Method and device for generating an autonomous driving bus operation plan based on variable time control points

Abstract

The present application provides a method, device, storage medium, and electronic device for generating an autonomous driving bus operation plan based on variable time control points, relating to the field of autonomous driving technology. The method comprises: obtaining a probability distribution function of bus travel time between stations on a target bus route based on first operation information; determining key stations on the target bus route based on second operation information, and generating a set of fixed time control points based on the key stations; and generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points. The method for generating an autonomous driving bus operation plan based on variable time control points provided in the present application is used to scientifically determine the time control point plan for each autonomous driving bus shift and its planned arrival time at each time control point through modeling, thereby fully leveraging the advantages of autonomous driving technology, improving line operation reliability, and improving bus service quality.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, storage medium, and electronic device for generating an autonomous driving bus operation plan based on variable time control points. Background Art

[0002] With the development of autonomous driving technology, self-driving buses have been deployed in many cities. Compared to manually driven buses, self-driving buses can implement more flexible operation plans and control schemes, providing passengers with more reliable and punctual transportation services.

[0003] However, the autonomous driving bus operation scheme in related technologies ignores the impact of the time-varying nature of road traffic conditions on bus operation reliability, resulting in difficulty in effectively ensuring line operation reliability when the probability distribution of travel time between bus stops changes significantly.

[0004] Based on this, there is an urgent need for a method to generate an autonomous driving bus operation plan to provide a bus operation plan that can better adapt to changes in traffic conditions, improve line operation reliability, and improve bus service quality. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, storage medium and electronic equipment for generating an autonomous driving bus operation plan based on variable time control points, which is used to scientifically decide the time control point plan for each autonomous driving bus trip and the planned arrival time at each time control point through modeling, so as to give full play to the advantages of autonomous driving technology, improve the reliability of line operation, and improve the quality of bus service.

[0006] The present application provides a method for generating an autonomous bus operation plan based on variable time control points, comprising: fitting a probability distribution function of bus travel time between stations on the target bus line based on first operation information of the target bus line; determining key stations on the target bus line based on second operation information of the target bus line, and generating a set of fixed time control points based on the key stations; generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points; wherein the first operation information includes: the travel time of the bus between adjacent stations and the stop time at each station; the second operation information includes: historical passenger flow data of the bus and route characteristic information of the bus; the time control points are stations on the target bus line used to constrain the arrival time of the bus; and the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point.

[0007] Optionally, the method generates a target operation plan based on the probability distribution function and the fixed time control point set using a deterministic mixed integer linear programming model, including: establishing a random mixed integer nonlinear programming model; wherein the random mixed integer nonlinear programming model is used to constrain the position and number of time control points and the vehicle operation slack time between adjacent stations, as well as to decide the optimal time control points for each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point, so that the weighted sum of the arrival time deviation negative utility and the operation time deviation negative utility of the autonomous driving bus is minimized.

[0008] Optionally, the objective function value of the random mixed integer nonlinear programming model is calculated based on the following formula: min z = α·z d +τ·z w

[0009] Where z is the objective function value; α is a non-negative weight coefficient, which is used to represent the negative utility z of reducing the arrival time deviation. d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w importance.

[0010] Optionally, based on the probability distribution function and the fixed time control point set, a deterministic mixed integer linear programming model is used to generate a target operation plan, including: introducing auxiliary variables to perform a linearization operation on the random mixed integer nonlinear programming model, and converting the random mixed integer nonlinear programming model into a random mixed integer linear programming model; wherein the objective function value of the random mixed integer linear programming model is: calculated based on the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the arrival time deviation, the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the running time deviation, the set of autonomous driving bus schedules, and the set of autonomous driving bus pass stations.

[0011] Optionally, the objective function value of the random mixed integer linear programming model is calculated based on the following formula:

[0012] Where z is the objective function value; and is an auxiliary variable; α is a non-negative weight coefficient used to characterize the negative utility of reducing arrival time deviation z d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of autonomous driving bus schedules; K is the set of autonomous driving bus routes, and K = {1, 2, ..., k, ..., |K|}; J is the set of autonomous driving bus stops, and J = {1, 2, ..., j, ..., |J|}.

[0013] Optionally, based on the probability distribution function and the fixed time control point set, a deterministic mixed integer linear programming model is used to generate a target operation plan, including: generating multiple sample observations based on the probability distribution function, and calculating the sample mean of the multiple sample observations; using the sample mean to replace the expected value of the random parameter in the random mixed integer linear programming model, and converting the random mixed integer linear programming model into a deterministic mixed integer linear programming model.

[0014] Optionally, the method of generating a target operation plan based on the probability distribution function and the fixed time control point set using a deterministic mixed integer linear programming model includes: using a branch and bound method to solve the deterministic mixed integer linear programming model to obtain the optimal solution of the time control points of each shift of the autonomous driving bus, and the planned arrival time corresponding to each time control point; generating the target operation plan based on the optimal solution of the time control points of each shift of the autonomous driving bus, and the planned arrival time corresponding to each time control point.

[0015] The present application also provides an apparatus for generating an autonomous bus operation plan based on variable time control points, comprising: an information acquisition module for fitting a probability distribution function of bus travel time between stations on a target bus line based on first operation information of the target bus line, and determining key stations on the target bus line based on second operation information of the target bus line, and generating a set of fixed time control points based on the key stations; a plan generation module for generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points; wherein the first operation information includes: the travel time of the bus between adjacent stations and the stop time at each station; the second operation information includes: historical passenger flow data of the bus and route characteristic information of the bus; the time control points are stations on the target bus line used to constrain the arrival time of the bus; and the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point.

[0016] Optionally, the solution generation module is specifically used to establish a random mixed integer nonlinear programming model; wherein the random mixed integer nonlinear programming model is used to constrain the location and number of time control points and the vehicle operation slack time between adjacent stations, and to decide the optimal time control points for each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point, so that the weighted sum of the negative utility of the arrival time deviation and the negative utility of the operating time deviation of the autonomous driving bus is minimized.

[0017] Optionally, the objective function value of the random mixed integer nonlinear programming model is calculated based on the following formula: min z = α·z d +τ·z w

[0018] Where z is the objective function value; α is a non-negative weight coefficient, which is used to represent the negative utility z of reducing the arrival time deviation. d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w importance.

[0019] Optionally, the solution generation module is specifically used to introduce auxiliary variables to perform a linearization operation on the random mixed integer nonlinear programming model, and convert the random mixed integer nonlinear programming model into a random mixed integer linear programming model; wherein the objective function value of the random mixed integer linear programming model is: calculated based on the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the arrival time deviation, the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the running time deviation, the set of autonomous driving bus schedules, and the set of autonomous driving bus pass stations.

[0020] Optionally, the objective function value of the random mixed integer linear programming model is calculated based on the following formula:

[0021]

[0022] Where z is the objective function value; and is an auxiliary variable; α is a non-negative weight coefficient used to characterize the negative utility of reducing arrival time deviation z d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of autonomous driving bus schedules; K is the set of autonomous driving bus routes, and K = {1, 2, ..., k, ..., |K|}; J is the set of autonomous driving bus stops, and J = {1, 2, ..., j, ..., |J|}.

[0023] Optionally, the solution generation module is specifically used to generate multiple sample observations based on the probability distribution function and calculate the sample mean of the multiple sample observations; the solution generation module is also specifically used to use the sample mean to replace the expected value of the random parameter in the random mixed integer linear programming model, and convert the random mixed integer linear programming model into a deterministic mixed integer linear programming model.

[0024] Optionally, the solution generation module is specifically used to use the branch and bound method to solve the deterministic mixed integer linear programming model to obtain the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point; the solution generation module is also specifically used to generate the target operation plan based on the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point.

[0025] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of any of the above-mentioned methods for generating an autonomous driving bus operation plan based on variable time control points.

[0026] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for generating an autonomous driving bus operation plan based on variable time control points as described above are implemented.

[0027] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for generating an autonomous driving bus operation plan based on variable time control points as described above are implemented.

[0028] The present application provides a method, device, storage medium, and electronic device for generating an autonomous bus operation plan based on variable time control points. First, based on first operation information of a target bus route, a probability distribution function of bus travel time between stations on the target bus route is fitted. Furthermore, based on second operation information of the target bus route, key stations of the target bus route are determined, and a set of fixed time control points is generated based on the key stations. Subsequently, a deterministic mixed integer linear programming model is used to generate a target operation plan based on the probability distribution function and the set of fixed time control points. The first operation information includes the travel time of buses between adjacent stations and the stop time at each station. The second operation information includes historical passenger flow data of buses and bus route characteristic information. The time control points are stations on the target bus route used to constrain the arrival times of buses. The target operation plan includes the optimal solution of the time control points for each autonomous bus trip and the planned arrival times corresponding to each time control point. In this way, by modeling and scientifically deciding the time control point plan for each autonomous bus service and its planned arrival time at each time control point, the advantages of autonomous driving technology can be fully utilized, the line operation reliability can be improved, and the quality of bus service can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0030] Figure 1 This is a flow chart of a method for generating an autonomous driving bus operation plan based on variable time control points provided by this application;

[0031] Figure 2 This is a schematic diagram of the structure of the device for generating an autonomous driving bus operation plan based on variable time control points provided by this application;

[0032] Figure 3 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0035] The widespread application of emerging technologies in the field of public transportation has prompted the traditional public transportation system to rapidly evolve into a smart public transportation system with integration, personalization, electrification and automation as its typical characteristics. At present and for a long period of time in the future, it is inevitable that self-driving buses will run on ordinary open roads, so scientific vehicle scheduling and operation control methods are still needed to ensure the reliability and punctuality of self-driving buses. Compared with manually driven buses, self-driving buses can implement more flexible operation plans and control plans, providing passengers with more reliable and punctual transportation services. Therefore, the embodiment of the present application proposes a method for designing an operation plan for an autonomous driving bus based on variable time control points. By modeling and scientifically deciding the time control point plan for each autonomous driving bus and its planned arrival time at each time control point, the advantages of autonomous driving technology are fully utilized, the reliability of line operation is comprehensively improved, and the quality of bus service is effectively improved.

[0036] The following, in conjunction with the accompanying drawings, describes in detail the method for generating an autonomous driving bus operation plan based on variable time control points provided by the embodiment of the present application through specific embodiments and their application scenarios.

[0037] like Figure 1 As shown, an embodiment of the present application provides a method for generating an autonomous driving bus operation plan based on variable time control points. The method may include the following steps 101 and 102.

[0038] Step 101: Based on the first operation information of a target bus route, a probability distribution function of bus travel time between stops of the target bus route is obtained by fitting. Based on the second operation information of the target bus route, key stops of the target bus route are determined, and a fixed-time control point set is generated based on the key stops.

[0039] The first operation information includes the bus's travel time between adjacent stops and the time it spends at each stop. The second operation information includes historical bus passenger flow data and bus route characteristics. This route characteristics information is used to describe the characteristics of the target bus route and includes information about stops along the route, land use data around the stops, and points of interest data.

[0040] Exemplarily, the above-mentioned target bus route is any bus route for which an autonomous driving bus operation method needs to be generated. Other bus routes can also refer to the autonomous driving bus operation plan generation method based on variable time control points provided in the embodiment of the present application to generate the required operation plan.

[0041] Exemplarily, the above-mentioned fixed time control point set includes multiple time control points, including at least the first and last stations of the line.

[0042] It should be noted that the time control point in the embodiment of the present application is a station on a bus line used to constrain the arrival time of a bus, for example, constraining the time when a bus arrives at a key station.

[0043] Step 102: Based on the probability distribution function and the fixed time control point set, a target operation plan is generated using a deterministic mixed integer linear programming model.

[0044] The time control points are stations on the target bus route used to constrain the arrival times of buses. The target operation plan includes the optimal solution for the time control points of each autonomous driving bus and the planned arrival times corresponding to each time control point.

[0045] For example, after obtaining the above-mentioned probability distribution function and the fixed-time control point set, a target operation plan for the target bus route can be generated using a deterministic mixed integer linear programming model.

[0046] It should be noted that the embodiments of this application consider the volatility of random bus operating times and the feasibility of autonomous buses implementing complex operating plans. A mathematical model is constructed to jointly determine the optimal time control point plan for each autonomous bus shift and its planned arrival time at each time control point, effectively improving the operational reliability of bus routes. This invention can provide theoretical guidance and decision-making support for public transportation companies to scientifically formulate autonomous bus operation plans and control schemes, and has broad application prospects.

[0047] Optionally, in an embodiment of the present application, the above-mentioned deterministic mixed integer linear programming model is obtained by converting the constructed random mixed integer nonlinear programming model.

[0048] Specifically, the above step 102 may further include the following step 102a.

[0049] Step 102a: Establish a random mixed integer nonlinear programming model.

[0050] The random mixed integer nonlinear programming model is used to determine the optimal time control points for each shift of the autonomous bus and the planned arrival times corresponding to each time control point, so as to minimize the weighted sum of the negative utility of the arrival time deviation and the negative utility of the running time deviation of the autonomous bus.

[0051] For example, the design of an autonomous bus operation plan based on variable time control points aims to minimize the weighted sum of the negative utility of the autonomous bus arrival time deviation and the negative utility of the operating time deviation within the study time range by scientifically deciding the optimal time control point plan for each autonomous bus shift and its planned arrival time at each time control point.

[0052] The details are shown in the following formula 1:

[0053] min z=α·z d +τ·z w (Formula 1)

[0054] Among them, z is the model objective function value, z d To study the negative utility caused by the deviation between the planned arrival time and the actual arrival time of autonomous driving bus stops within a certain time range, referred to as the arrival time deviation negative utility; w It is the negative utility caused by the deviation between the planned operating time of the autonomous driving bus section output by the model and the planned operating time of the autonomous driving bus section expected by the enterprise, referred to as the operating time deviation negative utility; α is a non-negative weight coefficient, which represents the importance of reducing the negative utility of arrival time deviation; τ is a non-negative weight coefficient, which represents the importance of reducing the negative utility of operating time deviation.

[0055] The arrival time deviation of the autonomous bus is the deviation between the planned arrival time of the autonomous bus and its actual arrival time, which reflects the punctuality of the autonomous bus. Therefore, the arrival time deviation of the kth autonomous bus at station j is Equal to the planned arrival time of the kth autonomous bus at station j The actual arrival time of the kth autonomous bus at station j The difference is shown in the following formula 2.

[0056]

[0057] The planned arrival time of the kth autonomous bus at station j The bus is scheduled to arrive at stop j-1 Average stop time at station j-1 and its planned travel time between station j-1 and station j Determine together, as shown in the following formula three.

[0058]

[0059] The above average stop time is determined based on the first operation information of the target bus line. Based on the first operation information, the average stop time of the bus at various locations can be determined.

[0060] Planned travel time of the autonomous bus between station j-1 and station j Equal to the actual driving time Expected value and relaxation time The sum of , as shown in the following formula 4.

[0061]

[0062] Relaxation time The existence of enables the autonomous bus to flexibly adjust its speed between station j-1 and station j as needed so as to arrive at the next time control point on time. However, the introduction of slack time may significantly increase the running time of the autonomous bus and increase the line operation cost. To this end, the constraint condition formula five is set to ensure that the sum of the slack time of each autonomous bus shift does not exceed the maximum value of the total slack time of 0.5·H·V-0.5·C determined by the number of equipped autonomous buses V, the planned departure interval H and the planned turnaround time C, that is, to ensure that the introduction of slack time does not increase the fleet size required for the line (an important component of line operation costs). Formula six further clarifies the slack time between adjacent stations. In formula 6, X min and X max are the minimum and maximum acceptable slack time between adjacent stops of autonomous buses, respectively.

[0063]

[0064]

[0065] The planned turnaround time is determined based on the first operation information of the target bus line. Based on the first operation information, the average turnaround time of the bus can be determined.

[0066] The actual arrival time of the kth autonomous bus at station j The actual arrival time at station j-1 Average stop time Actual travel time between station j-1 and station j and the adjustment time generated by the vehicle to "correct" the arrival time deviation at station j-1, as shown in Formula 7. In Formula 7, is the adjustment factor for the arrival time deviation of the k-th autonomous bus between station j-1 and station j at station j-1.

[0067]

[0068] Two non-negative parameters γ1 and γ2 are used to represent the penalty coefficients for the autonomous bus arriving earlier or later than planned at station j, respectively. Their values can be determined according to the preferences of the designers of the autonomous bus operation plan. Therefore, the generalized arrival time deviation of the kth autonomous bus at station j is It can be calculated according to the following formula 8.

[0069]

[0070] When designing the operation plan of autonomous buses, the deviation of generalized arrival time should be minimized. However, due to the openness and complexity of the road traffic environment, the actual driving time of autonomous buses is and its ability to adjust arrival time deviations are all random, and accordingly, the generalized arrival time deviation is also random. Therefore, if only minimizing the generalized arrival time deviation is considered when designing the operation plan, the generalized arrival time deviation may fluctuate greatly. Therefore, the negative utility of the arrival time deviation z is defined as d The weighted sum of the expected value of the generalized arrival time deviation and the expected value of the absolute deviation of the generalized arrival time deviation from its expected value can be calculated according to Formula 9. In Formula 9, λ is a parameter that penalizes the volatility of the arrival time deviation of the autonomous bus; is a binary variable. If bus stop j is the time control point of the k-th autonomous driving bus, its value is 1, otherwise it is 0, as shown in Formula 10.

[0071]

[0072]

[0073] When deciding whether bus stop j is the time control point for the kth autonomous bus, it is also necessary to comprehensively consider the total number of time control points along the route of the autonomous bus and the layout of other time control points along its route. When there are too few time control points along the route of the autonomous bus, the overall punctuality and operational reliability of the autonomous bus cannot be effectively guaranteed; on the contrary, if there are too many time control points along the route, the autonomous bus will frequently accelerate and decelerate to “catch up” with the planned arrival time at each time control point, which will have an adverse effect on the safety and comfort of the passengers and increase the energy consumption of the vehicle. Therefore, constraints are added to control the total number of time control points along the route of each autonomous bus, as shown in Formula 11 and Formula 12. In Formula 11, d k It is represented by the number of time control points of the k-th autonomous driving bus route; in Formula 12, D min and D max They represent the minimum and maximum time control points for each autonomous bus route.

[0074]

[0075]

[0076] binary variables The introduction of means that the time control point layout plan will be completely scientifically determined by the mathematical model established. Considering that some stations, such as bus terminals and transfer stations, have high requirements for the on-time arrival rate of buses, it is advisable to use them as fixed time control points to ensure the on-time arrival rate of each autonomous driving bus at such stations, as shown in Formula 13. In Formula 13, G is the set of fixed time control points, g∈G.

[0077]

[0078] In addition, in order to avoid "excessive" acceleration and deceleration behaviors of the autonomous bus within a short distance, the constraint condition formula 14 is added to ensure that adjacent bus stops are not set as time control points for the same autonomous bus at the same time.

[0079]

[0080] At the same time, the time control points along the routes of each autonomous bus should be evenly distributed. This means minimizing differences in the reliability of each section while improving the overall operational reliability of the route (ensuring no significant differences in bus service levels between sections and ensuring fairness in bus service). A uniform distribution of time control points also facilitates the smooth operation of autonomous buses, ensuring the safety and comfort of public transportation. Therefore, constraints Formulas 15, 16, and 17 are added to measure the uniformity of the distribution of time control points for each bus.

[0081]

[0082]

[0083]

[0084] In formula 15, The planned running time of the kth autonomous bus between the upstream time control point closest to station j and station j; in formula 16, b k is the planned operating time of the kth autonomous bus segment expected by the enterprise, and Y is the ratio of the number of ordinary stations (i.e., bus stations not set as time control points) in any segment expected by the enterprise to the total number of stations on the route; in Formula 17, w k It is the sum of the deviations between the planned operating time of each section of the k-th autonomous driving bus output by the model and the reference value of the planned operating time of each section expected by the enterprise.

[0085] The more time control points there are along the route, the less conducive it is to the smooth operation of the autonomous bus. Therefore, we should focus on the uniformity of the control point layout of the bus routes with more time control points, as shown in Formula 18. In Formula 18, z wEqual to w for each shift within the research time range k The weighted sum of the values, weight d k is the number of time control points along the route of each bus route, which is defined as the negative utility caused by the deviation between the planned operating time of the autonomous driving bus section output by the model and the planned operating time of the autonomous driving bus section expected by the enterprise, referred to as the operating deviation negative utility.

[0086] z w =∑ k∈K d k w k (Formula 18)

[0087] In order to ensure that the designed operation plan can be applied in practice, the core decision variable inter-station slack time Set to an integer variable with unit of minutes, as shown in Equation 19.

[0088]

[0089] Finally, the objective function formula 1 and constraint condition formulas 2 to 19 constitute a complete autonomous driving bus operation plan generation model based on variable time control points, which is a random mixed integer nonlinear programming model.

[0090] For example, after the random mixed integer nonlinear programming model is constructed, it needs to be converted in order to solve the random mixed integer nonlinear programming model.

[0091] Specifically, after the above step 102a, the above step 102 may further include the following step 102b.

[0092] Step 102b: introduce auxiliary variables to perform a linearization operation on the random mixed integer nonlinear programming model, and transform the random mixed integer nonlinear programming model into a random mixed integer linear programming model.

[0093] Among them, the objective function value of the random mixed integer linear programming model is: calculated based on the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the arrival time deviation, the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the running time deviation, the set of autonomous driving bus schedules, and the set of autonomous driving bus pass stations.

[0094] Exemplarily, the objective function value of the random mixed integer linear programming model is calculated based on the following formula:

[0095]

[0096] Where z is the objective function value; and is an auxiliary variable; α is a non-negative weight coefficient used to characterize the negative utility of reducing arrival time deviation z d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of autonomous driving bus schedules; K is the set of autonomous driving bus routes, and K = {1, 2, ..., k, ..., |K|}; J is the set of autonomous driving bus stops, and J = {1, 2, ..., j, ..., |J|}.

[0097] Exemplarily, the random mixed integer linear programming model obtained after conversion also includes the following formulas 21 to 72.

[0098]

[0099]

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125]

[0126]

[0127]

[0128]

[0129]

[0130]

[0131]

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142]

[0143]

[0144]

[0145]

[0146]

[0147]

[0148]

[0149]

[0150] In formula 20, z is the model objective function value (unit: minute); and is an auxiliary variable; α is a non-negative weight coefficient, which represents the importance of reducing the negative utility of the deviation of the arrival time of the autonomous bus; τ is a non-negative weight coefficient, which represents the importance of reducing the negative utility of the deviation of the running time of the autonomous bus; K is the set of autonomous bus schedules within the study time range, K = {1, 2, ..., k, ..., |K|}; J is the set of stations passed by the autonomous bus in the study, J = {1, 2, ..., j, ..., |J|}.

[0151] In formula twenty-one, is the arrival time deviation of the kth autonomous bus at station j (unit: minute); Plan the arrival time for the kth autonomous bus at station j; is the actual arrival time of the kth autonomous bus at station j.

[0152] In formula twenty-two, is the average stop time of the k-th autonomous bus at station j-1 (unit: minutes); Planned travel time (in minutes) for the kth autonomous bus between station j-1 and station j.

[0153] In formula 23, is the actual travel time of the k-th autonomous bus between station j-1 and station j (unit: minutes), which is random; is the slack time of the kth autonomous bus between station j-1 and station j (unit: minutes).

[0154] In Formula 24, H is the scheduled departure interval of the autonomous bus (unit: minutes); V is the number of available autonomous buses (unit: vehicles); C is the planned turnaround time of the autonomous bus (unit: minutes); in Formula 25, X min is the minimum acceptable relaxation time between adjacent sites (unit: minutes); X max is the maximum acceptable relaxation time between adjacent sites (unit: minute). In formula 26, is the adjustment factor for the arrival time deviation of the k-th autonomous bus between station j-1 and station j, which is random.

[0155] In formula 27, is the generalized arrival time deviation of the kth autonomous bus at station j (unit: minute); γ1 is the parameter that penalizes the autonomous bus for arriving at the station earlier than the planned arrival time; is an auxiliary variable; γ2 is a parameter that penalizes the autonomous bus for arriving at the station later than the planned arrival time; is an auxiliary variable. In formula 20, M is a very large positive number; is a binary auxiliary variable; in formula 34, is a binary auxiliary variable.

[0156] In formula 40, and is an auxiliary variable; in Formula 42, λ is a parameter that penalizes the volatility of the arrival time deviation of the autonomous driving bus; in Formula 43, is a binary variable. If bus stop j is the time control point of the kth autonomous bus, its value is 1, otherwise it is 0. In formula 47, d k It is represented by the number of time control points of the k-th autonomous driving bus route (unit: piece); in Formula 48, D min It is represented by the minimum number of time control points of each autonomous bus route (unit: number); D max It is represented by the maximum number of time control points (unit: number) of each autonomous driving bus route; in Formula 49, G is the fixed time control point set, g∈G.

[0157] In formula fifty-one, is the planned running time of the kth autonomous bus between the upstream time control point closest to station j and station j (unit: minutes); is an auxiliary variable; in formula 56, b kis the planned operating time of the kth autonomous bus segment expected by the enterprise (unit: minute); Y is the ratio of the number of ordinary stops (i.e., bus stops not set as time control points) in any segment expected by the enterprise to the total number of stops on the route; in Formula 57, is an auxiliary variable.

[0158] In formula sixty-one, and is an auxiliary variable; in formula 63, is an auxiliary variable; in formula 67, w k is the sum of the deviations between the planned operating time of each section of the k-th autonomous bus output by the model and the planned operating time of each section expected by the enterprise (unit: minute); in formula 68, is an auxiliary variable; in formula 72, is a set of integers.

[0159] For example, after the random mixed integer nonlinear programming model is converted into a random mixed integer linear programming model, in order to solve the model, the model needs to be converted again.

[0160] Specifically, after the above step 102b, the above step 102 may further include the following steps 102c1 and 102c2.

[0161] Step 102c1: Generate multiple sample observation values based on the probability distribution function, and calculate the sample mean of the multiple sample observation values.

[0162] Step 102c2: Use the sample mean to replace the expected value of the random parameter in the random mixed integer linear programming model, and convert the random mixed integer linear programming model into a deterministic mixed integer linear programming model.

[0163] For example, a random mixed-integer linear programming model is converted to a deterministic mixed-integer linear programming model based on Monte Carlo simulation. Monte Carlo simulation is used to randomly generate multiple sample observations based on the probability distribution function of bus stop travel time determined by fitting in the above steps. The sample mean is used to approximate the expected value, and the random mixed-integer linear programming model is converted to a deterministic mixed-integer linear programming model. The deterministic mixed-integer linear programming model is defined as shown in Formulas 73 to 125 below.

[0164]

[0165]

[0166]

[0167]

[0168]

[0169]

[0170]

[0171]

[0172]

[0173]

[0174]

[0175]

[0176]

[0177]

[0178]

[0179]

[0180]

[0181]

[0182]

[0183]

[0184]

[0185]

[0186]

[0187]

[0188]

[0189]

[0190]

[0191]

[0192]

[0193]

[0194]

[0195]

[0196]

[0197]

[0198]

[0199]

[0200]

[0201]

[0202]

[0203]

[0204]

[0205]

[0206]

[0207]

[0208]

[0209]

[0210]

[0211]

[0212]

[0213]

[0214]

[0215]

[0216]

[0217] In formula 73, z is the model objective function value (unit: minute); and is an auxiliary variable; α is a non-negative weight coefficient, which represents the importance of reducing the negative utility of arrival time deviation; τ is a non-negative weight coefficient, which represents the importance of reducing the negative utility of running time deviation; K is the set of autonomous driving bus schedules within the study time range, K = {1, 2, ..., k, ..., |K|}; J is the set of stations passed by the autonomous driving bus in the study, J = {1, 2, ..., j, ..., |J|}.

[0218] In formula seventy-four, is the arrival time deviation of the kth autonomous bus at station j (unit: minute); Plan the arrival time for the kth autonomous bus at station j; is the actual arrival time of the kth autonomous driving bus at station j; in formula 75, is the average stop time of the k-th autonomous bus at station j-1 (unit: minutes); is the planned travel time of the kth autonomous bus between station j-1 and station j (unit: minutes); in formula 76, is the actual travel time (in minutes) of the kth autonomous bus between station j-1 and station j, which is random; N is the number of samples randomly generated according to the probability distribution function of the bus travel time between stations in the Monte Carlo simulation; is the slack time of the kth autonomous bus between station j-1 and station j (unit: minute); in formula 77, H is the scheduled departure interval of the autonomous bus (unit: minute); V is the number of available autonomous buses (unit: vehicle); C is the planned turnaround time of the autonomous bus (unit: minute); in formula 78, X min is the minimum acceptable relaxation time between adjacent sites (unit: minutes); X max is the maximum acceptable relaxation time between adjacent sites (unit: minute); in formula 79, is the adjustment factor for the arrival time deviation of the k-th autonomous bus between station j-1 and station j, which is random.

[0219] Formula eighty, is the generalized arrival time deviation of the kth autonomous bus at station j (unit: minute); γ1 is the parameter that penalizes the autonomous bus for arriving at the station earlier than the planned arrival time; is an auxiliary variable; γ2 is a parameter that penalizes the autonomous bus for arriving at the station later than the planned arrival time; is an auxiliary variable; in formula 81, M is a very large positive number; is a binary auxiliary variable; in formula 87, is a binary auxiliary variable.

[0220] In formula ninety-three, and is an auxiliary variable; in Formula 95, λ is a parameter that penalizes the volatility of the arrival time deviation of the autonomous driving bus; in Formula 96, It is a binary variable. If bus stop j is the time control point of the k-th autonomous bus, its value is 1, otherwise it is 0.

[0221] In formula 100, d k It is represented by the number of time control points of the k-th autonomous driving bus route (unit: piece); in formula 101, D min It is represented by the minimum number of time control points of each autonomous bus route (unit: number); D max It is represented by the maximum number of time control points (unit: number) of each autonomous driving bus route; in formula 102, G is the fixed time control point set, g∈G; in formula 104, is the planned running time of the kth autonomous bus between the upstream time control point closest to station j and station j (unit: minutes); is an auxiliary variable; in formula 109, b k is the planned operating time of the kth autonomous bus segment expected by the enterprise (unit: minute); Y is the ratio of the number of ordinary stops (i.e., bus stops not set as time control points) in any segment expected by the enterprise to the total number of stops on the route; in Formula 110, is an auxiliary variable; in formula 114, and is an auxiliary variable; in formula 116, is an auxiliary variable.

[0222] In formula 120, w k is the sum of the deviations between the planned operating time of each section of the k-th autonomous bus output by the model and the planned operating time of each section expected by the enterprise (unit: minute); in formula 121, is an auxiliary variable; in formula 125, is a set of integers.

[0223] For example, after obtaining the deterministic mixed integer linear programming model, the branch and bound method can be used to solve the model to obtain the optimal time control point plan for each shift of autonomous driving buses and their planned arrival times at each time control point.

[0224] Specifically, after the above step 102c2, the above step 102 may further include the following steps 102d1 and 102d2.

[0225] Step 102d1: Use the branch-and-bound method to solve the deterministic mixed integer linear programming model to obtain the optimal solution for the time control points of each autonomous driving bus and the planned arrival time corresponding to each time control point.

[0226] Step 102d2: Generate the target operation plan based on the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point.

[0227] It should be noted that the branch and bound method can be implemented by some commercial solvers, such as Gurobi, Cplex, etc., and is not further limited in the embodiments of the present application.

[0228] The method for generating an autonomous bus operation plan based on variable time control points provided in an embodiment of the present application first obtains a probability distribution function of bus travel time between stops on a target bus route based on first operation information of the target bus route, and determines key stops on the target bus route based on second operation information of the target bus route, and generates a set of fixed time control points based on the key stops. Then, a deterministic mixed integer linear programming model is used to generate a target operation plan based on the probability distribution function and the set of fixed time control points. The first operation information includes the travel time between adjacent stops and the stop time at each stop. The second operation information includes historical passenger flow data and route characteristics of the bus. The time control points are stops on the target bus route that constrain the arrival time of the bus. The target operation plan includes the optimal solution for the time control points of each autonomous bus trip and the planned arrival time corresponding to each time control point. In this way, by modeling and scientifically determining the time control point plan for each autonomous bus trip and the planned arrival time at each time control point, the advantages of autonomous driving technology are fully utilized, the reliability of route operation is improved, and the quality of bus service is improved.

[0229] It should be noted that the method for generating an autonomous bus operation plan based on variable time control points provided in the embodiments of the present application can be executed by an autonomous bus operation plan generating device based on variable time control points, or by a control module in the autonomous bus operation plan generating device based on variable time control points that is used to execute the method for generating an autonomous bus operation plan based on variable time control points. In the embodiments of the present application, the method for generating an autonomous bus operation plan based on variable time control points is executed by an autonomous bus operation plan generating device based on variable time control points as an example to illustrate the apparatus for generating an autonomous bus operation plan based on variable time control points provided in the embodiments of the present application.

[0230] It should be noted that in the embodiments of this application, the above-mentioned methods and the methods for generating an autonomous driving bus operation plan based on variable time control points are each illustrated by way of example in conjunction with one of the drawings in the embodiments of this application. In specific implementation, the methods for generating an autonomous driving bus operation plan based on variable time control points shown in the above-mentioned method drawings can also be implemented in conjunction with any other combinable drawings shown in the above-mentioned embodiments, and will not be further described here.

[0231] The following describes the device for generating an autonomous driving bus operation plan based on variable time control points provided by this application. The method for generating an autonomous driving bus operation plan based on variable time control points described below can be referenced to each other.

[0232] Figure 2 A schematic diagram of the structure of the device for generating an autonomous driving bus operation plan based on variable time control points provided in an embodiment of the present application is shown as follows: Figure 2 As shown, specifically including:

[0233] The information acquisition module 201 is configured to obtain a probability distribution function of bus travel time between stations on the target bus route based on first operating information of the target bus route, determine key stations on the target bus route based on second operating information of the target bus route, and generate a set of fixed time control points based on the key stations. The plan generation module 202 is configured to generate a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points. The first operating information includes: the travel time of buses between adjacent stations and the stop time at each station; the second operating information includes: historical passenger flow data of buses and bus route characteristic information; the time control points are stations on the target bus route used to constrain the arrival time of buses; and the target operation plan includes: the optimal solution of the time control points for each autonomous bus shift and the planned arrival time corresponding to each time control point.

[0234] Optionally, the solution generation module 202 is specifically used to establish a random mixed integer nonlinear programming model; wherein the random mixed integer nonlinear programming model is used to constrain the location and number of time control points and the vehicle operation slack time between adjacent stations, and to determine the optimal time control points for each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point, so as to minimize the weighted sum of the negative utility of the arrival time deviation and the negative utility of the operating time deviation of the autonomous driving bus.

[0235] Optionally, the objective function value of the random mixed integer nonlinear programming model is calculated based on the following formula: min z = α·z d +τ·z w

[0236] Where z is the objective function value; α is a non-negative weight coefficient, which is used to represent the negative utility z of reducing the arrival time deviation. d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w importance.

[0237] Optionally, the solution generation module 202 is specifically used to introduce auxiliary variables to perform a linearization operation on the random mixed integer nonlinear programming model, and convert the random mixed integer nonlinear programming model into a random mixed integer linear programming model; wherein the objective function value of the random mixed integer linear programming model is: calculated based on the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the arrival time deviation, the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the running time deviation, the set of autonomous driving bus schedules, and the set of autonomous driving bus pass stations.

[0238] Optionally, the objective function value of the random mixed integer linear programming model is calculated based on the following formula:

[0239]

[0240] Where z is the objective function value; and is an auxiliary variable; α is a non-negative weight coefficient used to characterize the negative utility of reducing arrival time deviation z d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of autonomous driving bus schedules; K is the set of autonomous driving bus routes, and K = {1, 2, ..., k, ..., |K|}; J is the set of autonomous driving bus stops, and J = {1, 2, ..., j, ..., |J|}.

[0241] Optionally, the solution generation module 202 is specifically used to generate multiple sample observations based on the probability distribution function and calculate the sample mean of the multiple sample observations; the solution generation module 202 is also specifically used to use the sample mean to replace the expected value of the random parameter in the random mixed integer linear programming model, and convert the random mixed integer linear programming model into a deterministic mixed integer linear programming model.

[0242] Optionally, the solution generation module 202 is specifically used to use the branch and bound method to solve the deterministic mixed integer linear programming model to obtain the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point; the solution generation module 202 is also specifically used to generate the target operation plan based on the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point.

[0243] The present application provides an apparatus for generating an autonomous bus operation plan based on variable time control points. First, based on first operation information of a target bus route, a probability distribution function of bus travel time between stops on the target bus route is fitted. Based on second operation information of the target bus route, key stops on the target bus route are determined, and a set of fixed time control points is generated based on the key stops. Then, based on the probability distribution function and the set of fixed time control points, a deterministic mixed-integer linear programming model is used to generate a target operation plan. The first operation information includes the travel time between adjacent stops and the stop time at each stop. The second operation information includes historical passenger flow data and route characteristics of the bus. The time control points are stops on the target bus route that constrain the arrival times of the bus. The target operation plan includes the optimal time control point solution for each autonomous bus trip and the planned arrival time corresponding to each time control point. In this way, by modeling and scientifically determining the time control point solution for each autonomous bus trip and the planned arrival time at each time control point, the advantages of autonomous driving technology are fully utilized, the reliability of route operation is improved, and the quality of bus service is enhanced.

[0244] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3As shown, the electronic device may include: a processor (Processor) 310, a communication interface (Communications Interface) 320, a memory (Memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logic instructions in the memory 330 to execute a method for generating an autonomous bus operation plan based on variable time control points. The method includes: fitting a probability distribution function of bus travel time between stations on the target bus route based on first operation information of the target bus route; determining key stations on the target bus route based on second operation information of the target bus route, and generating a set of fixed time control points based on the key stations; and generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points. The first operation information includes: the travel time of the bus between adjacent stations and the stop time at each station; the second operation information includes: historical passenger flow data of the bus and bus route characteristic information; the time control points are stations on the target bus route used to constrain the arrival time of the bus; and the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point.

[0245] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0246] On the other hand, the present application also provides a computer program product, comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions. When the program instructions are executed by a computer, the computer is capable of executing the method for generating an autonomous bus operation plan based on variable time control points provided by the above methods. The method comprises: fitting a probability distribution function of bus travel time between stations on the target bus route based on first operation information of the target bus route; determining key stations on the target bus route based on second operation information of the target bus route, and generating a set of fixed time control points based on the key stations; generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points; wherein the first operation information comprises: the travel time of the bus between adjacent stations and the stop time at each station; the second operation information comprises: historical passenger flow data of the bus and bus route characteristic information; the time control points are stations on the target bus route used to constrain the arrival time of the bus; and the target operation plan comprises: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point.

[0247] In another aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method for generating an autonomous bus operation plan based on variable time control points. The method comprises: fitting a probability distribution function of bus travel time between stations on the target bus route based on first operation information of the target bus route; determining key stations on the target bus route based on second operation information of the target bus route, and generating a set of fixed time control points based on the key stations; generating a target operation plan using a deterministic mixed integer linear programming model based on the probability distribution function and the set of fixed time control points; wherein the first operation information includes: the travel time of the bus between adjacent stations and the stop time at each station; the second operation information includes: historical passenger flow data of the bus and bus route characteristic information; the time control points are stations on the target bus route used to constrain the arrival time of the bus; and the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point.

[0248] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0249] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0250] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating an autonomous driving bus operation plan based on variable time control points, characterized in that: include: Fitting a probability distribution function of bus travel time between stops on the target bus route based on first operation information of the target bus route, determining key stops on the target bus route based on second operation information of the target bus route, and generating a set of fixed-time control points based on the key stops; Based on the probability distribution function and the fixed time control point set, a target operation plan is generated using a deterministic mixed integer linear programming model; The first operation information includes: the travel time of the bus between adjacent stops and the stop time at each stop; the second operation information includes: historical passenger flow data of the bus and bus route characteristics; the time control points are: stops on the target bus route used to constrain the arrival time of the bus; the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point; The method of generating a target operation plan based on the probability distribution function and the fixed time control point set by using a deterministic mixed integer linear programming model includes: Establish a random mixed-integer nonlinear programming model; The randomized mixed integer nonlinear programming model is used to constrain the location and number of time control points and the slack time of vehicle operation between adjacent stations, and to determine the optimal time control points for each autonomous bus shift and the planned arrival time corresponding to each time control point, so as to minimize the weighted sum of the negative utility of the autonomous bus's arrival time deviation and the negative utility of its operating time deviation. The objective function value of the random mixed integer nonlinear programming model is calculated based on the following formula: min z=α z d +τ·z w Where z is the objective function value; α is a non-negative weight coefficient, which is used to represent the negative utility z of reducing the arrival time deviation. d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of z w The negative utility caused by the deviation between the planned operating time of the autonomous bus section output by the model and the planned operating time of the autonomous bus section expected by the enterprise, referred to as the operating time deviation negative utility; Disutility of arrival time deviation z d The calculation is based on the following formula 9, where λ is a parameter that penalizes the volatility of the arrival time of the autonomous bus; is the generalized arrival time deviation of the k-th autonomous bus at station j; is a binary variable. If bus stop j is the time control point of the kth autonomous bus, its value is 1, otherwise it is 0, as shown in the following formula 10; the negative utility of the running time deviation z w Calculated based on the following formula 18, where d k It is represented by the number of time control points of the k-th autonomous driving bus route, as shown in the following formula 11; k is the sum of the deviations between the planned operating time of each section of the k-th autonomous bus output by the model and the reference value of the planned operating time of each section expected by the enterprise. Formula 9: Formula 10: Formula 11: Formula 18: z w =Σ k∈K d k w k .

2. The method according to claim 1, characterized in that The method of generating a target operation plan based on the probability distribution function and the fixed time control point set by using a deterministic mixed integer linear programming model includes: introducing auxiliary variables to perform a linearization operation on the random mixed integer nonlinear programming model, thereby converting the random mixed integer nonlinear programming model into a random mixed integer linear programming model; Among them, the objective function value of the random mixed integer linear programming model is: calculated based on the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the arrival time deviation, the non-negative weight coefficient and auxiliary variables corresponding to the negative utility of the running time deviation, the set of autonomous driving bus schedules, and the set of autonomous driving bus pass stations.

3. The method according to claim 2, characterized in that The objective function value of the random mixed integer linear programming model is calculated based on the following formula: Where z is the objective function value; and is an auxiliary variable; α is a non-negative weight coefficient used to characterize the negative utility of reducing arrival time deviation z d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of autonomous driving bus schedules; K is the set of autonomous driving bus schedules, and K = {1, 2, …, k, …, |K|}; J is the set of autonomous driving bus stopovers, and J = {1, 2, …, j, …, |J|}.

4. The method according to claim 2, characterized in that The method of generating a target operation plan based on the probability distribution function and the fixed time control point set by using a deterministic mixed integer linear programming model includes: generating a plurality of sample observation values based on the probability distribution function, and calculating a sample mean of the plurality of sample observation values; The sample mean is used to replace the expected value of the random parameter in the random mixed integer linear programming model, and the random mixed integer linear programming model is converted into a deterministic mixed integer linear programming model.

5. The method according to claim 4, characterized in that The method of generating a target operation plan based on the probability distribution function and the fixed time control point set by using a deterministic mixed integer linear programming model includes: The deterministic mixed integer linear programming model is solved using the branch-and-bound method to obtain the optimal solution for the time control points of each autonomous bus trip and the planned arrival time corresponding to each time control point; The target operation plan is generated based on the optimal solution of the time control points of each shift of the autonomous driving bus and the planned arrival time corresponding to each time control point.

6. An automatic driving bus operation plan generation device based on variable time control points, characterized in that: The device comprises: an information acquisition module, configured to obtain, based on first operating information of a target bus route, a probability distribution function of bus travel time between stops on the target bus route by fitting, and to determine, based on second operating information of the target bus route, key stops on the target bus route, and to generate a set of fixed-time control points based on the key stops; A plan generation module is used to generate a target operation plan based on the probability distribution function and the fixed time control point set using a deterministic mixed integer linear programming model; The first operation information includes: the travel time of the bus between adjacent stops and the stop time at each stop; the second operation information includes: historical passenger flow data of the bus and bus route characteristics; the time control points are: stops on the target bus route used to constrain the arrival time of the bus; the target operation plan includes: the optimal solution of the time control points for each autonomous bus trip and the planned arrival time corresponding to each time control point; The method of generating a target operation plan based on the probability distribution function and the fixed time control point set by using a deterministic mixed integer linear programming model includes: Establish a random mixed-integer nonlinear programming model; The randomized mixed integer nonlinear programming model is used to constrain the location and number of time control points and the slack time of vehicle operation between adjacent stations, and to determine the optimal time control points for each autonomous bus shift and the planned arrival time corresponding to each time control point, so as to minimize the weighted sum of the negative utility of the autonomous bus's arrival time deviation and the negative utility of its operating time deviation. The objective function value of the random mixed integer nonlinear programming model is calculated based on the following formula: min z=α z d +τ·z w Where z is the objective function value; α is a non-negative weight coefficient, which is used to represent the negative utility z of reducing the arrival time deviation. d The importance of; τ is a non-negative weight coefficient used to characterize the negative utility z of reducing runtime deviation w The importance of z w The negative utility caused by the deviation between the planned operating time of the autonomous bus section output by the model and the planned operating time of the autonomous bus section expected by the enterprise, referred to as the operating time deviation negative utility; Disutility of arrival time deviation z d Based on the following formula 9, λ is the parameter that penalizes the volatility of the arrival time of the autonomous bus; is the generalized arrival time deviation of the k-th autonomous bus at station j; is a binary variable. If bus stop j is the time control point of the kth autonomous bus, its value is 1, otherwise it is 0, as shown in the following formula 10; the negative utility of the running time deviation z w Based on the following formula 18, d k It is represented by the number of time control points of the k-th autonomous driving bus route, as shown in the following formula 11; k is the sum of the deviations between the planned operating time of each section of the k-th autonomous driving bus output by the model and the reference value of the planned operating time of each section expected by the enterprise, Formula 9: Formula 10: Formula 11: Formula 18: .

7. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for generating an autonomous driving bus operation plan based on variable time control points as claimed in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method for generating an automatic driving bus operation plan based on variable time control points as described in any one of claims 1 to 5 are implemented.

Images