Cooperative decision planning method and model for mixed traffic off-ramp scene

Abstract

The application discloses a kind of cooperative decision planning methods for mixed traffic under ramp scene, the method is by constructing highway ramp merging scene, based on vehicle information and constraint condition, formulates right of way allocation scheme, obtains the time of vehicle through merging area under ideal condition, establishes optimal control problem to obtain the control scheme and predicted trajectory of all vehicles, in combination with the real-time driving state of vehicle and actual road condition, using event-driven trajectory re-planning method updates the driving trajectory of each vehicle in highway ramp merging scene, obtains the cooperative decision planning scheme of highway ramp merging scene under mixed traffic, controls the driving of all vehicles in highway ramp merging scene.The method is based on trajectory deviation event-driven vehicle driving trajectory planning, combined with adaptive deviation threshold, improves the decision-making efficiency, reduces the power consumption, is conducive to guiding the formulation of intelligent driving decision in mixed traffic scene.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of intelligent traffic control, in particular to a cooperative decision planning method for ramp scene under mixed traffic and a model thereof. BACKGROUND

[0002] Intelligent connected vehicle refers to a new generation of vehicles equipped with advanced vehicle-mounted sensors, controllers, actuators and other devices, which have complex environment perception, intelligent decision-making, cooperative control and other functions through the integration of modern communication and network technology, and can realize safe, efficient, comfortable and energy-saving driving, and ultimately replace manual operation. With the development of communication technology, multi-vehicle cooperative control under intelligent connected scenario can be realized. Compared with general traffic signal control methods, multi-vehicle cooperative control can achieve better traffic control performance through coordination and motion planning of vehicle groups, and reduce fuel consumption and environmental pollution caused by traffic.

[0003] In actual traffic environment, mixed traffic scenarios of manual driving vehicles and intelligent connected vehicles will exist for a long time. Since the driving style of manual driving vehicles is uncertain and generally takes individual optimization as the starting point of decision-making, the cooperative control method based on global optimization cannot be directly applied to control intelligent connected vehicles, otherwise it will cause the risk of traffic accidents.

[0004] Under this circumstance, how to observe manual driving vehicles based on roadside equipment and realize real-time and efficient control of intelligent connected vehicles to ensure the driving safety of intelligent connected vehicles and intelligent connected vehicles has become a challenging task. Therefore, it is urgent to propose a cooperative decision planning method for ramp scene under mixed traffic to guide the landing application of intelligent driving in mixed traffic scenarios. SUMMARY

[0005] The present disclosure provides a cooperative decision planning method for ramp scene under mixed traffic, comprising the following steps:

[0006] Obtaining vehicle information in a highway ramp merging scene at time t, predicting the driving trajectory of each vehicle based on the vehicle information of the highway ramp merging scene at time t, the vehicles including manual driving vehicles and intelligent connected vehicles;

[0007] And determining the driving trajectory of each vehicle in the highway ramp merging scene at time t+1 by using an event-driven trajectory re-planning method, obtaining the cooperative decision planning scheme, wherein the event-driven trajectory re-planning method is associated with the trajectory deviation degree of the target manual vehicle, and the trajectory deviation degree is determined based on the vehicle information and the driving prediction trajectory of the target manual vehicle;

[0008] The vehicle information based on the highway ramp merging scenario at time t, and the prediction of the driving trajectory of each intelligent connected vehicle, includes:

[0009] Based on the vehicle information and the constraints of the vehicles in the highway ramp merging scenario, a right-of-way allocation function is determined, and the right-of-way allocation scheme is obtained by solving the right-of-way allocation function. The right-of-way allocation scheme is used to determine the order in which each vehicle passes through the merging zone.

[0010] An optimal control scheme is established based on the right-of-way allocation scheme, and the optimal control scheme is used to optimize the energy consumption of vehicles during driving.

[0011] And solve the right-of-way allocation scheme and the optimal control scheme to obtain the driving prediction trajectory of all vehicles;

[0012] The constraints under the highway ramp merging scenario include constraint one and constraint two.

[0013] Among them, constraint condition one, based on the vehicle's own kinematic constraints, includes:

[0014]

[0015] In the formula, For the first The acceleration of a vehicle; Minimum acceleration; This is the maximum acceleration; For the first The speed of the vehicle; Minimum speed; Maximum speed;

[0016] Among them, constraint condition two is set based on the headway when the vehicle passes through the merging zone. Constraint condition two includes a first sub-constraint condition and a second sub-constraint condition.

[0017] The first sub-constraint is set relative to adjacent vehicles traveling in the same lane, including:

[0018]

[0019] in, , All vehicle numbers; For vehicles The moment when the merge zone is reached; For vehicles The moment when the merge zone is reached; This is the preset minimum headway when adjacent vehicles in the same lane pass through the merging zone;

[0020] The second constraint condition is set for adjacent vehicles driving on different lanes and passing through the merging area in sequence, and includes setting the second constraint condition as follows for adjacent vehicles driving on different lanes and passing through the merging area in sequence:

[0021]

[0022] wherein, is a preset minimum headway of adjacent vehicles on different lanes passing through the merging area;

[0023] The determination of the road right allocation function includes:

[0024] Based on the constraint conditions in the merging area of the highway ramp, a global traffic efficiency is taken as an optimization target to obtain an optimization objective function:

[0025]

[0026] wherein, is an optimization target; , are weight coefficients; is a maximum function; is a vehicle serial number; is a time when a vehicle reaches the merging area under a certain road right allocation scheme; is a time when the i-th vehicle reaches the merging area; is a shortest time when the vehicle reaches the merging area under the kinematic constraint; is a total number of manually driven vehicles; is a total number of intelligent connected vehicles; The determination of the road right allocation function

[0027] is as follows:

[0028]

[0029]

[0030] wherein, is a set of possible times when all vehicles reach the merging area under all road right allocation schemes; is a set of all zero-one variables ; is a sum of the number of all vehicles, i.e. ; is a preset positive number; is a set of all manually driven vehicles on the main lane; and N2 is a set of all intelligent connected vehicles on the merging lane; ​is a zero-one variable, used to represent the order of the merging of the vehicle on the main lane and the vehicle on the merging lane through the merging area, when the vehicle on the main lane passes through the merging area earlier than the vehicle on the merging lane, , when the vehicle on the main lane passes through the merging area later than the vehicle on the merging lane, ;

[0031] According to the road right allocation function, the road right allocation scheme is obtained as:

[0032]

[0033] , wherein, is the road right order of the controlled intelligent connected vehicle; is the vehicle in front of the road right of the intelligent connected vehicle; is the vehicle behind the road right of the intelligent connected vehicle.

[0034] The optimal control scheme is established based on the road right allocation scheme, and the optimal control scheme is determined as:

[0035] The energy consumption of the vehicle in the driving process is taken as the optimization target, the initial condition, the termination condition and the kinematic constraint of the vehicle entering the control area are combined, and the optimal control scheme is determined as:

[0036]

[0037]

[0038] , wherein, is a minimum function; is the acceleration of the vehicle; is the speed of the vehicle; is the position of the vehicle; is a certain specific time; is the time when the vehicle enters the control area; is the time when the vehicle reaches the merging area after the road right is allocated; is the initial speed of the vehicle; is the final speed of the vehicle.

[0039] Preferably, the road right allocation scheme and the optimal control scheme are solved, and the driving prediction trajectory of all vehicles is obtained, including:

[0040] The driving prediction trajectory of all vehicles in the highway ramp merging scene at the t time is determined by solving the global optimal solution of the road right allocation scheme and the optimal control scheme at the t time.

[0041] Preferably, the driving trajectory of each vehicle in the highway ramp merging scene at the t+1 time is determined by using the event-driven trajectory re-planning method, and the cooperative decision planning scheme is obtained, including:

[0042] determining whether a difference between the actual driving trajectory of the target human-driven vehicle at the tth moment and the driving prediction trajectory is greater than a preset trajectory deviation threshold value;

[0043] If the difference between the actual driving trajectory of the target human-driven vehicle and the driving prediction trajectory is greater than the preset trajectory deviation threshold value, it is determined that the cooperative decision control method at the t+1th moment is to allocate road rights to all vehicles in the highway ramp merging scene, update the driving trajectories of all intelligent connected vehicles in the highway ramp merging scene by executing the optimal control scheme, predict the prediction trajectory of the human-driven vehicle, and control the intelligent connected vehicle to perceive the vehicle information of the human-driven vehicle in real time.

[0044] Preferably, the method further comprises:

[0045] If the difference between the actual driving trajectory of the target human-driven vehicle and the driving prediction trajectory is less than or equal to the preset trajectory deviation threshold value, it is determined whether a preset allocation condition is true, the preset allocation condition being whether the main lane at the tth moment enters a new human-driven vehicle and the intelligent connected vehicle is allocated to the last road right.

[0046] If the preset allocation condition is true, it is determined that the cooperative decision control method executed at the t+1th moment is to allocate road rights to all vehicles in the highway ramp merging scene.

[0047] Preferably, the method further comprises:

[0048] If the preset allocation condition is false, it is determined that the cooperative decision control method executed at the t+1th moment is to control the intelligent connected vehicle to perceive the vehicle information of the human-driven vehicle in real time, update the time step, and continue to monitor the driving trajectories of all vehicles in the highway ramp merging scene.

[0049] Preferably, the trajectory deviation threshold value can be adaptively adjusted according to the highway ramp merging scene, and the calculation formula is:

[0050]

[0051] In the formula, is the trajectory deviation threshold value; is the minimum distance between all intelligent connected vehicles in the control area and the merging area; is the maximum threshold value; is the length of the control area.

[0052] The application further provides an intelligent driver model based on diversified driving behaviors, which is applied to the cooperative decision planning method for the ramp scene under mixed traffic and is used for simulating driving behaviors of drivers to predict driving trajectories of the artificial driving vehicle.

[0053] Preferably, the intelligent driver model is:

[0054]

[0055] wherein,

[0056]

[0057] wherein, is the acceleration of the vehicle; is the maximum acceleration of the vehicle; is the longitudinal speed of the vehicle; is the desired vehicle speed; is the acceleration exponent; is the desired distance; is the relative speed of the vehicle and the preceding vehicle; is the relative distance of the vehicle and the preceding vehicle; is the static safety distance; is the safety headway; is the desired deceleration;

[0058] The static safety distance, the safety headway, the desired deceleration and the acceleration exponent are IDM parameters;

[0059] By setting the IDM parameters and the behavior type occurrence probability of the intelligent driver model, the driving behaviors of the driver are predicted by using the intelligent driver model.

[0060] The application has the following beneficial technical effects:

[0061] (1) The application provides the cooperative decision planning method for the ramp scene under mixed traffic, solves the problem that the ramp merging decision scheme in the mixed traffic scene is difficult to accurately formulate, reduces the travel time and fuel consumption of the vehicle, avoids the collision between the autonomous driving vehicle and the artificial driving vehicle in the ramp merging process, and improves the traffic efficiency and safety of the vehicle at the ramp merging place of the expressway.

[0062] (2) The application provides a cooperative decision planning method for an on-ramp scene under mixed traffic, the trajectory deviation degree is introduced, the driving trajectory prediction result of the vehicle is more in line with the actual situation, the prediction accuracy of the vehicle trajectory is improved under the premise of ensuring the vehicle merging efficiency and safety, the influence of the prediction deviation on the control scheme and the predicted trajectory of the vehicle is weakened, the accuracy of the trajectory deviation degree setting of the method applied to different traffic scenes is effectively ensured, and a large amount of useless repeated calculation in the method execution process is effectively avoided. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 A flowchart of a traditional vehicle trajectory replanning method.

[0064] Figure 2 A schematic diagram of a highway ramp merging scene of the application.

[0065] Figure 3 A curve of the trajectory deviation degree threshold value changing with the minimum distance between the intelligent connected vehicle and the merging area.

[0066] Figure 4 A flowchart of a centralized cooperative decision control method under mixed traffic of the application.

[0067] In the figure: 1, a manually driven vehicle; 2, an intelligent connected vehicle; 3, a perception system; 4, a merging area; 5, a control area. DETAILED DESCRIPTION

[0068] The present disclosure will be further described in detail below with reference to the accompanying drawings and examples.

[0069] Example 1

[0070] In the prior art, for a manually driven vehicle, the driver generally takes individual driving efficiency as the driving target, the behavior is affected by many factors such as the driving style of the driver, the reaction time, the field of view, etc., so that there is a large difference between the driving trajectory of the vehicle and the predicted trajectory planned according to the global optimal target. In order to ensure the safety and efficiency of the intelligent connected vehicle during driving, it is necessary to adjust and replan the trajectory of the intelligent connected vehicle in real time.

[0071] The traditional vehicle trajectory replanning method is as follows Figure 1As shown, this method updates the planned trajectory at fixed time intervals. However, traditional vehicle trajectory replanning methods have certain limitations, namely, how to determine the time interval between two adjacent calculations. When the set time interval is too long, the update calculation frequency is too low, which can easily lead to a large deviation between the manually driven vehicle's trajectory and the predicted trajectory within that interval, causing potential risks. When the set time interval is too short, the calculation method is executed too frequently, resulting in frequent computational demands and additional resource consumption. In addition, factors such as traffic congestion under different traffic environments and differences in human driver driving styles can affect the execution interval of this calculation method. Therefore, adopting a time-driven centralized collaborative decision control method is not the optimal choice for vehicle trajectory planning.

[0072] To address the aforementioned problems in existing technologies, this embodiment proposes a collaborative decision-making and planning method for mixed traffic off-ramp scenarios, comprising the following steps:

[0073] Based on the actual situation of highway ramp merging under mixed traffic, a highway ramp merging scenario is constructed.

[0074] The scenario of highway ramp merging is as follows: Figure 2 As shown, the highway ramp includes a main road and merging lanes. Vehicles traveling on the main road are human-driven vehicles (HDVs), while vehicles traveling on the merging lanes are connected and autonomous vehicles (CAVs). A perception system is installed on one side of the main road in a highway ramp merging scenario to acquire driving status information of both human-driven and CAVs. The measurement area of ​​the perception system is the control area, the merging point where the merging lane merges into the main road is the merging point, and the area merging into the main road is the merging area. For ease of explanation, in the embodiments of this disclosure, it is assumed that the merging point and merging area are the same, both being the intersection of the main road and the merging lane. The perception system is connected to a central controller, which is used to perform trajectory planning for the CAVs based on the measurement information from the perception system and to send control commands to the CAVs.

[0075] Vehicle information in a highway ramp merging scenario at time t (e.g., the initial time) is obtained. In this embodiment, the vehicles include manually driven vehicles and intelligent connected vehicles. The vehicle information includes the position and speed of each manually driven vehicle and each intelligent connected vehicle. At time t, the speed and position of all manually driven vehicles and all intelligent connected vehicles in the ramp merging scenario can be determined. It should be understood that when t=0, the initial speed and initial position of all manually driven vehicles and all intelligent connected vehicles are obtained.

[0076] Under ideal conditions, the behaviors of manually driven vehicles and intelligent connected vehicles are the same, both of which follow the principle of global optimization under the guidance of the central controller to travel, and under such conditions, a global optimization problem can be established. Assuming that the driving behavior of manually driven vehicles in the on-ramp merging scenario of the expressway conforms to the global benefit maximization criterion, the trajectory of each vehicle in the on-ramp merging scenario of the expressway at the t+1 time is determined by using an event-driven trajectory re-planning method, and the cooperative decision planning scheme is obtained. In an embodiment of the present disclosure, the t+1 time is the next time of the t time. Through iterative calculation of the cooperative decision planning method, the real-time driving trajectory of the vehicle under the scenario of the present disclosure can be accurately predicted. The event-driven trajectory re-planning method is associated with the trajectory deviation degree of the target manually driven vehicle, and the trajectory deviation degree is determined based on the vehicle information and the driving prediction trajectory of the target manually driven vehicle. For each intelligent connected vehicle, at least one target manually driven vehicle is matched. For each intelligent connected vehicle, the manually driven vehicles passing through the merging area in front of and / or behind the vehicle can affect its merging behavior. Therefore, the manually driven vehicles in front of and / or behind the i-th intelligent connected vehicle passing through the merging area are the target manually driven vehicles of the i-th intelligent connected vehicle. The set of target manually driven vehicles of all intelligent connected vehicles is the target manually driven vehicle.

[0077] The embodiment adopts a centralized cooperative decision planning method for mixed traffic under the event-driven hybrid traffic, triggers trajectory updating when a specific event is detected, and reduces the execution frequency of the calculation method as much as possible under the premise of not affecting the performance of the cooperative decision planning method, thereby reducing unnecessary computing power demand and resource consumption. In each time step, the intelligent connected vehicle control is executed while the real-time trajectory of the manually driven vehicle is perceived, and when a preset driving event occurs, the preset centralized cooperative decision control method for mixed traffic under the event-driven hybrid traffic is automatically re-executed.

[0078] The method for predicting the driving trajectory of each intelligent connected vehicle based on the vehicle information of the on-ramp merging scenario of the expressway at the t time includes operations S1-S3.

[0079] In operation S1, a right-of-way allocation function is determined based on the vehicle information and the constraint conditions of the vehicles in the on-ramp merging scenario of the expressway, and a right-of-way allocation scheme is obtained by solving the right-of-way allocation function, which is used to determine the order of passing through the merging area of each vehicle.

[0080] Preferably, the constraint conditions in the on-ramp merging scenario of the expressway include constraint condition one and constraint condition two.

[0081] The constraint condition one is set based on the kinematic constraints of the vehicle, including:

[0082]

[0083] wherein, is the acceleration of the first vehicle; is the minimum acceleration; is the maximum acceleration; is the speed of the first vehicle; is the minimum speed; is the maximum speed; wherein, the second constraint condition is set based on the headway of the vehicles passing through the merging area, and the second constraint condition comprises a first sub-constraint condition and a second sub-constraint condition;

[0084] The first sub-constraint condition is set for adjacent vehicles running on the same lane, and comprises:

[0085]

[0086] wherein, k represents the number of the manually driven vehicle, and l represents the number of the intelligent and connected vehicle;

[0087] is the time when the vehicle reaches the merging area; is the time when the vehicle reaches the merging area; is the minimum headway of the adjacent vehicles running on the same lane and passing through the merging area; The second sub-constraint condition is set for adjacent vehicles running on different lanes and passing through the merging area in succession, and comprises that, for the adjacent vehicles running on different lanes, when the two vehicles pass through the merging area in succession, the second constraint condition is set as:

[0088]

[0089]

[0090] wherein, is the minimum headway of the adjacent vehicles running on different lanes and passing through the merging area.

[0091] wherein, determining the road right distribution function comprises:

[0092] Based on the constraint conditions under the merging scene of the highway ramp, a global traffic passing efficiency is taken as an optimization target to obtain an optimization objective function:

[0093]

[0094] wherein, is the optimization target; , are weight coefficients; is a maximum function; is the vehicle serial number; ​​​​For a specific right-of-way allocation scheme, the first The time it takes for the vehicle to arrive at the merged area; For vehicles The shortest time to reach the merging region under kinematic constraints; This represents the total number of manually driven vehicles. The total number of intelligent connected vehicles;

[0095] Determine the right-of-way allocation function for:

[0096]

[0097]

[0098] in, This is the set of possible arrival times for all vehicles in the merging zone under all right-of-way allocation schemes; For all zero and one variables A set; The sum of the number of all vehicles, i.e. ; The preset positive number; N1 is the collection of all manually driven vehicles on the main lane; N2 is the collection of all intelligent connected vehicles on the merging lane. This is a zero-to-one variable used to represent the order in which vehicles traveling on the main road and those merging in the merging lane pass through the merging zone. When a vehicle on the main road passes through the merging zone before a vehicle in the merging lane... When vehicles traveling on the main road pass through the merging zone later than vehicles traveling in the merging lane, .

[0099] In the embodiments of this disclosure, the right-of-way allocation function is the optimal solution of the aforementioned objective function. The values ​​of b_{k,l} are obtained by solving the objective function (i.e., the values ​​corresponding to each vehicle). The right-of-way allocation scheme can be obtained as follows:

[0100]

[0101] in, The right-of-way order for the controlled intelligent connected vehicles; For vehicles with right-of-way in front of intelligent connected vehicles; For vehicles with right-of-way following intelligent connected vehicles, typical solution methods can include general methods for solving mixed-integer linear programming problems, as well as existing dynamic programming algorithms.

[0102] In operation S2, an optimal control scheme is established based on the right-of-way allocation scheme. This optimal control scheme is used to optimize energy consumption during vehicle operation. For vehicles... According to the time node of entering the merging area, an optimal control scheme is used to obtain a planned trajectory from the current position to the merging area. For an intelligent network connected vehicle, the trajectory planning result is directly used for control; for a manually driven vehicle, the trajectory planning result is used as a comparison reference with the actual trajectory and applied to the subsequent trajectory updating process.

[0103] Preferably, the optimal control scheme is established based on the road right allocation scheme, and the optimal control scheme comprises:

[0104] Taking the energy consumption of the vehicle during driving as an optimization target, combining the initial condition, the termination condition and the kinematic constraint of the vehicle entering the control area, the optimal control scheme is determined as:

[0105]

[0106]

[0107] In the formula, is a minimum value function; is the acceleration of the vehicle; is the speed of the vehicle; is the position of the vehicle; is a certain specific time; is the time when the vehicle enters the control area; is the time when the vehicle reaches the merging area after the road right is allocated; is the initial speed of the vehicle; is the final speed of the vehicle.

[0108] In operation S3, the road right allocation scheme and the optimal control scheme are solved to obtain the driving prediction trajectory of all vehicles. In an embodiment of the present disclosure, the speed, position and control amount (i.e. acceleration) information of the planning vehicle at each time from the current time until reaching the merging area can be obtained by solving the optimal control scheme and the driving prediction trajectory.

[0109] Specifically, by solving the global optimal solution of the road right allocation scheme and the optimal control scheme at time t, the driving prediction trajectory of all vehicles in the highway ramp merging scene at time t can be determined.

[0110] In an embodiment of the present disclosure, the method for determining the driving trajectory of each vehicle in the highway ramp merging scene at time t+1 by using the event-driven trajectory re-planning method to obtain the cooperative decision planning scheme comprises operations S4-S8.

[0111] At operation S4, it is determined whether the difference between the actual driving trajectory of the target human-driven vehicle at time t and the driving prediction trajectory is greater than a preset trajectory deviation threshold. The trajectory deviation threshold is the maximum deviation amount Δ_x between the actual trajectory of the human-driven vehicle and the prediction trajectory before each update calculation needs to be recalculated.

[0112] In some embodiments, the trajectory deviation can be associated with position information. For example, the trajectory deviation can be calculated by comparing the difference between the position of the target human-driven vehicle at time t and the position prediction value of the driving prediction trajectory of the vehicle at time t.

[0113] When setting the trajectory deviation threshold, if the trajectory deviation threshold is too small, the planning method used in this embodiment will not have a large difference in execution frequency compared with the time-driven planning method, and cannot effectively reduce the consumption of computing power. If the trajectory deviation threshold is too large, the intelligent connected vehicle cannot timely adjust its trajectory according to the driving behavior of the human-driven vehicle, especially when approaching the merging area, which may cause potential safety problems.

[0114] Considering that when the intelligent connected vehicle is far away from the merging area, the deviation between the actual trajectory and the prediction trajectory of the human-driven vehicle has little effect on the final merging efficiency of the intelligent connected vehicle. However, when the intelligent connected vehicle is very close to the merging area, slight behavior deviation of the human-driven vehicle will have a great impact on the safety of vehicle merging, so the trajectory deviation threshold used in this embodiment can be adaptively adjusted according to the highway ramp merging scene, and the trajectory deviation threshold is:

[0115]

[0116] In the formula, is the trajectory deviation threshold; is the minimum distance between all intelligent connected vehicles in the control area and the merging area; is the maximum threshold; is the length of the control area.

[0117] Figure 3 The trajectory deviation threshold of the present disclosure changes with the minimum distance between the intelligent connected vehicle and the merging area, as shown in the curve Figure 3 As can be seen from the curve, as the distance between the human-driven vehicle and the merging area gradually decreases, the trajectory deviation threshold decays quadratically until it decreases to 0.

[0118] In the embodiments of the present disclosure, if the difference between the actual driving trajectory of the target human-driven vehicle and the driving prediction trajectory is greater than the preset trajectory deviation threshold, operation S5 is performed.

[0119] At operation S5, the cooperative decision-making control method at the t+1 time instant is determined to allocate road rights to all vehicles in the freeway ramp merging scene, update the driving trajectories of all intelligent connected vehicles in the freeway ramp merging scene by executing the optimal control scheme, and predict the predicted trajectory of the human-driven vehicle, and control the intelligent connected vehicle to perceive the vehicle information of the human-driven vehicle in real time.

[0120] In some embodiments, if the difference between the actual driving trajectory of the target human-driven vehicle and the driving prediction trajectory is less than or equal to a preset trajectory deviation threshold, operation S6 is performed.

[0121] At operation S6, it is determined whether a preset allocation condition is true, the preset allocation condition being: whether a new human-driven vehicle enters the main lane at the t time instant and the intelligent connected vehicle is allocated to the last road right. The method for determining the last road right is: for each lane, the last vehicle is allocated to the last road right.

[0122] If the preset allocation condition is true, operation S7 is performed.

[0123] At operation S7, the cooperative decision-making control method at the t+1 time instant is determined to allocate road rights to all vehicles in the freeway ramp merging scene.

[0124] If the preset allocation condition is false, operation S8 is performed.

[0125] At operation S8, the cooperative decision-making control method at the t+1 time instant is determined to control the intelligent connected vehicle to perceive the vehicle information of the human-driven vehicle in real time, update the time step, and continue to monitor the driving trajectories of all vehicles in the freeway ramp merging scene.

[0126] Figure 4 An exemplary centralized cooperative decision-making control method under mixed traffic according to one example of the present disclosure is shown. As shown in FIG. 6, the centralized cooperative decision-making control method under mixed traffic according to one example of the present disclosure includes the following steps. Figure 4As shown, if the difference between the actual driving trajectory and the predicted trajectory of the target human-driven vehicle at the current time step is greater than the preset trajectory deviation threshold τ, it is determined that the actual driving trajectory and the predicted trajectory of the target human-driven vehicle are too different, and only the human-driven vehicles located in front and behind the target human-driven vehicle are considered. When the target human-driven vehicle travels according to the established trajectory planning result, only when the trajectories of the vehicles traveling in front and behind the target human-driven vehicle deviate greatly, the target human-driven vehicle has a certain probability of failing to enter the merging area according to the original control scheme, and the trajectory deviation of the remaining vehicles does not affect the travel of the current intelligent connected vehicle, that is, the physical positions of the remaining vehicles are constrained by the vehicles traveling in front and behind the target vehicle. At this time, the cooperative decision control method is used to allocate road rights to all vehicles in the highway ramp merging scene, update the driving trajectories of all intelligent connected vehicles in the highway ramp merging scene by executing the optimal control scheme, and predict the predicted trajectory of the human-driven vehicle. The intelligent connected vehicle updates the vehicle information of the human-driven vehicle in real time and enters the next time step.

[0127] Otherwise, it is determined whether the main lane has a newly entered human-driven vehicle and the intelligent connected vehicle is allocated to the last road right. If the main lane has a newly entered human-driven vehicle and the intelligent connected vehicle is allocated to the last road right, it is considered that the newly entered human-driven vehicle does not affect the previously entered human-driven vehicle, that is, only whether it affects the original driving trajectory of the target human-driven vehicle needs to be considered. At this time, the cooperative decision control method is used to allocate road rights to all vehicles in the highway ramp merging scene, otherwise, the intelligent connected vehicle updates the vehicle information of the human-driven vehicle in real time and enters the next time step to continue to monitor the driving trajectories of all vehicles in the highway ramp merging scene.

[0128] According to the cooperative decision planning scheme of the highway ramp merging scene under mixed traffic according to the present disclosure, the central controller and the perception system arranged in the highway ramp merging scene are used to control the driving of all vehicles in the highway ramp merging scene.

[0129] The embodiments of the present disclosure also provide an intelligent driver model with diversified driving behaviors, which is applied to the cooperative decision planning method for the ramp scene under mixed traffic according to the embodiments of the present disclosure, and can be preset in the central controller to simulate the driving behavior of the driver to predict the driving trajectory of the human-driven vehicle.

[0130] In a real traffic driving scene, there can be differences in the driving behaviors of drivers for manually driven vehicles. In order to improve the authenticity and accuracy of simulation test results, the diversified driving behaviors or intentions of drivers need to be predicted during the simulation test, so as to ensure the robustness of the method in complex and changeable traffic environments.

[0131] Considering the influencing factors such as the distance of the preceding vehicle and the relative speed during the driving of the manually driven vehicle, and combining the driving habits of humans, the intelligent driver model is:

[0132]

[0133] wherein,

[0134]

[0135] In the formula, is the acceleration of the vehicle; is the maximum acceleration of the vehicle; is the longitudinal speed of the vehicle; is the desired speed; is the acceleration exponent; is the desired distance; is the relative speed of the vehicle and the preceding vehicle; is the relative distance of the vehicle and the preceding vehicle; is the static safety distance; is the safe time headway; is the desired deceleration;

[0136] The static safety distance, the safe time headway, the desired deceleration and the acceleration exponent are IDM parameters; the desired distance is the desired following distance (safety distance).

[0137] By setting the IDM parameters and the occurrence probability of the intelligent driver model, the driving behavior of the driver is predicted by using the intelligent driver model.

[0138] Embodiment 2

[0139] In order to verify the effectiveness of the cooperative decision planning method for ramp scenes under mixed traffic in embodiment 1, especially the event-driven centralized cooperative decision control method under mixed traffic in embodiment 1, this embodiment compares the event-driven centralized cooperative decision control method under mixed traffic in embodiment 1 with the traditional vehicle trajectory re-planning method through simulation.

[0140] To verify the effectiveness of the event-driven mixed traffic centralized cooperative decision control method in Embodiment 1, a simulation model of a highway ramp merging scene is constructed according to a highway ramp merging scene by using simulation software, a vehicle merging process at a highway ramp is simulated, and the method is compared with a traditional time-driven vehicle trajectory re-planning method in terms of algorithm performance in a simulation environment. The performance indicators for comparison include the number of executions, the number of collisions, the average delay time, the average energy consumption, and the average fuel consumption. Only the collisions, delay time, energy consumption, and fuel consumption of intelligent connected vehicles in the highway ramp merging scene are considered.

[0141] wherein the number of executions is the number of times of executing the calculation method from the simulation process and all time points when intelligent connected vehicles exist in the control area; the delay time is the difference between the actual time of each vehicle in the highway ramp merging scene to reach the merging area and the minimum possible time of the vehicle to reach the merging area , wherein, is the time of the vehicle to reach the merging area after the road right is allocated, is the minimum possible time of the vehicle to reach the merging area; the average delay time is the average value of the delay time of all vehicles in the highway ramp merging scene; the average energy consumption is the integral of the square of the acceleration of the vehicle along time during the driving process, ; the average fuel consumption is the sum of the fuel consumption of the vehicle driving at a constant speed and the additional fuel consumption when accelerating, wherein, is the fuel consumption function when the vehicle drives at a constant speed, , , , , are fitting coefficients of the fuel consumption function when the vehicle drives at a constant speed, is the fuel consumption function when the vehicle accelerates, , , , are fitting coefficients of the fuel consumption function when the vehicle accelerates, is the positive acceleration of the vehicle during the driving process, and when the vehicle decelerates, .

[0142] During the simulation process, a Poisson process is used to simulate mixed traffic flow, different vehicle arrival rates are set, the event-driven mixed traffic centralized cooperative decision control method proposed in the disclosure is compared with the traditional time-driven vehicle trajectory re-planning method in terms of performance, and the simulation results are shown in Table 1.

[0143] Table 1 Performance simulation results

[0144]

[0145] When the time interval is , it is equivalent to making the optimal decision based on the current situation at each time, that is, the performance obtained by simulation can be considered to be nearly optimal. Under the same vehicle arrival rate, the number of calculations is greatly reduced by using the method of the present disclosure compared with the traditional time-driven vehicle trajectory replanning method, and the zero accident rate of the vehicle is ensured. When the time interval is , compared with the traditional time-driven vehicle trajectory replanning method, the method of the present disclosure can effectively avoid the occurrence of vehicle accidents under the condition that the number of executions is similar.

[0146] When the vehicle arrival rate is low, the method of the present disclosure can have similar average delay time as the traditional time-driven vehicle trajectory replanning method based on deviation feedback, that is, the traffic efficiency of the two is similar, but the energy consumption is relatively large. This is because when there are few vehicles, the frequency of needing to re-execute the decision planning method is low, and it may be necessary to make a large decision adjustment at some time, and the vehicle acceleration and deceleration amplitude is large, so the energy consumption increases.

[0147] When the vehicle arrival rate is high, the average delay time obtained by the method of the present disclosure based on deviation feedback is lower than that of the traditional time-driven vehicle trajectory replanning method, because in the first half of the journey, the trajectory deviation threshold is large, but the traffic density is also large. If planned frequently, the intelligent connected vehicle is likely to yield to the manually driven vehicle on the main lane in advance, thereby reducing its own speed, and at this time, reducing the frequency of decision planning is beneficial to reducing the delay time.

[0148] In order to verify the effectiveness of the adaptive trajectory deviation threshold in the method of the present disclosure, the deviation feedback method based on the adaptive threshold is compared with the deviation feedback method based on the fixed threshold, the threshold is set to 0.1 m, 1 m and 10 m respectively, and the rest of the conditions remain unchanged. The simulation model of the on-ramp merging scene on the expressway is simulated respectively, and the simulation results are shown in Table 2.

[0149] Table 2 Threshold simulation results

[0150]

[0151] From the analysis of Table 2, compared with using a fixed threshold, the method of the present disclosure reasonably controls the number of executions of the method under the premise of ensuring the safety of vehicle driving by introducing an adaptive trajectory deviation threshold, so that the number of executions is reduced by 20% to 30% compared with using a small threshold. Moreover, under a higher vehicle arrival rate, the adaptive threshold in the method of the present disclosure can flexibly arrange the time node of decision planning, effectively avoiding unnecessary decisions, and improving the driving performance of intelligent networked vehicles.

[0152] In summary, through simulation, the present embodiment verifies the advantages of the method of the present disclosure compared with the traditional time-driven vehicle trajectory re-planning method. The method of the present disclosure converts time-driven into event-driven, greatly reduces the computational power consumption of the entire method calculation process under the premise of ensuring traffic safety and efficiency. At the same time, through the ablation experiment of the adaptive threshold, it is also verified that the introduction of the adaptive threshold can balance the computational power consumption and the overall performance of the traffic, avoiding excessive number of executions while obtaining better algorithm performance. In addition, analysis of the simulation results can also find that the method of the present disclosure can achieve more excellent results under high traffic flow, thereby verifying the effectiveness and feasibility of the method of the present disclosure.

[0153] Embodiment 3

[0154] In order to simulate the driving behavior of drivers in actual traffic scenarios, the present embodiment reduces the gap between simulation testing and real situations by randomly initializing an intelligent driver model. Considering that completely random parameter settings ignore the correlation between parameters, there may be unrealistic situations in the behavior of artificially driven vehicles during simulation testing. Therefore, the present embodiment proposes a scheme for artificially constraining IDM parameters of an intelligent driver model, wherein the IDM parameters include a static safety distance, a safety time headway, a desired deceleration, and an acceleration exponent.

[0155] The driving behavior of human drivers is divided into general, aggressive, and conservative types, and different IDM parameters and occurrence probabilities are set for each type, as shown in Table 3. The occurrence probability refers to the probability of occurrence of a certain type of driving behavior.

[0156] Table 3 Driving behavior parameter table

[0157]

[0158] Based on the above intelligent driver model settings, the cooperative decision planning method for ramp scenarios under mixed traffic proposed in Embodiment 1 is used to predict the driving trajectory of artificially driven vehicles and determine the driving behavior of artificially driven vehicles during simulation:

[0159]

[0160] wherein, represents a general type of driving behavior, represents an aggressive type of driving behavior, represents a conservative type of driving behavior; is an ideal trajectory obtained by solving an optimal control problem, is an actual driving trajectory of the vehicle; is a small number representing a tolerance level for deviation of the vehicle trajectory.

[0161] The intelligent driver model is applied to the simulation model of the highway ramp merging scene in Embodiment 2, and the simulation model of the highway ramp merging scene is reconstructed. The simulation test of the method of the present disclosure is performed by using the simulation model of the highway ramp merging scene considering diversified driving behaviors, and the simulation results are shown in Table 4.

[0162] Table 4 Simulation results considering diversified driving behaviors

[0163]

[0164] It can be obtained from Table 4 that, under the condition of fully considering diversified driving behaviors, the cooperative decision planning method for the ramp scene under mixed traffic adopted by the method of the present disclosure can still achieve the performance of approximate global optimization, i.e., approximate to the traditional vehicle trajectory re-planning method based on time driving when the time interval is 0.1 s, and the calculation efficiency of the method of the present disclosure is greatly improved, and the method has good robustness.

[0165] Of course, the above description is not a limitation of the present disclosure, and the present disclosure is not limited to the above examples. Changes, modifications, additions or substitutions made by those skilled in the art within the spirit and scope of the present disclosure should also be within the protection scope of the present disclosure.

Claims

1. A collaborative decision-making and planning method for mixed traffic off-ramp scenarios, characterized in that, Includes the following steps: Obtain vehicle information in the highway ramp merging scenario at time t, and predict the driving trajectory of each vehicle based on the vehicle information in the highway ramp merging scenario at time t. The vehicles include manually driven vehicles and intelligent connected vehicles. And the event-driven trajectory replanning method is used to determine the driving trajectory of each vehicle in the highway ramp merging scenario at time t+1, and a collaborative decision planning scheme is obtained. The event-driven trajectory replanning method is associated with the trajectory deviation of the target artificial vehicle, and the trajectory deviation is determined based on the vehicle information and driving prediction trajectory of the target artificial vehicle. The vehicle information based on the highway ramp merging scenario at time t, and the prediction of the driving trajectory of each intelligent connected vehicle, includes: Based on the vehicle information and the constraints of the vehicles in the highway ramp merging scenario, a right-of-way allocation function is determined, and the right-of-way allocation scheme is obtained by solving the right-of-way allocation function. The right-of-way allocation scheme is used to determine the order in which each vehicle passes through the merging zone. An optimal control scheme is established based on the right-of-way allocation scheme, and the optimal control scheme is used to optimize the energy consumption of vehicles during driving. And solve the right-of-way allocation scheme and the optimal control scheme to obtain the driving prediction trajectory of all vehicles; The constraints under the highway ramp merging scenario include constraint one and constraint two. Among them, constraint condition one, based on the vehicle's own kinematic constraints, includes: ； In the formula, For the first The acceleration of a vehicle; Minimum acceleration; This is the maximum acceleration; For the first The speed of the vehicle; Minimum speed; Maximum speed; Among them, constraint condition two is set based on the headway when the vehicle passes through the merging zone. Constraint condition two includes a first sub-constraint condition and a second sub-constraint condition. The first sub-constraint is set relative to adjacent vehicles traveling in the same lane, including: ； in, , All vehicle numbers; For vehicles The moment when the merge zone is reached; For vehicles The moment when the merge zone is reached; This is the preset minimum headway when adjacent vehicles in the same lane pass through the merging zone; The second sub-constraint is set relative to adjacent vehicles traveling in different lanes that successively pass through the merging zone. This includes setting constraint two for adjacent vehicles traveling in different lanes when both vehicles successively pass through the merging zone: ； in, This is the minimum headway between adjacent vehicles in different lanes when they pass through the merging zone. Determining the right-of-way allocation function includes: Based on the constraints of the highway ramp merging scenario, and taking global traffic efficiency as the optimization objective, the optimization objective function is obtained as follows: ； in, To optimize the objective; , All are weighting coefficients; It is a function for maximizing the value; For vehicle serial number; For a specific right-of-way allocation scheme, the first The time it takes for the vehicle to arrive at the merged area; For vehicles The shortest time to reach the merging region under kinematic constraints; This represents the total number of manually driven vehicles. The total number of intelligent connected vehicles; Determine the right-of-way allocation function for: ； ； in, This is the set of possible arrival times for all vehicles in the merging zone under all right-of-way allocation schemes; For all zero and one variables A set; The sum of the number of all vehicles, i.e. ; The preset positive number; The collection of all manually driven vehicles on the main road; This refers to the collection of all intelligent connected vehicles merging into the lane; This is a zero-to-one variable used to represent the order in which vehicles traveling on the main road and those merging in the merging lane pass through the merging zone. When a vehicle on the main road passes through the merging zone before a vehicle in the merging lane... When vehicles traveling on the main road pass through the merging zone later than vehicles traveling in the merging lane, ; Based on the right-of-way allocation function, the right-of-way allocation scheme is as follows: ； in, The right-of-way order for the controlled intelligent connected vehicles; For vehicles with right-of-way in front of intelligent connected vehicles; For vehicles whose right-of-way is located behind intelligent connected vehicles; The establishment of the optimal control scheme based on the right-of-way allocation scheme includes: Taking the energy consumption during vehicle operation as the optimization objective, and considering the initial and final conditions of the vehicle entering the control zone, as well as kinematic constraints, the optimal control scheme is determined as follows: ； ； In the formula, It is a minimum value function; The acceleration of the vehicle; The speed of the vehicle; The location of the vehicle; For a specific moment; The time when the vehicle enters the controlled area; The time it takes for vehicles to reach the merged area after right-of-way is allocated; The initial speed of the vehicle; This represents the vehicle's final speed.

2. The collaborative decision-making and planning method for mixed traffic off-ramp scenarios according to claim 1, characterized in that, Solving the right-of-way allocation scheme and the optimal control scheme to obtain the predicted driving trajectories of all vehicles includes: By solving for the global optimal solutions of the right-of-way allocation scheme and the optimal control scheme at time t, the predicted driving trajectories of all vehicles in the highway ramp merging scenario at time t are determined.

3. The collaborative decision-making and planning method for mixed traffic off-ramp scenarios according to claim 1, characterized in that, The event-driven trajectory replanning method is used to determine the driving trajectories of each vehicle in the highway ramp merging scenario at time t+1, resulting in the collaborative decision planning scheme, which includes: Determine whether the difference between the actual driving trajectory of the target manually driven vehicle at time t and the predicted driving trajectory is greater than a preset trajectory deviation threshold. If the difference between the actual driving trajectory of the target manually driven vehicle and the predicted driving trajectory is greater than a preset trajectory deviation threshold, the collaborative decision control method at time t+1 is determined to be allocating right-of-way to all vehicles in the highway ramp merging scenario, updating the driving trajectory of all intelligent connected vehicles in the highway ramp merging scenario by executing the optimal control scheme, predicting the predicted trajectory of the manually driven vehicle, and controlling the intelligent connected vehicle to perceive the vehicle information of the manually driven vehicle in real time.

4. The collaborative decision-making and planning method for mixed traffic off-ramp scenarios according to claim 3, characterized in that, The method also includes: If the difference between the actual driving trajectory of the target manually driven vehicle and the driving prediction trajectory is less than or equal to the preset trajectory deviation threshold, it is determined whether the preset allocation condition is true. The preset allocation condition is: whether a new manually driven vehicle enters the main road at time t and the intelligent connected vehicle is allocated to the last right-of-way. If the preset allocation condition is true, then the collaborative decision control method at time t+1 is determined to be allocating right-of-way to all vehicles in the highway ramp merging scenario.

5. The collaborative decision-making and planning method for mixed traffic off-ramp scenarios according to claim 4, characterized in that, The method also includes: If the preset allocation condition is false, then the collaborative decision control method for execution at time t+1 is determined to be: control the intelligent connected vehicle to perceive the vehicle information of the manually driven vehicle in real time, update the time step, and continue to monitor the driving trajectory of all vehicles in the highway ramp merging scenario.

6. The collaborative decision-making and planning method for mixed traffic off-ramp scenarios according to claim 3, characterized in that, The trajectory deviation threshold can be adaptively adjusted according to the highway ramp merging scenario, and the calculation formula is as follows: ； In the formula, The trajectory deviation threshold; This is the minimum distance between all intelligent connected vehicles within the control zone and the merged zone; The maximum threshold; This represents the length of the control area.

7. An intelligent driver model based on diversified driving behaviors, characterized in that, The method is applied to the collaborative decision-making and planning method for mixed traffic off-ramp scenarios as described in any one of claims 1 to 6, and is used to simulate the driving behavior of the driver in order to predict the driving trajectory of the manually driven vehicle.

8. The intelligent driver model based on diversified driving behaviors according to claim 7, characterized in that, The intelligent driver model is as follows: ； in, ； In the formula, The acceleration of the vehicle; This is the vehicle's maximum acceleration; The longitudinal speed of the vehicle; For the desired vehicle speed; The acceleration index; The desired distance; The relative speed between the vehicle and the vehicle in front; This refers to the relative distance between the vehicle and the vehicle in front. This is a static safety distance; For safe headway; For the desired deceleration; The static safety distance, safe headway, desired deceleration, and acceleration exponent are IDM parameters. By setting the IDM parameters and the probability of occurrence of behavior types in the intelligent driver model, the driving behavior of the driver can be predicted using the intelligent driver model.

Images