Dynamic management method, system, equipment, medium and product of mixed traffic flow

Abstract

The invention discloses a dynamic management method, system and device for mixed traffic flow, a medium and a product. The method comprises the following steps: acquiring participants of a mixed traffic flow scene; the participants comprise controllable participants and uncontrollable participants; clustering the controllable participants according to a preset group scale range to obtain at least one microscopic group; when a state change notification from the participant is received, searching an affected first microscopic group from the microscopic groups, and recombining the first microscopic group according to the state change notification; and reordering the microcosmic groups at each time step, regarding each reordered microcosmic group as a formation control object, and performing formation control on the participants. By adopting the embodiment of the invention, the efficient division of the traffic flow can be realized, the compactness of the microscopic group is ensured to be maintained in real time, the computing complexity of the cloud during traffic flow management is effectively reduced, and the management efficiency and the resource utilization rate are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, system, device, medium and product for dynamic management of mixed traffic flow. Background Technology

[0002] Currently, the management and control of traffic participants in traffic flow scenarios mainly relies on platooning methods. The core concept of platooning is that multiple traffic participants can travel evenly at the same speed and desired intervals. Compared to vehicles traveling independently, platooning offers greater controllability, effectively reduces air resistance, and lowers energy consumption.

[0003] However, formation methods are essentially based on finite state machines with fixed modes. Existing technologies treat long traffic flows as a large group during formation control. As the number of traffic participants increases, their trajectories become extremely complex and variable, making it impossible to accurately and comprehensively represent these trajectories using finite states. Meanwhile, cloud computing complexity increases quadratically with the number of traffic participants, a characteristic that makes existing technologies particularly difficult to handle complex mixed traffic flows on long road sections. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic management method, system, device, medium, and product for mixed traffic flow, which can achieve efficient traffic flow segmentation, maintain the compactness of micro-groups during changes in the control state of traffic participants, ensure that each traffic participant can be accurately assigned to a suitable micro-group at any time, effectively reduce the computational complexity of cloud-based traffic flow management, and greatly improve management efficiency and resource utilization.

[0005] This invention provides a dynamic management method for mixed traffic flow, comprising: Identify the participants in a mixed traffic flow scenario; the participants include controllable participants and uncontrollable participants; Based on a preset group size range, the controllable participants are clustered to obtain at least one micro-group; When a status change notification is received from the participant, the first affected microgroup is located from the microgroup, and the first microgroup is reorganized according to the status change notification; At each time step, the micro-groups are reordered, and each reordered micro-group is regarded as a group control object, and group control is performed on the participants.

[0006] As an improvement to the above scheme, the step of clustering the controllable participants according to a preset group size range to obtain at least one micro-group includes: Establish the gravitational potential energy field among the controllable participants within the micro-group, and calculate the total gravitational potential energy of the mixed traffic flow scenario; Establish a repulsive potential energy field between micro-groups and calculate the total repulsive potential energy of the mixed traffic flow scenario. Calculate the total potential energy of the mixed traffic flow scenario based on the total gravitational potential energy and the total repulsive potential energy; Based on a preset group size range, and with the goal of minimizing the total potential energy, the controllable participants are clustered to obtain at least one micro-group.

[0007] As an improvement to the above scheme, the step of establishing the repulsive potential energy field between micro-groups and calculating the total repulsive potential energy of the mixed traffic flow scenario includes: The second equivalent quality of the microgroup is obtained based on the first equivalent quality of all controllable participants within the microgroup; The geometric center of the micro-population is obtained based on the real-time local coordinates of all controllable participants within the micro-population and the second equivalent mass. Based on the second equivalent mass and the geometric center, the repulsive potential energy between every two micro-groups is calculated, a repulsive potential energy field is established, and the total repulsive potential energy of the mixed traffic flow scenario is obtained.

[0008] The process of establishing the gravitational potential energy field among the controllable participants within the micro-group and calculating the total gravitational potential energy of the mixed traffic flow scenario includes: Obtain the first equivalent mass and real-time local coordinates of the controllable participant; Calculate the gravitational potential energy between each two controllable participants based on the first equivalent mass and the real-time local coordinates; Based on the gravitational potential energy between every two controllable participants, a gravitational potential energy field is established among the controllable participants within the micro-group. The total gravitational potential energy of the mixed traffic flow scenario is calculated based on the gravitational potential energy field of each of the aforementioned micro-groups.

[0009] As an improvement to the above scheme, the controllable participants are clustered according to a preset group size range, with the goal of minimizing the total potential energy, to obtain at least one micro-group, including: Calculate the range of cluster numbers based on the preset group size range and the number of controllable participants; Within the range of the number of clusters, the controllable participants are clustered with the goal of minimizing the total potential energy to obtain the optimal number of clusters. Based on the clustering results corresponding to the optimal clustering number, at least one micro-population is obtained.

[0010] As an improvement to the above scheme, the step of finding the affected first micro-group from the micro-group when a state change notification is received from the participant, and reorganizing the first micro-group according to the state change notification, includes: When a status change notification is received from the participant, the coordinates of the participant are obtained; Based on the coordinates, the first affected micro-group and its corresponding index position are obtained through binary search. Update the first microgroup at the index position according to the status change notification; Based on the updated occupancy rate of the first micro-group, the updated first micro-group is reorganized.

[0011] As an improvement to the above scheme, the step of obtaining the affected first micro-group and its corresponding index position through binary search based on the coordinates includes: Based on the coordinates, the first affected microgroup is located from all the microgroups through a first binary search; Based on the coordinates and the first micro-group, the index position is found from the first micro-group through a second binary search.

[0012] As an improvement to the above scheme, the state change notification includes an exit control request from the controllable participant and an entry control request from the uncontrollable participant. Therefore, updating the first micro-group at the index position based on the state change notification includes: If the status change notification is an exit control request, then delete the controllable participant corresponding to the index position of the first microgroup; If the status change notification is a join control request, then the corresponding uncontrollable participant is inserted at the index position of the first microgroup; Update the status and index position of the participants in the first microgroup.

[0013] As an improvement to the above scheme, the step of reorganizing the updated first micro-group based on the updated occupancy rate of the first micro-group includes: Calculate the updated first occupancy rate of the first microgroup; If the first occupancy rate is greater than the preset maximum occupancy rate threshold, then the first micro-group will be split into two second micro-groups to form a new micro-group. If the first occupancy rate is less than the preset minimum occupancy rate threshold, then the first micro-group is merged with an adjacent micro-group to form a third micro-group, and the second occupancy rate of the third micro-group is calculated. If the second occupancy rate is greater than the preset maximum occupancy rate threshold, the third micro-group is split into two fourth micro-groups to form a new micro-group; otherwise, a new micro-group is obtained based on the third micro-group.

[0014] As an improvement to the above scheme, the reordering of the micro-groups at each time step, treating each reordered micro-group as a grouping control object, and performing grouping control on the participants includes: Build an initialization list at each time step; Based on the coordinates of the controllable participants in the micro-group, the micro-groups are merged and sorted one by one, and the micro-groups are added to the initialization list according to the merge and sort results; When the initialization list includes all the micro-groups, an ordered list is obtained; Based on the number of micro-groups, the ordered list is re-splitted to obtain reordered ordered micro-groups; Each of the ordered micro-groups is treated as a group control object, and group control is performed on the participants.

[0015] This invention also provides a dynamic management system for mixed traffic flow, comprising: The participant acquisition module is used to acquire participants in a mixed traffic flow scenario; the participants include controllable participants and uncontrollable participants; The micro-group segmentation module is used to cluster the controllable participants according to a preset group size range to obtain at least one micro-group. The micro-group reorganization module is used to, when receiving a status change notification from the participant, locate the first affected micro-group from the micro-groups and reorganize the first micro-group according to the status change notification; The formation control module is used to reorder the micro-groups at each time step, treat each reordered micro-group as a formation control object, and perform formation control on the participants.

[0016] This invention also provides a dynamic management device for mixed traffic flow, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the dynamic management method for mixed traffic flow as described above.

[0017] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to perform the dynamic management method for mixed traffic flow as described above.

[0018] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they perform the dynamic management method for mixed traffic flow as described above.

[0019] Compared with existing technologies, this invention discloses a dynamic management method, system, device, medium, and product for mixed traffic flow. It acquires participants in a mixed traffic flow scenario, including controllable and uncontrollable participants. Based on a preset group size range, the controllable participants are clustered to obtain at least one micro-group. When a state change notification is received from a participant, the affected first micro-group is located from the micro-groups, and the first micro-group is reorganized according to the state change notification. At each time step, the micro-groups are reordered, and each reordered micro-group is treated as a formation control object for formation control. Using this invention, efficient traffic flow segmentation can be achieved. During changes in the control state of traffic participants, the compactness of micro-groups is maintained, ensuring that each traffic participant can be accurately assigned to a suitable micro-group at any time. This effectively reduces the computational complexity of cloud-based traffic flow management and greatly improves management efficiency and resource utilization. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the steps of a dynamic management method for mixed traffic flow provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the division result of a micro-population provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the micro-group before and after a participant joins control, provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the micro-group before and after the addition of a second participant to the control provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the micro-group before and after a participant leaves control, as provided in the first embodiment of the present invention; Figure 6 This is a schematic diagram of the micro-group before and after a participant withdraws from control, as provided in the embodiments of the present invention; Figure 7 This is a schematic diagram of the structure of a dynamic management system for mixed traffic flow provided in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] In the description and claims, it should be understood that the terms "first," "second," etc., used in the description and claims are only for the purpose of distinguishing the description of the same technical features, and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated, nor necessarily the order of description or chronological order. The terms are interchangeable where appropriate. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature.

[0023] Early platooning research focused on one-dimensional platoon control. In this mode, each vehicle uses the trajectory of the lead vehicle as a reference and follows its path. At the same time, a series of studies were conducted on the platoon stability and the convergence of disturbance propagation. However, the stability of the platoon under one-dimensional platoon control is too dependent on the lead vehicle, and the lane utilization rate is also low, making it difficult to extend to complex application scenarios.

[0024] Given the limitations of one-dimensional queue control, two-dimensional queuing methods have emerged. This method assigns desired motion to the virtual rigid structure of each vehicle, enabling them to follow the virtual structure. Compared to one-dimensional queues, two-dimensional queuing performs better in terms of disturbance resistance and lane utilization. However, this method is typically only applicable to fixed road segment scenarios. When faced with scenario changes, such as lane merging or ramp merging, it struggles to achieve adaptive transformation, limiting its application in diverse traffic scenarios.

[0025] To address the issue of scene transitions, researchers have proposed a formation switching method. This method can adaptively adjust the formation configuration according to different scenes, achieving some success in scene transitions. However, the formation setting still relies on manual operation, and it is almost impossible to fully cover all possible formations in the face of large and complex traffic flows, which limits its wide applicability and effectiveness to some extent.

[0026] With the deep application of AI technology in the vehicle field, intelligent connected vehicles have ushered in a more comprehensive development. However, existing platooning control methods are all based on long traffic flows, resulting in insufficient generalization and difficulty in adapting to the complex and ever-changing traffic conditions in mixed traffic environments. New technologies and methods are urgently needed to overcome this predicament in order to meet the growing demand for intelligent transportation.

[0027] Based on the above considerations, embodiments of the present invention provide a dynamic management method for mixed traffic flows. Please refer to... Figure 1 In this embodiment, the dynamic management method for mixed traffic flow is specifically executed through steps S1 to S4: S1. Obtain the participants in the mixed traffic flow scenario; the participants include controllable participants and uncontrollable participants.

[0028] In some preferred embodiments, all participants are numbered according to their positions in the mixed traffic flow scenario. Numbering reflects the relative positions of the participants, helps describe the spatial distribution of elements in the traffic flow, and facilitates the analysis of dynamic changes in the traffic flow.

[0029] It should be noted that the controllable participant is one that can receive instructions from the traffic management center to automatically adjust traffic information such as vehicle speed, lane position, and following distance. Furthermore, in this embodiment of the invention, the controllable and uncontrollable participants can be interchanged under specific circumstances. For example, in a mixed traffic flow scenario, a smart vehicle connected to the intelligent traffic management center can optionally become either a controllable or uncontrollable participant at any given time.

[0030] It should also be noted that the use of vehicles as participants in the above-described mixed traffic flow scenario is merely an example. In some embodiments, the participants also include bicycles, electric vehicles, or pedestrians. In other embodiments, the mixed traffic flow scenario is an air traffic flow scenario, and the participants are aircraft or drones. The specific mixed traffic flow scenario and the specific selection of participants do not affect the beneficial effects of this invention.

[0031] S2. Based on the preset group size range, cluster the controllable participants to obtain at least one micro-group.

[0032] In this embodiment of the invention, by clustering controllable participants, complex long traffic flows can be divided. Compared to the overall participant group, the formation of micro-groups is relatively controllable, effectively reducing the computational complexity in the cloud during traffic flow management. Furthermore, control can be implemented based on the micro-groups that are actually affected by traffic without impacting other micro-groups, enhancing the overall adaptability and stability of the system and ensuring that traffic flow remains relatively smooth even in complex and ever-changing environments.

[0033] S3. When a status change notification is received from the participant, the first affected microgroup is located from the microgroup, and the first microgroup is reorganized according to the status change notification.

[0034] It should be noted that when a status change notification is received, the internal structure of the micro-group will change. Timely reorganization is beneficial to maintaining the compactness of the micro-group, ensuring smooth traffic flow, and improving overall traffic efficiency.

[0035] S4. At each time step, the micro-groups are reordered, and each reordered micro-group is regarded as a grouping control object. Grouping control is performed on the participants.

[0036] In this embodiment of the invention, formation control is based on micro-groups. Different micro-groups may have different control methods, which leads to different movements of different micro-groups. The micro-groups are reordered at each time step, which can dynamically adjust the position distribution of different micro-groups in the traffic space. This real-time dynamic optimization capability enables the mixed traffic flow scenario to always maintain a near-optimal operating state, effectively cope with fluctuations in traffic demand, and improve the stability and reliability of the traffic system.

[0037] In some preferred embodiments, the mixed traffic flow scenario is divided into road segments. The data for the mixed traffic flow scenario includes the start and end points of the road segments, the segment number, road boundary information, lane line information, and road sign information. Furthermore, the location, speed, acceleration, collision boundary, heading angle, vehicle number, and road segment number of the participants are recorded according to the local coordinate system of the road segments. This enables the localization and updating of participants in the mixed traffic flow scenario.

[0038] As a preferred implementation, step S2, clustering the controllable participants according to a preset group size range to obtain at least one micro-group, is specifically performed through steps S21-S24: S21. Establish the gravitational potential energy field among the controllable participants within the micro-group, and calculate the total gravitational potential energy of the mixed traffic flow scenario; S22. Establish the repulsive potential energy field between micro-groups and calculate the total repulsive potential energy of the mixed traffic flow scenario. S23. Calculate the total potential energy of the mixed traffic flow scenario based on the total gravitational potential energy and the total repulsive potential energy; S24. Based on the preset group size range, and with the goal of minimizing the total potential energy, cluster the controllable participants to obtain at least one micro-group.

[0039] It should be noted that the clustering of micro-groups in the preferred embodiment of this invention is based on the K-means algorithm, which uses intra- and inter-group distances as the classification standard. However, in the field of transportation, relying solely on distance as the safety assessment standard for division is too simplistic and cannot adequately characterize the interactions within and between different micro-groups. This invention innovatively introduces potential energy as a metric, introducing gravitational potential energy between controllable participants within a micro-group and repulsive potential energy between micro-groups. By minimizing the total potential energy after clustering, the classification effect is evaluated, yielding the optimal arrangement and management method for determining group division, thereby achieving safer and more efficient dynamic management of micro-groups.

[0040] Further, preferably, step S21, establishing the gravitational potential energy field among the controllable participants within the micro-group, and calculating the total gravitational potential energy of the mixed traffic flow scenario, includes: Obtain the first equivalent mass and real-time local coordinates of the controllable participant; Calculate the gravitational potential energy between each two controllable participants based on the first equivalent mass and the real-time local coordinates; Based on the gravitational potential energy between every two controllable participants, a gravitational potential energy field is established among the controllable participants within the micro-group. The total gravitational potential energy of the mixed traffic flow scenario is calculated based on the gravitational potential energy field of each of the aforementioned micro-groups.

[0041] It should be noted that the real-time local coordinates refer to the relative positions of the controllable participants within the micro-group.

[0042] In some preferred embodiments, the gravitational potential field among the controllable participants within the microgroup i is represented as: (1); Furthermore, the total gravitational potential energy of the mixed traffic flow scenario is expressed as: (2); in, The number of controllable participants within microgroup i; and These are the first equivalent qualities of controllable participant i and controllable participant j within microgroup i, respectively. Let j be the real-time local coordinates of a controllable participant j within a microgroup i. Let k be the real-time local coordinates of a controllable participant k within a microgroup i; This refers to the number of micro-groups.

[0043] Preferably, step S22, establishing the repulsive potential energy field between micro-groups and calculating the total repulsive potential energy of the mixed traffic flow scenario, includes: The second equivalent quality of the microgroup is obtained based on the first equivalent quality of all controllable participants within the microgroup; The geometric center of the micro-population is obtained based on the real-time local coordinates of all controllable participants within the micro-population and the second equivalent mass. Based on the second equivalent mass and the geometric center, the repulsive potential energy between every two micro-groups is calculated, a repulsive potential energy field is established, and the total repulsive potential energy of the mixed traffic flow scenario is obtained.

[0044] In some preferred embodiments, the second equivalent mass of microgroup i is represented as: (3); The geometric center of the microgroup i is represented as: (4); The total repulsive potential energy of the mixed traffic flow scenario is expressed as: (5); in, The number of controllable participants within microgroup i; The first equivalent quality of controllable participant j within a microgroup i; Let be the local coordinates of controllable participant j within the microgroup i; This refers to the number of micro-groups.

[0045] It should be noted that a gravitational constant G is typically introduced into conventional artificial potential energy fields to simulate real gravitational phenomena. The construction of the gravitational and repulsive potential energy fields described in this invention's embodiments is based on the principle of artificial potential energy fields. However, since the potential energy fields constructed in this invention's embodiments are not strictly based on the law of universal gravitation for gravitational calculations, but rather construct an abstract potential energy field with properties similar to gravity, modifications have been made to the conventional artificial potential energy field calculations. To reduce computational complexity, the reference to the gravitational constant is omitted. In some preferred embodiments, the gravitational constant can be introduced for calculations, and other gravitational constants can also be used. The schemes for establishing gravitational and repulsive potential energy fields in traffic flow scenarios described in this invention's embodiments, even with only variations in specific formulas, should also be considered within the scope of protection of this invention.

[0046] In some preferred embodiments, step S23 involves calculating the total potential energy of the mixed traffic flow scenario based on the total gravitational potential energy and the total repulsive potential energy. , is represented as: (6).

[0047] Preferably, step S24 involves clustering the controllable participants according to a preset group size range, with the goal of minimizing the total potential energy, to obtain at least one micro-group, including: Calculate the range of cluster numbers based on the preset group size range and the number of controllable participants; Within the range of the number of clusters, the controllable participants are clustered with the goal of minimizing the total potential energy to obtain the optimal number of clusters. Based on the clustering results corresponding to the optimal clustering number, at least one micro-population is obtained.

[0048] It should be noted that the choice of the number of clusters has a decisive impact on the partitioning effect. If the number of clusters is too small, the micro-groups will be too large, which will significantly increase the computational complexity within the micro-groups. If the number of clusters is too large, the group size will be too small. In this case, the group decision-making method is no different from the decision-making of a single vehicle, and the meaning of group decision-making is lost.

[0049] In some preferred embodiments of the present invention, a reasonable range of cluster numbers is selected based on a preset group size range. : (7); (8); in, The number of controllable participants. The maximum value within the preset group size range. This is the minimum value within the preset group size range.

[0050] After determining the range of cluster numbers, a traversal strategy is adopted to calculate the total potential energy of the traffic flow for each cluster number, and finally, the cluster number that minimizes the total potential energy is selected. As the optimal number of clusters, The corresponding clustering results, as the micro-population division results, are mathematically expressed as follows: (9).

[0051] Please see Figure 2 For the mixed traffic flow scenario shown in the figure, the method of this embodiment is used to divide the micro-groups. All controllable participants in this scenario are divided into three micro-groups, represented by yellow, gray, and red, respectively. Uncontrollable participants are not included in the clustering and are represented by white. It can be seen that the micro-groups divided using this embodiment are consistent with common sense.

[0052] In a preferred implementation, step S3, when a state change notification is received from the participant, involves finding the first affected micro-group from the micro-groups, reorganizing the first micro-group according to the state change notification, and executing steps S31-S34: S31. When a status change notification is received from the participant, obtain the coordinates of the participant; S32. Based on the coordinates, obtain the first affected micro-group and the corresponding index position through binary search; S33. Update the first micro-population at the index position according to the status change notification; S34. Based on the updated occupancy rate of the first micro-group, reorganize the updated first micro-group.

[0053] In the above scheme, the relevant micro-groups can be efficiently located upon receiving a state change notification. Compared to traversal methods, binary search has lower complexity, significantly reducing the search time and improving system response. Furthermore, the embodiments of this invention enable accurate updates, reducing data processing workload and exhibiting good dynamic adaptability.

[0054] Further, preferably, step S32, obtaining the affected first micro-group and its corresponding index position through binary search based on the coordinates, includes: Based on the coordinates, the first affected microgroup is located from all the microgroups through a first binary search; Based on the coordinates and the first micro-group, the index position is found from the first micro-group through a second binary search.

[0055] Individual search is the foundation of all operations in dynamic management, requiring the rapid identification of the micro-group to which a participant belongs and their location / expected location within that micro-group.

[0056] It should be noted that if the sender of the state change notification is a controllable participant, the controllable participant is within the microgroup, and there is an index position within the microgroup representing the controllable participant, which can be directly found; if the sender of the state change notification is an uncontrollable participant, the participant is within the microgroup, and the index position corresponds to the position where the uncontrollable participant needs to be inserted.

[0057] In a preferred embodiment of the present invention, the following pseudocode is used to find the affected first microgroup and its corresponding index position: proceduresearch(squads,car_id) binary search maximun i that satisfies squads[i][0].y ≤ car_id.y binary search maximun j that satisfies squads[ [j].y ≤ car_id.y return[ ] end procedure In the pseudocode above, y represents the coordinates along the centerline of the road in the mixed traffic flow scenario, and squads is an ordered three-dimensional tensor about y, where the first dimension represents the microgroup ID, the second dimension represents the controllable participant ID within the microgroup, and the third dimension represents the participant's state information.

[0058] In this embodiment of the invention, two binary search operations are used to return the index position corresponding to the participant. First, the ID of the largest microgroup is found in the first dimension. Next, in the second dimension, the ID of the largest controllable participant within the microgroup is found. ,Will As a return value.

[0059] The time complexity of binary search is O(logN). This embodiment of the invention uses two binary searches, resulting in a time complexity of O(logmax{ Compared to traditional search methods, the two binary search operations used in this embodiment of the invention can quickly search for the corresponding individual in an ordered group array, reducing the complexity of the search operation.

[0060] In some preferred embodiments, the state change notification includes an exit control request from the controllable participant and an entry control request from the uncontrollable participant.

[0061] It should be noted that, in order to ensure the normal and stable operation of mixed traffic flow scenarios, both the exit control request and the join control request are verified and approved by the traffic management center.

[0062] Furthermore, preferably, step S33, updating the first micro-population at the index position according to the state change notification, includes: If the status change notification is an exit control request, then delete the controllable participant corresponding to the index position of the first microgroup; If the status change notification is a join control request, then the corresponding uncontrollable participant is inserted at the index position of the first microgroup; Update the status and index position of the participants in the first microgroup.

[0063] It should be noted that after responding to a leave control request, the status of the corresponding controllable participant will be updated to uncontrollable participant. However, if it is still in a mixed traffic flow scenario, its location will still be continuously monitored. When responding to a join control request, the status of the corresponding uncontrollable participant will be updated to controllable participant.

[0064] It should also be noted that after updating the first micro-group, the group size of the micro-group may change. Subsequent reordering of the micro-groups will be based on the changed group size. For example, if the number of controllable participants in a certain micro-group after the update is 5, the number of controllable participants in it will not change during reordering. More specifically, the reordering will only be performed between the micro-groups.

[0065] Preferably, step S34, reorganizing the updated first micro-population according to the updated occupancy rate of the first micro-population, includes: Calculate the updated first occupancy rate of the first microgroup; If the first occupancy rate is greater than the preset maximum occupancy rate threshold, then the first micro-group will be split into two second micro-groups to form a new micro-group. If the first occupancy rate is less than the preset minimum occupancy rate threshold, then the first micro-group is merged with an adjacent micro-group to form a third micro-group, and the second occupancy rate of the third micro-group is calculated. If the second occupancy rate is greater than the preset maximum occupancy rate threshold, the third micro-group is split into two fourth micro-groups to form a new micro-group; otherwise, a new micro-group is obtained based on the third micro-group.

[0066] In managing mixed traffic flow scenarios, situations may arise where new, uncontrollable participants need to be added to micro-groups. To ensure that the addition of uncontrollable participants does not disrupt the order of the micro-group and to maximize efficiency, the individual joining operation is a crucial step. When an uncontrollable participant requests to join a micro-group, the cloud will determine whether the participant meets the joining criteria. If so, it will first find the nearest index position in the squares and insert the participant at that position. Subsequently, it will check the size of the group after insertion. If the group size exceeds the specified range, the micro-group will be split into two smaller micro-groups at the median of the y-coordinate. Through the insertion and detection mechanism, the occupancy rate of the micro-group can be controlled between 50% and 100%, thereby ensuring the efficiency of micro-group control.

[0067] In some preferred embodiments, the occupancy rate is calculated based on a preset group size range. Specifically, the updated first occupancy rate of the first microgroup is calculated based on the number of controllable participants within the first microgroup and the maximum value within the preset group size range.

[0068] In a preferred embodiment, please refer to Figure 3 Upon receiving a join control request from an uncontrollable participant in the lower left corner of the left diagram, the system determines through location that this uncontrollable participant should join the first microgroup (marked in red) in the diagram. The first microgroup contains 5 controllable participants; after the uncontrollable participant joins, the first microgroup will have 6 controllable participants. In this case, the first occupancy rate is calculated to be approximately 6 / 8 ≈ 67%, which is greater than the preset minimum occupancy rate threshold of 50% and not greater than the preset maximum occupancy rate threshold of 100%. A new microgroup is then obtained directly from the first microgroup, which includes 6 controllable participants, as shown in the diagram on the right, and the process ends.

[0069] In another preferred embodiment, please refer to Figure 4 Upon receiving a join control request from an uncontrollable participant in the lower left corner of the left diagram, the system determines that this uncontrollable participant should join the first micro-group (marked in red) in the diagram. The first micro-group currently has 8 controllable participants. After the update, the first micro-group has 9 controllable participants, resulting in a first occupancy rate of 9 / 8 > 100%, which exceeds the preset maximum occupancy threshold. Next, the first micro-group is split into two second micro-groups, as shown in the right diagram, represented by red and red-white respectively, to form new micro-groups. Since the new micro-groups meet the occupancy requirements, the process ends.

[0070] Individual exit operations are just as important as individual join operations, ensuring that the orderliness and efficiency of the micro-group are not affected when a participant leaves. Specifically, this module first locates the index position of the controllable participant in the `squads` and removes all information within that index. It then checks the size of the micro-group after the exit; if the size is too small, it merges the micro-group with an adjacent group to form a larger micro-group. Next, it checks the size of the merged group again; if the merged size exceeds a specified range, it splits the group into two smaller groups at the median of the y-coordinate, similar to the individual join operation. Through exit and two detection operations, this module can also control the occupancy rate of the micro-queue between 50% and 100%.

[0071] In a preferred embodiment, please refer to Figure 5In the left diagram, the controllable participant in the upper left corner issues a withdrawal request. By locating the affected first micro-group and its index position, the participant can be removed from the first micro-group, making it an uncontrollable participant. The updated first micro-group is divided as shown in the right diagram, with participants in the first micro-group represented in red and participants leaving the micro-group represented in white. The updated occupancy rate of the first micro-group is 7 / 8 = 87.5%, which is within the normal occupancy rate range, and the process ends.

[0072] In another preferred embodiment, please refer to Figure 6 There were originally two micro-groups, represented by gray and red respectively. A participant in the top left corner issued a withdrawal control request, identifying the first affected micro-group as the gray micro-group. By deleting the participant from the gray micro-group, the updated gray micro-group's occupancy rate was 3 / 8 = 37.5%, less than the preset minimum occupancy rate threshold. Therefore, the gray micro-group was further merged with the red micro-group to obtain a third micro-group. The occupancy rate of the third micro-group was checked again. Since 7 / 8 = 87.5% is within the normal occupancy rate range, no further splitting is necessary. The third micro-group is then represented as red, forming a new micro-group, and the process ends.

[0073] As a preferred implementation, step S4 involves reordering the micro-groups at each time step, treating each reordered micro-group as a grouping control object, and performing grouping control on the participants, including: Build an initialization list at each time step; Based on the coordinates of the controllable participants in the micro-group, the micro-groups are merged and sorted one by one, and the micro-groups are added to the initialization list according to the merge and sort results; When the initialization list includes all the micro-groups, an ordered list is obtained; Based on the number of micro-groups, the ordered list is re-splitted to obtain reordered ordered micro-groups; Each of the ordered micro-groups is treated as a group control object, and group control is performed on the participants.

[0074] In managing mixed traffic flow scenarios, if overtaking or other events cause changes in the order of vehicles, the order of the squares tensor with respect to the y-coordinate will be disrupted. This invention addresses this by reordering the micro-groups at each time step to ensure effectiveness.

[0075] In a preferred embodiment of the present invention, the following pseudocode is used to reorder the micro-population to obtain an ordered micro-population: procedureupdate(squads) Initialize LIST [squads[1][j].y for j = 1: ] fori = 1: -1do listA LIST list_B [squads[i+1][j].y for j = 1: ] LIST Merge_sort(listA, listB) end for squads split LIST according to group size returnsquads end procedure In the pseudocode above, at each time step, a list LIST is first initialized. Then, a microgroup in LIST and one of the squares are merged and sorted according to the group index, gradually obtaining a large LIST with ordered y-coordinates for all controllable participants. Finally, the list is re-split according to its original size to obtain squares with ordered y-coordinates.

[0076] It should be noted that the time complexity of merge sort is O(NlogN), therefore the time complexity of the above algorithm for reordering the micro-group is O(NlogN). ).

[0077] The above scheme can dynamically adjust the positional distribution of different micro-groups in the traffic space. This real-time dynamic optimization capability enables the mixed traffic flow scenario to always maintain a near-optimal operating state, effectively cope with fluctuations in traffic demand, and improve the stability and reliability of the traffic system.

[0078] In a preferred embodiment, the present invention is simulated and verified on the SUMO platform. A mixed traffic flow on a circular road is designed, where white represents uncontrollable participants, colored represents uncontrollable participants and different micro-groups, and vehicles follow each other according to the default IDM model of the SUMO platform, using the DK2008 method to implement lane changes. At any given time, white vehicles may join a micro-group or colored vehicles may leave a micro-group, illustrated by changes in vehicle color. At t=0s, there are 13 cloud-controlled vehicles: 5 in the red micro-group at the rear of the traffic flow, 4 in the gray micro-group in the middle, and 4 in the blue micro-group at the front. There are also 9 cloud-uncontrolled vehicles. At t=3s, 2 cloud-uncontrolled vehicles join the red group, 1 cloud-controlled vehicle leaves the gray group, and 1 cloud-uncontrolled vehicle joins. The blue group shows no dynamic operation. At t=6s, 3 cloud-controlled vehicles leave the red group, 2 cloud-controlled vehicles leave the gray group, and 3 cloud-uncontrolled vehicles join the gray group. The blue group shows no dynamic operation. At t=10s, 4 cloud-controlled vehicles join the red group, 1 cloud-controlled vehicle leaves the gray group, and 1 cloud-uncontrolled vehicle joins. The blue group shows 1 cloud-controlled vehicle leaves the gray group, and 1 cloud-uncontrolled vehicle joins. SUMO simulations verify that the group dynamic management method of this invention has low computational complexity, can achieve real-time traffic flow segmentation and dynamic entry and exit, and is feasible for practical application.

[0079] The dynamic management method for hybrid traffic flow provided by the embodiments of the present invention can achieve efficient traffic flow division, maintain the compactness of micro-groups during the change of control state of traffic participants, ensure that each traffic participant can be accurately assigned to a suitable micro-group at any time, effectively reduce the computational complexity of cloud during traffic flow management, and greatly improve management efficiency and resource utilization.

[0080] This invention provides a dynamic management system for mixed traffic flow. Please refer to [link / reference]. Figure 7 The dynamic management system for the mixed traffic flow includes a participant acquisition module 11, a micro-group segmentation module 12, a micro-group reorganization module 13, and a formation control module 14, wherein: The participant acquisition module 11 is used to acquire participants in a mixed traffic flow scenario; the participants include controllable participants and uncontrollable participants; The micro-group segmentation module 12 is used to cluster the controllable participants according to a preset group size range to obtain at least one micro-group. The micro-group reorganization module 13 is used to find the first affected micro-group from the micro-groups when a status change notification is received from the participants, and to reorganize the first micro-group according to the status change notification; The formation control module 14 is used to reorder the micro-groups at each time step, treat each reordered micro-group as a formation control object, and perform formation control on the participants.

[0081] In a preferred embodiment, the micro-population segmentation module 12 includes: The gravitational potential energy calculation unit is used to establish the gravitational potential energy field among the controllable participants within the micro-group and to calculate the total gravitational potential energy of the mixed traffic flow scenario. The repulsive potential energy calculation unit is used to establish the repulsive potential energy field between micro-groups and calculate the total repulsive potential energy of the mixed traffic flow scenario. The total potential energy calculation unit is used to calculate the total potential energy of the mixed traffic flow scenario based on the total gravitational potential energy and the total repulsive potential energy. The micro-group segmentation unit is used to cluster the controllable participants according to a preset group size range, with the goal of minimizing the total potential energy, to obtain at least one micro-group.

[0082] Further, preferably, the gravitational potential energy calculation unit is specifically used for: Obtain the first equivalent mass and real-time local coordinates of the controllable participant; Calculate the gravitational potential energy between each two controllable participants based on the first equivalent mass and the real-time local coordinates; Based on the gravitational potential energy between every two controllable participants, a gravitational potential energy field is established among the controllable participants within the micro-group. The total gravitational potential energy of the mixed traffic flow scenario is calculated based on the gravitational potential energy field of each of the aforementioned micro-groups.

[0083] Preferably, the repulsive potential energy calculation unit is specifically used for: The second equivalent quality of the microgroup is obtained based on the first equivalent quality of all controllable participants within the microgroup; The geometric center of the micro-population is obtained based on the real-time local coordinates of all controllable participants within the micro-population and the second equivalent mass. Based on the second equivalent mass and the geometric center, the repulsive potential energy between every two micro-groups is calculated, a repulsive potential energy field is established, and the total repulsive potential energy of the mixed traffic flow scenario is obtained.

[0084] Preferably, the micro-population segmentation unit is specifically used for: Calculate the range of cluster numbers based on the preset group size range and the number of controllable participants; Within the range of the number of clusters, the controllable participants are clustered with the goal of minimizing the total potential energy to obtain the optimal number of clusters. Based on the clustering results corresponding to the optimal clustering number, at least one micro-population is obtained.

[0085] In a preferred embodiment, the micro-population recombination module 13 includes: A coordinate acquisition unit is used to acquire the coordinates of the participant when a status change notification is received from the participant. The location unit is used to obtain the first affected micro-group and its corresponding index position by binary search based on the coordinates. The first micro-group update unit is used to update the first micro-group at the index position according to the state change notification. The occupancy rate calculation unit is used to reorganize the updated first micro-group based on the updated occupancy rate of the first micro-group.

[0086] Further, preferably, the search and location unit is specifically used for: Based on the coordinates, the first affected microgroup is located from all the microgroups through a first binary search; Based on the coordinates and the first micro-group, the index position is found from the first micro-group through a second binary search.

[0087] Preferably, the first micro-population update unit is specifically used for: If the status change notification is an exit control request, then delete the controllable participant corresponding to the index position of the first microgroup; If the status change notification is a join control request, then the corresponding uncontrollable participant is inserted at the index position of the first microgroup; Update the status and index position of the participants in the first microgroup.

[0088] Preferably, the occupancy rate calculation unit is specifically used for: Calculate the updated first occupancy rate of the first microgroup; If the first occupancy rate is greater than the preset maximum occupancy rate threshold, then the first micro-group will be split into two second micro-groups to form a new micro-group. If the first occupancy rate is less than the preset minimum occupancy rate threshold, then the first micro-group is merged with an adjacent micro-group to form a third micro-group, and the second occupancy rate of the third micro-group is calculated. If the second occupancy rate is greater than the preset maximum occupancy rate threshold, the third micro-group is split into two fourth micro-groups to form a new micro-group; otherwise, a new micro-group is obtained based on the third micro-group.

[0089] In a preferred embodiment, the formation control module 14 is specifically used for: Build an initialization list at each time step; Based on the coordinates of the controllable participants in the micro-group, the micro-groups are merged and sorted one by one, and the micro-groups are added to the initialization list according to the merge and sort results; When the initialization list includes all the micro-groups, an ordered list is obtained; Based on the number of micro-groups, the ordered list is re-splitted to obtain reordered ordered micro-groups; Each of the ordered micro-groups is treated as a group control object, and group control is performed on the participants.

[0090] The dynamic management system for hybrid traffic flow provided by this invention can achieve efficient traffic flow segmentation, maintain the compactness of micro-groups during changes in the control state of traffic participants, and ensure that each traffic participant can be accurately assigned to a suitable micro-group at any time. This effectively reduces the computational complexity of cloud computing in traffic flow management and greatly improves management efficiency and resource utilization.

[0091] This invention also provides a dynamic management device for mixed traffic flow, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the dynamic management method for mixed traffic flow as described above. The working principles and beneficial effects of the two are one-to-one, so they will not be described in detail here.

[0092] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to perform the dynamic management method for mixed traffic flow as described above.

[0093] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they perform the dynamic management method for mixed traffic flow as described above.

[0094] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0095] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A dynamic management method for mixed traffic flow, characterized in that, include: Identify participants in mixed traffic flow scenarios; The participants include controllable participants and uncontrollable participants; Based on a preset group size range, the controllable participants are clustered to obtain at least one micro-group; When a status change notification is received from the participant, the first affected microgroup is located from the microgroup, and the first microgroup is reorganized according to the status change notification; At each time step, the micro-groups are reordered, and each reordered micro-group is regarded as a group control object, and group control is performed on the participants.

2. The dynamic management method for mixed traffic flow as described in claim 1, characterized in that, The step of clustering the controllable participants according to a preset group size range to obtain at least one micro-group includes: Establish the gravitational potential energy field among the controllable participants within the micro-group, and calculate the total gravitational potential energy of the mixed traffic flow scenario; Establish a repulsive potential energy field between micro-groups and calculate the total repulsive potential energy of the mixed traffic flow scenario. Calculate the total potential energy of the mixed traffic flow scenario based on the total gravitational potential energy and the total repulsive potential energy; Based on a preset group size range, and with the goal of minimizing the total potential energy, the controllable participants are clustered to obtain at least one micro-group.

3. The dynamic management method for mixed traffic flow as described in claim 2, characterized in that, The process of establishing the gravitational potential energy field among the controllable participants within the micro-group and calculating the total gravitational potential energy of the mixed traffic flow scenario includes: Obtain the first equivalent mass and real-time local coordinates of the controllable participant; Calculate the gravitational potential energy between each two controllable participants based on the first equivalent mass and the real-time local coordinates; Based on the gravitational potential energy between every two controllable participants, a gravitational potential energy field is established among the controllable participants within the micro-group. The total gravitational potential energy of the mixed traffic flow scenario is calculated based on the gravitational potential energy field of each of the aforementioned micro-groups.

4. The dynamic management method for mixed traffic flow as described in claim 2, characterized in that, The process of establishing the repulsive potential energy field between micro-groups and calculating the total repulsive potential energy of the mixed traffic flow scenario includes: The second equivalent quality of the microgroup is obtained based on the first equivalent quality of all controllable participants within the microgroup; The geometric center of the micro-population is obtained based on the real-time local coordinates of all controllable participants within the micro-population and the second equivalent mass. Based on the second equivalent mass and the geometric center, the repulsive potential energy between every two micro-groups is calculated, a repulsive potential energy field is established, and the total repulsive potential energy of the mixed traffic flow scenario is obtained.

5. The dynamic management method for mixed traffic flow as described in claim 2, characterized in that, The process involves clustering the controllable participants according to a preset group size range, with the goal of minimizing the total potential energy, to obtain at least one micro-group, including: Calculate the range of cluster numbers based on the preset group size range and the number of controllable participants; Within the range of the number of clusters, the controllable participants are clustered with the goal of minimizing the total potential energy to obtain the optimal number of clusters. Based on the clustering results corresponding to the optimal clustering number, at least one micro-population is obtained.

6. The dynamic management method for mixed traffic flow as described in claim 1, characterized in that, When a state change notification is received from the participant, the step of finding the affected first micro-group from the micro-group and reorganizing the first micro-group according to the state change notification includes: When a status change notification is received from the participant, the coordinates of the participant are obtained; Based on the coordinates, the first affected micro-group and its corresponding index position are obtained through binary search. Update the first microgroup at the index position according to the status change notification; Based on the updated occupancy rate of the first micro-group, the updated first micro-group is reorganized.

7. The dynamic management method for mixed traffic flow as described in claim 6, characterized in that, The step of obtaining the affected first micro-group and its corresponding index position through binary search based on the coordinates includes: Based on the coordinates, the first affected microgroup is located from all the microgroups through a first binary search; Based on the coordinates and the first micro-group, the index position is found from the first micro-group through a second binary search.

8. The dynamic management method for mixed traffic flow as described in claim 6, characterized in that, The state change notification includes a leave control request from the controllable participant and a join control request from the uncontrollable participant. Therefore, updating the first micro-group at the index position based on the state change notification includes: If the status change notification is an exit control request, then delete the controllable participant corresponding to the index position of the first microgroup; If the status change notification is a join control request, then the corresponding uncontrollable participant is inserted at the index position of the first microgroup; Update the status and index position of the participants in the first microgroup.

9. A dynamic management method for mixed traffic flow as described in claim 6, characterized in that, The step of reorganizing the updated first micro-group based on the updated occupancy rate of the first micro-group includes: Calculate the updated first occupancy rate of the first microgroup; If the first occupancy rate is greater than the preset maximum occupancy rate threshold, then the first micro-group will be split into two second micro-groups to form a new micro-group. If the first occupancy rate is less than the preset minimum occupancy rate threshold, then the first micro-group is merged with an adjacent micro-group to form a third micro-group, and the second occupancy rate of the third micro-group is calculated. If the second occupancy rate is greater than the preset maximum occupancy rate threshold, the third micro-group is split into two fourth micro-groups to form a new micro-group; otherwise, a new micro-group is obtained based on the third micro-group.

10. The dynamic management method for mixed traffic flow as described in claim 1, characterized in that, The reordering of the micro-groups at each time step, treating each reordered micro-group as a grouping control object, and performing grouping control on the participants includes: Build an initialization list at each time step; Based on the coordinates of the controllable participants in the micro-group, the micro-groups are merged and sorted one by one, and the micro-groups are added to the initialization list according to the merge and sort results; When the initialization list includes all the micro-populations, an ordered list is obtained; Based on the number of micro-groups, the ordered list is re-splitted to obtain reordered ordered micro-groups; Each of the ordered micro-groups is treated as a group control object, and group control is performed on the participants.

11. A dynamic management system for mixed traffic flow, characterized in that, include: The participant acquisition module is used to acquire participants in a mixed traffic flow scenario; the participants include controllable participants and uncontrollable participants; The micro-group segmentation module is used to cluster the controllable participants according to a preset group size range to obtain at least one micro-group. The micro-group reorganization module is used to, when receiving a status change notification from the participant, locate the first affected micro-group from the micro-groups and reorganize the first micro-group according to the status change notification; The formation control module is used to reorder the micro-groups at each time step, treat each reordered micro-group as a formation control object, and perform formation control on the participants.

12. A dynamic management device for mixed traffic flow, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the dynamic management method for mixed traffic flow as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the dynamic management method for mixed traffic flow as described in any one of claims 1 to 10.

14. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, perform the dynamic management method for mixed traffic flow as described in any one of claims 1 to 10.

Images