167 results about "Road mapping" patented technology

In various examples, embodiments are directed to navigation-road and perception-lane matching for autonomous and semi-autonomous systems and applications. In this regard, lane-road matching is performed using geometric similarity to generate effective lane-road mappings for use in lane planning and decision making, among other things. In some embodiments, road data representing at least one road section and lane data representing a lane associated with a location of an ego-machine are received. Thereafter, a determination is made that one or more consecutive road sections match a lane based at least on a geometric similarity between the lane and the one or more consecutive road sections. A representation of the lane being mapped to the one or more consecutive road sections is generated based at least on the determining that the one or more consecutive road sections matched the lane.

The invention discloses a multi-robot path planning system and method based on sampling, and belongs to the technical field of robot path planning, and the system comprises a route map initialization module, a scanning volume calculation module, a collision inspection module, a path expansion module and a reconnection module. A space is explored and planned in a random sampling mode, the method is suitable for dynamically changing industrial scenes, in addition, compared with a traditional method, the method pays more attention to improving the planning efficiency instead of an absolute optimal path, the collision detection process is optimized by pre-calculating the sweeping volume, the calculation overhead in the search process is reduced, and the search efficiency is improved. The problem of mutual interference among multiple machines is solved through a deadlock strategy, unnecessary calculation is reduced through a simplified updating strategy, and the efficiency of multi-robot path planning is remarkably improved while the effect of a solution is kept.

The invention discloses an unmanned aerial vehicle route planning method based on a graph neural network, and belongs to the field of unmanned aerial vehicle route planning. According to the method, nodes and edges are generated through random sampling in a target area by using a probability route map, the safety distance with a building is considered, a complex map structure is simplified, and a continuous space is converted into a discrete space; then path node selection is carried out on the path network diagram, so that the problem of low search efficiency in a complex space is solved, and meanwhile, the safety of the unmanned aerial vehicle in the flight process is ensured; according to the graph attention network of an encoder-decoder structure, an encoder uses an attention mechanism to carry out feature extraction on an obtained probability route map, different weights are given to nodes through a self-attention mechanism, and influences of key nodes related to paths and neighbors of the key nodes are emphasized; and the decoder uses attention weight to guide node selection according to node features extracted by the encoder, and finally an optimal path is formed.

A computer-implemented method for generating a knowledge graph for traffic motion prediction. The method includes: receiving environment sensor data of at least one environment sensor of an ego-vehicle; receiving map data from an electronic road map; extracting the information regarding the at least one traffic participant from the environment sensor data and extracting the information regarding the motion track the traffic participant is positioned on from the map data; and generating a knowledge graph of the road network in the environment of the ego-vehicle including nodes and edges based on the map data and / or the environment sensor data. The knowledge graph includes at least one node representing the traffic participant and at least one node representing the lane the traffic participant is positioned on.

The invention relates to the field of gypsum library scheduling, and discloses an intelligent gypsum library job scheduling control system, which is provided with a monitoring module, a task scheduling module, a constraint reforming module, a grading module, a collision avoidance regulation and control module and a task scheduling module, simulates different operation task allocation conditions based on a driving scheduling model, and screens an optimal task allocation scheme; the constraint reforming module draws a driving speed change diagram according to the instruction parameters of the driving grading instruction based on the speed constraint, and draws a walking route map according to the speed change diagram; the grading module determines the collision avoidance priority of driving based on the task remaining time; the collision avoidance regulation and control module controls the travelling crane with the low collision avoidance priority to start a collision avoidance program when the distance difference between the two travelling cranes tends to and is equal to the maximum safety distance. According to the invention, on the basis of considering the speed constraint, task allocation optimization is realized, the speed change diagram of driving is updated by taking the speed constraint as a reference, and the driving collision avoidance effect is optimized on the basis of considering the driving speed constraint.

The invention relates to the technical field of cadastral data dynamic management, and discloses a cadastral data dynamic updating and storage method, device and equipment and a storage medium. By receiving a land law enforcement task set of a target law enforcement vehicle, a law enforcement driving route map for a plurality of law enforcement tasks is constructed; issuing cadastral data of each law enforcement task to a cadastral data edge library at different driving road sections is taken as a decision variable, and the storage capacity of a target law enforcement vehicle, the maximum communication capability of each driving road section, the cadastral data advanced issuing characteristic and the cadastral data real-time performance are considered; and controlling cadastral data scheduling of the cadastral data edge library and the cadastral data core library, and assisting law enforcement officers in land law enforcement. Therefore, by adopting the task-oriented accurate data issuing and dynamic and the space-time analysis-based bandwidth prediction and optimization strategy, organic unification of the real-time performance, the security and the access efficiency of the cadastral data is realized, and efficient and reliable data support is provided for land law enforcement.

A method for determining an egress route for a vehicle to a target off-ramp of a highway, as well as a corresponding automotive control unit and a vehicle, are provided. To determine the egress route, an egress route graph is generated based on map data arranged in links. The egress route graph comprises a plurality of egress route nodes and a plurality of egress route edges, which includes lane direction edges based on lane information included in at least some of the links and lane change edges. To each egress route edge, a confidence value and a cost value are assigned. Based on the accordingly determined egress route graph, the egress route is determined, which corresponds to a path through the egress route graph to the target off-ramp, which has an optimized total confidence value and an optimized total cost value.

The invention discloses a charging decision-making method, system and device for an extended-range automobile and a storage medium, and relates to the technical field of electric automobiles, and the method comprises the steps that first automobile state data and first external environment data are collected; setting a first parameter according to the first vehicle state data and the first external environment data; dynamically generating a charging decision rule according to the first parameter; decision making is carried out on the candidate charging stations according to the charging decision rule, and candidate charging station recommendation schemes are generated; evaluating the candidate charging station according to the candidate charging station recommendation scheme to obtain a target charging station; and feeding back the target charging station to the user and generating a route map for navigating to the target charging station. According to the technical scheme provided by the invention, the rule can be dynamically generated based on the real-time environment data, and the target charging decision system is provided through the multi-target optimization algorithm, so that the user experience and the energy utilization efficiency are improved.

A vehicle travel route control system controls a plurality of vehicles having an autonomous driving function or a driving assist function, wherein a vehicle dispatch information data server creates a travel route map, in which driving mode switching position at which vehicles have switched over during travel to the manual driving mode from the autonomous driving mode, have been added to a road map. Based on the travel route map, a travel route that avoids the driving mode switching position is calculated from among a plurality of routes on which a dispatch vehicle candidate travels to a destination via user position. When a travel route that avoids the driving mode switching position is calculated, a dispatch vehicle candidate is set as a dispatch vehicle, and the calculated travel route information is transmitted to an on-board unit mounted in the dispatch vehicle.

The invention discloses an AI-based new energy commercial vehicle dynamic path optimization method and system, and relates to the technical field of path planning. Determining a driving path between every two effective nodes in the route map to obtain a distance matrix; obtaining an energy consumption matrix according to the distance matrix and the energy consumption rate of the new energy commercial vehicle, and obtaining a time matrix according to the distance matrix and the driving speed of the new energy commercial vehicle; initializing an effective node set and a function node set, and randomly combining effective nodes and function nodes to construct a plurality of expression trees; sorting all client nodes according to the distance matrix, the energy consumption matrix and the time matrix to obtain a client importance list, and substituting the client importance list into a genetic algorithm to determine a route plan of each new energy commercial vehicle; after the new energy commercial vehicles drive one node, the route of each new energy commercial vehicle is dynamically planned, and the operation efficiency of the new energy commercial vehicles is improved.

The invention discloses a probabilistic route map path planning method and device. The method comprises the following steps: S1, acquiring global position information and obstacle information of an automatic driving vehicle; s2, sampling to obtain candidate path nodes; s3, constructing a covariance matrix; s4, calculating the mahalanobis distance between each candidate path node and the barrier distribution; s5, discarding sampling points whose mahalanobis distances are smaller than a set safety threshold, and performing preliminary screening on candidate path nodes; s6, constructing a probability route map based on the screened candidate path nodes; and S7, completing path planning. According to the method, useless and low-efficiency sampling nodes can be accurately eliminated, so that the construction of the probabilistic route map is simpler and more efficient, and the construction quality and effect of the probabilistic route map are greatly improved; meanwhile, interference and calculation burden caused by invalid nodes are reduced, and the efficiency of path planning is remarkably improved; in addition, waste of computer resources is reduced, and resource utilization efficiency is improved.

A method for coronary road mapping may include receiving a current image associated with a medical scan, determining an image that matches the current image from a sequence of images for which respective blood vessel maps have been determined, and overlaying the current image with the blood vessel map associated with the matching image. The sequence of images may be captured when a contrast agent was present, and the matching image may be identified in response to determining that the physiological phase (e.g., cardiac cycle) and / or view depicted by the image match those depicted by the current image. Motion compensation may be performed as part of the blood vessel overlay, which may enable better visualization of blood vessels and medical device(s) (e.g., a catheter) placed in the blood vessels even when the contrast agent is worn out.

The invention discloses a smart park security data early warning method and system based on big data, and belongs to the technical field of security early warning. The system comprises a data acquisition module, a security analysis module, an image management module and a risk early warning module. The data acquisition module is used for acquiring a traffic route map of a park and historical logs of vehicles, and acquiring video images in the park in real time through monitoring equipment; the security analysis module defines a target object through the vehicle and the pedestrian in the video image, calculates a behavior coefficient according to the historical record of the vehicle object, predicts the moving tracks of the vehicle object and the pedestrian object, divides an attention area and calculates a risk coefficient; the image management module calculates a transaction index according to the pixel change condition, defines a risk area according to the transaction index, adjusts parameters of the monitoring equipment, and improves the picture ratio of the risk area; and the risk early warning module is used for displaying the video image of each monitoring device, highlighting the real-time video image of the risk area and performing automatic early warning.

The invention discloses an intelligent design method and system for a well track of a high-density cluster well. The method comprises the steps that a three-dimensional collision detection route map is constructed; performing path search and intelligent obstacle avoidance on the three-dimensional collision detection route map by using a path search algorithm, judging whether the search paths meet the dog-leg degree constraint in the search process, performing path cost calculation on the paths meeting the dog-leg degree constraint in sequence, and sorting and storing the search paths meeting the dog-leg degree constraint according to the path cost; and according to a sorting result, selecting an optimal path, and smoothing the segment of which the dog-leg degree exceeds a preset threshold value. According to the method, a route map from a wellhead position to a target spot for three-dimensional collision detection is automatically constructed through a probability route map algorithm, then an automatic path search algorithm is utilized to perform path search under the condition that the set maximum dog-leg degree is met until an optimal feasible path is found, and local smoothing processing is performed on the found path, so that the optimal path is obtained. The design time can be effectively saved, and the collision risk of the borehole track is reduced.

A method for coordinating a vehicle in a depot divided into multiple function regions, the vehicle being driven in the depot through at least some of the function regions into a defined destination region, includes receiving a travel profile. The travel profile has at least one function rule, each function rule of the at least one function rule being assigned to a function region in the depot and defining how the vehicle is activated and / or may not be activated in the depot in the respectively assigned function region. While the vehicle is being driven through at least some of the function regions into the destination region, the method includes continuously ascertaining a position of the vehicle, ascertaining, from the received travel profile, the function region assigned to the presently ascertained position of the vehicle, and reading in, from the received travel profile, the function rule assigned to the region.

The invention discloses a scenic spot ticket business management system and method based on big data analysis, and relates to the technical field of ticket business management.The scenic spot ticket business management method comprises the steps that all scenic spot route maps in a scenic spot are analyzed, segmented scenic spots are extracted by marking overlapped routes, a ticket is set for each segmented scenic spot, and a distributed ticket selling strategy is formulated in the scenic spot; the peak period and the low peak period of the scenic area are determined by analyzing the sales; calculating a normal people number interval of each scenic spot in the scenic area according to the number of visitors in the history; calculating a circulation threshold value when the tourists are not congested by using the circulation time and distance between the different block scenic spots; whether congestion risks exist in the partitioned scenic spots or not is judged according to the normal people number interval and the circulation threshold value, early warning is carried out, and scenic spot ticket business is adjusted according to early warning information; and in the low peak period of the scenic area, judging the number of visitors of each block scenic spot in the scenic area by using the normal operating interval, and adjusting different block scenic spot tickets according to the number of visitors.

The invention relates to an automatic navigation method and device for a robot with a body, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a task instruction and an environment map; generating a task sequence and a key path point based on the environment map and the analyzed task instruction; sampling points are generated in the environment map, the sampling points serve as nodes, a connecting line, not colliding with the obstacle, between any two nodes serves as an edge, and a probability route map is constructed; obtaining an initial feasible path in the probability route map based on a preset path optimization target and semantic constraint information; the actual position of the dynamic obstacle is obtained in real time, path updating is triggered when the deviation between the actual position and the predicted trajectory exceeds a preset threshold value, and an updated feasible path is obtained; smoothing the updated feasible path to obtain a task path; and converting the task path and the task sequence into a control instruction, and controlling the robot with the body to complete automatic navigation according to the control instruction.

The application discloses a kind of unmanned aerial vehicle autonomous exploration method and device under dynamic unknown environment, method includes: by map module updates current three-dimensional voxel map;By map module, the target boundary region is obtained by boundary processing to current three-dimensional voxel map;By map module, global route map is updated;By perception module, image key information is obtained by current environmental image processing;By planning module, the target working mode of unmanned aerial vehicle is determined according to binary image;If target working mode is detection mode, then control unmanned aerial vehicle detects target detection object and obtains target detection information;If target working mode is exploration mode, then target exploration path is generated by planning module according to target boundary region, global route map and dynamic obstacle information.This application can realize seamless switching of detection mode and exploration mode, guarantee the efficient target search capability of unmanned aerial vehicle when autonomous exploration in dynamic unknown environment, and can be widely applied in unmanned aerial vehicle technical field.

Embodiments relate to a method for diagnosing a failure of a freight car through image analysis based on reinforcement learning and may comprise the steps of: acquiring road image information and wheel image information through at least one sensor installed in a freight car; acquiring freight car-related information and environmental information; generating vehicle-related information on the basis of the road image information, the wheel image information, the freight car-related information, and the environmental information; and providing the generated vehicle-related information to a user.

[Task] The goal is to enable a driver to correctly and intuitively identify a course change point such as an intersection, etc. visually. [Solution] A head-up display device (HUD device 100) comprises both an image display unit 120, which displays a first virtual image (route image) showing a turning point near a course change point of a vehicle, consisting of a section of an arrow shaft extending to the turning point and superimposed on a road surface, and a second virtual image (AR image), the display position of which changes along the first virtual image and which is displayed stationary as the vehicle approaches the course change point near the turning point, as well as a control unit 110, which, when displaying the second virtual image, performs a control operation that projects a shadow image of the second virtual image onto the first virtual image for display.and when the second virtual image comes to a standstill near a turning point of the first virtual image, as the vehicle approaches the course change point, a control action is performed that stops the projection of the shadow image.

The invention discloses a flight trajectory coordinate and orientation correction method and device based on an airport flight area sliding structure chart, equipment and a medium, and the method comprises the steps: constructing a flight area sliding route chart structure chart of a target airport, and obtaining an airport sliding line path segment data set; performing path matching and coordinate point matching on a current track point and a historical track point in the track time sequence of the target aircraft to obtain a matched path and a matched coordinate point; according to the matched coordinate point, determining an end point of a path section of the target aircraft in the advancing direction of the current matched path; according to the matched coordinate point corresponding to the current track point and the end point of the path section, determining a traveling point; and determining a corrected direction value of the target aircraft and a matched coordinate point corresponding to the advancing point based on the matched coordinate point corresponding to the current track point and the advancing point. The invention belongs to the field of aircraft advancing track correction. According to the invention, accurate navigation of the aircraft on the ground can be realized.

This disclosure provides a route map-based parking method, comprising: an on-board parking module receiving a start control signal generated and sent by a terminal parking module; the on-board parking module starting based on the start control signal; the terminal parking module generating a path navigation route map; and the on-board parking module executing a parking control process based on the path navigation route map; or, the on-board parking module sending historical trajectory information of the vehicle associated with its current location and including at least one historical parking target location to the terminal parking module; and the on-board parking module executing a parking control process based on a historical parking target location selection instruction received by the terminal parking module. This disclosure also provides a parking system, an electronic device, a readable storage medium, and a computer program product.

The application discloses a flight trajectory coordinate and direction correction method and device based on an airport flight area sliding structure diagram, equipment and a medium, and comprises the following steps: constructing a flight area sliding route structure diagram of a target airport, and obtaining an airport sliding line path segment data set; performing path matching and coordinate point matching on a current trajectory point and a historical trajectory point in a trajectory time sequence of a target aircraft, and obtaining a matching path and a matching coordinate point; determining an endpoint of a path segment in the advancing direction of the target aircraft on the current matching path according to the matching coordinate point; determining a travel point according to the matching coordinate point corresponding to the current trajectory point and the endpoint of the path segment; and determining a correction direction value of the target aircraft and a matching coordinate point corresponding to the travel point based on the matching coordinate point corresponding to the current trajectory point and the travel point. The application belongs to the field of aircraft travel trajectory correction. The application can realize accurate navigation of the aircraft on the ground.

The invention discloses a method for drawing a patrol route map based on Graphics 2D Qt scanning data, and the method comprises the steps: creating a Graphics 2D object, and constructing an image object of a specified pixel through employing BuffedImage; obtaining point cloud original file data, performing preprocessing, and extracting common point locations, inspection routes and inspection point locations; calculating an offset rate of a coordinate system taking the upper left corner as an original point, the right corner as an X-axis positive direction and the lower corner as a Y-axis positive direction according to the original point location; converting full data according to the offset rate, and performing coordinate system conversion; drawing map elements including routes and inspection point locations by using a Graphics2D tool; and after all elements are drawn, generating an image by using an image writing tool. According to the method, the high-quality patrol route map meeting the fixed resolution requirement can be generated, the display effect and practicability of the image are improved, and meanwhile real-time monitoring and management of a robot patrol system can be conveniently achieved.

Apparatuses and methods related to routing robots are provided. A route map of an environment including first and second robots can be received. The route map can be annotated with one-way lanes connecting conflict areas, where each lane ends to avoid blocking a conflict area. A first route and a second route used by the first and second robots, respectively, can be determined, where the first route and the second route each include a first lane connecting to a first conflict area. A first higher priority and a second lower priority can be assigned to the first and second robots, respectively. It can be determined that the second robot following the second route will block the first robot on the first lane. Based on the first priority being higher than the second priority, a computing device can alter the second route to prevent the second robot from blocking the first robot.

The invention relates to the technical field of AI patrol robots, in particular to an intelligent scheduling system and scheduling method for AI patrol robots. An intelligent scheduling system of an AI patrol robot comprises a scenic spot modeling device which constructs a scenic spot two-dimensional road network based on a scenic spot route map; the people counting device is used for counting the current tourist number of each node in the two-dimensional road network in real time and generating current people flow data; according to the intelligent scheduling system provided by the invention, the initial patrol plan is generated according to the future people number distribution prediction map of the scenic spot, the dynamic matching precision and adaptability of the patrol strategy and the real-time people flow density are remarkably improved, and the inherent limitation of a fixed route patrol mode is effectively overcome.

This invention discloses a method and system for detecting the number of unconventional particulate matter emissions, belonging to the technical field of vehicle monitoring and management. It includes the following steps: a vehicle monitoring system is installed on each heavy-duty diesel vehicle, and the vehicle monitoring system is connected to a cloud server; the vehicle monitoring system monitors the location information and pollutant emissions of the heavy-duty diesel vehicle; the cloud server generates a vehicle driving route map based on the location information and calculates the pollutant emissions; a neural network model is trained using the vehicle driving route map and pollutant emissions; when the vehicle monitoring system receives a new vehicle driving route map, it uses the neural network model to calculate the pollutant emissions corresponding to each short-distance road segment and calculates the total pollutant emissions of the new vehicle driving route map, marking the new vehicle driving route map. This invention has the effect of predicting and displaying details of pollutant emissions from heavy-duty diesel vehicles before the start of a trip, allowing vehicle owners to manage their trips in advance.

An HUD device (100), which is a head-up display device, is provided with: an image display unit (120) that displays a first virtual image (road image) and a second virtual image (AR image), the first virtual image is provided with a bending point in the vicinity of a travel route changing point of the vehicle, is composed of a arrow handle part extending towards the bending point, and is displayed on the road surface in an overlapping manner, and the second virtual image changes the display position along the first virtual image and is displayed in a stagnant manner in the vicinity of the bending point when the vehicle approaches the travel route changing point; and a control unit (110) that, when the second virtual image is displayed, performs control to project a shadow image that displays the second virtual image onto the first virtual image, and when the vehicle approaches the travel route change point and the second virtual image is stopped in the vicinity of the bending point of the first virtual image, performs control to stop projection of the shadow image. According to the present invention, it is possible for a driver to accurately and visually observe a route change location such as an intersection.

Device for providing eco-driving information for a vehicle, comprising: a vehicle weight calculation unit (1) which is configured to calculate a current weight of the vehicle based on data received from a plurality of devices within the vehicle; a computing unit (3) for the electrical load, which is equipped to calculate an electrical load of auxiliary machines currently used in the vehicle; a vehicle speed calculation unit (5) configured to calculate, using a route map, a fuel-efficiency-oriented vehicle speed that maximizes the vehicle's travel distance according to the calculated vehicle weight and electrical load; and a display device (7) which is set up to display the calculated fuel efficiency-oriented vehicle speed to a user. where the weight of the vehicle is calculated from the electricity consumption of a vehicle drive motor, an air density, a drag coefficient, a projection area of ​​the vehicle, the vehicle speed, a coefficient of friction of a current road on which the vehicle is traveling, the acceleration due to gravity and an inclination of the current road on which the vehicle is traveling, where the weight of the vehicle is calculated using the following equation m = ( TF + 1 2 ρ air C d AV 2 ) / ( μ g cos θ+ g sin θ ) where m represents vehicle weight, TF represents a driving force, ρ air which represents air density, C da drag coefficient, A a projection area of ​​the vehicle, V the vehicle speed, µ a coefficient of friction of the current road, g the acceleration due to gravity of the vehicle, and θ the current inclination of the road, and The driving force is obtained from a relationship TF = P / V, where P represents the power input of the drive motor and V represents the vehicle speed. wherein the vehicle weight calculation unit (1), the electrical load calculation unit (3) and the vehicle speed calculation unit (5) are incorporated into a single chip and the route map comprising the vehicle weight, electrical load and vehicle speed is embedded in the chip.

The invention relates to a method for determining an outdated map version of a digital road map (S). According to the invention, it is provided that - if it is determined that a map version already present on the vehicle does not match a specific map version for a transmitted service information (D), it is reported that the service information (D) will be discarded, - for each received service information (D) it is checked whether a map segment version number matches the stored version number of the map segment (K1 to Kn) and in case of a discrepancy this is transmitted with a next request (A) for a service information (D) to the central computer unit (2), - if it is determined that an outdated version number of a map segment (K1 to Kn) exists, the vehicle (1) is prompted to update the map segment (K1 to Kn), - if it is determined that the vehicle (1) has a newer version number of a map segment (K1 to Kn) of the digital road map (S), it is checked why an older version number was not updated for all vehicles (1) in the vehicle fleet, and - in the digital road map (S) the map segment (K1 to Kn) is marked as “not monitored”, in which service information (D) is discarded because there is a discrepancy between the map segment version number and the version number stored on the vehicle.