Tidal lane layout optimization method and system for fully connected autonomous driving scenarios

Abstract

The present invention discloses a tidal lane layout optimization method and system for a fully connected autonomous driving scenario, aiming to optimize the number of lanes and direction allocation by making full use of existing road resources and the technical advantages of connected autonomous driving vehicles, so as to achieve the goal of reducing the total travel cost of the road network. The present invention combines genetic algorithms with mathematical optimization models, considers the mutual influence of two types of connected autonomous driving vehicles with different ownership and lane planning decisions and travelers' path selection behaviors, and flexibly adjusts the number of lanes in different driving directions to adapt to traffic needs at different times. The tidal lane layout optimization method proposed in the present invention significantly improves the traffic efficiency of the road network, reduces traffic congestion, and demonstrates the potential and advantages of connected autonomous driving technology in traffic management.

Description

Technical Field

[0001] The present invention relates to the field of intelligent traffic management technology, and in particular to a tidal lane layout optimization method and system for a fully connected autonomous driving scenario. Background Art

[0002] With the rapid development of Internet of Vehicles and autonomous driving technologies, connected and autonomous vehicles (CAV) will gradually replace existing manually driven vehicles, and the entire society will enter the era of connected and autonomous driving, and residents' travel choices will also undergo earth-shaking changes. For traditional online car-hailing and taxi travel, since the driver's labor cost is an important part of the online car-hailing fee, this leads to a higher cost of using online car-hailing, and families who choose to travel by car for daily commuting tend to choose to buy private cars. At the same time, since CAV can be uniformly controlled by the cloud center and does not require a human driver, this means that CAV is easy to operate as an online car-hailing and will greatly reduce the cost of passengers. It is generally believed that online car-hailing will be the first application scenario of CAV in a fully connected and autonomous driving environment, which will lead to a large number of residents choosing not to own a private car and instead adopting connected and autonomous online car-hailing as a daily travel method. Therefore, in the future connected autonomous driving environment, CAVs in cities will be divided into two categories based on their ownership: one is the connected autonomous private car (PCAV), which is owned by individual residents, and individual travelers choose travel routes according to the rule of minimizing travel time; the other is the connected autonomous online car-hailing (SCAV), which is owned by the online car-hailing operating company. All vehicles are centrally dispatched by the operating company's cloud center, and travel routes are selected according to the rule of minimizing the total travel time of all operating vehicles.

[0003] At the same time, major cities are generally facing unbalanced travel demands. There is a common tidal phenomenon in the traffic flow of road sections during peak hours in the morning and evening. There are fewer vehicles in one direction of the lane, but at the same time there is serious traffic congestion in the opposite lane. Faced with such unbalanced travel demands, the deployment of tidal lanes is recognized as the best solution to alleviate traffic congestion. However, in traditional traffic scenarios, the deployment of tidal lanes requires the use of matching hardware facilities such as tidal lane zipper cars and special water horses, and can only change the driving direction of a single lane at a time. In the networked autonomous driving environment, since the networked autonomous driving vehicles are uniformly controlled by the cloud center, they can change the driving direction of multiple lanes in real time according to the instructions of the cloud center without relying on hardware facilities such as tidal lane zipper cars and special water horses, which greatly reduces the daily operating costs of tidal lanes. Therefore, the deployment and use of tidal lanes in a fully networked autonomous driving environment will be more convenient and efficient, and will give full play to the role of tidal lanes in utilizing limited road space resources and improving road traffic efficiency. Summary of the invention

[0004] In view of the defects of the prior art, the present invention provides a tidal lane layout optimization method and system for a fully connected autonomous driving scenario. Based on the uneven travel demand, considering two different vehicles, PCAV and SCAV, the number of lanes in different driving directions of each section in the existing traffic network is optimized, and the tidal lane layout scheme with the highest traffic efficiency of the entire road network is obtained, thereby optimizing the spatial distribution of PCAV and SCAV vehicles in the road network, and finally achieving the goal of reducing the total travel cost of the road network.

[0005] In order to achieve the above invention object, the technical solution adopted by the present invention is as follows:

[0006] A tidal lane layout optimization method for a fully connected autonomous driving scenario includes the following steps:

[0007] Step 1: Create an urban road network model, including a node set N and a road segment set A, and identify the starting point set R and the end point set S of the travel demand.

[0008] Step 2: Introduce the variable z of the number of lanes on the road segment ij , the starting point of the road section is i, the end point of the road section is j, and the number of lanes in different driving directions is constrained.

[0009] Step 3: Use the segment travel cost model to calculate the travel cost of each segment (i, j).

[0010] Step 4: Ensure that the vehicle flow from each road section to the end point s is non-negative and satisfies the conservation conditions of the node's inflow and outflow flows.

[0011] Step 5: Establish the user equilibrium condition for PCAV traffic, requiring that the marginal cost brought by PCAV vehicle traffic is equal to the marginal cost difference on the shortest path of the road section.

[0012] Step 6: Establish the system optimal conditions for SCAV traffic flow to ensure that the sum of all SCAV vehicle travel costs is minimized, reflecting the optimal SCAV usage pattern.

[0013] Step 7, establish an optimization model with the goal of minimizing the total travel cost of the road network, including decision variables such as vehicle flow and number of lanes, and apply the above constraints.

[0014] Step 8, use the combination of genetic algorithm and GAMS solver to solve the mixed integer nonlinear programming problem and obtain the optimal tidal lane layout solution.

[0015] Furthermore, in step 1, the graph model G(N,A) is used to represent the road network, where N represents the node set and A represents the road segment set. Let R and S represent the set of starting points and end points in the road network respectively. Let r and s represent a starting point and an end point in the road network respectively, r∈R, s∈S, (i,j) represents the road section with starting point i and end point j, (i,j)∈A.

[0016] Furthermore, in step 2, the number of lanes z ij The following constraints must be met:

[0017]

[0018] Formula (1) indicates that the sum of the number of lanes on the road section (i, j) and the number of lanes on the road section (j, i) in the optimized road network should be less than or equal to the total number of lanes that do not distinguish directions between nodes i and j in the existing road network. Formula (2) indicates that the number of lanes on the road section (i, j) in the optimized road network should be a non-negative integer.

[0019] Furthermore, in step 3, the travel cost of the road segment is calculated as follows:

[0020]

[0021] In the formula, represents the free flow travel time of road segment (i, j); represents the sum of the traffic of PCAV and SCAV on the road section; c ij represents the traffic capacity of a single lane of road section (i, j); c ij z ij Represents the traffic capacity of road section (i, j); α, β are non-negative parameters in the BPR function.ij is a binary variable. When the number of lanes on the road section (i, j) is 0 (z ij =0), δ ij = 0, otherwise, the number of lanes in the road section (i, j) is not 0 (z ij ≠0), δ ij =1.

[0022] Furthermore, in step 4, it is ensured that the vehicle flow to the end point s is non-negative, as shown in the following formula:

[0023]

[0024] The inflow and outflow conservation conditions of the node are as follows:

[0025] For each node i except the terminal s, the vehicle flow out of the node and ending at s should be equal to the vehicle flow into the node and ending at s.

[0026] For a terminal s, the vehicle flow into the terminal should be equal to the inverse of the total demand of all starting points for the terminal.

[0027] Furthermore, the user balance condition in step 5 includes:

[0028] If there is PCAV flow on the road segment (i, j), then the road segment is on the shortest path from node i to end point s, and the PCAV travel cost on this road segment should be equal to the minimum travel cost from node i to end point s minus the minimum travel cost from node j to end point a.

[0029] If there is no PCAV traffic on the road segment (i, j), the travel cost of the PCAV on this road segment should be greater than or equal to the minimum travel cost from node i to the end point s minus the minimum travel cost from node j to the end point s.

[0030] The flow rate of PCAV should be non-negative.

[0031] Furthermore, determining the optimal conditions of the system in step 6 includes:

[0032] The generalized travel cost of SCAV on the shortest path should be equal to the generalized minimum travel cost from node i to end point s minus the generalized minimum travel cost from node j to end point a.

[0033] If there is no SCAV flow on the road segment (i, j), the generalized travel cost of SCAV on this road segment should be greater than or equal to the generalized minimum travel cost from node i to end point s minus the generalized minimum travel cost from node j to end point s.

[0034] The flow rate of SCAV should be non-negative.

[0035] Furthermore, in step 7, the optimization model is constructed as follows:

[0036]

[0037] in, and They represent the flow of PCAV and SCAV on the road segment (i, j) flowing to the end point s; t ij Represents the travel cost of road segment (i, j).

[0038] The constraints include: number of lanes for different driving directions, calculation of road section travel cost, non-negative flow and flow conservation constraints, user equilibrium constraints and user system optimal constraints.

[0039] The present invention also discloses a tidal lane layout optimization system for a fully networked autonomous driving scenario, which can be used to implement the above-mentioned tidal lane layout optimization method, specifically including:

[0040] Road network construction module: Create a city road network model, including a node set and a road segment set, and identify the starting point set and the end point set.

[0041] Lane number relationship module: introduces the lane number variable on the road section and satisfies the lane number constraints for different driving directions.

[0042] Travel cost calculation module: Use the road segment travel cost model to calculate the travel cost of each road segment.

[0043] Non-negative flow and flow conservation constraint module: ensure that the vehicle flow to the end point is non-negative and satisfies the inflow and outflow conservation conditions of the node.

[0044] User equilibrium condition module: establishes the user equilibrium condition for PCAV traffic, requiring that the marginal cost brought by PCAV vehicle traffic is equal to the marginal cost difference on the shortest path of the road section.

[0045] System optimal condition module: establishes the system optimal condition for SCAV traffic, ensures that the sum of all SCAV vehicle travel costs is minimized, and reflects the best SCAV usage pattern.

[0046] Optimization model building module: Establish an optimization model with the goal of minimizing the total travel cost of the road network, including decision variables such as vehicle flow and number of lanes, and apply the above constraints.

[0047] Optimization solution module: Use the combination of genetic algorithm and GAMS solver to solve the mixed integer nonlinear programming problem and obtain the optimal tidal lane layout solution.

[0048] Result display module: displays the optimization results, including the optimal lane layout plan, lane configuration of each road section and corresponding travel cost analysis.

[0049] The present invention also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned tidal lane layout optimization method when executing the program.

[0050] The present invention also discloses a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned tidal lane layout optimization method is implemented.

[0051] Compared with the prior art, the advantages of the present invention are:

[0052] 1. Improve the traffic efficiency of the road network: By flexibly setting the number of lanes in each direction and adjusting them according to real-time travel needs, the existing lane resources can be maximized, thereby optimizing the traffic efficiency of the road network.

[0053] 2. Alleviate traffic congestion: The optimized lane layout can effectively alleviate traffic congestion, especially during peak hours and congested nodes. By optimizing lane allocation and reducing bottlenecks on the road section, vehicles can pass through the road section more smoothly.

[0054] 3. Adapt to networked autonomous driving technology: Combining the characteristics and advantages of networked autonomous driving technology, such as real-time data exchange and intelligent road condition adaptability, it can respond to traffic changes more accurately and improve the overall operating efficiency of the system.

[0055] 4. Flexibility and adjustability: The method allows the lane layout to be adjusted according to the traffic demand in different time periods and regions. It has strong flexibility and adjustability and can quickly adapt to different traffic conditions and travel modes.

[0056] 5. Significant cost-effectiveness: By reducing the total travel cost of the road network, such as the case where the total travel cost of the optimized road network was reduced by 52.38%, it shows that this method can significantly improve traffic operation efficiency and reduce economic costs.

[0057] 6. Sustainability advantage: By reducing traffic congestion and vehicle emissions, the optimized road network can have a positive impact on the urban environment and promote the goal of sustainable urban development. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of the Nguyen-Dupuis network structure of an embodiment of the present invention.

[0059] Figure 2 It is a schematic diagram of the number of lanes of section 7 and section 26 before and after the optimization of the tidal lane layout according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and examples.

[0061] The present invention provides a tidal lane layout optimization method for a fully connected autonomous driving scenario, comprising the following steps:

[0062] Step 1: Construction of urban road network for fully connected autonomous driving scenarios

[0063] First, the road network for the fully connected autonomous driving scenario is constructed. G(N,A) is used to represent the road network, where N represents the node set and A represents the road segment set. R and S represent the set of starting points and end points in the road network, respectively. r and s represent a starting point and an end point in the road network, r∈R, s∈S. (i,j) represents a road segment with starting point i and end point j, (i,j)∈A. The traffic on the road segment will be distinguished by the different end points and vehicle types (PCAV or SCAV). For example, Represents the flow of SCAV on the link (i, j) flowing to the end point s.

[0064] Step 2: Constraints on the number of lanes for different driving directions in the lane layout scheme

[0065] For the existing road network, ij is used to represent the total number of lanes that do not distinguish directions between nodes i and j. For the road network after the deployment of tidal lanes (referred to as the optimized road network), z ij Represents the number of lanes on the road segment (i, j), which needs to satisfy the following constraints:

[0066]

[0067] In the formula, l ij Indicates the total number of lanes that do not distinguish between directions between nodes i and j in the existing road network; Formula (1) indicates that the sum of the number of lanes on the section (i, j) and the number of lanes on the section (j, i) in the optimized road network should be less than or equal to the total number of lanes that do not distinguish between directions between nodes i and j in the existing road network. Formula (2) indicates that the number of lanes on the section (i, j) in the optimized road network should be a non-negative integer.

[0068] Step 3. Calculation of road segment travel cost

[0069] The travel cost of road segment (i, j) is calculated using the Bureau of Public Roads (BPR) function. Since the number of lanes in road segment (i, j) can be 0 (z ij=0), in order to ensure that the traffic capacity as the denominator in the BPR function is always not 0, a binary variable δ ij and an arbitrary positive number H to transform the original BPR function. In summary, the calculation of the road segment travel cost can be expressed as follows:

[0070]

[0071] In the formula, represents the free flow travel time of road segment (i, j); represents the traffic volume of PCAV and SCAV vehicles on the road section; c ij represents the traffic capacity of a single lane of road section (i, j); c ij z ij Represents the traffic capacity of road section (i, j); α, β are non-negative parameters in the BPR function. ij is a binary variable. When the number of lanes on the road section (i, j) is 0 (z ij =0), δ ij = 0, otherwise, the number of lanes in the road section (i, j) is not 0 (z ij ≠0), δ ij =1.

[0072] Step 4. Flow non-negativity and flow conservation constraints

[0073] For each road segment (i, j) in the road network, the flow of PCAV and SCAV flowing to the end point s is non-negative, as shown in formula (4). For each node in the road network (except the end point), the flow out of node j and ending at s is equal to the flow into node j with s as the end point (including the travel demand generated by node j with s as the end point), as shown in formula (5); for the end point, the flow into the end point s is equal to the total travel demand from all starting points to the end point s, as shown in formula (6). In summary, it can be expressed as follows:

[0074]

[0075] In the formula, represents the flow of m-type vehicles (PCAV or SCAV) on the road segment (i, j) flowing to the end point s; It represents the travel demand of m types of vehicles (PCAV or SCAV) between node i and end point s.

[0076] Step 5. User equilibrium constraints

[0077] PCAV selects the travel path according to the principle of User Equilibrium (UE). The user equilibrium based on link-node can be expressed as follows: when the road network reaches equilibrium, if there is PCAV traffic on link (i, j), then the link (i, j) is on the shortest path from node i to end point s, and the travel cost of PCAV on link (i, j) should be equal to the minimum travel cost from node i to end point s minus the minimum travel cost from node j to end point s; if there is no PCAV traffic on link (i, j), then the link is not on the shortest path from node i to end point s, and the travel cost of PCAV on link (i, j) is greater than or equal to the minimum travel cost from node i to end point s minus the minimum travel cost from node j to end point s. The mathematical expression of the user equilibrium in the form of equivalent complementary relaxation is as follows:

[0078]

[0079]

[0080] In formulas (7)-(9), M is a large number tending to positive infinity; represents the minimum PCAV travel cost from node j to end point s; represents the minimum travel cost of PCAV from node i to end point s; the flow of PCAV on the road section PCAV flow on road sections with different end points The relationship between

[0081] Step 6. System Optimization Constraints

[0082] SCAV selects travel paths according to the principle of system optimality (SO). By adding a marginal travel cost to the travel cost function, the system optimality can also be regarded as a user equilibrium (UE) with a generalized travel cost. The link-node-based system optimality can be expressed as follows: when the road network reaches equilibrium, if there is SCAV flow on link (i, j), then the link is on the shortest path from node i to terminal s, and the generalized travel cost of SCAV on link (i, j) should be equal to the generalized minimum travel cost from node i to terminal s minus the generalized minimum travel cost from node j to terminal s; if there is no SCAV flow on link (i, j), then the link is not on the shortest path from node i to terminal s, and the generalized travel cost of SCAV on link (i, j) is greater than or equal to the generalized minimum travel cost from node i to terminal s minus the generalized minimum travel cost from node j to terminal s. The mathematical expression of the user equilibrium of the generalized travel cost in the equivalent complementary relaxation form is as follows:

[0083]

[0084] In formulas (10)-(13), ε ij is the marginal travel cost of road section (i, j); M is a large number tending to positive infinity; represents the generalized minimum travel cost of the SCAV from node j to the destination s; represents the generalized minimum travel cost of SCAV from node i to end point s; the flow of SCAV on the road section SCAV flow of road sections with different end points The relationship between

[0085] Step 7. Model construction

[0086] A tidal lane layout optimization model [LOP] for fully connected autonomous driving scenarios is established, in which the optimization goal is to minimize the total travel cost of the road network. The objective function is shown in Equation (14), and the traffic flow of the destination and vehicle type is distinguished by the road segment in the road network. and the number of lanes in different driving directions z ij ,z ij is the decision variable, and equations (1)-(13) are the constraints of the model. In summary, the optimization model is constructed as follows:

[0087] [LOP]

[0088]

[0089] Constraints:

[0090] a) Lane number and direction constraints (1)-(2);

[0091] b) Calculation of road segment travel cost (3);

[0092] c) non-negative flow and flow conservation constraints (4)-(6);

[0093] d) User equilibrium constraints (7)-(9);

[0094] e) User system optimal constraints (10)-(13).

[0095] Step 8. Model solution

[0096] Since [LOP] is a mixed integer nonlinear programming problem, the genetic algorithm function (GA) integrated in MATLAB is used to integrate and call the GAMS solver for solution. The specific steps are as follows:

[0097] The first step is to define a traffic assignment sub-function and use it as the fitness function of GA, and call the GAMS solver in this sub-function.

[0098] The second step is to set the independent variable of the fitness function (z ij ) and the upper and lower bounds of the independent variables, and define the linear inequality constraints that the independent variables need to satisfy.

[0099] The third step is to set the parameters of the GA function (population size, crossover rate, mutation rate, etc.).

[0100] In the fourth step, the custom fitness function, the number of independent variables of the fitness function, the linear inequality constraints that the independent variables need to satisfy, the upper and lower bounds of the independent variables, and the GA parameters are used as the input of the GA function.

[0101] The fifth step is to run the GA function and output the results to obtain the tidal lane layout optimization plan.

[0102] This embodiment adopts the Nguyen-Dupuis network (such as Figure 1 As shown in the figure, it contains 13 nodes, 38 road segments and 8 OD pairs (1-2, 1-3, 4-2, 4-3, 2-1, 2-4, 3-1, 3-4), and its OD requirements are:

[0103] The detailed section information of the Nguyen-Dupuis network is shown in Table 1 below. After the tidal lane layout is optimized according to the method of the present invention, the lane optimization layout results of the Nguyen-Dupuis network are shown in Table 2, wherein the lane optimization results of the section 7 and the section 26 between the nodes 6 and 7 in the optimized Nguyen-Dupuis network are shown in Table 2. Figure 2 The total travel cost of the optimized road network was reduced from 762052.31h to 362917.96h, with a cost reduction of 52.38%.

[0104] Table 1. Section information of Nguyen-Dupuis network

[0105]

[0106]

[0107] Table 2 Nguyen-Dupuis network lane layout optimization results

[0108]

[0109] In another embodiment of the present invention, a tidal lane layout optimization system for a fully connected autonomous driving scenario is provided. The system can be used to implement the above-mentioned tidal lane layout optimization method, specifically including:

[0110] Road network construction module: Create an urban road network model, including a set of nodes and a set of road sections, and identify the starting point set and the end point set of travel needs.

[0111] Lane number relationship module: introduces the lane number variable on the road section and satisfies the lane number constraints for different driving directions.

[0112] Travel cost calculation module: Use the road segment travel cost model to calculate the travel cost of each road segment.

[0113] Non-negative flow and flow conservation constraint module: ensure that the vehicle flow to the end point is non-negative and satisfies the inflow and outflow conservation conditions of the node.

[0114] User equilibrium condition module: establishes the user equilibrium condition for PCAV traffic, requiring that the marginal cost brought by PCAV vehicle traffic is equal to the marginal cost difference on the shortest path of the road section.

[0115] System optimal condition module: establishes the system optimal condition for SCAV traffic, ensures that the sum of all SCAV vehicle travel costs is minimized, and reflects the best SCAV usage pattern.

[0116] Optimization model building module: Establish an optimization model with the goal of minimizing the total travel cost of the road network, including decision variables such as vehicle flow and number of lanes, and apply the above constraints.

[0117] Optimization solution module: Use the combination of genetic algorithm and GAMS solver to solve the mixed integer nonlinear programming problem and obtain the optimal tidal lane layout solution.

[0118] Result display module: displays the optimization results, including the optimal lane layout plan, lane configuration of each road section and corresponding travel cost analysis.

[0119] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the tidal lane layout optimization method.

[0120] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0121] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the tidal lane layout optimization method in the above embodiment; one or more instructions in the computer-readable storage medium are loaded and executed by the processor.

[0122] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0124] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the implementation methods of the present invention, and should be understood that the protection scope of the present invention is not limited to such special statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A tidal lane layout optimization method for a fully connected autonomous driving scenario, characterized by: The following steps are involved: Step 1: Create a city road network model, including a node set N and a road segment set A, and identify the starting point set R and the end point set S of the travel demand; In step 1, the graph model G(N,A) is used to represent the road network, where N represents the node set and A represents the road segment set; Let R and S represent the set of starting points and end points in the road network respectively, Let r and s represent a starting point and an end point in the road network respectively, r∈R, s∈S, (i,j) represents the road segment with starting point i and end point j, (i,j)∈A; Step 2: Introduce the variable z of the number of lanes on the road segment ij , the starting point of the road section is i, the end point of the road section is j, and the number of lanes in different driving directions is satisfied; the number of lanes on the road section is z ij The following constraints must be met: In the formula, l ij represents the total number of lanes that do not distinguish between directions between nodes i and j in the existing road network; Formula (1) indicates that the sum of the number of lanes on the road section (i, j) and the number of lanes on the road section (j, i) in the optimized road network should be less than the total number of lanes that do not distinguish between directions between nodes i and j in the existing road network; Formula (2) indicates that the number of lanes on the road section (i, j) in the optimized road network should be a non-negative integer; Step 3: Use the segment travel cost model to calculate the travel cost of each segment (i, j); the segment travel cost calculation is expressed as follows: In the formula, represents the free flow travel time of road segment (i, j); represents the sum of the traffic of PCAV and SCAV on the road section; c ij represents the traffic capacity of a single lane of road section (i, j); c ij z ij represents the traffic capacity of road section (i, j); α, β are non-negative parameters in the BPR function; δ ij is a binary variable. When the number of lanes on the road section (i, j) is 0 (z ij =0), δ ij = 0, otherwise, the number of lanes in the road section (i, j) is not 0 (z ij ≠0), δ ij =1; Step 4: Ensure that the vehicle flow from each road section to the end point s is non-negative and meets the conservation conditions of the node's inflow and outflow; ensure that the vehicle flow to the end point s is non-negative, as shown in the following formula: The inflow and outflow conservation conditions of the node are as follows: For each node i except the terminal s, the vehicle flow out of the node and ending at s should be equal to the vehicle flow into the node and ending at s; For the terminal s, the vehicle flow into the terminal should be equal to the inverse of the total demand of all starting points for the terminal; Step 5: Establish the user equilibrium condition for PCAV traffic, requiring that the marginal cost brought by PCAV vehicle traffic is equal to the marginal cost difference on the shortest path of the road section; the user equilibrium condition includes: If there is PCAV flow on the road segment (i, j), then the road segment is on the shortest path from node i to end point s, and the travel cost of PCAV on this road segment should be equal to the minimum travel cost from node i to end point s minus the minimum travel cost from node j to end point s; If there is no PCAV traffic on the road segment (i, j), the travel cost of PCAV on this road segment should be greater than or equal to the minimum travel cost from node i to end point s minus the minimum travel cost from node j to end point s; The flow rate of PCAV should be non-negative; Step 6: Establish the optimal conditions for SCAV traffic flow, ensure that the sum of all SCAV vehicle travel costs is minimized, and reflect the best SCAV usage pattern; determine the optimal conditions for the system including: The generalized travel cost of SCAV on the shortest path should be equal to the generalized minimum travel cost from node i to end point s minus the generalized minimum travel cost from node j to end point s; If there is no SCAV flow on the road segment (i, j), the generalized travel cost of SCAV on this road segment should be greater than or equal to the generalized minimum travel cost from node i to end point s minus the generalized minimum travel cost from node j to end point s; The flow rate of SCAV should be non-negative; Step 7, establish an optimization model with the goal of minimizing the total travel cost of the road network, including decision variables such as vehicle flow and number of lanes, and apply constraints, including: number of lanes for different driving directions, calculation of road segment travel cost, non-negative flow and flow conservation constraints, user equilibrium constraints and user system optimal constraints; The optimization model is constructed as follows: in, and They represent the flow of PCAV and SCAV on the road segment (i, j) flowing to the end point s; t ij represents the travel cost of road segment (i, j); Step 8, use the combination of genetic algorithm and GAMS solver to solve the mixed integer nonlinear programming problem and obtain the optimal tidal lane layout solution.

2. A tidal lane layout optimization system for a fully connected autonomous driving scenario, characterized by: The system can be used to implement the tidal lane layout optimization method described in claim 1, specifically including: Road network construction module: Create a city road network model, including a set of nodes and a set of road sections, and identify the starting point set and the end point set of travel needs; Lane quantity relationship module: introduces the lane quantity variable on the road section and satisfies the lane quantity constraints of different driving directions; Travel cost calculation module: uses the road segment travel cost model to calculate the travel cost of each road segment; Non-negative flow and flow conservation constraint module: ensure that the vehicle flow to the end point is non-negative and satisfies the inflow and outflow conservation conditions of the node; User equilibrium condition module: establishes the user equilibrium condition for PCAV traffic, requiring that the marginal cost brought by PCAV vehicle traffic is equal to the marginal cost difference on the shortest path of the road section; System Optimal Condition Module: Establishes the system optimal conditions for SCAV traffic, ensures that the sum of all SCAV vehicle travel costs is minimized, and reflects the best SCAV usage pattern; Optimization model building module: Building an optimization model with the goal of minimizing the total travel cost of the road network, including decision variables such as vehicle flow and number of lanes, and applying the above constraints; Optimization solution module: Use the combination of genetic algorithm and GAMS solver to solve the mixed integer nonlinear programming problem and obtain the optimal tidal lane layout solution; Result display module: displays the optimization results, including the optimal lane layout plan, lane configuration of each road section and corresponding travel cost analysis.

3. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the tidal lane layout optimization method described in claim 1 when executing the program.

Images