24 results about "Navigation mesh" patented technology

The present application provides a method for generating a user interface and a method for controlling avatar movement through a user interface. An overhead view, a navigation mesh map and a local environment map that are generated and a main view constitute the user interface. Controlling avatars through the user interface allows users to control the avatars intuitively and immersively while allowing operators to control the freedom of limb movements of the avatars.

The invention discloses an automatic generation method of an intelligent unmanned system city simulation test scene, and relates to the field of simulation scene construction and intelligent unmanned system test.The method comprises the steps that based on terrain boundary parameters, a plurality of rectangular areas with function labels are generated through Poisson disc sampling and a distance gradient algorithm; constructing a navigation grid representing the passable area; arranging a plurality of road intersections by adopting a constrained Poisson sampling algorithm; calculating the heart weight based on each intersection, and calculating the connection strength between the intersections through a gravity model; generating a global road network topology structure by adopting an improved minimum spanning tree algorithm; performing path search by adopting an algorithm A to obtain an optimal path, and automatically generating a road model and ancillary facilities; and extracting road network, road parameters and subsidiary facility information in the generated urban scene, and generating a standardized scene description file according to an OpenDRIVE standard format. And the construction efficiency of the simulation test scene, the test effectiveness and the cross-platform compatibility are improved.

The invention provides a training data generation method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a three-dimensional simulation environment constrained by a natural language navigation instruction; executing the natural language navigation instruction in a simulation environment corresponding to the three-dimensional simulation environment to verify the construction correctness of the three-dimensional simulation environment; if the navigation route is correct, verifying whether the navigation route described by the natural language navigation instruction is reachable in the three-dimensional simulation environment or not based on a navigation grid corresponding to a ground walkable area in the three-dimensional simulation environment; and if yes, generating training data of a visual language navigation task for the preset intelligent agent according to the natural language navigation instruction and the three-dimensional simulation environment. According to the method and the device, the diversity of the VLN training data and the consistency of the three-dimensional space can be considered, and the accessibility of the path corresponding to the navigation instruction in the three-dimensional environment is ensured while the data diversity is improved.

The invention discloses an intelligent label dynamic guidance interactive management system, and relates to the technical field of label management, a weak area identification module analyzes channel connectivity in a navigation grid, identifies an abnormal channel area and marks the abnormal channel area as a weak connection area, a parameter endowing module endowing each path node in the weak connection area with a guidance constraint parameter, and a parameter endowing module endowing each path node in the weak connection area with the guidance constraint parameter; the path optimization module calculates congestion coefficients of the weak connection areas, judges whether the congestion coefficients exceed a coefficient threshold value or not, performs iterative correction on weights of path nodes of the weak connection areas according to the guide constraint parameters if the congestion coefficients exceed the coefficient threshold value, and performs path optimization when the congestion coefficients of all the weak connection areas are detected to be not higher than the coefficient threshold value. And the output module outputs the current global path guiding scheme after iteration optimization to all the intelligent labels for display. According to the management system, an intelligent interaction management mechanism with people flow behaviors as the center is constructed, and transformation and upgrading of a label system from a static guiding tool to a self-adaptive guiding platform are achieved.

The invention provides a processing method and device for a motion path in a virtual scene, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a first navigation grid and a second navigation grid which are not adjacent in a virtual scene, wherein a space area between the first navigation grid and the second navigation grid cannot walk; detecting a motion end edge corresponding to the second navigation grid based on the motion start edge corresponding to the first navigation grid to obtain a target motion end edge; generating a target motion path crossing the space area based on the motion starting edge and the target motion end edge; wherein the target motion path is used for controlling a virtual object to execute a target action along the target motion path when a motion control operation for the virtual object located in the first navigation grid is received, so that the virtual object moves from the first navigation grid to the second navigation grid. According to the invention, the accuracy of generating the motion path can be improved.

This disclosure provides a game editing method, game editing device, program product, and electronic device, relating to the field of game technology. The method includes: during the editing phase of a first game map, in response to a first trigger command, providing component baking setting controls corresponding to a first scene component in a graphical user interface; in response to a first editing operation, determining component baking parameters for the first scene component; during the editing phase, in response to a second trigger command, providing navigation setting controls in the graphical user interface; in response to a second editing operation on the navigation setting controls, determining target navigation parameters; baking the first scene component based on the component baking parameters and the target navigation parameters to generate a navigation mesh; during the running phase, determining the automatic movement trajectory of a first virtual object based on the navigation mesh, and controlling the first virtual object to move automatically. This disclosure lowers the operational threshold for automatic pathfinding settings in UGC editors, improving editing efficiency and flexibility.

The invention provides a motion data processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The motion data processing method and device are applied to various group motion control scenes such as cloud technology, artificial intelligence, intelligent transportation and games. The motion data processing method comprises the steps that the following processing is executed on a target motion individual in a motion group: based on current motion information of the target motion individual, interaction motion characteristics are determined, and the interaction motion characteristics represent interaction between the target motion individual and M other motion individuals in the motion group in the motion process; based on the navigation grid and the current motion information, determining a group target motion feature, the group target motion feature representing a motion feature of the target motion individual for the group target position; determining next motion information in combination with the interaction motion features and the group target motion features; and controlling the motion of the target motion individual based on the next motion information. According to the invention, the authenticity of motion control can be improved.

The invention discloses a dynamic path planning method and system in a mixed reality scene, and belongs to the technical field of computer vision and mixed reality (MR). The method comprises the steps that spatial data of a real environment where a user is located is obtained in real time through a spatial perception interface of mixed reality equipment, and preprocessing is conducted; the spatial data comprises environmental geometric information, plane information and obstacle information; dynamically generating a navigation grid of a passable area based on the preprocessed spatial data; based on the navigation grid, performing path planning by using a path search algorithm, and generating a moving path of the non-player character; and controlling the behavior of the non-player character according to the moving path, and triggering local path re-planning when a dynamic obstacle is detected. The rationality and the intelligent level of non-player character behaviors can be effectively improved, so that the non-player character behaviors are more fit with the current real or virtual space environment of players, and the overall immersion and game performance are enhanced.

The invention relates to the field of meteorological data fusion, in particular to a man-machine collaborative ocean vessel route planning method and system combined with meteorological data, and the method comprises the steps: obtaining historical vessel navigation trajectory data and electronic chart data in response to a route planning request, and generating a global navigation grid covering a navigation area based on the data; generating an initial route from a starting point to a terminal point based on the global navigation grid in combination with preset ship parameters; acquiring weather forecast data, and coupling the weather forecast data with the initial route to deduce a future ship position of a ship on the initial route; based on the deduced initial route, receiving an editing operation of a user on the deduced initial route in real time, and forming an optimized route based on an operation result; according to the weather forecast data, calculating a comprehensive navigation performance index of an optimized route; and outputting the optimized route and the corresponding comprehensive navigation performance index based on the calculation result.

The invention provides a method and a device for generating occlusion data and electronic equipment. The method comprises the following steps of: determining a scanning point from navigation grid data for indicating an area which a virtual character can enter in a virtual scene; determining a collision detection range based on the position of the scanning point, emitting a ray in the collision detection range, and recording collision information of collision between a scene object in the collision detection range and the ray; generating a shielding object coarse model based on a shielding database determined by the collision information; importing the shielding object rough model into the virtual scene, and hiding a plurality of scene objects contained in the virtual scene; and setting a first label for indicating that the scene object is a shelter for the shelter coarse model in the virtual scene, and baking the shelter coarse model provided with the first label to obtain shelter data. According to the method, the shielding object rough model is generated through completely offline automatic scanning and collision information processing, and then the shielding data is generated through baking the shielding object rough model, so that the manufacturing efficiency and accuracy of the shielding data in the offline stage are improved.

The invention discloses a three-dimensional engine positioning and navigation method and device fused with AR navigation and a medium, and the method comprises the steps: obtaining multi-source sensor data, and constructing an environment sparse three-dimensional point cloud; constructing and updating a dynamic navigation grid, importing the dynamic navigation grid and a physical collision body into a built-in physical engine of the three-dimensional engine, and constructing a dynamic digital twin environment model; on the basis of the dynamic navigation grid, searching a global optimal path, generating a curve path conforming to human body movement habits through local movement planning smoothing processing, and meanwhile, triggering real-time re-planning in combination with dynamic environment change to generate a path transition animation; based on the environment sparse three-dimensional point cloud and the curve path, depth testing and template buffering are carried out, virtual guidance elements are driven through a physical engine, and AR navigation guidance is generated through a visual, auditory and tactile multi-modal fusion mode. According to the invention, the navigation positioning precision, the environmental adaptability and the user experience are effectively improved.

The invention relates to the technical field of image analysis, in particular to a robot vision obstacle avoidance path planning method, which comprises the following steps of: dividing an image frame into a plurality of navigation grid units based on the image frame acquired by a camera sensor, and respectively calculating the variance of a gradient magnitude for each navigation grid unit, the standard deviation, the high-frequency component energy and the saturated pixel proportion with the gray level histogram in the navigation grid unit are calculated. According to the method, the image frame is divided into the navigation grid units, the gradient magnitude variance, the gray histogram standard deviation, the high-frequency component energy and the saturated pixel proportion of the grid units are quantitatively analyzed, deep mining of detail characteristics and quality characteristics in the environmental visual information is achieved, and the stability and reliability of visual perception information are improved; on the basis, the depth information and the perception uncertainty are dynamically fused and adjusted, an accurate depth perception result with high confidence is formed, and the accuracy and safety of path obstacle area recognition are improved.

The invention provides an automatic guided vehicle scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a navigation grid, and obtaining the task states of a plurality of guided vehicles, and the plurality of guided vehicles comprise an automatic guided vehicle and other automatic guided vehicles; determining a to-be-scheduled guide vehicle from the plurality of guide vehicles based on the task state of each guide vehicle and a preset priority rule table; if the automated guided vehicle is determined to be the guided vehicle to be dispatched, planning a target planning path of the automated guided vehicle in the navigation grid according to the current position and the target position of the automated guided vehicle; and moving from the current position to the target position based on the target planned path. On the basis, the distributed decision-making mechanism is adopted, each guided vehicle can independently complete local path planning, the single-point fault risk of a centralized architecture is effectively relieved, the calculation load of a center node is reduced, and the system expansibility is enhanced.

The present application provides a user interface generation method and a method for controlling avatar motion by means of a user interface. A user interface is formed by means of a generated aerial view, navigation grid map, local environment map, and front view, and an avatar is controlled by means of the user interface, so that a user can immersively and visually control the avatar, and at the same time, an operator can control the degree of freedom of an avatar body movement.

The invention discloses an airport navigation method and a related device, and relates to the technical field of navigation, and the method comprises the following steps: obtaining a current airport realistic picture and user flight information; wherein the user flight information comprises a navigation destination and the emergency degree of a flight state; carrying out obstacle detection on the current airport realistic image to obtain a detection result; wherein the detection result comprises an obstacle position and a confidence score; generating a navigation grid according to the obstacle position; wherein the navigation grid comprises the passing cost of the area where the obstacle is located, and the passing cost is obtained according to the mapping relation between the passing cost and the confidence score; obtaining a navigation path according to the navigation grid and the navigation destination; and according to the emergency degree of the flight state, the confidence score, the traffic cost and the height variation of the navigation path, generating an identifier for indicating the navigation path, and displaying the identifier on the current airport realistic picture. The guiding effect of airport navigation can be improved, and the problem that passengers enter wrong routes by mistake or miss flights is reduced.

This application provides a method for determining cover positions, an occlusion method, corresponding devices, and electronic devices, relating to fields such as games, artificial intelligence, cloud technology, automatic navigation, and blockchain technology. The method includes: determining each boundary segment of a navigation grid within a predetermined range, and generating candidate query points on each boundary segment; performing ray detection on each candidate query point based on at least one direction to obtain the collision situation of each candidate query point; and determining the candidate query points with collision situations as query points, which are used to determine the position where virtual objects are occluded using cover in the virtual environment. This application embodiment can achieve accurate and efficient cover location, providing a basis for virtual characters to locate cover, thereby improving the accuracy of human-computer interaction in the virtual environment.

The invention relates to the technical field of dismounting path planning, in particular to a path planning method based on mixed information of global memory and local perception, which comprises the following steps: S1, establishing a virtual environment; s2, collecting topographic data of the virtual environment; s3, constructing a virtual maintenance personnel global planner for the static environment of the virtual environment; planning a global moving path of the virtual maintenance personnel in the navigation grid body through a cost evaluation function to obtain an optimal moving direction at the next moment; and S4, constructing a virtual maintenance personnel local planner for the dynamic object in the virtual environment, obtaining local path point information through ray detection, and updating the optimal movement direction of the virtual maintenance personnel at the next moment. According to the mixed information path planning method jointly constructed by the global planner and the local planner, the problems that real-time feedback cannot be achieved and the accuracy is insufficient in a dynamic scene are solved.

This invention relates to a navigation waypoint prediction method for guiding continuous navigation behavior of a robot, comprising the following steps: extracting image feature vectors from panoramic RGBD images captured by the robot's camera; obtaining the robot's current offset angle and expanding the data dimension, then concatenating it with the image feature vectors to form corresponding action feature codes and panoramic image feature codes; aligning the robot's natural language commands with the panoramic image feature codes and orientation angle-related behavioral feature codes, respectively; performing cross-modal attention fusion on the encoded and aligned natural language commands at the decoder end with the command semantics after applying behavioral and visual attention, outputting a panoramic orientation selection prediction result; and predicting the navigation waypoint positions of sub-targets in the local navigation grid based on the panoramic orientation selection prediction result for the single-view RGBD image. Compared with existing technologies, this invention has advantages such as a close correlation between waypoint prediction and the navigation process, and strong model generalization.

The invention discloses a navigation grid generation method, a related device, equipment and a storage medium. The method comprises the following steps: acquiring an initial navigation grid corresponding to a virtual scene map; obtaining a first initial polygon from the initial navigation grid; determining T polygons having a reachable relationship with the first starting polygon from the initial navigation grid; under the condition that T is smaller than K, according to the T polygons, obtaining the remaining (K-T-1) polygons from the initial navigation grid; and removing (K-T-1) polygons from the initial navigation grid to obtain a first target navigation grid. According to the method provided by the invention, the unreachable polygons can be automatically screened and removed from the initial navigation grid, so that the labor cost is saved, the resource consumption can be reduced, and the memory space is saved.

The application provides an NPC following position positioning method and device and a computer device, and relates to the technical field of three-dimensional games. The application determines an effective detection grid area of a target player character in a two-dimensional map grid range of a current game scene by acquiring character position information of the target player character when the target player character is beyond a navigation grid coverage range of the current game scene, extracts a plurality of expected grid edges from all navigation grid edges of the current game scene, the expected grid edges at least partially overlap with the effective detection grid area and character height data is in a corresponding effective edge height range, and then determines a to-be-positioned grid edge with the shortest vertical distance from the target player character to each expected grid edge by traversing the plurality of expected grid edges. A vertical point position of the to-be-positioned grid edge corresponding to the target player character is taken as an expected following position of a target NPC, so that the automatic following effect of the NPC is quickly realized, and the game experience of a game player is improved.

The invention relates to the technical field of artificial intelligence, and discloses an open scene tool intelligent interaction method and system based on a multi-modal large model, and the method comprises the steps: generating a navigation grid and an action feasibility matrix related to a new environment; generating matched candidate actions in response to a natural language instruction input by a user; calculating success probabilities of the candidate actions according to the action feasibility matrix; optimizing the candidate action according to the success probability of the candidate action to determine a final execution action; aligning the interaction point to the geometric center of the target object according to the visual observation image of the new environment and the natural language instruction; and controlling the action execution of the intelligent agent according to the attribute of the final execution action. Thus, after the agent enters a new environment, through autonomous perception and analysis reasoning of scenes and semantics, decision-making of final execution actions is realized based on the action feasibility matrix, and action execution of the agent is controlled based on the attributes of the final execution actions, so that semantic planning and physical execution are better linked, and the agent can better adapt to an unknown environment.

The application discloses a route searching method and device and a storage medium. The method comprises the following steps: generating a navigation grid for an input scene; detecting whether a feasible area of the navigation grid meets a first preset standard requirement; if the feasible area of the navigation grid meets the first preset standard requirement, searching a route according to the feasible area of the navigation grid, and generating a route searching route. In this way, the application can automatically and batch detect the feasible area of the navigation grid, and improve the production efficiency.

This invention provides a three-dimensional path planning method, system, and electronic equipment for nuclear engineering plant buildings, belonging to the field of nuclear engineering radiation protection technology. The method includes: discretizing the three-dimensional geometric model of the nuclear engineering plant building into multiple voxels, and labeling each voxel with a radiation dose rate value based on radiation field data; labeling each voxel with the traversability results corresponding to the M protection levels according to preset geometric constraint parameters and radiation constraint parameters, obtaining a multi-level traversability voxel map; generating navigation meshes corresponding one-to-one with each protection level; receiving path planning requests; loading the corresponding navigation meshes according to the requests; and running an improved heuristic search algorithm on the loaded navigation meshes to search for the optimal three-dimensional path from the starting point to the destination. This method addresses the problem in related technologies where path planning fails to adequately consider radiation safety and does not match the safety requirements of protection levels.