89 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 provides an end-to-end automatic driving track generation method and system, computer equipment and a medium, and belongs to the field of path intelligent planning, and the method comprises the steps: obtaining traffic environment three-dimensional perception information and a natural language instruction; converting the traffic environment three-dimensional perception information to obtain a structured semantic mark, and adjusting the weight of the structured semantic mark through a natural language instruction; based on the weight of the structured semantic mark, visual flow features are extracted from the structured semantic mark, and language flow features are extracted from the natural language instruction; based on a cross-modal attention mechanism, the visual flow features and the language flow features are fused, fusion features are obtained, and a simulation track is generated; real-time collision time is calculated, when the real-time collision time is larger than a collision time threshold value, the simulation track is corrected based on physical constraints and a traffic regulation library, and a corrected driving track is obtained. The automatic driving simulation track constructed by the method conforms to the intention of a user, and the system reliability and the man-machine cooperation efficiency are improved.

Multimodal large language models (MLLMs) have excellent reasoning capabilities and are used for autonomous driving applications. For real-world applications, understanding and navigating in three-dimensional (3D) space is necessary, particularly for autonomous vehicles (AVs) to make informed decisions, anticipate future states, and interact safely with the environment. An MLLM agent system includes a 3D projector model and an adapted LLM that extends understanding and reasoning capability from 2D to 3D. Another component of the MLLM agent system is development of a benchmark visual question-answering (VQA) training dataset for training the MLLM agent. The VQA tasks include scene description, traffic regulation, 3D grounding, counterfactual reasoning, decision making, and planning.

The invention discloses a question answering system and a construction method for a motor vehicle driving teaching knowledge graph, and aims to overcome the defects of knowledge coverage integrity, scene adaptability, reasoning depth and interaction naturalness in the prior art. A traffic regulation document, coach voice and short videos and vehicle-mounted real-time data are integrated through a data acquisition module to cover rules and experience knowledge, a knowledge construction module constructs a space-time dynamic knowledge graph containing static and dynamic nodes based on Dgraph, space-time association is achieved by means of GeoHash coding, real-time updating is completed through an MQTT protocol, and the time-space dynamic knowledge graph is stored through a storage module. The intelligent reasoning module calls a DoWhy model to construct an'operation, principle and result 'causal chain in combination with a physical formula so as to output deep interpretation, and the interaction module achieves multi-mode immersion teaching through speech synthesis, gesture recognition and 3D animation, dynamically optimizes knowledge pushing according to student operation data, and achieves multi-mode teaching. The comprehensiveness, the real-time performance, the scientificity and the interaction naturalness of driving teaching are improved, and the method is suitable for intelligent driving teaching scenes.

The invention provides a double-end cooperative network-on-chip flow control method and device and electronic equipment, and the method comprises the steps: receiving first flow counting information synchronously transmitted by a destination end through a rapid signal, and determining second flow counting information of a source end, the source end and the destination end are respectively a starting node and an ending node of a complete link in the network-on-chip; estimating the link state of the network-on-chip according to the first flow counting information and the second flow counting information; and controlling the flow injection rate of the source end according to the link state. According to the method, counting information synchronization of a source end and a destination end is realized by utilizing the characteristics of low cost and high speed of a control signal in the network-on-chip, so that the link state of the network-on-chip is accurately estimated, the process ensures that no obvious flow accumulation exists on a path, bandwidth resource waste caused by excessive speed limitation is avoided, and the link state of the network-on-chip is accurately estimated. Quicker and more accurate flow management is supported; and more timely and accurate flow regulation is realized.

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 discloses a highway edge calculation flow regulation and control method based on OpenHarmony, and belongs to the technical field of intelligent traffic control systems. The method comprises the following steps: traffic flow detection adopts a lightweight improved YOLOv8 model, a backbone network is replaced by an OfficientViT, a neck network is optimized by phantom convolution, a feature fusion module is enhanced by SCConv, and a dynamic non-monotonic focusing loss function is introduced; according to traffic flow prediction, a spatio-temporal feature fusion Transform model is constructed, a multi-head convolution low-rank decomposition attention mechanism is adopted to capture time dependence, spatial topological features are extracted in combination with attention graph convolution, spatio-temporal information is fused through a gating unit, and a prediction error is controlled within 1.5-3.0 times of historical standard deviation; a triple lightweight LSTM-AutoEncoder is adopted for abnormal early warning, so that the false alarm rate is reduced; the OpenHarmony distributed task scheduling is cooperated with the above modules, the variable information sign and the dynamic speed limit sign are driven to execute regulation and control, the response delay is reduced, the problem of real-time accurate regulation and control under the condition that the computing power of the edge device is limited is solved, and the traffic efficiency is improved.

The invention discloses an automatic driving vehicle driving behavior compliance simulation test method, which comprises the following steps of S1, decomposing a natural language traffic regulation into an initial premise and a constraint condition, digitalizing the initial premise and the constraint condition by utilizing measurement sequential logic, and generating a mathematical formula which can be analyzed by a machine; s2, constructing a simulation scene according to the initial premise; s3, accessing the tested automatic driving algorithm to the self-vehicle in the simulation scene, and collecting vehicle state and environment data in real time; and S4, dynamically adjusting a violation detection threshold based on the constraint condition and the current weather and road conditions, and outputting a detection result. The method is different from a traditional real vehicle testing method, and various possible scenes including extreme weather, road conditions and the like can be covered more comprehensively; different from a traditional violation detection method, the method considers the influence of road and weather factors on violation detection conditions for different test scenes, and is higher in universality.

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.

The present invention discloses a driving decision-making reasoning question-answering method and device enhanced by a traffic law knowledge graph. The method relates to the technical field of traffic scene understanding for assisted driving systems in intelligent transportation. Aimed at online simulated driving test scenarios, the method solves the semantic confusion problem of traffic diagrams under limited sample size and enhances the interpretability of traffic diagram question-answering. The method comprises: using an electronic device to receive a traffic diagram question to be answered input by a user; inputting the traffic diagram question to be answered into a trained traffic diagram driving decision-making reasoning question-answering model to output a reasoning answer; and using the electronic device to display the reasoning answer so that the user can make a driving decision by referring to the reasoning answer. The present invention ensures the accuracy of traffic diagram question-answering in the presence of semantic confusion in the sample, providing good technical support for applications such as assisted driving systems and autonomous driving in intelligent transportation scenarios.

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 invention relates to the technical field of traffic regulation and control, and discloses an AI-based global traffic adaptive regulation and control method and system, and the method comprises the steps: determining the type of information needing to be collected for a target intersection based on a current date and a current time period, and collecting the multi-dimensional information of the target intersection based on the information type; and according to the multi-dimensional information of the target intersection and a traffic control AI model which is trained to converge in advance, generating a target traffic light control parameter for the target intersection, and executing a corresponding traffic light control operation based on the target traffic light control parameter corresponding to the target intersection. And the traffic flow congestion condition and the pedestrian flow congestion condition of the target intersection are slowed down through the adjusted traffic light. Therefore, the accuracy and the reliability of the traffic light control parameters can be improved, the traffic regulation and control accuracy, the reliability, the efficiency and the convenience of the intersection are further improved, and the vehicle driving smoothness and the road safety of the intersection and related roads are improved.

The invention discloses an active speed limiting system and method for an automatic driving vehicle, which are used for solving the problem of how to enable the automatic driving vehicle to flexibly adjust the driving speed according to a real-time environment on the premise of obeying traffic laws and regulations. The active speed limiting system comprises a planner, a controller, a sensor and a high-precision map, wherein the controller, the sensor and the high-precision map are connected with the planner. The road condition of the automatic driving vehicle is sensed through the sensor, and peripheral obstacle information is generated and transmitted to the planner; map information of the autonomous vehicle is obtained from the high-precision map through a planner, risk speed limit information is calculated based on surrounding obstacle information, a driving track is generated in combination with the risk speed limit information and the map information, and the driving track is converted into a control instruction to be issued to a controller so that the controller can execute an active speed limit action based on the control instruction.

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.

The invention relates to a comprehensive inspection, management and repair method and system for an inspection well, computer equipment and a storage medium. The method comprises the following steps: acquiring a target position and a fault type of a to-be-repaired target inspection well; obtaining a starting point position of the repairing personnel, and based on the starting point position and the target position, performing multi-target inspection well path planning by adopting a genetic algorithm to obtain a target path; the target path is used for indicating the repairing personnel to pass through each target inspection well according to the optimal path; when the position information of the repairing personnel is matched with the target position, a downhole operation instruction is generated according to the fault type; the well descending operation instruction is used for indicating the repairing personnel to repair the target inspection well according to the fault type. The multi-target inspection well path planning is carried out by comprehensively considering factors such as road conditions and traffic rules through a genetic algorithm, so that the purposes of accurately positioning target inspection wells and faults, planning an optimal repair path to improve the working efficiency, ensuring that the inspection wells can be recovered to be normal in time and ensuring the stable operation of related infrastructure systems are achieved.

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 application discloses a kind of based on metro station video monitoring crowd intelligence analysis method, the method sets decomposition frequency to carry out continuous decomposition and screening to station video data, obtains screening frame element library, sets linear activation kernel and carries out confluence extraction, obtains covering characteristic value, according to covering characteristic value, element replacement is carried out to linear activation kernel, obtains replacement capture kernel;Pass through replacement capture kernel to screening frame element library is marked capture and nuclide matching, obtains net value matching kernel, according to net value matching kernel, element net value library is constructed;To element net value library is carried out identity analogy, obtains the same kind identity net value library, net value matching kernel is carried out pattern positioning and is carried out the same kind identification with the same kind identity net value library, obtains target class identification node, to target identification node is carried out location tracking and different kind analysis, obtains traffic regulation strategy;Realize the automatic detection and tracking of crowd, improve the passenger flow management efficiency of metro station.

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 present application relates to the technical field of behavior recognition, in particular to a large-scale incomplete multi-view, multi-modal scene image library construction and recognition method, comprising the following steps: deploying multiple sensors and cameras in a traffic scene, and unifying multi-modal data to the same space-time coordinate system; fusing the multi-modal data after space-time alignment, predicting the target state and updating the measurement value; based on the fused data, using the adversarial generative network under space-time constraints, dynamically generating multi-view candidate views, combining the target kinematic model to complete the missing views; fusing the target kinematic model and deep learning technology to track the cross-camera target, constructing the traffic regulation ontology library, and combining the image recognition technology to automatically identify and classify the traffic violation behavior. The present application ensures the consistency of different sensor data in time and space dimensions, avoiding data confusion and errors caused by space-time differences.

The invention discloses a vehicle driving habit forming method and device, electronic equipment and a storage medium, and relates to the field of vehicle driving, and the method comprises the steps: identifying the relevance between the process data of driving control and the vehicle state data according to the vehicle state data and the corresponding process data of driving control; analyzing the vehicle state data and the corresponding driving control process data, and marking to-be-corrected driving control process data; according to the marked to-be-corrected driving control process data, a correction intervention strategy is set; according to an intervention correction strategy, prompt or / and intervention information is output on the man-machine terminal and the driving control feedback; analyzing the vehicle state data and the process data of the corresponding driving control according to the execution of the intervention correction strategy, and evaluating the correction state of the driving control; a large driving control correction model is constructed, and data information of a traffic specification class, a vehicle operation specification class and a biological feature adaptation class is integrated into the large model.

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 technique for generating a road map particularly suitable for automatic driving AD of a vehicle is provided. A method includes the step of receiving image input data. The image input data includes acquired image data representing at least one region in which the vehicle is drivable. The method further includes the step of generating a road map based on the received image input data. The generation of the road map is performed by a trained visual base model for road map generation, in particular suitable for AD. The generated road map includes a road layout within the at least one area in which the vehicle is drivable and contextual information taking into account a local assignment of applicable traffic regulations.