Collaborative optimization method and platform of green sensing robot in intelligent traffic

Abstract

The invention discloses a collaborative optimization method and platform of a green sensing robot in smart traffic, and relates to the technical field of smart traffic, and the method comprises the steps: obtaining a green sensing robot topology network; splitting the green sensing robot topology network, and determining a green sensing robot collaborative sharing topology sub-network set; obtaining a monitoring data real-time collaborative sharing topology sub-network set, carrying out real-time information entropy analysis, and carrying out computing power resource balanced allocation on the communication processing sub-unit set to obtain a configured communication processing sub-unit set; and performing real-time data sharing on the monitoring data real-time collaborative sharing topology sub-network set, and analyzing the shared data by using a data processing component to obtain a node traffic collaborative control result set. According to the invention, the technical problem of low traffic cooperative control efficiency caused by non-uniform computing power resource allocation during traffic data processing in the prior art is solved, and the technical effect of efficient and intelligent traffic cooperative control is achieved.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and in particular to a collaborative optimization method and platform for green perception robots in smart transportation. Background Art

[0002] With the acceleration of urbanization, traffic congestion is becoming increasingly serious, especially at key road nodes and intersections in cities. Traditional traffic management methods mainly rely on traffic lights, surveillance cameras and manual inspections. Although they can collect traffic data, they are difficult to respond quickly and accurately due to the lag in information collection and low analysis efficiency. Therefore, the research and development of intelligent transportation systems has gradually become the key to alleviating traffic pressure. Existing intelligent transportation technologies mostly rely on centralized data processing architectures and static data collection methods, resulting in low information flow efficiency and inability to respond to sudden traffic incidents in real time.

[0003] In addition, in traditional traffic management systems, the collection and processing of traffic data are mainly concentrated on a few fixed devices, which cannot fully cover all road conditions and have a slow response speed to data such as traffic flow and road conditions. The uneven distribution of computing resources has also exacerbated this problem. Especially when processing large amounts of dynamic data, it is difficult to balance data sharing and computing burdens, resulting in limited system processing capabilities and affecting the timeliness and accuracy of intelligent decision-making. Summary of the invention

[0004] This application provides a collaborative optimization method and platform for green perception robots in smart transportation, which is used to solve the technical problem that the existing technology has uneven distribution of computing resources when processing traffic data, resulting in low efficiency of traffic collaborative control.

[0005] In view of the above problems, this application provides a collaborative optimization method and platform for green perception robots in smart transportation.

[0006] The first aspect of the present application provides a collaborative optimization method of a green perception robot in smart transportation, the method comprising:

[0007] Green perception robots are deployed at a set of key road nodes in a target area to obtain a green perception robot topology network; based on the association relationship between the key road node sets, the green perception robot topology network is split to determine a set of green perception robot collaborative sharing topology subnetworks; the green perception robot collaborative sharing topology subnetwork set is traversed to collect real-time perception data to obtain a set of monitoring data real-time collaborative sharing topology subnetworks; real-time information entropy analysis is performed on the set of monitoring data real-time collaborative sharing topology subnetworks, and computing power resources are evenly allocated to a set of communication processing subunits corresponding to the set of monitoring data real-time collaborative sharing topology subnetworks according to the real-time information entropy set to obtain a configured set of communication processing subunits; the communication processing subunit set is used to share data in real time with the corresponding set of monitoring data real-time collaborative sharing topology subnetworks, and the data processing component of each green perception robot in the green perception robot topology network is used to analyze the received shared data to obtain a set of node traffic collaborative control results.

[0008] The second aspect of the present application provides a collaborative optimization platform for green perception robots in smart transportation, the platform comprising:

[0009] A topological network establishment module, wherein the topological network establishment module deploys green perception robots in a set of key road nodes in a target area to obtain a green perception robot topological network; a topological network splitting module, wherein the topological network splitting module splits the green perception robot topological network based on the association relationship between the key road node sets to determine a set of green perception robot collaborative sharing topological subnetworks; a data acquisition module, wherein the data acquisition module traverses the set of green perception robot collaborative sharing topological subnetworks to perform real-time perception data acquisition to obtain a set of monitoring data real-time collaborative sharing topological subnetworks; a resource balancing allocation module, wherein the resource balancing allocation module performs real-time information entropy analysis on the set of monitoring data real-time collaborative sharing topological subnetworks, and performs computing power resource balancing allocation on a set of communication processing subunits corresponding to the set of monitoring data real-time collaborative sharing topological subnetworks according to the real-time information entropy set to obtain a configured set of communication processing subunits; and a traffic collaborative control module, wherein the traffic collaborative control module uses the set of communication processing subunits to perform real-time data sharing on a corresponding set of monitoring data real-time collaborative sharing topological subnetworks, and uses the data processing component of each green perception robot in the green perception robot topological network to analyze the received shared data to obtain a set of node traffic collaborative control results.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The present application deploys green perception robots at a set of key road nodes in a target area to obtain a green perception robot topology network; splits the green perception robot topology network based on the association relationship between the key road node sets to determine a set of green perception robot collaborative sharing topology subnetworks; traverses the set of green perception robots collaborative sharing topology subnetworks to collect real-time perception data to obtain a set of monitoring data real-time collaborative sharing topology subnetworks; performs real-time information entropy analysis on the set of monitoring data real-time collaborative sharing topology subnetworks, and performs balanced allocation of computing power resources on a set of communication processing subunits corresponding to the set of monitoring data real-time collaborative sharing topology subnetworks according to the real-time information entropy set to obtain a configured set of communication processing subunits; uses the communication processing subunit set to perform real-time data sharing on the corresponding set of monitoring data real-time collaborative sharing topology subnetworks, and uses the data processing component of each green perception robot in the green perception robot topology network to analyze the received shared data to obtain a set of node traffic collaborative control results. The present invention solves the technical problem that in the prior art, when processing traffic data, there is uneven distribution of computing resources, resulting in low efficiency of traffic collaborative control. Green perception robots are deployed at key road nodes in the target area and a topological network is constructed. The network is split into collaborative shared topological sub-networks using association relationships. Real-time data collection is performed and computing resources are evenly distributed through information entropy analysis. Finally, data sharing and real-time analysis are achieved. Each green perception robot generates a node traffic collaborative control result by analyzing the shared data, thereby optimizing traffic management and decision-making, and achieving the technical effect of realizing efficient and intelligent traffic collaborative control. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a collaborative optimization method for a green perception robot in smart transportation provided in an embodiment of the present application;

[0014] Figure 2 Schematic diagram of the collaborative optimization platform structure of the green perception robot in smart transportation provided in the embodiment of the present application.

[0015] Explanation of the reference numerals: topological network establishing module 11 , topological network splitting module 12 , data acquisition module 13 , resource balanced allocation module 14 , traffic coordinated control module 15 . DETAILED DESCRIPTION

[0016] This application provides a collaborative optimization method and platform for green perception robots in smart transportation, aiming to solve the technical problem of low efficiency of traffic collaborative control caused by uneven distribution of computing resources when processing traffic data in the prior art. Green perception robots are deployed at key road nodes in the target area and a topological network is constructed. The network is split into collaborative shared topological sub-networks using association relationships. Real-time data collection is performed and computing resources are evenly distributed through information entropy analysis, ultimately achieving data sharing and real-time analysis. Each green perception robot generates node traffic collaborative control results by analyzing shared data, thereby optimizing traffic management and decision-making, and achieving the technical effect of efficient and intelligent traffic collaborative control.

[0017] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, platform, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0019] Embodiment 1, as Figure 1 As shown, the present application provides a collaborative optimization method of a green perception robot in smart transportation, the method comprising:

[0020] Step S100: deploy green perception robots at a set of key road nodes in the target area to obtain a green perception robot topology network.

[0021] In the embodiment of the present application, the key road node set refers to the traffic nodes pre-set by technical personnel in the target area according to traffic planning and needs. These nodes are usually road intersections and hubs with large traffic flow, complex traffic management or requiring special attention.

[0022] Green perception robots are deployed on the key road nodes in the target area. According to the preset key nodes, these green perception robots are installed at each key node through precise positioning and deployment to ensure coverage of key locations in the target area. Each robot is equipped with multiple sensors (such as vision, radar, temperature and humidity, etc.) to perceive the environment and traffic conditions in real time.

[0023] These green perception robots are connected with other green perception robots around them through wireless communication, mobile networks, etc., forming a green perception robot topology network.

[0024] Step S200: Based on the association relationship between the key road node sets, the green perception robot topology network is split to determine the green perception robot collaborative sharing topology sub-network set.

[0025] In an embodiment of the present application, the associated neighborhood of each node is first identified by a preset associated index, wherein the preset associated index set includes a traffic flow index, a road connectivity index, and a traffic condition consistency index. Then, the key nodes are screened to determine multiple collaborative shared topology subnetwork centers. Finally, the network is split based on these central nodes to obtain a set of multiple green perception robot collaborative shared topology subnetworks. The set includes several collaborative shared topology subnetworks, each of which is composed of multiple green perception robot nodes and can perform data sharing and collaborative control.

[0026] Furthermore, in the method provided in the embodiment of the application, based on the association relationship between the key road node sets, the green perception robot topology network is split to determine the green perception robot collaborative sharing topology sub-network set, and further includes:

[0027] According to the preset association index set, the key road node set is traversed to perform node association neighborhood identification to obtain the associated road node association neighborhood set; the key road nodes are screened according to the associated road node association neighborhood set, and based on the screening result, a collaborative shared topology sub-network center set is obtained; based on the collaborative shared topology sub-network center set, the green perception robot topology network is split to obtain the green perception robot collaborative shared topology sub-network set.

[0028] Furthermore, in the method provided in the embodiment of the application, the preset associated indicator set includes a traffic flow indicator, a road connectivity indicator and a traffic condition consistency indicator.

[0029] In an embodiment of the present application, the set of key road nodes in the target area is first analyzed, and the neighborhood association of each node is identified based on a preset set of association indicators. The preset set of association indicators includes a traffic flow indicator, a road connectivity indicator, and a traffic condition consistency indicator. The preset set of association indicators such as traffic flow, road connectivity, and traffic condition consistency is used to evaluate the association between key road nodes. Specifically, the traffic flow indicator evaluates the busyness of the road through real-time traffic monitoring data, the traffic connectivity measures the closeness between nodes by analyzing the physical connection of the road, and the traffic condition consistency considers whether the traffic conditions between different road sections are consistent. Based on these indicators, the Euclidean distance is used to calculate the association between nodes, and the smaller the distance, the higher the association. Through the Euclidean distance calculation results, nodes with high association are identified and classified as associated neighborhoods, and finally a set of associated neighborhoods of associated road nodes is obtained.

[0030] Then, based on the obtained associated road node associated neighborhood set, the key road nodes are screened to determine the central node of the collaborative shared topology subnetwork. At this time, the association coefficient is used as the screening criterion. The association coefficient is calculated from two dimensions: the number of associations and the association density of the node. The number of associations reflects the number of other nodes with strong associations in the node neighborhood, and the association density measures the closeness of the connection between the node and its neighboring nodes. By calculating the association coefficient of each node, all nodes are arranged in descending order according to the association coefficient, and the first m nodes with the largest association coefficient are selected as the central nodes of the collaborative shared topology subnetwork. These screened nodes are determined as the central set of the collaborative shared topology subnetwork.

[0031] Finally, based on the selected set of central nodes of the collaborative shared topology subnetwork, the green perception robot topology network is split by the graph segmentation algorithm to form a set of green perception robot collaborative shared topology subnetworks. The graph segmentation algorithm ensures that the green perception robots in each subnetwork can work together efficiently while maintaining appropriate connections between the subnetworks. Finally, through these steps, the obtained set of green perception robot collaborative shared topology subnetworks contains multiple local subnetworks dominated by central nodes. These subnetworks can operate independently and efficiently, and work together with other subnetworks to improve the overall efficiency and responsiveness of the intelligent transportation system.

[0032] Furthermore, the method provided in the application embodiment also includes:

[0033] From the two dimensions of association quantity and association density, the association neighborhood set of the associated road nodes is traversed to identify the association coefficients and obtain a node association coefficient set; the key road nodes corresponding to the first m node association coefficients in the node association coefficient set are taken as screening results; the green perception robots deployed at the key road nodes in the screening results are taken as a collaborative shared topology sub-network center set.

[0034] In an embodiment of the present application, the association coefficient is identified by traversing the associated neighborhood set of associated road nodes from two dimensions: the number of associations and the association density. The number of associations is the number of connections between each node and its neighboring nodes, and the association density is the closeness of the connection between the node and its neighboring nodes. When identifying the association coefficient, first, the importance of the node is judged by calculating the degree of the node (that is, the number of connections with other nodes). The higher the degree, the more important the role the node occupies in the traffic network. Next, the association density between the node and the neighboring nodes is calculated, that is, the connection strength between the node and the neighboring nodes. The nodes with higher density mean that they are more closely connected with the surrounding nodes in the network. Through the analysis of these two dimensions, a set of node association coefficients is obtained, and then sorted according to the level of the association coefficients, and the top m nodes with the highest association coefficients are selected as the screening results.

[0035] Finally, the set of collaborative sharing topology sub-network centers is determined by screening out key road nodes. These nodes will serve as central nodes, and green perception robots will be deployed on them to achieve data sharing and collaborative control between nodes. Specifically, by deploying green perception robots on these screened key nodes, multiple small sub-networks with these central nodes as the core are formed. These sub-networks will achieve real-time data sharing and traffic collaborative optimization under the collaborative work of green perception robots.

[0036] Step S300: traverse the green perception robot collaborative sharing topology sub-network set to collect real-time perception data and obtain a real-time collaborative sharing topology sub-network set of monitoring data.

[0037] In the embodiment of the present application, the green perception robot collaborative sharing topology sub-network set is first traversed to collect real-time perception data, and the initial monitoring data real-time collaborative sharing topology sub-network set is obtained. Then, it is determined whether there are missing values ​​in these initial monitoring data. If there are missing values, the interpolation filling method is used to process the missing values, so as to obtain a complete monitoring data real-time collaborative sharing topology sub-network set to ensure the accuracy and completeness of the data.

[0038] Furthermore, in the method provided in the embodiment of the application, traversing the green perception robot collaborative sharing topology sub-network set to collect real-time perception data and obtain the monitoring data real-time collaborative sharing topology sub-network set also includes:

[0039] Traverse the green perception robot collaborative shared topology subnetwork set to collect real-time perception data and obtain an initial monitoring data real-time collaborative shared topology subnetwork set; determine whether there are missing values ​​in the initial monitoring data real-time collaborative shared topology subnetwork set, and if so, interpolate and fill the missing values ​​to obtain the monitoring data real-time collaborative shared topology subnetwork set.

[0040] In the embodiment of the present application, in order to obtain real-time monitoring data, the green perception robot performs data collection tasks in each collaborative sharing topology sub-network. Each robot collects specific perception information during collection, such as traffic flow, road conditions, weather conditions, driving speed, etc. By traversing these green perception robots, preliminary monitoring data in the entire area is obtained, and an initial monitoring data real-time collaborative sharing topology sub-network set is generated.

[0041] Next, the monitoring data collected after preliminary collection needs to be checked for quality, especially to determine whether there are missing values. Missing values ​​may be caused by a variety of factors, such as signal loss, equipment failure, sensor failure, etc. Therefore, a data integrity check method is used. The specific steps include marking each data point and checking whether there are gaps in the monitoring data of each subnetwork. If a missing data point is detected, it will be marked as a missing value and prepared for the next step of processing.

[0042] When missing values ​​are found, these missing data are interpolated and filled. Interpolation is a commonly used technical method, the purpose of which is to infer the reasonable value of missing data based on the existing valid data. In this case, the most commonly used interpolation method is linear interpolation. Linear interpolation infers the value of the missing data point through the two known data points before and after. For example, suppose that at a certain moment or in a certain area, the data of a certain monitoring point is missing. The missing value is calculated through the linear relationship of the data points at the previous moment and the next moment. In this way, the missing data can be reasonably filled according to the surrounding data trends, thereby ensuring the integrity of the data.

[0043] Finally, the data set processed by interpolation filling is the real-time collaborative sharing topology sub-network set of monitoring data.

[0044] Step S400: Perform real-time information entropy analysis on the monitoring data real-time collaborative sharing topology sub-network set, and evenly allocate computing power resources to the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set based on the real-time information entropy set to obtain a configured communication processing sub-unit set.

[0045] In an embodiment of the present application, firstly, the monitoring data real-time collaborative sharing topology sub-network set is traversed to perform real-time information entropy calculation to obtain a real-time information entropy set. This process obtains information entropy by calculating the complexity and diversity of the data in each sub-network. The higher the information entropy, the more complex the data. Then, the ratio of each real-time information entropy value to the sum in the set is calculated to obtain a set of computing power resource balanced allocation coefficients. This coefficient set reflects the proportion of computing resources that should be allocated to each sub-network. The higher the information entropy, the greater the proportion of computing resources allocated to the sub-network. Finally, based on the computing power resource balanced allocation coefficient set, the corresponding communication processing sub-unit set in the monitoring data real-time collaborative sharing topology sub-network set is evenly allocated computing power resources, thereby obtaining a configured communication processing sub-unit set.

[0046] Furthermore, in the method provided in the embodiment of the application, real-time information entropy analysis is performed on the monitoring data real-time collaborative sharing topology sub-network set, and computing power resources are evenly allocated to the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set according to the real-time information entropy set to obtain a configured communication processing sub-unit set, which also includes:

[0047] The real-time collaborative sharing topology subnetwork set of monitoring data is traversed to perform real-time information entropy calculation to obtain a real-time information entropy set; any one real-time information entropy in the real-time information entropy set is respectively compared with the sum of the real-time information entropy set to obtain a computing power resource balanced allocation coefficient set; based on the computing power resource balanced allocation coefficient set, computing power resources are balanced allocated to the communication processing subunit set corresponding to the monitoring data real-time collaborative sharing topology subnetwork set to obtain a configured communication processing subunit set.

[0048] In an embodiment of the present application, the real-time collaborative sharing of the monitoring data topology sub-network set is first traversed to perform real-time information entropy calculation. Information entropy is a core concept in information theory, which is used to quantify the uncertainty of information. For the real-time monitoring data of each sub-network, the entropy value of each network node is calculated using the Shannon entropy formula. The entropy value is calculated by performing statistical analysis on the monitoring data of the node to obtain the distribution of its information volume. The calculation result is a real-time information entropy set, which includes the entropy value of each topology sub-network, representing the information complexity and uncertainty of each sub-network.

[0049] Next, the real-time information entropy set is normalized, and the computing power resource balance allocation coefficient of each sub-network is calculated. Specifically, the ratio of the entropy value of each sub-network to the total entropy value is calculated, that is, the computing power resource allocation coefficient corresponding to each sub-network is obtained by calculating the ratio of the real-time information entropy of each sub-network to the total. This method is based on the resource allocation algorithm to ensure that sub-networks with higher entropy values ​​(i.e., sub-networks with greater data complexity and processing requirements) obtain more computing resources, while sub-networks with lower entropy values ​​obtain relatively fewer resources. This method uses the measure of entropy to reflect the needs of each sub-network and allocates resources through ratios to achieve the purpose of balance.

[0050] Then, based on the above-obtained set of balanced allocation coefficients of computing power resources, computing power resources are allocated to the set of communication processing subunits corresponding to the set of monitoring data real-time collaborative sharing topology subnetworks. Through the load balancing algorithm, these balanced allocation coefficients of computing power resources are applied to the computing resource allocation of the communication processing unit. Specifically, according to the demand coefficient of each subnetwork, a certain computing power is allocated to the corresponding communication processing subunit to ensure that subnetworks with higher complexity obtain more resource support and avoid excessive concentration or dispersion of resources. This step completes the dynamic allocation of computing power resources, ensuring the rational use of system resources and optimal work efficiency.

[0051] Through the aforementioned process, a set of configured communication processing sub-units is finally obtained, that is, each communication processing sub-unit has been evenly configured in terms of computing power and can efficiently process data according to the actual needs of each topology sub-network.

[0052] Step S500: Use the communication processing sub-unit set to share the corresponding monitoring data in real-time collaborative sharing topology sub-network set, and use the data processing component of each green perception robot in the green perception robot topology network to analyze the received shared data to obtain a node traffic collaborative control result set.

[0053] In the embodiment of the present application, firstly, in the preliminary stage of the whole process, the corresponding monitoring data is shared in real time by the communication processing sub-unit set in real time collaborative sharing of the topological sub-network set. Specifically, the communication processing unit collects and shares the monitoring data in each topological sub-network. These data include information such as traffic flow, road conditions, traffic light status, vehicle speed, etc., to ensure that each green perception robot node can share and receive each other's data in real time, and provide real-time input for subsequent decision-making and control.

[0054] Next, the data processing component of each green perception robot in the green perception robot topology network, that is, the embedded computing module, receives these shared data and performs real-time data analysis. The data processing component of each node analyzes the received shared data. Each robot node will generate a node traffic collaborative control result set based on its analysis results.

[0055] Furthermore, the method provided in the application embodiment also includes:

[0056] Acquire sample sharing data and the results of traffic collaborative control of sample nodes as training data; use the training data to supervise learning of a framework built based on a feedforward neural network until the training converges to obtain a data processor; embed the data processor into the data processing component of each green perception robot in the green perception robot topology network.

[0057] In the embodiment of the present application, sample data is first obtained from the historical database, including shared data and corresponding node traffic collaborative control results. These sample data are used as training data to provide support for subsequent neural network model training. A large number of traffic data samples are stored in the historical database, covering a variety of traffic scenarios and different traffic control decisions, ensuring the diversity and representativeness of the data.

[0058] Next, the training data is used to supervise the learning of the framework built on the feedforward neural network. The feedforward neural network is a classic artificial neural network structure, which includes an input layer, a hidden layer, and an output layer. During the training process, the network gradually adjusts the weights and biases to minimize the error between the predicted results and the actual results, and finally reaches training convergence. In this process, the network learns how to map the input shared data (such as traffic flow, road status, vehicle speed, etc.) to the corresponding node traffic collaborative control results.

[0059] Once the training is completed and converged, a well-trained neural network model, the data processor, is obtained. This processor is able to process real-time shared data and generate accurate traffic cooperative control decisions for each green perception robot.

[0060] Finally, this trained data processor is embedded into the data processing component of each green perception robot in the green perception robot topology network. In this way, the green perception robot can process the shared data from its surrounding environment in real time and generate corresponding traffic collaborative control results, thereby realizing intelligent traffic management and control.

[0061] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0062] The present application deploys green perception robots at a set of key road nodes in a target area to obtain a green perception robot topology network; splits the green perception robot topology network based on the association relationship between the key road node sets to determine a set of green perception robot collaborative sharing topology subnetworks; traverses the set of green perception robots collaborative sharing topology subnetworks to collect real-time perception data to obtain a set of monitoring data real-time collaborative sharing topology subnetworks; performs real-time information entropy analysis on the set of monitoring data real-time collaborative sharing topology subnetworks, and performs balanced allocation of computing power resources on a set of communication processing subunits corresponding to the set of monitoring data real-time collaborative sharing topology subnetworks according to the real-time information entropy set to obtain a configured set of communication processing subunits; uses the communication processing subunit set to perform real-time data sharing on the corresponding set of monitoring data real-time collaborative sharing topology subnetworks, and uses the data processing component of each green perception robot in the green perception robot topology network to analyze the received shared data to obtain a set of node traffic collaborative control results. The present invention solves the technical problem that in the prior art, when processing traffic data, there is uneven distribution of computing resources, resulting in low efficiency of traffic collaborative control. Green perception robots are deployed at key road nodes in the target area and a topological network is constructed. The network is split into collaborative shared topological sub-networks using association relationships. Real-time data collection is performed and computing resources are evenly distributed through information entropy analysis. Finally, data sharing and real-time analysis are achieved. Each green perception robot generates a node traffic collaborative control result by analyzing the shared data, thereby optimizing traffic management and decision-making, and achieving the technical effect of realizing efficient and intelligent traffic collaborative control.

[0063] Embodiment 2, based on the same inventive concept as the collaborative optimization method of the green perception robot in smart transportation in the above embodiment, Figure 2 As shown, the present application provides a collaborative optimization platform for green perception robots in smart transportation. The platform and method embodiments in the present application are based on the same inventive concept. The platform includes:

[0064] A topology network establishment module 11, the topology network establishment module 11 deploys green perception robots in a set of key road nodes in a target area to obtain a green perception robot topology network; a topology network splitting module 12, the topology network splitting module 12 splits the green perception robot topology network based on the association relationship between the key road node sets, and determines a set of green perception robot collaboratively shared topology sub-networks; a data acquisition module 13, the data acquisition module 13 traverses the set of green perception robot collaboratively shared topology sub-networks to collect real-time perception data, and obtains a set of monitoring data real-time collaboratively shared topology sub-networks; a resource balancing allocation module 14, the resource balancing module 15 The balance allocation module 14 performs real-time information entropy analysis on the monitoring data real-time collaborative sharing topology sub-network set, and balances the computing resources on the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set according to the real-time information entropy set to obtain a configured communication processing sub-unit set; the traffic collaborative control module 15 uses the communication processing sub-unit set to share data with the corresponding monitoring data real-time collaborative sharing topology sub-network set in real time, and uses the data processing component of each green perception robot in the green perception robot topology network to analyze the received shared data to obtain a node traffic collaborative control result set.

[0065] Furthermore, the platform is also used to implement the following functions:

[0066] According to the preset association index set, the key road node set is traversed to perform node association neighborhood identification to obtain the associated road node association neighborhood set; the key road nodes are screened according to the associated road node association neighborhood set, and based on the screening result, a collaborative shared topology sub-network center set is obtained; based on the collaborative shared topology sub-network center set, the green perception robot topology network is split to obtain the green perception robot collaborative shared topology sub-network set.

[0067] Furthermore, the platform is also used to implement the following functions:

[0068] The preset associated index set includes a traffic flow index, a road connectivity index and a traffic condition consistency index.

[0069] Furthermore, the platform is also used to implement the following functions:

[0070] From the two dimensions of association quantity and association density, the association neighborhood set of the associated road nodes is traversed to identify the association coefficients and obtain a node association coefficient set; the key road nodes corresponding to the first m node association coefficients in the node association coefficient set are taken as screening results; the green perception robots deployed at the key road nodes in the screening results are taken as a collaborative shared topology sub-network center set.

[0071] Furthermore, the platform is also used to implement the following functions:

[0072] Traverse the green perception robot collaborative shared topology subnetwork set to collect real-time perception data and obtain an initial monitoring data real-time collaborative shared topology subnetwork set; determine whether there are missing values ​​in the initial monitoring data real-time collaborative shared topology subnetwork set, and if so, interpolate and fill the missing values ​​to obtain the monitoring data real-time collaborative shared topology subnetwork set.

[0073] Furthermore, the platform is also used to implement the following functions:

[0074] The real-time collaborative sharing topology subnetwork set of monitoring data is traversed to perform real-time information entropy calculation to obtain a real-time information entropy set; any one real-time information entropy in the real-time information entropy set is respectively compared with the sum of the real-time information entropy set to obtain a computing power resource balanced allocation coefficient set; based on the computing power resource balanced allocation coefficient set, computing power resources are balanced allocated to the communication processing subunit set corresponding to the monitoring data real-time collaborative sharing topology subnetwork set to obtain a configured communication processing subunit set.

[0075] Furthermore, the platform is also used to implement the following functions:

[0076] Acquire sample sharing data and the results of traffic collaborative control of sample nodes as training data; use the training data to supervise learning of a framework built based on a feedforward neural network until the training converges to obtain a data processor; embed the data processor into the data processing component of each green perception robot in the green perception robot topology network.

[0077] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0079] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The collaborative optimization method of green perception robots in smart transportation is characterized by: The method comprises: Deploy green perception robots at key road node sets in the target area to obtain a green perception robot topology network; Based on the association relationship between the key road node sets, the green perception robot topology network is split to determine the green perception robot collaborative sharing topology sub-network set; Traversing the green perception robot collaborative sharing topology sub-network set to collect real-time perception data, and obtaining a real-time collaborative sharing topology sub-network set of monitoring data; Performing real-time information entropy analysis on the monitoring data real-time collaborative sharing topology sub-network set, and performing balanced allocation of computing power resources on the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set according to the real-time information entropy set, to obtain a configured communication processing sub-unit set; The communication processing sub-unit set is used to share the corresponding monitoring data in real-time collaborative sharing topology sub-network set, and the data processing component of each green perception robot in the green perception robot topology network is used to analyze the received shared data to obtain a node traffic collaborative control result set.

2. The method according to claim 1, characterized in that Based on the association relationship between the key road node sets, the green perception robot topology network is split to determine the green perception robot collaborative sharing topology sub-network set, including: Traversing the key road node set according to a preset association index set to identify node association neighborhoods, and obtaining an association neighborhood set of associated road nodes; Screening key road nodes according to the associated road node associated neighborhood set, and obtaining a collaborative shared topology sub-network center set according to the screening result; The green perception robot topology network is split based on the collaborative shared topology sub-network center set to obtain the green perception robot collaborative shared topology sub-network set.

3. The method according to claim 2, characterized in that The preset associated index set includes a traffic flow index, a road connectivity index and a traffic condition consistency index.

4. The method according to claim 3, characterized in that include: From the two dimensions of association quantity and association density, traverse the association neighborhood set of the associated road nodes to identify the association coefficients and obtain a node association coefficient set; The key road nodes corresponding to the first m node association coefficients in the node association coefficient set are taken as screening results; The green perception robots deployed at key road nodes in the screening results are taken as the center set of collaborative sharing topology sub-network.

5. The method according to claim 1, characterized in that Traversing the green perception robot collaborative sharing topology sub-network set to collect real-time perception data, and obtaining a monitoring data real-time collaborative sharing topology sub-network set, including: Traversing the green perception robot collaborative shared topology sub-network set to collect real-time perception data, and obtaining an initial monitoring data real-time collaborative shared topology sub-network set; It is determined whether there are missing values ​​in the initial monitoring data real-time collaborative sharing topology sub-network set. If so, the missing values ​​are interpolated and filled to obtain the monitoring data real-time collaborative sharing topology sub-network set.

6. The method according to claim 1, characterized in that Performing real-time information entropy analysis on the monitoring data real-time collaborative sharing topology sub-network set, and performing balanced allocation of computing power resources on the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set according to the real-time information entropy set, to obtain a configured communication processing sub-unit set, including: Traversing the monitoring data real-time collaborative sharing topology sub-network set to perform real-time information entropy calculation to obtain a real-time information entropy set; Compare any one real-time information entropy in the real-time information entropy set with the sum of the real-time information entropy set to obtain a computing power resource balanced allocation coefficient set; Based on the computing power resource balanced allocation coefficient set, computing power resources are balanced allocated to the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set to obtain a configured communication processing sub-unit set.

7. The method according to claim 1, characterized in that include: Obtain sample sharing data and traffic cooperative control results of sample nodes as training data; Using the training data, supervised learning is performed on the framework built based on the feedforward neural network until the training reaches convergence, thereby obtaining a data processor; The data processor is embedded in the data processing component of each green perceptual robot in the green perceptual robot topology network.

8. The collaborative optimization platform of green perception robots in smart transportation is characterized by: The platform includes: A topology network building module, wherein the topology network building module deploys green perception robots at a set of key road nodes in a target area to obtain a green perception robot topology network; A topology network splitting module, wherein the topology network splitting module splits the green perception robot topology network based on the association relationship between the key road node sets, and determines the green perception robot collaborative sharing topology sub-network set; A data collection module, wherein the data collection module traverses the green perception robot collaborative sharing topology sub-network set to collect real-time perception data and obtain a real-time collaborative sharing topology sub-network set of monitoring data; A resource balancing allocation module, wherein the resource balancing allocation module performs real-time information entropy analysis on the monitoring data real-time collaborative sharing topology sub-network set, and performs computing power resource balancing allocation on the communication processing sub-unit set corresponding to the monitoring data real-time collaborative sharing topology sub-network set according to the real-time information entropy set, to obtain a configured communication processing sub-unit set; A traffic collaborative control module, wherein the traffic collaborative control module utilizes the communication processing sub-unit set to collaboratively share the corresponding monitoring data in real time with the topological sub-network set, and utilizes the data processing component of each green perception robot in the green perception robot topological network to analyze the received shared data to obtain a node traffic collaborative control result set.

Images