53 results about "Traffic regulation" patented technology

The invention relates to an automatic driving risk quantification method based on a conflict risk field. Comprising the steps of 1, constructing a basic risk field; step 2, under a basic risk field framework, constructing a conflict risk field by taking an ADV as a center; step 3, regarding the conflict risk field as a repulsive force acting on the ADV, and using the repulsive force to quantify the dynamic influence of the environmental elements and various TP states on the driving safety of the ADV; the method comprises the following steps: firstly, constructing a basic risk field on the basis of traffic vehicle distribution and motion characteristics, further forming a vehicle forward, lateral, backward and traffic regulation constraint multi-dimensional conflict risk field on the basis, and converting an abstract traffic conflict relationship into a computable repulsive force model; dynamic quantitative characterization of driving risks in a state dimension, a space dimension and a time dimension is realized, and continuous optimization and evolution of an end-to-end automatic driving algorithm are supported by means of a repulsive force model constructed based on a conflict risk field.

The invention discloses an automatic driving evaluation benchmark construction method, system and device, and belongs to the technical field of automatic driving evaluation. The method comprises the following steps: analyzing original traffic regulations into atomic rules, and generating candidate rule pairs with hierarchical labels; performing space-time coexistence verification on the candidate rule pair, and constructing a hierarchical rule set; converting the hierarchical rule set into a text scene description and generating a structured semantic representation, then mapping the structured semantic representation into an automatic driving simulator, rendering and capturing a multi-view image sequence, and generating high-fidelity visual scene data; constructing a multi-choice question and answer pair based on the generated high-fidelity visual scene data, and forming an evaluation data set containing different cognitive levels; and training or evaluating an automatic driving model by using the evaluation data set, and optimizing a planning strategy of the model according to an evaluation result. The technical problem of automatic driving model evaluation is solved.

The invention relates to the technical field of traffic control optimization, and discloses a traffic jam control optimization algorithm based on a regional population scale and an economic structure. The algorithm comprises the following steps: firstly, obtaining population distribution data, economic industry data and real-time traffic flow original data of a target area, and generating an area traffic characteristic representative data set through multi-dimensional clustering processing; generating a traffic regulation and control allocation instruction set based on the data set; then constructing a dynamic traffic state hierarchical optimization model containing a top layer road network stability model and a bottom layer resource cost model; and finally, determining a cooperative constraint condition of the two models, inputting an instruction set into the models, performing cross-layer iteration updating solution according to the constraint condition, and outputting an optimal traffic control strategy configuration scheme. According to the algorithm, multi-dimensional data are fused, collaborative optimization of road network stability and resource cost is realized, the accuracy and adaptability of traffic jam treatment are improved, and regional traffic jam is effectively relieved.

In various examples, machine learning models may be trained and used to determine associations between traffic control devices (e.g., traffic signs, traffic lights, etc.) and lane segments of a driving surface. The systems and methods of the present disclosure may effectively combine rule-based methods and machine-learning based methods for traffic control device to lane association. For instance, training data may be synthetically generated based on traffic regulations relating to placement of traffic lights, and machine learning models may be trained to associate traffic lights to respective lanes using the training data with ground truth generated by rules. As such, image data may not be needed for the machine learning models to predict light to lane associations. Instead, given a set of non-image features indicative of lane segment and traffic light geometry and / or semantics, the machine learning models may predict the associated lane segment for each traffic light.

The invention relates to the technical field of unmanned vehicle path planning, in particular to a path planning method and device for an unmanned vehicle and electronic equipment. The method effectively solves the problem of loss of connectivity of map narrow channels caused by a traditional fixed corrosion radius through divide-and-conquer corrosion treatment and dynamic skeleton line extraction, ensures the feasibility of path planning, and innovatively utilizes the contour extraction and reference path scanning technology to improve the accuracy of path planning. According to the method, the right-side driving traffic rule is converted into the continuous right-side channel geometric constraint, so that the planned path naturally conforms to the traffic regulations and is personified in behavior, the safe, smooth and efficient optimal path is generated while the kinematics constraint of the vehicle is strictly met, and the navigation safety and intelligence of the unmanned vehicle in the structured environment are remarkably improved.

The application discloses a scene library data authorization management system for intelligent automobile traffic regulation compliance test verification, comprising a traffic regulation compliance test application scene library platform, a terminal device, a scene library management module arranged on the terminal device and a scene library application client; the traffic regulation compliance test application scene library platform is used for responding to an access request of the terminal device, authenticating the terminal device, and sending encrypted scene library data to the terminal device that passes the authentication; the scene library management module is used for receiving and storing the encrypted scene library data, and is also used for responding to an access request of the scene library application client, authenticating the scene library application client, decrypting the encrypted scene library data, and calling the decrypted scene library data by the scene library application client that passes the authentication; and the scene library application client is used for reading the scene library data and performing simulation operation on the scene library data. The application can effectively prevent illegal access of non-authorized devices to the scene library data, and improves access security.

This invention discloses a method for accident liability determination that integrates retrieval enhancement generation and thought chain analysis. The method includes acquiring traffic accident surveillance video, extracting and preprocessing keyframes from the video to obtain a temporal image feature sequence; constructing a traffic law knowledge base and generating a retrieval query based on the temporal image feature sequence; retrieving a set of legal clauses related to the accident scenario from the knowledge base; inputting the temporal image feature sequence, the set of legal clauses, and prompts containing thought chain hints into a multimodal large language model to drive multi-step liability reasoning, ultimately generating a structured road traffic accident liability determination report. This invention accurately identifies dynamic elements and violations in complex accident scenarios, fundamentally overcoming the judgment bias problem caused by the inability of traditional rules to understand multimodal data, and achieving accurate liability determination in complex accident scenarios.

The invention provides an accident liability judgment method and device, and relates to the technical field of insurance. When the scheme is executed, accident information is firstly obtained and then input into the accident liability judgment model, so that the accident liability judgment model analyzes the accident information based on related traffic laws and regulations to obtain an accident liability pre-judgment result, a logic chain of liability pre-judgment, liability-immediate suggestions and a thinking process of the accident liability judgment model. Thus, accident liability judgment is upgraded from a traditional manual dependence mode to a standardized and intelligent processing mode, an accident liability pre-judgment result, a liability pre-judgment logic chain, liability-mediating suggestions and a model thinking process are synchronously output depending on the accurate adaptation and structural analysis capability of the model to traffic laws and regulations, and the accident liability judgment efficiency and accuracy are improved.

This invention provides a macro-micro traffic control method, device, electronic device, and storage medium based on an optimization solver, relating to the field of traffic control technology. The method includes: acquiring multi-source traffic data for a target area; calling a macro-model to determine the origin-destination demand matrix based on the multi-source traffic data; inputting the origin-destination demand matrix into a meso-model to generate traffic flow parameters; using the traffic flow parameters as input conditions for a micro-model, constructing a mixed-integer programming model based on the traffic flow parameters, solving the mixed-integer programming model based on a preset solver strategy to obtain a traffic control scheme; updating the road network operating state based on the traffic control scheme, and determining the current road network state as the optimal road network state when the deviation rate between the updated road network state and the real-time collected traffic monitoring data does not exceed a preset threshold. This invention can select an appropriate solver based on the actual problem scale, thus adapting to traffic control needs in different scenarios.

The invention relates to the technical field of traffic planning, and discloses a traffic planning path optimization method based on Beidou positioning, and the method comprises the steps: constructing a regional traffic node network based on Beidou positioning data, and generating an initial path link; according to real-time traffic flow, dynamically distributing node traffic weights, dividing a path adjustment gradient in a pre-planning stage, matching traffic parameters, and collecting dynamic traffic data; clustering the traffic parameters based on the dynamic data to generate a path adaptation parameter set; in the navigation execution stage, traffic state data are acquired in real time, target parameters are determined, and the adaptive parameter set is called to generate a traffic regulation and control instruction. The method further comprises abnormal event processing, parameter set storage calling, dynamic optimization and a user interactive adjustment mechanism. According to the method, the high-precision characteristic of Beidou positioning is utilized, multi-dimensional traffic data dynamic processing is combined, real-time accurate optimization of path planning is achieved, traffic passing efficiency and user navigation experience are improved, and the method is suitable for the field of urban traffic planning and navigation.

The application discloses an automatic driving decision system test case generation method based on adversarial counter-optimization, and aims to solve the problem that the test case generation method of the automatic driving decision system is difficult to generate test cases which can trigger the risk of the decision system and meet the requirements of engineering execution, reproducibility and demand traceability. The application uses the test requirements, interfaces, behaviors and constraints described by the SysML model of the test scene as the basis, uses offline reinforcement learning to construct a reusable offline risk evaluator, and constructs an adversarial counter-optimization target based on the vehicle trajectory and the offline risk evaluator. The disturbance parameters of the test scene are searched through adversarial counter-optimization iteration, and then the disturbance parameters are projected and checked in combination with the constraints such as vehicle dynamics, road topology, traffic regulations and multi-agent interaction rationality, so that the test scene and the test case which are high in risk, high in coverage, executable and reproducible are finally generated. The application belongs to the technical field of automatic driving.

Embodiments of the present disclosure disclose a road section traffic regulation method, system, device, equipment, medium and program product, wherein the road section traffic regulation method comprises: determining whether a first road section is congested based on a driving speed of a first vehicle detected at an entrance of the first road section; adjusting a target traffic light for controlling a driving state of a vehicle in the first road section in a case where the first road section is congested; determining whether the first road section resumes smoothness based on a driving speed of a second vehicle detected at the entrance of the first road section; and adjusting the target traffic light to a default value in a case where the first road section resumes smoothness. In this way, the congestion of the road section can be sensed in time, and the purpose of immediately relieving traffic congestion is achieved.

The invention provides a traffic law violation reminding method and system based on a multi-modal large model, and belongs to the technical field of automobile intelligent driving, the method comprises the following steps: obtaining multi-modal data of a current traffic scene, the multi-modal data of the current traffic scene comprising image data, audio data and text data; inputting the multi-modal data of the current traffic scene into a pre-trained multi-modal large model, and performing real-time reasoning and outputting a reasoning result by the pre-trained multi-modal large model; and generating traffic regulation violation reminding information according to the reasoning result. The comprehensive road scene understanding ability is constructed by fusing multi-source data such as vehicle-mounted vision, hearing, positioning and vehicle state. Compared with a traditional single-mode identification scheme, the traffic violation detection accuracy can be greatly improved in complex driving environments (such as severe weather and dense building groups), and the problems of view limitation and insufficient environmental adaptability of a single sensor are effectively solved.

The application discloses a kind of motor vehicle intelligent light adaptive control device, belong to motor vehicle active safety technical field.Device includes main control module, road condition signal acquisition unit and vehicle state acquisition unit, can reuse signal source such as vehicle event data recorder, vehicle camera, millimeter wave radar or mobile terminal camera, for vehicle event data recorder using passive optical beam splitting structure to realize light multiplexing, without affecting original imaging function.Device can be externally hung lossless installation or integrated in car machine, car computer, adapt to passenger car, commercial vehicle, motorcycle and tricycle full vehicle type.Main control module is switched according to road condition and vehicle driving state to realize high beam and low beam adaptive switching, match pluggable satellite positioning module to adapt to different regional traffic regulations, and storage capacity can be flexibly configured.Device is provided with data interface to meet law enforcement evidence requirement, vehicle data acquisition is not limited to interface form, with strong universality, low cost, can reduce night glare hazard, improve driving safety, with higher practical and commercial value.

The invention provides a self-adaptive road right decision-making method, system and equipment for an autonomous vehicle, and the method comprises the steps: obtaining road perception data, constructing a road heterogeneous graph according to the road perception data, and enabling the heterogeneous graph to comprise a plurality of agents and road nodes; according to the road heterogeneous graph, extracting a node feature vector of each agent and a node embedding vector of each road node; calculating rule violation scores between the vehicle and all other agents to obtain a score sequence; global interaction information of the vehicle is generated according to the node feature vectors of all the agents, the road node embedded vectors and the score sequence, and then the vehicle driving track of the vehicle is generated based on the global interaction information. According to the method, the problem of decision uncertainty caused by fuzziness of an existing traffic regulation in the aspect of guiding automatic driving vehicle decision in the prior art is solved.

A traffic control system, facility management device, traffic control method, and traffic control procedure are provided to manage the movement of mobile bodies in a manner that can further improve the movement efficiency of mobile bodies operating in the facility. The facility is divided into multiple zones. The traffic control system (1) includes a facility information management department (15), a traffic management department (16), and a mobile body control department. Nodes represent the locations where mobile bodies (2) move. Areas correspond to zones and are collections containing nodes as elements. The facility information management department (15) manages information about nodes and areas. Nodes with external attributes are contained as common elements in multiple areas. Nodes with intermediate attributes are contained as elements in a single area. The traffic management department (16) sorts and selects two nodes with external and intermediate attributes in the same area to set traffic rules, thereby managing traffic for multiple mobile bodies (2) in multiple adjacent zones.

The invention discloses an intersection vehicle cooperative control method based on low earth orbit satellites and reinforcement learning, and relates to the technical field of intelligent traffic and vehicle cooperative control, and the method comprises the steps: enabling a vehicle to upload the state information to a ground cooperative control center through a satellite communication terminal, a data fusion module of the control center carries out space-time alignment processing on vehicle state information, constructs an intersection traffic state vector, inputs the state vector into a multi-agent reinforcement learning model, takes traffic efficiency, safety and energy consumption as optimization targets, introduces hard constraints and soft constraints of traffic regulations, outputs a cooperative control strategy and a prediction track, and carries out cooperative control. The cooperative control strategy is issued to the vehicle through the satellite network, the suggested path is displayed to a driver through the vehicle-mounted display system, wide-area reliable communication is achieved through the low-orbit satellite, global optimization decision making is achieved through reinforcement learning, and the intersection passing efficiency and safety are effectively improved.

The application provides a kind of dendritic search enhanced automatic driving car compliance behavior induction method, belongs to the technical field of automatic driving, including 1) reading traffic regulations text, it is blocked according to paragraph structure, further subdivides using large language model to block result, obtains several traffic regulations clauses 2) constructs road traffic scene tree structure and cross-regulation clause scene semantic analysis model, forms traffic regulations knowledge base of cross-regulation clause-element coding form 3) based on driving data extraction scene element, obtain the node distribution of each element in tree structure and build query representation, match the corresponding coding clause in cross-regulation knowledge base 4) constructs behavior constraint thinking chain, generates prohibited behavior list and mandatory behavior list, guides the compliance driving of automatic driving vehicle.The application constructs road traffic scene tree structure, proposes tree search algorithm, can simultaneously retrieve universal regulations and targeted regulations, improves the accuracy of traffic regulations retrieval and behavior constraint generation.

The application provides an end-to-end automatic driving trajectory generation method, system, computer device and medium, belongs to the field of path intelligent planning, and comprises the following steps: acquiring traffic environment three-dimensional perception information and a natural language instruction; converting the traffic environment three-dimensional perception information to obtain a structured semantic label, and adjusting the weight of the structured semantic label through the natural language instruction; extracting a visual flow feature from the structured semantic label based on the weight of the structured semantic label, and extracting a language flow feature from the natural language instruction; fusing the visual flow feature and the language flow feature based on a cross-modal attention mechanism to obtain a fusion feature and generate a simulation trajectory; calculating a real-time collision time, and when the real-time collision time is greater than a collision time threshold, modifying the simulation trajectory based on a physical constraint and a traffic regulation library to obtain a modified driving trajectory. The automatic driving simulation trajectory constructed by the method conforms to the user's intention, and the system reliability and human-computer cooperation efficiency are improved.

This invention discloses a method for generating autonomous driving scenarios based on risk perception and quantitative iteration, relating to the field of autonomous vehicle simulation test scenario generation technology. The method includes: based on user test commands, retrieving information from a domain knowledge base with both semantic and topological dimensions to obtain regulatory boundaries, physical limits, and topological constraints, and injecting this information into a prompt word template; performing scenario element parsing and structured mapping to generate an initial hazardous scenario description that meets traffic regulations and generate an executable simulation scenario; when the comprehensive risk assessment value of the executable simulation scenario is less than a preset risk threshold, performing causal diagnosis and reverse reasoning of low-risk causes to generate optimization commands to guide the generation of executable simulation scenarios in the next iteration, until the comprehensive risk assessment value of the executable simulation scenario is greater than or equal to the preset risk threshold, resulting in a high-risk autonomous driving scenario. This method improves the risk level of the generated autonomous driving scenarios.

The invention discloses an Amazon commodity comment automatic collection system applying machine learning. The system comprises a data acquisition unit, an intelligent flow regulation and control unit, an anti-crawling self-healing unit and a data processing unit. The data acquisition unit is used for initiating a commodity comment data request by adopting a multi-thread scheduling and flow monitoring mechanism; and the intelligent flow regulation and control unit is used for dynamically regulating request parameters based on a reinforcement learning model and generating a self-adaptive scheduling scheme in combination with a flow fitting algorithm. According to the Amazon commodity comment automatic collection system applying machine learning, through a multi-thread scheduling and flow monitoring mechanism, a grabbing request of commodity comment data can be efficiently initiated and managed, and meanwhile, the request frequency and the concurrent number are dynamically adjusted through the intelligent flow regulation and control unit, so that optimal management of flow is realized.

This invention discloses a highway compliance behavior decision-making method based on large language model imitation learning, relating to the field of autonomous driving technology. It includes: S1: Extracting traffic regulations and expert driving trajectories to construct a compliance instruction dataset, and combining kinematic safety masks to correct potentially dangerous actions; S2: Obtaining a law-enhanced large language model through supervised fine-tuning and hyperparameter optimization; S3: Inputting the environmental state vector into multi-branch parallel decision processing, outputting action Q-values ​​by a deep Q-network, outputting compliance scores by the law-enhanced large language model, and outputting dynamic efficiency and safety weights by the SE-Net mechanism; S4: Performing multi-source weighted fusion of Q-values ​​and compliance scores, selecting the optimal action with the highest comprehensive score for execution; S5: Monitoring and controlling rounds through a composite termination criterion. This invention achieves a dynamic balance between driving safety and traffic efficiency, effectively suppresses model illusions, and improves compliance and robustness in complex scenarios.

The invention discloses an intelligent traffic management system based on space-time sequence characteristics, and relates to the technical field of intelligent traffic management. Wherein the data fusion and space-time sequence management module is used for collecting multi-dimensional traffic data in real time and carrying out data preprocessing; the space-time causal chain modeling and traceability analysis module is used for carrying out space-time causal chain modeling, evaluating the causal intensity of the road event and carrying out a causal regulation decision; the traffic state prediction and intelligent regulation and control module is used for predicting traffic states and comprehensively analyzing traffic regulation and control requirements; the anomaly detection and self-adaptive optimization module is used for evaluating traffic anomaly and implementing self-adaptive traffic regulation and control measures; the intelligent feedback and self-evolution module is used for comprehensively analyzing regulation and control income feedback and automatically implementing an optimization strategy; the problem that in a complex traffic environment, due to superposition of various tiny traffic abnormities, traffic event causal chain intelligent traceability is difficult to automatically carry out, and consequently traffic control is not timely is solved.

Embodiments of the present disclosure disclose a method and device for controlling traffic progress. A specific embodiment of the method comprises: obtaining current traffic and current ranking of each to-be-regulated commodity corresponding to a target condition, the current traffic representing the cumulative traffic of the to-be-regulated commodity from an initial time to a current time; determining an increment total amount of the traffic of each to-be-regulated commodity based on the current traffic and the current ranking of each to-be-regulated commodity and a pre-determined traffic regulation factor of the current time; determining an increment component of the traffic of each to-be-regulated commodity based on the increment total amount and a pre-determined increment distribution weight, the increment distribution weight being positively correlated with a click-through rate and a conversion rate of the to-be-regulated commodity; and adjusting the ranking of each to-be-regulated commodity based on a pre-determined correspondence between the traffic increment and the commodity ranking and the increment component of each to-be-regulated commodity. The method combines the feature attributes of commodities to distribute traffic, thereby improving the pertinence and accuracy of traffic progress control.

This invention provides an information management device, a traffic control system, a traffic control method, and a traffic control procedure for managing the movement of mobile bodies operating within a facility in a manner that can further improve the movement efficiency of mobile bodies. In the traffic control system (1), the facility information management unit (15) of the information management device manages information from an application map, which includes: a first vertex representing a first region consisting of a set of nodes representing multiple locations within a first spatial range of the facility; a second vertex representing a second region consisting of a set of nodes representing multiple locations within a second spatial range that partially overlaps with the first spatial range; and an edge connecting the first vertex and the second vertex, representing a common region consisting of a set of common nodes representing one or more locations within the partially overlapping range, and which are collectively contained within the first and second regions. The traffic management unit (16) generates instructions for mobile bodies (2) moving within the facility based on the information from the application map.

The invention discloses a multi-source sensing traffic abnormal event detection method and system, and relates to the technical field of traffic abnormal detection.The method comprises the steps that synchronous data acquisition is executed at a multi-mode sensing array of a target intersection, and a multi-mode spatio-temporal data stream is obtained; carrying out traffic abnormity identification, and outputting a traffic abnormity event; traffic behavior backtracking is carried out, and a historical trajectory flow is obtained; performing event evolution trend prediction, and outputting a space-time influence vector; carrying out traffic influence range framing; generating a real-time traffic regulation and control intervention strategy by taking the traffic influence range as a dynamic constraint; and performing signal control real-time optimization and regional road network collaborative scheduling by adopting a real-time traffic regulation and control intervention strategy. According to the method and the device, the technical problems of insufficient traffic abnormal event detection accuracy and traffic regulation intervention lag in the prior art are solved, and the technical effects of realizing accurate detection of traffic abnormal events and real-time traffic regulation and control and improving intelligence and high efficiency of traffic management are achieved.

The present invention relates to a traffic law violation monitoring system comprising: a sensor unit including a camera and a LiDAR; a preprocessing unit for preprocessing sensor data output from the camera and the LiDAR of the sensor unit; an object detection unit for detecting an object from the data preprocessed by the preprocessing unit; a bad weather detection unit for determining bad weather by using object detection result data output from the object detection unit; an object tracking unit for tracking the object detected by the object detection unit, wherein the object is tracked by using bad weather determination result data from the bad weather detection unit; an unexpected situation determination unit for determining whether there is an unexpected situation, by using object tracking result data output from the object tracking unit; and a traffic law violation determination unit for determining whether there is a traffic law violation for the unexpected situation determined by the unexpected situation determination unit.

In various examples, machine learning models can be trained and used to determine mappings between traffic control devices (e.g., traffic signs, traffic lights, etc.) and lane segments of a road surface. The systems and methods of this disclosure can effectively combine rule-based and machine learning-based methods for mapping traffic control devices to lanes. For example, training data based on traffic regulations regarding the placement of traffic lights can be synthetically generated, and machine learning models can be trained to map traffic lights to the respective lanes using the training data with the ground truth generated by rules. Therefore, image data may not be required for the machine learning models to predict traffic light-to-lane mappings.Instead, if a set of non-image features is given that specify the geometry and / or semantics of the lane segment and the traffic light, the machine learning models can predict the associated lane segment for each traffic light.

The application provides a traffic signal lamp intelligent regulation system, and relates to the technical field of traffic regulation.The system comprises a traffic information collection unit and an upper computer software system;by fusing modern frontier technologies such as the Internet of Things, big data and geomagnetic field measurement, and combining scientific theories such as automatic control theory, operations research and artificial intelligence, a traffic signal lamp self-adaptive control system based on period time expansion is constructed, and the green light release time is automatically adjusted according to the real-time arrival condition of the traffic flow at the intersection.

This invention discloses a method, system, and device for constructing an autonomous driving evaluation benchmark, belonging to the field of autonomous driving evaluation technology. The method includes parsing original traffic regulations into atomic rules to generate candidate rule pairs with hierarchical labels; verifying the spatiotemporal coexistence of the candidate rule pairs to construct a hierarchical rule set; converting the hierarchical rule set into a textual scene description and generating a structured semantic representation, then mapping it to an autonomous driving simulator to render and capture multi-view image sequences, generating high-fidelity visual scene data; constructing multi-choice question-answer pairs based on the generated high-fidelity visual scene data to form an evaluation dataset containing different cognitive levels; using the evaluation dataset to train or evaluate an autonomous driving model, and optimizing the model's planning strategy based on the evaluation results. This invention solves the technical problem of autonomous driving model evaluation.