Method and system for matching a fixed-site based autonomous taxi with a passenger

Abstract

The application provides a fixed station-based automatic driving taxi and passenger matching method and system, belongs to the technical field of urban travel service operation and optimization management, and meets the feasible matching set according to the waiting time of passengers, the passenger pickup mileage of the automatic driving taxi and the constraint condition of the income; the preference sequence value matrix of the passengers and the preference sequence value matrix of the automatic driving taxi are defined according to the preference function and the preference ordering rule of the passengers and the automatic driving taxi; the matching mechanism and the corresponding constraint condition are determined by taking the social welfare maximization as the objective function, combining the supply information of the automatic driving taxi with the demand information of the passengers, and constructing a stable matching model; and the stable matching model is solved to obtain the matching result. The application can improve the operation management capability of the automatic driving travel service provider, improve the matching efficiency and stability, reduce the empty mileage, improve the travel service satisfaction of users, and provide technical support for the operation management of the automatic driving operation area.

Description

Technical Field

[0001] This invention relates to the field of urban mobility service operation and optimization management technology, specifically to a method and system for matching autonomous taxis and passengers based on fixed stations. Background Technology

[0002] With the development and deep integration of autonomous driving technology and shared mobility services, travel modes and service formats will undergo significant adjustments. Autonomous taxis, as a carrier and key link between shared mobility and autonomous driving technology, have become a hot topic in the new travel ecosystem. Because the development of autonomous taxis is still in its early stages, their operating models differ from traditional taxis and ride-hailing services. Mobility service operators such as Pony.ai, WeRide, and Baidu Apollo all adopt a fixed-stop pick-up and drop-off model, primarily based on convenience and controllability. Firstly, due to the need for further development of precise positioning technology, current travel services still face limitations due to discrepancies between the platform's location and the passenger's actual pick-up location. Given the driverless nature of autonomous vehicles, they lack the flexibility for direct communication with passengers; therefore, the service model involves passengers picking up and dropping off at fixed stops. Secondly, autonomous driving technology is still under development and cannot guarantee high safety in all extreme weather conditions and complex road environments. The establishment of fixed stops will make the parking of autonomous taxis more standardized, improving driving safety. In the early stages, the safety of vehicle operation has a greater impact on the public than on service quality. Therefore, it is of great significance to study the matching problem between autonomous taxis and passengers in fixed-station scenarios.

[0003] Current solutions for matching autonomous taxis do not consider the practical scenario of picking up passengers at fixed stops, and most are based on system-optimal allocation aimed at minimizing negative externalities or maximizing social welfare. However, passengers and vehicles are not necessarily obligated to accept the matching solutions offered by the platform. If passengers or vehicles believe they can choose a better match themselves, they may reject the platform's offer, which relates to the concept of stability in cooperative game theory. Two-way selection between passengers and autonomous taxis is crucial for the efficient development of autonomous driving mobility services, and a reasonable matching mechanism is beneficial for improving overall efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a stable matching method between autonomous taxis and passengers based on fixed stations, in order to solve at least one of the technical problems mentioned above.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] On one hand, the present invention provides a method for matching autonomous taxis with passengers based on fixed stations, including:

[0007] Receive current time and destination location information data sent by passengers with travel needs;

[0008] Receive the current location information data of autonomous taxis;

[0009] Based on the constraints of passenger waiting time, autonomous taxi pick-up mileage, and revenue, a feasible matching set is selected.

[0010] Based on the preference functions and preference ranking rules of passengers and autonomous taxis, the preference order matrix of passengers and the preference order matrix of autonomous taxis are defined respectively.

[0011] Using the maximization of social welfare as the objective function, and combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed.

[0012] The Gale-Shapley algorithm is used to solve the stable matching model to obtain the matching results.

[0013] Preferably, passenger demand information data includes: current location coordinates, fixed station location coordinates for disembarking, walking speed per unit time, cost per unit time, and maximum acceptable waiting time.

[0014] Preferably, the supply information data for autonomous taxis includes: current location coordinates, speed per unit time, cost per unit distance, cost per unit time, starting fare, and the distance covered by the starting fare.

[0015] Preferably, the matching mechanism includes: during matching, any passenger's request is assigned to at most one autonomous taxi; any autonomous taxi carries at most one passenger, without considering ride-sharing behavior; the stable matching scheme does not include hindering matching pairs, that is, neither the passenger nor the autonomous taxi has a better choice than the current matching object.

[0016] Preferably, the objective function is a social welfare value, which consists of two parts: the profit obtained by the successfully matched autonomous taxi providing travel services and the utility of the successfully matched passengers.

[0017] Preferably, evaluation metrics for establishing stable matching models are also included:

[0018] The passenger matching success rate is used as the first indicator, which is the ratio of the number of successfully matched passengers to the total number of requests.

[0019] The second indicator is the success rate of matching autonomous taxis, which is the ratio of the number of successfully matched autonomous taxis to the total supply.

[0020] The third indicator is the average waiting time of passengers, which is the ratio of the total waiting time of successfully matched passengers to the number of successfully matched passengers.

[0021] The fourth indicator is the average empty mileage of autonomous taxis, which is the ratio of the total empty mileage of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis.

[0022] The fifth indicator is the average revenue of autonomous taxis, which is the ratio of the total revenue of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis.

[0023] Secondly, the present invention provides an autonomous taxi and passenger matching system based on fixed stations, comprising:

[0024] The first receiving module is used to receive the current location and destination geographic information data sent by passengers with travel needs;

[0025] The second receiving template is used to receive the current location data of the autonomous taxi;

[0026] The filtering module is used to filter out feasible matching sets that meet the constraints of passenger waiting time, autonomous taxi pick-up mileage, and revenue based on passenger waiting time constraints, autonomous taxi pick-up mileage, and revenue constraints.

[0027] Define a model to define the preference order matrix for passengers and the preference order matrix for autonomous taxis, based on the preference functions and preference ranking rules of passengers and autonomous taxis, respectively.

[0028] The module constructs a matching mechanism and corresponding constraints based on the feasible matching set and the preference order matrix of passengers and autonomous taxis, and builds a stable matching model for the objective function.

[0029] The computation module is used to solve the stable matching model using the Gale-Shapley algorithm to obtain a stable matching scheme.

[0030] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the above-described method for matching autonomous taxis with passengers based on fixed stations.

[0031] Fourthly, the present invention provides an electronic device including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the above-described method for matching autonomous taxis with passengers based on fixed stations.

[0032] Fifthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for matching autonomous taxis with passengers based on fixed stations as described above.

[0033] Beneficial effects of this invention:

[0034] From an urban transportation perspective, autonomous taxis, as an emerging mobility service, combine autonomous driving technology with the sharing economy model, further driving disruptive changes in the form and value chain of mobility services and even the transportation system. In its early development, studying the matching problem of autonomous taxis under a fixed-station model provides a reference for subsequent station site selection, route planning, and operation management. From an economic perspective, it can effectively solve the operational management capabilities of autonomous mobility service providers during the trial operation phase, improve matching efficiency and reduce empty mileage, increase user satisfaction with mobility services, and provide technical support for the operation and management of autonomous driving in the operating area. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 The flowchart illustrates the design of a stable matching method between autonomous taxis and passengers based on fixed stations, as described in this embodiment of the invention.

[0037] Figure 2 This is a schematic diagram of the process for establishing a stable matching model according to an embodiment of the present invention.

[0038] Figure 3 This is a schematic diagram of the objective function established according to an embodiment of the present invention.

[0039] Figure 4 This is a schematic diagram of the matching mechanism established according to an embodiment of the present invention.

[0040] Figure 5 This is a schematic diagram of the Gale-Shapley algorithm established according to an embodiment of the present invention.

[0041] Figure 6 This is a schematic diagram of the evaluation index established according to an embodiment of the present invention.

[0042] Figure 7 This is a schematic diagram of the basic scenario described in an embodiment of the present invention.

[0043] Figure 8 This is a schematic diagram illustrating the impact of different vehicle unit mileage travel costs on the matching results according to an embodiment of the present invention.

[0044] Figure 9 This is a schematic diagram illustrating the relationship between the unit mileage travel cost of different vehicles and the average waiting time of passengers, as described in an embodiment of the present invention.

[0045] Figure 10 This is a schematic diagram illustrating the relationship between the unit driving cost of different vehicles and the average revenue of autonomous taxis, as described in an embodiment of the present invention.

[0046] Figure 11 This is a schematic diagram illustrating the impact of the maximum acceptable waiting time for passengers on the matching results, as described in an embodiment of the present invention.

[0047] Figure 12 This is a schematic diagram illustrating the relationship between the maximum acceptable waiting time for passengers and the average waiting time for passengers, as described in an embodiment of the present invention.

[0048] Figure 13 This is a schematic diagram illustrating the relationship between the maximum acceptable waiting time for passengers and the average revenue of autonomous taxis, as described in an embodiment of the present invention.

[0049] Figure 14 This is a schematic diagram illustrating the impact of the maximum acceptable mileage of an autonomous taxi as described in an embodiment of the present invention on the matching results.

[0050] Figure 15 This is a schematic diagram illustrating the relationship between the maximum acceptable mileage of an autonomous taxi and the average waiting time for passengers, as described in an embodiment of the present invention.

[0051] Figure 16 This is a schematic diagram illustrating the relationship between the maximum acceptable mileage of an autonomous taxi and the average revenue of an autonomous taxi according to an embodiment of the present invention.

[0052] Figure 17 This is a schematic diagram illustrating the impact of the number of commercial center sites on the matching results according to an embodiment of the present invention.

[0053] Figure 18 This is a schematic diagram illustrating the relationship between the number of commercial center stations and the average passenger waiting time in an embodiment of the present invention.

[0054] Figure 19This is a schematic diagram illustrating the relationship between the number of commercial center stations and the average revenue of autonomous taxis, as described in an embodiment of the present invention. Detailed Implementation

[0055] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0056] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0057] It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as here.

[0058] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0059] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0060] To facilitate understanding of the present invention, the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. However, the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0061] Those skilled in the art should understand that the accompanying drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0062] Example 1

[0063] This embodiment 1 provides a stable matching system for autonomous taxis and passengers based on fixed stations. By considering the impact of factors such as passenger waiting time and travel utility, autonomous taxi pick-up mileage and revenue, a matching model is established according to the preference ranking rules of passengers and autonomous taxis, thus achieving stable matching between passengers and autonomous taxis.

[0064] Specifically, the fixed-site-based autonomous taxi matching system described in Embodiment 1 includes: a first receiving module for receiving current location and destination geographic information data sent by passengers with travel needs; a second receiving module for receiving the current geographic location data of autonomous taxis; a filtering module for filtering feasible matching sets that meet the constraints of passenger waiting time, autonomous taxi pick-up mileage, and revenue based on passenger waiting time constraints, autonomous taxi pick-up mileage, and revenue constraints, thereby simplifying the matching process; a model definition module for defining the passenger preference order matrix and the autonomous taxi preference order matrix based on the passenger and autonomous taxi preference functions and preference ranking rules, respectively; a construction module for determining the matching mechanism and corresponding constraints based on the feasible matching set and the passenger and autonomous taxi preference order matrices, and constructing a stable matching model with the objective function; and a calculation module for solving the stable matching model using the Gale-Shapley algorithm to obtain a stable matching scheme.

[0065] In this embodiment 1, the above-described system can be used to implement a method for matching autonomous taxis with passengers based on fixed stations, including:

[0066] Step 1: The first receiving module receives the passenger's current location and destination geographic information data.

[0067] Passengers upload their travel information to the ride-hailing service platform, including their current location. Drop-off point location information Travel service platforms calculate station locations (x k ,y k Distance between the current location and the passenger's current location and the distance between drop-off points Calculate passenger P i Walking time to the nearest boarding station Passenger P i Walking time between the nearest drop-off point and the destination

[0068] Step 2: The second receiving module receives the current location data of the autonomous taxi.

[0069] Autonomous taxis submit their current location information (x) to the ride-hailing service platform. j ,y j Based on the known cost information of autonomous taxis in the system, including the driving cost γ per unit mile, the time value cost δ of waiting at fixed stops, the starting fare Γ, the cost per kilometer beyond the starting fare λ, and the mileage l covered by the starting fare, the cost of the autonomous taxi T is further calculated. j To passenger P i The nearest boarding station is S. k distance d jk and the revenue generated from matching autonomous taxis with passengers. ij :

[0070] e ij =f ij -γ(d jk +s i )-δ·max{0,t ik -t jk}; where s i For passenger P i The travel distance is the mileage from the boarding point to the alighting point.

[0071] Step 3: The filtering module refines the set of feasible matches that meet the constraints of passengers and autonomous taxis.

[0072] To simplify the matching problem, feasible matching sets are selected from all matching sets based on constraints for autonomous taxis and passengers.

[0073] The first constraint is the passenger time constraint, where passenger P... i With autonomous taxi T j Matching must satisfy T j Driving to passenger P i The nearest station S k Time t jk No more than the time it takes for passengers to walk to the nearest boarding point Right now

[0074] The second constraint is the passenger pick-up mileage constraint for autonomous taxis, where T is the autonomous taxi's mileage. j It is with passenger P i Matching requires satisfying T j Drive to P i The nearest station S k The distance cannot exceed the maximum passenger pick-up distance of the autonomous taxi, that is...

[0075] The third constraint is the revenue constraint for autonomous taxis, where T is the autonomous taxi revenue. j It is with passenger P i Matching requires that the revenue of autonomous taxis be non-negative, i.e., f ij -γ·(d jk +s i )-δ·max{0,t ik -t jk}≥0.

[0076] Step 4: The sorting module defines the preference order matrix based on the passenger and autonomous driving preference functions and sorting principles.

[0077] First, define the preference function for the matching subject, and the passenger's preference function defines the waiting time:

[0078]

[0079] Where μ(·) is the matching function, μ(P) i ) = T j Passenger P i With autonomous taxi T j Matching, μ(P) i ) = P i Passenger P i There is no match that meets the feasible constraints, and M is a very large positive number.

[0080] The preference function for autonomous taxis is defined as the revenue gained from providing a ride service. The revenue function consists of the fare paid by the passenger, the driving cost, and the waiting time cost.

[0081]

[0082] Where μ(·) is the matching function, μ(T) j ) = P i Indicates autonomous taxi T j With passenger P i Matching, μ(T) j ) = T j Indicates autonomous taxi T j No matching matches that meet the constraints.

[0083] The preference ranking rules for both parties are as follows: Passengers tend to choose autonomous taxis that minimize waiting time. Autonomous taxis tend to choose passengers who maximize their benefit function value.

[0084] Therefore, the passenger preference order matrix is ​​S = [S1, S2, ..., S...]. m The preference order matrix for autonomous taxis is R = [R1, R2, ..., R].i ,...,R n ], R i =(r i1 ,r i2 ,...,r in ) T For taxi T j For passenger P i The preference order vector, r ij Indicates autonomous taxi T j Passenger P i Placed at the rth ij Position. Let S j =(s1,s2,...,s mj ) T For passenger P i For autonomous taxis T j The preference order matrix, s ij Passenger P i autonomous taxi T j In the s ij Bit.

[0085] Step 5: Based on the preference ranking principles of passengers and autonomous taxis, the module determines the matching mechanism and corresponding constraints, and constructs a stable matching model with social welfare as the objective function.

[0086] Step 6: The calculation module uses the Gale-Shapley algorithm to solve the stable matching model, obtains the stable matching results, and informs the passengers and the autonomous taxi.

[0087] The matching mechanism includes the following: during matching, any passenger's request is assigned to at most one autonomous taxi; any autonomous taxi carries at most one passenger; and the stable matching scheme does not include hindering matching pairs, i.e., neither the passenger nor the autonomous taxi has a better choice than the current match.

[0088] The objective function is to maximize social welfare. By combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed.

[0089] In this embodiment 1, the method described above also includes an evaluation index for establishing a stable matching model:

[0090] The passenger matching success rate is used as the first indicator, which is the ratio of the number of successfully matched passengers to the total number of requests.

[0091] The second indicator is the success rate of matching autonomous taxis, which is the ratio of the number of successfully matched autonomous taxis to the total supply.

[0092] The third indicator is the average waiting time of passengers, which is the ratio of the total waiting time of successfully matched passengers to the number of successfully matched passengers.

[0093] The fourth indicator is the average empty mileage of autonomous taxis, which is the ratio of the total empty mileage of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis.

[0094] The fifth indicator is the average revenue of autonomous taxis, which is the ratio of the total revenue of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis.

[0095] Example 2

[0096] like Figure 1 As shown in this embodiment 2, a stable matching method for autonomous taxis and passengers based on fixed stations is provided, including the following steps:

[0097] Step 100: Passengers send matching request information to the platform: Passengers with travel needs can upload their information to the sharing platform through a mobile internet APP, including the passenger's current location, the passenger's destination location, the passenger's maximum waiting time, the passenger's walking speed, and the passenger's time value cost in the vehicle. The platform can calculate the distance between the passenger and each fixed station based on the passenger information, and from this, obtain the mileage and walking time of the passenger to the nearest boarding station.

[0098] Step 101: Autonomous taxis send matching supply information to the platform. Within the operating area, all autonomous taxis are mobile internet-enabled and shareable. Autonomous taxis can upload supply information to the sharing platform via a mobile app, including the vehicle's current location, maximum pick-up distance, vehicle speed, cost per unit mileage, waiting time cost at fixed stops, starting fare, mileage covered by the starting fare, and per-kilometer cost beyond the starting fare. Based on the information provided by the autonomous taxis, the platform determines the distance and travel time of each autonomous taxi to various fixed stops.

[0099] Step 103: Select feasible matching sets based on constraints. The first constraint is that the time taken for the autonomous taxi to reach the nearest station to the passenger does not exceed the passenger's walking and waiting time to reach that station; the second constraint is that the distance traveled by the autonomous taxi to the nearest station to the passenger cannot exceed the maximum pick-up distance of the autonomous taxi; the third constraint is that the revenue from matching the autonomous taxi with the passenger is non-negative. Based on these three constraints, feasible matching sets are selected from all matching sets.

[0100] Step 104: Rank the passengers and autonomous taxis in the feasible matching set according to the preference ranking principle. The passenger's preference function is defined as the utility of the travel service, consisting of perceived utility, in-vehicle utility, travel cost, and waiting time cost. The passenger preference ranking principle prioritizes autonomous taxis that maximize their travel utility. The autonomous taxi's preference function is defined as the utilization of the vehicle for the travel service, consisting of fare, vehicle waiting time cost, and driving cost. The autonomous taxi's preference ranking principle prioritizes passengers who maximize their profit.

[0101] Step 105: Establish a stable matching model. Using social welfare as the objective function, establish a 0-1 integer programming model and determine the corresponding constraints based on the matching requirements. Social welfare consists of the profit obtained by the successfully matched autonomous taxis providing travel services and the utility of the successfully matched passengers.

[0102] Step 106: The model outputs the matching results and informs the passenger: The Gale-Shapley algorithm is used to solve the problem, and the final matching results and the model's evaluation index values ​​are output, including whether each request is accepted. If accepted, the matching passenger is also returned. The platform returns this information to the passenger.

[0103] Step 107, establish evaluation indicators for the model: Select appropriate evaluation indicators for the matching model based on the actual situation, including passenger matching success rate, autonomous taxi matching success rate, average passenger waiting time, average empty mileage of autonomous taxis, and average revenue of autonomous taxis.

[0104] like Figure 2 As shown, the stable matching model established in this embodiment includes:

[0105] Step 200: Determine the composition of the social welfare function and establish an objective function with the goal of maximizing social welfare;

[0106] Step 201: Based on the matching scenario of autonomous taxis at fixed stations, a matching mechanism for the model is proposed;

[0107] Step 202: Determine the corresponding constraints based on the matching constraints.

[0108] like Figure 3 As shown, the objective function established in this embodiment includes:

[0109] Step 300: Determine that the social welfare consists of two parts: the benefits obtained from providing travel services to successfully matched autonomous taxis and the utility of successfully matched passengers.

[0110] Step 301: Construct the expressions for the two parts separately. The profit obtained by a successfully matched autonomous taxi in providing travel services is... Revenue from autonomous taxis ij =f ij -γ·(d jk +s i )-δ·max{0,t ik -t jk},k=argmin(d ik ), where f ij For passenger P i Take an autonomous taxi T j The fare for the travel service payment, γ·(d jk +s i (T) is an autonomous taxi. j The driving cost, δ·max{0,t ik -t jk} is an autonomous taxi T j The waiting time cost. The utility of a successfully matched passenger is... Passenger utility Among them, I i For passenger P i Perceived utility For passenger P i The distance from the current location to the nearest boarding station, α·s i For passenger in-vehicle utility, f ij For passenger P i Take an autonomous taxi T j The fare paid for the travel service. Passenger P i The cost of walking.

[0111] like Figure 4 As shown, the matching mechanism established in this embodiment includes:

[0112] Step 400: During matching, any passenger's travel request will be assigned to at most one autonomous taxi. The constraint expression determined according to this matching principle is as follows:

[0113] Step 401: During matching, any passenger's travel request will be assigned to at most one autonomous taxi, according to the constraint expression determined by this matching principle.

[0114] Step 402 ensures the stability of the bilateral matching constraint, guaranteeing that there are no pairs hindering stability in the obtained stable matching scheme. The constraint expression determined according to this matching principle is as follows:

[0115] like Figure 5 As shown, the process of solving the stable matching model using the Gale-Shapley algorithm in this embodiment is as follows:

[0116] In step 500, initially, both passengers and autonomous taxis in the feasible matching set are in an unmatched state.

[0117] Step 501: If there are still unmatched passengers in the travel service matching system and their preference list has not been traversed, proceed to step 3; otherwise, the algorithm terminates.

[0118] Step 502, any unmatched passenger P i Based on its preference list, the autonomous taxi T with the smallest ordinal value is selected. j Send a matching request.

[0119] Step 503, if the autonomous taxi T j If no match is found, then passenger P i With autonomous taxi T j Match successful; if autonomous taxi T j Passenger P has been contacted. h Match, if in T j In the preference list, r ij <r hj That is, passenger P i Compared to passenger P h If passenger P is listed earlier in the order, then... i With autonomous taxi T j Match successful, passenger P h Become an unmatched state, otherwise passenger P i It remains unmatched.

[0120] Step 504: Repeat steps 503 and 504 until the algorithm terminates. At this point, the obtained matching scheme is the final stable matching scheme.

[0121] like Figure 6 As shown, the evaluation indicators established in this embodiment include:

[0122] Step 600: Consider passenger matching success rate (PS) as the first indicator for evaluating platform operations. Where the numerator is the sum of the number of successfully matched passengers, x ij Let N be a 0-1 decision variable, and N be the total number of passengers in demand.

[0123] Step 601: Consider the autonomous taxi matching success rate (TS) as the second indicator for platform operation evaluation. Where the numerator is the sum of the number of successfully matched autonomous taxis, x ij Let M be the total number of autonomous taxis, and M be the decision variable between 0 and 1.

[0124] Step 602, consider the average passenger wait time PW as the third indicator for platform operation evaluation. The numerator represents the total waiting time of successfully matched passengers, and the denominator represents the total number of successfully matched passengers.

[0125] Step 603, considering the average empty mileage TD of autonomous taxis as the fourth indicator value, The numerator represents the total empty mileage of the successfully matched autonomous taxis, and the denominator represents the total number of successfully matched autonomous taxis.

[0126] Step 604, using the average revenue TE of autonomous taxis as the fifth indicator, The numerator represents the total revenue earned by each successfully matched autonomous taxi, and the denominator represents the total number of successfully matched autonomous taxis, where x ij For 0-1 decision variables,

[0127] e ij Revenue generated from matching passengers with autonomous taxis.

[0128] Example 3

[0129] In this embodiment 3, a numerical experiment is used as an example to further illustrate the stable matching method of autonomous taxis and passengers based on fixed stations:

[0130] Assuming the autonomous driving ride-hailing service operates in a commercial area, such as Figure 7 As shown in the diagram, each grid cell is 500m wide and 500m long, with a total operating area of ​​19250m × 11250m. The basic scenario includes 20 stations randomly distributed, with 4 stations located in the commercial center. The passenger capacity is 300, distributed across a multivariate Gaussian distribution around each station, with 15 passengers surrounding each station. There are 240 autonomous vehicles: 120 autonomous taxis distributed across the commercial center stations (30 vehicles surrounding each commercial station), and the remaining 120 autonomous taxis randomly distributed. The supply-demand ratio in the basic scenario is 0.8.

[0131] Assuming the passenger's walking speed (m / s), the speed of the autonomous taxi is v = 8 (m / s), and the maximum acceptable waiting time for passengers is T. max =5 (minutes), the maximum acceptable passenger mileage S for autonomous taxis max= 4 (km), the driving cost γ required for autonomous taxi to travel a unit mileage is 0.8 (yuan / km), the time value cost of autonomous taxi waiting at fixed stations is δ = 72 (yuan / hour), the starting price of autonomous taxi is Γ = 15 (yuan), the mileage covered by the starting price of autonomous taxi is l = 3 (km), and the cost per kilometer of autonomous taxi beyond the starting price is λ = 4 (yuan / km).

[0132] To investigate the impact of different vehicle unit mileage costs on various evaluation indicators, fuel-powered ride-hailing vehicles, electric ride-hailing vehicles, and autonomous taxis were selected for comparison. According to the research report, the unit mileage cost for traditional fuel-powered ride-hailing vehicles is 1.93 yuan, while the unit mileage cost for traditional electric ride-hailing vehicles is 1.43 yuan. The impact of different vehicle unit mileage costs on the matching results is as follows: Figure 8-10 As shown in the figure, the study reveals that compared to traditional gasoline-powered taxis and electric taxis, the use of autonomous taxis improves both passenger and vehicle matching success rates. The impact on passenger waiting time is not significant. In terms of average vehicle revenue, autonomous taxis also have a clear advantage over the other two types of vehicles, firstly due to the higher vehicle matching rate, and secondly due to the lower cost per unit mileage, resulting in higher revenue.

[0133] To assess the impact of maximum passenger waiting time on various evaluation indicators, maximum passenger waiting times were set to 0 min, 1 min, 3 min, 5 min, 8 min, and 10 min. The impact of different maximum passenger waiting times on the matching results is shown below. Figure 11-13 As shown in the example analysis, it can be observed that as the maximum passenger waiting time increases, the matching success rate between passengers and autonomous taxis gradually increases and then plateaus. Regarding the average passenger waiting time, before the maximum waiting time reaches 8 minutes, the average waiting time gradually increases, then stabilizes after 8 minutes. However, as the maximum passenger waiting time increases, the average empty mileage of autonomous vehicles continuously increases, while the average vehicle revenue changes relatively little. This indicates that setting a reasonable maximum passenger waiting time is crucial for the operation and management of autonomous driving services. A moderate increase in waiting time will improve the successful matching rate, but an excessive increase will not only affect the quality of passenger travel services but also increase the empty mileage of vehicles, significantly reducing social welfare.

[0134] To investigate the impact of the maximum acceptable passenger pick-up mileage for autonomous taxis on various evaluation indicators, the maximum passenger pick-up mileage directly affects the number of passengers that an autonomous taxi can match. When the maximum passenger pick-up mileage is set too low, the vehicle can only choose the nearest stop or a stop more than the acceptable mileage. The maximum acceptable passenger pick-up mileage for autonomous taxis was set to 1km, 2km, 4km, 6km, 8km, and 10km. The impact of different maximum acceptable passenger pick-up mileages on the matching results is as follows: Figure 14-16 As shown in the example analysis, increasing the maximum passenger pick-up mileage for autonomous taxis can improve the matching success rate, but a continuous increase will lead to an increase in the vehicle's empty mileage and a decrease in average revenue. A reasonable mileage value should be set to ensure the maximization of overall benefits.

[0135] To investigate the impact of the number of business center stations on various evaluation indicators, the number of business center stations was set to 0, 1, 2, 3, 4, 5, 6, 7, and 8. As the number of business center stations increases, the vehicle distribution changes; the number of vehicles following a random distribution gradually decreases, while the number following a multivariate Gaussian distribution increases. The impact of different numbers of business center stations on the matching results is as follows: Figure 17-19 As shown in the example analysis, the increase in the number of commercial stations reduces both the passenger and autonomous driving matching success rates. While this lowers the average passenger waiting time and vehicle revenue, it increases the average empty mileage of vehicles. Therefore, the land use nature of the operating area has a certain impact on the matching results, and selecting appropriate station locations and attributes will be a key issue in the operation and management of autonomous driving mobility.

[0136] Example 4

[0137] Embodiment 4 of the present invention provides an electronic device, including a memory and a processor, wherein the processor and the memory communicate with each other, and the memory stores program instructions that can be executed by the processor. The processor calls the program instructions to execute a method for stable matching of autonomous taxis and passengers based on fixed stations. The method includes the following steps:

[0138] Receive current time and destination location information data sent by passengers with travel needs;

[0139] Receive the current location information data of autonomous taxis;

[0140] Based on constraints such as passenger waiting time, autonomous taxi pick-up mileage, and revenue, a feasible matching set is selected.

[0141] Based on the preference functions and preference ranking rules of passengers and autonomous taxis, the preference order matrix of passengers and the preference order matrix of autonomous taxis are defined respectively.

[0142] Using the maximization of social welfare as the objective function, and combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed.

[0143] The Gale-Shapley algorithm is used to solve the stable matching model to obtain the matching results.

[0144] Example 5

[0145] Embodiment 5 of the present invention provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements a method for stable matching of autonomous taxis and passengers based on fixed stations. The method includes the following steps:

[0146] Receive current time and destination location information data sent by passengers with travel needs;

[0147] Receive the current location information data of autonomous taxis;

[0148] Based on constraints such as passenger waiting time, autonomous taxi pick-up mileage, and revenue, a feasible matching set is selected.

[0149] Based on the preference functions and preference ranking rules of passengers and autonomous taxis, the preference order matrix of passengers and the preference order matrix of autonomous taxis are defined respectively.

[0150] Using the maximization of social welfare as the objective function, and combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed.

[0151] The Gale-Shapley algorithm is used to solve the stable matching model to obtain the matching results.

[0152] Example 6

[0153] Embodiment 6 of the present invention provides a computer device, including a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute a method for stable matching of autonomous taxis and passengers based on fixed stations, the method including the following steps:

[0154] Receive current time and destination location information data sent by passengers with travel needs;

[0155] Receive the current location information data of autonomous taxis;

[0156] Based on constraints such as passenger waiting time, autonomous taxi pick-up mileage, and revenue, a feasible matching set is selected.

[0157] Based on the preference functions and preference ranking rules of passengers and autonomous taxis, the preference order matrix of passengers and the preference order matrix of autonomous taxis are defined respectively.

[0158] Using the maximization of social welfare as the objective function, and combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed.

[0159] The Gale-Shapley algorithm is used to solve the stable matching model to obtain the matching results.

[0160] In summary, the stable matching method and system for autonomous taxis and passengers based on fixed stops described in this invention, tailored to the operational characteristics of autonomous taxis picking up passengers at fixed stops during the trial operation phase, fully considers the goals of both passengers and autonomous taxis, as well as constraints such as passenger waiting time, autonomous taxi pick-up mileage, and revenue. Based on the preference ranking principles of passengers and autonomous taxis, a stable matching model is constructed, and the Gale-Shapley algorithm is applied to ensure a stable matching solution between passengers and autonomous taxis under this system. This prevents passengers from increasing their utility or revenue by changing their current choices, thus contributing to the platform's effective matching and stable operation. This invention can effectively address the operational management capabilities of autonomous driving mobility service providers during the trial operation phase, improve matching efficiency and stability, reduce empty mileage, increase user satisfaction with travel services, and provide technical support for the operational management of autonomous driving in operating areas.

[0161] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0162] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0163] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0164] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0165] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or variations that can be made by those skilled in the art without creative effort should be included within the scope of protection of the present invention.

Claims

1. A method for matching autonomous taxis with passengers based on fixed stations, characterized in that, include: Receive current time and destination location information data sent by passengers with travel needs; Receive the current location information data of autonomous taxis; Based on constraints such as passenger waiting time, autonomous taxi pick-up mileage, and revenue, a feasible matching set is selected. Based on the preference functions and preference ranking rules of passengers and autonomous taxis, the preference order matrix of passengers and the preference order matrix of autonomous taxis are defined respectively. The preference function of passengers is defined as the utility of using the travel service, which consists of perceived utility, in-vehicle utility, travel cost and waiting time cost. The preference function of autonomous taxis is defined as the utilization of the vehicle for travel services, which consists of fare, vehicle waiting time cost and driving cost. Using the maximization of social welfare as the objective function, and combining the supply information and passenger demand information of autonomous taxis, a matching mechanism and corresponding constraints are determined, and a stable matching model is constructed. Passenger demand information data includes: current location coordinates, fixed stop location coordinates for disembarkation, walking speed per unit time, cost per unit time, and maximum acceptable waiting time; autonomous taxi supply information data includes: current location coordinates, driving speed per unit time, cost per unit mileage, cost per unit time, starting fare, and the mileage covered by the starting fare; the objective function consists of two parts: the profit obtained by the successfully matched autonomous taxi providing travel services and the utility of the successfully matched passenger; The Gale-Shapley algorithm is used to solve the stable matching model to obtain the matching results.

2. The fixed-site based method for matching autonomous taxis with passengers according to claim 1, wherein, The matching mechanism includes: During matching, any passenger's request is assigned to at most one autonomous taxi; any autonomous taxi carries at most one passenger, regardless of ride-sharing behavior; the stable matching scheme does not include hindering matching pairs, i.e., neither the passenger nor the autonomous taxi has a better option than the current match. 3.The fixed-site based autonomous taxi and passenger matching method of claim 1, wherein, It also includes evaluation metrics for establishing stable matching models: The passenger matching success rate is used as the first indicator, which is the ratio of the number of successfully matched passengers to the total number of requests. The second indicator is the success rate of matching autonomous taxis, which is the ratio of the number of successfully matched autonomous taxis to the total supply. The third indicator is the average waiting time of passengers, which is the ratio of the total waiting time of successfully matched passengers to the number of successfully matched passengers. The fourth indicator is the average empty mileage of autonomous taxis, which is the ratio of the total empty mileage of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis. The fifth indicator is the average revenue of autonomous taxis, which is the ratio of the total revenue of successfully matched autonomous taxis to the total number of successfully matched autonomous taxis.

4. A fixed site based autonomous taxi and passenger matching system, characterized in that, Based on the method for matching autonomous taxis with passengers at fixed stations as described in any one of claims 1-3, the system includes: The first receiving module is used to receive the current location and destination geographic information data sent by passengers with travel needs; The second receiving module is configured to receive the geographic position data of the autonomous taxi at the current time; The screening module is configured to screen a feasible matching set meeting the waiting time of the passenger, the pickup mileage of the autonomous taxi and the revenue constraint of the autonomous taxi according to the waiting time constraint of the passenger, the pickup mileage of the autonomous taxi and the revenue constraint, so as to simplify the matching process; The definition model is configured to define a preference order value matrix of the passenger and a preference order value matrix of the autonomous taxi according to the preference function and the preference order rule of the passenger and the autonomous taxi, respectively; The construction module is configured to determine a matching mechanism and corresponding constraint conditions according to the feasible matching set and the preference order value matrix of the passenger and the autonomous taxi, and to construct a stable matching model with the maximization of social welfare as an objective function; The calculation module is configured to use the Gale-Shapley algorithm to solve the stable matching model and obtain a stable matching scheme.

5. A computer device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, and the processor invoking the program instructions to perform the method for matching autonomous taxis with passengers based on fixed stations according to any one of claims 1-3.

6. An electronic device, comprising: A computer device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, and the processor invoking the program instructions to perform the method for matching autonomous taxis with passengers based on fixed stations according to any one of claims 1-3.

7. A computer readable storage medium characterized in that, A computer device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, and the processor invoking the program instructions to perform the method for matching autonomous taxis with passengers based on fixed stations according to any one of claims 1-3.

Images