88results about How to "Reduce planning time" patented technology

The invention discloses a spray gun track planning method for a free-form surface spraying robot. According to the spray gun track planning method disclosed by the invention, the characteristic that a numerical control processing process is very similar to the spaying process is utilized, so that the motion track of a spray gun can be obtained by little calculation on the basis of the tool path. The method comprises the following steps of: firstly, dividing the sprayed surface in three-dimensional modeling software into a plurality of areas with regular shape, generating m equidistant tool paths and deriving the equidistant tool paths into standard APT (Automatic Programming Tools) files by using a five-axis numerical control machining method; extracting tool motion information contained in the APT files, extending the obtained tool points, processing the corner parts into circular arc transition to generate a spray gun path point sequence and then solving a spray gun posture sequence on the path point sequence; and interpolating the spray gun posture sequence to generate a complete motion track of the spray gun. According to the spray gun track planning method disclosed by the invention, accurate control over the track of the spray gun can be realized and the high praying quality is ensured; and the spray gun track planning method is simple in calculation process and calculation amount.

A computer-implemented method is provided for assigning tasks to resources. The method includes receiving one or more constraints corresponding to each of the tasks and one or more constraints corresponding to each of the resources. The method also includes receiving a value from a user defining at least one of a plurality of variables including: (i) a resource variable representing resources available for allocation to the tasks, (ii) a duration variable representing a time frame for completing the tasks, and iii) a scope variable representing one or more of the plurality of tasks requiring execution. The method further includes applying a first optimization scheme to determine a value for each undefined variable to formulate a task delivery plan and applying a second optimization scheme to determine a task for assignment to a resource.

Systems and methods for rotating shield brachytherapy. In an aspect, some of the systems and methods can be used to facilitate shield selection for use in rotating shield brachytherapy. In an aspect, the invention is a shielded needle or catheter system with a rotational controller for delivering radioisotope-based interstitial rotating shield brachytherapy (I-RSBT), In an aspect, I-RSBT needles can deliver dose distributions that can be non-radially symmetric about each needle, enabling reduced doses to sensitive normal tissues. Further provided are methods and systems for selecting an emission angle for use in S-RSBT and for sequencing the rotating shields. Further provided are methods and system for the multiple application of M-RSBT in a single setting.

The invention belongs to the field of remote control and artificial intelligence and relates to an intelligent adjuvant therapy robot device for performing real-time social capability training for autism children. The device comprises a head movement driver (1), an arm movement driver (2), a device loader (3), a driving-driven wheel type chassis (4) and a casing module (7). A multi-joint combined driving mode is adopted, the collaborated driving capability of the robot for every movement joint is improved, the problem that time delay affects the interaction effect is solved, precise posture control of the robot in the random direction is achieved, a limb movement path planning function for automatically avoiding obstacles is achieved, and intelligent emotion interaction between a human and the robot and a safe and reliable family remote rehabilitation therapy model are achieved in various modes such as voice, images, touch and induction in the man-machine interactive process in response to emotion cognitive disorder which occurs universally in child patients.

The invention discloses a global path planning method based on a weighted A * algorithm for expanding a search neighborhood, and the method comprises the steps: S1, carrying out the environment modeling according to the point cloud information collected by a sensor, and building a two-dimensional environment model through a grid method; S2, optimizing a target cost estimation function h (n) in anestimation function f (n) of path planning of a weighted A * algorithm for expanding a search neighborhood, adding distance information and angle information, and performing weighted measurement; S3,expanding the searchable neighborhood of the current node of the A * algorithm; and S4, according to the searchable neighborhood obtained in the step S3 and the estimation function cost value of the calculation A * algorithm defined in the step S2, sequentially selecting the node with the minimum global estimation cost value as the next node until the target point, so that the path is the shortestpath. By designing the new heuristic function and expanding the operation of searching the neighborhood, the optimized A * algorithm is more excellent in path length, better in smoothness and shorterin path finding time compared with the original algorithm, and can be suitable for the situation with many obstacles.

The invention provides a surgical puncture path intelligent automatic planning method and system based on machine learning and a medical system. The surgical puncture path intelligent automatic planning method and system based on machine learning and the medical system can rapidly determine a surgical puncture path and a needle inserting point position and can allow a brain stereotaxic apparatus or a medical mechanical arm to achieve automatic puncture surgery operation. The planning method comprises the following steps that (1) sample image data of an existing case are acquired, and trainingdata and test data are made; (2) a three-dimensional segmentation deep neural network model is designed, and the three-dimensional segmentation deep neural network model is trained; (3) the sample image data of a patient are segmented and identified by using the trained three-dimensional segmentation deep neural network model; (4) a three-dimensional model is constructed based on a segmentation identification result and the sample image data; (5) a safe needle insertion constraint area is determined based on the target point position and medical prior information; and (6), in the safe needle insertion constraint area, a three-dimensional space trajectory planning algorithm is utilized to complete surgical puncture path planning.

The invention is suitable for the intelligent robot technology field, and provides a method of an intelligent robot of automatically planning paths. The method is characterized in that after a to-be-reached destination position is received by the intelligent robot, the path planning mode is switched on; by taking the current position of the intelligent robot as the start point, the intelligent robot is used to calculate the position of the next step by adopting the fuzzy logic algorithm; the intelligent robot can move from the current position to the position of the next step according to the calculated position of the next step; the intelligent robot is used to determine whether the position of the next step is the destination position; when the position of the next step is not the destination position according to the determination result, the process of taking the current position as the start point, and calculating the position of the next step by adopting the fuzzy logic algorithm can be carried out again; the operation can be ended until the position of the next step is the destination position according to the determination result. According to the invention, the defect of the conventional security robot of inability of planning the paths automatically can be overcome, and the technical scheme of planning the paths simply and effectively can be provided, and the intelligentization of the intelligent robot can be improved.

The invention discloses a complex curved surface machining track generation method in off-line programming. The complex curved surface machining track generation method in off-line programming comprises the steps of using a NURBS complex curved surface track generation algorithm based on STEP standard to generate a track and visualize the track; before animation simulation, detecting the generatedtrack points in advance by using a robot kinematics algorithm so as to detect abnormal points such as unreachable points, axis overrun points and jumping points; and correcting the abnormal points byusing a track posture correction module until all the track points are normal, and finally performing animation simulation by using computer graphics, and converting the post-code into a real machineto operate. The complex curved surface machining track generation method in off-line programming can be applied to generating and planning a complex curved surface machining track in off-line programming and provides systematic solutions for the problems of high workload, high difficulty, low efficiency and the like of manual demonstration for machining a complex curved surface by a robot; the method has the characteristics of high precision, speed and universality and good simulation visualization effect, and can be widely applied to the machining environment of the complex curved surface; and meanwhile, the provided complex curved surface track generation algorithm is high in precision and robustness.

The invention discloses a time-optimal trajectory planning system and method for robot path tracking. The system comprises a path processing unit, a trajectory planning unit and an instruction generating unit. The path processing unit performs path displacement calculation processing, path function fitting processing, path differential coefficient calculation processing and path planning point selection processing. The trajectory planning unit is used for planning an optimal trajectory. The instruction generating unit is used for generating a control instruction and the like. Besides, the method comprises the following steps: S1, carrying out path displacement calculation processing; S2, acquiring a path function; S3, carrying out path differential coefficient calculation processing; S4, selecting a path planning point; S5, calculating a path boundary speed and acceleration of the planning point; S6, planning a time-optimal trajectory; S7, acquiring each control period path displacement; S8, acquiring angular displacement of each axis at each moment; and S9, converting the angular displacement of each axis into a control command pulse signal and the like. Therefore, the path tracking time and computation time of trajectory planning are shortened.

The invention discloses a multi-dimensional constraint wind power plant current collection line automatic planning method. The method comprises the steps: 1) intelligent partitioning; 2) optimal planning of cost in the area; 3) the global cost of cross-regional planning of the line being optimal; 4) T-connection path optimization. According to the invention, the problems of large calculation amount and long time of the traditional NP algorithm such as dimensionality disaster, genetic algorithm, RRT fast search algorithm, ant colony algorithm and the like are solved. Large-scale and large-quantity wind power plant current collection line planning problems are broken in a regional and hierarchical manner, so that the problems of high strength, nonlinearity and high time complexity of currentcollection line planning are solved. The planning of the wind power plant can be carried out considerably and gradually, self-optimization is carried out under multi-dimensional constraints, and theinfluence of human factors on a planning result is reduced.

The invention discloses an autonomous attitude maneuver control method of a deep space probe, which relates to the autonomous attitude maneuver control method and belongs to the technical field of spacecraft attitude control. The autonomous attitude maneuver control method comprises the following steps of carrying out random sampling on uniformly-distributed nodes of an attitude space with an ORRT (Optimized Rapidly Exploring Random Tree) algorithm as a path planning method, making a balance and choosing the optimum path to expand, carrying out incremental expansion in a safety space in a greedy expansion manner, respectively establishing a probe attitude maneuver dynamic constraint model, an actual engineering constraint model and a probe geometric constraint model under a probe body coordinate system to obtain path nodes which meet the constraint and generate a control moment for the nodes, thereby generating a probe attitude maneuver path and a required control moment, and implementing the purpose that probe maneuvers to a target attitude according to the generated probe attitude maneuver path and the required control moment. According to the autonomous attitude maneuver control method, the path planning time is shortened and the efficiency that the probe maneuvers to the target attitude from the initial attitude is improved under the condition that all kinds of complicated constraint conditions faced by the probe are met.

The invention provides a multi-platform joint task planning method for complex observation tasks. The method comprises the steps of preprocessing complex observation tasks and obtaining a plurality ofsubtasks corresponding to the geographic grids; constructing a multi-platform joint task planning model; substituting the plurality of sub-tasks preprocessed in the step 1 into a multi-platform jointtask planning model for solving; depending on solving results, outputting a task sequence of decomposing a complex observation task on each observation platform; according to the method, task preprocessing, optimal modeling, swarm intelligence and machine learning are organically combined, so that complex problems are simplified, experiments show that the multi-platform joint task planning time for complex observation tasks can be shortened to the minute level from the hour level, and the planning efficiency of multi-type observation platforms is effectively improved.

The invention discloses a planning method for a power distribution network wiring line. The method comprises the steps: performing the grid division of a target power distribution network region, abstracting the grids as path nodes, further determining the distances between the path nodes and the power distribution loads of the path nodes, and finally determining the optimal wiring line of the path nodes in the target power distribution network region by utilizing an ant colony algorithm according to the power distribution loads of the path nodes, the distances between the path nodes and the maximum load capacity of the line. Therefore, the method utilizes the ant colony algorithm to iteratively optimize and solve the wiring line of the plurality of nodes in the power distribution network.Due to the fact that the ant colony algorithm can summarize the information harvested in the iteration process every time after the iteration process, a reference is provided for the subsequent iteration process, thereby remarkably increasing the planning speed after the ant colony algorithm is used for power distribution network planning, and saving the planning time. In addition, the inventionfurther provides a planning device and equipment for the power distribution network wiring line and a computer readable storage medium, wherein the functions of the device and equipment are corresponding to those of the method.

The invention discloses a plant cultivation recommendation method, which comprises the following steps: when a planting area selection instruction is received, obtaining a target area corresponding tothe planting area selection instruction; obtaining environment information of the target area, wherein the environment information comprises local climate, temperature information and soil texture information; and outputting plant recommendation information according to the local climate, the temperature information and the soil texture information. The invention further discloses a plant cultivation recommendation device and equipment and a computer readable storage medium. According to the invention, the environmental information in the target area is acquired, the plants suitable for planting in the target area are determined according to the environmental information, and the plants suitable for planting are recommended to the user, so that the intelligence of plant planting is realized, and the plant planting in the target area is more accurate.

The invention provides a navigation path planning method based on area segmentation and a computer readable storage medium. The navigation path planning method based on area segmentation comprises thefollowing steps of acquiring an area planned in a golf course, averagely dividing the planned area into an upper area and a lower area; carrying out path pre-planning in each area by adopting a PRM algorithm; finding a target upper feasible point and a target lower feasible point, determining a target upper path and a target lower path, and connecting the target upper feasible point and the target lower feasible point according to a second preset rule to obtain a target middle path; taking the paths of the target upper path, the target middle path and the target lower path as the first targetpaths, and guaranteeing that no obstacle exists on the first target paths, thereby completing the preliminary path planning of a golf cart. According to the present invention, the planning time is shortened to a certain extent, the planned path length is shortened, the number of path nodes is reduced, and the golf ball collecting efficiency is improved.

The invention provides a method for determining movement tracks of an industrial robot. The method includes: dividing robotic tools into rotational tools and non-rotational tools; enabling the rotational tools and the non-rotational tools to be in one-to-one correspondence with standard machining tools according to contact modes of the robotic tools and a workpiece; making models of the standard machining tools in CAM (computer-aided manufacturing) software, performing track planning on a machining area of the workpiece with the models, and acquiring a five-axis CAM track; defining information of a sixth axis in the five-axis CAM track, adjusting postures in the five-axis CAM track to be postures of the robotic tools, and acquiring six-axis tracks of the robotic tools. Plenty of five-axis CAM tracks can be transformed into stable and rational robot tracks, and accordingly the robot can be applied to the field of complex surface machining; time for robot track planning is shortened effectively, and working efficiency is improved; in addition, the tools in many machining fields such as cutting, polishing, welding, spraying and profiling are considered in the method, so that the method has general applicability.

The invention provides a route planning method, device and equipment and a computer readable storage medium, and the method comprises the steps: determining a target merchant according to the distancebetween a warehouse and a distribution merchant, and determining a fan-shaped region range which takes the warehouse as a vertex and comprises the target merchant according to the target merchant; and planning a route according to the distribution merchants in the fan-shaped area range, the route satisfying a preset constraint condition. According to the method, the device, the equipment and thecomputer readable storage medium provided by the invention, the target merchant is determined according to the distance between the merchant and the warehouse, and the sector area range including thetarget merchant is determined, so that the number of merchants included in route planning can be reduced, the planning efficiency is improved, and the planning time is shortened.

The invention belongs to the technical field of electronic information, and particularly relates to a random walk social network event recommendation method based on user similarity, and the method comprises the following specific steps: S1, event category division; S2, establishing a user similarity model; S3, restarting random walk of the user group network; S4, performing cold start user processing. Characteristic data of network event activities are calculated, and are fused in the group analysis of an online social network appliance; a random walk algorithm based on restart is utilized toperform community division on the users again, so the purpose of recommending events for the users, especially cold start user recommendation, is achieved, explicit and implicit feedback data in thesocial network are fully utilized, and the accuracy of a recommendation system is improved.

The invention relates to a mobile robot full-coverage path planning method, a chip and a robot, and the method comprises the following steps: S1, the robot detects an obstacle in a cleaning region, generates a map containing obstacle information, and divides the map into a plurality of sub-blocks; S2, the robot plans a cleaning path in the sub-block; and S3, the robot determines the initial sub-blocks and performs cleaning, then calculates the path cost between the sub-blocks, selects the next cleaning sub-block according to the path cost, and cycles the step until cleaning of all the sub-blocks is completed. According to the new full-coverage path planning method, the calculation complexity can be reduced, and the coverage efficiency of the robot is improved.

The invention discloses a system and a method for planning paths in a hospital. The system for planning the paths in the hospital comprises a plurality of path detection devices. The path detection devices are mounted in the hospital, each path detection device comprises a distance measuring module, a recognition module, a movement detection module, a processor, a lamplight control module and an audio frequency control module, corresponding lamps can be turned on and off under the control of the lamplight control modules, corresponding audio frequencies can be played under the control of the audio frequency control modules, and real-time conversation can be carried out by the aid of the audio frequency control modules; communication modules are connected and communicated with central computers. Nodes in the paths can be sequentially listed according to sequences from starting points to end points after the paths are computed by the central computers, the path detection devices corresponding to the nodes are further found out, lamp lighting and audio frequency playing commands are sequentially transmitted to the path detection devices at corresponding addresses step by step, and accordingly lamplight and audio frequency navigation can be completely carried out.

The invention discloses a path planning method integrating a dense convolution network and a competitive architecture. The method includes the following steps that: a mobile robot samples mini-batch pieces of conversion information from an experience playback memory, and selects one of two fusion path planning networks as an online network and the other as a target network according to preset rules; the maximum value of a predicted target action value function is obtained through a predicted online action value function Q(s, a; w) and a corresponding greedy action; a loss function at a currenttime step is calculated according to the maximum value of the predicted target action value function and the predicted online action value function; and an online network weight w is updated with a stochastic gradient descent method according to the loss function. According to the path planning method of the invention, the dense convolution network and the competitive architecture form a more lightweight fusion path planning network, and therefore, model parameters are simplified, training costs are reduced, planning time is shortened, and the requirements of high-speed path planning can be satisfied to a certain extent.

A method for creating a system layout of a photovoltaic open-space power plant includes: providing configuration data for the photovoltaic open-space power plant and components thereof, predefined configuration rules for the photovoltaic open-space power plant, and configuration parameters that define the configuration rules; and optimizing allocation of location of the components of the power plant in a system layout matrix, wherein the system layout matrix images a site for the photovoltaic open-space power plant using the configuration data and the defined configuration rules to create the system layout of the photovoltaic open-space power plant.

Systems and methods for rotating shield brachytherapy. In an aspect, some of the systems and methods can be used to facilitate shield selection for use in rotating shield brachytherapy. In an aspect, the invention is a shielded needle or catheter system with a rotational controller for delivering radioisotope-based interstitial rotating shield brachytherapy (I-RSBT). In an aspect, the catheter system can utilize paddle-based RSBT. Further provided are methods and systems for helical RSBT.

The invention belongs to the fields of construction machinery, computation and control automation, and relates to a method for planning the hoisting action sequence of a crawling crane according to a rapidly-exploring random tree, a heuristic strategy, and a CAD technology, namely, computer-assisted hoisting scheme design technology on the basis of modern brand new hoisting scheme design theory method. With the adoption of the method, the problems of terrible roundabout path, large route cost, long planning time and poor route quality of the existing hoisting action planning method can be solved; a specific action sequence for automatically switching from the starting pose position and orientation into the placing pose position and orientation on the premise that the crane is automatically avoided collision from a hoisted matter; therefore, the hoisting can be safely and efficiently done through the crane based on the action sequences; the simulating and rehearsing result of the hoisting shows that the method is effective and efficient.

The invention relates to an emergency evacuation simulation plan programming method which comprises the steps of establishing a population dynamic distribution rule database of a dense-population area and a key disaster preventing area; establishing a disaster type database according to different disaster types; correlating the population dynamic distribution rule database with the disaster type database, establishing an emergency evacuation simulation plan knowledge base; and after a disaster occurs, obtaining the emergency evacuation simulation plan with highest population distribution matching degree and highest disaster type matching degree from the emergency evacuation simulation plan knowledge base through real-time population distribution data. The invention further relates to an emergency evacuation simulation plan programming system. The emergency evacuation simulation plan programming method and the emergency evacuation simulation plan programming system have advantages of improving efficiency in an optimal evacuation simulation plan planning process, reducing programming time and obtaining higher practicability.

The invention relates to the technical field of unmanned driving, and provides a vehicle obstacle avoidance method and device, electronic equipment and a storage medium. The method is applied to unmanned equipment, namely automatic driving equipment or an unmanned vehicle, and comprises the following steps: carrying out collision detection on obstacles on a driving path of the vehicle, and when a detection result is that collision is predicted to occur, executing first feedback processing, wherein the first feedback processing is used for re-planning the driving path of the vehicle; performing collision detection according to a result of the first feedback processing, and executing second feedback processing when a detection result is that collision is predicted to occur, wherein the second feedback processing is used for re-planning the running speed of the vehicle; and performing collision detection according to a result of the second feedback processing, and executing the iterative processing process until an obstacle avoidance track is planned for the vehicle, so that the vehicle can travel along the obstacle avoidance track. The time consumption of trajectory planning during obstacle avoidance can be reduced, the compatibility of the planning algorithm is improved, and the response capability of the vehicle to the dynamic environment is improved.

The invention relates to an intelligent recommendation technology in the field of data analysis, in particular to a travel route planning method based on intelligent recommendation and related equipment, and the method comprises the steps: obtaining a travel city selected by a user and travel time; screening scenic spots according to travel cities and travel time, and prompting a user to select and recommend the scenic spots; and generating a travel route according to the recommended scenic spot, generating a travel report from the travel route and displaying the travel report to the user. According to the method, the travel route planning process of the user is simplified, planning time is saved, and dilemma and troubles caused by field preparation of the user are reduced by reminding theuser of the auxiliary tools needing to be carried.

The invention discloses a goods shelf rapid planning method and device in AGV path planning, and computer equipment. The method comprises the following steps that the coordinate positions of goods allocation centers at the two ends of a goods shelf and goods shelf parameters are obtained; a shelf model is generated, and shelf positions in the two-dimensional plane space are identified; goods allocation parameters in the shelf model are calculated; and AGV path planning is carried out according to the goods allocation parameters. When the method is used for carrying out shelf planning in AGV path planning, only several pieces of shelf attribute data need to be collected, and the shelf model can be quickly and accurately generated, so that the method is applied to AGV path planning, the shelf planning time is shortened, and the working efficiency is improved.

The invention discloses a ship-oriented intelligent marine ship distress early warning system. The ship body condition monitoring system comprises a cabin water immersion monitoring system, a smoke detection system, an echo detection system, a ship body structure analysis system, a panoramic scanning system and a stormy wave environment acquisition system, wherein the cabin water immersion detection system can monitor the water inlet condition of each cabin of a ship, the smoke detection system can monitor the fire condition of the ship, the echo detection system can detect the draught condition of the ship, and the panoramic scanning system can establish a three-dimensional model of each cabin of the ship and the whole ship. According to the ship-oriented intelligent marine ship distressearly warning system, through the ship body condition monitoring system and the distress early warning decision-making system, the planning time for making a search and rescue scheme and deploying search and rescue force by a marine search and rescue center between ship distress and rescue can be effectively shortened, the safety guarantee of the personnel in distress is enhanced, and the ship-oriented intelligent marine ship distress early warning system is worth vigorously popularizing.