead of the target lane in the total acceleration, a1，b1，c1，a2，b2，c2Is a parameter;
(2) calculating the acceleration under the LV selection lane change-free strategy:
Figure FDA0003021718190000017
wherein the content of the first and second substances,
Figure FDA0003021718190000018
indicating the acceleration that the LV is going to select under the lane-change-free strategy,
Figure FDA0003021718190000019
is the longitudinal safe speed of the LV vehicle relative to the vehicle PV, calculated as follows:
Figure FDA0003021718190000021
wherein, bpAnd blIs the respective maximum braking acceleration, x, of the vehicles PV and LVl(t) is the longitudinal position of the lane-change vehicle LV at time t, xp(t) is the longitudinal position of the front vehicle PV at time t, τ is the reaction time;
(3) calculating the acceleration under the RV selection avoidance strategy:
Figure FDA0003021718190000022
in the formula (I), the compound is shown in the specification,
Figure FDA0003021718190000023
representing the avoidance acceleration, L, of the RVrRepresents the distance, v, of the RV from the potential conflict pointr(t) represents the speed of the RV vehicle at time t,
Figure FDA0003021718190000024
the velocity of the RV vehicle to the potential conflict point is represented and calculated according to the following formula:
Figure FDA0003021718190000025
in the formula (I), the compound is shown in the specification,
Figure FDA0003021718190000026
representing the expected avoidance speed of the RV;
(4) calculating the acceleration under the RV selection non-avoidance strategy:
Figure FDA0003021718190000027
wherein the content of the first and second substances,
Figure FDA0003021718190000028
the acceleration of the RV under the avoidance-free strategy is shown,
Figure FDA0003021718190000029
is the longitudinal safe speed of the RV vehicle relative to the vehicle FV, calculated according to the following formula:
Figure FDA00030217181900000210
in the formula, brAnd bfIs the respective maximum braking acceleration, x, of the vehicles RV and FVrWhen (t) is tLongitudinal position, x, of the lane-change vehicle RVf(t) is the longitudinal position of the preceding vehicle FV at time t;
step four, solving the optimal strategy to be selected by the LV;
step five, judging whether the lane changing game termination condition is met: if yes, entering step ten, and if not, entering step six;
step six, turning on a steering lamp by the LV and performing tentative transverse deviation;
step seven, the LV selects lane changing acceleration;
step eight, judging whether the rear vehicle RV of the target lane selects avoidance: if not, returning to the third step; if yes, entering the ninth step;
step nine, the LV starts to change the lane until the lane change is finished;
step ten, the LV continues to follow the original lane, and the lane changing intention is finished;
wherein: the lane change game starting condition comprises the following steps: the LV and the PV keep a safe distance, and the collision time difference between the LV and the PV does not exceed a set threshold value, wherein:
(1) the safe distance between the LV and the PV is calculated by the following formula:
Figure FDA0003021718190000031
in the formula, GlFor the safe distance, x, of the lane-changing vehicle LV from the vehicle PV ahead of the current lanel(t) the LV position, x, of the lane-changing vehicle at time tp(t) the PV position of the front vehicle of the current lane at time t,/pThe length of the body of the vehicle PV ahead of the current lane, blMaximum deceleration of LV, τlReaction time of LV, vl(t) the velocity at time LV, vp(t) is the velocity of PV at time t;
(2) the method for calculating the conflict time difference between the LV and the PV comprises the following steps:
1) calculating the distance traveled by the LV from the lane change starting point to the potential conflict point according to the following formula:
Figure FDA0003021718190000032
wherein L islChanging the driving distance of the LV from the current position to the potential conflict point; x is the number ofeAnd yeRespectively the transverse coordinate and the longitudinal coordinate of the track changing track terminal point; the position of the potential conflict point is determined by adopting the following method:
a) calculating the ordinate y of the potential conflict pointc：
yc＝ye-wcar
Wherein, yeFor the ordinate, w, of the end point of the track-changing curvecarRepresenting a vehicle width;
b) establishing a track changing track equation:
Figure FDA0003021718190000041
wherein x and y are the transverse and longitudinal positions of the left end of the LV head;
c) will ycThe value of (A) is substituted into a lane-changing track curve equation to solve the abscissa x of the potential conflict pointcFinally, the position (x) of the potential conflict point is obtainedc，yc)；
2) The distance the RV travels from the current location to the potential conflict point is calculated as follows:
Lr＝xc+d
wherein L isrRepresents the distance traveled by the RV from the current position to the potential conflict point, xcRepresenting the longitudinal distance between the left front corner point of the lane changing vehicle and the potential conflict point, and d representing the locomotive distance between the LV and the RV in the longitudinal direction;
3)
Figure FDA0003021718190000042
wherein: v. ofr(t) and vl(t) represents the velocity of the RV and LV at the current time t, respectively.
2. The method for establishing the automatic driving lane change decision model in the hybrid driving environment according to claim 1, wherein the method comprises the following steps: the lane-changing game termination condition comprises the following steps: when the game step number of the automatic driving lane changing vehicle LV reaches the set step number or when the following distance between the automatic driving vehicle LV and the vehicle PV in front of the current lane does not meet the safety distance in the lane changing process.
3. The method for establishing the automatic driving lane change decision model in the hybrid driving environment according to claim 1, wherein the method comprises the following steps: the method for calculating the total benefit value of the LV and the RV under the combination of the four strategies respectively comprises the following steps:
(1) calculating the speed gain:
1) LV speed gain under no lane change strategy:
Figure FDA0003021718190000043
wherein the content of the first and second substances,
Figure FDA0003021718190000044
indicates the velocity gain, v, of the LV under a no-lane-change strategyp(t) represents the velocity of the PV at time t, vl(t) represents the velocity of the LV at time t;
2) LV speed gain under lane change strategy:
Figure FDA0003021718190000051
wherein the content of the first and second substances,
Figure FDA0003021718190000052
indicates the velocity gain, v, of the LV under the lane-change strategyf(t) velocity of FV at time t, vl(t) represents the velocity of the LV at time t;
3) the velocity gain of the RV under the avoidance strategy is as follows:
Figure FDA0003021718190000053
wherein the content of the first and second substances,
Figure FDA0003021718190000054
the speed gain under the RV avoidance strategy is shown,
Figure FDA0003021718190000055
the expected avoidance velocity of the RV is represented by the following equation:
Figure FDA0003021718190000056
wherein, TlRepresents the travel time of the LV to the potential conflict point for performing a lane change from the current position; l isrRepresents the distance traveled by the RV from the current position to the potential conflict point;
4) the velocity gain of the RV under the avoidance strategy is as follows:
Figure FDA0003021718190000057
wherein the content of the first and second substances,
Figure FDA0003021718190000058
represents the velocity gain v under the RV non-avoidance strategyf(t) and vr(t) speeds of the front cars FV and RV of the target lanes, respectively;
(2) calculating comfort benefits:
1) comfort benefits of LV:
Figure FDA0003021718190000059
wherein the content of the first and second substances,
Figure FDA00030217181900000510
representing LVComfort benefit, al(t- λ) represents the acceleration of the last step length LV;
2) comfort benefits of RV:
Figure FDA00030217181900000511
wherein the content of the first and second substances,
Figure FDA00030217181900000512
shows the comfort gain of RV, ar(t- λ) represents the acceleration of the previous step RV;
(3) calculating the safety income:
1) safety gains of LV in selecting lane change strategy:
Figure FDA0003021718190000061
wherein the content of the first and second substances,
Figure FDA0003021718190000062
the safe profit of the LV when selecting the lane change strategy is shown, delta T represents the conflict time difference between the RV of the rear vehicle of the target lane and the LV of the lane change vehicle, and TMRepresenting a safety critical point;
2) safety gains of LV in choosing a no-change strategy:
Figure FDA0003021718190000063
wherein the content of the first and second substances,
Figure FDA0003021718190000064
representing the safety benefit of the LV when selecting a non-lane change strategy;
3) when the LV is changed, the RV selects the safety benefit of the non-avoidance strategy:
Figure FDA0003021718190000065
wherein the content of the first and second substances,
Figure FDA0003021718190000066
representing the safety benefit of the non-avoidance strategy selected by the RV when the LV is changed;
4) when the LV is changed, the RV selects the safety benefit of an avoidance strategy:
Figure FDA0003021718190000067
wherein the content of the first and second substances,
Figure FDA0003021718190000068
representing the safety benefit of the avoidance strategy selected by the RV when the LV is changed;
5) the safety gains of RV when LV is not changed are as follows:
Figure FDA0003021718190000069
wherein the content of the first and second substances,
Figure FDA00030217181900000610
representing the safety benefit of RV when the LV is not changed;
(4) calculating a total benefit value:
1) calculate total yield of LV:
Figure FDA00030217181900000611
wherein the content of the first and second substances,
Figure FDA0003021718190000071
the velocity gain of the LV is represented,
Figure FDA0003021718190000072
indicating the safety benefits of the LV in the area,
Figure FDA0003021718190000073
indicates the comfort benefit of LV, α1，β1，γ1Respectively representing the weighting parameters among the three benefits of the LV, and f (#) representing a function for normalizing each benefit;
2) calculating the total yield of RV:
Figure FDA0003021718190000074
wherein the content of the first and second substances,
Figure FDA0003021718190000075
the speed gain of the RV is expressed,
Figure FDA0003021718190000076
the safety gain of the RV is represented,
Figure FDA0003021718190000077
representing the comfort benefit, α, of RV2，β2，γ2And delta represents a random number of benefits of the human-driven vehicle RV.
4. The method for establishing the automatic driving lane change decision model in the hybrid driving environment according to claim 1, wherein the method comprises the following steps: and solving the optimal strategy to be selected by the LV by adopting an inverse induction method.
CN201910603412.7A 2019-07-05 2019-07-05 Method for establishing automatic driving lane change decision model in hybrid driving environment Active CN110298131B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910603412.7A CN110298131B (en) 2019-07-05 2019-07-05 Method for establishing automatic driving lane change decision model in hybrid driving environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910603412.7A CN110298131B (en) 2019-07-05 2019-07-05 Method for establishing automatic driving lane change decision model in hybrid driving environment

Publications (2)

Publication Number Publication Date
CN110298131A CN110298131A (en) 2019-10-01
CN110298131B true CN110298131B (en) 2021-07-13

Family

ID=68030488

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910603412.7A Active CN110298131B (en) 2019-07-05 2019-07-05 Method for establishing automatic driving lane change decision model in hybrid driving environment

Country Status (1)

Country Link
CN (1) CN110298131B (en)

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110962853B (en) * 2019-11-25 2021-04-06 浙江工业大学 Vehicle game lane change cooperation method in Internet of vehicles environment
CN111081065B (en) * 2019-12-13 2021-03-30 北京理工大学 Intelligent vehicle collaborative lane change decision model under road section mixed traveling condition
CN111199284A (en) * 2019-12-17 2020-05-26 天津职业技术师范大学(中国职业培训指导教师进修中心) Vehicle-vehicle interaction model under condition of manned and unmanned mixed driving
CN110884423B (en) * 2019-12-20 2023-09-08 吉林大学 Automatic control system and method for steering lamp under automatic lane change of vehicle
CN111267846B (en) * 2020-02-11 2021-05-11 南京航空航天大学 Game theory-based peripheral vehicle interaction behavior prediction method
CN111391848B (en) * 2020-03-02 2022-03-08 吉林大学 Automatic driving vehicle lane changing method
CN111739342B (en) * 2020-03-26 2022-03-01 腾讯科技（深圳）有限公司 Method, device, medium, and vehicle for avoiding vehicle ahead of side
CN111439264B (en) * 2020-04-03 2021-06-11 东南大学 Implementation method of lane change control model based on man-machine hybrid driving
CN111361564B (en) * 2020-04-29 2023-07-07 吉林大学 Lane changing system considering benefit maximization and comprehensive decision method
CN113954869B (en) * 2020-06-01 2024-04-09 北京航迹科技有限公司 Road condition reminding method and device, electronic equipment and storage medium
CN111994089A (en) * 2020-09-02 2020-11-27 中国科学技术大学 Driver lane change intention identification method and system based on hybrid strategy game
CN111994090B (en) * 2020-09-02 2021-11-02 中国科学技术大学 Method and system for identifying lane-changing cut-in intention of driver based on hybrid strategy game
CN111994088A (en) * 2020-09-02 2020-11-27 中国科学技术大学 Driver lane change intention identification method and system based on hybrid strategy game
CN112406905B (en) * 2020-09-10 2022-01-28 腾讯科技（深圳）有限公司 Data processing method and device based on vehicle, computer and storage medium
CN114506324B (en) * 2020-10-23 2024-03-15 上海汽车集团股份有限公司 Lane decision method and related device
CN112348198A (en) * 2020-10-30 2021-02-09 上海对外经贸大学 Coordination method of machine behaviors of man-machine hybrid decision in conflict
CN112373485A (en) * 2020-11-03 2021-02-19 南京航空航天大学 Decision planning method for automatic driving vehicle considering interactive game
CN112590791B (en) * 2020-12-16 2022-03-11 东南大学 Intelligent vehicle lane change gap selection method and device based on game theory
CN112721929B (en) * 2021-01-11 2022-11-22 成都语动未来科技有限公司 Decision-making method for lane changing behavior of automatic driving vehicle based on search technology
CN112907967B (en) * 2021-01-29 2022-06-10 吉林大学 Intelligent vehicle lane change decision-making method based on incomplete information game
CN113823118B (en) * 2021-02-19 2022-07-08 石家庄铁道大学 Intelligent networking vehicle lane changing method combining urgency degree and game theory
CN113076897B (en) * 2021-04-09 2024-06-25 广州机械科学研究院有限公司 Game dynamic driving safety measurement and control method and terminal for intelligent network-connected automobile
CN113313941B (en) * 2021-05-25 2022-06-24 北京航空航天大学 Vehicle track prediction method based on memory network and encoder-decoder model
CN113335282B (en) * 2021-06-01 2023-06-30 南京航空航天大学 Channel switching decision method based on game theory
CN113495563B (en) * 2021-06-10 2022-09-20 吉林大学 Traffic vehicle lane change decision planning method for automatic driving virtual test
CN113361613B (en) * 2021-06-15 2024-06-21 东南大学 Method and device for classifying on-ramp vehicle lane change simulation model based on track data
CN113963535B (en) * 2021-09-30 2023-01-13 华为技术有限公司 Driving decision determination method and device and electronic equipment storage medium
CN113954828B (en) * 2021-10-26 2023-08-29 江苏科创车联网产业研究院有限公司 Automatic driving vehicle cruise control method and device and electronic equipment
CN113920740B (en) * 2021-11-16 2023-12-29 北京白龙马云行科技有限公司 Vehicle-road cooperative driving system and method combining vehicle association degree and game theory
WO2023087157A1 (en) * 2021-11-16 2023-05-25 华为技术有限公司 Intelligent driving method and vehicle applying same
CN114360319B (en) * 2022-01-17 2023-03-24 中山大学 Remote driving speed optimization method of driving simulator
CN114882705B (en) * 2022-05-30 2024-04-26 武汉理工大学 Freight vehicle interactive game lane change decision method based on lane change decision system
CN115412883A (en) * 2022-08-31 2022-11-29 重庆交通大学 Intelligent network connection over-the-horizon driving auxiliary system based on 5G position sharing
CN115456392B (en) * 2022-09-06 2023-09-05 长安大学 High-speed multi-vehicle multi-driving behavior conflict collaborative decision-making method and device
CN115547047A (en) * 2022-09-30 2022-12-30 中汽院智能网联科技有限公司 Intelligent internet vehicle following model based on attention model
CN115906265B (en) * 2022-12-27 2024-05-10 中交第二公路勘察设计研究院有限公司 Near main line outlet marking optimization method based on channel change behavior characteristics
CN117284297B (en) * 2023-11-27 2024-02-27 福思(杭州)智能科技有限公司 Vehicle control method and device and domain controller
CN117649143A (en) * 2023-11-29 2024-03-05 山东大学 Driver-based ecological driving behavior evaluation method and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106379237A (en) * 2016-09-30 2017-02-08 西南交通大学 Augmented reality-based lane changing whole-process driver assistant system of vehicle
CN108387242A (en) * 2018-02-07 2018-08-10 西南交通大学 Automatic Pilot lane-change prepares and executes integrated method for planning track
CN109540159A (en) * 2018-10-11 2019-03-29 同济大学 A kind of quick complete automatic Pilot method for planning track

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6176028B2 (en) * 2013-09-26 2017-08-09 株式会社デンソー Vehicle control system, image sensor
CN107452201B (en) * 2017-07-24 2020-05-08 重庆大学 Method for determining following acceleration of rear vehicle in consideration of lane change and driving away of front vehicle and following behavior modeling method
CN108595823B (en) * 2018-04-20 2021-10-12 大连理工大学 Autonomous main vehicle lane changing strategy calculation method combining driving style and game theory
CN108583578B (en) * 2018-04-26 2019-12-31 北京领骏科技有限公司 Lane decision method based on multi-objective decision matrix for automatic driving vehicle
CN109855639B (en) * 2019-01-15 2022-05-27 天津大学 Unmanned driving trajectory planning method based on obstacle prediction and MPC algorithm

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106379237A (en) * 2016-09-30 2017-02-08 西南交通大学 Augmented reality-based lane changing whole-process driver assistant system of vehicle
CN108387242A (en) * 2018-02-07 2018-08-10 西南交通大学 Automatic Pilot lane-change prepares and executes integrated method for planning track
CN109540159A (en) * 2018-10-11 2019-03-29 同济大学 A kind of quick complete automatic Pilot method for planning track

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"A dynamic lane-changing trajectory planning model for automated vehicles";yang da 等;《TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES》;20181030;第95卷;第228-247页 *
"基于博弈的车辆协作换道策略研究";薛春铭;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20180415(第04期);C035-138，正文第16-24页 *
"高速公路车辆自主性换道行为建模研究";聂建强;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20190115(第01期);C034-101 *

Also Published As

Publication number Publication date
CN110298131A (en) 2019-10-01

Similar Documents

Publication Publication Date Title
CN110298131B (en) Method for establishing automatic driving lane change decision model in hybrid driving environment
CN110362910B (en) Game theory-based automatic driving vehicle lane change conflict coordination model establishment method
CN109035862B (en) Multi-vehicle cooperative lane change control method based on vehicle-to-vehicle communication
CN110298122B (en) Unmanned vehicle urban intersection left-turn decision-making method based on conflict resolution
CN108919795B (en) Automatic driving automobile lane change decision method and device
CN108387242B (en) Integrated trajectory planning method for automatic driving lane change preparation and execution
CN109976340B (en) Man-machine cooperation dynamic obstacle avoidance method and system based on deep reinforcement learning
CN112907967B (en) Intelligent vehicle lane change decision-making method based on incomplete information game
CN111081065A (en) Intelligent vehicle collaborative lane change decision model under road section mixed traveling condition
CN112965476B (en) High-speed unmanned vehicle trajectory planning system and method based on multi-window model
CN110861634A (en) Interaction aware decision making
CN113276884A (en) Intelligent vehicle interactive decision passing method and system with variable game mode
CN115817460B (en) Intelligent network linkage vehicle active coordination collision avoidance method under mixed flow condition
CN112201070B (en) Deep learning-based automatic driving expressway bottleneck section behavior decision method
CN115050183B (en) Method for generating simulated traffic flow
CN115056798A (en) Automatic driving vehicle lane change behavior vehicle-road cooperative decision algorithm based on Bayesian game
CN114475608B (en) Method and device for changing lane for automatic driving vehicle, vehicle and storage medium
Yan et al. A multi-vehicle game-theoretic framework for decision making and planning of autonomous vehicles in mixed traffic
CN116142194A (en) Personification channel changing decision method
CN115973179A (en) Model training method, vehicle control method, device, electronic equipment and vehicle
WO2023004698A1 (en) Method for intelligent driving decision-making, vehicle movement control method, apparatus, and vehicle
CN114148349A (en) Vehicle personalized following control method based on generation countermeasure simulation learning
Saraoglu et al. A Minimax-Based Decision-Making Approach for Safe Maneuver Planning in Automated Driving
Gu et al. Mandatory Lane-Changing Decision-Making in Dense Traffic for Autonomous Vehicles based on Deep Reinforcement Learning
CN116572994B (en) Vehicle speed planning method, device and computer readable medium

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