324 results about "Traffic simulation" patented technology

The invention discloses a control strategy model construction method based on big data, and relates to the technical field of intelligent control, a traffic situation deduction and emergency strategy generation module uses a multi-agent traffic simulation technology, simulates a traffic situation in combination with real-time traffic data, evaluates risks and early warns potential crisis by integrating multiple factors, and provides a control strategy model for the traffic situation deduction and emergency strategy generation module. And after an early warning is received, an emergency strategy is generated by using an intelligent algorithm, the strategy is evaluated and optimized by using virtual rehearsal, a result is fed back to a management department, and a synergistic effect with other modules is achieved. Traditional traffic detection equipment data is integrated with multi-source heterogeneous data such as mobile phone signaling, shared bicycle and online hailed bicycle GPS, intelligent vehicle-mounted equipment and public traffic operation, more comprehensive and accurate information such as traffic flow, flow direction, travel behavior track and the like is provided, and rich and accurate basis is provided for traffic management decisions.

Apparatuses, systems, and techniques to retrieve a set of retrieved scenarios using at least one example scenario, to use at least one first neural network to combine at least the set of retrieved scenarios to obtain combined information, and to use at least one second neural network to infer a new scenario based at least in part on the combined information. In at least one embodiment, scenarios are retrieved from a set of real-world driving scenarios and the new scenario is used to generate a simulation of automobile traffic.

The invention discloses a large-scale urban network multi-agent traffic simulation prediction method, and relates to the technical field of traffic simulation prediction. The method comprises the following steps: constructing a multi-agent city network model; processing and analyzing traffic demand data; urban network traffic flow distribution; constructing a vehicle driving model; urban network traffic monitoring and feedback; and iterating the simulation scheme. The travel demand data is processed by receiving the travel demand, the traffic path is allocated to the vehicle agent by using the classic user balance model, the vehicle agent simulates the driving behavior according to the car-following model and the lane changing model, and data support is provided for the vehicle agent to select the path according to the traffic flow macroscopic parameters fed back by the road section agent. And the simulation precision and the prediction reliability of the traffic flow are improved by utilizing the simulation of the multi-agent.

The invention discloses an automatic driving test scene generation framework and generation method, and the method comprises the steps: a road network generator is used for obtaining a node file and an edge file generated by a multi-modal large language model based on prompt word engineering and scene description, inputting the node file and the edge file into a traffic simulation tool, and obtaining a road network file synthesized by the traffic simulation tool; the vehicle generator is used for acquiring a plurality of initial vehicle models generated by the multi-modal large language model based on prompt word engineering and scene description, inputting the initial vehicle models into a traffic simulation tool, and acquiring a vehicle model generated after the traffic simulation tool adds a path file for each initial vehicle model; and the scene generation module is used for integrating the road network file and the plurality of vehicle models, obtaining an automatic driving test scene, building a bridge for interactive use of the multi-modal large language model and a traffic simulation tool, and constructing a traffic simulation mechanism of the multi-modal large language model based on a prompt project. A customized, real, reliable and targeted automatic driving test scene can be generated.

In various examples, a traffic model including one or more traffic scenarios may be generated and / or updated based on using human feedback. Human feedback may be provided indicating a preference for various traffic scenarios to identify which scenarios in a model are more realistic. A reward model may capture the preference information and rank the realism of one or more traffic scenarios.

The invention provides a dynamic traffic flow distribution method based on multi-agent reinforcement learning, and the method achieves the dynamic optimization and real-time response of a large-scale vehicle path through a cloud-edge collaborative architecture, and comprises the steps: constructing a multi-agent traffic simulation environment, and carrying out the real-time traffic flow distribution according to the real-time traffic flow distribution. Generating an intelligent body vehicle with a random starting point through the Poisson distribution model; constructing a multi-dimensional observation vector comprising road topological coding, current road density, a neighborhood speed mean value, a target distance ratio and a congestion coefficient; adopting a near-end strategy optimization algorithm to carry out parallel strategy optimization on the multi-agent enhanced strategy network under a Ray RLlib framework; designing a multi-target reward mechanism based on path efficiency, congestion punishment and progress reward; a steering decision is generated according to the real-time observation state, and a vehicle driving route is dynamically updated through a Nash equilibrium solution of the game theory; and a cooperative emergency mechanism is triggered when the traffic jam suddenly occurs. According to the method, the problems of path convergence, response delay and secondary congestion of a traditional method are solved.

According to the urban traffic automatic simulation plug-in based on the large language model and the implementation method, after a user inputs a request for a road network and a request for vehicle routing by using a natural language, the request is transmitted into a full-process automatic simulation module, and the full-process automatic simulation module carries out simulation; the input analysis agent extracts a key value from a natural language to generate a character string in a Json format, then the character string is spliced, a prompt input simulation input construction agent containing detailed simulation information is generated, the simulation input construction agent calls a packaged tool function, a vehicle route xml file and a road network xml file are generated respectively, and the vehicle route xml file and the road network xml file are connected with the simulation input construction agent. And the simulation execution intelligent body opens the SUMO-gu i to start simulation, and returns a result through a graphical interface. According to the method, the technical complexity of traditional traffic simulation is effectively simplified, a simulation tool is promoted to be transformed from professional modeling to intelligent decision support, and an innovative technical path is provided for optimization and management of a dynamic traffic system.

The invention relates to the technical field of highway management and control, in particular to a highway hard shoulder opening management and control method based on artificial intelligence. The scheme comprises the steps of collecting traffic flow and vehicle speed in real time; transmitting the preprocessed data to a central control system through a high-speed communication network; testing and optimizing the intelligent decision algorithm by using traffic simulation software, evaluating the performance of the algorithm by simulating different traffic scenes, and adjusting parameters according to a test result; testing and optimizing the optimal strategy by using traffic simulation software, and adjusting parameters according to a test result; integrating the optimized intelligent decision algorithm into a control system of the expressway; the performance of the expressway control system is continuously monitored, the performance comprises the passing efficiency and the accident rate, and the optimal strategy for opening the hard road shoulder is optimized online. According to the scheme, road side sensing is combined with automatic road shoulder development control dynamic adjustment, and safety and passing efficiency of a road system are achieved.

The invention relates to reinforcement learning for traffic simulation. In various examples, a traffic model including one or more traffic scenes may be generated and / or updated based on the use of human feedback. Human feedback may be provided indicating preferences for various traffic scenes to determine which scenes in the model are more realistic. The reward model may capture preference information and rank the authenticity of one or more traffic scenes.

The invention discloses an urban cross-domain multi-mode network space modeling method, and belongs to the technical field of traffic simulation. In order to solve the problem that urban traffic cross-domain spatial modeling is complex, the method comprises the steps that road, hub and track BIM models are classified, traffic semantics in different BIM objects in the BIM models are recognized, and traffic elements are extracted; geometric element abstraction is carried out, spatial topology connection relations and attribute information of geometric elements are defined, and single-mode traffic network model modeling is carried out; coordinate conversion is carried out, and the relative position coordinates of the single-mode traffic network model are converted into 1984 world geodetic surveying geographic coordinates; a walking traffic network is used as an intermediate network, a walking traffic mode and transfer rules of roads, rails, buses and hubs are used as strategies, network fusion is achieved through a map matching algorithm, and a multi-mode network space is modeled; and carrying out topological structure verification on the obtained multi-mode network space. According to the invention, full-link calculation from design to simulation is realized.

The invention aims to provide a large-range urban road network intelligent management and control method based on mobile phone signaling data, and belongs to the technical field of traffic management and control. Real-time traffic flow parameters are obtained by preprocessing the mobile phone signaling data, a high-fidelity microscopic traffic simulation environment is constructed, and on the basis, the real-time traffic flow parameters are obtained; the method comprises the following steps: establishing a multi-dimensional evaluation index system containing operation safety and efficiency, constructing a macro-micro collaborative double-layer planning model, adopting a deep reinforcement learning algorithm, taking continuous-discrete mixed decision variables such as intersection signal timing and a variable lane strategy as optimization objects, carrying out strategy learning and iterative optimization through an Actor-Critic architecture, and carrying out optimization on the optimization objects. And outputting the optimal control strategy combination. According to the invention, dynamic and accurate cooperative management and control of the large-range urban road network are realized, and the traffic efficiency is remarkably improved while the operation safety is guaranteed.

The invention relates to the field of urban traffic management and supervision and the field of traffic simulation, and provides a human-vehicle interactive simulation method and system based on an improved social force model and application. The method comprises the following steps: S1, constructing an improved social force model; s2, constructing a decision-making model, wherein the decision-making model is used for determining a behavior mode when the pedestrian and the vehicle meet; and S3, giving initial basic data of pedestrians and vehicles, and performing interactive simulation on human-vehicle movement conditions by using the improved social force model and the decision model. The method can be applied to scenes where vehicles and pedestrians are crossed and mixed, such as intersections without traffic lights, including crossroads and multi-directional intersections. According to the method, the trueness of the model in a complex traffic environment is remarkably improved, and behavior decisions of pedestrians in an actual scene can be more accurately simulated, especially under the condition that potential conflicts occur between the pedestrians and vehicles; through the introduction of modular design and transfer learning, the model can quickly adapt to a dynamically changing environment.

The invention discloses a deep reinforcement learning-based cooperative control method for an expressway confluence area, and the method comprises the steps: building a LiikeSim-Python joint simulation environment, and setting a coil detector in the simulation environment to obtain the traffic flow data of the upstream and downstream of the expressway confluence area; an EM algorithm based on Gaussian mixture distribution is used as a traffic state classifier, traffic flow data of the highway confluence area are used as input, and traffic states of the highway confluence area are divided; designing a state space, an action space and a reward function; taking the state space of the highway confluence area as input, taking the actions of the variable speed-limiting intelligent agent and the ramp metering intelligent agent as output, and constructing a network model of multi-agent sharing experience under time sequence characteristics; an independent experience pool is set for each of the variable speed limit agent and the ramp metering agent, and interaction experience of the agents and the traffic simulation environment is collected with the control period as the frequency; training an agent model by using the sampled samples; and realizing cooperative control of the highway confluence area by using the trained intelligent agent model. According to the invention, the traffic travel delay of the highway confluence area can be reduced.

The invention relates to the technical field of artificial intelligence and automatic driving, and discloses an automatic driving digital twin agent system based on reinforcement learning training, which comprises an agent library construction module, a simulation and configuration module, a distributed simulation execution module, a scheduling and learning module, a strategy training module and a simulation migration module. The method comprises the following steps: constructing a modular digital twin agent library, combining to generate an urban traffic simulation scene, executing large-scale parallel simulation on a distributed computing cluster, implementing dynamic task scheduling and course learning according to an agent learning progress, and training a reinforcement learning strategy and a value network based on simulation data. And verifying the strategy model and implementing migration deployment from simulation to reality. According to the method, the training efficiency can be improved, the diversity of simulation environments is enriched, and the sim-to-real migration difficulty is reduced, so that the robustness of the strategy model is improved.

A main line traffic flow management and control optimization method based on a high-performance traffic simulation agent comprises the steps that a target area road network is selected, and a main line road section and intercommunication road section structure is constructed; a multi-scene sample set is generated through microscopic traffic simulation, and traffic operation states under different traffic requirements, speed limiting and hard shoulder open conditions are simulated; training a neural network model based on a deep learning method, and constructing an efficient traffic simulation agent by taking the target road section and upstream and downstream multilayer associated topological information as input features and taking travel time and average speed as labels; and in combination with a multi-objective optimization algorithm, taking total travel time and carbon emission as optimization objectives, and dynamically iterating to generate an optimal management and control scheme of road section speed limitation and hard road shoulder opening. According to the method, traditional low-efficiency microscopic simulation is replaced with the simulation agent, the calculation performance is remarkably improved, and collaborative optimization of the complex road network and scientific formulation of a low-carbon management and control strategy are achieved.

The invention discloses a track digital twinning real-time online deduction method and system, and belongs to the technical field of traffic simulation based on machine learning. The problem that in the prior art, a traditional traffic simulation and rail passenger flow dynamic allocation method is low in solving efficiency, and consequently the large-scale rail traffic network dynamic passenger flow allocation requirement is difficult to meet is solved. The method comprises the following steps: constructing a track road network model; generating road network passenger flow data and line shift data; further, simulation individuals of the train and the passengers are generated, path track matching based on time and space is carried out, and passenger-train dynamic traffic distribution and passenger-train interactive operation deduction are completed; according to the real-time detection data and the simulation result, dynamic line shift and passenger flow adjustment is carried out until a preset convergence condition is reached, and dynamic traffic checking is completed; and simulation is carried out to realize reduction and prediction of the passenger flow / flow direction of the whole line network. The method effectively improves the rail passenger flow dynamic distribution efficiency, and can be applied to large-scale traffic network simulation.

The invention discloses an urban traffic three-dimensional model vegetation element automatic generation method and system based on streetscape recognition, a terminal and a storage medium. The method comprises the steps of constructing a vegetation element knowledge graph, defining a vegetation type and typical attributes, directionally collecting a three-dimensional model and a multi-view image, unifying metadata and storing the metadata. Pixel-level semantic segmentation is carried out on the streetscape image, vegetation categories are identified based on transfer learning and an attention mechanism, and ROI and feature vectors are output; screening the candidate set based on ontology mapping, selecting a best matched vegetation model for the local feature vector of the recognized ROI and a pre-stored feature vector in a material library, and recording mapping; based on reference object correction, knowledge graph fusion and automatic discrimination or optimization strategies, reliable scale correction, number or position deduction and batch three-dimensional model import placement meeting ecological constraints are carried out on the vegetation ROI. According to the invention, efficient, intelligent and standardized technical support is provided for traffic simulation and urban visualization.

The invention discloses an automatic driving scene generation method and electronic equipment, and the method comprises the steps: obtaining a driving scene material used for generating an automatic driving scene, and obtaining driving scene description information used for describing the automatic driving scene according to the obtained driving scene material through employing a multi-mode large model; based on the obtained driving scene description information, generating a road network structure in an automatic driving scene by using a multi-modal large model and a traffic simulation device; based on the obtained driving scene description information, obtaining a driving scene script file used for generating an automatic driving scene by using a multi-modal large model; according to the obtained driving scene script file and the automatic driving simulator, controlling traffic facilities and road obstacles in the automatic driving scene to be displayed in the generated road network structure, and controlling traffic participants in the automatic driving scene to move in the generated road network structure so as to obtain the automatic driving scene. Therefore, the generation rate of the automatic driving scene is improved.

The invention discloses a macro-micro integrated microscopic three-dimensional simulation method and system for a composite traffic network, and relates to the technical field of traffic simulation. The method comprises the following steps: constructing a real-time linkage global dynamic traffic scene; carrying out multi-source traffic agent parameter fusion calibration; a front-end and back-end bidirectional integrated communication rendering module; and development of a composite traffic network scene reproduction analysis response dynamic visualization demonstration interaction and evaluation system and full-view simulation video stream archiving return visit analysis. On the basis of macro-micro integration of a composite traffic network, a micro three-dimensional simulation system is constructed through an improved centralized learning-distributed execution depth multi-source agent algorithm, micro simulation model parameter multi-dimensional calibration, a micro traffic flow individual interaction model and a micro traffic evaluation index calculation system; and a reliable and practical means is provided for three-dimensional simulation of urban traffic from a microscopic angle.

The invention discloses a BIM-based municipal road construction method and system, and the method comprises the steps: collecting traffic flow data, accident information and weather conditions, and generating original traffic data and traffic state data; collecting construction data; cleaning and processing the collected original traffic data and traffic state data to obtain traffic data and traffic information characteristics; generating traffic flow prediction data and an initial model framework based on the traffic data and the traffic information features; generating a construction scheme and a stage schedule by using an optimization algorithm in combination with the predicted traffic flow data and construction data; and filling the construction scheme and the stage schedule into the initial model framework to generate an initial BIM model, and generating the BIM model according to the construction data through dynamic traffic simulation. Through collection, processing and analysis of comprehensive traffic data and construction data, a construction scheme is optimized, and dynamic traffic simulation is carried out, so that the construction efficiency is remarkably improved, traffic congestion is reduced, and the construction safety is improved.

The invention provides an electric vehicle charging load analysis system based on deep learning and real-time traffic simulation. The system comprises an offline simulation deduction module, a deep neural network training module and an online simulation deduction module. An energy consumption model is constructed by collecting an electric vehicle starting toll station record, ETC door frame vehicle passing information and service area charging station data in an expressway, and offline simulation deduction is achieved. The deep neural network adopts a self-attention mechanism model, and combines a multi-head attention mechanism and time sequence coding to predict the EV charging load. The on-line simulation deduction module collects vehicle data in real time and carries out prediction based on real-time traffic simulation software. And performing weighted analysis and dynamic adjustment on simulation and deep learning prediction results through a feedback mechanism so as to improve the prediction precision. Through the distributed calculation and real-time data processing technology, mass data can be efficiently processed, accurate charging demand prediction is provided, and the method adapts to dynamic changes in different scenes.

The invention provides an ultra-large city comprehensive traffic data and intelligent research and strategy system, which establishes a multi-dimensional traffic research and strategy task through a traffic research and strategy task module, and processes the traffic research and strategy task through a traffic characteristic diagnosis module to obtain a traffic characteristic index vector rank and a candidate traffic root cause index set. The traffic traceability analysis module performs further processing to obtain main traffic root cause indexes and measure indexes, and the traffic strategy generation module outputs traffic characteristic indexes according to the main traffic root cause indexes and the measure indexes to optimize a pre-generation strategy; the traffic simulation deduction module optimizes a simulation task item distribution model generated by a pre-generation strategy according to traffic characteristic indexes to obtain a pre-selection result, and the traffic strategy evaluation module and the traffic strategy release module finally perform evaluation and release, thereby solving a problem that a single factor outputs a single execution scheme with relatively high precision. Therefore, when single execution schemes are overlapped and fused into a set of optimal executable solutions for the comprehensive traffic of the super-large city, scheme execution conflicts are easy to occur.

The invention discloses a mixed traffic scene-oriented different-intelligence network-connected vehicle collaborative decision-making method and system, and relates to the technical field of multi-vehicle collaborative decision-making, and the method comprises the specific steps: building a mixed traffic simulation environment for multi-agent reinforcement learning training; constructing a different intelligence network vehicle physical model, and performing function module configuration based on the grade of each vehicle; the different-intelligence networked vehicle physical model comprises a sensing module, a decision planning module, a control module and a communication module. A heterogeneous multi-agent deep reinforcement learning method is adopted to carry out cooperative training on the different-intelligence network vehicle simulation queue based on a mixed traffic simulation environment, and an optimal cooperative decision strategy is obtained; and deploying the optimal collaborative decision-making strategy to the different intelligence network connection vehicle queue for collaborative decision-making information generation. Through the parameter sharing and independent optimization mechanism of the high-level and low-level intelligent vehicle strategy and state value networks, hierarchical cooperation between different-intelligence vehicles is realized; and the overall traffic efficiency in the complex mixed traffic scene is improved.

The invention discloses an expressway reconstruction and extension traffic diversion method, system and device and a medium, and the method comprises the steps: obtaining multi-source dynamic traffic data, and constructing a road network origin-destination matrix through data fusion and demand deduction; a traffic flow distribution result is obtained by constructing a system optimal traffic distribution model; identifying the first congestion time period, and calculating the traffic flow exceeding the residual traffic capacity in the congestion time period to obtain the traffic flow to be shunted; solving an optimal shunting path under the target of minimizing the total travel time of the system through a hybrid intelligent algorithm to obtain an optimal shunting path scheme; and verifying the optimal shunting path scheme by using microscopic traffic simulation software, updating traffic data based on a simulation result, and carrying out iterative optimization to obtain a differentiated traffic organization scheme. According to the invention, the traffic flow passing efficiency during the highway reconstruction and extension period is effectively improved.

The invention discloses a sewage treatment plant intelligent layout method based on a genetic optimization algorithm, and the method comprises the steps: enabling a system to obtain parameters through the automatic importing and sorting of multi-source data, and completing the machine learning preprocessing; mapping the functional characteristics of the monomers and the process dependency relationship into a map structure, and realizing dynamic grouping according to a reasoning result; a multi-target adaptive algorithm and interactive visualization are adopted, and automatic arrangement of buildings and pipelines is achieved in a local range; during overall layout, an evolutionary genetic algorithm and a self-adaptive reward and punishment mechanism are introduced, and parameters of each group are globally optimized; determining road details based on external traffic simulation and future capacity expansion requirements; performing comprehensive optimization in a whole plant pipeline arrangement stage; updating the design scheme; and outputting a plurality of achievement forms. According to the method, the modification requirement can be quickly met, and the algorithm can be restarted and a new scheme can be efficiently generated only by updating parameters no matter the size of a single body, the land condition or the technological process is changed.

The invention relates to a traffic simulation agent system construction method based on a large model, and the method comprises the steps: constructing a simulation tool library, and achieving the precise evaluation and continuous optimization of a simulation result through the fusion of multi-source heterogeneous traffic data, the construction of standardized input, and the establishment of a quantitative evaluation system. A large language model is utilized to understand a natural language instruction of a user, tasks are intelligently disassembled, an execution process is planned, dependence management and parallel scheduling are carried out in combination with a directed acyclic graph, and professional tools are driven to automatically execute. And performing evaluation, problem diagnosis and adaptive re-planning on an execution result through a large language model reflection mechanism to form an understanding-planning-execution-reflection closed loop. According to the method, the problems of how to assist a user to interact with a traffic system by utilizing an agent technology driven by a large language model, reducing the technical threshold of traffic simulation software use and saving time cost and labor cost are solved, the traffic simulation use threshold is reduced, the automation and intelligence level is improved, and efficient and accurate traffic system interaction and optimization are realized.

The invention discloses a traffic simulation parameter calibration method based on GMM clustering and Bayesian optimization, and the method comprises the following steps: inputting and preprocessing data, including data collection, driving style clustering analysis and simulation environment construction; calculating simulation repetition times of the simulation parameter sample points; according to a simulation result of the simulation parameter sample point, estimating expectation and variance distribution of an objective function; and determining a next simulation parameter sampling point based on a Bayesian optimization method. The traffic simulation parameter calibration method considering the heterovariance noise is established, the accuracy of parameter calibration is improved by identifying different driving styles, the mean square percentage error is reduced from 20.2% to 3.1%, and an effective tool is provided for the accuracy of highway traffic simulation.

The invention discloses an intelligent decision-making system construction method for traffic signal control. The method comprises a model training and deployment stage and an application and evolution stage, and specifically comprises the following steps of: S1, generating a pairing training sample set of traffic state structured data and conflict-free signal control instructions based on a pre-stored road traffic conflict rule in the model training and deployment stage; utilizing the paired training sample set to supervise and finely adjust a large language model to obtain a basic model; s2, accessing the basic model into a traffic simulation environment for reinforcement learning training; and in each training step, the basic model outputs a signal control instruction according to the current traffic state, performs safety verification on the instruction according to the road traffic conflict rule, generates a safety reward signal and the like. The traffic signal intelligent decision-making system which is safe, credible, sustainable in evolution and suitable for edge independent deployment is constructed.

The invention discloses an encrypted domain name resolution protocol simulation and characterization system, and relates to the technical field of network security and network traffic analysis. The invention aims to simulate an encrypted domain name resolution process in a real network environment, collect the flow of the process and extract features to construct a data set, and ensure the quality of the generated data set through data enhancement and a data set evaluation scheme. The system comprises a traffic simulation module, a traffic representation module, a data enhancement module and a data set evaluation module. The flow simulation and characterization module simulates and encrypts domain name resolution flow and extracts a structured feature vector containing 34 side channel features; and the data enhancement and data set evaluation module is used for enhancing a feature set based on a conditional table generative adversarial network CTGAN so as to construct a feature data set which is closer to traffic in a real network environment, and ensuring that the constructed data set has engineering availability and theoretical rationality through evaluation. The system can be used for constructing a current scarce encrypted domain name resolution protocol side channel feature data set, and provides data support for related security detection and research.

This invention discloses a lane-level conflict prediction method for expressway weaving areas based on real-time traffic flow data, comprising the following steps: S1, selecting a suitable expressway weaving area as the survey location and conducting on-site investigation; S2, collecting traffic flow data and traffic conflict data for each lane, and defining thresholds for different conflict types; S3, building a traffic simulation model using the traffic parameters obtained from the survey, defining different conflict types according to the conflict thresholds obtained in step S2, and obtaining traffic conflict data for different types; S4, extracting feature variables from the data obtained in step S3, and constructing datasets for prediction models of different conflict types; S5, constructing a conflict analysis model; S6, constructing a conflict prediction model. This invention can achieve real-time lane-level traffic conflict prediction in expressway weaving areas, thereby providing more accurate lane-level conflict risk information for vehicles in each lane, helping drivers choose safer lanes and routes.