Unmanned bus distribution scheduling method and system based on demand response

Abstract

The invention discloses an unmanned bus distribution scheduling method and system based on demand response, and the method comprises the steps: firstly, sensing the riding demands of all bus stops in real time through a bus stop sensing module, obtaining the riding demand data, and outputting the riding demand data to a rear-end scheduling module; then, the back-end scheduling module is used for calculating and obtaining an optimal scheduling scheme by using an unmanned bus flexible formation method according to the riding demand, and outputting a scheduling instruction to a bus-end operation module of the unmanned bus; according to the method, the function of dynamically adjusting the bus formation and scheduling by adopting the real-time sensing technology and the demand prediction model is realized, the waiting time of passengers is reduced, the vehicle passenger carrying rate is optimized, the formation recombination cost is reduced, the flexibility and adaptability of bus operation are enhanced, the public traffic service quality is improved, and the system is suitable for popularization and application. And sustainable traffic development is promoted, and the method is suitable for being widely popularized and used.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation and autonomous driving technology, and in particular to a demand-response-based driverless bus allocation and dispatching method and system. Background Art

[0002] The public transportation system includes multiple modes, such as rail transportation, road transportation, water transportation and air transportation. These different modes of transportation together constitute a multi-level and extensive public transportation network to meet the travel needs of different regions and people. Public transportation is not only an important link connecting various areas of the city, but also an effective means to alleviate traffic congestion and reduce environmental pollution. In order to improve the efficiency and attractiveness of public transportation, many cities have taken measures such as setting up bus lanes, implementing regional rail commuting and promoting new energy buses. At the same time, some cities have further improved the service level and passenger volume of public transportation through intelligent technology.

[0003] At present, most existing bus systems rely on fixed routes and timetables to dispatch vehicles, which makes it difficult to flexibly respond to fluctuations in passenger demand during peak hours and sudden large passenger flows. This rigid operating model usually leads to vehicle congestion in areas with dense passenger flow and empty vehicles in other areas, which results in inefficient resource utilization and prolonged waiting time for passengers. At the same time, there is a general lack of sufficient flexibility and response speed when faced with uneven passenger flow distribution and frequently changing passenger demand. Therefore, it is necessary to design a demand-responsive unmanned bus allocation and dispatching method and system. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art, in order to better and effectively solve the problem that the existing public transportation system mostly relies on fixed routes and timetables to dispatch vehicles, which makes it difficult to flexibly respond to fluctuations in passenger demand during peak hours and sudden large passenger flows, and this rigid operation mode is usually prone to vehicle congestion in passenger flow-intensive areas and empty vehicles in other areas, which results in low resource utilization efficiency and prolonged passenger waiting time. At the same time, there is a general lack of sufficient flexibility and response speed when facing uneven passenger flow distribution and frequently changing passenger demand. A demand-responsive unmanned bus allocation and dispatching method and system are provided, which realizes the function of dynamically adjusting bus formation and dispatching by using real-time sensing technology and demand prediction model, which not only reduces passenger waiting time, but also optimizes vehicle occupancy rate, while also reducing formation reorganization costs and enhancing the flexibility and adaptability of public transportation operations, improving the quality of public transportation services, and promoting sustainable transportation development.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A method for dispatching driverless buses based on demand response includes the following steps: Step A, using the bus stop sensing module to sense the bus demand at each bus stop in real time and obtain the bus demand data, and then output the bus demand data to the back-end scheduling module; Step B, using the back-end dispatching module to calculate the optimal dispatching plan based on the passenger demand using the driverless bus flexible formation method and output the dispatching instruction to the vehicle-side operation module of the driverless bus; In step C, the vehicle-side operation module of the driverless bus disassembles and assembles the driverless bus according to the dispatching instructions to form a new bus formation, and then completes the passenger pick-up and drop-off operations at each bus stop through the new bus formation.

[0006] The above-mentioned demand-response-based driverless bus allocation and dispatching method includes step A, using a bus stop sensing module to sense the riding demand of each bus stop in real time and obtain riding demand data, and then output the riding demand data to a back-end dispatching module, wherein the bus stop sensing module uses a video camera to monitor the riding demand of passengers waiting at the bus stop in real time, and the riding demand includes the number of waiting passengers and the waiting time of passengers. The specific real-time sensing steps are as follows: Step A1, image acquisition and passenger detection, wherein the image acquisition specifically uses a video camera to collect images of the waiting area of ​​the bus station in real time, and the passenger detection specifically uses an image processing method to detect waiting passengers in the image; Step A2, passenger counting and waiting time calculation, wherein the passenger counting specifically counts the detected waiting passengers and obtains the current number of waiting passengers, and the waiting time calculation specifically calculates the waiting time of each passenger according to the continuous appearance time of the waiting passengers in the image; Step A3, output the riding demand data to the back-end scheduling module, specifically, transmit the calculated number of waiting passengers, waiting time information and platform code to the back-end scheduling module, the number of waiting passengers is the total number of passengers waiting at the current platform, the waiting time information is the average value calculated based on the continuous appearance time, and the platform code is the unique identification code of each platform.

[0007] The above-mentioned demand-response-based driverless bus allocation and dispatching method, step B, uses the back-end dispatching module to use the driverless bus flexible formation method to calculate the optimal dispatching plan according to the riding demand and output the dispatching instruction to the vehicle-side operation module of the driverless bus, wherein the specific steps of the driverless bus flexible formation method are as follows: Step B1, data reception and integration, specifically, integrating the bus demand data received from the bus station sensing module at five-minute intervals to form a demand matrix. Demand matrix for time periods As shown in formula (1), (1) in, Code the i-th station, is the total number of waiting passengers, is the average waiting time, n is the number of platforms; Step B2, data analysis and demand forecasting, specifically, threshold detection of the number of waiting passengers and waiting time at each platform is performed to calculate the peak passenger demand area, and then identify the demand hotspot area and time period, as shown in formula (2). (2) in, and They are the passenger number threshold and waiting time threshold respectively; Step B3, fleet optimization, specifically, calculates the optimal bus fleet and dispatching plan based on real-time passenger demand data and forecast data to meet peak passenger demand and optimize vehicle operating efficiency. The specific steps are as follows: Step B31, determine the decision variable as the module deployment instruction , Vehicle dispatch instructions and passenger allocation variables , the module deployment instructions For disassembling the kth modular bus body from the jth shift for redeployment, the vehicle dispatching instruction For selecting the j-th shift vehicle for dispatch optimization, the passenger allocation variable Used to allocate the demand of the ith station to the jth shift; Step B32, establish a scheduling optimization model, specifically setting the objective function to minimize passenger waiting time, optimize vehicle passenger load factor and reduce fleet reorganization cost. The objective function is shown in formula (3): (3) in, is the total waiting time of passengers at platform i, m is the total number of bus trips on the bus line, n is the total number of platforms, is the formation reorganization cost of reorganization module k of shift j, is the maximum passenger capacity of a single vehicle, is the number of vehicles in shift j, and is the weighting coefficient; Step B4, generating a dispatch instruction, using a back-end dispatch module to generate a dispatch instruction according to the formation optimization strategy and the dispatch plan, wherein the dispatch instruction includes a platform target, formation structure, route, arrival time, and disassembly and splicing operation instructions; Step B5, dispatch instruction sending and confirmation, the back-end dispatch module uses a wireless network and a reliable data transmission protocol to send the dispatch instruction to the vehicle-side operation module of the driverless bus and receive a confirmation receipt. If the back-end dispatch module finds a problem in the confirmation receipt, it will resend or adjust the instruction; Step B6, real-time monitoring and feedback, using the bus stop sensing module to continuously monitor the changes in demand at each stop, the operating status of the bus and the number of passengers boarding the bus, and to provide real-time feedback data to the back-end scheduling module, which then dynamically adjusts the formation, route and scheduling plan based on the monitoring data.

[0008] In the above-mentioned demand-response-based driverless bus allocation and dispatching method, the constraint conditions of the objective function in step B32 include demand allocation constraint, vehicle capacity constraint, platoon structure constraint, total vehicle number constraint, platoon operation constraint, route arrangement constraint, vehicle dispatch optimization constraint and demand allocation sum constraint. The specific objective function constraint construction steps are as follows: Step B321, construct the allocation constraint, as shown in formula (4): (4) in, is the i-th bus stop, is any i-th bus stop; Step B322, construct vehicle capacity constraints, specifically, the number of passengers in each shift must not exceed the total capacity of the vehicles in shift j, as shown in formula (5), (5) in, is any j-th bus trip; Step B323, construct the formation structure constraint. Specifically, the number of vehicles in each shift j is composed of the selected buses, as shown in formula (6): (6) in, is the original modular bus body k in the jth shift; Step B324, construct the total number of vehicles constraint. The total number of vehicles on all shifts on a specific route must be equal to the total number of vehicles on the current route, as shown in formula (7). (7) in, is the total number of all modular bus bodies on the current line; Step B325, construct the formation operation constraints. The disassembly and assembly operation time of the specific formation must be completed within the allowed operation time, as shown in formula (8). (8) in, is the formation operation time of module k in shift j, is the maximum allowed operation time, is any module k; Step B326, construct route scheduling constraints. Specifically, the route scheduling time of each shift j must be completed within the set time window, as shown in formula (9): (9) in, is the route time of flight j, for a given time window; Step B327, construct vehicle scheduling optimization constraints, specifically to determine which shifts j need scheduling optimization, as shown in formula (10), (10); Step B328, construct the demand allocation sum constraint, specifically to ensure that the sum of the demand for each shift does not exceed its carrying capacity, as shown in formula (11), (11).

[0009] The aforementioned demand-response-based driverless bus allocation and dispatching method, step C, the vehicle-side operation module of the driverless bus disassembles and assembles the driverless bus according to the dispatching instruction to form a new bus formation, and then completes the passenger pick-up and drop-off operations at each bus stop through the new bus formation, wherein the vehicle-side operation module of the driverless bus includes a driving control module and a module control module, and the process of the vehicle-side operation module of the driverless bus executing the dispatching instruction specifically adjusts the configuration and route of the bus fleet.

[0010] A demand-response-based unmanned bus allocation and dispatching system comprises a detection input module, a dispatching output module and a dispatching execution module, wherein the detection input module is used to use a bus stop sensing module to sense the riding demand of each bus stop in real time and obtain riding demand data, and then output the riding demand data to a back-end dispatching module; the dispatching output module is used to use the back-end dispatching module to use an unmanned bus flexible formation method to calculate an optimal dispatching scheme according to the riding demand and output dispatching instructions to a vehicle-side operation module of the unmanned bus; the dispatching execution module is used to use the vehicle-side operation module of the unmanned bus to disassemble and splice the unmanned buses according to the dispatching instructions and form a new bus formation, and then complete the passenger pick-up and drop-off operations at each bus stop through the new bus formation.

[0011] The beneficial effects of the present invention are as follows: the present invention is a demand-response-based unmanned bus allocation and dispatching method and system, firstly, a bus stop sensing module is used to sense the riding demand of each bus stop in real time and obtain riding demand data, and then the riding demand data is output to a back-end dispatching module, and then the back-end dispatching module is used to calculate the optimal dispatching scheme according to the riding demand using the unmanned bus flexible formation method and output the dispatching instruction to the vehicle-side operation module of the unmanned bus, and then the vehicle-side operation module of the unmanned bus disassembles and splices the unmanned bus according to the dispatching instruction to form a new bus formation, and then the passenger pick-up and drop-off operation of each bus stop is completed by the new bus formation; the unmanned bus allocation and dispatching method and system are effectively realized to have the function of dynamically adjusting the bus formation and dispatching by using the real-time sensing technology and the demand prediction model, which not only reduces the waiting time of passengers, but also optimizes the vehicle passenger load factor, while also reducing the formation reorganization cost and enhancing the flexibility and adaptability of bus operation, improving the quality of public transportation services, and promoting sustainable transportation development. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of a demand-response-based driverless bus allocation and dispatching method and system of the present invention. DETAILED DESCRIPTION

[0013] The present invention will be further described below in conjunction with the accompanying drawings.

[0014] like Figure 1 As shown, a demand response-based driverless bus allocation and scheduling method of the present invention comprises the following steps: Step A, using the bus stop sensing module to sense the riding demand of each bus stop in real time and obtain riding demand data, and then output the riding demand data to the back-end scheduling module, wherein the bus stop sensing module uses a video camera to monitor the riding demand of passengers waiting at the bus stop in real time, and the riding demand includes the number of waiting passengers and the waiting time of passengers. The specific real-time sensing steps are as follows: Step A1, image acquisition and passenger detection, wherein the image acquisition specifically uses a video camera to collect images of the waiting area of ​​the bus station in real time, and the passenger detection specifically uses an image processing method to detect waiting passengers in the image; Step A2, passenger counting and waiting time calculation, wherein the passenger counting specifically counts the detected waiting passengers and obtains the current number of waiting passengers, and the waiting time calculation specifically calculates the waiting time of each passenger according to the continuous appearance time of the waiting passengers in the image; Step A3, output the riding demand data to the back-end scheduling module, specifically, transmit the calculated number of waiting passengers, waiting time information and platform code to the back-end scheduling module, the number of waiting passengers is the total number of passengers waiting at the current platform, the waiting time information is the average value calculated based on the continuous appearance time, and the platform code is the unique identification code of each platform.

[0015] Step B, using the back-end dispatching module to calculate the optimal dispatching plan according to the riding demand using the driverless bus flexible formation method and output the dispatching instruction to the vehicle-side operation module of the driverless bus, wherein the specific steps of the driverless bus flexible formation method are as follows: Step B1, data reception and integration, specifically, integrating the bus demand data received from the bus station sensing module at five-minute intervals to form a demand matrix. Demand matrix for time periods As shown in formula (1), (1) in, Code the i-th station, is the total number of waiting passengers, is the average waiting time, n is the number of platforms; Step B2, data analysis and demand forecasting, specifically, threshold detection of the number of waiting passengers and waiting time at each platform is performed to calculate the peak passenger demand area, and then identify the demand hotspot area and time period, as shown in formula (2). (2) in, and They are the passenger number threshold and waiting time threshold respectively; Step B3, fleet optimization, specifically, calculates the optimal bus fleet and dispatching plan based on real-time passenger demand data and forecast data to meet peak passenger demand and optimize vehicle operating efficiency. The specific steps are as follows: Step B31, determine the decision variable as the module deployment instruction , Vehicle dispatch instructions and passenger allocation variables , the module deployment instructions For disassembling the kth modular bus body from the jth shift for redeployment, the vehicle dispatching instruction For selecting the j-th shift vehicle for dispatch optimization, the passenger allocation variable Used to allocate the demand of the ith station to the jth shift; Step B32, establish a scheduling optimization model, specifically setting the objective function to minimize passenger waiting time, optimize vehicle passenger load factor and reduce fleet reorganization cost. The objective function is shown in formula (3): (3) in, is the total waiting time of passengers at platform i, m is the total number of bus trips on the bus line, n is the total number of platforms, is the formation reorganization cost of reorganization module k of shift j, is the maximum passenger capacity of a single vehicle, is the number of vehicles in shift j, and is the weighting coefficient; Step B4, generating a dispatch instruction, using a back-end dispatch module to generate a dispatch instruction according to the formation optimization strategy and the dispatch plan, wherein the dispatch instruction includes a platform target, formation structure, route, arrival time, and disassembly and splicing operation instructions; Step B5, dispatch instruction sending and confirmation, the back-end dispatch module uses a wireless network and a reliable data transmission protocol to send the dispatch instruction to the vehicle-side operation module of the driverless bus and receive a confirmation receipt. If the back-end dispatch module finds a problem in the confirmation receipt, it will resend or adjust the instruction; Step B6, real-time monitoring and feedback, using the bus stop sensing module to continuously monitor the changes in demand at each stop, the operating status of the bus and the number of passengers boarding the bus, and to provide real-time feedback data to the back-end scheduling module, which then dynamically adjusts the formation, route and scheduling plan based on the monitoring data.

[0016] The constraints of the objective function in step B32 include demand allocation constraints, vehicle capacity constraints, platoon structure constraints, total vehicle number constraints, platoon operation constraints, route arrangement constraints, vehicle scheduling optimization constraints and demand allocation sum constraints. The specific objective function constraint construction steps are as follows: Step B321, construct the allocation constraint, as shown in formula (4): (4) in, is the i-th bus stop, is any i-th bus stop; Step B322, construct vehicle capacity constraints, specifically, the number of passengers in each shift must not exceed the total capacity of the vehicles in shift j, as shown in formula (5), (5) in, is any j-th bus trip; Step B323, construct the formation structure constraint. Specifically, the number of vehicles in each shift j is composed of the selected buses, as shown in formula (6): (6) in, is the original modular bus body k in the jth shift; Step B324, construct the total number of vehicles constraint. The total number of vehicles on all shifts on a specific route must be equal to the total number of vehicles on the current route, as shown in formula (7). (7) in, is the total number of all modular bus bodies on the current line; Step B325, construct the formation operation constraints. The disassembly and assembly operation time of the specific formation must be completed within the allowed operation time, as shown in formula (8). (8) in, is the formation operation time of module k in shift j, is the maximum allowed operation time, is any module k; Step B326, construct route scheduling constraints. Specifically, the route scheduling time of each shift j must be completed within the set time window, as shown in formula (9): (9) in, is the route time of flight j, for a given time window; Step B327, construct vehicle scheduling optimization constraints, specifically to determine which shifts j need scheduling optimization, as shown in formula (10), (10); Step B328, construct the demand allocation sum constraint, specifically to ensure that the sum of the demand for each shift does not exceed its carrying capacity, as shown in formula (11), (11).

[0017] Step C, the vehicle-side operation module of the driverless bus disassembles and assembles the driverless bus according to the dispatch instruction to form a new bus formation, and then completes the passenger pick-up and drop-off operations at each bus stop through the new bus formation, wherein the vehicle-side operation module of the driverless bus includes a driving control module and a module control module, and the process of the vehicle-side operation module of the driverless bus executing the dispatch instruction specifically adjusts the configuration and route of the bus fleet.

[0018] A demand-response-based unmanned bus allocation and dispatching system comprises a detection input module, a dispatching output module and a dispatching execution module, wherein the detection input module is used to use a bus stop sensing module to sense the riding demand of each bus stop in real time and obtain riding demand data, and then output the riding demand data to a back-end dispatching module; the dispatching output module is used to use the back-end dispatching module to use an unmanned bus flexible formation method to calculate an optimal dispatching scheme according to the riding demand and output dispatching instructions to a vehicle-side operation module of the unmanned bus; the dispatching execution module is used to use the vehicle-side operation module of the unmanned bus to disassemble and splice the unmanned buses according to the dispatching instructions and form a new bus formation, and then complete the passenger pick-up and drop-off operations at each bus stop through the new bus formation.

[0019] In summary, the demand-responsive unmanned bus allocation and dispatching method and system of the present invention firstly uses the bus stop sensing module to sense the riding demand of each bus stop in real time and obtain the riding demand data, and then outputs the riding demand data to the back-end dispatching module, and then uses the back-end dispatching module to calculate the optimal dispatching plan according to the riding demand using the unmanned bus flexible formation method and outputs the dispatching instruction to the vehicle-side operation module of the unmanned bus, and then the vehicle-side operation module of the unmanned bus disassembles and splices the unmanned bus according to the dispatching instruction to form a new bus formation, and then completes the passenger pick-up and drop-off operation of each bus stop through the new bus formation; the unmanned bus allocation and dispatching method and system effectively realize the function of dynamically adjusting the bus formation and dispatching by using the real-time sensing technology and the demand prediction model, which not only reduces the waiting time of passengers, but also optimizes the vehicle passenger load factor, while also reducing the formation reorganization cost and enhancing the flexibility and adaptability of bus operation, improving the quality of public transportation services, and promoting sustainable transportation development.

[0020] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for dispatching driverless buses based on demand response, characterized in that: The following steps are included: Step A, using the bus stop sensing module to sense the bus demand at each bus stop in real time and obtain the bus demand data, and then output the bus demand data to the back-end scheduling module; Step B, using the back-end dispatching module to calculate the optimal dispatching plan based on the passenger demand using the driverless bus flexible formation method and output the dispatching instruction to the vehicle-side operation module of the driverless bus; In step C, the vehicle-side operation module of the driverless bus disassembles and assembles the driverless bus according to the dispatching instructions to form a new bus formation, and then completes the passenger pick-up and drop-off operations at each bus stop through the new bus formation.

2. The demand-response-based driverless bus dispatching method according to claim 1, characterized in that: Step A, using the bus stop sensing module to sense the riding demand of each bus stop in real time and obtain riding demand data, and then output the riding demand data to the back-end scheduling module, wherein the bus stop sensing module uses a video camera to monitor the riding demand of passengers waiting at the bus stop in real time, and the riding demand includes the number of waiting passengers and the waiting time of passengers. The specific real-time sensing steps are as follows: Step A1, image acquisition and passenger detection, wherein the image acquisition specifically uses a video camera to collect images of the waiting area of ​​the bus station in real time, and the passenger detection specifically uses an image processing method to detect waiting passengers in the image; Step A2, passenger counting and waiting time calculation, wherein the passenger counting specifically counts the detected waiting passengers and obtains the current number of waiting passengers, and the waiting time calculation specifically calculates the waiting time of each passenger according to the continuous appearance time of the waiting passengers in the image; Step A3, output the riding demand data to the back-end scheduling module, specifically, transmit the calculated number of waiting passengers, waiting time information and platform code to the back-end scheduling module, the number of waiting passengers is the total number of passengers waiting at the current platform, the waiting time information is the average value calculated based on the continuous appearance time, and the platform code is the unique identification code of each platform.

3. The demand-response-based driverless bus dispatching method according to claim 2 is characterized by: Step B, using the back-end dispatching module to calculate the optimal dispatching plan according to the riding demand using the driverless bus flexible formation method and output the dispatching instruction to the vehicle-side operation module of the driverless bus, wherein the specific steps of the driverless bus flexible formation method are as follows: Step B1, data reception and integration, specifically, integrating the bus demand data received from the bus station sensing module at five-minute intervals to form a demand matrix. Demand matrix for time periods As shown in formula (1), （1） in, Code the i-th station, is the total number of waiting passengers, is the average waiting time, n is the number of platforms; Step B2, data analysis and demand forecasting, specifically, threshold detection of the number of waiting passengers and waiting time at each platform is performed to calculate the peak passenger demand area, and then identify the demand hotspot area and time period, as shown in formula (2). （2） in, and They are the passenger number threshold and waiting time threshold respectively; Step B3, fleet optimization, specifically, calculates the optimal bus fleet and dispatching plan based on real-time passenger demand data and forecast data to meet peak passenger demand and optimize vehicle operating efficiency. The specific steps are as follows: Step B31, determine the decision variable as the module deployment instruction , Vehicle dispatch instructions and passenger allocation variables , the module deployment instructions For disassembling the kth modular bus body from the jth shift for redeployment, the vehicle dispatching instruction For selecting the j-th shift vehicle for dispatch optimization, the passenger allocation variable Used to allocate the demand of the ith station to the jth shift; Step B32, establish a scheduling optimization model, specifically setting the objective function to minimize passenger waiting time, optimize vehicle passenger load factor and reduce fleet reorganization cost. The objective function is shown in formula (3): （3） in, is the total waiting time of passengers at platform i, m is the total number of bus trips on the bus line, n is the total number of platforms, is the formation reorganization cost of reorganization module k of shift j, is the maximum passenger capacity of a single vehicle, is the number of vehicles in shift j, and is the weighting coefficient; Step B4, generating a dispatch instruction, using a back-end dispatch module to generate a dispatch instruction according to the formation optimization strategy and the dispatch plan, wherein the dispatch instruction includes a platform target, formation structure, route, arrival time, and disassembly and splicing operation instructions; Step B5, dispatch instruction sending and confirmation, the back-end dispatch module uses a wireless network and a reliable data transmission protocol to send the dispatch instruction to the vehicle-side operation module of the driverless bus and receive a confirmation receipt. If the back-end dispatch module finds a problem in the confirmation receipt, it will resend or adjust the instruction; Step B6, real-time monitoring and feedback, using the bus stop sensing module to continuously monitor the changes in demand at each stop, the operating status of the bus and the number of passengers boarding the bus, and to provide real-time feedback data to the back-end scheduling module, which then dynamically adjusts the formation, route and scheduling plan based on the monitoring data.

4. The demand-response-based driverless bus dispatching method according to claim 3 is characterized by: The constraints of the objective function in step B32 include demand allocation constraints, vehicle capacity constraints, platoon structure constraints, total vehicle number constraints, platoon operation constraints, route arrangement constraints, vehicle scheduling optimization constraints and demand allocation sum constraints. The specific objective function constraint construction steps are as follows: Step B321, construct the allocation constraint, as shown in formula (4): （4） in, is the i-th bus stop, is any i-th bus stop; Step B322, construct vehicle capacity constraints, specifically the number of passengers in each shift must not exceed the total capacity of the vehicles in shift j, as shown in formula (5), （5） in, is any j-th bus trip; Step B323, construct the formation structure constraint. Specifically, the number of vehicles in each shift j is composed of the selected buses, as shown in formula (6): （6） in, is the original modular bus body k in the jth shift; Step B324, construct the total number of vehicles constraint. The total number of vehicles on all shifts on a specific route must be equal to the total number of vehicles on the current route, as shown in formula (7). （7） in, is the total number of all modular bus bodies on the current route; Step B325, construct the formation operation constraints. The disassembly and assembly operation time of the specific formation must be completed within the allowed operation time, as shown in formula (8). （8） in, is the formation operation time of module k in shift j, is the maximum allowed operation time, for any module k; Step B326, construct route scheduling constraints. Specifically, the route scheduling time of each shift j must be completed within the set time window, as shown in formula (9): （9） in, is the route time of flight j, for a given time window; Step B327, construct vehicle scheduling optimization constraints, specifically to determine which shifts j need scheduling optimization, as shown in formula (10), （10）； Step B328, construct the demand allocation sum constraint, specifically to ensure that the sum of the demand for each shift does not exceed its carrying capacity, as shown in formula (11), （11）。 5. The demand-response-based driverless bus dispatching method according to claim 4, characterized in that: Step C, the vehicle-side operation module of the driverless bus disassembles and assembles the driverless bus according to the dispatch instruction to form a new bus formation, and then completes the passenger pick-up and drop-off operations at each bus stop through the new bus formation, wherein the vehicle-side operation module of the driverless bus includes a driving control module and a module control module, and the process of the vehicle-side operation module of the driverless bus executing the dispatch instruction specifically adjusts the configuration and route of the bus fleet.

6. A demand-response-based driverless bus allocation and dispatching system, wherein the specific allocation and dispatching process of the driverless bus allocation and dispatching system is based on the driverless bus allocation and dispatching method according to any one of claims 1 to 5, characterized in that: It includes a detection input module, a dispatch output module and a dispatch execution module. The detection input module is used to use the bus stop sensing module to sense the riding demand of each bus stop in real time and obtain the riding demand data, and then output the riding demand data to the back-end dispatch module; The dispatch output module is used to use the back-end dispatch module to calculate the optimal dispatch plan according to the passenger demand using the driverless bus flexible formation method and output the dispatch instruction to the vehicle-side operation module of the driverless bus; The dispatch execution module is used for the vehicle-side operation module of the driverless bus to disassemble and assemble the driverless bus according to the dispatch instruction to form a new bus formation, and then complete the passenger pick-up and drop-off operations at each bus stop through the new bus formation.

Images