28 results about "Local road" patented technology

The invention relates to the technical field of intelligent traffic, in particular to a local road network flow change prediction method under the influence of traffic events. Comprising the steps of generating a high-quality mixed data set, constructing a road network dynamic graph structure fused with traffic event characteristics, constructing and training an end-to-end space-time prediction model based on self-adaptive dynamic partitioning and real-time data closed-loop and online rolling prediction. Through an innovative data generation strategy of'historical data calibration + high-fidelity traffic event simulation ', a large-scale, high-density, accurate-label and consistent-physical-significance'traffic event-traffic flow' mixed space-time synchronization data set is obtained, and the data bottleneck problem of road network flow prediction under traffic events is effectively solved. And a solid data foundation is laid for training and verification of a complex prediction model.

The invention provides a method for detecting vehicles retained in a highway section, and relates to the technical field of data processing, and the method comprises the steps: obtaining multi-source vehicle passing data in a target space-time scene, and enabling the multi-source vehicle passing data to be fused with each other through a vehicle identifier, and obtaining vehicle track data; constructing a candidate road network topology according to the vehicle trajectory data, and identifying abnormal road sections and abnormal events in the candidate road network topology; optimizing the candidate road network topology according to an identification result to obtain a local road network topology; selecting a target detection time window according to the to-be-detected time, and determining candidate remaining vehicles, missing detection vehicles and accident remaining vehicles of the to-be-detected road section in the target detection time window; and according to the candidate reserved vehicles, the missed vehicles and the accident retained vehicles, determining final reserved vehicles. By adopting the method for detecting the retained vehicles on the highway section, the road network topology can be dynamically updated, the retained vehicles are detected under the updated road network topology, and the accuracy of detecting the retained vehicles on the highway section is improved.

The invention discloses an autonomous positioning method and terminal equipment, and the method comprises the steps: obtaining a first observation position of a mobile body in a world coordinate system at a current moment, the first observation position being determined according to a positioning signal of a positioning sensor of the mobile body at the current moment; matching the first observation position with local road information in a road network map to obtain a target road point where the mobile subject is currently located, the target road point being a projection point of the first observation position in the road network map; calculating road network observation noise at the current moment by taking the position of the target road point as road network observation quantity according to the spatial network attribute information of the target road point; and according to the road network observation noise, determining an estimated position of the mobile body in the world coordinate system at the current moment so as to update the state of the mobile body according to the estimated position.

The application discloses a kind of based on transfer learning's city road network detectorless section flow real-time estimation method, belong to intelligent transportation system field.The method of the application includes city local road network similarity evaluation step and model transfer learning step, city local road network similarity evaluation step is by to the multi-dimension road network characteristics of influence road section flow quantitative analysis and weight assignment, establishes similarity evaluation system, to find the detector road network similar to the detectorless road section road network, model transfer learning step with the detectorless road section road network needing to be estimated as transfer learning target field, with the detector road network found by similarity evaluation system as source field, using fine-tuning method carries out the transfer learning of flow estimation model, to complete the flow real-time estimation of no data road section;The application fully excavates the influence law of city road network to flow, realizes high-precision flow estimation of no data road section with a brand-new data-driven thought.

This invention relates to an autonomous navigation method for unstructured environments based on multi-level trajectory prediction and dynamic spatiotemporal risk assessment, belonging to the field of intelligent vehicles and autonomous driving technology. The method includes the following steps: S1: Extracting the current state of the vehicle, the state of surrounding vehicles, and local road network topology information based on sensor and map data; S2: Constructing a short-term kinematic prediction model based on CTRV; S3: Constructing a background vehicle topology intent assessment model based on the joint weights of map features and motion features; S4: Predicting the long-term trajectory of the background vehicle based on topology intent and target pose; S5: Constructing a dynamic spatiotemporal risk field to identify vehicles in hazardous environments; S6: Constructing a local trajectory planning model based on the dynamic risk assessment results and target task constraints; S7: Constructing an LQR controller that combines feedforward-feedback tracking and continuous TTC monitoring, and realizing vehicle navigation control based on the local trajectory planning results.

The invention discloses a road network crack repairing method based on federated learning, and belongs to the technical field of road network repairing. In order to solve the problems of data islands, privacy leakage risks, poor strategy adaptability and the like in existing road network fracture repair, the method constructs a federated decision architecture comprising local decision nodes, a federated decision center and an environment sensing module, generating a local repair strategy set through multi-objective optimization; the federation decision center integrates the local strategies to form a global restoration strategy pool, and a global optimal restoration strategy set is generated through multi-objective optimization; and the global strategy is dynamically adjusted in combination with real-time data of the environment sensing module and then is issued to the restoration execution unit. According to the method, multi-participant collaborative decision-making is realized on the premise of protecting data privacy, conflict targets are balanced through multi-target optimization, decision-making quality is continuously optimized by means of real-time dynamic adjustment and closed-loop learning, and road maintenance efficiency and quality are remarkably improved.

The application discloses a vehicle positioning method and device, electronic equipment and computer storage medium. The vehicle positioning method comprises the following steps: performing road perception processing on a collected target image to obtain a road center point in a vehicle coordinate system; performing projection processing on the road center point according to a vehicle trajectory to obtain current local road information of the vehicle; performing matching processing on the current local road information and each local road information in a positioning area of the vehicle; and determining a road center point in target local road information matched with the current local road information in the positioning area as a target position of the vehicle. In this way, the positioning accuracy of vehicle position information can be improved.

The utility model provides a weep hole cleaning device, which relates to the technical field of bridge maintenance equipment and specifically comprises a suction assembly, a collection assembly and a negative pressure mechanism, the negative pressure generating piece generates high-speed airflow and is connected to the suction pipe through the negative pressure amplifying piece, so that the high-speed airflow facing the containing space is generated in the suction pipe, negative pressure is formed at the end, away from the collecting assembly, of the suction pipe, the suction pipe is inserted into the water drainage hole, and the suction pipe can suck deposits in the water drainage hole into the suction pipe; the negative pressure amplification piece can increase the flow speed of the air flow so as to further improve the strength of the generated negative pressure and ensure that the suction pipe can smoothly suck the deposits into the containing space, so that the weep hole is cleaned, the cleaning efficiency is high, the cleaning effect is good, the pipeline is not prone to being damaged, the deposits can be collected, and the practicability is high. And environmental pollution caused by the fact that deposits easily fall into local roads or water source protection areas again is avoided.

The invention discloses a pavement disease data generation method and device and electronic equipment. The method comprises the following steps: acquiring an aerial expressway pavement image and a local pavement disease area image; performing lane line identification on the aerial expressway surface image to obtain a point set of lane lines; according to the point set of the lane line, selecting a to-be-mapped area, and determining a perspective transformation matrix between the to-be-mapped area and the local pavement disease area image; determining a segmentation mask image corresponding to the local pavement disease area image; performing perspective transformation on the local pavement disease area image according to the perspective transformation matrix to obtain a target disease area image, and performing perspective transformation on the segmentation mask image according to the perspective transformation matrix to obtain a target segmentation mask image; and determining a target image according to the target disease area image, the target segmentation mask image and the aerial highway surface image. The technical problem that it is difficult to use an unmanned aerial vehicle to shoot pavement disease data during pavement disease recognition in the prior art is solved.

This invention provides an intelligent operation and maintenance scheduling method for charging stations based on a large language model and multi-starting-point policy reinforcement learning. The main steps include: collecting alarm and latitude / longitude data of target charging stations, and constructing a symmetrical global time-distance matrix by combining macro and local road networks; initializing the large language model decision center to generate macro control parameters (including weight parameters and penalty coefficients for each region, and the number of clusters) containing the number of operation and maintenance personnel; using a clustering algorithm based on these parameters to divide all stations into several controlled operation and maintenance areas; extracting real two-dimensional coordinates, using a multi-starting-point policy reinforcement learning network to perform path planning for stations within the operation and maintenance areas, and implementing real-time posterior arbitration; calculating the total maintenance time and workload variance of the planned routes; if the target is not met, generating a natural language diagnostic report and feeding it back to the large language model to readjust the weight coefficients, penalty coefficients, and number of clusters, and iterating until the solution meets the workload balance satisfaction threshold; and outputting the final optimal path planning routes and total time consumption for all target operation and maintenance charging stations.

The invention relates to the technical field of hazardous waste transportation management, in particular to a hazardous waste transfer abnormal behavior self-sensing early warning method based on a transportation track, which comprises the following steps: acquiring transportation information, acquiring a regional local map according to a transportation site, identifying a path in combination with a transportation direction, marking an intersection point, and setting a local road section; determining a local transfer time period and calculating the steady-state flow of the target road section by taking each local road section as a target and combining the predicted transfer time and historical data; according to the number of local road sections extending from the intersection, passing road sections are screened out and connected to generate a transfer transportation track, finally, the track serves as an actual transfer path to be used for dangerous waste transfer, and a precise path basis is provided for abnormal behavior sensing and early warning; through automatic road section screening and track generation, the manual intervention cost is reduced, meanwhile, the clear track generation logic is convenient for supervisors to quickly trace the transportation process, and the convenience and efficiency of hazardous waste transfer supervision are improved.

The application discloses a highway automatic driving commercial vehicle trajectory prediction and decision method and system based on complex network theory, which utilizes a complex network encoder in a prediction model to encode a high-definition map and an agent context into node coding of a directed weighted complex network to obtain the accessibility of each node.A target point predictor predicts target points of each agent according to historical trajectory information and local road features of the agent, and obtains a joint distribution of reference trajectories in combination with lane node accessibility and agent node criticality.A trajectory decoder inputs historical trajectories of the agent and kinematics or dynamics constraints to decode and generate a predicted trajectory and optimize the predicted trajectory under the condition of the reference trajectory.A decision model inputs a navigation route provided by an upstream global path planning layer, judges whether there is a lane changing requirement, and determines a priority of a lane.Combining a joint distribution probability of the reference trajectory, a complex network risk value and the lane priority, a cost function is designed to select an optimal trajectory as a decision result.

The invention discloses an automatic driving control method based on vehicle-road cloud cooperation, and the method comprises the steps: transmitting obstacle, weather and local road condition information to a vehicle end and a cloud end through a road end, and giving a local speed curve of the road end; through vehicle-road cloud global information sharing, the vehicle end marks timestamps on data sent by the cloud end and the road end so as to match corresponding sensing results, and a vehicle end speed curve is generated according to the vehicle end sensing results and road end road condition information; the cloud end gives a cloud end global speed curve according to a navigation planning route of the vehicle and a sensing result of a corresponding road end on the planning route in combination with global traffic flow, historical data and high-precision map information; and adjusting weights corresponding to the cloud end, the road end and the vehicle end, and planning a final speed curve, so that the vehicle performs self-vehicle tracking execution according to the final speed curve. The intelligent level of automatic driving of the vehicle can be improved, and the use comfort of a user is improved.

The invention discloses a trajectory prediction method based on dual-view fusion, which belongs to the technical field of trajectory prediction, and comprises the following steps: respectively acquiring road data and proxy data under a global view and a local view; obtaining global road node features and global agent node features according to the road data and the agent data under the global perspective, and obtaining local road node features and local agent node features according to the road data and the agent data under the local perspective; based on the sparse graph structure, splicing local road node features and local agent node features to obtain time sensitive features of agent nodes; screening the global road node features and the global agent node features to obtain target road node features and target agent node features; fusing the time sensitive feature, the target road node feature and the target agent node feature to obtain an agent node depth feature; and predicting a plurality of candidate end points according to the depth features of the proxy node, and splicing the depth features of the proxy node and the plurality of candidate end points to obtain a prediction trajectory.

The present disclosure provides a determination method and device for gate passing state, and relates to the technical field of artificial intelligence such as large model, deep learning, natural language processing, automatic driving and map navigation. The determination method for gate passing state comprises: determining a target local road network according to a target gate, and obtaining a gate entry track and a gate exit track corresponding to the target gate according to the target local road network; generating a gate entry track graph according to the target local road network and the gate entry track, and generating a gate exit track graph according to the target local road network and the gate exit track; using a multi-modal large model, generating a first answer according to the gate entry track graph, and generating a second answer according to the gate exit track graph; and obtaining the passing state of the target gate according to the first answer and the second answer. The present disclosure can enhance the robustness when judging the gate passing state, and improve the efficiency and accuracy of obtaining the gate passing state.

1. Name of the product in this design: Integrated entrance overload control equipment. 2. Purpose of this design: For the management of overloaded vehicles and toll collection on highways and local roads. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

The invention provides an intelligent traffic management method and system, and relates to the technical field of intelligent traffic. The method comprises the following steps: a vehicle terminal determines whether a traffic event exists at present according to collected current road environment data; if yes, responding to the traffic event, and controlling the vehicle to execute vehicle emergency operation; the vehicle terminal sends the execution result of the vehicle emergency operation and the type of the traffic event to the corresponding roadside equipment; the roadside equipment performs local road traffic coordination control according to the execution result of the vehicle emergency operation, the type of the traffic event and the vehicle driving data of each driving vehicle in the control range of the roadside equipment; and the cloud device performs global road traffic coordination control according to the reported data of each vehicle-mounted terminal and the reported data of each road side device. According to the method, through cooperative processing of the vehicle terminal, the roadside equipment and the cloud equipment, an efficient traffic decision-making mechanism considering real-time performance, safety and globality is realized.

This invention discloses a robot scheduling method and system for sand and gravel stacking sites based on inventory heat, belonging to the field of intelligent control technology. By establishing a road network topology including inventory areas and road units, the time axis is discretized into scheduling time slices. Inventory heat is calculated and graded based on inventory quantity, inbound / outbound frequency, and task time limits, forming an inventory heat distribution. Based on inventory heat and a preset maximum travel distance threshold, a subset of candidate tasks is generated for the robot. Under the constraints of empty travel distance threshold and road unit throughput parameters, the robot collaboratively completes target task selection and travel path planning. Operating status, task results, and inventory inbound / outbound information are collected to calculate empty travel, congestion, and inventory response indicators. The inventory heat calculation rules and task priority rules are adjusted to adaptively update the inventory heat distribution. This invention can reduce empty travel distance, alleviate local road congestion, and improve the operational efficiency of stacking sites.

Method for determining local weather conditions (41), local precipitation (42) and / or local road surface conditions (43) in the immediate vicinity of a vehicle (1) by evaluating signals (23-30) from at least one vehicle environment sensor (2; 3), wherein at least one interference signal (24; 26; 28; 30) of the at least one vehicle environment sensor is taken into account for determining the local weather conditions (41), local precipitation (42) and / or the local road surface conditions (43), wherein the at least one vehicle environment sensor (2; 3) comprises a radar, lidar sensor and / or a laser scanner.

The invention belongs to the technical field of logistics transportation evaluation, and provides a logistics transportation path evaluation method and system based on atlas analysis, electronic equipment and a storage medium. The method comprises the steps of fusion data set construction, map construction, effective road network map construction, effective path information extraction, local prediction map sequence construction, multi-dimensional evaluation and grade matching. According to the invention, through construction of the dynamic road network map and the historical road network map database and multi-time-step prediction, the perspectiveness of an evaluation result is improved; by constructing a local road network set, comprehensive assessment of path passing efficiency and risk is realized, and the integrity of an assessment result is improved; and by integrating dynamic influence data and utilizing a multi-rule and multi-dimensional processing mechanism for correction, the reliability and robustness of an evaluation result are enhanced.

The invention discloses a vehicle driving assistance control method and device, electronic equipment and a readable storage medium. The method comprises the steps that a navigation path of a vehicle and road information of a road on which the vehicle is currently driven are obtained in response to the fact that a driving assistance function of the vehicle is in an open state, and the road information is used for representing local road characteristics of the road on which the vehicle is currently driven; based on the position information of the current position of the vehicle and the navigation path, navigation map information is obtained, and the navigation map information is used for representing global road features of the vehicle within a preset distance range; based on the navigation path, the navigation map information and the road information, a driving strategy of the vehicle is determined, and the driving strategy is used for representing a driving rule of the vehicle along the navigation path; and controlling the vehicle to run along the navigation path according to the driving strategy. According to the invention, the technical problem of low application efficiency of a driving assistance function in a complex or long-distance scene in the related art is solved.

The invention discloses an unmanned aerial vehicle road property inspection image recognition method and system based on semantic segmentation, and the method comprises the steps: carrying out the spatial partitioning of a single-source road property inspection image, which is aerially photographed by an unmanned aerial vehicle, according to a size label of a road property target, after obtaining a plurality of road property inspection sub-images containing complete local road property areas, inputting the road property inspection sub-images into a feature pyramid semantic segmentation model, adjusting the robustness loss weight of the model based on shooting angle deviation and illumination non-uniform features, and outputting abnormal shooting correction sub-images; adjusting the feature extraction weight of the small target attention mechanism module, extracting the features of the small target road property region, and splicing and integrating the features to obtain a semantic segmentation result; extracting a shape texture feature set according to a semantic segmentation result, matching the shape texture feature set with a preset road property target classification library to obtain classification information, extracting state features, and performing evolution analysis to determine an abnormal state; and performing spatial geographical coupling analysis by using the classification information, the abnormal state and the unmanned aerial vehicle flight log, and generating an inspection report carrying road property position marks.

The application relates to the technical field of artificial intelligence, and provides a vehicle violation identification method and system based on three-dimensional posture perception. The method comprises the following steps: obtaining a vehicle violation detection point through violation site positioning; pre-disposing equipment at the detection site to obtain a high-position image collection array; setting a trigger distance to determine a trigger range; when a target vehicle enters the range, activating the image collection array to obtain a real-time image set; realizing three-dimensional posture perception based on the image set to obtain real-time three-dimensional posture parameters; taking the trigger range as a constraint to obtain local road geometric parameters; and combining the posture parameters and the road geometric parameters to identify the violation to obtain a vehicle violation identification result. The application realizes three-dimensional posture perception on the real-time images collected by the high-position image collection array, solves the technical problem that a traditional monocular camera cannot construct a three-dimensional scene, and ensures high-precision identification of the vehicle position.

The application discloses a kind of electric heavy truck dynamics parameter estimation and driving power prediction method and system and readable storage medium, belong to new energy automobile energy management technical field.The method collects vehicle operation data and matches local road topology network;Utilize state and parameter joint estimation algorithm interactive transfer covariance, real-time decoupling output vehicle mass and road slope estimated value, automatically reset covariance matrix when loading and unloading;Based on topology network, construct topological graph, integrate space-time characteristics and use speed prediction neural network to output speed and acceleration sequence;The estimated value is substituted into longitudinal dynamics inverse equation to solve reference driving power, and the error caused by the fluctuation of resistance coefficient is compensated by using Gaussian process regression model, and the power demand with confidence interval is output.The system includes data acquisition, parameter estimation, working condition prediction and power joint prediction module, and the corresponding program is stored in the medium.The application realizes high-precision decoupling and fast convergence of parameters.

The invention provides a vehicle-mounted navigation recommendation system and method, electronic equipment and a medium, and belongs to the technical field of intelligent driving. Vehicle pavement safety information is collected through a sensor module, the vehicle pavement safety information is obtained through an intelligent driving domain controller, and local road monitoring information is formed according to the vehicle pavement safety information; the cloud platform obtains local road monitoring information and evaluates the safety level of each road in real time according to the local road monitoring information, and the intelligent video domain controller recommends a navigation road according to the evaluation information of the safety level of each road. Road safety data collected by the shared vehicle end is sent to the cloud end, information uploaded by a large number of vehicles is processed and analyzed through big data, unsafe road points are marked, the safety risk of each road is evaluated, the safety of different routes is integrated through navigation, the smoothness and safety of road traffic are improved, and therefore the traffic efficiency is improved.

The utility model belongs to the technical field of road engineering equipment, and particularly relates to a local pavement repairing device which comprises a frame, a compaction box is arranged in the frame, a liftable compaction plate is arranged at the bottom of the compaction box in a sliding mode, a heat insulation cavity is formed in the compaction plate, and the heat insulation cavity is communicated with the compaction box. A plurality of telescopic rods with cavities are arranged on the end face of the compaction plate, a water tank is arranged at the tops of the telescopic rods, a refrigeration assembly is arranged on the surface of the water tank, an exhaust part is arranged on one side of the compaction box, and a movable plate capable of rotating in one direction is arranged in the exhaust part. By arranging the heat insulation cavity and the water tank, the interior of the compaction plate can be cooled, so that a temperature difference is formed between the surface of the compaction plate and an asphalt pavement, the temperature of an asphalt contact surface is reduced, asphalt adhesion is prevented, and by arranging the exhaust part, the asphalt surface to be compacted can be cleaned.

The invention provides a road condition map construction method and system, electronic equipment and a storage medium, and is applied to a vehicle-mounted unit, and the method comprises the steps: obtaining a basic static map of a current road section; acquiring sensing data acquired by a sensor of the current vehicle; the sensing data comprises current vehicle running state data and current vehicle position environment data; obtaining dynamic data in a target range; the dynamic data at least comprises one of data sent by other vehicles and data sent by a road side unit; according to the perception data, the dynamic data and the basic static map, drawing a road condition map corresponding to the current road section; and sending the sensing data and the dynamic data to an edge computing platform, so that the edge computing platform constructs a dynamic map corresponding to the current road section. The construction efficiency and precision of the local road condition map and the overall dynamic map can be effectively improved, and more accurate road condition information and driving safety guarantee are provided for drivers.

The invention discloses a sandstone material stacking site robot scheduling method and system based on inventory heat, and belongs to the technical field of intelligent control. The method comprises the following steps of: discretizing a time axis into scheduling time slices by establishing a road network topology containing an inventory area and a road unit, calculating inventory popularity according to an inventory quantity, a warehouse-in and warehouse-out frequency and a task time limit, and grading to form inventory popularity distribution; a task candidate subset is generated for the robot based on the inventory heat and a preset maximum driving distance threshold, and target task selection and driving path planning are cooperatively completed under the condition that an empty driving distance threshold and road unit passing capacity parameter constraints are met; and collecting a running state, a task result and inventory warehouse-in and warehouse-out information, calculating empty driving, congestion and inventory response indexes, adjusting an inventory popularity calculation rule and a task priority rule, and adaptively updating inventory popularity distribution. According to the invention, the empty driving distance can be reduced, local road congestion is relieved, and the working efficiency of a stacking field is improved.