Unmanned vehicle cluster cooperative scheduling method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of unmanned vehicles, and provides an unmanned vehicle cluster cooperative scheduling method and device, electronic equipment and a storage medium. The method processes the unmanned vehicle as a special vehicle, determines a vehicle conversion coefficient of the unmanned vehicle based on a driving restriction condition of the unmanned vehicle, further calculates a first equivalent traffic volume of the unmanned vehicle, simultaneously calculates a second equivalent traffic volume of other vehicles in a road, further determines a road service level based on the calculated equivalent traffic volumes, determines whether a target unmanned vehicle triggers an abnormal event of the road within a target time slice based on the road service level, and if yes, executes a scheduling strategy on an associated unmanned vehicle cluster until the abnormal event is terminated. The method provides an unmanned vehicle cluster cooperative scheduling scheme based on a road resource occupation condition, and can prevent deterioration of road traffic capacity and a service level caused by unreasonable use of road resources by the unmanned vehicle.

Description

Technical Field

[0001] This application relates to the field of unmanned vehicle technology, and in particular to a method, device, electronic device and storage medium for collaborative scheduling of unmanned vehicle clusters. Background Technology

[0002] With the development of artificial intelligence technology, autonomous driving technology is becoming increasingly mature, and driverless vehicles are becoming more and more common users of public road resources. However, existing methods for calculating road capacity and level of service are based on ordinary vehicles and are not applicable to fleets of driverless vehicles.

[0003] Traffic behavior in autonomous vehicle swarms differs significantly from that of human-driven vehicles. In most cases, human-driven vehicles lack coordination, and their traffic behavior is considered independent. However, in autonomous vehicle swarms, the traffic behavior of a single autonomous vehicle is not independent but rather part of a swarm intelligence built upon the cooperation of Cooperative Automated Vehicles (CAVs). On the one hand, CAVs represent an important way to utilize road traffic resources more efficiently and at a lower cost; on the other hand, CAVs can also lead to the inefficient use of road resources, such as multiple autonomous vehicles simultaneously using the same road, potentially degrading the level of service. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, electronic device and storage medium for collaborative scheduling of unmanned vehicle clusters, in order to solve the problem that the prior art has not proposed a system scheduling for the entire unmanned vehicle cluster to avoid the unreasonable occupation of road resources by the unmanned vehicle cluster.

[0005] A first aspect of this application provides a method for collaborative scheduling of unmanned vehicle clusters, including:

[0006] Obtain the traffic volume of the road where the target autonomous vehicle is located within the target time slice;

[0007] Obtain the driving restrictions of the autonomous vehicle, and determine the first vehicle conversion factor based on the driving restrictions. The first vehicle conversion factor is the vehicle conversion factor of the autonomous vehicle.

[0008] The first equivalent traffic volume of the road within the target time slice is calculated based on the first vehicle conversion factor.

[0009] Calculate the second equivalent traffic volume of the road in the target time slice. The second equivalent traffic volume is the equivalent traffic volume of the road for vehicles other than driverless vehicles in the target time slice.

[0010] A first road service level is determined based on the first equivalent traffic volume, and a second road service level is determined based on the first equivalent traffic volume and the second equivalent traffic volume.

[0011] In response to an abnormal event being triggered on the road within the target time slice, based on a first road service level or a first road service level and a second road service level, the associated unmanned vehicle cluster of the road is obtained;

[0012] The scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates.

[0013] A second aspect of this application provides an unmanned vehicle cluster collaborative scheduling device, comprising:

[0014] The acquisition module is configured to acquire the traffic volume of the road where the target unmanned vehicle is located within a target time slice.

[0015] The acquisition template is also configured to acquire the driving restriction conditions of the unmanned vehicle, and determine a first vehicle conversion factor based on the driving restriction conditions. The first vehicle conversion factor is the vehicle conversion factor of the unmanned vehicle.

[0016] The calculation module is configured to calculate the first equivalent traffic volume of the road in the target time slice based on the first vehicle conversion factor;

[0017] The calculation module is also configured to calculate the second equivalent traffic volume of the road in the target time slice, wherein the second equivalent traffic volume is the equivalent traffic volume of the road for vehicles other than driverless vehicles in the target time slice;

[0018] The determination module is configured to determine a first road service level based on the first equivalent traffic volume, and to determine a second road service level based on the first equivalent traffic volume and a second equivalent traffic volume.

[0019] The acquisition template is also configured to acquire the associated unmanned vehicle cluster of the road in response to an abnormal event being triggered on the road within the target time slice, based on a first road service level, or a first road service level and a second road service level.

[0020] The scheduling module is configured to execute a scheduling strategy on the associated unmanned vehicle cluster until the abnormal event terminates.

[0021] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0023] The beneficial effects of this application embodiment compared with the prior art are as follows: This application embodiment treats unmanned vehicles as special vehicles, determines the vehicle conversion coefficient of the unmanned vehicle based on its driving restrictions, and then calculates the first equivalent traffic volume of the unmanned vehicle. At the same time, it calculates the second equivalent traffic volume of other vehicles on the road, and further determines the road service level based on the calculated equivalent traffic volume. Based on the road service level, it determines whether the target unmanned vehicle has triggered an abnormal event on the road within the target time slice. If so, a scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates. That is, this application embodiment provides an unmanned vehicle cluster collaborative scheduling scheme based on road resource occupancy. This scheme can prevent the deterioration of road capacity and service level caused by the unreasonable use of road resources by unmanned vehicles by performing real-time quantitative calculation of the road service level when unmanned vehicles use road resources, and use this as a basis for real-time control and scheduling of associated unmanned vehicle clusters. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram illustrating an application scenario of this application.

[0026] Figure 2 This is a flowchart illustrating a collaborative scheduling method for unmanned vehicle clusters provided in an embodiment of this application.

[0027] Figure 3(A) is a schematic diagram of a method for obtaining traffic volume provided in an embodiment of this application.

[0028] Figure 3(B) is a schematic diagram of another method for obtaining traffic volume provided in an embodiment of this application.

[0029] Figure 4 This is a flowchart illustrating the method for calculating the first equivalent traffic volume provided in an embodiment of this application.

[0030] Figure 5 This is a flowchart illustrating the method for calculating the second equivalent traffic volume provided in an embodiment of this application.

[0031] Figure 6This is a flowchart illustrating the method for determining a first road service level provided in an embodiment of this application.

[0032] Figure 7 This is a flowchart illustrating the method for determining a second road service level provided in an embodiment of this application.

[0033] Figure 8 This is a flowchart illustrating another unmanned vehicle cluster collaborative scheduling method provided in the embodiments of this application.

[0034] Figure 9 This is a schematic diagram of an unmanned vehicle cluster collaborative scheduling device provided in an embodiment of this application.

[0035] Figure 10 This is a schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0036] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0037] The following will describe in detail, with reference to the accompanying drawings, a method and apparatus for collaborative scheduling of unmanned vehicle clusters according to embodiments of this application.

[0038] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application. The application scenario may include unmanned vehicles 1, 2, and 3, server 4, and network 5.

[0039] Unmanned vehicles 1, 2, and 3 can be various types of unmanned vehicles, including unmanned delivery vehicles, unmanned logistics vehicles, and unmanned vending vehicles. Server 4 can be a server that provides various services, such as a backend server that receives requests sent by unmanned vehicles with which it has established communication connections. This backend server can receive and analyze the requests sent by the unmanned vehicles and generate processing results. Server 4 can be a single server, a server cluster consisting of several servers, or a cloud computing service center; this embodiment of the application does not impose any limitations on this.

[0040] It should be noted that server 4 can be either hardware or software. When server 4 is hardware, it can be various electronic devices that provide various services to unmanned vehicles 1, 2, and 3. When server 4 is software, it can be multiple software programs or software modules that provide various services to unmanned vehicles 1, 2, and 3, or it can be a single software program or software module that provides various services to unmanned vehicles 1, 2, and 3. This application embodiment does not impose any limitations on this.

[0041] Network 5 can be a wired network using coaxial cable, twisted pair, and fiber optic connection, or it can be a wireless network that enables interconnection of various communication devices without wiring, such as Bluetooth, Near Field Communication (NFC), and Infrared. This application embodiment does not limit this.

[0042] Users can establish communication connections with server 4 via network 5 through driverless vehicles 1, 2, and 3 to receive or send information. Specifically, server 4 can issue autonomous driving tasks or remote control tasks to driverless vehicles 1, 2, and 3, enabling them to perform the corresponding driving tasks. Simultaneously, the driverless vehicles can also collect their own vehicle data, operational data, and environmental data through their sensors or other information collection devices, and upload this data to server 4, allowing the server to determine the driver's driving mode based on this data.

[0043] It should be noted that the specific types, quantities, and combinations of unmanned vehicles 1, 2, and 3, server 4, and network 5 can be adjusted according to the actual needs of the application scenario, and this application embodiment does not impose any restrictions on this.

[0044] As mentioned above, the traffic behavior of autonomous vehicle swarms differs significantly from that of human-driven vehicles. In most cases, human-driven vehicles lack coordination, and their traffic behavior is considered independent. However, for autonomous vehicle swarms, the traffic behavior of a single autonomous vehicle is not independent but rather part of the Swarm Intelligence behavior built upon Carrier Availability Vehicles (CAVs). On the one hand, CAVs are an important way to use road traffic resources more efficiently and at a lower cost; on the other hand, CAVs can also lead to the inappropriate use of road resources, such as multiple autonomous vehicles using the same road simultaneously potentially degrading the level of service.

[0045] In view of this, embodiments of this application provide a method for collaborative scheduling of unmanned vehicle clusters. By treating unmanned vehicles as special vehicles, a vehicle conversion factor is determined based on their driving constraints, thereby calculating the first equivalent traffic volume of the unmanned vehicle. Simultaneously, the second equivalent traffic volume of other vehicles on the road is calculated, and the road service level is further determined based on the calculated equivalent traffic volume. Based on the road service level, it is determined whether the target unmanned vehicle has triggered an abnormal event on the road within a target time slice. If so, a scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates. That is, embodiments of this application provide a collaborative scheduling scheme for unmanned vehicle clusters based on road resource occupancy. This scheme, by performing real-time quantitative calculation of the road service level when unmanned vehicles use road resources, and based on this, performs real-time control and scheduling of associated unmanned vehicle clusters, which can prevent the deterioration of road capacity and service level caused by the unreasonable use of road resources by unmanned vehicles.

[0046] It should be noted that in the following description, "driverless car" and "unmanned vehicle" have the same meaning.

[0047] Figure 2 This is a flowchart illustrating a collaborative scheduling method for unmanned vehicle clusters provided in an embodiment of this application. Figure 2 The autonomous vehicle cluster collaborative scheduling method can be derived from Figure 1 The server executes the command. For example... Figure 2 As shown, the autonomous vehicle cluster collaborative scheduling method includes the following steps:

[0048] In step S201, the traffic volume of the road where the target unmanned vehicle is located within the target time slice is obtained.

[0049] In step S202, the driving restrictions of the unmanned vehicle are obtained, and the conversion factor of the first vehicle is determined based on the driving restrictions.

[0050] Among them, the first vehicle conversion factor is the vehicle conversion factor for unmanned vehicles.

[0051] In step S203, the first equivalent traffic volume of the road within the target time slice is calculated based on the first vehicle conversion factor.

[0052] In step S204, the second equivalent traffic volume of the road within the target time slice is calculated.

[0053] The second equivalent traffic volume is the equivalent traffic volume of all vehicles other than driverless cars on the road within the target time slice.

[0054] In step S205, a first road service level is determined based on a first equivalent traffic volume, and a second road service level is determined based on the first equivalent traffic volume and a second equivalent traffic volume.

[0055] In step S206, in response to an abnormal event being triggered on a road within a target time slice, based on a first road service level or a determination of a first road service level and a second road service level, the associated unmanned vehicle cluster of the road is obtained.

[0056] In step S207, a scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates.

[0057] In this embodiment, the autonomous vehicle cluster collaborative scheduling method can be applied to scenarios where autonomous vehicles use any transportation infrastructure. The transportation infrastructure can be roads, bridges, tunnels, etc., and is not limited thereto.

[0058] In this embodiment of the application, the autonomous vehicle cluster collaborative scheduling method can be executed by a server. The server can first obtain the traffic volume of the road where the target autonomous vehicle is located within the target time slice. Figures 3(A) and 3(B) illustrate two different methods for obtaining traffic volume, respectively.

[0059] In the embodiment shown in Figure 3(A), traffic information within the detection area can be acquired using a camera or sensor carried by the target unmanned vehicle, and then uploaded to a server. The target unmanned vehicle can directly upload the acquired real-time traffic information to the server, which then calculates the traffic volume of the road within the target time slice based on the received traffic information. Alternatively, the target unmanned vehicle can autonomously calculate the traffic volume of the road within the target time slice based on the acquired traffic information, and then upload the calculated traffic volume to the server.

[0060] In the embodiment shown in Figure 3(B), a detection device positioned near the road can also obtain traffic information for the road within a target time slice by counting the traffic volume passing through the detection line, and then upload the obtained traffic information to the server. Similarly, the detection device can directly upload the acquired real-time traffic information to the server, which will then calculate the traffic volume of the road within the target time slice based on the received traffic information. Alternatively, the detection device can also autonomously calculate the traffic volume of the road within the target time slice based on the acquired traffic information, and then upload the calculated traffic volume to the server.

[0061] In this embodiment, the server can also obtain the driving restrictions of the unmanned vehicles and determine a first vehicle conversion factor based on the obtained driving restrictions to characterize the unmanned vehicles. The driving restrictions refer to the conditions that the unmanned vehicle cluster must meet when driving on designated roads, including conditions stipulated by administrative departments and the driving conditions of the unmanned vehicles themselves. The first vehicle conversion factor can be determined with reference to the Passenger Car Equivalent (PCE) calculation method for special vehicles. Specifically, a vehicle type can be selected as the standard vehicle, with a coefficient of 1. Based on the degree of road occupation by various types of vehicles, the number of each type of vehicle relative to the standard vehicle equivalent (PCU) is determined, thereby obtaining the conversion factor for each type of vehicle.

[0062] In this embodiment of the application, the first equivalent traffic volume of the road within the target time slice can be calculated based on the first vehicle conversion factor. That is, the first vehicle conversion factor can be used to convert the traffic volume of the unmanned vehicle on the road within the target time slice into the first equivalent traffic volume.

[0063] In this embodiment of the application, a second equivalent traffic volume of the road within the target time slice can also be calculated. The second equivalent traffic volume is the equivalent traffic volume of other vehicles on the road within the target time slice, excluding driverless vehicles.

[0064] In this embodiment, a first road service level can be determined based on a first equivalent traffic volume, and a second road service level can be determined based on a first equivalent traffic volume and a second equivalent traffic volume. The first road service level characterizes the impact of the target autonomous vehicle on road service, and the second road service level characterizes the impact of all vehicles, including the target autonomous vehicle and other vehicles, on road service.

[0065] In this embodiment, the server can use a preset judgment strategy to determine whether the target unmanned vehicle has triggered an abnormal event on the road within the target time slice, based on a first road service level. Alternatively, the server can also use a preset judgment strategy to determine whether the target unmanned vehicle has triggered an abnormal event on the road within the target time slice, based on a first road service level and a second road service level. When the server determines, based on the first road service level or the first and second road service levels, that the target unmanned vehicle has triggered an abnormal event on the road within the target time slice, the server can identify an associated unmanned vehicle cluster and then execute a scheduling strategy on the associated unmanned vehicle cluster until the abnormal event terminates. The associated unmanned vehicle cluster can be a set of unmanned vehicles that are currently using the road or that need to use the road to complete the current task based on navigation.

[0066] According to the technical solution provided in this application, by treating unmanned vehicles as special vehicles, the vehicle conversion factor of the unmanned vehicles is determined based on their driving restrictions, and then the first equivalent traffic volume of the unmanned vehicles is calculated. Simultaneously, the second equivalent traffic volume of other vehicles on the road is calculated, and the road service level is further determined based on the calculated equivalent traffic volume. Based on the road service level, it is determined whether the target unmanned vehicle has triggered an abnormal event on the road within the target time slice. If so, a scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates. That is, this application provides an unmanned vehicle cluster collaborative scheduling scheme based on road resource occupancy. This scheme, by performing real-time quantitative calculation of the road service level when unmanned vehicles use road resources, and based on this, performs real-time control and scheduling of the associated unmanned vehicle cluster, which can prevent the deterioration of road capacity and service level caused by the unreasonable use of road resources by unmanned vehicles.

[0067] Figure 4 This is a flowchart illustrating the method for calculating the first equivalent traffic volume provided in an embodiment of this application. Figure 4 As shown, the method includes the following steps:

[0068] In step S401, the first percentage of all vehicles on the road within the target time slice is determined.

[0069] In step S402, the first percentage and the first vehicle conversion factor are multiplied to obtain the first corrected traffic volume.

[0070] In step S403, the product of the road's traffic volume and the first corrected traffic volume is determined as the first equivalent traffic volume of the road within the target time slice.

[0071] In this embodiment of the application, when calculating the first equivalent traffic volume of a road within a target time slice, the percentage of the target unmanned vehicle among all vehicles on the road within the target time slice can be calculated first. Then, the first percentage and the first vehicle conversion factor are multiplied to obtain the first corrected traffic volume. Finally, the road's traffic volume is multiplied by the first corrected traffic volume to obtain the first equivalent traffic volume of the road within the target time slice.

[0072] In one example, if the first percentage is denoted as P A Let the conversion factor for the first vehicle be E. A Let V be the traffic volume of the road within the target time slice. Then the first equivalent traffic volume V A It can be calculated using the following formula:

[0073] V A =V*P A *E A .

[0074] Figure 5 This is a flowchart illustrating the method for calculating the second equivalent traffic volume provided in an embodiment of this application. Figure 5 As shown, the method includes the following steps:

[0075] In step 501, the types of vehicles other than driverless cars are determined on the road within the target time slice.

[0076] In step 502, the second percentage of each type of other vehicles in the total number of vehicles is determined.

[0077] In step 503, the second vehicle conversion factor for each type of other vehicle is determined.

[0078] In step 504, the second percentage of each type of vehicle is multiplied by the second vehicle conversion factor, and the products of the second percentage of each type of vehicle and the second vehicle conversion factor are summed to obtain the second corrected traffic volume.

[0079] In step 505, the product of the road's traffic volume and the second modified traffic volume is determined as the second equivalent traffic volume of the road within the target time slice.

[0080] In this embodiment, the types of vehicles other than autonomous vehicles on the road within the target time slice can be determined first, and the second percentage of each type of other vehicle among all vehicles can be determined. Further, a second vehicle conversion factor for each type of other vehicle can be determined. Next, the second percentage of each type of vehicle is multiplied by the second vehicle conversion factor, and the products of the second percentage of each type of vehicle and the second vehicle conversion factor are summed to obtain the second corrected traffic volume. Finally, the traffic volume of the road is multiplied by the second corrected traffic volume to obtain the second equivalent traffic volume of the road within the target time slice. In other words, the calculation method for the second equivalent traffic volume is basically the same as that for the first equivalent traffic volume. The only difference is that the vehicle types included in the autonomous vehicle can be considered as a single type, all of which correspond to the same first vehicle conversion factor. However, there are many different types of other vehicles, such as standard vehicles, buses, and water trucks. The second vehicle conversion factors corresponding to these different types of vehicles are also different. Therefore, it is necessary to calculate the second percentage for each type of vehicle separately, and calculate the corrected traffic volume for each type of vehicle based on the second percentage and the second vehicle conversion factor. Finally, the corrected traffic volumes of each type of vehicle are summed to obtain the overall corrected traffic volume for other vehicles.

[0081] In one example, if the second percentage is denoted as P i The conversion factor for the second vehicle is denoted as E. i Where i represents the vehicle type and i is a positive integer, then the first equivalent traffic volume V E It can be calculated using the following formula:

[0082]

[0083] Furthermore, the overall equivalent traffic volume V of the road within the target time slice. total It could be:

[0084]

[0085] Figure 6 This is a flowchart illustrating the method for determining a first road service level provided in an embodiment of this application.

[0086] like Figure 6 As shown, the method includes the following steps:

[0087] In step 601, a correction factor is determined based on the driving restriction conditions.

[0088] In step 602, the product of the correction factor and the first equivalent traffic volume, and the ratio of the product to the design traffic volume of the road, are determined as the first road service level.

[0089] In this embodiment, a correction coefficient can be determined based on the aforementioned driving restrictions. This correction coefficient can be determined based on factors such as road speed limits, the proportion of autonomous vehicles with speed limits, or the average density of autonomous vehicles on a specific road segment, or other conditions; no restrictions are imposed here. Furthermore, the design traffic volume of the road can be obtained. This design traffic volume is data matched during road design and can be queried; details are omitted here. The correction coefficient is multiplied by the first equivalent traffic volume, and the ratio of the obtained product to the design traffic volume can be determined as the first road service level.

[0090] In one example, if the correction factor is denoted as W and the design traffic volume is denoted as C, then the first road service level L A It can be calculated using the following formula:

[0091] L A =(W*V A ) / C.

[0092] Figure 7 This is a flowchart illustrating the method for determining a second road service level provided in an embodiment of this application.

[0093] like Figure 7 As shown, the method includes the following steps:

[0094] In step 701, a correction factor is determined based on the driving restriction conditions.

[0095] In step 702, the product of the correction factor and the first equivalent traffic volume, and the ratio of this product to the road's design traffic volume, are determined as the first road service level.

[0096] In step 703, the ratio of the second equivalent traffic volume to the road's design traffic volume is determined as the third road service level.

[0097] In step 704, the sum of the first road service level and the third road service level is determined as the second road service level.

[0098] In this embodiment, when determining the second road service level, the first road service level can be determined first, and then the third road service level, reflecting the impact of other vehicles on road service, can be determined. Specifically, the third road service level can be determined by the ratio of the second equivalent traffic volume to the road's design traffic volume. Finally, the second road service level is obtained by summing the first and third road service levels.

[0099] In one example, the third road service level L E It can be calculated using the following formula:

[0100] L E =V E / C.

[0101] Furthermore, the second level of service L total for:

[0102] L total =L E +L A =V E / C+(W*V A ) / C.

[0103] In this embodiment, it can be determined whether an abnormal event has been triggered on a road within a target time slice by using a first road service level, or by using a first road service level and a second road service level. Specifically, it can be determined that an abnormal event has been triggered on a road within a target time slice when the first road service level is greater than or equal to a preset threshold for the first service level. Alternatively, it can be determined that an abnormal event has been triggered on a road within a target time slice when the second road service level is greater than or equal to a preset threshold for the second service level. Or, it can be determined that an abnormal event has been triggered on a road within a target time slice when the first road service level is greater than or equal to a third road service level while determining the second road service level.

[0104] In other words, the preset threshold H for the first service level can be determined. A H A H is used to characterize the maximum acceptable impact of autonomous vehicle swarms on road service levels. AThe value of L can be determined based on urban road service level classification standards or specific standards for a specific scenario; no restrictions are imposed here. A >=H A At this point, it can be assumed that an abnormal event has been triggered on the road within the target time slice. At this time, the state of road R in that time slice ti is abnormal, i.e., the road's state Si = 1, and road R has triggered an abnormal event (AE). R .

[0105] On the other hand, the second service level preset threshold H can also be determined. total H total H is used to characterize the maximum acceptable impact of all vehicles on the level of service. total The method for determining the value of H is the same as that for H. A Similarly, this will not be elaborated upon here. When L total >=H total Similarly, it can be assumed that an abnormal event was triggered on the road within the target time slice. At this time, the state of road R in the time slice ti is an abnormal state, that is, the state of the road Si = 1.

[0106] On the other hand, it can also be determined whether the first road service level is greater than or equal to the third road service level in the second road service level. If so, it can also be considered that the road has been triggered by an abnormal event within the target time slice. That is to say, if the road service level of all vehicles in the autonomous vehicle cluster is lower than that of other vehicles in the second road service level, it can be considered that the autonomous vehicle cluster has had a significant impact on the road service. In this case, it can also be determined that the state of road R in the time slice ti is an abnormal state, that is, the state of the road Si = 1.

[0107] It is understandable that the above-mentioned multiple judgment strategies can be used in combination, and there are no restrictions here.

[0108] In this embodiment of the application, after determining that an abnormal event has been triggered on the road within the target time slice, the server needs to execute a scheduling strategy on the associated unmanned vehicle cluster, specifically including: controlling the vehicles in the associated unmanned vehicle cluster to use alternative routes to avoid the road; or controlling the vehicles in the associated unmanned vehicle cluster to stop at the stop point; or controlling the vehicles in the associated unmanned vehicle cluster to pass through the road in a specific formation.

[0109] In other words, when road R experiences an AE R When an event occurs, you can first obtain the set of associated autonomous vehicles that are currently using or have completed navigation and will be using the road {A}. j}, for {A j Issue scheduling policies to enable {A} jVehicles in the sequence can use alternative routes to avoid road R, stop at designated stops on the road edge, or pass through road R in a specific formation. This specific formation can be a specific headway or a specific headway, etc.

[0110] In this embodiment, when an abnormal event is triggered on a road within a target time slice, the server can record the road's state using a Markov process until the abnormal event terminates. After the abnormal event terminates, the server can also send a release control command to parked vehicles in the associated autonomous vehicle cluster or vehicles passing through the road in a specific formation, so that the vehicles in the associated autonomous vehicle cluster can resume normal driving. The method for determining the termination of the abnormal event can be: determining the road's state in multiple time slices following the target time slice. If the road is in a normal state for m consecutive time slices following the target time slice, then the abnormal event can be determined to have terminated, where m is a positive integer.

[0111] In other words, when road R is in an abnormal state Si at time ti, i.e., AE is triggered. R During an event, the state of road R can be recorded using a Markov process until the End of Abnormal Event (EAE) occurs. The condition for an EAE to occur is: if road R triggers an EAE at time ti. R If m consecutive states following ti are all normal states, such as non-congested states, then an abnormal event is triggered to terminate the EAE. Furthermore, the AE... R and EAE R For event pairs, they are interrelated, when EAE R When it occurs, it can be applied to {A} j The system issues release commands to vehicles that stop or pass through road R in a specific formation, so that these vehicles can resume normal driving.

[0112] Figure 8 This is a flowchart illustrating another method for collaborative scheduling of unmanned vehicle clusters provided in an embodiment of this application. Figure 8 The method includes the following steps: real-time acquisition of road traffic state data by autonomous vehicles; conversion of autonomous vehicles into standard vehicle equivalents as special vehicles; calculation of road traffic volume and service level; definition of abnormal road states based on the impact of autonomous vehicles on road service levels; definition of abnormal events and termination of abnormal events based on Markov processes of road states; scheduling and control of autonomous vehicles associated with the abnormal event after the occurrence of the abnormal event; and decontrolling the autonomous vehicles designed for the associated abnormal event after the termination of the abnormal event.

[0113] The technical solution adopted in this application provides a method for calculating road resource occupancy status, including a method for calculating the impact of autonomous vehicle clusters using road resources on road capacity and road service level; a method for defining normal and abnormal states of autonomous vehicle clusters using road resources based on road service level; and a real-time scheduling strategy for autonomous vehicle clusters triggered by abnormal state events of road resource use, which can prevent the degradation of road service level caused by the use of road resources by autonomous vehicle clusters. In other words, the technical solution of this application provides a method for real-time quantitative calculation of road capacity and service level when autonomous vehicle clusters use road resources, and based on this, performs real-time control and scheduling of the autonomous vehicle clusters to prevent unreasonable use of road resources by autonomous vehicle clusters from causing deterioration of road capacity and service level.

[0114] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0115] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0116] Figure 9 This is a schematic diagram of an unmanned vehicle cluster collaborative scheduling device provided in an embodiment of this application. Figure 9 As shown, the unmanned vehicle cluster collaborative scheduling device includes:

[0117] The acquisition module 901 is configured to acquire the traffic volume of the road where the target unmanned vehicle is located within the target time slice.

[0118] Template 901 is also configured to obtain the driving restrictions of the unmanned vehicle, and determine the first vehicle conversion factor based on the driving restrictions. The first vehicle conversion factor is the vehicle conversion factor of the unmanned vehicle.

[0119] The calculation module 902 is configured to calculate the first equivalent traffic volume of the road within the target time slice based on the first vehicle conversion factor.

[0120] The calculation module 902 is also configured to calculate the second equivalent traffic volume of the road in the target time slice, which is the equivalent traffic volume of the road for vehicles other than driverless cars in the target time slice.

[0121] The determination module 903 is configured to determine a first road service level based on a first equivalent traffic volume, and to determine a second road service level based on a first equivalent traffic volume and a second equivalent traffic volume.

[0122] Template 901 is also configured to retrieve the associated unmanned vehicle cluster of the road in response to an abnormal event triggered on the road within a target time slice, based on a first road service level, or a first road service level and a second road service level.

[0123] The scheduling module 904 is configured to execute scheduling strategies on the associated unmanned vehicle cluster until an abnormal event terminates the process.

[0124] According to the technical solution provided in this application, by treating unmanned vehicles as special vehicles, the vehicle conversion factor of the unmanned vehicles is determined based on their driving restrictions, and then the first equivalent traffic volume of the unmanned vehicles is calculated. Simultaneously, the second equivalent traffic volume of other vehicles on the road is calculated, and the road service level is further determined based on the calculated equivalent traffic volume. Based on the road service level, it is determined whether the target unmanned vehicle has triggered an abnormal event on the road within the target time slice. If so, a scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates. That is, this application provides an unmanned vehicle cluster collaborative scheduling scheme based on road resource occupancy. This scheme, by performing real-time quantitative calculation of the road service level when unmanned vehicles use road resources, and based on this, performs real-time control and scheduling of the associated unmanned vehicle cluster, which can prevent the deterioration of road capacity and service level caused by the unreasonable use of road resources by unmanned vehicles.

[0125] In this embodiment of the application, the calculation of the first equivalent traffic volume of the road in the target time slice based on the first vehicle conversion factor includes: determining the first percentage of the target unmanned vehicle to the total number of vehicles on the road in the target time slice; multiplying the first percentage and the first vehicle conversion factor to obtain the first corrected traffic volume; and determining the product of the road's traffic volume and the first corrected traffic volume as the first equivalent traffic volume of the road in the target time slice.

[0126] In this embodiment of the application, calculating the second equivalent traffic volume of a road within a target time slice includes: determining the types of vehicles other than driverless vehicles on the road within the target time slice; determining the second percentage of each type of other vehicles among all vehicles; determining the second vehicle conversion factor for each type of other vehicles; producting the second percentage of each type of vehicle with the second vehicle conversion factor, and summing the products of the second percentage of each type of vehicle with the second vehicle conversion factor to obtain the second corrected traffic volume; and determining the product of the road's traffic volume and the second corrected traffic volume as the second equivalent traffic volume of the road within the target time slice.

[0127] In this embodiment, determining a first road service level based on a first equivalent traffic volume includes: determining a correction coefficient based on driving restrictions; and determining the first road service level by dividing the product of the correction coefficient and the first equivalent traffic volume by the road's design traffic volume. Determining a second road service level based on the first and second equivalent traffic volumes includes: determining a correction coefficient based on driving restrictions; and determining the first road service level by dividing the product of the correction coefficient and the first equivalent traffic volume by the road's design traffic volume; determining a third road service level by dividing the second equivalent traffic volume by the road's design traffic volume; and determining the second road service level by summing the first and third road service levels.

[0128] In this embodiment of the application, determining that an abnormal event has been triggered on a road within a target time slice based on a first road service level, or a first road service level and a second road service level, includes at least one of the following: determining that an abnormal event has been triggered on a road within a target time slice in response to determining that a first road service level is greater than or equal to a preset threshold of a first service level; determining that an abnormal event has been triggered on a road within a target time slice in response to determining that a second road service level is greater than or equal to a preset threshold of a second service level; or determining that an abnormal event has been triggered on a road within a target time slice in response to determining that, within a second road service level, the first road service level is greater than or equal to a third road service level.

[0129] In this embodiment of the application, the scheduling strategy for the associated unmanned vehicle cluster includes: controlling the vehicles in the associated unmanned vehicle cluster to use alternative routes to avoid roads; or controlling the vehicles in the associated unmanned vehicle cluster to stop at rest points; or controlling the vehicles in the associated unmanned vehicle cluster to pass through roads in a specific formation.

[0130] In this embodiment of the application, the method further includes: in response to determining that an abnormal event has been triggered on the road within the target time slice, recording the state of the road through a Markov process until the abnormal event terminates; in response to the termination of the abnormal event, sending a release control command to parked vehicles or vehicles passing through the road in a specific formation in the associated unmanned vehicle cluster, so that the vehicles in the associated unmanned vehicle cluster can resume normal driving; wherein, the termination of the abnormal event is determined in the following manner: determining the state of the road in multiple time slices after the target time slice; in response to the road being in a normal state for m consecutive time slices after the target time slice, determining that the abnormal event has terminated, where m is a positive integer.

[0131] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0132] Figure 10This is a schematic diagram of an electronic device provided in an embodiment of this application. Figure 10 As shown, the electronic device 10 of this embodiment includes: a processor 1001, a memory 1002, and a computer program 1003 stored in the memory 1002 and executable on the processor 1001. When the processor 1001 executes the computer program 1003, it implements the steps in the various method embodiments described above. Alternatively, when the processor 1001 executes the computer program 1003, it implements the functions of each module / unit in the various device embodiments described above.

[0133] Electronic device 10 may be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 10 may include, but is not limited to, a processor 1001 and a memory 1002. Those skilled in the art will understand that... Figure 10 This is merely an example of electronic device 10 and does not constitute a limitation on electronic device 10. It may include more or fewer components than shown, or different components.

[0134] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0135] The memory 1002 can be an internal storage unit of the electronic device 10, such as a hard disk or RAM of the electronic device 10. The memory 1002 can also be an external storage device of the electronic device 10, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc., equipped on the electronic device 10. The memory 1002 can also include both internal and external storage units of the electronic device 10. The memory 1002 is used to store computer programs and other programs and data required by the electronic device.

[0136] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0137] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0138] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for collaborative scheduling of unmanned vehicle clusters, characterized in that, include: Obtain the traffic volume of the road where the target autonomous vehicle is located within the target time slice; Obtain the driving restrictions of the autonomous vehicle, and determine the first vehicle conversion factor based on the driving restrictions. The first vehicle conversion factor is the vehicle conversion factor of the autonomous vehicle. The first equivalent traffic volume of the road within the target time slice is calculated based on the first vehicle conversion factor. Calculate the second equivalent traffic volume of the road in the target time slice. The second equivalent traffic volume is the equivalent traffic volume of the road for vehicles other than driverless vehicles in the target time slice. A first road service level is determined based on the first equivalent traffic volume, and a second road service level is determined based on the first equivalent traffic volume and the second equivalent traffic volume. In response to an abnormal event being triggered on the road within the target time slice, based on a first road service level or a first road service level and a second road service level, the associated unmanned vehicle cluster of the road is obtained; The scheduling strategy is executed on the associated unmanned vehicle cluster until the abnormal event terminates.

2. The method according to claim 1, characterized in that, The calculation of the first equivalent traffic volume of the road within the target time slice based on the first vehicle conversion factor includes: Determine the first percentage of the target unmanned vehicle among all vehicles on the road within the target time slice; The first corrected traffic volume is obtained by multiplying the first percentage and the first vehicle conversion factor. The product of the traffic volume on the road and the first corrected traffic volume is determined as the first equivalent traffic volume of the road within the target time slice.

3. The method according to claim 1, characterized in that, The calculation of the second equivalent traffic volume of the road within the target time slice includes: Determine the types of vehicles other than driverless cars on the road within the target time slice; Determine the second percentage of all vehicles of each type; Determine the conversion factor for the second vehicle of each type of other vehicles; The second revised traffic volume is obtained by multiplying the second percentage of each type of vehicle with the second vehicle conversion factor, and summing the products of the second percentage of each type of vehicle with the second vehicle conversion factor. The product of the traffic volume on the road and the second corrected traffic volume is determined as the second equivalent traffic volume of the road within the target time slice.

4. The method according to claim 1, characterized in that, Determining the first road service level based on the first equivalent traffic volume includes: The correction coefficient is determined based on the aforementioned driving restrictions; The first road service level is determined by the ratio of the product of the correction factor and the first equivalent traffic volume to the design traffic volume of the road. The determination of the second road service level based on the first equivalent traffic volume and the second equivalent traffic volume includes: The correction coefficient is determined based on the aforementioned driving restrictions; The first road service level is determined by the ratio of the product of the correction factor and the first equivalent traffic volume to the design traffic volume of the road. The ratio of the second equivalent traffic volume to the design traffic volume of the road is determined as the third road service level; The sum of the first road service level and the third road service level is determined as the second road service level.

5. The method according to claim 4, characterized in that, Based on a first road service level, or a first road service level and a second road service level, it is determined that the road was triggered by an anomalous event within the target time slice, including at least one of the following: In response to determining that the first road service level is greater than or equal to a first service level preset threshold, it is determined that the road has been triggered by an abnormal event within the target time slice; In response to determining that the second road service level is greater than or equal to a preset threshold for the second service level, it is determined that the road has been triggered by an abnormal event within the target time slice; In response to determining that the first road service level is greater than or equal to the third road service level in the second road service level, it is determined that the road was triggered by an abnormal event within the target time slice.

6. The method according to claim 1, characterized in that, The execution of the scheduling strategy for the associated unmanned vehicle cluster includes: Control the vehicles in the associated autonomous vehicle cluster to use alternative routes to avoid the road; or Control the vehicles in the associated unmanned vehicle cluster to stop at designated stops; or Control the vehicles in the associated unmanned vehicle cluster to pass through the road in a specific formation.

7. The method according to claim 6, characterized in that, The method further includes: In response to determining that an abnormal event has been triggered on the road within the target time slice, the state of the road is recorded via a Markov process until the abnormal event terminates. In response to the termination of the abnormal event, a release control command is sent to parked vehicles in the associated unmanned vehicle cluster or vehicles passing through the road in a specific formation, so that the vehicles in the associated unmanned vehicle cluster can resume normal driving. The termination of the abnormal event is determined in the following manner: The state of the road is determined in multiple time slices following the target time slice; In response to the fact that the road is in a normal state for m consecutive time slices after the target time slice, the abnormal event is determined to terminate, where m is a positive integer.

8. A collaborative scheduling device for unmanned vehicle clusters, characterized in that, include: The acquisition module is configured to acquire the traffic volume of the road where the target unmanned vehicle is located within a target time slice. The acquisition module is also configured to acquire the driving restriction conditions of the unmanned vehicle, and determine a first vehicle conversion factor based on the driving restriction conditions, wherein the first vehicle conversion factor is the vehicle conversion factor of the unmanned vehicle. The calculation module is configured to calculate the first equivalent traffic volume of the road in the target time slice based on the first vehicle conversion factor; The calculation module is also configured to calculate the second equivalent traffic volume of the road in the target time slice, wherein the second equivalent traffic volume is the equivalent traffic volume of the road for vehicles other than driverless vehicles in the target time slice; The determination module is configured to determine a first road service level based on the first equivalent traffic volume, and to determine a second road service level based on the first equivalent traffic volume and a second equivalent traffic volume. The acquisition module is further configured to acquire the associated unmanned vehicle cluster of the road in response to an abnormal event being triggered on the road within the target time slice, based on a first road service level, or a first road service level and a second road service level. The scheduling module is configured to execute a scheduling strategy on the associated unmanned vehicle cluster until the abnormal event terminates.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images