297 results about "Road map" patented technology

The invention provides a vehicle navigation path processing method and system based on online information, and is applied to the technical field of data processing. The method comprises the following steps: processing meteorological data of target road environment information and target road map information in a preset time period to generate an environment influence factor; processing the real-time traffic information and the target road map information to generate a road influence factor; processing the vehicle state information, the target vehicle attribute information and the driving information of the target driver to generate a vehicle driving influence factor; processing the environment influence factor and the road influence factor based on a target vehicle navigation path generation model to generate initial vehicle navigation path information; and processing the initial vehicle navigation path information based on the vehicle driving influence factor to generate target vehicle navigation path information.

The invention relates to the field of intelligent automatic driving, in particular to a multi-vehicle cooperative controllable confrontation test method based on a diffusion model. Comprising the following steps: S1, a diffusion model training stage: training a diffusion model based on real driving data, and learning vehicle behavior distribution through forward noise addition and reverse denoising to obtain fixed model parameters; s2, scene and multi-vehicle space-time modeling: fusing the road map, the lane topology and the vehicle state information, and constructing a space-time scene representation of multi-vehicle interaction as input of diffusion generation; s3, a diffusion generation mechanism based on adversarial guidance; s4, performing partial diffusion control and diversified confrontation generation; and S5, evaluating the authenticity and controllability of the multi-agent confrontation scene. Compared with the prior art, the method has the advantage that the authenticity, controllability and closed-loop consistency of multi-vehicle cooperative confrontation scene generation are obviously improved.

The invention relates to a vehicle-cloud integrated wet and slippery road vehicle driving risk early warning method and system, and the method comprises the following steps: obtaining the forward video data of a vehicle, recognizing the type of a current driving road according to the forward video data through a road segmentation and road classification multi-task model, and carrying out the early warning of the driving risk of the vehicle through a pre-established road adhesion coefficient reference table. A road adhesion coefficient is obtained and uploaded to the cloud; continuously counting global road adhesion coefficients, establishing a road adhesion coefficient fusion model, and fusing the global road adhesion coefficients through road section matching and introduction of time difference factors to generate a wet and slippery road map; determining an early warning area corresponding to any wet and slippery road section on the wet and slippery road surface map through a dynamic calculation method; and for a wet and slippery road section, phase plane stability boundaries of different types of vehicles are calculated, typical driving control behaviors are simulated, instability risks are evaluated, and early warning information is sent out. Compared with the prior art, the method achieves the observation of the wet and slippery road surface, and has the advantages of high early warning precision, high pertinence and the like.

The invention provides a method and a device for determining an end-to-end perception decision regulation and control architecture, and belongs to the technical field of automatic driving. A first multi-modal data set is constructed based on a basic traffic signal image of an automatic driving scene, road map data and a basic driving rule; the second multi-modal data set is constructed based on dynamic traffic element image sequence data of an automatic driving scene, complex environment element image sequence data and complex driving rules, and the third multi-modal data set is constructed based on an automatic driving scene image, an automatic driving target and sensor time sequence data; and performing staged training on the multi-modal large model to obtain an end-to-end perception decision regulation and control architecture suitable for an automatic driving scene. A multi-modal large model is trained through a staged training strategy, basic element recognition, complex element recognition and decision training are gradually realized, the real-time performance of the model is enhanced, and the requirement of an automatic driving task for the real-time performance is met.

The invention discloses a road scene space rapid investigation system combining RTK and image reconstruction, relates to the technical field of road scene space investigation, and is used for solving the problem of poor road mapping splicing effect. According to the method, an RTK track in road inspection is collected and synchronized with an image frame, after abnormal points are removed, continuous control points are extracted to construct a road topology skeleton, a space is divided into a plurality of mapping units based on the control points and direction vectors, redundant overlapping areas are set, and a mapping task package with structural continuity is generated; a road structure area in an image is extracted through semantic segmentation and edge detection, a structure mask is constructed and projected to a three-dimensional space, and point cloud density enhancement and reconstruction optimization are guided, so that block boundary structure anchor points are further identified, local rigid body registration is completed, and a global error minimization model is constructed. The posture consistency and the space continuous splicing of all the image blocks are realized, and the exploration efficiency of the road scene space is improved.

Various embodiments include a backend for an object updating system for removing objects present in a digital road map comprising: a memory storing a set of instructions; and a processor in communication with the memory. The digital road map is stored in the memory. The set of instructions, when loaded and executed by the processor, cause the processor to: receive a path and environmental data captured along this path from a vehicle; recognize objects in the environmental data; and remove an object from the digital road map if the object is not recognized in the environmental data.

The invention belongs to the technical field of virtual reality redirection, and provides a method and system for generating a virtual road map of a predictive redirection controller, and the method comprises the steps: carrying out the curve polygon subdivision of a given virtual scene, and calculating a shortest path tree of a current position of a user in the scene through a shortest path tree algorithm; performing skeleton processing on the given virtual scene to obtain a polygonal skeleton; calculating a visible polygonal area of the current position of the user based on the shortest path tree; extracting virtual road points according to the intersection points of the visible polygonal area and the polygonal skeleton; fitting a path between adjacent virtual road points by using a clothoid; and judging whether the current road point depth meets the given depth or not, and if not, repeatedly fitting the next virtual road point as the current position of the user until a virtual road map meeting the given depth is generated. According to the method, a prediction redirection controller virtual road map generation scheme of a curve boundary complex scene can be supported, and the problem that the application range of a prediction redirection controller in the prior art is small is solved.

The invention relates to the technical field of data processing, in particular to a calibration system and calibration method for inertial measurement units, and the system comprises a setting module which firstly determines a plurality of key point locations of a test aircraft and arranges a plurality of inertial measurement units according to the key point locations. The data acquisition module acquires the real-time acceleration of the inertial measurement unit according to a preset frequency. The comparison module compares the real-time acceleration of each unit, determines a first acceleration range according to the result, further determines a first calibration parameter, or adjusts the frequency, and sends out a secondary judgment instruction. And after receiving the instruction, the route judgment module draws a real-time route map according to the real-time acceleration, compares the real-time route map with a preset route map to determine a second calibration parameter, and adjusts the first acceleration range or sends out three judgment instructions if necessary. And after receiving the instruction, the temperature judgment module collects a real-time temperature value, draws a curve and analyzes the curve, and determines a third calibration parameter. And the calibration module comprehensively applies the parameters to calibrate the inertial measurement unit. The measurement accuracy of the inertial measurement unit is improved.

In various examples, a simulation platform generates a simulated driving environment by processing road map data to derive the location of wear-related visual artifacts for sections of a lane surface. Using map data, the simulation platform generates texture maps for aesthetic road rendering, which are used to apply textures to a 3D polygon topology mesh. The simulation platform generates visual artifacts representing the wear and tear of the road surface based on a calculation of one or more lane feature distances derived from the map data. The simulation platform calculates distances associated with reference line data derived from an image to render a texture of one or more lane features.The spacing is used to determine how the appearance of the texel is adjusted to include wear-related visual artifacts when displayed on a lane of the simulated driving environment.

The invention relates to an intelligent networked vehicle formation test method based on digital twin virtual-real combination, and belongs to the field of automatic driving test. The method comprises the following steps: collecting traffic road map data, and constructing a digital twin virtual traffic scene; constructing an intelligent networked vehicle formation model, and loading the intelligent networked vehicle formation model into a digital twin system; the virtual traffic scene is transmitted to the driver in-the-loop simulation device, and the artificial driver controls the artificial driving simulation vehicle according to the virtual traffic scene, thereby realizing simulation of the artificial driving vehicle; the intelligent network connection vehicle formation model generates a control instruction of the automatic driving simulation vehicle based on the driving track of the artificial driving simulation vehicle, and sends the control instruction to the miniature vehicle for real vehicle verification; and collecting simulation data of the digital twin system and real vehicle data of the miniature vehicle for analysis, and verifying the validity of the intelligent network connection vehicle formation model. According to the invention, the problem of difficulty in interactive simulation of a manual driving vehicle and an automatic driving vehicle is solved, and the authenticity is high.

A vehicle traveling information analysis device comprises: a reception unit that receives, from a plurality of vehicles, traveling information which includes location information and time information; a traveling information recording unit that stores, in a traveling information storage unit, the traveling information received from the reception unit together with identification information of vehicles; an analysis condition input unit that accepts, from a user, designation of an analysis condition which includes information pertaining to an analysis target road; an extraction region setting unit that sets extraction regions each having a predetermined area to a respective plurality of locations on a road map on the basis of the designated analysis condition; and a vehicle identification information extraction unit that extracts identification information of a vehicle having a record of traveling information in all the extraction regions which have been respectively set to the plurality of locations on the road map.

The invention provides a safety and efficiency coupled post-earthquake rescue path optimization LGNN algorithm, and relates to the technical field of post-earthquake rescue path optimization, and the algorithm comprises the steps: obtaining multi-source data; constructing a road map through the multi-source data and the susceptibility result; according to an emergency rescue report in the multi-source data, determining a rescue center and a disaster site; constructing a lightweight graph neural network; inputting the road map, the rescue center and the disaster point into a lightweight map neural network; and taking the cumulative weight of each node from the rescue center to the road map as a node feature, iterating the node feature representation through the lightweight map neural network to obtain the minimum value of the cumulative weight of the disaster-affected point, and backtracking the cumulative weight of the disaster-affected point to obtain the optimal rescue path from the rescue center to the disaster-affected point. And efficient emergency rescue path optimization is realized on a wide-area complex road network in a wide-area strong earthquake area.

The invention discloses a vehicle multi-modal motion trajectory prediction method considering dynamic executable constraints, aims to consider the influence of a vehicle motion model on prediction performance, and specifically comprises the following steps: (1) coding a vehicle trajectory and a road map by using an encoder through an LSTM network; (2) encoding the interaction relationship between the predicted vehicle and the surrounding vehicles and the interaction relationship between the predicted vehicle and the road map through an encoder; and (3) modeling the predicted vehicle into a two-degree-of-freedom kinematics model, incorporating the model into a decoder, and outputting a dynamically executable multi-modal prediction trajectory. According to the method, the influence of the motion of the vehicle in the interaction scene and the two-degree-of-freedom kinematics model are brought into the motion trail prediction of the vehicle, and finally the purpose of predicting the multi-modal motion trail of the vehicle is achieved.

A method of constructing a map based on a large model, a vehicle control method, an electronic device, and a storage medium are provided, which relate to a field of artificial intelligence technology, in particular to fields of computer vision, deep learning, large model and generative model technologies. The method includes: acquiring an associated-region lane attribute and an image to be detected, which is collected by an onboard sensor and represents a road region to be detected; constructing a target prompt information based on the associated-region lane attribute; and processing the target prompt information and the image to be detected by using the large model to obtain a regional road map for the road region to be detected. The associated-region lane attribute corresponds to an associated road region, and the associated road region and the road region to be detected meet a predetermined similarity condition.

The invention belongs to the technical field of intelligent traffic, and particularly relates to a traffic prediction system based on a historical track set. The method comprises the following steps of: collecting track data generated when a vehicle runs on a road network by using navigation positioning equipment, and constructing a hypergraph attention model based on a historical track set; the model is used for capturing space-time related characteristics on the hypergraph structure and the road network, so that the driving speed change of different roads in the future road network is accurately predicted; the system comprises a trajectory set feature extraction and enhancement module, a trajectory set hypergraph construction module, a hypergraph attention model module and a traffic prediction layer module. According to the method, heterogeneous and complex traffic semantic information is integrated by means of various space-time attention mechanisms; and meanwhile, a feature conversion relation between the road map and the track set hypergraph is established, so that features of a hypergraph space and a road network space are efficiently exchanged, and the future traffic speed is accurately predicted.

According to the present invention, autonomous driving may be performed according to an autonomous driving strategy defined in trajectory constraints generated based on object recognition information about a road map and various traffic participants, and thus, because collision avoidance does not obstruct traffic of an adjacent lane despite a situation where an autonomous vehicle stops for avoiding a collision, the stability of autonomous driving may increase and vehicle traffic management may be easily performed.

The invention discloses a GNSS (Global Navigation Satellite System) / INS (Inertial Navigation System) / map tightly integrated navigation positioning method and system based on road marking matching, and belongs to the technical field of navigation positioning, and the method comprises the following steps: acquiring priori road map data, foresight road image data, a GNSS original observation value and an INS original observation value; a semantic segmentation network is adopted to extract road marking semantic features in the foresight road image data, and a road marking feature instance is obtained; performing nearest neighbor search on the road marking feature instance and map elements in the prior road map data, and obtaining corresponding map matching observation based on a nearest neighbor search result; and coupling the GNSS original observation value, the INS original observation value and map matching observation to obtain a navigation positioning result. According to the method, a tight combination model based on GNSS / INS and map matching original observation values is provided, the positioning performance of a navigation system in a complex city scene is improved, and omni-directional pose constraint is provided for a vehicle.

The invention relates to the technical field of map making, in particular to a method and system for making a three-dimensional high-precision map containing road geometric elements, and the method comprises the steps: extracting original data from an original file through employing a user-defined analysis tool; preprocessing and checking the extracted original data to obtain core element data; and according to the core element data, generating a road three-dimensional model by adopting a space calculation model, and according to the core element data and a road design specification, performing derivative element calculation and generative three-dimensional element supplementation to form a three-dimensional lane-level road electronic map. According to the scheme, the three-dimensional high-precision map containing the road geometric elements can be manufactured, the map manufacturing efficiency is improved, the map precision is enhanced, and the cost is reduced.

Proximity-based surface texture generation for simulated environment systems and applications is disclosed. In various examples, a simulation platform generates a simulated driving environment by processing road map data to infer locations of wear-related visual artifacts for portions of a roadway surface. The simulation platform uses the map data to generate texture maps for aesthetic road rendering, which are used to apply texture to the 3D polygon topology mesh. The simulation platform generates visual artifacts representing use and wear of the roadway surface based on calculating one or more distances from roadway lane features derived from the map data. The simulation platform calculates a distance from the one or more roadway lane features associated with reference line data derived from the image to render the texture. The distances are used to determine how to adjust the appearance of texels to include wear-related visual artifacts when rendering wear-related virtual artifacts on the roadway of the simulated driving environment.

A computer-implemented method is provided for determining a navigation route between a start point and a target point. The method includes setting the start and target points, and then generating a road map with a road graph having plural edges between the star and target points representing traversable route portions. The generated road map also has nodes that interconnect the adjacent edges. The road map is generated from geospatial data retrievably stored in a database. The method proceeds by generating an emotion map layer by a machine learning model that is trained to predict, based on static and / or dynamic contextual input data for each of the edges, the likely emotions of a driver as they traverse the relevant edge and generate emotion weightings in the emotion map layer. The method then calculates the navigation route by the emotion map layer with the emotion weightings obtained in the previous step.

The invention discloses an automatic driving online vectorization map construction method, model and equipment combined with high-precision positioning, and the method comprises the steps: constructing a high-quality beyond-visual-range online vectorization road map through the mutual enabling of multi-modal information of a vehicle-end around-view camera, a cloud low-orbit satellite and the like; the problem of vehicle end sensing failure in complex scenes such as large crossroads, high-speed confluence areas and canyon tall buildings is solved. The method comprises the following steps: firstly, fusing a streaming strategy and a stacking strategy to improve the time sequence modeling capability, and enhancing the characterization capability by using global information of a height dimension and a width dimension; secondly, cloud information and vehicle end information are deeply fused based on an attention mechanism, and the perception performance is improved. And finally, the fusion features of different scales of the cloud end and the vehicle end are efficiently decoded based on hierarchical perception aggregation of adaptive query, and according to different scales of map instances, adaptive query dynamically interacts with the fusion features of different resolutions and focuses on key target instances, so that the convergence efficiency and the construction effect of map elements of different scales are improved.

The invention relates to a method for determining at least one safety-critical peak region (R1, R2, R3) on the basis of an indicator value (Z) for statistical characterization of event descriptions detected by at least one vehicle in a location-related manner, wherein those inflow- and outflow-free road sections of which the section length is greater than or equal to a predetermined minimum section length are identified on the basis of a road map or navigation map. Identified road sections which adjoin one another are connected to form in each case a section chain (10) with a starting point (11) and an end point (12). Event descriptions comprising a geoposition (P1, P2) and at least one parameter of a vehicle environment model are detected by vehicles and transferred to an analysis system. The analysis system in each case assigns a nearest road network location (O1, O2) of a section chain (10) to a geoposition (P1, P2) of an event description and describes it by a longitudinal distance (L, L1, L2) in relation to the starting point (11) of the section chain (10). For at least one section chain (10), a profile of a density value (p) of event descriptions that is related to the longitudinal distance (L, L1, L2) from the starting point (11) is determined by means of a kernel density estimator of a predetermined bandwidth. The profile of the density value (p) is transformed, using local, bandwidth-related, Z standardization, into a Z profile (Z1, Z2) of a Z value (Z) which is mean-free in relation to bandwidth. In each case a region of road network locations (O1, O2) along the motorway-like road (100) which are connected along a section chain (10) between a peak beginning (Lmin) and a peak end (Lmax) and at which the Z value (Z) exceeds a predetermined threshold value (θ) is identified as a safety-critical peak region (R1, R2, R3).

To provide a driving evaluation apparatus for appropriately evaluating the driving skill of a driver.SOLUTION: A driving evaluation apparatus includes: an error information generation section 12 that generates steering error information, which is information on an error of an actual measured value with respect to a predicted value of steering, on an evaluation target road identified by road map information on the basis of traveling information of a plurality of vehicles acquired by an information acquisition section 11; and a driving evaluation section 13 that evaluates a driving skill of a driver of an evaluation target vehicle on the basis of a difference between a reference error value determined by the generated steering error information of the plurality of vehicles for the evaluation target road within a predetermined period and a target error value determined by the steering error information, which is generated by the error information generation section, of the evaluation target vehicle for the evaluation target road within the predetermined period.SELECTED DRAWING: Figure 4

The embodiment of the invention discloses a road element prediction method and device, equipment, a medium and a product, and the method comprises the steps: obtaining upstream and downstream roads adjacent to a target road, and constructing a road map with the target road as the center according to the topological relation between the target road and the upstream and downstream roads; taking roads in the road map as nodes, and obtaining static attribute information and track flow time sequence data of each node; generating node features in the road map according to the static attribute information of each node and the trajectory flow time sequence data to obtain a target road map; and carrying out spatial topology feature extraction on the target road map to obtain a representation vector of the target road map, and obtaining a prediction result of whether the road elements of the target road change or not according to the representation vector of the target road map. The technical scheme of the embodiment of the invention can be applied to the field of maps, the change of the road elements can be accurately predicted, and meanwhile, the timeliness and effectiveness of obtaining the change of the road elements are ensured.

The invention provides an in-charging-station vehicle guiding method and device based on appointment charging, and the method comprises the steps: a station server selects idle charging piles in a charging station to form a charging pile candidate list, and a user selects the charging piles from the charging pile candidate list through a client as appointment charging piles; the station server pulls a video stream of each camera in the charging station, and obtains the position of the reserved vehicle through a positioning algorithm after recognizing that the reserved vehicle enters the charging station; the station server plans an entrance path from the position of the reserved vehicle to the reserved electric pile according to an internal road map of the charging station, and generates navigation information according to the entrance path to guide the reserved vehicle to a target parking space where the reserved electric pile is located; and after the station server recognizes that the reserved vehicle arrives at the designated area of the target parking space, a ground lock of the target parking space is automatically unlocked or a barrier gate of the target parking space is automatically lifted, and the reserved vehicle is driven into the target parking space. According to the invention, the charging convenience is improved through navigation in the station and automatic unlocking of the barrier gate ground lock.

The invention provides a vehicle trajectory planning method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining an image of a surrounding environment of a target vehicle, historical trajectory information of an object in the surrounding environment, and a road map, carrying out the fusion coding according to the historical trajectory features of the object, the map features of the road map, and the image features of the image, and obtaining a target trajectory; the method comprises the steps of obtaining a fusion feature according to current positioning information of a target vehicle, the position of each pixel point in an image, a set position in a road map and the fusion feature, decoding according to the current positioning information of the target vehicle, the position of each pixel point in the image, the set position in the road map and the fusion feature to obtain a target decoding feature, and predicting a trajectory according to the target decoding feature to obtain a trajectory planning result of the target vehicle. Fusion coding is carried out based on the trajectory features, the map features and the image features, so that association relationships among different types of features are extracted by fusion coding, trajectory prediction is carried out based on fusion coding, and the accuracy of trajectory prediction is improved.

The present invention provides a method, device, equipment and readable storage medium for generating a dangerous scene. The method comprises: extracting a target scene segment based on target information; generating a target object list in the target scene segment; generating a target vehicle driving trajectory and a high-precision road map in the target scene segment based on the target object list; weighting based on a weighting factor to generate a first preset number of driving behavior parameters of a host vehicle and a target vehicle driving behavior parameter; combining to obtain a second preset number of driving behavior combinations; mapping the driving behavior combinations to the high-precision road map to generate a target scene; and performing simulation re-play on the target scene, with the target scene in which an accident occurs in the simulation re-play and the target scene in which an accident is dangerous but no accident occurs as the dangerous scene. The present invention makes it possible to obtain dangerous scenes without artificially creating dangerous driving, and reduces costs while improving the efficiency of dangerous scene generation.

An information processing apparatus comprises a processor configured to: acquire, from a first vehicle, lane topology information, estimated based on data acquired via a vehicle-mounted sensor of the first vehicle, indicating a lane topology of a road traveled by the first vehicle, and first information including position information corresponding to the lane topology information, associate, based on the first information, one or more pieces of the lane topology information acquired from a plurality of the first vehicles with each of a plurality of road segments included in a road map, and determine a lane topology for each of the plurality of road segments included in the road map, based on the one or more pieces of the lane topology information that is associated.

The invention provides a vegetable and fruit picking robot path planning method and system. The method comprises the following steps: firstly, constructing a global scene model represented by an octree; then collecting a quality path data packet of the risk local area, generating a local planner, generating a corresponding local area octree code for the risk local area, binding the local planner and the local area octree code as an experience record, and storing the experience record in a knowledge base; in the face of a new picking task scene, new local area octree codes are generated for the new local areas, and the most similar empirical records are retrieved from the knowledge base through recursive structure similarity calculation so as to determine a planning strategy of each new local area; and finally, constructing a discrete road map according to the starting point and the ending point of the new picking task, calculating a new local region sequence, forming a global planner, generating a collision-free continuous track from the starting point to the ending point by using the global planner, and delivering the collision-free continuous track to the robot for execution. The path planning efficiency, the success rate and the path quality of the robot in the complex picking environment can be effectively improved.

The present invention provides a safety distance warning method and system for a substation, which relates to the field of safety distance warning technology. The method includes using an equipment processing model to determine the substation high-voltage cable information and multiple live equipment information in the station based on the substation panoramic image information and the substation design drawing information; constructing an equipment map; processing the equipment map based on a first graph neural network to determine multiple electrical risk point information and multiple electrical safety point information; constructing a road map; processing the road map based on a second graph neural network to determine the operating route of the equipment to be operated; determining multiple line segments and the safe activity range of the boom of each line segment based on the crane boom information and the operating route of the equipment to be operated; and issuing an early warning to the equipment to be operated based on the operating route of the equipment to be operated and the safe activity range of the boom of each line segment. This method can accurately determine the safe activity range of the equipment operation.