54results about How to "Solving Path Planning Problems" patented technology

The invention provides a mobile robot path planning method in a complex environment. The method is characterized in that 1. information of environment in which a robot is positioned is acquired, and obstacles in the environmental space are indicated by using rectangular enclosing boxes after processing and displayed on a human-computer interaction module; 2. the initial position of the robot is confirmed and recorded as an initial point; a target position expected to be reached by the robot is confirmed and recorded as a target point; 3. the initial point, the target point and the vertexes of all the obstacle enclosing boxes meeting the condition are connected by using line segments, wherein the requirement indicates that the connecting line of any two points does not penetrate through the enclosing boxes, based on which a visual graph is constructed; 4. the optimal path is planned in the visual graph via an artificial immune algorithm, and key nodes in the optimal path are stored; and 5. The entity robot is controlled to start from the initial point, pass the key nodes in the optimal path one by one and finally reach the target point. Algorithm efficiency and convergence rate can be effectively enhanced under the premise of guaranteeing solution of the optimal path.

The invention discloses a real-time path planning method for an unmanned aerial vehicle based on deep reinforcement learning. The method comprises the steps of S1, obtaining the current environment state of the unmanned aerial vehicle from a simulation environment, calculating the threat degree of a target object defense unit to the unmanned aerial vehicle according to a situation evaluation model, and constructing a situation map of a task area of the unmanned aerial vehicle; constructing a main network and a target network of the convolutional neural network and the competitive neural network to perform action selection; S2, obtaining the current environment state of the unmanned aerial vehicle according to the communication link, calculating a threat value of the target object defense unit to the unmanned aerial vehicle according to the situation evaluation model, constructing a situation map of the task areas of the unmanned aerial vehicle, constructing a competitive dual-Q network, loading the trained network model, evaluating the Q value of each action in the current state, selecting the action corresponding to the maximum Q value, determining the flight direction of the unmanned aerial vehicle, and completing the flight task. According to the invention, the autonomous decision-making ability of the unmanned aerial vehicle can be effectively improved, and the method has high robustness and application value.

The invention discloses a UAV formation control algorithm based on the Lagrange's equation. An improved manual potential energy field is used in the aspect of formation UAV path programming, and motion of formation UAVs is seen as a constraint dynamic system in the formation maintaining aspect. When the constraint dynamic system is established, a spatial formation constraint equation is established according to a needed formation shape by utilizing spatial geometric relations of the UAVs relative to an inertia coordinate system, a Lagrange multiplier is introduced to establish a constraint dynamic equation set including the formation constraint formation UAVs, and certain stability is combined to eliminate the Lagrange multiplier directly and solve the Lagrange multiplier. The spatial geometric relation of the UAVs is established via the constraint equation, and the formation dynamic equation including the formation constraints is solved to obtain a flight track of the formation UAV to maintain an expected formation, and formation maintenance and transformation are relatively flexible and effective during flight of the UAV formation.

The invention discloses a multi-target path planning method for an unmanned cruise ship under a dynamic obstacle, and relates to the technical field of water quality sampling and path planning. The method comprises the steps that: an unmanned aerial vehicle collects an image of a lake surface environment, grid segmentation is carried out, and a starting point and a plurality of sampling points areset on a grid map; an improved grey wolf optimization algorithm is adopted to perform sequence optimization on the plurality of sampling points, and the sampling points with the optimal sequence aremarked on a map one by one; an optimal grid path is calculated between every two sampling points marked in the grid map by utilizing a D* Lite algorithm to obtain an optimal path from the starting point to the final sampling point; and finally, the autonomous cruise ship completes cruise along the optimal path. According to the invention, the convergence factor in the grey wolf optimization algorithm is improved, the global search capability and the local search capability of the grey wolf optimization algorithm are balanced, the convergence speed and the stability of the grey wolf optimization algorithm are improved, and the path planning of a plurality of target points in a dynamic unknown environment can be realized.

The embodiment of the invention relates to the robot field, and discloses a path planning method and a robot. The path planning method includes the steps: acquiring an environment map, and carrying out block division on the map according to the current map information; according to the information of each block, grading the blocks; and determining the target position, and according to the grade of each block, planning the path of the robot from the current position to the target position. The path planning method performs block division on the map and obtains the grade of each block, and then according to the grades, the robot can clearly know about where allow walking and where not allow walking and where are more clear in the surrounding environment. After knowing about the surrounding environment, the robot plans the path from the current position to the target position. Therefore, the path planning method enables the robot to avoid obstacles and the areas prohibiting the robot to walk, thus being conductive to improvement of reliability of the planned path, and being able to guarantee that the robot can quickly and smoothly arrive at the target position.

The invention provides a path planning device and method for an unmanned underwater vehicle based on a detection threat domain, which solve a path planning problem of a UUV (Unmanned Underwater Vehicle) in a terrain obstacle environment according to a path planning algorithm based on the detection threat domain, and can satisfy kinematic constraints, collision avoidance constraints and concealment detection constraints of the UUV. A path from a starting point to an end point of the movement is planned with the given initial position, the end point position, maximum curvature constraints, the path discrete point resolution, concealment safety indexes and the like being given. The planned path is smooth and can be guided continuously, sailing and turning curvature constraints, the concealment safety indexes and the like of the UUV are satisfied, and the UUV is enabled to reach the end point safely in a concealed manner with the shortest time. According to the invention, a detection threat theory and a geometric theory of the sailing and turning curvature constraints are applied to the field of path planning for the UUV for the first time, and path planning can be realized quickly. The path planning method is simple, reliable, easy to implement, small in calculation amount and good in real-time performance, can meet path planning requirements, improves the practicability of path planning, and has positive significance for development of the underwater path planning field in the future.

The invention provides a layered dynamic path planning method applied to virtual simulation, and is applied to the field of virtual simulation adopting large-scale topographic data. The planning method adopts a layered strategy to realize dynamic path planning in large-scale virtual simulation topography, and comprises the following steps: conducting blocking pre-treatment on earth's surface attribute data; utilizing a configuration file generated automatically to organize and manage the pre-treatment partitioning file to realize efficient mapping visit of the file; pre-calculating and generating a fine granularity path planning for data blocks; generating a coarse grit path planning result by using a cost file based on a high-level map during operation; dynamically combining the two results and renewing partial cost map to generate a final path planning result. The method has the advantages of being high in data dispatching efficiency and expansibility, and suitable for path planning in application of virtual simulation with large-scale data.

The invention discloses a fast expansion random tree and potential field method based visual servo path planning method. The method includes giving mapping relation between task space coordinates andimage plane pixel coordinates of target feature points of a robot under any pose; and randomly producing new poses in task space, no obstacles between the new poses and the closest original pose beingguaranteed, and calculating the image plane pixel coordinates of the target feature points under the corresponding poses so as to maintain the image plane pixel coordinates in camera visual field scope. The method searches feasible camera paths in the task space to obtain corresponding image plane feature trajectories, and utilizes an image based visual servo (IBVS) to perform tracking control sothat the robot can realize the obstacle avoidance from an initial pose to an expected pose, and visual field constrained motion can be met. Through the introduction of a path planning technology in the visual servo of the robot, the problems of obstacle avoidance and feature visibility in the visual servo of the robot can be solved.

The invention belongs to the technical field of robot path planning, and discloses a robot rolling path planning method and system, a storage medium, equipment and application. The method comprises the steps of carrying out initialization; constructing a rolling path planning area and calculating a comprehensive static situation field borne by each non-obstacle node; calculating a dynamic repulsive force potential field of eight nodes around the current node; judging whether the current node is a target point or not, and judging whether the current point is located at the window boundary of the rolling planning; outputting a planned path in the current rolling window; judging whether the feasible path length planned in the current rolling window is larger than the robot advancing step length or not; on the basis of a local path obtained by each round of rolling planning, carrying out path smoothing on connectivity detection of path nodes; and storing the path points subjected to the smoothing processing in a PointList. According to the method, a vector synthesis method is replaced by a potential field intensity calculation method, so that the problem of local extremum of a traditional artificial potential field method is avoided, and the requirement of dynamic obstacle avoidance is better met.

The invention discloses an intelligent warehousing map platform building and AGV path optimization method. The method is characterized in by building a map platform; collecting all path points, shelfposition information and obstacle area position information to make a rectangular map; non-passable marking is carried out on the shelf points and the obstacle points; the AGV path optimization comprises the following steps: firstly, marking path points, which have planned paths but do not pass by, of other AGVs in a built map as impassable path points; and then AGV path optimization is carried out through a genetic algorithm according to the starting point and the destination. Compared with a traditional genetic algorithm, the efficiency is higher, and the phenomenon that a result in the genetic algorithm goes back to the head is optimized.

The invention discloses a vehicle routing method for simulating missile guidance. The principle and the method are used for simulating missile guidance so that a missile needs to overcome earth gravity, air resistance and the like, and a vehicle can avoid congested road sections (save travel time) in running so that vehicle routing is realized. The method includes a global mode and a stepping mode, and the two modes respectively have advantages. The stepping mode places particular emphasis on achieving a single-vehicle routing goal, and the global mode simultaneously achieves the single-vehicle routing goal and a system optimization goal. By being improved, the vehicle routing method for simulating missile guidance can also be used for realizing routing to avoid the congested road sections (save travel time) and shorten travel distance. The method is a dynamic routing method, and the single-vehicle routing goal can be changed when the vehicle runs. Compared with other methods, the method is suitable for routing of urban intelligent transportation, so that the vehicle using the method avoids the congested road sections.

The invention relates to a robot overall path planning method based on the charge system search. The method includes the steps that a robot path planning mathematic model is established; environment parameters for planning paths of a robot and relevant parameters of a charge system search algorithm are initialized; N paths and the initial position and the speed of each charge are randomly initialized; according to robot environment information and the robot path planning mathematic model, the fitness value fit, the best fitness value fitbest and the worst fitness value fitworst of each charge are calculated; the charge quantity qj of each charge, an attraction mark pij between every two charges and the Euclidean distance rij between every two charges are updated; the position and the speed of each charge are updated; fitness of each charge is recalculated according to the robot path planning mathematic model, the position Xbest new of the charge with the best fitness currently is found, and therefore the optimal path of the robot is obtained; if the number of iteration times is larger than the number itermax of iteration, a circulation is ended, the optimal path is output, and otherwise iteration of the next time is conducted.

The invention discloses a multi-antenna unmanned aerial vehicle perception and transmission optimization method based on information age minimization, and the method comprises the steps: constructing a multi-antenna unmanned aerial vehicle perception and transmission system model which comprises a multi-antenna unmanned aerial vehicle, a base station, and a plurality of Internet of Things devices; the plurality of Internet of Things devices are divided into different device sets according to data transmission characteristics; and constructing an information age model according to the multi-antenna unmanned aerial vehicle perception and transmission system model: optimizing the multi-antenna unmanned aerial vehicle perception and transmission method through minimization of the information age model, and obtaining an optimal multi-antenna unmanned aerial vehicle perception and transmission method. The invention provides a multi-antenna unmanned aerial vehicle sensing and transmission method for solving the problems that a single-antenna unmanned aerial vehicle is small in sensing range, low in information transmission efficiency and the like, the sensing range and the transmission efficiency of the unmanned aerial vehicle are improved, and the multi-antenna unmanned aerial vehicle sensing and transmission method is further optimized by adopting information age model minimization.

The invention discloses an intelligent warehousing method and system for a four-way shuttle vehicle. The intelligent warehousing method comprises the following steps: receiving warehousing task information; judging whether a target goods location in the warehouse-in task information is blocked or not; if the target goods allocation is not blocked, directly calculating a warehousing path of the four-way shuttle vehicle; if the target goods location is blocked, searching a temporary storage goods location by taking the goods location of the shifting goods as a center; moving the warehouse-moving goods to a temporary storage goods position according to the warehouse-moving path; after the warehouse-moving goods are moved, calculating the warehouse-in path of the four-way shuttle vehicle; and executing a warehousing task according to the warehousing path. According to the invention, the warehousing paths of the four-way shuttle vehicles are planned according to whether the target goods allocations are blocked or not, so that the path planning problem of the four-way shuttle vehicles when the target goods allocations are blocked can be effectively solved.

The invention discloses a route planning method of a multi-wave missile launching vehicle. The method comprises the following steps: using a model established and a Floyd algorithm, respectively calculating the shortest route from each standby region to each missile launching node and route length; selecting w routes from several planned optimal routes and taking the selected routes as travellingroutes of the missile launching vehicle of a first wave, finding out the longest route from the selected w routes and then dividing the longest route by speed of the missile launching vehicle on a normal road to obtain maximum exposure time, namely, gradually completing route planning from the standby region to each missile launching node. The method provided by the invention can effectively solvea problem of route planning of the multi-wave missile launching vehicle and obtain the overall optimal route plan, can play an important role in data support of decision making of a military commandcenter, is beneficial for improving military task completion rate and enhancing overall fighting ability of troops.

The invention provides a using method of an intelligent meal selling robot based on machine vision. The using method comprises the steps that a dining car slowly moves back and forth on a student dormitory building, the dining car automatically stops when it is detected that someone exists, and a student can select a needed meal on a touch screen; a mechanical arm obtains information and performs image recognition on the meal to obtain a color image and depth; the area where a target object is located is segmented, and the target object is identified; the pose of the identified target object is obtained; motion planning is carried out according to the pose; the target meal is grabbed according to the motion planning; the grabbed meal is placed on a dinner plate to be weighed, the price is calculated, and an external display screen displays the price and a two-dimensional code to wait for payment; and after payment is completed, a valve on the dining car is opened to send out the meal. According to the using method of the intelligent meal selling robot based on machine vision, the mechanical arm has high identification accuracy and pose information estimation precision, intelligent operation is achieved according to image recognition and remote control, the using method can further cope with a complex working environment, and the using method is very convenient in the using process.

The invention relates to a heuristic algorithm-based underwater glider path planning method. The method comprises the following steps of performing rasterization processing on an underwater environment: dividing the underwater environment into grids, performing environment modeling, and distinguishing a feasible region and an obstacle region, wherein the grids located in the feasible region are called feasible grids and represented by 0, and the grids located in the obstacle region are called obstacle grids and represented by 1; performing population initialization; performing crossover operation on individuals in a population; performing mutation operation; calculating fitness values of the individuals in the population, and performing selection operation; after the crossover and mutationare finished, calculating the fitness values of the individuals, and selecting reserved individuals by adopting a roulette mechanism, wherein the higher the fitness is, the easier the reservation is;and in addition, performing elite reservation before the selection operation, namely selecting the individual with the highest fitness in the population and directly adding the selected individual tothe next generation of population, thereby ensuring that an optimal solution always exists; and performing pheromone concentration updating.

The invention discloses a multi-Agent airport surface taxiing path planning method based on historical data analysis, and the method carries out the real-time dynamic planning of a surface aircraft taxiing path based on the analysis of the historical surface taxiing data of an aircraft in combination with a Q learning algorithm in reinforcement learning. According to the method, the possibility of aircraft ground conflict can be greatly reduced, and the scene operation efficiency can be improved. According to the method, different dimensions, including time sequence data and scene resources, of historical sliding data are analyzed, conflict hot spot areas and conflict peak periods in the historical operation process are obtained, and then intelligent learning is carried out by setting corresponding Agents. A searching strategy based on the shortest path is adopted, the sliding path is shortest under the constraint conditions of the minimum safety interval, sliding speed constraint and the like, and a corresponding priority conflict avoiding method is adopted for solving the conflict when the conflict occurs.