162 results about "Traffic flow modeling" patented technology

An embodiment of the invention provides an interactive type visual simulation system under the vehicle road collaborative environments.The system comprises a real traffic simulation three-dimensional model, a virtual driving vehicle, a driver-vehicle interactive simulation unit and a traffic flow model, and the traffic flow model considers driver factors and combines a vehicle starting and stop module.The system is based on the three-dimensional simulation environments, an interactive type dynamic mapping model corresponding to the virtual vehicle, different typical scene simulation and the like, the traffic flow model considering the driver behavior is designed, the behavior and the effect of a cooperative vehicle infrastructure system can be displayed to a user from multiple angles, at the same time, the acceptance degree of the driver on vehicle road collaboration certain functions and the design rationality of certain functions are analyzed, and a virtual driving environment with sense of reality and sense of immersion can be provided for the driver.

The invention relates to a test system for an automatic driving vehicle. A real vehicle data collection module is used for collecting control data; a test bench is used for generating a reaction forceaccording to the control data and scene information and obtaining state data of an automatic driving vehicle according to the reaction force; a scene model establishing module is used for establishing a traffic scene model, a traffic flow model, an automatic driving vehicle dynamics model and an environment perception sensor model and obtaining position data of the automatic driving vehicle; andan evaluation module is used for calculating a return value for evaluating the running state of the automatic driving vehicle according to the position data and the state data. By combining the test bench with a scene model comprising traffic flow data, the environment recognition capability, the dangerous condition recognition response time and the processing mode of the automatic driving vehiclecan be more truly tested, and the safety and the stability of the autonomous recognition capability under a complex traffic environment can be more truly tested.

The invention relates to a method for predicting the range influenced by an abnormal traffic event of highway, and suitable for main lines of the highway. The method comprises that A Van Aerde traffic flow model of a road is established; a target function and an extremely low error threshold are set, and the duration of the event and the longest queuing time are predict; the traffic capacities of an accident point under multiple factors are determined, the upstream flows of the accident point within different time intervals are predicted based on data of vehicle detectors, and corresponding densities are obtained; the velocity of evanescent waves, the velocity of queuing waves at corresponding time and the influence length are calculated by utilizing the traffic wave theory; the position relation among the currently estimated queuing position, upstream and downstream ramps and the vehicle detectors is determined; and the solution of the target function is determined, and the longest queuing time and the range influenced by the event are determined. Based on establishment of the Van Aerde model, the method takes influence of traffic flow change and other factors on the velocities of the waves, the practical traffic flow features can be more effectively reflected, the adaptability is higher, and the prediction accuracy can be improved.

The invention provides a traffic signal light control method and system based on vehicle queuing length measurement. Vehicle flow information is divided into steady flow and combined flow by building a city road combined traffic flow model, and actual vehicle flow information can be accurately simulated. Pixel points in an original map of a digital graph can serve as road coordinates by carrying out digital graph collecting on a road, a sampling time interval is set, digital graph information of the road is collected on a sampling position again when it is detected that a vehicle on the road does not move forward any more in a road go-through cycle, a congestion starting position is obtained, a real-time vehicle queuing length can be calculated according to the distance from the congestion starting point to a detection point by means of a vehicle queuing length computational formula, the operation state of an upstream intersection signal light is controlled according to the real-time vehicle queuing length, and accordingly upstream intersection traffic congestion caused due to the fact that the upstream intersection vehicle enters the congested road is avoided.

The invention provides a highway optimization control method which comprises the following steps of: (1) dividing a section of highway into N intervals, and selecting a space-time discrete traffic flow model to represent the intervals of the highway, wherein each interval contains an entrance ramp and an exit ramp; (2) determining the regulation rate of each ramp by setting a highway multi-ramp combination control optimization target with maximal total flow of services and shortest mean waiting time of vehicles at each entrance ramp; (3) solving the highway multi-ramp combination control optimization model by adopting an ant colony algorithm; and (4) obtaining the optimal regulation rate of each entrance ramp in each section interval by the step (3), and regulating the traffic flow of each entrance ramp in each section interval according to the calculation results. Through the invention, a control algorithm is simplified, the calculation speed is high, and the control effect is optimized.

The invention discloses a traffic flow model training method based on an attention mechanism, being characterized in that a pre-trained and fused model is applied as a building block of a deep architecture model to measure traffic data for prediction, and a pre-trained station model having a plurality of fused layer architectures is proposed, and the model takes into account traffic network structure and traffic status of each station to predict traffic speed over a network range. The traffic flow model training method captures spatial features and temporal dependencies from historical data using multiple fusion layers, and the proposed model can process missing values in input data by using a masking mechanism. Experiments are established in a real data set, and compared with other classic and most advanced models, results show that the model of the invention is superior to other models in terms of accuracy and robustness.

An embodiment generally relates to systems and methods for enhanced cellular automata (CA) models. A processing module can generate a traffic model that comprises a set of vehicles. The traffic model can be processed according to the enhanced CA model. In particular, a perceived gap between vehicles in the set of vehicles can be identified. Further, a subsequent velocity of a following vehicle can be calculated based on metrics such as a maximum velocity, the perceived gap, and various time components.

The invention discloses a high-speed traffic flow prediction method based on multi-modal fusion and a graph attention mechanism. Short-time prediction is carried out on the traffic flow of a target checkpoint road segment in a future time period through fusion of multi-modal data of a highway, including portal frame checkpoint road speed data, toll station access flow data and road segment lane information and the like. According to the method, time and space characteristics in a traffic flow model are comprehensively considered; a plurality of factors are fused in a coding mode, a model forspeed prediction is constructed by integrating methods such as a graph attention mechanism and cavity convolution, a model is constructed by applying measured data of a certain expressway section andverified, and a prediction result and a measured result have a better effect by being compared with a vehicle speed prediction method provided by the research.

The invention discloses a method for estimating city expressway traffic states based on mobile detection of smartphones, wherein a city expressway cell transmission model is built firstly, a observing network is built by adopting a smartphone to rapidly detect parameters, then a state space model based on a lighthill-whitham-richards (LWR) traffic flow model is designed, a traffic state and a boundary flux are synchronously estimated by utilizing three-step type recursive filters algorithm, then are coalesced with upstream and downstream subsection boundary flux by adopting a weighted average algorithm, and traffic parameter estimation is upgraded, thereby achieving real-time distributed estimation of city expressway network traffic state. The method for estimating the city expressway traffic states based on the mobile detection of the smartphones can collect average speed information of vehicles on any time and space positions of a loop, enables traffic estimation not to be restrained by the position of a detector, can achieve synchronization estimation of traffic density and boundary flux by designing a state-space model and a three-step recursive filter, and achieves the problem of large range expressway network traffic estimation by being coalesced with subsection boundary flux, reduces model order, and improves efficiency of algorithm.

The invention discloses a trunk road section classification method under green-wave coordinated control. According to inherent attributes of a road section and changes of traffic parameters, similarities of adjacent intersections and road sections, and constraints of traffic flow models and traffic flow density in a macroscopic fundamental diagram are utilized to divide one trunk line into a plurality of road sections, on that basis, the coordinated control is carried out; the trunk road section classification method under the green-wave coordinated control uses the road attributes in the macroscopic fundamental diagram for classifying the road section with larger changes of the trunk line traffic parameters to solve the problem that the green-wave coordinated control of the traffic trunk line is narrow in bandwidth. Furthermore, the method is based on real-time data, so that the dynamic adjustment and real-time feedback functions are achieved, and the adaptability and accuracy of the method are increased.

The invention discloses a traffic flow modeling method of an unmanned vehicle and belongs to the field of unmanned driving. The method comprises steps that on the basis of analyzing factors that affect the traffic of the expressway, a traditional traffic model based on the differential equation is established; the relation map of the number of lanes affecting the average daily traffic flow in the average period and the peak period is made; the unmanned vehicle hypothesis and the classical Gipps safety distance rule are introduced; the NaSch model is improved; the automatic driving cellular automaton traffic flow model is proposed based on the safe distance; the new control method based on the spring damper is used to analyze the cooperation between the multiple vehicles; and finally the sensitivity detection is performed by increasing the reaction time of the unmanned vehicle from 0.1s to 1s. The traffic flow modeling method of the unmanned vehicle is introduced to improve the traffic safety and solve the traffic jam.

The invention discloses a multi-ICU co-spatiotemporal hardware simulation testing system and method for an automatic driving vehicle. The testing system is integrally divided into a simulation layer,an ICU (Intelligent Control Unit) layer and a data transmission layer. The simulation layer provides a virtual environment model, a sensor model, a traffic participant model, a traffic flow model anda vehicle dynamics model of simulation testing; the ICU layer is a simulation testing object; and the data transmission layer provides a communication interface of the simulation layer and the ICU layer, software for testing monitoring and automatic testing, and a high-performance processor for ensuring the real-time performance of the whole simulation process. The testing method provides a construction method for quickly generating a virtual environment required by testing and a multi-ICU co-spatiotemporal testing method. Compared with the prior art, the testing system and method has the advantages that multiple ICUs are co-spatiotemporal, multi-stage simulation data oriented to decision planning system requirements is generated, a rapid construction method for a virtual testing scene isprovided, and the like.

The invention discloses an optimization arrangement method of a rapid road network traffic sensing network. According to the method brought forward by the invention, traffic sensing networks are arranged only at certain roads of a rapid road network for directly obtaining traffic parameters, and it is ensured that the whole system is observable; and traffic parameters of roads without the traffic sensing networks can be obtained through deduction from the obtained traffic parameters of the roads with the traffic sensing networks, a road network traffic flow model and historical data. In such a way, arrangement of the traffic sensing networks in a rapid road network can be optimized, the investment cost of road facilities is reduced, the utilization efficiency of traffic sensors is improved, an important basic guarantee is provided for traffic state estimation and ramp adjustment of a city rapid road network, and accordingly, a basis is provided for making a scheme for improving city traffic congestion.

The invention provides a road condition information monitoring method and system. The method comprises the following steps: calculating through adopting a pre-set data mining algorithm model according to a current average speed of each road section and a traffic flow model of a historical same period, so as to obtain predicated road condition information of each road section in pre-set time intervals in the future; then, transmitting the current road condition information and the predicated road condition information of a pre-set road section to a vehicle, wherein the pre-set road section comprises a driving road section of the vehicle and a road section which is arranged in a pre-set range in a manner of being separated from the driving road section; and a user can adjust an own driving route according to the corresponding current road condition information and predicated road condition information of the pre-set road section, and does not need to worry about the problem that the road section has traffic jam when driving to the certain road section.

A smart navigation mark comprises a navigation mark communication system, a navigation mark monitoring system which acquires and monitors hydrological environment information and voyage ship information and transmits the information to a coast station control center through the navigation mark communication system, and an intelligent navigation mark system which dynamically builds a traffic flow model according to the acquired information and historical information, automatically identifies surrounding rule-violation ships and ships in distress, provides offshore information service for surrounding ships and automatically conducts on-site traffic guidance for ship voyage. The coast station control center remotely controls the smart navigation mark, directly gives guidance and manages and maintenances the smart navigation mark. The smart navigation mark effectively reduces the VTS pressure. When communication in the coast station control center is not smooth, the smart navigation mark can provide on-site traffic guidance service. The smart navigation mark is of great importance to offshore traffic safety.

The invention discloses a social force-based intersection crossing type construction area traffic flow model establishing method. The method comprises the following steps of: 1, establishing a signalized intersection construction area traffic flow model; 2, carrying out data acquisition on a signalized intersection construction area; 3, building a simulation platform to simulate a real construction area traffic flow; 4, calibrating a signalized intersection construction area traffic flow mode parameter by utilizing the data acquired in the step 2; and 5, verifying the signalized intersection construction area traffic flow model by utilizing the data acquired in the step 2 and the simulation result. According to the method, the method is capable of better reflecting the heterogeneity of traffic flows. Compared with traditional micro traffic flow models, the social force-based model is more suitable for traffic flows without lane division. According to the method, an existing social force model is improved firstly, then the new model is calibrated, and the calibrated model is utilized to simulate and analyze traffic flows.

The invention provides a highway service area driving-in traffic flow modeling method, which comprises the following steps: collecting the driving-in quantity of vehiclesin a certain service area formultiple days, calculating the driving-in traffic flow change curve of the vehicles in the service area every day, and clustering the driving-in traffic flow change curve to obtain a plurality of service area driving-in traffic flow change modes; fitting the service area vehicle driving-in time distributions of different driving-in traffic flow change modes by utilizing a Gaussian mixture model toobtain driving-in quantity models of a plurality of service areas; according to the main line section traffic volume near the service area, the service area scale, and the distance between the service area and the front and rear service areas or cities, carrying out sample expansion construction on the service area driving-in quantity model to obtain a service area driving-in traffic flow model with individual characteristics of each service area.

A car following modeling method considering optimal speed memory and a rear-view effect includes the following steps: a. building a car microscopic following traffic flow model through a mathematical expression; b. simplifying the car following model; c. selecting an optimal speed function; d. according to the following model, obtaining linear stable conditions of the model, and drawing a boundary between a stable region and an unstable region of the model; e. setting a traffic scene that needs to be simulated by changing a pace car motion state; f. obtaining the initial states of all vehicles; and g. performing analogue simulation of the motion state of a following motorcade when t is larger than 0, assuming that a specific pace car changes the motion state according to a preset situation, the following motorcade running according to the following model considering optimal speed memory and the rear-view effect, investigating the motion states of all the vehicles when t is larger than 0, and obtaining a speed distribution map of the cars of the model in a selected traffic scene after updates are carried out according to a rule. The car following modeling method considering the optimal speed memory and rear-view effect can improve stability of traffic flow, and relieve traffic congestion.

The invention relates to an iterative dynamic linearization and self-learning control method of an express way traffic system, and belongs to the technical field of express way traffic control. The method comprises the following steps that (1) a spatial discrete traffic model of the express way traffic system is established; (2) the spatial discrete traffic flow model is expressed in the form a general nonlinear discrete time system; (3) a general nonlinear discrete time model is converted into a dynamic linear data model; and (4) learning control and parameter update rules of the dynamic linear data model are established. The provided LDM-AILC method can be used to process a nonlinear system needless of a known linear parameter structure, and serves as a data driving control method, and design and analysis of a controller are only dependent on I / O data. In addition, under the condition that a random initial state and a tracking object of iterative change can be repeated in a non-strict way, the provided LDM-AILC method can achieve a complete tracking performance.

A method for modeling a car-following traffic flow characteristic in an Internet of vehicles (IOV) environment comprises the following steps of: 1) modeling by using a full speed difference car-following model as an ordinary vehicle microcosmic car-following traffic flow model; 2) connected vehicle car-following behavior modeling; 3) ordinary vehicle car-following model stability analysis; 4) connected vehicle car-following model stability analysis; 5) mixed traffic flow stability analysis; 6) parameter calibration of a ordinary vehicle car-following model and a connected vehicle car-following model; 7) simulation verification of a mixed traffic flow under different IOV permeability by using the parameter-calibrated models. The method complies with the actual situation of popularization and promotion of the IOV, calibrates the parameters of the selected ordinary vehicle and connected vehicle car-following models by using actually measured traffic data, and increases the credibility of a traffic simulation verification result. The method can provide a basic basis for the design of the traffic control and driving strategy in the process of popularization of the IOV.

The invention provides a false message detection method based on a traffic flow model in vehicular ad hoc networks and aims at an attack initiated by an attacker in the network through sending a falsealarm message and forging an emergency traffic event; vehicles in the upstream and downstream road sections serve as authenticators, the local vehicle density is observed based on a vehicle-mounted sensor, a Bayesian decision model is established to calculate a posterior probability of real occurrence of the emergency event, and the false alarm message is detected; in order to reasonably take values for key parameters of the model, a traffic model is established based on a traffic flow theory, a dynamic change process of a state of the traffic flow is represented by using a differential equation, a balanced concept is defined to indicate that the emergency event is a steady state of the vehicle density in true / false two traffic modes, and a balance point derivation method is given. Experimental results show that the established traffic model can better predict the dynamic change of the traffic flow, the detection accuracy can be effectively enhanced, and meanwhile, the collusion attack resistance is remarkably enhanced.

The invention provides an intelligent vehicle in-loop simulation test method based on a mixed traffic flow model, and the method comprises the steps: building a mixed traffic flow model through a generative adversarial network and an Actor-Critic network, solving a traffic flow vehicle driving strategy through a near-end strategy optimization algorithm, and carrying out the interaction with the environment to form a vehicle driving track; through a discrimination model, the generated track being distinguished from the actual track and the retrograde motion, and a reward signal being provided for the traffic flow environment. According to the method, the values of multiple influence factors of the mixed traffic flow model are combined by utilizing a combined test method, so that the test times are reduced, and the influence on the test during the interaction of the factors is explored; according to the traffic flow model generation method based on generative adversarial imitation learning, a vehicle can obtain a decision similar to an actual traffic flow; the combined case test generation method based on the greedy algorithm can improve the test efficiency. According to the method, a good improvement effect is obtained through empirical analysis.

The invention belongs to the intelligent transportation technical field and relates to a sectional type urban road traffic state estimation method. The method of the invention includes the following steps that: (1) traffic flow detectors are located in different locations in a whole road section, and the whole road section is divided into three sub road sections, namely, an upstream road section, a midstream road section and a downstream road section; (2) the speeds of the sub road sections are calculated through using a speed-flow polynomial traffic flow model; (3) the average speed of the whole road section is calculated according to the speeds of the sub road sections; (4) the traffic state of the road is calculated according to the average speed of the whole road section; and (5) the calculation model can be extended according to the change of the number of the traffic flow detectors. With the sectional type urban road traffic state estimation method provided by the technical schemes of the invention adopted, the problem of ambiguity in a speed-flow conversion process can be solved, and the accuracy and reliability of road traffic state prediction can be effectively improved.

The invention discloses a novel expressway traffic state estimation method based on parallel computing. The method comprises a parallel computing framework and four sub-modules which are a data center module, a data unification processing module, an online traffic flow model parameter correction module and an improved Kalman filter optimization module; the data center module is used for collecting and storing historical and real-time data of a traffic detector; the data unification processing module unifies the different types of traffic data into the same format; the online traffic flow model parameter correction module is used for parameter correction of the traffic flow model; and the Kalman filter optimization module further optimizes corrected model results. The parallel computing framework brought forward by the invention is used for automatic processing of the execution sequence of the above modules. Compared with existing traffic state estimation methods based on Kalman filtering, the method of the invention has higher execution efficiency and precision, can support expressway fixed detector data of different types and has a very good application and popularization prospect.

The invention discloses an improved cellular automaton traffic flow simulation analysis method based on a geographic information system. According to the method, multi-criteria judgment, logistic regression, an improved principal component analysis method and an improved decision-making tree and kernel-based learning machine method are comprehensively used for mining and extracting the transformational rule of a cellular automaton, then the improved cellular automaton is used for conducting simulation analysis of traffic flow, and corresponding traffic flow data, geographic information data and the like are used for conducting traffic flow modeling and analysis. The method is based on a geographic information system technology and a database technology to conduct unified control and management on traffic flow information, geographic information and social information in a studied area. The method achieves integrated simulation analysis and maintenance management with diagrams and texts, comprehensive inquiry, thematic map and spatial analysis and traffic flow simulation analysis, the intelligence level and the aid decision making capacity of traffic management are improved, and the method is of certain reference significance to work study in the related fields.

The invention discloses a traffic safety risk feedback precaution system and method based on microcosmic driving. The system includes a current vehicle, a fore vehicle and a feedback precaution device; the feedback precaution device is mounted on the fore vehicle, current vehicle data and fore vehicle data are collected to serve as input signals, in combination with preset risk indexes, a precaution signal is generated, and precaution is conducted on a driver of the current vehicle. According to the traffic safety risk feedback precaution system and method, basic data is easy to obtain, risk problems under multiple conditions can be treated, the application range is wide, the driver can judge risks according to personal driving states and then adjust behaviors, the safety and comfort of driving are improved, hidden traffic safety danger of a road is reduced, the reliability and running efficiency of a road system are improved, meanwhile, the traffic safety risk feedback precaution system and method do not rely on specific parameters of a microcosmic vehicle traffic flow model, hardware implementation is easy, the cost is low, and the application range is wide.

The invention discloses a modeling method considering the influence of sub-adjacent vehicles to traffic flow time lag car-following model stability. The modeling method includes that a microscopic traffic flow model DOVM (as shown in the description) including reaction time lag is established; the influence of sub-adjacent vehicles to traffic flow is considered, and an optimal speed function V(Deltax<n>, Deltax<n>+1)=(1-p) U (Deltax<n>) + pU (Deltax<n>+1) is selected, the optimal speed function is obtained through measured data fitting, wherein 0<=p<1 / 2, and an influencing factor representing the sub-adjacent vehicles refers to U(Deltax<n>)=16.8[tanh0.0860(Deltax<n>-25)+0.913]; a new traffic flow model GDOVM is established and stability analysis is carried out, the optimal speed function is put into the microscopic traffic flow model DOVM including reaction time lag and the new traffic flow model GDOVM is obtained, and according to the critical stability conditions, the influence of the reaction time lag and the sub-adjacent vehicle influencing factors to the system stability area can be obtained.

The invention relates to an inter-vehicle interaction potential based entrance ramp traffic flow model simulation method. According to the invention, the interaction between upstream and downstream vehicles of an entrance ramp and vehicles intending to pass the entrance ramp is considered, and an inter-vehicle interaction potential based entrance ramp system traffic flow model is provided. Compared with previous models, the new model particularly considers influences imposed on decision-making of a driver for entrance ramp passage by the upstream and downstream vehicle density of the entrance ramp.

The invention discloses an optimization method for road network traffic flow based on an improved TASEP model. The method comprises the following steps of: firstly, setting the edges of the network tohave different hopping rates and conform to the Poisson distribution; then, combining the real-time flow values and the number of particles on the corresponding sides at each intersection of the roadnetwork to design path strategies of the particles and control the motions of the particles; and finally, selecting a reasonable path of particles according to the roulette algorithm. The invention aims at the complex urban traffic road network, performs abstract modeling based on methods and concepts in the field of complex networks, and then reasonably controls the particle motion under the action of the TASEP model and the path strategy to achieve the optimization of the urban road network traffic flow and relieve the congestion. The invention makes two improvements on the basis of a traditional model, and designs a reasonable path strategy, thereby reasonably controlling the motions of the particles to achieve the optimization of system flow and relieve congestion, and providing new ideas and methods for studying urban traffic flow models.

The invention discloses a non-motorized vehicle lane mixed traffic flow model construction method based on microscopic traffic simulation. The method comprises the steps of establishing a multi-lane cellular automaton model containing non-motorized vehicles and pedestrians; and establishing a traffic flow model on the basis of the multi-lane cellular automaton model. The traffic flow model constructed by the non-motorized vehicle lane mixed traffic flow model construction method for microscopic traffic simulation fuses non-motorized vehicles and pedestrians.