Intersection vehicle control method and device, roadside equipment and storage medium

Abstract

The invention relates to an intersection vehicle control method and device, roadside equipment and a storage medium, and belongs to the technical field of intelligent traffic. The intersection vehicle control method comprises the steps that the initial speed of a vehicle in a preset sensing area is acquired, determining an earliest arrival time at which the vehicle arrives at the intersection based on the initial speed and a desired speed at which the vehicle passes through the intersection; determining the earliest occupied time when the vehicle passes through a target cellular grid needing to be occupied at the intersection based on the occupied condition of each cellular grid at the intersection after the earliest arrival time, and determining the earliest passing start time when the vehicle can pass through the intersection based on the earliest occupied time; and determining a vehicle speed control strategy of each vehicle based on the interval duration between the earliest passing starting moment and the current moment, wherein the vehicle speed control strategy is used for regulating the speed of the vehicle from the initial speed to the expected speed within the interval duration. The method can adapt to the traffic demand of dynamic change of the intersection, and improves the passing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and particularly to a vehicle control method, device, roadside device and storage medium for an intersection. Background Art

[0002] With the increasingly serious problem of urban traffic congestion, intersections, as the key nodes of urban traffic, their traffic efficiency and safety have always been the focus of research.

[0003] In the prior art, although some studies have attempted to alleviate congestion by optimizing signal timings, most of these methods have failed to fully utilize the networking and intelligent characteristics of autonomous vehicles, and are unable to achieve efficient traffic flow and energy conservation and emission reduction at intersections. In addition, the signal control method essentially relies on fixed cycles and phases, and it is difficult to adapt to dynamically changing traffic demands. Especially in the context of the gradual popularization of autonomous vehicles, its limitations have become increasingly obvious.

[0004] It can be seen that in the existing vehicle control technologies for intersections, they cannot adapt to dynamically changing traffic demands. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle control method, device, roadside device and storage medium for an intersection to solve the problem that in the existing vehicle control technologies for intersections, they cannot adapt to dynamically changing traffic demands.

[0006] To solve the above problems, in a first aspect, the present invention provides a vehicle control method for an intersection, including: Obtain the initial speed of vehicles in a preset sensing area, and determine the earliest arrival time of the vehicles at the intersection based on the initial speed and the expected speed of the vehicles passing through the intersection; Based on the occupancy of each cell grid at the intersection after the earliest arrival time, determine the earliest available time of the target cell grid that the vehicle needs to occupy to pass through the intersection, and determine the earliest start time for the vehicle to pass through the intersection based on the earliest available time; Determine the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time and the current time, where the vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the expected speed within the time interval.

[0007] In a possible implementation manner of the present invention, determining the earliest arrival time of the vehicles at the intersection based on the initial speed and the expected speed of the vehicles passing through the intersection includes: Calculate the earliest arrival time when the vehicle reaches the intersection with optimal acceleration performance and optimal braking performance and the speed of the vehicle when it reaches the intersection is the expected speed.

[0008] In a possible implementation manner of the present invention, determining the earliest available time of the target cell grids that each vehicle needs to occupy when passing through the intersection based on the occupancy of each cell grid at the intersection after the earliest arrival time includes: Determining the target cell grids that the vehicle needs to occupy when passing through the intersection based on the driving direction of the vehicle; Determining the earliest available time of each target cell grid after the earliest arrival time based on a preset time-cell grid matrix; the time-cell grid matrix is used to represent the occupancy of each cell grid at each moment.

[0009] In a possible implementation manner of the present invention, determining the earliest start time for the vehicle to pass through the intersection based on the earliest available time includes: Calculating the earliest start time for the vehicle to continuously pass through each target cell grid based on the order of the vehicle passing through each target cell grid, the earliest available time of each target cell grid, and the time duration for the vehicle to pass through each target cell grid.

[0010] In a possible implementation manner of the present invention, determining the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time and the current time includes: Determining a plurality of preset candidate vehicle speed regulation strategies based on the magnitude relationship between the initial speed and the desired speed; Calculating the shortest required time for each candidate vehicle speed regulation strategy to adjust the vehicle speed from the initial speed to the desired speed within a preset cooperative regulation area; Determining the target vehicle speed control strategy based on the relationship between the shortest required time of each candidate vehicle speed regulation strategy and the time interval.

[0011] In a possible implementation manner of the present invention, after determining the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time and the current time, it includes: Optimizing the vehicle speed control strategy of the following vehicle among adjacent vehicles according to the initial speed of the adjacent vehicles in the same lane, the distance between the adjacent vehicles, and a preset safety distance between the adjacent vehicles, so as to ensure that when the speed of the following vehicle is the same as that of the preceding vehicle among the adjacent vehicles, the distance between the following vehicle and the preceding vehicle is greater than or equal to the preset safety distance.

[0012] In a possible implementation manner of the present invention, after determining the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time and the current time, it includes: Regarding the vehicles entering the sensing area within the same moving time window as a group of vehicles; Using a preset optimization algorithm to optimize the order of each vehicle passing through the intersection among the group of vehicles, so that the total time duration for each vehicle in the group of vehicles to pass through the intersection is the shortest.

[0013] In a second aspect, the present invention further provides a vehicle control device for an intersection, including: An earliest arrival time calculation module, configured to obtain the initial speed of a vehicle within a preset sensing area, and determine the earliest arrival time of the vehicle at the intersection based on the initial speed and the desired speed of the vehicle passing through the intersection; An earliest start passing time calculation module, configured to determine the earliest available time of the target cell grid that the vehicle needs to occupy when passing through the intersection based on the occupancy of each cell grid of the intersection after the earliest arrival time, and determine the earliest start passing time of the vehicle passing through the intersection based on the earliest available time; A vehicle speed control strategy determination module, configured to determine the vehicle speed control strategy for each vehicle based on the time interval between the earliest start passing time and the current time, where the vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the desired speed within the time interval.

[0014] In a third aspect, the present invention further provides a roadside device, including a memory and a processor, where The memory is configured to store a program; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement the steps in the vehicle control method for an intersection described in any of the above embodiments.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium for storing computer-readable programs or instructions, and when the programs or instructions are executed by a processor, the steps in the vehicle control method for an intersection described in any of the above embodiments can be implemented The beneficial effects of the present invention are as follows: By determining the earliest arrival time of the vehicle at the intersection according to the initial speed of the vehicle in the sensing area and the desired speed of the vehicle passing through the intersection, and dividing the intersection into cells, and determining the occupancy of each cell grid of the intersection after the earliest arrival time to determine the earliest available time of the target cell grid that the vehicle needs to occupy when passing through the intersection, the passable conditions of each cell grid in the intersection can be determined, and based on the earliest available time, the earliest start passing time of the vehicle passing through the intersection can be determined, and the earliest start passing time when the vehicle can pass through the intersection can be determined, and the passing conditions of vehicles in each lane connected to the intersection can be counted, ensuring that the vehicle passes through the intersection as early as possible and improving the vehicle passing efficiency. At the same time, by determining the vehicle speed control strategy for each vehicle based on the time interval between the earliest start passing time and the current time, the vehicle speed control is optimized, and it is ensured that the vehicle passes through the intersection in an optimal vehicle speed control manner, which can adapt to the dynamically changing passing conditions of the intersection and ensure the smoothness of the intersection passage. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic flowchart of a method for controlling vehicles at an intersection provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of an intersection partition provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the division of a cellular grid at an intersection provided by an embodiment of the present invention; Figure 4 It is a schematic flowchart of a method for calculating the earliest available time provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of a vehicle passing through an intersection provided by an embodiment of the present invention; Figure 6 It is a schematic diagram of the binary vector representation of the cell occupancy time provided by an embodiment of the present invention; Figure 7 It is a schematic flowchart of a method for determining a vehicle speed control strategy provided by an embodiment of the present invention Figure 8 It is a schematic flowchart of a method for determining the vehicle passing sequence provided by an embodiment of the present invention Figure 9 It is a schematic structural diagram of a vehicle control device at an intersection provided by an embodiment of the present invention; Figure 10 It is a schematic structural diagram of a roadside device provided by an embodiment of the present invention. Detailed implementation manners

[0018] The following will specifically describe the preferred embodiments of the present invention in conjunction with the accompanying drawings. Among them, the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to explain the principle of the present invention, rather than to limit the scope of the present invention.

[0019] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present invention. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0020] A specific embodiment of the present invention is as follows Figure 1 As shown, it discloses a vehicle control method for an intersection, including: S101, obtaining the initial speed of the vehicles in the preset sensing area, and determining the earliest arrival time of the vehicles at the intersection based on the initial speed and the expected speed of the vehicles passing through the intersection.

[0021] In the embodiment of the present invention, the vehicle control for the intersection needs to be realized in combination with the roads connected to the intersection. For the convenience of description, taking a two-way four-lane symmetric cross intersection as an example, the intersection is divided into areas. As Figure 2 shown, the import directions of the intersection are sequentially marked as the east import, the south import, the west import, and the north import. The intersection is a symmetric intersection. The import road segments in each direction of the intersection are divided into three key functional areas: the sensing area, the collaborative regulation area, and the adaptation area. Before entering the intersection, the vehicles pass through the sensing area, the collaborative regulation area, and the adaptation area in sequence to complete information collection, speed regulation, and adaptive adjustment. The sensing area is the first section that the vehicle reaches before entering the intersection. In this section, the roadside sensing device collects key information such as the speed, position, and driving direction of the vehicle in real time through high-precision sensors. Based on the collected information, the roadside control center generates the optimal passing sequence of the vehicle group and the corresponding regulation strategy on the premise of ensuring driving safety. The core function of the sensing area is to provide accurate vehicle state data for the subsequent collaborative regulation area and adaptation area, providing basic support for global optimization. The collaborative regulation area is the key area for the vehicle to execute the regulation strategy returned by the roadside control center. In the collaborative regulation area, the vehicle adjusts its speed according to the speed control strategy generated by the roadside brain to ensure that the vehicle enters the intersection at the planned time and speed. The core function of the collaborative regulation area is to ensure speed matching before the vehicle enters the intersection through dynamic speed adjustment, avoid conflicts, and optimize the passing efficiency. The adaptation area is the last functional area before the vehicle enters the intersection, and its function varies according to the driving direction of the vehicle. For straight-going vehicles, in the adaptation area, the main task of the straight-going vehicle is to maintain its speed to ensure entering the intersection at a stable speed and avoid the impact of speed fluctuations on the passing efficiency; for right-turning vehicles, it is necessary to adjust its own speed to the expected right-turn speed in the adaptation area and maintain this speed to enter the intersection. This process ensures the effective resolution of the merging and diverging conflicts between the right-turning vehicle and the straight-going vehicle through precise speed control.

[0022] In an embodiment of the present invention, the provided vehicle control method for intersections can control vehicles passing through the intersection in various directions. When a vehicle enters the sensing area, information such as the initial speed and driving direction of the vehicle is collected by roadside devices (such as speedometers and cameras), and the earliest arrival time of the vehicle at the intersection is calculated based on the expected speed preset for the vehicle to pass through the intersection. The specific calculation method will be described in detail later in the present invention.

[0023] S102. Determine the earliest available time of the target cell grid that the vehicle needs to occupy to pass through the intersection based on the occupancy of each cell grid at the intersection after the earliest arrival time, and determine the earliest start time for the vehicle to pass through the intersection based on the earliest available time.

[0024] In an embodiment of the present invention, the cell grids of the intersection are obtained by dividing the intersection into grids. For example, Figure 3 as shown, the overlapping part of the extensions of two mutually perpendicular lanes is set as one cell. An intersection with two-way four lanes can be divided into 16 cells, and each cell has its specific state, including being occupied by a vehicle or being empty (i.e., no vehicle), so as to discretize the intersection.

[0025] In an embodiment of the present invention, after determining the earliest arrival time of the vehicle in the sensing area at the intersection, determine the occupancy of each cell grid at the intersection after the earliest arrival time, and determine the earliest available time of each cell grid. Among them, a straight-through vehicle needs to occupy multiple cell grids to pass through the intersection, so it is necessary to determine the earliest start time for the vehicle to pass through the intersection based on the earliest available time of each cell grid. The specific determination method for the earliest start time for the vehicle to pass through the intersection will be described in detail later in the present invention.

[0026] S103. Determine the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time to pass through the intersection and the current time. The vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the expected speed within the time interval.

[0027] In an embodiment of the present invention, after determining the earliest start time for the vehicle to pass through the intersection, calculate the time interval between the earliest start time and the current time, and determine the vehicle speed control strategy for each vehicle based on the time interval and the time required for each control strategy. The vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the expected speed within the time interval.

[0028] The present invention determines the earliest arrival time of a vehicle at an intersection based on the initial speed of the vehicle in the sensing area and the desired speed for the vehicle to pass through the intersection, divides the intersection into cells, determines the occupancy of each cell grid at the intersection after this earliest arrival time, determines the earliest available time for the target cell grid that the vehicle needs to occupy to pass through the intersection, can determine the passable conditions of each cell grid in the intersection, and determines the earliest start time for the vehicle to pass through the intersection based on the earliest available time, and can count the passing situations of vehicles in each lane connected to the intersection in all directions, ensuring that the vehicle passes through the intersection as early as possible and improving the vehicle passing efficiency. At the same time, the vehicle speed control strategy of each vehicle is determined based on the time interval between the earliest start time and the current time, optimizing the speed control of the vehicle, ensuring that the vehicle passes through the intersection in the optimal speed control mode, being able to adapt to the dynamically changing passing situations at the intersection, and ensuring the smoothness of passing at the intersection.

[0029] In some possible embodiments of the present invention, determining the earliest arrival time of a vehicle at an intersection based on the initial speed and the desired speed for the vehicle to pass through the intersection includes: Calculating the earliest arrival time when the vehicle reaches the intersection with optimal acceleration performance and optimal braking performance and the speed of the vehicle when it reaches the intersection is the desired speed.

[0030] In the embodiments of the present invention, in order to determine the earliest arrival time of a vehicle at an intersection, the vehicle can be controlled to accelerate at the maximum acceleration at the current time and decelerate at the maximum braking force at a certain moment, ensuring that the speed of the vehicle when it reaches the intersection is exactly the desired speed. This control strategy is an ideal control strategy, and the earliest arrival time when the vehicle reaches the intersection fastest can be determined in theory.

[0031] The present invention calculates the earliest arrival time when the vehicle is about to reach the intersection under the ideal control strategy, facilitating the subsequent determination of the earliest start time of the vehicle and improving the passing efficiency of the intersection.

[0032] In some possible embodiments of the present invention, as Figure 4 shown, determining the earliest available time for the target cell grid that each vehicle needs to occupy to pass through the intersection based on the occupancy of each cell grid at the intersection after the earliest arrival time includes: S401, determining the target cell grid that the vehicle needs to occupy to pass through the intersection based on the driving direction of the vehicle; S402, determining the earliest available time for each target cell grid after the earliest arrival time based on a preset time-cell grid matrix; the time-cell grid matrix is used to represent the occupancy of each cell grid at each moment.

[0033] In an embodiment of the present invention, as Figure 5 shown, for vehicles traveling in different directions, when passing through an intersection, for straight-through vehicles, they need to pass through 4 cell grids, which are successively , , and , for right-turn vehicles, they only pass through 1 cell grid, which is . Similarly, it is possible to determine the cell grids that vehicles in each direction need to pass through when passing through the intersection within the same time period.

[0034] In an embodiment of the present invention, in order to more conveniently determine the available time slots of each cell grid, a time-cell grid matrix can be constructed. As Figure 6 shown, the x ( ) dimension of the matrix represents continuously changing time points, and the y ( ) dimension of the matrix represents cells. The time slot occupied by a cell is denoted as 1, and the unoccupied time slot is denoted as 0. Through this modeling method, the occupancy situation of cells by vehicles can be visually presented, including information such as when they are occupied and the occupancy duration. Further, starting from the earliest arrival time of the vehicle at the intersection, the binary values corresponding to the rows of cells to be occupied are successively connected from left to right to form binary strings, and finally, according to the order in which the cells are occupied, the binary strings of all rows are assembled from top to bottom to form an overall cell scheduling binary vector. With the representation of the binary vector, the roadside management center only needs to perform 0 / 1 determination on the cell scheduling binary vector to quickly find out the earliest available time slot of the target cell grid that the vehicle will occupy during driving. As Figure 6 shown, is the maximum arrival time of the vehicle at the intersection. After this time, the earliest available time slots of the four cell grids that a straight-through vehicle needs to occupy when passing through the intersection are respectively , , and .

[0035] By analyzing the occupancy situation of each target cell grid after the earliest arrival time and combining the binary vector representation method, the present invention can quickly determine the earliest available time slot of each target cell grid, ensuring the efficiency of intersection passage.

[0036] In some possible embodiments of the present invention, determining the earliest start time for a vehicle to pass through an intersection based on the earliest available time slot includes: Calculate the earliest start time for the vehicle to continuously pass through each target cell grid based on the order in which the vehicle passes through each target cell grid, the earliest available time for each target cell grid, and the duration for the vehicle to pass through each target cell grid.

[0037] In the embodiments of the present invention, as in the foregoing embodiments, after determining the earliest occupancy time of each target cell grid, it is necessary to calculate the earliest start crossing time for the vehicle to continuously pass through the intersection. Because the determination of the earliest available time for the target cell grid is discrete. Taking a straight vehicle as an example, it needs to pass through 4 cell grids in sequence, and there may be conflicts between the earliest available times of each cell grid. Therefore, it is necessary to calculate the earliest start crossing time for the vehicle to continuously pass through each target cell grid according to the order in which the vehicle passes through each target cell grid and the duration for the vehicle to pass through each target cell grid. Specifically, the theoretical time for a straight vehicle to occupy each cell is:

[0038] Where, is the lane width, unit ; is the vehicle length, unit ; is the reserved error for the vehicle to pass through each target cell grid time, unit is s , is the expected speed of the vehicle, unit is m / s , is the duration for the vehicle to pass through the i th target cell grid.

[0039] The theoretical time for a right-turn vehicle to occupy a cell is:

[0040] Where, is the turning angle, unit ; is the turning radius of the vehicle, unit ; is the minimum safety time interval introduced to solve the conflict of vehicle merging and diverging, is the theoretical time for a right-turn vehicle to occupy a target cell grid.

[0041] Based on this, it can be determined that the earliest start crossing time for the vehicle to continuously pass through each target cell grid is:

[0042] Where, is the earliest start crossing time for the vehicle to continuously pass through each target cell grid, is the earliest available time for the first cell to be occupied by the straight-going vehicle, unit s ; is the earliest available time for the second cell to be occupied by the straight-going vehicle, unit s ; is the earliest available time for the third cell to be occupied by the straight-going vehicle, unit s ; is the earliest available time for the fourth cell to be occupied by the straight-going vehicle, unit s ; is the theoretical duration for the straight-going vehicle to occupy one cell, unit s .

[0043] The earliest start time for the right-turning vehicle to cross is defined as:

[0044] wherein, is the earliest available time for the cell to be occupied by the right-turning vehicle, unit s .

[0045] In the embodiments of the present invention, by calculating the earliest start time for the vehicle to continuously pass through each target cell grid based on the order in which the vehicle passes through each target cell grid, the earliest available time for each target cell grid, and the duration for the vehicle to pass through each target cell grid, while ensuring that the vehicle can successfully pass through the intersection, the traffic efficiency is improved.

[0046] In some possible embodiments of the present invention, as Figure 7 shown, based on the time interval between the earliest start time and the current time, a vehicle speed control strategy for each vehicle is determined, including: S701, determining a plurality of preset candidate vehicle speed regulation strategies based on the magnitude relationship between the initial speed and the desired speed; S702, calculating the shortest required time for each candidate vehicle speed regulation strategy to adjust the vehicle speed from the initial speed to the desired speed within a preset cooperative regulation area; S703, determining the target vehicle speed control strategy based on the relationship between the shortest required time for each candidate vehicle speed regulation strategy and the time interval.

[0047] In the embodiments of the present invention, multiple preset candidate vehicle speed control strategies can be determined according to the magnitude relationship between the initial speed and the desired speed of the vehicle in the sensing area. For the convenience of description, the case where the initial speed of the vehicle in the sensing area is greater than the desired speed is taken as an example. When the initial speed of the vehicle in the sensing area is greater than the desired speed, it is necessary to decelerate the vehicle to control the vehicle speed to the desired speed. To achieve this goal, the embodiments of the present invention design four candidate vehicle speed control strategies to adapt to different interval durations. The core goal of these strategies is to minimize the delay time of the vehicle while meeting the time interval, taking into account driving comfort and energy consumption optimization. The following is a detailed description of these four candidate vehicle speed control strategies.

[0048] Strategy 1: The vehicle first travels at a constant speed and then decelerates at the maximum deceleration, just reaching the desired speed when arriving at the intersection. This strategy is applicable to scenarios with relatively loose time constraints and can achieve the shortest travel time. The starting time of vehicle deceleration can be determined by the following formula:

[0049] Where, is the earliest time constraint for the vehicle to enter the conflict area, with the unit s ; is the travel time of the vehicle in the adaptation area, with the unit s ; is the initial speed of the vehicle entering the cooperation area, with the unit m / s ; is the desired speed of the vehicle, with the unit m / s ; is the maximum acceleration of the vehicle, with the unit .

[0050] Strategy 2: The vehicle first travels at a constant speed based on the initial speed, then decelerates to the desired speed at a set acceleration at a certain moment, and finally travels at a constant speed to the intersection at the desired speed. The set acceleration of each vehicle is dynamically calculated according to its initial speed, desired speed, and time constraints. Once determined, the variable-speed movement of the vehicle in this stage will be carried out at a constant acceleration. This strategy optimizes the driving trajectory of the vehicle by dynamically adjusting the deceleration time and is applicable to medium time constraint scenarios.

[0051] The first acceleration change time, the second acceleration change time of the vehicle, and the set acceleration of the vehicle can be determined by the following linear programming: Objective function:

[0052] Constraint conditions:

[0053] Where, is the earliest start crossing time, unit s ; is the initial time when the vehicle enters the cooperative regulation area, unit s ; is the moment of the vehicle's first acceleration change, unit s; is the moment of the vehicle's second acceleration change, unit s; is the travel time of the vehicle in the adaptation area, unit s ; is the maximum acceleration of the vehicle, unit ; is the acceleration of the vehicle, unit ; is the total length of the cooperative regulation area, unit m ; is the initial speed of the vehicle when entering the cooperative regulation area, unit .

[0054] The smaller the value of the objective function of this strategy is considered, the smaller the acceleration magnitude is and the later the deceleration start time is. From the aspect of traffic flow, the smaller the acceleration magnitude is, the slower the vehicle speed changes and the more stable the traffic flow is; from the aspect of fuel consumption, the later the deceleration starts, the longer the vehicle maintains the initial speed at high speed cruising and the lower the fuel consumption. Therefore, it is reasonable and feasible to generate the optimal speed control strategy with the minimum objective function. In the objective function, the coefficients k 1, k 2 are determined by Max-Min normalization to ensure that the data sizes are on the same scale and are determined by the following formula:

[0055] Strategy three: The vehicle first decelerates at the maximum deceleration to an intermediate speed lower than the desired speed, then accelerates to the desired speed at a set acceleration at a certain moment, and finally enters the adaptation area at a constant speed. The set acceleration of each vehicle is dynamically calculated according to its initial speed, desired speed and time constraints, and once determined, the variable speed motion of the vehicle in this stage will be carried out with a constant acceleration. This strategy further optimizes the driving trajectory of the vehicle by adjusting the speed in stages and is applicable to scenarios with relatively strict time constraints.

[0056] The moment of the vehicle's first acceleration change, the moment of the second acceleration change and the set acceleration of the vehicle can be determined by the following formula:

[0057] Among them, is an intermediate speed lower than the desired speed, unit .

[0058] The value can be determined through cost optimization. In the case of delay determination, this strategy defines the set speed. The larger it is, the smaller the cost. The specific reasons are as follows: From the perspective of road traffic flow stability, the larger it is, the smaller the change in traffic flow speed, and the higher the traffic flow stability; from the perspective of riding comfort, under the same delay strategy, the larger it is, the smaller the vehicle deceleration, and the better the riding comfort; from the perspective of fuel consumption, the larger it is, the more sufficient the vehicle fuel, and the lower the fuel consumption. In summary, the effectiveness of this defined cost is obtained.

[0059] Strategy Four: The vehicle first decelerates to the lowest cruise speed at its own maximum deceleration, then maintains this speed and travels at a constant speed, and finally accelerates to the desired speed at a certain set acceleration of the vehicle at a certain moment, and just reaches the desired speed when entering the adaptation zone. By introducing the lowest cruise speed, this strategy further optimizes the driving trajectory of the vehicle and is applicable to the most stringent time constraint scenarios. The set acceleration of each vehicle is dynamically calculated based on its lowest cruise speed, target speed, and time constraint to ensure that the acceleration process is efficient and meets the time constraint.

[0060] The moment of the first acceleration change, the moment of the second acceleration change of the vehicle, and the set acceleration of the vehicle can be determined by the following formula:

[0061] where, is the lowest cruise speed of the section, with the unit .

[0062] To ensure the smooth switching and efficient execution of the speed control strategy, the present invention defines the boundary conditions between the four strategies. These boundary conditions are based on the initial speed, desired speed, time constraint of the vehicle entering the cooperative regulation area, and the kinematic characteristics of the vehicle to ensure the selection of the optimal speed control strategy under different time constraints. The specific boundary conditions and their descriptions are as follows: Boundary Condition One ( ): The vehicle first travels at a constant speed at the initial speed for a period of time, and then decelerates to the desired speed at the maximum deceleration and just reaches the desired speed when entering the adaptation zone. This boundary condition defines the upper limit of Strategy One and the lower limit of Strategy Two. The calculation formula is as follows:

[0063] Boundary Condition Two ( ): The vehicle first decelerates to the desired speed at the maximum deceleration, and then immediately maintains the desired speed and travels at a constant speed and enters the adaptation zone. This boundary condition defines the upper limit of Strategy Two and the lower limit of Strategy Three. The calculation formula is as follows:

[0064] Boundary condition three ( ): The vehicle first decelerates at the maximum deceleration to the lowest cruise speed, then accelerates at the set acceleration to the desired speed, and exactly reaches the desired speed when entering the intersection. This boundary condition defines the upper limit of Strategy Three and the lower limit of Strategy Four. The calculation formula is as follows:

[0065] Boundary condition four ( ): The vehicle first decelerates at the maximum deceleration to the lowest cruise speed, then maintains the lowest cruise speed for a period of time, and finally accelerates at the maximum acceleration to the desired speed, and exactly reaches the desired speed when entering the adaptation zone. This boundary condition defines the upper limit of Strategy Four. The calculation formula is as follows:

[0066] The roadside control center dynamically selects the optimal speed control strategy according to the comparison result of the time constraint of the vehicle and the above boundary conditions. The specific selection logic is as follows:

[0067] In the embodiment of the present invention, by setting a variety of candidate strategies and determining the target vehicle speed control strategy according to the relationship between the shortest required duration and the interval duration of each candidate vehicle speed regulation strategy, the optimality of the vehicle speed control strategy is ensured, and the traffic efficiency of the intersection is improved.

[0068] In some possible embodiments of the present invention, after determining the vehicle speed control strategy of each vehicle based on the interval duration between the earliest start crossing time and the current time, it includes: Optimizing the vehicle speed control strategy of the rear vehicle in the adjacent vehicles according to the initial speed of the adjacent vehicles in the same lane, the distance between the adjacent vehicles, and the preset safety distance between the adjacent vehicles, so as to ensure that when the speed of the rear vehicle is the same as the speed of the front vehicle in the adjacent vehicles, the distance between the rear vehicle and the front vehicle is greater than or equal to the preset safety distance.

[0069] In the embodiment of the present invention, in order to prevent rear-end collisions between vehicles in the same lane, a safety distance needs to be set. For adjacent vehicles in the same lane, if the speed of the rear vehicle is greater than the speed of the front vehicle, the speed of the rear vehicle needs to be adjusted. This adjustment process requires a safe adjustment distance. Calculate the distance required for the rear vehicle to decelerate to the speed of the front vehicle at the maximum deceleration. The formula is as follows:

[0070] Wherein, is the safety distance, is the driving speed of the rear vehicle, unit ; is the driving speed of the vehicle in front in the same lane as the following vehicle, with the unit ; is the driving reaction time of the intelligent driving vehicle, with the unit s ; is the minimum safe distance that should be maintained between vehicles, with the unit .

[0071] Within the intersection, considering that the expected speed of the right-turning vehicle is less than that of the straight-going vehicle, traffic conflicts may occur due to the speed difference when the straight-going vehicle merges with the right-turning vehicle in the adjacent direction and when the straight-going vehicle diverges from the right-turning vehicle in the same lane ahead. To solve this problem, the minimum safe time interval is added to the cell occupancy time of the above-mentioned right-turning vehicle . By delaying the time for the rear straight-going vehicle to occupy the same cell, the merging and diverging conflicts can be solved

[0072] Calculation formula for the minimum safe time interval:

[0073] where is the driving reaction time of the intelligent driving vehicle, with the unit s ; is the maximum acceleration of the vehicle, with the unit ; is the minimum safe distance that should be maintained between vehicles, with the unit .

[0074] Furthermore, taking the above safety distance as the control index, if it is detected that the distance between the following vehicle and the vehicle in front is lower than this safety distance, it is determined that there is a risk of rear-end collision in the same lane in the trajectory planning, and the current vehicle speed control strategy does not meet the safety requirements. The grey wolf optimization algorithm is introduced to re-plan the speed control strategy of the following vehicle. This algorithm optimizes the speed adjustment strategy of the following vehicle to ensure that the following vehicle reaches speed synchronization with the vehicle in front through a reasonable speed change operation. After that, the two vehicles maintain consistent driving behaviors, thus effectively avoiding rear-end collisions in the same lane and ensuring driving safety. Specifically, the specific calculation framework of the grey wolf optimization algorithm is as follows Step 1: Initially input the motion parameters of the front and rear vehicles, including information such as the vehicle speed control strategy, initial speed, start crossing time, vehicle speed regulation time, etc Step 2: Randomly initialize the position vector of the grey wolf population . Among them n is the scale of the wolf pack is the acceleration change time of the front and rear vehicles when they reach the same speed is the acceleration of the front and rear vehicles when they reach the same speed. For each wolf , according to its position vector in and value and calculate the motion trajectory of the following vehicle.

[0075] Step 3: Based on the vehicle distance when the two vehicles have the same speed, calculate the fitness value of each wolf. If the vehicle distance between the vehicles is always greater than the minimum safety distance throughout the process, the higher the fitness; conversely, if the vehicle distance is less than the minimum safety distance, the lower the fitness value. Sort the fitness values of all wolves, find the three wolves with the highest fitness, and determine them as Wolf, Wolf, Wolf, and record their positions as , .

[0076] Step 4: Update the positions of the optimal solution ( Wolf), the sub-optimal solution ( Wolf), and the third-optimal solution ( Wolf) in the wolf pack. Update the position of each wolf in the wolf pack according to the following formula:

[0077] where , , , and , , are coefficient vectors, and the calculation method is as follows: (j = 1, 2, 3) where , are random numbers between decreases linearly from 2 to 0 and decreases as the number of iterations increases to balance the global search and local search capabilities of the algorithm.

[0078] Step 5: Compare the fitness value of each wolf in the updated wolf pack with the fitness values of the current optimal solution ( Wolf), the sub-optimal solution ( Wolf), and the third-optimal solution ( Wolf). If the fitness value of a wolf is better than the current optimal solution or sub-optimal solution, etc., update the position of the corresponding optimal solution.

[0079] Step 6: After reaching the maximum number of iterations, stop the iteration and output the optimal solution ; otherwise, return to Step 4 to continue the iteration.

[0080] Based on this, the determined speed regulation strategy for the following vehicle can avoid rear-end collisions of vehicles.

[0081] In the embodiments of the present invention, vehicle rear-end collision detection is performed through an optimized algorithm, and the vehicle speed control strategy is optimized to prevent vehicle rear-end collisions and ensure vehicle passing safety.

[0082] As some possible embodiments of the present invention, such as Figure 8 shown, after determining the vehicle speed control strategy for each vehicle based on the time interval between the earliest start crossing time and the current time, it includes: S801, taking the vehicles entering the sensing area within the same moving time window as a group of vehicles; S802, using a preset optimization algorithm to optimize the order in which each vehicle in the group of vehicles passes through the intersection, so that the total time for each vehicle in the group of vehicles to pass through the intersection is the shortest.

[0083] In the embodiments of the present invention, in addition to regulating the speed of the vehicle, it is also necessary to determine the passing order of the vehicle. The present invention uses a moving time window and an improved simulated annealing algorithm to dynamically optimize the passing order of the vehicle. The optimization goal is to minimize the total delay of the vehicles within the group on the basis of ensuring vehicle passing safety and meeting vehicle constraint conditions. That is, the optimization goal is:

[0084] Among them, is the number of group optimization rounds; is the total number of vehicles entering the sensing area in the round; is the th vehicle entering the sensing area in the round; is the actual travel time of the th vehicle in the round of group optimization, with the unit ; is the ideal travel time of the th vehicle in the round of group optimization, with the unit

[0085] In the embodiments of the present invention, the vehicles entering the sensing area within the same time period are considered as a whole. Specifically, let be the moment when vehicle enters the sensing area, be the moment when vehicle leaves the sensing area. At this time, a time window is formed. The vehicles entering the sensing area within this window will be grouped together for order optimization. The next vehicle entering the sensing area later than will trigger the time window to move backward, and a new time window (where , is the moment when the vehicle leaves the sensing area), a new set of vehicles to be optimized is formed. The introduction of the moving time window enables the system to dynamically adjust the optimization range, ensuring that the passing order of vehicles is always in the optimal state under real-time traffic flow changes.

[0086] The improved simulated annealing algorithm combines the global search ability of the simulated annealing algorithm and the mutation mechanism of the genetic algorithm, significantly improving the convergence speed and optimization effect of the algorithm, and ensuring the optimality of the vehicle passing order. The specific calculation framework of the improved simulated annealing algorithm is as follows: Step l: Generate an initial feasible solution , that is, sort according to the order of the vehicle entering the sensing area, and calculate the cost function of the current solution to obtain .

[0087] Step2: Set the initial temperature , the temperature reduction coefficient , the termination temperature , and the temperature change function is .

[0088] Step3: At the current temperature, perform a neighborhood search on the current solution , and the neighborhood solution set is represented as .

[0089] Among them, A, B, C, D... represent the unique identifiers of vehicles.

[0090] Step4: Calculate the increment value , according to the Metropolis criterion, if ΔE < 0, then accept the new solution and update the current solution and the corresponding cost . Otherwise, calculate the state transition probability with the formula and accept the new solution with probability 𝑃. The specific state transition probability integration is as follows:

[0091] Step 5: Perform a temperature reduction operation according to the temperature change function , and check whether the termination condition is met, that is, whether the current temperature is less than the termination temperature . If the termination condition is met, end the iteration; otherwise, continue to return to Step3 to continue the neighborhood search and new solution acceptance process.

[0092] Step 6: When the entire iterative process terminates, record the current solution as the optimal solution. This optimal solution is the optimal passing sequence of the vehicles, which can significantly reduce the total delay time at the intersection and improve the passing efficiency.

[0093] In the standard simulated annealing algorithm, neighborhood search usually adopts the 2-swap two-point replacement method to generate neighborhood solutions by swapping two nodes in the path. Although it can effectively jump out of the local optimal solution, there is a contradiction between the global search ability and the calculation time, which easily leads to premature convergence. To overcome this limitation, the present invention introduces the mutation operator of the genetic algorithm, and by randomly changing the node positions or orders, it increases the randomness and globality of the search. This improvement not only expands the search range on the premise of ensuring the search speed, but also effectively avoids the algorithm from falling into the local optimum prematurely, and significantly improves the global search ability and optimization performance of the algorithm.

[0094] Through vehicle-road cooperation technology and intelligent algorithms, the present invention can dynamically optimize the passing sequence and speed control strategy at intersections, effectively solve the limitation that the existing signal control method cannot adapt to dynamic traffic demands, significantly reduce the vehicle delay time, and reduce fuel consumption and exhaust emissions. At the same time, in view of the particularity of right-turn vehicles, the present invention proposes a refined conflict resolution model and trajectory optimization strategy, which can effectively ensure the safe passing of through-right mixed vehicles at intersections and reduce the occurrence of traffic accidents. In addition, the present invention adopts a conflict resolution algorithm based on the cellular automaton model and an improved simulated annealing algorithm to optimize the passing sequence and vehicle trajectory planning at intersections, achieve more efficient conflict resolution and global optimization, and improve the passing efficiency and driving comfort at intersections. Finally, through vehicle-road cooperation technology and real-time data interaction, the present invention makes full use of the networking and intelligent characteristics of autonomous vehicles to realize dynamic cooperation and speed adjustment between vehicles, significantly improve the passing efficiency at intersections, reduce energy waste, and promote the development of intelligent transportation systems.

[0095] To better implement the vehicle control method at intersections in the embodiments of the present invention, correspondingly, based on the vehicle control method at intersections, as Figure 9 shown, the embodiments of the present invention also provide a vehicle control device at intersections. The vehicle control device 900 at intersections includes: The earliest arrival time calculation module 901 is configured to obtain the initial speed of the vehicles in the preset sensing area, and determine the earliest arrival time of the vehicles at the intersection based on the initial speed and the expected speed of the vehicles passing through the intersection; The earliest start passing time calculation module 902 is configured to determine the earliest available time of the target cell grid that the vehicle needs to occupy to pass through the intersection based on the occupancy of each cell grid at the intersection after the earliest arrival time, and determine the earliest start passing time when the vehicle can pass through the intersection based on the earliest available time; A vehicle speed control strategy determination module 903, configured to determine a vehicle speed control strategy for each vehicle based on the time interval between the earliest start crossing time and the current time, where the vehicle speed control strategy is used to adjust the speed of the vehicle from an initial speed to a desired speed within the time interval.

[0096] The intersection vehicle control device 900 provided in the above embodiment can implement the technical solutions described in the above embodiment of the intersection vehicle control method. The specific implementation principles of the above modules or units can be referred to the corresponding content in the above embodiment of the intersection vehicle control method, which will not be elaborated here.

[0097] As Figure 10 shown, the present invention also correspondingly provides a roadside device 1000. The roadside device 1000 includes a processor 1001 and a memory 1002. Figure 10 Only some components of the roadside device 1000 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0098] The processor 1001 may be a central processing unit (CPU), a microprocessor or other data processing chips in some embodiments, and is used to run the program code stored in the memory 1002 or process data, such as the intersection vehicle control method in the present invention.

[0099] In some embodiments, the processor 1001 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1001 may be local or remote. In some embodiments, the processor 1001 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0100] The memory 1002 may be an internal storage unit of the roadside device 1000, such as a hard disk or a memory of the roadside device 1000, in some embodiments. The memory 1002 may also be an external storage device of the roadside device 1000, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the roadside device 1000, in some other embodiments.

[0101] Furthermore, the memory 1002 may also include both the internal storage unit and the external storage device of the roadside device 1000. The memory 1002 is used to store the application software installed on the roadside device 1000 and various types of data.

[0102] In some embodiments, when the processor 1001 executes the intersection vehicle control program in the memory 1002, the following steps may be implemented: Obtain the initial speed of the vehicle in the preset sensing area, and determine the earliest arrival time of the vehicle at the intersection based on the initial speed and the expected speed of the vehicle passing through the intersection; Based on the occupancy of each cell grid at the intersection after the earliest arrival time, determine the earliest available time of the target cell grid that the vehicle needs to occupy to pass through the intersection, and determine the earliest start time for the vehicle to pass through the intersection based on the earliest available time; Determine the vehicle speed control strategy for each vehicle based on the time interval between the earliest start time to pass through and the current time. The vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the expected speed within the time interval.

[0103] It should be understood that when the processor 1001 executes the intersection vehicle control program in the memory 1002, in addition to the above functions, other functions may also be implemented. For specific details, please refer to the descriptions of the corresponding method embodiments above.

[0104] Correspondingly, an embodiment of the present application further provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the intersection vehicle control method provided by the above method embodiments can be implemented.

[0105] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0106] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for controlling vehicles at an intersection, characterized in that: include: Obtaining an initial speed of the vehicle in the preset sensing area, and determining the earliest arrival time of the vehicle at the intersection based on the initial speed and an expected speed of the vehicle crossing the intersection; Determine the earliest occupancy time of the target cellular grid that the vehicle needs to occupy when crossing the intersection based on the occupancy status of each cellular grid at the intersection after the earliest arrival time, and determine the earliest starting crossing time when the vehicle can cross the intersection based on the earliest occupancy time; The vehicle speed control strategy of each vehicle is determined based on the interval between the earliest start crossing time and the current time, and the vehicle speed control strategy is used to adjust the speed of the vehicle from the initial speed to the expected speed within the interval time.

2. The vehicle control method at an intersection according to claim 1, characterized in that: The determining the earliest arrival time of the vehicle at the intersection based on the initial speed and the expected speed of the vehicle crossing the intersection comprises: The earliest time at which the vehicle reaches the intersection with the optimal acceleration performance and the optimal braking performance and the speed of the vehicle when it reaches the intersection is calculated as the expected speed.

3. The vehicle control method at an intersection according to claim 1, characterized in that: The determining the earliest occupancy time of the target cellular grid that each vehicle needs to occupy when crossing the intersection based on the occupancy status of each cellular grid at the intersection after the earliest arrival time includes: Determine the target cellular grid that the vehicle needs to occupy when crossing the intersection based on the driving direction of the vehicle; The earliest occupancy time of each of the target cellular grids after the earliest arrival time is determined based on a preset time-cellular grid matrix; the time-cellular grid matrix is ​​used to represent the occupancy status of each cellular grid at each time.

4. The vehicle control method at an intersection according to claim 3, characterized in that: The determining, based on the earliest occupiable time, the earliest start time at which the vehicle can cross the intersection comprises: The earliest start crossing time at which the vehicle can continuously cross each target cellular grid is calculated based on the order in which the vehicle crosses each target cellular grid, the earliest occupiable time of each target cellular grid, and the duration of the vehicle crossing each target cellular grid.

5. The method for controlling vehicles at an intersection according to claim 1, characterized in that: The determining of the vehicle speed control strategy of each vehicle based on the interval between the earliest start crossing time and the current time includes: Determining a plurality of preset candidate vehicle speed control strategies based on a magnitude relationship between the initial speed and the expected speed; Calculating the shortest required time for each of the candidate vehicle speed control strategies to adjust the vehicle speed from the initial speed to the desired speed within the preset coordinated control area; The target vehicle speed control strategy is determined based on the relationship between the shortest required duration of each candidate vehicle speed regulation strategy and the interval duration.

6. The vehicle control method at an intersection according to claim 1, characterized in that: After determining the vehicle speed control strategy of each vehicle based on the interval between the earliest start crossing time and the current time, the method includes: The speed control strategy of the rear vehicle among the adjacent vehicles is optimized according to the initial speeds of the adjacent vehicles in the same lane, the distance between the adjacent vehicles, and the preset safety distance between the adjacent vehicles, so as to ensure that when the speed of the rear vehicle is the same as the speed of the front vehicle among the adjacent vehicles, the distance between the rear vehicle and the front vehicle is greater than or equal to the preset safety distance.

7. The method for controlling vehicles at an intersection according to claim 1, characterized in that: After determining the vehicle speed control strategy of each vehicle based on the interval between the earliest start crossing time and the current time, the method includes: The vehicles entering the sensing area within the same moving time window are regarded as the same group of vehicles; A preset optimization algorithm is used to optimize the order in which each vehicle in the same group of vehicles passes through the intersection, so that the total time for each vehicle in the same group of vehicles to pass through the intersection is the shortest.

8. A vehicle control device at an intersection, characterized in that: include: An earliest arrival time calculation module, used to obtain an initial speed of a vehicle in a preset perception area, and determine the earliest arrival time of the vehicle at the intersection based on the initial speed and an expected speed of the vehicle crossing the intersection; An earliest start crossing time calculation module is used to determine the earliest occupancy time of the target cellular grid that the vehicle needs to occupy when crossing the intersection based on the occupation status of each cellular grid of the intersection after the earliest arrival time, and determine the earliest start crossing time at which the vehicle can cross the intersection based on the earliest occupancy time; The vehicle speed control strategy determination module is used to determine the vehicle speed control strategy of each vehicle based on the interval between the earliest starting crossing time and the current time, and the vehicle speed control strategy is used to adjust the vehicle speed from the initial speed to the expected speed within the interval time.

9. A roadside equipment, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the intersection vehicle control method described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the intersection vehicle control method described in any one of claims 1 to 7.

Images