442results about How to "Improve planning efficiency" patented technology

The invention discloses a path planning method for vertical automatic parking comprising creating an overall coordinate system by using surrounding environment information of a vehicle needing for parking obtained by a sensor, determining whether the vehicle needing for parking can accomplish automatic parking in the current overall coordinate system by combining with vehicle steering characteristics based on an Ackermann steering mechanism and carrying out a vertical parking path planning. By using a simple geometric construction method for the vertical parking path planning, the path planning method for the vertical automatic parking has the advantages of successfully accomplishing the parking in three times, improving the efficiency of the vertical parking path planning, possessing better robustness and rapidly realizing path planning when the parking is only obstructed by obstacle garages.

A ground navigation planning control method of a rover comprises the steps of sequential image splicing, three-dimensional terrain recovery, terrain traversability analysis, path planning and moving strategy generating. By means of the ground navigation planning control method of the rover, ground navigation planning control over the rover is conducted on the basis of a binocular stereoscopic vision system, a plurality of images comprising detection targets can be selected to be processed according to the positions of the detection targets of the rover with combination of practical situations, unnecessary calculation is reduced, and planning efficiency is high; an automatic noise reduction and manual denoising mode is provided so as to process three-dimensional terrain data, environmental perception accuracy is improved, and high-precision navigation planning control over the rover is facilitated; a data fusion mode is provided so as to splice multiple sets of terrain data, the environmental perception range is enlarged, and safety of navigation planning is improved; navigation planning control schemes of terrain traversability analysis, path planning and moving strategy generating provided in the ground navigation planning control method are still suitable for rovers provided with other sensors for environmental perception.

A path planning method for avoiding of traffic hotspots helps to realize an intelligent path planning method with a purpose of the shortest journey time, by dynamical planning of paths with an avoiding property, based on a destination where a driving user goes. The traffic hotspot information, such as large-scale activities, traffic accidents, traffic-peak block roads, school time or commuter time of large-scale units, weather information and the like, are mined continually from a plurality of data sources comprising webpages, microblogs, real-time reported traffic information, historical regularity information and the like. By acquisition of the traffic hotspot information in real time, and combination with influences of a road maximum speed limit, road width and traffic light delay at intersections to driving as well as whether a main road containing a non-motor vehicle zone, a rapid navigation route with an avoiding function is planed, and also a dynamic path planning can be carried out in real time base on a current position. The method helps to provide a fastest path to the destination for drivers and alleviate city traffic jam in certain degree.

An autonomous obstacle-avoiding planning method of a tour detector based on a binocular stereo vision is characterized by: generating DEM data of a local topography; constructing a raster map of a field range of a binocular stereo vision system, carrying out DEM data statistics to each grid in the map and carrying out de-noising processing to the DEM; carrying out topography traversability analysis so as to generate a suitability map; using the suitability maps generated during back and forth two planning to carry out data fusion and obtaining the fused suitability map which is used in the obstacle-avoiding planning; placing several alternative path arcs on the suitability map; evaluating the each alternative path arc from two aspects of a distance from the alternative path arc to a target point and a safe obstacle-avoiding ability; selecting the alternative path arcs whose evaluation values are higher a setting threshold from all the alternative path arcs and selecting the path arc who has the highest evaluation value as a result of the obstacle-avoiding planning. The method of the invention is simple and complete. Security is high. Planning efficiency is high. Engineering realization is easy to be achieved. The method can be used to perform a tour detection task of a complex terrain.

The invention discloses a design method of a full-coverage traversal path planning algorithm of a cleaning robot. The design method of the full-coverage traversal path planning algorithm of the cleaning robot comprises the following main processes of generating a traversal cleaning trajectory in a rectangular region by utilizing a Standard chaotic equation, decomposing a to-be-cleaned region into rectangular sub-regions, constructing rectangular iterative sub-regions, constructing an optimal sub-region joining path, constructing rectangular transition sub-regions and repeated sub-regions, constructing an optimal full-coverage traversal cleaning connection diagram, automatically joining the iterative sub-regions, and realizing a full-coverage traversal cleaning task in a feasible region. The algorithm of the design method of the full-coverage traversal path planning algorithm of the cleaning robot is low in repetitive rate and high in coverage rate; a cleaning blind area does not exist; the algorithm is high in planning efficiency; a start point and an end point are not needed to be determined; and the algorithm is simple and is easy to realize. By using the design method of the full-coverage traversal path planning algorithm of the cleaning robot, the indoor cleaning by the robot can be met quite well and the task of planning the full-coverage traversal path is realized.

The invention relates to a redundant robot dynamic obstacle avoidance route planning method using a pre-selected minimum distance index under an obstacle random motion environment. The method includes steps of using an oriented bounding box (OBB) to model a redundant robot and establishing the pre-selected minimum distance index; rejecting safe rod pieces through an intersection testing before a real-time distance is calculated; using a local mapping distance calculation method and target point coordinate values to directly obtain a real-time minimum distance and determining impact point positions in a local coordinate system of corresponding rod pieces; and on this basis, establishing obstacle avoidance gains and escape velocities relevant to the minimum distance and using a null space mapping matrix of the redundant robot to plan obstacle avoidance routes. According to the redundant robot dynamic obstacle avoidance route planning method, the safe rod pieces are rejected before dynamic obstacle avoidance planning, unnecessary trivial calculations are removed, a distance calculation method is optimized, planning efficiencies of dynamic obstacle avoidance are improved, and real-time requirements are met.

The invention discloses power utilization mode classification and control method based on user behavior characteristics. With an improved secondary clustering model built by use of a secondary clustering method, the load point of each day of the same user in one year in an industrial park is taken as a characteristic vector, the daily power utilization characteristics of the user can be concluded from a clustering result, and a plurality of typical power utilization modes of the enterprise user can be provided, and therefore, basis can be provided for load prediction, fault diagnosis, electricity pricing and the like in the industrial park; furthermore, the optimal plane power utilization mode in demand side management can be selected by virtue of optimization function modeling on load data; the model is advantageous for a power supply company to reduce the loss of electricity selling profit as much as possible under the premise of guaranteeing power supply; at last, a user power utilization behavior mode library in the industrial park built on the basis is capable of comparing a new settling enterprise inconvenient to model with the modelled typical user mode and obtaining the load characteristics of the new settling enterprise by virtue of analogizing, and therefore, the planning efficiency of the park can be improved.

This invention provides a novel tool path planning method for five-axis flank milling by imposing the constraints of curve interpolation on the tool path. The tool motion is described in the form of spline curves during its optimization-driven calculation process, instead of discrete cutter locations in CNC linear interpolation. The coefficients of the curve equations are generated by minimizing accumulated geometrical errors on the machined surface using optimization algorithms. The continuity imposed by the spline motion reduces uneven modifications of cutter locations during the optimization process. The resultant tool path yields superior.

The invention discloses a simultaneous positioning and mixed map construction method for a dynamic parking environment. By introducing environmental semantic information for data association, a dynamic target in a feature point map for realizing positioning is removed, and meanwhile, static state semantic information such as parking spots is introduced during the positioning, so that the positioning precision in the dynamic environment is improved; a full-view stereoscopic vision platform is taken as a unique environmental perception source of the system and is combined with the advantages offull-view cameras and vision, so that the environmentally accurate dimension information is realized; meanwhile, the view is wide, and the standing time of feature points in the map is long, so that the positioning precision can be increased; and the semantic information such as the parking spots can be fused with a topologic road network structure in the environment, so that the route planning efficiency can be effectively improved, and the instantaneity of an autonomous parking system is further improved.

The invention provides a method for distributing satellite receiving tasks. The method comprises the steps of decomposing the satellite receiving task planning problem by the divide-and-conquer method; decomposing the satellite data receiving task problem under a large task quantity into a plurality of sub-problems under a small task quantity; optimally configuring a ground receiving resource of each satellite data receiving task of each conflict task set by the genetic algorithm by considering the satellite-earth resource limitation, so as to reach the purpose of fully utilizing the ground receiving resource. According to the method, the parallel strategy of dividing and conquering is carried out to greatly increase the satellite receiving task planning efficiency; in addition, the genetic algorithm is performed for the satellite receiving task planning problem under each small task quantity, and therefore, the ground receiving resource is quickly and fully distributed, and the optimal satellite receiving task planning scheme can be obtained. According to the method, the automatic mode is performed, so that the brain power of operators can be relieved, and the planning efficiency and the capacity of responding to the emergency task can be greatly increased.

The invention discloses a pipeline planning method and device based on data driven modeling and simulation optimization, and belongs to the field of production line planning and design. The method comprises a step of performing rapid analysis on each data of an assembly line based on data driving and building a data model, a step of building a simulation model based on the data model through hierarchical modeling and driving the simulation model to run, outputting an simulation result and evaluating a result according to set indicators, continuously optimizing and improving the unreasonable allocation of device resources, and quickly performing reasonable pipeline planning and design. According to the invention, the model is quickly established through data driving, the model has good flexibility and reusability, the simulation model can be driven by modifying external data to run different simulation tests, the flexibility, versatility and portability of the simulation model are enhanced, the planning efficiency is improved, and the efficiency is improved and the correctness is ensured on the basis of automatic rapid modeling.

The invention discloses a multi-AGV-guiding and dynamic path planning method. The multi-AGV-guiding and dynamic path planning method comprises the following four steps: step one, division of nodes and lines of a movement region; step two, design of an AGV-guiding scheme; step three, design of a competitive mode of motion nodes of AGV; and step four, path planning of the AGV. The invention aims to provide a scheme capable of realizing multi-AGV motion line guiding and dynamic path planning to guarantee that a plurality of AGVs moving in the same region can effectively arrive at target locations, and are prevented from colliding with other AGVs.

The invention discloses a dynamic path planning method of a robot by combining an A* algorithm and a VFH obstacle avoiding algorithm. The method comprises steps of representing the environment where the robot is located into a grid map and searching a global initial path in a grid map by use of the A* algorithm; when the robot moves towards a target point along the initial path, judging whether the robot comes across an obstacle, if yes, using the VFH algorithm to carry out obstacle avoidance, or else allowing the robot to move towards the target point; during obstacle avoidance, firstly, setting a stage target point in the initial path, generating an obstacle avoiding path between the current position and the stage target point, moving for one step forwards, updating the current position,judging whether the space between the current position of the robot and the stage target point is shielded, if yes, re-calculating the obstacle avoiding path, or else, allowing the robot to move forone step forwards towards the stage target point along the obstacle avoiding path; and carrying out circulation until the robot reaches the stage target point, returns back to the initial path and continues to move towards a destination. By combining the two algorithms, efficiency of path planning of the robot is improved; and the autonomous navigation ability of the robot in the indoor dynamic environment is ensured.

The invention provides a global-local hybrid unmanned ship path planning method based on dynamic constraints. The global-local hybrid unmanned ship path planning method comprises the steps of: S1, constructing an unmanned ship kinematics model, and conducting kinetic analysis; S2, considering a safety range of an unmanned ship, realizing the planning of a global path of the unmanned ship by adopting a storage node mode, and constraining the safe driving of the unmanned ship by optimizing the generated path points; S3, for a dynamic unpredictable environment, constructing a hierarchical structure based on an FDM fuzzy decision module and an FDW precise dynamic window module, and realizing the planning of a local path of the unmanned ship, precisely taking drivable forward, heading angular velocities and acceleration into account in the planning of the local path, and generating a traceable path that enables real-time local collision avoidance; S4, and fusing a global path planning scheme and a local path planning scheme of the unmanned ship to form a global-local hybrid obstacle avoidance strategy. According to the global-local hybrid unmanned ship path planning method, virtual pathpoints are inserted into the global optimal path, so that global and local path planning is perfectly combined, and the whole path tracking task is completed.

The invention provides a method for constructing an indoor two-dimensional semantic grid map with an object navigation point. The method comprises the following steps of S1, constructing an environment grid map, and acquiring a real-time position of a robot; S2, completing recognition of an object in an environment; S3, obtaining a main body part of the target object, and obtaining coordinates ofthe target object in a camera coordinate system; S4, performing coordinate conversion to obtain the coordinates of the recognized object in a grid map coordinate system, and establishing an object grid map; S5, combining the object grid map and the environment grid map to obtain a semantic grid map reflecting environment semantic information; and S6, extracting a navigation point of the target object in the semantic grid map to obtain an indoor two-dimensional semantic grid map with the navigation point. According to the method, an original grid map contains semantic information and also contains the object navigation point, the semantic grid map provides richer features for robot positioning and navigation, and higher-level complex tasks can be completed.

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 relates to a weight matrix-based improved ant colony path planning method. The weight matrix-based improved ant colony path planning method innovatively introduces the weight matrix intopath planning to improve the algorithm efficiency, optimize the values of initial pheromones and reasonably limit residual pheromones and path weights. The weight matrix-based improved ant colony path planning method can achieve humanized path planning according to practical application context and avoid repeated site visiting to acquire the shortest and optimal path, thereby greatly improving the practical operation efficiency.

The invention discloses a method and system for supporting an urban land utilization and traffic integrated planning policy. The method comprises the following steps of: S1, constructing a land utilization model; S2, constructing a traffic planning demand predicting model; S3, judging a convergence property of a traffic accessibility value according to a traffic accessibility value result and an accessibility convergence index obtained according to the traffic planning demand predicting model, if a result indicates no convergence, executing an S4, and if the result indicates convergence, executing an S5; S4, feeding a result of the traffic planning demand predicting model back to the land utilization model, and returning to the S1 to restart a model computing process; and S5, stopping a cyclic feedback process, meanwhile, evaluating results of each land utilization scheme and each traffic planning scheme in real time when the cyclic feedback process is stopped, and selecting a preferential land utilization and traffic planning scheme. According to the invention, the urban land utilization and traffic planning can be realized automatically according to basic data, and the planning efficiency and the reasonableness, the scientificity and the continuity for planning can be improved.

The present invention provides a dynamic path planning method, device and system, and a storage medium. The method comprises the following steps: determining, in a high-level grid map, at least one initial candidate path according to locations of a start point and an end point; obtaining a grid where the initial candidate path passes in the high-level grid map as a path grid; acquiring a low-levelgrid map corresponding to the path grid; optimizing the initial candidate path according to the low-level grid map to acquire a target candidate path. The dynamic path planning method can reduce processed data of path planning to improve the planning efficiency, and adopts a boundary node according to a dynamic traffic state to improve the accuracy and reasonability of the path planning.

The invention relates to a route planning method and a route planning system which are applied to plant protection of an unmanned aerial vehicle. The method comprises the steps of judging whether the polygon of a plot is a convex polygon; calculating the narrowest strip of the convex polygon so as to determine a starting edge if the polygon of the plot is the convex polygon; otherwise, determining the starting edge according to the perpendicular direction of the sunk interval of the polygon of the plot and the length of each edge of the polygon of the plot; calculating a route according to the starting edge. According to the route planning method and the route planning system, the optimal starting edge and the optimal route can be automatically calculated according to the shape of the plot, so that the route planning efficiency and quality are increased; in addition, the actual demand of a concave polygon is considered in a route planning process, so that the route is prevented from passing through the boundary of the plot so as not to pass through exterior areas of the plot.

The invention provides a two-dimensional route planning method for a UUV to geometrically bypass circular barriers. The method comprises the following steps: 1, reading a route origin Ob, a route terminal point Oe and parameters of each circular barrier from a mission text; 2, performing expansion processing on each circular barrier, and calculating the parameters of each circular barrier after expansion; 3, establishing a bypassing point set S, making a planning current point Oc to be a starting point Ob, and placing the starting point in the bypassing point set S; 4, if the planning current point Oc is the route terminal point Oe, or the planning current point Oc and the route terminal point O2 are visual, skipping to the sixth step, and otherwise, executing the fifth step; 5, performing geometric bypassing on a circular barrier closest to the planning current point Oc, obtaining a bypassing point, placing the bypassing point in the bypassing point set S, updating the planning current point Oc, and skipping to the fourth step; and 6, placing the route terminal point Oe in the bypassing point set S, and at the moment, planning ends. According to the invention, bypassing of the circular barriers is realized through a simple geometric principle, and the UVV can rapidly and efficiently obtain a safe bump-free two-dimensional route in a complex environment with multiple circular barriers.

The invention discloses a mixed-experience multi-agent reinforcement learning motion planning method, namely an ME-MADDPG algorithm. According to the method, through MADDPG algorithm training, when a sample is generated, experience is generated through exploration and learning, high-quality experience of successfully planning multiple unmanned aerial vehicles to a target through an artificial potential field method is added, and the two kinds of experience are stored in different experience pools. During training, a neural network collects samples from the two experience pools through dynamic sampling according to the changing probability, state information and environment information of the agents serve as input of the neural network, and the speeds of the multiple agents serve as output. Meanwhile, the neural network is slowly updated in the training process, the training of a multi-agent motion planning strategy is stably completed, and finally, the agents autonomously avoid obstacles in a complex environment and can smoothly reach the respective target positions. According to the method, a motion planning strategy with better stability and adaptability can be efficiently trained in a complex dynamic environment.

The invention discloses a satellite cluster configuration adjustment planning method for space target collaborative observation. According to the method, each satellite is regarded as an intelligent Agent with autonomous planning and decision-making capability, a coordination graph based on a cluster communication structure is established, and tasks optimized by a global optimal configuration adjustment strategy are decomposed to local learning of each satellite based on the communication coordination graph. According to the method, the top-layer planning of configuration adjustment and bottom-layer control are comprehensively considered; solving is carried out from the perspective of cluster cooperation planning; the global planning learning task is divided into the paired Agents according to the communication relationship, so that the autonomy and intelligence of the satellite cluster are enhanced, the on-orbit viability and the task execution level of the satellite cluster are improved, and a new idea and method are provided for on-orbit autonomous operation and management of the satellite cluster.

The invention is suitable for the technical field of robots, and provides a robot path planning method based on multiple regions, a robot and terminal equipment, and the method comprises the steps: obtaining an initial position and a target position of the robot; if the initial position and the target position are located in different areas, obtaining information of a switching point located in the initial area; determining cross-domain paths according to the information of the switching point in the initial area and a pre-stored cross-domain topological map; determining a corresponding initial area sub-path for each cross-domain path according to the area topological map, the initial position and the cross-domain path of the initial area; determining a corresponding target area sub-path for each cross-domain path according to the area topological map of the target area, the target position and the cross-domain path; and determining a target path according to the cross-domain path, theinitial area sub-path and the target area sub-path. According to the embodiment of the invention, robot path planning based on multiple regions can be efficiently realized.

The invention provides an artificial fish swarm algorithm-based power wireless private network base station planning method. The method comprises the steps of mapping base station planning position information in a planning region to artificial fish position information in an artificial fish swarm algorithm, establishing a target function by integrating parameters in two aspects of a station establishment cost and a power distribution and utilization business coverage rate, and by calculating the target function, searching for and solving a global optimal target function value; and based on an optimized artificial fish swarm algorithm, by adjusting a visual field, a step distance and a motion mode of an artificial fish, based on the global optimum search, further accurately solving an optimal target function value, thereby obtaining an optimal planning scheme of power wireless private network base station planning, greatly simplifying the calculation process, and improving the accuracy. According to the artificial fish swarm algorithm-based power wireless private network base station planning method provided by the invention, the calculation accuracy and reliability are improved, the calculation efficiency is enhanced, and the construction cost is reduced.

The invention discloses a fast search-based agile satellite task planning method. The method comprises the following steps of: firstly establishing a target observation queue according to different sorting rules; inserting to-be-observed objects in sequence and dynamically updating a sliding imaging window of each target in the observation queue according to a target insertion position; when all the tasks are inserted, determining a practical imaging window according to a target imaging time length and the sliding imaging windows to ensure that the imaging quality is optimum; and finally comparing planning schemes obtained according to the different task sorting rules and selecting a planning scheme with the optimum imaging quality. The method has the characteristics of being high in imaging quality, simple in time sequence control logic, low in time complexity and high in task arrangement efficiency, and is particularly suitable for the field of agile imaging satellite task planning.

The invention, which belongs to the technical field of power system planning, provides a distribution network differential planning method with consideration of a composite fault risk. The method comprises: according to a climatic condition of a region where a distribution network is located, meteorological protection levels of the region are set; historical failure rates of all lines under all meteorological protection levels are calculated; according to the historical failure rates, composite line failure rate prediction values are planned; candidate distribution network differential planning schemes are formulated; and a comprehensive evaluation system is constructed, all candidate distribution network differential planning schemes are evaluated, and then an candidate distribution network differential planning schemes is selected. According to the distribution network differential planning method, with consideration of influences on the distribution network by composite meteorological disasters, the comprehensive disaster handling capability of the distribution network is enhanced and security operation of the distribution network is guaranteed; on the basis of the composite failure rate economic risk evaluation, a cost and a failure disaster risk are balanced; the planning scheme is evaluated in terms of the failure recovery capability, so that the method has an important practical significance in promoting application and perfection of distribution network planning work; and the distribution network planning efficiency and planning quality can be improved.

The present invention provides an intelligent tower connected graph construction method for planning the inspection route of an unmanned aerial vehicle (UAV). The method comprises the steps of A, predicting the distribution of transmission line towers according to the single-element nonlinear regression prediction method to generate a plurality of tower lines, wherein each tower line is composed of a plurality of towers; B, based on the critical conditions of tower distribution, connecting the plurality of tower lines to form a line connection graph, wherein the critical conditions are composed of crossed crossing condition, parallel distribution situation of multiple tower lines at a relatively near distance relative to one another, tower steering condition and tower branch condition; C, constructing a storage structure of the line connection graph. According to the technical scheme of the invention, power transmission lines are intelligently planned based on the above algorithm, so that the planning efficiency is improved. Meanwhile, an entire patrol scheme is provided. In this way, not only the patrol can be conducted on going and returning paths, but also the line inspection is conducted on going and returning paths. Therefore, the line inspection efficiency is greatly improved. Based on the intelligent traversal algorithm, an optimal inspection route for a line network can be planned. In this way, all towers can be traversed within a region at a shortest inspection distance.

The invention discloses an unmanned vehicle motion planning method oriented to planning control joint optimization. The method comprises the steps: obtaining a global linearized model through the recognition of an original kinetic model of a vehicle, and obtaining a simplified model through the order reduction of the global linearized model. During planning, a simplified kinetic model is considered and the non-convex obstacle constraint is also convex to consider the existing obstacle constraint, and the planning module plans the trajectory, the speed and the like by combining the simplified model and a rolling time domain ADP method, so that the planning efficiency is improved, the consistency of planning and control is ensured, and the motion result of the vehicle effectively meets the anticipated requirements.