22results about How to "Quick planning" patented technology

The invention relates to an emergency vehicle control method based on an intersection dynamic lane in an intelligent network connection environment, and belongs to the field of emergency traffic control. The method comprises two parts of macroscopic planning and microcosmic control. According to the macroscopic planning part, an optimal path from an emergency vehicle to an accident point is planned through an A * algorithm, and a traffic organization method of each intersection is determined. According to the micro control part, an intersection is divided into a normal driving area, a buffer area and a conflict area through the vehicle-road cooperation technology, a road side control unit is used for planning a special lane for emergency vehicles, then other vehicles in the special lane are regulated and controlled to change lanes and enter a variable regulation and control lane, and finally the passing phases of the special lane and the variable regulation and control lane are controlled. And the emergency vehicle can be ensured to rapidly pass at a high speed per hour when driving into the buffer area. According to the method, the efficiency and the safety of emergency traffic are effectively improved by accurately controlling the intelligent signal lamp and combining the lane queue length and passing phase calculation.

The invention discloses an in-building emergency rescue system and method based on digital twinning modularization and multi-scale simulation, and the system comprises a parameterization equipment model construction module, a parameterization floor environment simulation module, a data real-time collection and monitoring module, a fault monitoring and fault analysis module, and an emergency rescue path intelligent generation module. And a user interaction interface module. The system adopts a modular design, can be independently deployed and can also be flexibly combined so as to meet the requirements of different building structures, floor environments and elevator brands. Meanwhile, by means of the multi-scale simulation technology of a Unity 3D platform, high-precision simulation and visualization of the operation state of the equipment are achieved, operation and maintenance personnel and rescue personnel can visually and accurately know the operation state of the equipment and the floor environment, a precise and visual virtual environment is provided for emergency rescue, and the safety of emergency rescue is improved. And powerful technical support is provided for development and application of a simulation equipment emergency rescue system.

The application discloses a power emergency passage evaluation method and system based on a spaceborne hyperspectrum, belongs to the technical field of power grid engineering management and emergency disaster rescue management, and comprises the following steps: receiving a spaceborne hyperspectrum remote sensing image and a geographic elevation data set; extracting a surface material characteristic vector matrix and combining the elevation data set to construct a three-dimensional landform model; performing surface disaster element identification on the model to generate an emergency passage topological network containing a passage blocking node and a passable edge link; and performing emergency rescue path optimization operation based on the network to generate a power emergency passage evaluation result. The method can intelligently avoid blocking risks, and accurately and efficiently plan a post-disaster power repair route by adopting multi-band hyperspectrum data fusion modeling and combining disaster element identification to construct a topological network for optimization.

The invention discloses an optimal path planning method of a pulse coupling neural network based on double constraints. The method comprises the following steps: mapping a path planning environment to a DC-PCNN network; a DC-PCNN neural network model is constructed, and all neurons are initialized; activating a target neuron, and recording the current neuron as a father node; calculating an exponential decay function of the torque deviation, and multiplying the calculated value as a penalty factor by an update item of the internal activity item; calculating a gravitational function value of the flow field constraint, and using the calculated value to update a current neuron dynamic threshold value; comparing the internal activity item with a dynamic threshold; when gt; if yes, activating the neuron, and recording the current neuron as a father node; repeating the steps S4-S6 until the initial neuron is activated; and backtracking all activated nodes, and planning an optimal path. According to the method, the search efficiency is remarkably improved while the path optimality is ensured.

The invention discloses an emergency evacuation planning method based on improved ant colony algorithm and genetic fusion, and belongs to the technical field of emergency management and public safety. The method comprises the following steps: constructing a multi-objective optimization model taking minimization of total evacuation time T, total road section risk R and total personnel panic index P as objectives, and solving the multi-objective optimization model based on fusion of an improved ant colony algorithm and a genetic algorithm to obtain an optimal evacuation path scheme. The evacuation efficiency, safety and personnel psychological factors are comprehensively considered, the state transition probability and the pheromone updating strategy of the ant colony algorithm are improved, the global search mechanism of the genetic algorithm is introduced for deep fusion, and finally, the evacuation efficiency can be improved in a complex evacuation scene. And a global optimal evacuation path giving consideration to timeliness, safety and personnel psychological factors is quickly planned, and the evacuation efficiency is effectively improved.

The utility model discloses a hydraulic multi-pipeline simulation device which comprises a box body and a connecting pipe, a plurality of first simulation pipes and second simulation pipes which are mutually parallel and crossed are arranged in the box body, and each first simulation pipe is communicated with all the second simulation pipes. Solenoid valves are installed at the two ends of the first simulation pipe and the second simulation pipe and on the first simulation pipe or the second simulation pipe between the adjacent joints, the solenoid valves are electrically connected with an operation panel, and a pressure sensor, a flow sensor and a temperature sensor are installed in the box body. According to the utility model, a plurality of different paths are formed by the plurality of mutually connected first simulation pipes and second simulation pipes, and the opening and closing of each electromagnetic valve are freely controlled by using the operation panel, so that the paths needing to be simulated can be quickly planned and adjusted, the effect of simulation diversification is achieved, and the simulation efficiency is improved. The problems that an existing pipeline path testing device is complex to disassemble and assemble and low in efficiency are solved.

The ship trajectory monitoring method and system based on Beidou positioning of the present invention belong to the field of radio positioning technology. The buoy component is applied to trajectory monitoring and navigation route planning. Before the ship sails, the obstacles faced by the ship during navigation or the ocean conditions during the ship's navigation can be monitored in advance according to the set buoy component, and the navigation route of the ship can be planned in advance. When the navigation route needs to be changed, the original coordinate position of the buoy component can be used as the center of the circle and a certain distance can be used as the radius to drive the collection buoy to rotate around the ocean to detect the sea conditions or obstacle information on the ocean surface. After comparison, the best navigation position is selected, and the buoy component is changed from the original coordinates to the existing best navigation position coordinates, thereby re-planning the navigation route of the ship, and the navigation route of the ship can be planned quickly, accurately and more safely.

The present invention relates to the field of intelligent networked vehicle testing, and in particular, to a lane line positioning method, system, electronic device and medium. The lane line positioning method comprises: constructing a coordinate system according to the initial position of the vehicle sent by the navigation positioning device on the vehicle; the origin of the coordinate system is the initial position of the vehicle, and the direction in which the front of the vehicle points is the X direction; determining multiple positioning intervals according to the initial position of the vehicle, the expected path, lane line information and the coordinate system; the positioning interval includes a corresponding initial position and an end position; controlling the vehicle to travel along the expected path starting from the initial position of the vehicle; when the vehicle is located in the positioning interval, controlling the powder leakage marking device to leak powder, and the powder leakage marking device includes a left powder leakage port and a right powder leakage port. This method is free from a large amount of manual operation, can realize automatic marking, and has higher accuracy and efficiency.

The invention relates to the technical field of group collaborative robots, in particular to a robot and a motion control method and device thereof. The method comprises the steps of obtaining a task point location of a task area according to preset task information; acquiring a barrier point location in real time; constructing a composite concentration field based on the task point location and the obstacle point location; acquiring a current point location of the robot, and constructing a target circular area; obtaining a first target point location, and determining a first motion vector of the robot based on the first target point location; acquiring motion information of each collaborative robot, and determining a second motion vector of the robot based on the motion information; determining a target motion vector based on the first motion vector and the second motion vector, and controlling the robot to move to a second target point location; and if the second target point location is not overlapped with the task point location, repeating the steps until the second target point location is overlapped with the task point location. The task execution efficiency of the robot can be improved, and obstacle avoidance can be effectively carried out.

The present invention belongs to the technical field of hypersonic aircraft trajectory planning, and discloses a hypersonic aircraft trajectory planning method based on reinforcement learning, including constructing a trajectory planning scenario; designing an action set, a state space, and a reward form; establishing a DQN network, inputting the current state into the DQN network, and outputting the evaluation value of each element in the current state; based on the trajectory prediction result, filtering the inactive actions in the current state, and modifying the evaluation value of the inactive action element; selecting the action element with the highest evaluation value as the aircraft kinematic equation input, and updating the position, speed, and state based on the aircraft kinematics; judging whether the trajectory planning task is completed according to the latest position, and starting training after completion. The present invention improves the accuracy and rapidity of hypersonic aircraft trajectory planning, and provides strong support for the safe flight of hypersonic aircraft.

The application provides an antenna profile precision measurement method based on unmanned aerial vehicle photogrammetry. Firstly, flight and photogrammetry parameters of the unmanned aerial vehicle used for antenna profile precision measurement are preliminarily planned according to antenna parameters. Then, the light incidence angle, the frequency of being photographed and the intersection angle of the to-be-measured points on the main reflector of the antenna are calculated according to the antenna equation and the camera station position. The shooting effect of the unmanned aerial vehicle photogrammetry is evaluated according to the frequency of being photographed and the intersection angle of all the to-be-measured points on the main reflector of the antenna. Then, the camera shooting angle at the camera station coordinate position is planned based on the obtained each unmanned aerial vehicle camera station coordinate. The final obtained camera station position and shooting angle of the unmanned aerial vehicle photogrammetry are converted into a path planning file executable by the unmanned aerial vehicle, and the photogrammetry is automatically performed by the unmanned aerial vehicle photogrammetry system. The application can quickly plan the unmanned aerial vehicle shooting position and shooting angle under the premise of ensuring the measurement precision.

The invention discloses a whole body motion planning system and method based on contact mode switching, and belongs to the technical field of robots. The method comprises the following steps: acquiring a centroid feasibility map representing environmental geometric information and physical attributes; determining a centroid target trajectory from an initial state to a target state according to the centroid feasibility map; and based on the centroid target trajectory and the centroid feasibility map, according to a preset cost function, planning to obtain a contact mode sequence. The system includes modules for performing the method. According to the method, the guiding track is planned in the low-dimension centroid space firstly, then the track serves as a strong constraint to reversely solve the contact sequence, the problem of combinatorial explosion in traditional contact state space search is fundamentally avoided, and the technical problems that in the prior art, planning calculation complexity is high, and the real-time requirement is difficult to meet are solved.

The application discloses an interactive scanning viewpoint online generation planning method, and belongs to the technical field of assembly state detection, and comprises the following steps: a, pasting a circle of coding blocks at the boundary of a scanning area; b, completing global three-dimensional reconstruction of all coding blocks; c, setting pose adjustment parameters of a coordinate system, and calculating an adjusted coordinate system homogeneous matrix; d, determining the connection order between reference sampling points according to a continuous scanning type, generating other sampling points between the reference sampling points and corresponding sampling directions; e, generating scanning viewpoints and corresponding scanning directions by using sampling point positions and sampling directions according to an effective scanning distance; and f, completing online generation planning of the scanning viewpoints. Through online generation of the scanning viewpoints, the application can realize self-positioning of a scanning device, and can also realize fast generation and planning of a large-range scanning viewpoint in a non-structure environment without a model, and has good applicability.

The invention provides a remote dispatching system and method for a fire scene, and relates to the technical field of fire dispatching, wavelet transformation is performed on a collected on-site thermal infrared image to obtain an interference-free on-site thermal infrared image, fire node extraction is performed on the interference-free on-site thermal infrared image to obtain all fire nodes in a target fire scene, and the fire nodes in the target fire scene are extracted. Determining a fire behavior spreading coefficient of each fire node in the target fire scene; acquiring fire scene information of the target fire scene, constructing a path topological graph by using corresponding node position parameters of each fire node in the fire scene information and all fire behavior spreading coefficients, and performing path search on the path topological graph according to scene fire behavior characteristics in the fire scene information to obtain a fire-fighting advancing path; the remote dispatching center dispatches the fire-fighting vehicles on the fire scene based on the fire-fighting advancing path, and transmits the state data to the block chain, so that a safe and effective fire-fighting path can be searched in time in a complex fire scene environment, and the efficiency of the remote dispatching system is improved.

The present invention discloses a trajectory planning system based on a kinematic model of a quadruped robot. Based on the movement characteristics of the quadruped robot, the lateral movement ability of the quadruped robot is taken into account, and the influence of the angle between the robot speed and the robot orientation on its movement rate is also taken into account; the moving task of the quadruped robot is simplified to point-to-point movement, and it is only necessary to complete the state increment required by the quadruped robot within a specified time; using the kinematic model of the quadruped robot and the moving task, a passable trajectory is automatically generated, and the shortest time to complete the moving task is found at the same time. The present invention can realize the unstructured trajectory planning of the quadruped robot, has the advantages of high efficiency and speed, and solves the disadvantage that the current quadruped robot can only use inefficient and low-adaptability trajectory planning methods.

The invention discloses a ship track monitoring method and system based on Beidou positioning, and belongs to the technical field of radio positioning. According to the invention, obstacles in the ship navigation process or ocean conditions in the ship navigation process can be monitored in advance according to the arranged buoy assembly before the ship runs, the navigation route of the ship is planned in advance, and when the navigation route needs to be changed, the position of the original coordinate of the buoy assembly can be taken as the circle center in advance; by taking a certain distance as a radius, the acquisition buoy is driven to rotate around the ocean so as to detect the sea condition or obstacle information of the ocean surface, the optimal navigation position is selected after comparison, and the original coordinate of the buoy assembly is changed into the existing optimal navigation position coordinate, so that the navigation route of the ship is re-planned, and the navigation efficiency of the ship is improved. The ship navigation route can be planned quickly, accurately and more safely.

The invention discloses an automatic following and autonomous navigation system for fruit and vegetable collection and transportation, and relates to the technical field of following navigation. The control center is in communication connection with an environment sensing module, a target recognition and positioning module, a relative course deflection angle detection module, a deflection angle adjustment decision module, a power and steering execution module, an autonomous navigation planning module and a man-machine interaction module, and all the modules are in electric signal connection. Through autonomous navigation and obstacle avoidance functions, the following vehicle can automatically and accurately follow the guiding vehicle or autonomously plan the path, complex transportation tasks can be completed without manual intervention, meanwhile, the system can rapidly plan the optimal path according to the target position and the current position, the transportation time is further shortened, the transportation efficiency is improved, and the transportation efficiency is improved. The system also has high-precision positioning and attitude estimation capability, can obtain the position and attitude information of the following vehicle in real time, and ensures that the following vehicle can stably run in a complex environment.

The present invention provides a method, medium and device for realizing multi-task motion of a robot based on temporal logic. The method expands the traditional TLTL to wTLTL (Weighted truncated linear temporal logic, hereinafter referred to as wTLTL), and combines DMPs with wTLTL to realize complex operation tasks with user preferences. The DMPs are used to approximate the trajectory with user preferences, and the trajectory shape is determined by the DMPs parameters, and the black box optimization strategy (Policy Improvement with Black‑Box optimization, hereinafter referred to as PI) based on the weighted average covariance matrix is ​​used to optimize the trajectory shape. BB ) for optimization. The wTLTL provides interpretable task specifications and is able to design a cost function with user preferences based on quantitative semantics. BB The algorithm is used to identify the optimal shape parameters of DMPs, thereby realizing the motion trajectory of complex operation tasks. The user preference is reflected by adjusting the weight in wTLTL. Compared with the traditional multi-task operation motion planning method, this method can quickly plan the motion trajectory of complex operation tasks with user preferences, with low computational complexity and high planning efficiency.

This invention relates to the field of control, and in particular to an edge computing collaborative control method and system for heterogeneous interconnection of multiple devices in an intelligent manufacturing unit. Specifically, by collecting functional metadata and real-time status data of heterogeneous devices, a weighted directed acyclic service graph is constructed based on a unified resource representation framework, and the weights of the edges in the graph are initialized as collaborative costs. Then, the production task is parsed as the target state of the service graph, and multiple candidate collaborative paths are generated through reverse search. A resource occupancy spatiotemporal tensor is constructed for each path and the execution risk coefficient is calculated. The path with the smallest coefficient is selected as the optimal task sequence. Subsequently, control commands are distributed and theoretical state vectors are predicted. The feedback from the collected devices is fused into actual state vectors. The Mahalanobis distance between the two is calculated. If the distance exceeds a threshold, the current sequence is frozen, a compensation path is replanned, and the collaborative costs of the corresponding edges of the service graph are updated nonlinearly based on the distance and abnormal task segments.

The present disclosure provides a method and device for unmanned equipment path planning, which relates to the field of unmanned equipment. The method includes: determining the positions of various landmarks in the warehouse; taking the current landmark as the current node, obtaining the landmark corresponding to the goods to be picked that is closest to the path of the current node, and taking the landmark corresponding to the goods to be picked as the current node, repeating the steps of obtaining the landmark corresponding to the goods to be picked that is closest to the path of the current node, and taking the landmark corresponding to the goods to be picked as the current node, until the landmark corresponding to the last goods to be picked is obtained, wherein the initial value of the current node is the initial landmark of the unmanned equipment; and taking the line formed by the initial landmark of the unmanned equipment and the landmarks corresponding to the goods to be picked selected in sequence as the driving path of the unmanned equipment. The present invention can quickly plan the travel route of the unmanned equipment in the warehouse.

This application discloses a route planning method, apparatus, electronic device, and storage medium. This application can acquire a first topographic map; generate an initial road curve for the first topographic map; divide the first topographic map into multiple first topographic blocks according to a preset division rule; determine a first target topographic block from the multiple first topographic blocks, the first target topographic block being a first topographic block containing curve segments of the initial road curve; perform route planning processing on the first target topographic block based on the curve segments contained therein to obtain sub-routes corresponding to the first target topographic block; and determine the target route corresponding to the first topographic map based on all the sub-routes corresponding to the first target topographic blocks. In this application embodiment, the computational resources required to plan the target route corresponding to the first topographic map can be reduced, thereby improving the efficiency of route planning.

The invention discloses a mountainous area environment multi-unmanned aerial vehicle path planning method based on a Q-learning optimized dual-objective eagle algorithm. The method comprises the steps that 1, a dual-objective function with the minimum unmanned aerial vehicle flight distance and the threat cost under the mountainous area background as the dual-objective function is constructed; 2, establishing spatial constraints such as a three-dimensional terrain environment, a mountain obstacle and a radar threat area and multi-machine related constraints; and 3, designing a Q-learning-fused multi-action disturbance strategy to guide adaptive behavior selection of the Balde Eagle algorithm in a search process, thereby obtaining an optimal unmanned aerial vehicle flight path. According to the method, the reinforcement learning strategy is embedded into the bald eagle algorithm, and the precision, stability and safety of unmanned aerial vehicle path planning are improved through adaptive search in a complex three-dimensional terrain, so that reliable support is provided for unmanned aerial vehicle autonomous operation in actual scenes of mountain reconnaissance and electric power inspection.