62 results about "Random tree" patented technology

The invention relates to the technical field of unmanned aerial vehicle trajectory planning, in particular to a bidirectional tree random search method based on a complex environment node cost function, which comprises the steps of surveying obstacle data in a flight area and modeling, then introducing a target deviation strategy and a bidirectional search tree mechanism, and combining with an improved minimum cost method to obtain a random search result. Alternately expanding the two trees to generate an initial path, and integrating the path length, the obstacle distance and the flight height energy consumption by a cost function; and finally, pruning the initial path, removing redundant nodes, smoothing the trajectory by adopting a cubic spline interpolation method, ensuring curvature continuity, and generating an optimal path meeting the flight performance of the unmanned aerial vehicle. According to the invention, through an improved bidirectional minimum cost fast expansion random tree algorithm, dynamic association of obstacle constraint, target deviation and path cost in unmanned aerial vehicle path planning in a complex environment is represented, and a more efficient search convergence speed and better path quality are obtained. And rapid convergence and global optimization of the track of the unmanned aerial vehicle in a high-dynamic environment are realized.

The invention provides an incremental reinforcement learning path planning method based on dynamic reward remodeling, which is used for solving the problems of training efficiency and composite optimization in path planning. According to the method, a rapid exploration random tree and an artificial potential field method are combined with reinforcement learning, a dynamic reward function is designed, real-time feedback is provided for an intelligent agent, and strategy learning is accelerated. The system specifically comprises a reward remodeling module which provides process rewards through a fast exploration random tree and an artificial potential field method; the sub-target course learning module is used for gradually increasing task complexity and optimizing sample utilization; the progressive reward adjustment module dynamically adjusts the reward weight and solves the reward coupling problem; and the strategy fine tuning module dynamically adjusts the learning rate and supports strategy optimization. Experimental results show that in static and dynamic path planning tasks, compared with a traditional method, the method has the advantages that the training efficiency and the composite optimization performance are remarkably improved, the reward coupling problem is effectively solved, and the intelligent agent can efficiently learn and converge to a global optimal strategy.

The invention discloses an automatic wiring method and system of a secondary screen cabinet, a medium and a product, and belongs to the field of automatic wiring of the secondary screen cabinet, and the method comprises the steps: obtaining the design drawing data of the secondary screen cabinet, and extracting the installation position of each component and the insertion starting point and end point of a wiring harness; setting a plurality of bundling middle points for each wire harness based on the positions of the components, and forming a node sequence by combining starting and ending points; generating path fragments for each pair of adjacent nodes in the sequence by adopting a fast exploration random tree connection algorithm with sampling region constraint and an obstacle approaching penalty term; and sequentially splicing all the segments into a complete wiring path, and controlling a wiring device to automatically complete wiring harness arrangement and fixation according to the complete wiring path. By implementing the method, the problems of low efficiency and poor safety of automatic wiring path planning of the wiring harnesses in the secondary screen cabinet in the prior art can be solved.

The invention discloses a multi-robot affine formation path optimization method driven by a virtual navigator, and the method comprises the steps: firstly setting a point set composed of the virtual navigator and followers, enabling the virtual navigator to form a convex hull and meet an affine localization condition, so as to guarantee that the followers are always located in the convex hull; generating a collision-free reference trajectory of the mass center of the virtual navigator based on a fast random tree algorithm; constructing a nonlinear constraint optimization problem NCO which contains linear transformation constraint and meets smoothness, obstacle avoidance, speed and angular speed constraint; and establishing a communication graph of the virtual navigator and the follower, calculating balance stress, designing a smoother follower distributed differential speed control law, and realizing formation path optimization and obstacle avoidance control. Compared with an existing method, the formation path generation method has the advantages that the smooth and stable formation path fitting the reference trajectory can be generated while obstacle avoidance and physical feasibility are guaranteed, and the cooperative motion capability and the control performance of a multi-robot system in a complex environment are improved.

The invention discloses a path planning method for cooperative operation of multiple unmanned aerial vehicles, and belongs to the technical field of unmanned aerial vehicle control. The method comprises the following steps: acquiring real-time state information of each unmanned aerial vehicle; dynamic tasks are allocated based on a lightweight auction protocol, and distance, energy consumption, task urgency and load are comprehensively considered in a bidding function; generating a global reference path for each unmanned aerial vehicle, and applying for a space-time reserved window of the three-dimensional space logic grid unit in a specific time interval from the coordination agent; the coordination agent performs conflict detection and feeds back a reservation result; each unmanned aerial vehicle carries out local re-planning in combination with an improved artificial potential field-fast extended random tree algorithm so as to avoid dynamic obstacles; and when the task is changed or the unmanned aerial vehicle fails, a task release and redistribution mechanism is triggered. According to the method, safe, efficient and extensible cooperative path planning of multiple unmanned aerial vehicles in a high-dynamic environment is realized, and the method is suitable for scenes such as logistics distribution, electric power inspection, emergency search and rescue and the like.

The invention discloses a multi-sensor data fusion path planning method and system for a pipeline robot, and the method comprises the steps: collecting laser radar and inertial measurement data through an environment perception module, and executing time-space calibration in a semantic map construction module to generate a three-dimensional semantic map containing obstacle attributes; the global path planning module adopts an algorithm to dynamically adjust a heuristic function for a straight pipe, a bent pipe and a branch pipe to generate an initial path; and the local dynamic adjustment module establishes a rolling window based on the advancing speed, and replans the dynamic obstacle by using a fast expansion random tree algorithm. And the path execution conversion module performs smooth optimization on the path through quintic polynomial fitting and curvature change rate constraint and generates a bottom layer control instruction. Through the multi-source fusion and hierarchical planning strategy, the problems of pipeline environment positioning drifting and dynamic obstacle avoidance are effectively solved, and the stability and safety of robot advancing are remarkably improved.

The application discloses a drilling and anchoring robot drilling arm trajectory planning method and system and electronic equipment, relates to the technical field of trajectory planning, and comprises the following steps: acquiring a three-dimensional working area model of a drilling and anchoring robot, a working starting point and a drilling point; determining an initial drilling arm path of the drilling and anchoring robot by using a rapidly-exploring random tree algorithm; the initial drilling arm path is a path of a drilling arm of the drilling and anchoring robot from the working starting point to the drilling point in the three-dimensional working area model; removing redundant points in the initial drilling arm path of the drilling and anchoring robot by using a connection method to obtain a first optimized path; and fitting the first optimized path by using a second-order Bezier curve to obtain a final drilling arm path of the drilling and anchoring robot. The drilling and anchoring robot drilling arm trajectory is optimized to assist in realizing fast and accurate hole finding and drilling.

The application discloses a UAV robust path planning method and system for uncertain dynamic environment, relates to the field of path planning, and realizes real-time tracking of dynamic obstacles by using EKF, and constructs a probability repulsive field based on Mahalanobis distance, effectively solves the sensing vulnerability and static model limitation of a traditional APF algorithm, and provides a robust dynamic obstacle avoidance guide for random tree expansion; secondly, a fuzzy logic adaptive step (FLC-AS) module is designed; the module intelligently adjusts the expansion step according to the risk degree of a local environment and an exploration stage, and realizes dynamic balance of exploration safety and search efficiency; comparison and analysis of the method and various mainstream algorithms show that the PFLS-RRT* algorithm has excellent adaptability in a complex environment, and achieves the best comprehensive performance in key indexes such as path quality, planning efficiency and robustness.

The application discloses a path planning method based on deep reinforcement learning-fast exploration random tree, comprising the following steps: S1, obtaining a starting point and an ending point; S2, calculating candidate path points and selecting an action in an action state according to a Q value; S3, calculating a reward value and a new action state after the action is executed; S4, storing the action state, the action, the reward value and the new action state to an experience pool, in response to the number of stored experience values in the experience pool being greater than a batch size, randomly selecting experience values of the batch size, and updating the Q value and a time difference error through a policy network; S5, updating policy network parameters through a mean square error loss, and calculating a target network update step according to the time difference error; S6, judging whether a searched path reaches the ending point or satisfies a set maximum path point search number, if yes, outputting a current path, and if not, returning to S2. The application improves the search efficiency of the algorithm without increasing the search time of the algorithm.

The global path planning method based on potential energy guidance fast search random tree algorithm belongs to the technical field of intelligent vehicle path planning, and solves the technical problem that the traditional fast search random tree algorithm can cause the planned trajectory to travel close to the obstacles. First, the position of the obstacles and the start and end positions are determined through the two-dimensional space map planned by the vehicle. For any point in the map, the potential energy value thereof is calculated, and the potential energy values of all the obstacles are superimposed to obtain the potential energy value of the arbitrary point. The potential energy values of all the arbitrary points in the two-dimensional space map are obtained in the same way. Then, the potential energy values of each point of the whole map are normalized to obtain a potential energy map matrix. The potential energy map matrix is introduced into the fast search random tree algorithm, a potential energy threshold is set, and the randomly generated points are screened. After screening, the potential energy values are introduced into the cost function of the fast search random tree algorithm, and rewiring optimization is performed, so as to perform vehicle path planning.

The invention discloses a maintenance step simulation method based on model fusion, and relates to the technical field of virtual maintenance. According to the method, a high-fidelity multi-physics field simulation environment is constructed by deeply fusing a three-dimensional geometric model with physical attributes such as density and friction coefficient and assembly logic; an obstacle avoidance path is planned by using a fast expansion random tree algorithm, and real-time calculation of the deformation of the flexible pipeline and the statics equilibrium state of parts is realized in combination with a mass spring model and a polyhedral friction cone theory. On the basis, a multi-dimensional evaluation system containing space gaps, view shielding and operation torque weights is constructed, feasibility confidence indexes of overhaul steps are quantitatively evaluated, and a virtual guide potential field and directed acyclic graph logic verification are assisted, so that an overhaul guide file conforming to physical rules and process specifications is finally and automatically generated. The problems that traditional simulation lacks mechanical verification and flexible body simulation is distorted are effectively solved, and the reliability of maintenance process design is remarkably improved.

This invention discloses a visual-language navigation method with cross-modal alignment in dynamic occlusion environments. The method utilizes visual sensors, inertial measurement units, and LiDAR to collect multimodal data, and performs preprocessing and time synchronization. It perceives dynamic occlusions using a model composed of convolutional neural networks and long short-term memory networks, and predicts their future changes using a spatiotemporal sequence prediction algorithm. It extracts and fuses visual and semantic features using a dual-branch convolutional neural network and a Transformer based on a dynamic attention mechanism. Based on occlusion prediction, it extracts potential occlusion region features in advance from the temporal dimension, and repairs occluded images in the spatial dimension using generative adversarial networks and geometric constraints. It optimizes cross-modal feature alignment through an attention mechanism. Finally, it plans the path using a hybrid reinforcement learning algorithm based on deep Q-networks, spatial and fast exploratory random trees, and dynamically adjusts the path according to real-time occlusion. This invention improves the accuracy, adaptability, and reliability of visual-language navigation in dynamic occlusion environments.

This invention discloses a working path planning method and system for grain surface leveling equipment. In one specific embodiment, the method includes constructing a map based on the location information of grain piles and grain pits within a grain silo, and setting parameters according to preset anti-collision distances; performing global path planning for the grain surface leveling equipment based on the map and using a particle swarm optimization algorithm improved from a genetic algorithm; performing local path planning for the grain surface leveling equipment from the grain piles to the grain pits based on the results of the global path planning and using a table-based operation method; and optimizing obstacle avoidance for the grain surface leveling equipment based on the results of the local path planning and using a fast expanding random tree algorithm improved from an artificial potential field method with the set parameters. This embodiment enables intelligent and efficient grain leveling operations, reduces labor costs, and improves work efficiency.

The application provides a flash memory bad block prediction method and system based on a deep forest, a medium and equipment, and the method comprises the following steps: obtaining historical data of a flash memory bad block, classifying and arranging the historical data to obtain a data set, and dividing the data set into a training set, a verification set and a test set; training an improved deep forest network model by using the training set to obtain a trained deep forest network model, wherein the improved deep forest network model comprises a multi-granularity scanning structure and a cascaded extreme random tree structure; optimizing the trained deep forest network model by using the verification set to obtain an optimal deep forest network model; and inputting data of the test set into the optimal deep forest network model to obtain a prediction result for the flash memory bad block. The improved deep forest network model is used to accurately predict the flash memory bad block, which is helpful for early warning before the data block becomes a bad block and prediction of the proportion of bad blocks of the entire solid state disk.

This invention discloses a high-precision indoor personnel positioning method based on machine learning, comprising the following steps: collecting samples, labeling locations, and generating a dataset; extracting inertial features and clustering them to obtain behavioral pattern labels; constructing a signal topology map based on wireless data; constructing extreme random trees for each pattern subset, dynamically selecting splitting features and thresholds to generate an environment-adaptive tree; introducing node splitting into the topology map with topological proximity constraints, and performing local weighted regression combining topology and environmental weights to obtain each extreme random tree model; acquiring real-time data, obtaining pattern probabilities from the clustering model, selecting the corresponding tree model for traversal, and obtaining the predicted location for each pattern; fusing the predicted location output results with probabilities as weights, and updating the topology map, environmental statistics, and tree splitting thresholds. This invention achieves high-precision positioning in dynamic and complex indoor environments, improving positioning robustness and environmental adaptability.

The application relates to a mobile robot path planning method based on an improved bidirectional RRT algorithm, and belongs to the technical field of mobile robot path planning. a b The bidirectional random tree T a b is constructed by taking a starting point and an ending point as root nodes, adaptive sampling is realized by adopting a directional deviation heuristic function containing a bias angle sampling strategy, node distribution is optimized by combining a redundant point removal strategy based on adaptive adjustment of an environmental complexity threshold, and the random tree is directionally expanded by introducing an improved artificial potential field method. The application can quickly generate a safer optimal path which is shorter and smoother, significantly improves the efficiency and robustness of path planning, and is suitable for complex scene path planning tasks of various mobile robots such as service robots and unmanned toy cars.

The AUV energy optimization path planning method comprises the following steps: initializing a three-dimensional planning environment, and constructing a first random tree with a starting point as a root node and a second random tree with an end point as the root node; flow field information of the three-dimensional planning environment is obtained, if unknown, the flow field information is sensed in real time through a sensor, and if known, a pre-stored flow field model is called; calculating sampling probability distribution based on the flow field information, and correcting the sampling probability through the consistency of the flow field and the target, the distance weight and the target bias strategy; alternately expanding the first random tree and the second random tree, and introducing an artificial potential field to carry out flow field adaptive optimization on node positions in the expansion process; performing collision detection on a path segment between a newly generated node and a father node of the newly generated node, and if the path segment is safe, adding a random tree and performing reconnection optimization; and when the first random tree and the second random tree are successfully connected, extracting a global path, and outputting an energy optimization path. According to the method, a downstream energy-saving mechanism can be fully utilized, so that the length of an AUV planned path is shorter, and the calculation efficiency is higher.

The application discloses a multi-agent dynamic real-time path planning method and device based on signal timing logic, and relates to the technical field of control methods. The method comprises the following steps: acquiring multi-robot path planning task information and a preset space-time constraint task demand; constructing a multi-robot task specification based on signal timing logic, and defining a corresponding robustness evaluation function; constructing a comprehensive path cost function based on the robustness evaluation function; introducing the path cost function into a path expansion and reconnection process based on a real-time rapid expansion random tree algorithm, updating a search tree structure, and generating a candidate path meeting environment constraints and timing constraints; planning paths for robots in sequence according to a preset multi-robot cooperative planning strategy, taking the path information of the robots that have been planned as dynamic obstacles and performing progressive cooperative obstacle avoidance, and outputting a conflict-free trajectory adaptive to a dynamic environment. The application can solve the path planning problem in a multi-agent scene.

The invention relates to the technical field of multi-robot path planning, and discloses an improved Bi-RRT and enhanced search algorithm fused path planning method, which comprises the following steps: improving a bidirectional fast expansion random tree; an enhanced search algorithm based on conflicts; firstly, an initial path is planned for each robot through an improved bidirectional fast extended random tree algorithm, then dynamic conflict detection and processing are carried out by using a conflict-based enhanced search algorithm, and a final path is output through conflict priority ranking, frame insertion waiting and path optimization. The path searching efficiency, the path safety and the conflict avoidance capability are comprehensively improved, the actual application requirements of scenes such as logistics storage are met, and the problems of redundant path, low planning efficiency and high conflict rate among the robots in multi-robot path planning in high-density obstacle environments such as logistics storage are solved.

The application discloses a diagenetic facies identification method based on a multi-modal fusion feature and an extreme random tree model, and comprises the following steps: S1, dividing the lithofacies of a research area into a strong compaction facies, a calcareous cementation facies, a siliceous cementation-medium dissolution facies and a strong dissolution facies; S2, acquiring well logging curves of the research area, and determining well logging facies corresponding to each lithofacies according to the well logging curves; S3, pre-processing and multi-view feature transformation are performed on the well logging curves, a multi-modal fusion feature set is obtained, and the multi-modal fusion feature set and the corresponding lithofacies type constitute a sample set; S4, an extreme random tree model is constructed, and the sample set is used for training the extreme random tree model, so as to obtain a diagenetic facies identification model; and S5, well logging curves of a well to be measured are acquired, pre-processing and multi-view feature transformation are performed on the well logging curves, and the diagenetic facies identification model is used for predicting the lithofacies type of the well to be measured. The application can more quickly and accurately identify the diagenetic facies type, and provides technical support for tight sandstone oil and gas exploration and development.

The invention discloses a mechanical arm obstacle avoidance planning method based on an extended random tree connection algorithm. The mechanical arm obstacle avoidance planning method comprises the steps that S1, a starting point and a target point are initialized into root nodes of two random trees Tstart and Tgoal respectively; s2, in each iteration, generating a sampling point I in the working space; s3, a first node closest to the sampling point is searched in the random tree Tstart, a second new node is generated through extension according to the step length epsilon, and when a connecting line between the second node and a father node of the second node does not collide, the second node is added into the random tree Tstart; s4, searching a node 3 closest to the node 2 in the random tree Tgoal, generating a new node 4 through extension according to a step length epsilon, and adding the node 4 into the random tree Tgoal when a connecting line between the node 4 and a father node 3 of the node 4 is not collided; s5, after each round of iteration is finished, the roles of the two random trees are exchanged through Swap operation, and iteration is repeated until the distance between the second node and the fourth node is smaller than the extension step length epsilon or the maximum number of iterations is reached.

The application relates to the field of mobile robot path planning, and particularly relates to a robot rapid path optimization method based on multi-strategy fusion, which comprises the following steps: step 1, initializing iteration greedy algorithm parameters, and generating an initial path by using a bidirectional rapid expansion random tree method; step 2, using a difference guided path optimization mechanism to destruct and reconstruct the path, and expanding a path exploration space; step 3, performing path pruning, node insertion and node mutation operations by selecting an adaptive adjustment strategy, and locally searching the current path; step 4, accepting the path according to a simulated annealing criterion; step 5, judging whether the algorithm termination time is reached; if the algorithm termination time is reached, the algorithm ends, and the current best path is output; otherwise, returning to step 2. The application effectively solves the problems of minimizing path length and path smoothness in robot path planning, and has the positive effects of improving path planning efficiency and optimizing path quality.

A robotic arm path planning method based on a Direction Extended Rapidly-exploring Random Tree (RRT) algorithm includes: determining a workspace of a robotic arm; determining a starting node and a target node based on the workspace, and performing modeling using an initialized random tree to obtain an obstacle space; generating a random node in the obstacle space, and setting a bias probability; determining whether a current random node collides with an obstacle; if yes, obtaining a new random node, until a currently generated random node does not collide with an obstacle; if not, determining whether the current random node is the target node; if the current random node is not the target node, continuing to generate new random nodes; if the current random node is the target node, obtaining an initial path; and optimizing the initial path to obtain a final path.

A method for robot path planning using skills extracted from human-taught motion programs applied to a new obstacle environment. A three-dimensional convolutional neural network is used to extract features characterizing an obstacle environment, where the feature vector representation of the obstacles overcomes problems encountered when using point cloud obstacle data. The obstacle feature data and robot path start and goal points are provided to an encoder / decoder neural network system which is trained to extract skills from a database of human-generated motion programs. The encoder / decoder neural network system produces a distribution of waypoints for the current obstacle environment and start / goal points. The distribution of waypoints is used to perform a final collision-free path generation using either a rapidly-exploring random tree (RRT) technique or an optimization-based technique.

The invention relates to the technical field of numerical control machining, and discloses a non-cutting path planning method and electronic equipment, and the method comprises the steps: obtaining a path starting point and a path ending point; constructing two exploration random trees by respectively taking the path starting point and the path ending point as root nodes; by taking the path distance of a non-cutting path between the path starting point and the path ending point as an optimization target, respectively adjusting the two exploration random trees to obtain two first exploration random trees; and obtaining a target non-cutting path based on the first exploration random tree. The problem that the workpiece machining efficiency is low can be solved.

The application discloses a kind of adaptive multistate bidirectional RRT mechanical arm path planning methods based on branch direct connection, the method is distinguished to random tree growth state, different exploration algorithms are used for dense obstacle environment and open environment;Target-oriented mechanism is introduced, adaptive target sampling algorithm is designed, exploration and target orientation are reasonably carried out;Adaptive growth step controller is designed, and the growth step is reasonably adjusted for open environment, complex environment and narrow channel environment;Design branch connection strategy, save computing resources while improving path search speed;In addition, two trees independently add target sampling and growth step controller to fully utilize the characteristics of double search tree.The method is aimed at the problem that path search algorithm is slow and inefficient in different environments, by designing adaptive target sampling probability algorithm, adaptive growth step algorithm and branch direct connection strategy, the performance of the algorithm is effectively improved.

The invention discloses a global path planning method based on a potential energy guided fast search random tree algorithm. The method belongs to the technical field of intelligent automobile path planning. The technical problem that a traditional fast search random tree algorithm causes a planned track to run close to an obstacle is solved. The method comprises the following steps of: determining the positions of obstacles and the starting point and terminal point positions through a two-dimensional space map planned by a vehicle, calculating the potential energy value of any point in the map, superposing the potential energy values of all the obstacles to obtain the potential energy value of any point, and obtaining the potential energy values of all the points in the two-dimensional space map according to the same method; normalizing the potential energy value of each point of the whole map to obtain a potential energy map matrix; and introducing the potential energy map matrix into a fast search random tree algorithm, setting a potential energy threshold, screening random generation points, introducing the potential energy value into a cost function of the fast search random tree algorithm after screening, and performing rewiring optimization, thereby performing vehicle path planning.

A construction method of a derrick parallel control digital twinning system comprises the steps that S1, a digital twinning geometric model of a derrick is constructed based on derrick work site and derrick structure data, a knowledge graph of the derrick is constructed based on data related to the derrick, and the knowledge graph and the digital twinning geometric model of the derrick are fused to deduce a construction planning process scheme; s2, on the basis of the digital twinborn geometric model of the derrick, simulation of derrick operation is carried out according to different working conditions, an intelligent derrick parallel controller is constructed, intelligent prediction is carried out on the basis of a simulation result by using an extreme random tree algorithm in combination with a Donglong optimization algorithm, and a multi-target optimization solution model is constructed; and S3, integrating the multi-target optimization solution model into a derrick parallel controller, and realizing parallel control of the derrick by taking a construction planning process as a target. The deduction result of the design serves as a control target of a physical system, parallel control of the physical system and an artificial system is achieved, and then digital management and control of power grid tower building construction are achieved.

A mechanical arm path planning method and system based on adaptive expansion sampling belong to the technical field of path planning, and solve the problems of slow sampling rate, slow convergence speed and poor initial path quality caused by too random sampling area and unsuitable expansion step length selection when planning the path of the mechanical arm under the prior art; the adaptive expansion sampling strategy provided by the present application introduces a target bias force to correct the growth direction of the random tree based on the F-RRT* optimization algorithm, so that it is biased towards the target point, optimizes the inflection point, makes the generated path smoother, introduces the concept of target point gravity deviation, adaptively expands the strategy according to the complexity of obstacles in the environment, and expands with a dynamic step length, improves the stability and precision of the trajectory, and reduces the length of the generated path, the sampling times and the convergence time.

The invention relates to the technical field of ship path planning, and particularly discloses an unmanned sailing ship local path planning method and system, and the method comprises the steps: S1, building a sea area map; s2, constructing a random tree; s3, obtaining a new node, if the new node is in a headwind state, executing the step S4, otherwise, executing the step S5; s4, judging whether the new node falls outside a preset headwind constraint area, if so, executing S5, and if not, terminating the expansion and returning to S3; s5, judging whether the new node passes collision detection or not, if so, adding the new node to the random tree, otherwise, terminating the expansion and returning to S3; s6, reselecting a father node for the new node; s7, re-routing the random tree; and S8, judging whether the new node arrives at the terminal point, if so, judging whether the number of iterations reaches the maximum number of iterations, if so, completing local path planning, if not, returning to S3, and if not, returning to S3. According to the method, the local path of the unmanned sailboat is optimized and planned.