Intelligent connection method and system based on modularized automatic driving vehicle
Through the intelligent shuttle system of modular autonomous driving vehicles, dynamic scheduling and path planning is used to use passenger demand information, the problem of inconvenience in bus services in low-density areas is solved, and the efficiency of shuttle service and traffic safety are improved.
Patent Information
- Application Number
- CN202411124343.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-16
AI Technical Summary
In low-density areas, bus operation costs are high and the return on investment is low, making it difficult to meet residents' immediate travel needs, especially for the elderly and disabled passengers, and the increase in private cars has caused serious environmental and traffic congestion.
Using an intelligent connection method and system based on modular autonomous driving vehicles, intelligent connection is realized by obtaining passenger transfer appointments and historical demand information, optimal departure time interval and service community area planning, dynamic scheduling and path planning are carried out.
It improves the reliability and efficiency of shuttle services, improves resource utilization and vehicle flexibility, significantly improves driving safety and traffic efficiency, and reduces traffic accidents and congestion problems.
Smart Images

Figure CN119028163A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent traffic management technology, and in particular to an intelligent docking method and system based on modular autonomous driving vehicles. Background Art
[0002] The urban space scale in my country is expanding. Many large cities are becoming more suburbanized. More and more people choose to live on the edge of the city far from the city center. Residents need to take shuttle buses to reach the starting station of urban rail transit or nearby airports, stations and other transportation hubs. In low-density areas, residents have little travel demand and their residential locations are scattered, making it difficult to concentrate on regular bus routes. Therefore, passengers need to walk to fixed bus stops, and the bus departure intervals in low-density areas are large, making it difficult to meet immediate needs. For special groups such as the elderly or disabled passengers in the suburbs of the city, bus travel is even more inconvenient. In areas with low passenger density, conventional bus routes have high operating costs and low investment returns. Some newly developed suburbs have even become blind spots for bus services. As a result, the number of private cars has further increased, and the resulting environmental problems and urban congestion problems have become increasingly serious. What kind of operation mode should be adopted to balance the interests between operators and passengers has become a difficult problem that needs to be solved urgently.
[0003] Therefore, there is an urgent need for a method and system that can intelligently connect passengers to solve the above problems. Summary of the invention
[0004] The purpose of the present invention is to provide an intelligent docking method and system based on modular autonomous driving vehicles to improve the above problems. In order to achieve the above purpose, the technical solutions adopted by the present invention are as follows:
[0005] In a first aspect, the present application provides an intelligent docking method based on a modular autonomous driving vehicle, comprising:
[0006] Acquire the passenger's transfer reservation information and the passenger's historical transfer demand information, wherein the passenger's transfer reservation information includes the passenger's reservation time information and transfer location information, and the passenger's historical transfer demand information includes the passenger's historical transfer demand quantity information and the passenger's historical transfer demand location information;
[0007] Send the historical connection demand information and the connection reservation information of the passengers to the preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service community area planning of the modular autonomous driving vehicles, and obtain the optimal departure time interval and service community area of the planned modular autonomous driving vehicles;
[0008] Performing vehicle dispatching and path planning based on the passenger's pick-up reservation information, the optimal departure time interval of the planned modular autonomous driving vehicle, and the service area, to obtain the planned vehicle dispatch path information;
[0009] Based on the planned vehicle path scheduling information, the modular autonomous driving vehicle is controlled to disassemble and group passengers, and the vehicle vacancy information and the passenger's grouping reservation information are obtained in real time, and the vehicle scheduling and path planning are repeated until the modular autonomous driving vehicle arrives at the preset first designated location for grouping;
[0010] The modular self-driving vehicles are assembled and run to the first designated location along a preset route.
[0011] In the second aspect, the present application also provides an intelligent docking system based on a modular autonomous driving vehicle, comprising:
[0012] an acquisition unit, configured to acquire the passenger's connection reservation information and the passenger's historical connection demand information, wherein the passenger's connection reservation information includes the passenger's reservation time information and connection location information, and the passenger's historical connection demand information includes the passenger's historical connection demand quantity information and the passenger's historical connection demand location information;
[0013] The first processing unit is used to send the historical connection demand information and the connection reservation information of the passenger to a preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service cell area planning of the modular autonomous driving vehicle, and obtain the optimal departure time interval and service cell area of the planned modular autonomous driving vehicle;
[0014] A second processing unit is used to perform vehicle scheduling and path planning based on the passenger's pick-up reservation information, the planned optimal departure time interval of the modular autonomous driving vehicle, and the service cell area, to obtain the planned vehicle scheduling path information;
[0015] A third processing unit is used to control the modular autonomous driving vehicle to disassemble and perform passenger docking based on the planned vehicle path scheduling information, and to obtain vehicle vacancy information and passenger docking reservation information in real time, and to repeat vehicle scheduling and path planning until the modular autonomous driving vehicle arrives at a preset first designated location for marshaling;
[0016] The fourth processing unit is used to operate the assembled modular autonomous driving vehicles to the first designated location according to a preset route.
[0017] The beneficial effects of the present invention are:
[0018] According to the actual travel situation of passengers, the system of the present invention uses demand response technology to realize intelligent scheduling according to the reservation situation or immediate needs of passengers, optimize the vehicle operation path and departure interval, thereby improving the reliability and efficiency of the shuttle service; the system uses modular design, and the vehicle can be dynamically disassembled and assembled according to demand, which improves resource utilization and vehicle flexibility. In addition, the application of autonomous driving technology enables vehicles to autonomously perceive the surrounding environment, plan driving paths, and perform driving tasks, which significantly improves driving safety and traffic efficiency, and reduces traffic accidents and congestion problems.
[0019] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 It is a schematic flow chart of an intelligent docking method based on modular autonomous driving vehicles described in an embodiment of the present invention;
[0022] Figure 2 Schematic diagram of the structure of the intelligent docking system based on modular autonomous driving vehicles described in an embodiment of the present invention.
[0023] In the figure: 701, acquisition unit; 702, first processing unit; 703, second processing unit; 704, third processing unit; 705, fourth processing unit; 7021, first calculation subunit; 7022, second calculation subunit; 7023, third calculation subunit; 70221, fourth calculation subunit; 70222, fifth calculation subunit; 70223, sixth calculation subunit; 70224, seventh calculation subunit; 70225, eighth calculation subunit; 70231, ninth calculation subunit; 70232, tenth calculation subunit; 70233, eleventh calculation subunit; 7031, first processing subunit; 7032, second processing subunit; 7033, third processing subunit; 7034, fourth processing subunit; 70311, fifth processing subunit; 70312, sixth processing subunit; 70313, seventh processing subunit. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0026] Embodiment 1:
[0027] This embodiment provides an intelligent docking method based on a modular autonomous driving vehicle.
[0028] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4 and step S5.
[0029] Step S1, obtaining the passenger's transfer reservation information and the passenger's historical transfer demand information, wherein the passenger's transfer reservation information includes the passenger's reservation time information and transfer location information, and the passenger's historical transfer demand information includes the passenger's historical transfer demand quantity information and the passenger's historical transfer demand location information;
[0030] It is understandable that this step can better arrange vehicles, improve connection efficiency, and reduce passenger waiting time by obtaining passengers' connection reservation information and historical needs. Based on historical demand data, peak connection times and popular connection locations can be predicted to optimize the allocation of vehicles and resources. By analyzing passengers' historical behaviors and needs, more personalized and accurate services can be provided to improve user satisfaction. It can also provide data support for subsequent vehicle scheduling and route planning.
[0031] Step S2: Send the historical connection demand information and the connection reservation information of the passenger to a preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service cell area planning of the modular autonomous driving vehicle, and obtain the optimal departure time interval and service cell area of the planned modular autonomous driving vehicle;
[0032] It can be understood that this step can maximize the utilization of vehicles and improve the efficiency of docking by sending the historical docking demand information and docking reservation information of passengers to the planning model to accurately plan the departure time interval and service area. The planning model can reasonably allocate vehicles and resources and avoid waste of resources based on demand density and cost calculation. The planning model optimizes the scheduling plan and reduces the overall operating cost by comprehensively calculating the costs of passengers and operators. The planning model reduces the waiting time and travel costs of passengers and improves user satisfaction through precise time and area planning. In this step, step S2 includes step S21, step S22 and step S23.
[0033] Step S21, calculating the passenger demand density based on the historical connection demand information of the passenger to obtain the passenger demand density information;
[0034] It can be understood that the calculation of passenger demand density in this step is to divide the demand quantity by the regional area to obtain the passenger demand density information. Through the demand density calculation, the areas with high connection demand can be accurately identified, providing a basis for subsequent planning and scheduling.
[0035] Step S22: Calculate the passenger's travel cost information and the operator's operating cost information based on the passenger's demand density information and the passenger's connection reservation information;
[0036] It can be understood that this step provides basic data for subsequent optimization, and the optimal scheduling solution is achieved by comprehensively considering the costs of passengers and operators. In this step, step S22 includes
[0037] Step S221, calculating the average waiting time cost of passengers based on the passenger's transfer reservation information, the preset vehicle status information and the average waiting time cost calculation formula of passengers;
[0038] It can be understood that the average waiting time cost calculation formula in this step is as follows:
[0039]
[0040] Among them, C wis the average waiting time cost of the passenger, w is the unit waiting time cost of the passenger, L is the length of the rectangular service area, W is the width of the rectangular service area, Q is the demand density of the service area, h is the departure interval, k is the coefficient in the TSP shortest expected path formula, A is the area of the service cell, and c is the capacity of the vehicle unit.
[0041] Step S222: Calculate the average on-board time cost of the passenger based on the passenger's transfer reservation information, the preset vehicle status information and the average on-board time cost calculation formula of the passenger;
[0042] It can be understood that the calculation formula for the average passenger time cost in this step is as follows:
[0043]
[0044] Among them, C V represents the average time cost of passengers in the car, J is the connection distance, that is, the distance from the subway station to the area to be connected, L is the length of the rectangular service area, W is the width of the rectangular service area, and V is the driving speed of the modular unit vehicle, where β is the constant in the longest expected distance of TSP, k is the coefficient in the shortest expected path formula of TSP, A is the area of the service cell, c is the capacity of the vehicle unit, and V is the driving speed of the modular unit vehicle.
[0045] Where, the TSP detour time t of each vehicle unit in the cell is i Independent and uniformly distributed, the value range is The mean is The coefficient σ is t i The degree of deviation from the average value is 0≤σ≤1, and the random array r is introduced i , obeys the uniform distribution on [0,1], then obey The uniform distribution on t i Replace with Then the expected value of the maximum TSP time of the vehicle unit is T C It can be expressed as in
[0046] Step S223, summing up the average waiting time cost of the passengers and the average on-board time cost of the passengers to obtain the travel cost information of the passengers;
[0047] It can be understood that by accurately calculating the operating costs in this step, the system can optimize resource allocation, reduce operating costs, and improve economic benefits.
[0048] Step S224: Calculate the long-distance transport segment operating cost and the connecting transport segment operating cost of the operator based on the preset historical operation information, the preset long-distance transport segment cost calculation formula, and the connecting transport segment cost calculation formula to obtain the long-distance transport segment operating cost and the connecting transport segment operating cost of the operator;
[0049] It can be understood that the long-distance transport cost calculation formula preset in this step is as follows:
[0050]
[0051] Among them, C L represents the cost of the long-distance transport segment, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, A is the area of the service area, Q is the demand density of the service area, h is the departure interval, J is the connection distance, that is, the distance from the subway station to the area to be connected, L is the length of the rectangular service area, W is the width of the rectangular service area, and V is the driving speed of the modular unit vehicle;
[0052] The calculation formula for the connecting transport segment cost is as follows:
[0053]
[0054] Among them, C c represents the cost of the connecting transport section, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, c is the capacity of the vehicle unit, β is the constant in the longest expected distance of TSP, k is the coefficient in the formula of the shortest expected path of TSP, A is the area of the service cell, Q is the demand density of the service area, L is the length of the rectangular service area, W is the width of the rectangular service area, and V is the driving speed of the modular unit vehicle.
[0055] Step S225: The operator's operating cost information is obtained by summing up the operator's operating cost for the long-distance transport segment and the connecting transport segment.
[0056] It can be understood that this step can comprehensively evaluate the total cost of the operator in the entire connection service process by calculating the operator's operating cost information, and provide data support for cost management and optimization.
[0057] Step S23: Calculate the average total cost of passenger transfer based on the passenger's travel cost information and the operator's operating cost information, and calculate based on the average total cost of passenger transfer and the preset optimal departure interval calculation formula and service cell area calculation formula to obtain the optimal departure time interval and service cell area of the modular autonomous driving vehicle.
[0058] It can be understood that this step can effectively reduce the waiting time of passengers and improve passenger satisfaction by scientifically calculating the optimal departure time interval. By calculating the optimal service area, the system can cover more high-demand areas and improve service efficiency. Taking into account the costs of passengers and operators, the system can provide high-quality shuttle services while reducing operating costs.
[0059] In this step, step S33 includes step S331, step S332 and step S333.
[0060] Step S331: summing and averaging the passenger's travel cost information and the operator's operating cost information to obtain an average total cost of passenger transfers;
[0061] It can be understood that the calculation formula for calculating the average total cost of passenger transfers in this step is as follows:
[0062]
[0063] Among them, C a is the average total cost of passenger transfer, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, c is the capacity of the vehicle unit, w is the passenger waiting cost per unit time, β is the constant in the longest expected distance of TSP, k is the coefficient in the formula of the shortest expected path of TSP, A is the area of the service area, Q is the demand density of the service area, L is the length of the rectangular service area, W is the width of the rectangular service area, J is the connection distance, that is, the distance from the subway station to the area to be transferred, V is the speed of the modular unit vehicle, w is the passenger's unit waiting time cost, h is the departure interval, and v is the passenger's unit time cost in the car.
[0064] Step S332, taking the first-order partial derivatives of the departure interval and the service cell area in the calculation formula of the average total cost of the passenger connection, and setting them equal to zero, to obtain the first-order partial derivative formula for calculating the departure interval and the service cell area;
[0065] It can be understood that this step processes the calculation formula of the average total cost of the passenger connection by minimizing the system average cost of each trip as the final objective function, and calculates the first-order partial derivative formula and sets it equal to 0, wherein the final objective function is as follows:
[0066]
[0067] Constraints:
[0068]
[0069] h≥hmin ,A≥0
[0070] Among them, C a is the average total cost of passenger transfer, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, c is the capacity of the vehicle unit, w is the waiting cost per unit time of the passenger, β is the constant in the longest expected distance of TSP, k is the coefficient in the formula of the shortest expected path of TSP, A is the area of the service area, Q is the demand density of the service area, L is the length of the rectangular service area, W is the width of the rectangular service area, J is the connection distance, that is, the distance from the subway station to the area to be connected, V is the speed of the modular unit vehicle, h is the departure interval, h min is the minimum departure interval, w is the unit waiting time cost of the passenger, represents a positive integer, v is the passenger's unit time cost in the vehicle;
[0071] Where I is the number of vehicle units, which must be a positive integer. Due to road conditions, the number of vehicle units is at most 11. The second constraint is the non-negative constraint of the decision variable, h min It is the minimum departure interval, which is determined by objective factors such as actual safety needs and road capacity.
[0072] Among them, the result of finding the first-order partial derivative formula is as follows:
[0073]
[0074] Among them, C a is the average total cost of passenger transfer, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, c is the capacity of the vehicle unit, w is the passenger waiting cost per unit time, β is the constant in the longest expected distance of TSP, k is the coefficient in the formula of the shortest expected path of TSP, A is the area of the service area, Q is the demand density of the service area, L is the length of the rectangular service area, W is the width of the rectangular service area, J is the connection distance, that is, the distance from the subway station to the area to be transferred, V is the speed of the modular unit vehicle, h is the departure interval, w is the passenger's unit waiting time cost, and v is the passenger's unit time cost in the car.
[0075] Step S333: Calculate the second-order partial derivative of the departure interval and the service cell area based on the first-order partial derivative formula of the departure interval and the service cell area to obtain the optimal departure interval and the optimal service cell area.
[0076] It can be understood that the formula obtained by calculating the second-order partial derivative in this step is as follows:
[0077]
[0078] Among them, A * represents the optimal service cell area, h * represents the optimal departure interval, a is the fixed cost in the unit operating cost, b is the positive correlation coefficient between the variable cost and the number and capacity of modular unit vehicles, c is the capacity of the vehicle unit, w is the waiting cost per unit time of the passenger, β is the constant in the longest expected distance of TSP, k is the coefficient in the shortest expected path formula of TSP, Q is the demand density of the service area, L is the length of the rectangular service area, W is the width of the rectangular service area, J is the connection distance, that is, the distance from the subway station to the connection area, V is the driving speed of the modular unit vehicle, w is the unit waiting time cost of the passenger, and v is the unit time cost of the passenger in the car.
[0079] Step S3, performing vehicle dispatching and path planning based on the passenger's pick-up reservation information, the planned optimal departure time interval of the modular autonomous driving vehicle, and the service cell area, to obtain the planned vehicle dispatch path information;
[0080] It can be understood that this step ensures that the vehicle can arrive at the docking location on time and improves docking efficiency through a reasonable scheduling model and optimal path planning. Among them, by using an optimization algorithm for path planning, it is ensured that the vehicle chooses the optimal path, reduces driving time and distance, and reduces operating costs. By optimizing vehicle scheduling and path planning, the system can effectively control operating costs and improve economic benefits. In this step, step S3 includes step S31, step S32, step S33 and step S34.
[0081] Step S31: construct a connection network model according to the connection reservation information of the passenger, and establish a passenger boarding weight matrix based on the passenger reservation time information and connection location information of the passenger;
[0082] It can be understood that this step converts the passenger connection reservation information into a graph structure to facilitate subsequent path planning and scheduling decisions. Among them, the establishment of the weight matrix is based on the actual passenger reservation information to ensure the accuracy and effectiveness of path planning. Through the weight matrix, the subsequent steps can calculate the optimal path, reduce vehicle travel time and distance, and improve connection efficiency. In this step, step S31 includes step S311, step S312 and step S313.
[0083] Step S311, performing regional judgment on the pick-up reservation information of the passenger, the departure time interval of the modularized autonomous driving vehicle, and the service cell area, to obtain the location information of the passenger to be picked up and the corresponding cell map data information;
[0084] It can be understood that this step can determine the specific location information of each passenger to be picked up through regional judgment, ensuring that the vehicle can accurately reach the pick-up location. By judging whether the passenger is within the service area, the system can optimize the service range of the vehicle and improve the efficiency of the pick-up. By obtaining the cell map data, the system can obtain detailed geographic information and provide data support for subsequent route planning and scheduling. Through accurate regional judgment and efficient route planning, the system can reduce the driving time and distance of the vehicle and reduce operating costs.
[0085] Step S312: extracting features from the corresponding cell map data information, wherein the feature extraction is performed by extracting all paths available for vehicle operation in the cell to obtain the position information of each passenger to be picked up and the path data between each passenger to be picked up;
[0086] It can be understood that in this step, through feature extraction, the system can identify all paths available for vehicle operation in the community and ensure the accuracy of path data. By extracting and calculating the path data between each passenger to be connected, the system can perform efficient path planning and reduce driving time and distance. Through accurate path data, the system can optimize the efficiency of vehicle connection and improve passenger satisfaction. Through efficient path planning and optimized connection, the system can reduce the operating cost of the vehicle and improve the overall service quality.
[0087] Step S313: construct a model based on the location information of each passenger to be connected and the path data between each passenger to be connected, wherein the location information of each passenger to be connected is used as a node, the path data between each passenger to be connected is used as an edge, and each node and each edge are connected to obtain a connection network model.
[0088] It can be understood that this step helps to organize and manage data by structuring the scattered location information and path data into a complete connection network model.
[0089] Step S32: sorting the location nodes of passengers in the connection network model according to their importance based on the weight matrix of passengers riding the bus;
[0090] It can be understood that by sorting the nodes in this step, the system can arrange vehicle connections more reasonably, reduce passengers' waiting time and travel distance, give priority to high-demand passengers, ensure that their connection needs are met in a timely manner, and improve passenger satisfaction and experience.
[0091] Step S33: taking the preset unpacking position point closest to the modular autonomous driving vehicle in the docking network model as the starting point, and visiting other nodes in descending order of importance to obtain at least one docking path corresponding to the unpacked modular autonomous driving vehicle;
[0092] It can be understood that by sorting by importance, it is ensured that high-weight nodes are visited first, the connection needs of high-demand passengers are met, and passenger satisfaction is improved.
[0093] Step S34: perform correlation analysis on the connecting paths corresponding to all the disassembled modular autonomous driving vehicles and the optimal departure time interval and service cell area, and obtain the connecting path information corresponding to the modular autonomous driving vehicles at each departure time interval.
[0094] It can be understood that this step ensures that each route runs in the most appropriate time period through association analysis, thereby improving the overall efficiency of the shuttle service. By optimizing the service area and departure time interval, passenger needs can be covered to the maximum extent and passenger satisfaction can be improved. Then, dynamic adjustments can be made based on real-time data to adapt to different passenger needs and traffic conditions.
[0095] Step S4: based on the planned vehicle path scheduling information, control the modular autonomous driving vehicle to disassemble and perform passenger docking, obtain vehicle vacancy information and passenger docking reservation information in real time, and repeat vehicle scheduling and path planning until the modular autonomous driving vehicle arrives at the preset first designated location for marshaling;
[0096] It can be understood that the control of modular autonomous driving vehicles in this step is mainly composed of information collection system, information transmission system, information processing system (dispatching command center), and information release system. The demand response system center mainly operates through modern technologies such as mobile 5G traffic, Geographic Information System (GIS), Global Positioning System (GPS), Passenger Information System (PIS), and Automatic Vehicle Location (AV).
[0097] Through GIS and GPS, the operating status of modular vehicle units can be monitored at any time, and information on the road traffic network, such as road congestion and intersection locations, can be obtained to ensure the smooth operation of vehicles; the passenger position can be accurately located within the community, the TSP route can be planned, and the fastest shuttle service can be provided.
[0098] PIS is an important operational service production system that can provide passengers with dynamic vehicle operation information, such as elapsed time and estimated arrival time.
[0099] AVL can upload the position of modular vehicle units and vehicles in train formation to the operation dispatch center for control at any time. It accurately tracks the operating status of vehicles and each vehicle unit, and this technology plays a key role when a vehicle fails.
[0100] It can be understood that this step controls the modular autonomous driving vehicles to be disassembled and grouped, divided into multiple connecting vehicles, and then quickly and effectively connects according to the planned route.
[0101] Step S5: The assembled modular autonomous driving vehicles run to the first designated location along a preset route.
[0102] Embodiment 2:
[0103] like Figure 2 As shown, this embodiment provides an intelligent docking system based on modular autonomous driving vehicles, see Figure 2 The system includes an acquisition unit 701 , a first processing unit 702 , a second processing unit 703 , a third processing unit 704 and a fourth processing unit 705 .
[0104] The acquisition unit 701 is used to acquire the passenger's connection reservation information and the passenger's historical connection demand information, wherein the passenger's connection reservation information includes the passenger's reservation time information and connection location information, and the passenger's historical connection demand information includes the passenger's historical connection demand quantity information and the passenger's historical connection demand location information;
[0105] The first processing unit 702 is used to send the historical connection demand information of the passenger and the connection reservation information of the passenger to a preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service cell area planning of the modular autonomous driving vehicle, and obtain the optimal departure time interval and service cell area of the planned modular autonomous driving vehicle;
[0106] The first processing unit 702 includes a first calculation subunit 7021 , a second calculation subunit 7022 and a third calculation subunit 7023 .
[0107] The first calculation subunit 7021 is used to calculate the passenger demand density based on the historical connection demand information of the passenger to obtain the passenger demand density information;
[0108] The second calculation subunit 7022 is used to calculate the passenger's travel cost information and the operator's operating cost information based on the passenger's demand density information and the passenger's connection reservation information;
[0109] The second computing subunit 7022 includes a fourth computing subunit 70221 , a fifth computing subunit 70222 , a sixth computing subunit 70223 , a seventh computing subunit 70224 and an eighth computing subunit 70225 .
[0110] The fourth calculation subunit 70221 is used to calculate the average waiting time cost of the passenger based on the passenger's connection reservation information, the preset vehicle status information and the passenger average waiting time cost calculation formula;
[0111] The fifth calculation subunit 70222 is used to calculate the average on-board time cost of the passenger based on the passenger's transfer reservation information, the preset vehicle status information and the average on-board time cost calculation formula of the passenger;
[0112] The sixth calculation subunit 70223 is used to calculate the sum of the average waiting time cost of the passengers and the average on-board time cost of the passengers to obtain the travel cost information of the passengers;
[0113] The seventh calculation subunit 70224 is used to calculate based on the preset historical operation information, the preset long-distance transport segment cost calculation formula and the connecting transport segment cost calculation formula to obtain the operator's long-distance transport segment operation cost and the connecting transport segment operation cost;
[0114] The eighth calculation subunit 70225 is used to perform a summation calculation based on the operator's long-distance transport segment operating cost and the connecting transport segment operating cost to obtain the operator's operating cost information.
[0115] The third calculation subunit 7023 is used to calculate the average total cost of passenger transfer based on the passenger's travel cost information and the operator's operating cost information, and to calculate based on the average total cost of passenger transfer and the preset optimal departure interval calculation formula and service cell area calculation formula to obtain the optimal departure time interval and service cell area of the modular autonomous driving vehicle.
[0116] The third computing subunit 7023 includes a ninth computing subunit 70231 , a tenth computing subunit 70232 and an eleventh computing subunit 70233 .
[0117] A ninth calculation subunit 70231 is used for performing sum calculation and average calculation on the passenger's travel cost information and the operator's operating cost information to obtain an average total cost of passenger transfer;
[0118] A tenth calculation subunit 70232 is used to obtain the first-order partial derivative of the departure interval and the service cell area in the calculation formula of the average total cost of the passenger connection, and set them equal to zero to obtain a first-order partial derivative formula for calculating the departure interval and the service cell area;
[0119] The eleventh calculation subunit 70233 is used to calculate the second-order partial derivative of the departure interval and the service cell area based on the first-order partial derivative formula of the departure interval and the service cell area, so as to obtain the optimal departure interval and the optimal service cell area.
[0120] The second processing unit 703 is used to perform vehicle scheduling and path planning based on the passenger's pick-up reservation information, the planned optimal departure time interval of the modular autonomous driving vehicle, and the service cell area, to obtain the planned vehicle scheduling path information;
[0121] The second processing unit 703 includes a first processing sub-unit 7031 , a second processing sub-unit 7032 , a third processing sub-unit 7033 and a fourth processing sub-unit 7034 .
[0122] The first processing subunit 7031 is used to build a connection network model according to the connection reservation information of the passenger, and to establish a weight matrix for the passenger to take the bus based on the time information of the passenger reservation and the connection location information of the passenger;
[0123] The second processing subunit 7032 is used to sort the location nodes of the passengers in the connection network model according to their importance based on the weight matrix of the passengers;
[0124] The third processing subunit 7033 is used to use the preset unpacking position point closest to the modular autonomous driving vehicle in the docking network model as the starting point, and visit other nodes in descending order of importance to obtain at least one docking path corresponding to the unpacked modular autonomous driving vehicle;
[0125] The fourth processing sub-unit 7034 is used to associate the connection paths corresponding to all the disassembled modular autonomous driving vehicles with the optimal departure time interval and the service cell area, so as to obtain the connection path information corresponding to the modular autonomous driving vehicles at each departure time interval.
[0126] The first processing sub-unit 7031 includes a fifth processing sub-unit 70311 , a sixth processing sub-unit 70312 and a seventh processing sub-unit 70313 .
[0127] The fifth processing sub-unit 70311 is used to perform regional judgment on the pick-up reservation information of the passenger, the departure time interval of the modularized autonomous driving vehicle, and the service cell area, and obtain the location information of the passenger to be picked up and the corresponding cell map data information;
[0128] The sixth processing subunit 70312 is used to perform feature extraction on the corresponding cell map data information, wherein the feature extraction is performed by extracting all paths available for vehicle operation in the cell to obtain the position information of each passenger to be connected and the path data between each passenger to be connected;
[0129] The seventh processing sub-unit 70313 is used to construct a model based on the location information of each passenger to be connected and the path data between each passenger to be connected, wherein the location information of each passenger to be connected is used as a node, the path data between each passenger to be connected is used as an edge, and each node and each edge are connected to obtain a connection network model.
[0130] The third processing unit 704 is used to control the modular autonomous driving vehicle to disassemble and perform passenger docking based on the planned vehicle path scheduling information, and obtain vehicle vacancy information and passenger docking reservation information in real time, and repeat vehicle scheduling and path planning until the modular autonomous driving vehicle arrives at the preset first designated location for marshaling;
[0131] The fourth processing unit 705 is used to drive the assembled modular autonomous driving vehicles to the first designated location according to a preset route.
[0132] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0133] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
[0134] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. An intelligent docking method based on modular autonomous driving vehicles, characterized in that: include: Acquire the passenger's transfer reservation information and the passenger's historical transfer demand information, wherein the passenger's transfer reservation information includes the passenger's reservation time information and transfer location information, and the passenger's historical transfer demand information includes the passenger's historical transfer demand quantity information and the passenger's historical transfer demand location information; Send the historical connection demand information and the connection reservation information of the passengers to the preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service community area planning of the modular autonomous driving vehicles, and obtain the optimal departure time interval and service community area of the planned modular autonomous driving vehicles; Performing vehicle dispatching and path planning based on the passenger's pick-up reservation information, the optimal departure time interval of the planned modular autonomous driving vehicle, and the service area, to obtain the planned vehicle dispatch path information; Based on the planned vehicle path scheduling information, the modular autonomous driving vehicle is controlled to disassemble and group passengers, and the vehicle vacancy information and the passenger's grouping reservation information are obtained in real time, and the vehicle scheduling and path planning are repeated until the modular autonomous driving vehicle arrives at the preset first designated location for grouping; The modular self-driving vehicles are assembled and run to the first designated location along a preset route.
2. The intelligent docking method based on modular autonomous driving vehicles according to claim 1, characterized in that The method of sending the historical connection demand information of the passenger and the connection reservation information of the passenger to the preset modular autonomous driving vehicle planning model to perform the optimal departure time interval planning and service area planning of the modular autonomous driving vehicle includes: Calculate the passenger demand density based on the historical connection demand information of the passengers to obtain the passenger demand density information; Calculate the passenger's travel cost information and the operator's operating cost information based on the passenger's demand density information and the passenger's connection reservation information; The average total cost of passenger transfer is calculated based on the passenger's travel cost information and the operator's operating cost information, and the optimal departure time interval and service cell area of the modular autonomous driving vehicle are calculated based on the average total cost of passenger transfer and the preset optimal departure interval calculation formula and service cell area calculation formula.
3. The intelligent docking method based on modular autonomous driving vehicles according to claim 2 is characterized in that ,Calculate the passenger's travel cost information and the operator's operating cost information based on the passenger's demand density information and the passenger's connection reservation information, including: The average waiting time cost of passengers is calculated based on the passenger's connection reservation information, the preset vehicle status information and the average waiting time cost calculation formula of passengers; The average time cost of passengers in the vehicle is calculated based on the passenger's connection reservation information, the preset vehicle status information and the average time cost calculation formula of passengers in the vehicle; The average waiting time cost of the passengers and the average on-board time cost of the passengers are summed up to obtain the travel cost information of the passengers; Based on preset historical operation information 、 The preset long-distance transport segment cost calculation formula and the connecting transport segment cost calculation formula are used to calculate and obtain the operator's long-distance transport segment operating cost and the connecting transport segment operating cost; The operator's operating cost information is obtained by summing up the operator's long-distance transport segment operating cost and the connecting transport segment operating cost.
4. The intelligent docking method based on modular autonomous driving vehicles according to claim 2, characterized in that , based on the passenger's travel cost information and the operator's operating cost information, the average total cost of passenger connection is calculated, and the average total cost of passenger connection and the preset optimal departure interval calculation formula and service community area calculation formula are calculated, including: The passenger's travel cost information and the operator's operating cost information are summed and averaged to obtain an average total cost of passenger transfers; Taking the first-order partial derivative of the departure interval and the service cell area in the calculation formula of the average total cost of the passenger connection and setting them equal to zero, a first-order partial derivative formula for calculating the departure interval and the service cell area is obtained; Based on the first-order partial derivative formula of the departure interval and the service cell area, the second-order partial derivative of the departure interval and the service cell area is calculated to obtain the optimal departure interval and the optimal service cell area.
5. The intelligent docking method based on modular autonomous driving vehicles according to claim 1, characterized in that , based on the passenger's pick-up reservation information, the optimal departure time interval of the planned modular autonomous driving vehicle and the service area, vehicle scheduling and route planning are performed, including: A connection network model is constructed based on the connection reservation information of the passenger, and a weight matrix of the passenger's ride is established based on the time information of the passenger reservation and the connection location information of the passenger; Based on the passenger riding weight matrix, the location nodes of the passengers in the connecting network model are sorted according to their importance; Taking the preset unpacking position point closest to the modular autonomous driving vehicle in the docking network model as the starting point, and visiting other nodes in descending order of importance to obtain at least one docking path corresponding to the unpacked modular autonomous driving vehicle; The connecting paths corresponding to all the disassembled modular autonomous driving vehicles are respectively correlated with the optimal departure time interval and the service cell area to obtain the connecting path information corresponding to the modular autonomous driving vehicles at each departure time interval.
6. An intelligent docking system based on modular autonomous driving vehicles, characterized in that: include: an acquisition unit, configured to acquire the passenger's connection reservation information and the passenger's historical connection demand information, wherein the passenger's connection reservation information includes the passenger's reservation time information and connection location information, and the passenger's historical connection demand information includes the passenger's historical connection demand quantity information and the passenger's historical connection demand location information; The first processing unit is used to send the historical connection demand information and the connection reservation information of the passenger to a preset modular autonomous driving vehicle planning model to perform optimal departure time interval planning and service cell area planning of the modular autonomous driving vehicle, and obtain the optimal departure time interval and service cell area of the planned modular autonomous driving vehicle; A second processing unit is used to perform vehicle scheduling and path planning based on the passenger's pick-up reservation information, the planned optimal departure time interval of the modular autonomous driving vehicle, and the service cell area, to obtain the planned vehicle scheduling path information; A third processing unit is used to control the modular autonomous driving vehicle to disassemble and perform passenger docking based on the planned vehicle path scheduling information, and to obtain vehicle vacancy information and passenger docking reservation information in real time, and to repeat vehicle scheduling and path planning until the modular autonomous driving vehicle arrives at a preset first designated location for marshaling; The fourth processing unit is used to operate the assembled modular autonomous driving vehicles to the first designated location according to a preset route.
7. The intelligent docking system based on modular autonomous driving vehicles according to claim 6, characterized in that: The first processing unit comprises: A first calculation subunit is used to calculate the passenger demand density based on the historical connection demand information of the passenger to obtain the passenger demand density information; A second calculation subunit, for calculating the passenger's travel cost information and the operator's operating cost information based on the passenger's demand density information and the passenger's connection reservation information; The third calculation subunit is used to calculate the average total cost of passenger transfer based on the passenger's travel cost information and the operator's operating cost information, and to calculate based on the average total cost of passenger transfer and a preset optimal departure interval calculation formula and service cell area calculation formula to obtain the optimal departure time interval and service cell area of the modular autonomous driving vehicle.
8. The intelligent docking system based on modular autonomous driving vehicles according to claim 7, characterized in that: The second computing subunit comprises: A fourth calculation subunit, configured to calculate the average waiting time cost of the passenger based on the passenger's connection reservation information, the preset vehicle status information and the average waiting time cost calculation formula of the passenger; A fifth calculation subunit, configured to calculate the average on-board time cost of the passenger based on the passenger's transfer reservation information, the preset vehicle status information and the average on-board time cost calculation formula of the passenger; a sixth calculation subunit, configured to calculate the sum of the average waiting time cost of the passengers and the average on-board time cost of the passengers to obtain the travel cost information of the passengers; The seventh calculation subunit is used to calculate the historical operation information based on the preset 、 The preset long-distance transport segment cost calculation formula and the connecting transport segment cost calculation formula are used to calculate and obtain the operator's long-distance transport segment operating cost and the connecting transport segment operating cost; The eighth calculation subunit is used to perform a summation calculation based on the operator's long-distance transport segment operating cost and the connecting transport segment operating cost to obtain the operator's operating cost information.
9. The intelligent docking system based on modular autonomous driving vehicles according to claim 7, characterized in that: The third computing subunit comprises: A ninth calculation subunit, configured to perform sum calculation and average calculation on the passenger's travel cost information and the operator's operating cost information to obtain an average total cost of passenger transfer; a tenth calculation subunit, configured to obtain a first-order partial derivative of the departure interval and the service cell area in the calculation formula of the average total cost of the passenger connection, and set them equal to zero, so as to obtain a first-order partial derivative formula for calculating the departure interval and the service cell area; The eleventh calculation subunit is used to calculate the second-order partial derivative of the departure interval and the service cell area based on the first-order partial derivative formula of the departure interval and the service cell area, so as to obtain the optimal departure interval and the optimal service cell area.
10. The intelligent docking system based on modular autonomous driving vehicles according to claim 6, characterized in that: The second processing unit comprises: A first processing subunit is used to construct a connection network model according to the connection reservation information of the passenger, and to establish a weight matrix for the passenger to take the bus based on the time information of the passenger reservation and the connection location information of the passenger; A second processing subunit is used to sort the location nodes of passengers in the connection network model according to importance based on the weight matrix of passengers riding the bus; A third processing subunit is configured to use the preset unpacking position point closest to the modular autonomous driving vehicle in the docking network model as a starting point, and sequentially visit other nodes in descending order of importance to obtain at least one docking path corresponding to the unpacked modular autonomous driving vehicle; The fourth processing sub-unit is used to perform correlation analysis on the connecting paths corresponding to all the disassembled modular autonomous driving vehicles with the optimal departure time interval and the service cell area, so as to obtain the connecting path information corresponding to the modular autonomous driving vehicles at each departure time interval.
Citation Information
Patent Citations
Connection bus timetable adjusting method for dealing with railway delay
CN115186901A
Airport passenger distribution system based on modularized automatic driving bus connection
CN115456257A
