39 results about "Optimal trajectory planning" patented technology

The invention relates to the field of four-rotor control, and discloses an optimal trajectory planning method for a four-rotor suspension payload system, which comprises the following steps of: establishing a four-rotor suspension payload system kinetic model; for unknown lumped disturbance in the established model, estimating the lumped disturbance through a predefined time nonlinear disturbance observer to obtain a compensated nominal model; based on the real-time positions of the four rotors, a dynamic window particle swarm optimization algorithm is adopted in the detection range of a sensor carried by the four rotors to minimize a cost function about path points, and an initial optimal track is found; and taking the compensated nominal model as a new prediction model, taking the initial optimal trajectory as a reference trajectory, and using nonlinear model prediction control to minimize a cost function so as to obtain a prediction trajectory meeting system constraints. According to the method disclosed by the invention, the load transportation reliability and stability can be improved, and the control precision is effectively ensured.

The invention provides an improved particle swarm optimization (PSO) algorithm for mechanical arm trajectory planning, and aims at solving the problems that a traditional PSO algorithm is low in convergence speed and prone to falling into a local optimal solution. Therefore, the inertia weight and the learning factor of the algorithm are dynamically adjusted, so that the inertia weight and the learning factor change along with the increase of the number of iterations, and the global search capability and the convergence speed are enhanced; meanwhile, an elite reverse learning (EL) strategy is introduced, an optimal trajectory planning scheme is selected according to a fitness function, a new search area is explored through reverse particles, and the local search capability is enhanced; and a Gaussian-Cauchy variation (GC) strategy is combined, so that the global search capability is further improved, and a local optimal solution is avoided. In the optimization process, a single-target optimization method is adopted to carry out hierarchical classification on population solutions, and the performance of the algorithm under single-target optimization and constraint conditions is improved. Finally, the trajectory of the mechanical arm is optimized based on the algorithm, and particularly, each time period in a 3-5-3 polynomial interpolation method is finely optimized, so that the time from an initial point to a target point is shortened, a trajectory planning scheme with the optimal time is obtained, and the working efficiency of the mechanical arm is improved.

The invention belongs to the technical field of robot control, and particularly discloses a robot time optimal trajectory planning method based on dynamic constraints, which comprises the following steps: establishing a dynamic model, initializing a genetic algorithm population, and generating a joint space trajectory parameter set; performing genetic manipulation on the population; evaluating the trajectory execution time of each trajectory parameter group, and judging whether a constraint condition is met or not; if the conditions are not met, continuing iteration, otherwise, screening a plurality of trajectory parameter groups as local optimization initial solutions; taking the initial solution as input, constructing a trajectory model based on a B-spline curve, and adopting a sequential quadratic programming method to carry out iterative optimization on a trajectory parameter group under constraint conditions; and comparing the plurality of optimized trajectory schemes, and outputting a group which meets the constraint and has the shortest trajectory time as a final trajectory. According to the method, the global search capability of a genetic algorithm and the local fine optimization capability of sequential quadratic programming are fused, and global optimization of trajectory execution time can be realized under complex physical constraints.

The invention relates to an SPMSM time optimal trajectory planning method considering a short-time dynamic feasible region, and belongs to the technical field of servo motor control and trajectory planning. The method comprises the following steps: constructing a trapezoidal feasible region consisting of a peak torque boundary, a constant power curve boundary and a maximum rotating speed boundary based on an actual torque-rotating speed characteristic of the SPMSM as a basic dynamic constraint of trajectory planning; on the basis of the trapezoidal feasible region, introducing short-time overload thermal power constraint based on an energy consumption model, and forming a short-time dynamic feasible region of the trapezoidal feasible region and the thermal power constraint; the method comprises the following steps: by taking'positioning time minimization 'as a target, combining short-time dynamic feasible region constraint, and adopting a high-order polynomial trajectory and an SLSQP algorithm, completing solution and optimization of a time optimal trajectory. According to the invention, the reliability and wide working condition adaptability of the trajectory planning scheme are improved.

The invention discloses a multi-strategy fusion whale optimization algorithm, belongs to the technical field of algorithm optimization, and constructs a multi-strategy fusion whale optimization algorithm for solving the problems of low operation efficiency and poor stability and globality in a time optimal trajectory planning process of an industrial mechanical arm on the premise of meeting kinematics constraints. An optimal neighborhood disturbance and variable spiral position updating strategy is introduced on the basis of a traditional whale optimization algorithm, the limitation of local optimum is broken through, a nonlinear convergence factor and an adaptive weight are introduced, and better solving precision and higher iteration speed are achieved. A trajectory curve frame is constructed by using a 3-5-3 polynomial interpolation function, and a target function of time is established by taking a UR3 mechanical arm as a research object. Simulation experiments show that the operation time of the mechanical arm is shortened by 11.3% compared with that of a similar whale algorithm, the kinematics curve of each joint is continuous and smooth, and the feasibility of the scheme in the industrial mechanical arm is verified.

The invention discloses a valve core soft landing optimal trajectory planning and control method, and relates to the field of high-speed switch valve control, and the method comprises the following steps: (1) building a non-linear dynamic model of a high-speed switch valve under multi-field coupling; (2) giving a soft landing state constraint equation and a soft landing objective function of the high-speed switch valve to construct a soft landing nonlinear programming problem of the valve element of the high-speed switch valve; (3) solving an optimal soft landing curve of the valve element of the high-speed switch valve by using a primal-dual interior point method; (4) constructing a sliding mode observer to estimate the displacement of the valve element, feeding the displacement back to a sliding mode controller, and inversely solving a driving voltage curve; soft landing of the valve element is achieved. According to the method, the optimal soft landing track of the valve element of the high-speed switch valve can be solved, soft landing control is conducted on the valve element, noise and vibration are reduced, abrasion is reduced, and the service life is prolonged. The method is suitable for the fields of high-speed switch valve control strategies, soft landing trajectory planning and control and the like, and a new thought is brought to the high-speed switch valve driving control strategies.

The invention is suitable for the technical field of trajectory planning, and provides an optimal trajectory planning method for excavator pipe ditch operation, which comprises the following steps: establishing an excavator kinematics and dynamics model; the pipe ditch operation mode is divided into straight ditch excavation and side wall finishing; a piecewise polynomial interpolation method is adopted, a straight ditch excavation track and a side wall finishing track are planned in a joint space, and the angle, the angular speed and the angular acceleration of each joint of the excavator are obtained; the interpolation time of each segment in the segmented polynomial trajectory is used as a variable, and a trajectory planning model with mining time, joint impact and mining energy consumption as a comprehensive target is established; optimizing the trajectory planning model by adopting a self-adaptive genetic algorithm; and outputting the optimized pipe ditch excavation track. According to the method, aiming at the optimal excavation trajectory planning problem, the excavation trajectory is optimized, and the working efficiency, the smoothness and the energy consumption are effectively considered.

The present invention belongs to the field of robotic arm control technology, and more specifically, is a method for optimal trajectory planning for a robotic arm based on a cascade filter. The method comprises the following steps: Step 1: Using a quintic Bezier curve to locally smooth corners of small line segments; Step 2: Establishing an optimal model for curvature extrema within a constraint range, using the bat algorithm to solve for the optimal control point and complete curve optimization; Step 3: Using a cascaded second-order filter and a sliding window filter to perform dynamic speed planning. The present invention optimizes curvature and employs dynamic speed planning to improve the stability of the robotic arm and the maximum allowable corner feed rate, thereby resolving the issues with traditional speed planning algorithms, which are difficult to modify online and suffer from large speed fluctuations.

The application provides a multi-robot trajectory planning method, which comprises: a preliminary planning step S21, wherein a plurality of planning trajectories containing time information for a plurality of mobile robots are obtained, the plurality of planning trajectories being planning trajectories generated by performing a time-optimal trajectory planning method on the plurality of mobile robots respectively; a conflict identification step S22, wherein a conflict point between two planning trajectories in the plurality of planning trajectories in the spatial and time dimensions is identified, the conflict point indicating that the mobile robots moving according to the two planning trajectories will arrive at the same position at the same time; and a conflict resolution step S23, wherein the conflict is resolved by adjusting time information of one of the two planning trajectories. A corresponding computer program product is provided. According to the application, the plurality of mobile robots can reach respective destinations without collision in the shortest time.

This invention discloses an optimal trajectory planning method for space robots based on an improved genetic particle swarm optimization algorithm. This method, applied to the optimal trajectory planning of space robots, includes: establishing the kinematic and dynamic equations of the space robot; defining the objective function for optimal trajectory optimization; parameterizing the joint angles of the space robot using sine functions; finding the optimal parameters using an improved genetic particle swarm optimization hybrid algorithm; and solving for the optimal trajectory of the robot using the obtained optimal parameters. The trajectory planning method of this invention minimizes the interference from the base on the space robot. Simultaneously, it uses time and energy consumption as planning objectives, thereby improving the time efficiency and energy utilization efficiency of the robot in completing tasks. This method has advantages such as fast convergence speed and ease of finding the optimal solution, and can provide satisfactory trajectories for space robots.

The application discloses a kind of mud pipeline extension automatic assembly control method and system based on mechanical arm, solve the existing technology in tunnel construction slurry shield mud pipeline extension pipeline assembly docking difficult, low degree of automation Problem.Through being arranged machine vision / radar sensor on pipeline extension walking device trailer, obtain mud pipeline grabbing, transfer and the plane pixel / space point cloud information in the process of assembly, adopt a series of methods such as edge detection, pipeline feature extraction, model fitting to realize the identification and spatial pose positioning of pipeline, realize real-time obstacle avoidance, alarm and optimal trajectory planning in the process of mechanical arm grabbing, transferring pipeline by carrying mechanical arm obstacle avoidance path and trajectory planning module running in industrial computer;Finally realize slurry shield mud pipeline extension automatic assembly whole-process operation, improve the degree of automation of tunnel construction, improve pipeline docking precision, reduce operation time, directly reduce construction period and construction cost.

This invention discloses a time-optimal trajectory planning method for flapping-wing aircraft based on time-varying wind field information, relating to the field of flapping-wing aircraft technology. The method includes: establishing a time-varying wind field model, outputting continuous wind speed and direction that vary with time; establishing a particle kinematic model of the flapping-wing aircraft in both inertial and air coordinate systems based on the time-varying wind field model, and achieving the transformation between the two coordinate systems by designing a virtual target point; deriving the optimal trajectory form of the flapping-wing aircraft in the time-varying wind field model based on the Pontryagin minimum principle; establishing the trajectory equation of the flapping-wing aircraft in the air coordinate system based on the particle kinematic model; establishing equality conditions for solving the trajectory parameters based on the geometric characteristics of the flapping-wing aircraft trajectory; and solving the trajectory parameters using Newton's method based on the equality conditions to obtain the flight trajectory in the inertial coordinate system. This invention can improve the trajectory planning capability of flapping-wing aircraft in complex wind field environments.

The present invention relates to the field of quadrotor control and discloses an optimal trajectory planning method for a quadrotor suspension payload system, comprising the following steps: establishing a dynamic model of the quadrotor suspension payload system; estimating the unknown lumped disturbance in the established model using a predefined time nonlinear disturbance observer to obtain a compensated nominal model; minimizing a cost function about path points within the detection range of the quadrotor's onboard sensor using a dynamic window particle swarm optimization algorithm based on the real-time position of the quadrotor to find an initial optimal trajectory; using the compensated nominal model as a new prediction model and the initial optimal trajectory as a reference trajectory, and using nonlinear model predictive control to minimize the cost function to obtain a predicted trajectory that meets system constraints. The method disclosed by the present invention can improve the reliability and stability of load transportation and effectively ensure control accuracy.

The present application relates to the technical field of multi-degree-of-freedom robot control, and particularly relates to a robot time-optimal trajectory planning method based on an improved sand cat swarm optimization algorithm, which optimizes the working time of the robot with time optimization as the target and ensures that the robot always moves under the constraint condition, and specifically proposes five improvement strategies for the original sand cat swarm optimization algorithm: cubic chaos-refraction reverse learning initialization, adaptive hearing sensitivity, elite pool weighted guided search behavior, spiral Levy flight predation behavior and sand cat alert behavior, which improves the slow convergence efficiency of the sand cat swarm algorithm and improves the working efficiency of the robot; and a motion trajectory is constructed through a 5-7-5 polynomial interpolation function to ensure smooth transition of the overall trajectory of the robot in the motion process, avoid sudden speed changes or shaking, reduce the wear and energy consumption of the robot and achieve good dynamic performance.

The invention discloses a variational auto-encoder trajectory planning method and device for a communication and inductance integrated unmanned aerial vehicle network, and relates to the technical field of wireless communication. The method comprises the following steps: constructing a double-layer unmanned aerial vehicle cooperative network architecture; configuring orthogonal time-frequency air conditioning parameters and antenna array parameters based on the network architecture; based on the modulation parameters and the antenna array parameters, adopting an orthogonal time-frequency modulation technology to extract delay-Doppler domain channel parameters and calculating a communication rate; defining a comprehensive cost objective function; according to the objective function and the communication rate, constructing an optimal problem of trajectory planning under multiple constraint conditions; constructing a model based on a variational auto-encoder; based on an optimal problem, constructing a composite loss function containing a reconstruction error and a constraint penalty term, and training the model to obtain a trained variational auto-encoder-based model; and based on the trained variational auto-encoder-based model, generating an optimal flight path. According to the invention, the flight energy consumption and safety risk of the unmanned aerial vehicle can be reduced.

The invention relates to the technical field of intelligent control, and provides a parallel robot trajectory planning method and system based on a digital twin and dynamic response butterfly algorithm in order to solve the problem that the trajectory tracking synchronization rate is low due to the fact that factors such as actual friction and disturbance are not considered in a traditional method. The method comprises the following steps: firstly, constructing a parallel robot digital twinborn model comprising a kinematic model and a digital twinborn tracking control model; then, a dynamic response butterfly algorithm is adopted to carry out time-optimal trajectory planning; and then carrying out track secondary smoothing processing by introducing an NURBS curve of dynamic weight adjustment and non-uniform node vector optimization. According to the method, the problems of large trajectory tracking error, obvious operation vibration and low virtual-real synchronization rate when the physical entity of the parallel robot is controlled due to the fact that factors such as actual friction and disturbance are not considered in a traditional method are effectively solved, and stable trajectory operation with high precision, high synchronization rate, low vibration and optimal time is realized.

The application discloses a kind of sampling-based mechanical arm time optimal trajectory planning algorithm, it includes: the modeling of industrial robot body;Industrial robot is dynamically modeled, extract the relationship between joint space and corresponding joint angular acceleration, as the drawing condition of trajectory planning map of high-dimensional joint space;The obtained dynamic model is preprocessed, and the joint space sampling probability map is obtained with the reference standard of target joint angular acceleration by space discretization of trajectory planning map;The improved RRT algorithm is used to complete the motion trajectory planning optimization design of mechanical arm.The application can improve the joint utilization of industrial robot as a whole, realize the trajectory planning optimization of mechanical arm with time optimal orientation.

This invention provides a crane anti-sway method and system based on feedforward optimal trajectory planning and feedback model predictive control. The method includes: S1, real-time acquisition and fusion processing of data by an encoder and inertial measurement unit to form a state vector representing the current motion state of the system; S2, based on a simplified dynamic prediction model, using the state vector and target position as input, continuously solving a finite-time-domain constrained optimization problem in each planning cycle to generate a dynamically updated optimal speed reference sequence; S3, using the optimal speed reference sequence as the tracking target, based on an extended prediction model incorporating motor dynamic characteristics, solving a tracking optimization problem in each control cycle to output the optimal torque command at the current moment; S4, sending the torque command to the driver for execution, driving a change in the system state. This invention achieves a deep fusion of globally optimal trajectory planning and locally robust tracking, significantly shortening positioning time, reducing load sway, and possessing strong anti-disturbance capabilities, making it suitable for the automation upgrade of various types of bridge and gantry cranes.

The application belongs to the technical field of robot control, and specifically discloses a robot time-optimal trajectory planning method based on dynamics constraints, which comprises the following steps: establishing a dynamics model, initializing a genetic algorithm population, and generating a joint space trajectory parameter group; performing genetic operations on the population; evaluating the trajectory execution time of each trajectory parameter group, and judging whether the constraint condition is met; if the condition is not met, iteration is continued, otherwise, multiple trajectory parameter groups are screened as local optimization initial solutions; taking the initial solutions as inputs, constructing a trajectory model based on B-spline curves, and iteratively optimizing the trajectory parameter groups under the constraint condition by using a sequential quadratic programming method; comparing the optimized multiple trajectory schemes, and outputting a group meeting the constraint and having the shortest trajectory time as the final trajectory. The method fuses the global search capability of the genetic algorithm and the local fine optimization capability of the sequential quadratic programming, and can realize the global optimization of the trajectory execution time under complex physical constraints.

The application provides a robot strict path time-optimal trajectory planning method and system based on arc length segmentation optimization, and belongs to the technical field of robot control and trajectory planning. The method comprises the following steps: according to a preset Cartesian space path, a continuous mapping relationship between a mechanical arm end pose and joint position along a path parameter and geometric derivatives of each order of the path parameter relative to the path parameter are established; the path parameter is segmented, and a basic motion law of the path parameter changing with time is defined based on each segmented motion time interval; joint space high-order dynamics constraints are converted into algebraic inequality groups dependent on pseudo-motion state variables, geometric derivatives of each order and each segmented motion time interval; a nonlinear programming model is constructed and an optimal time interval sequence is solved, a continuous function of the path parameter with respect to time is reconstructed, and a position, velocity and acceleration trajectory of the mechanical arm joint space is generated in combination with the continuous mapping relationship. The application strictly tracks the path, is time-optimal and satisfies high-order dynamics constraints.

The invention belongs to the technical field of unmanned aerial vehicle intelligent inspection and ground base station docking, and particularly provides an unmanned aerial vehicle inspection docking method and device, and the method comprises the steps of multi-source fusion positioning, optimal trajectory planning, attitude closed-loop control, compliant calibration, docking locking and energy supply. Through a vision, inertia and target fusion positioning algorithm, an optimal trajectory planning algorithm, an attitude closed-loop control algorithm and a compliant calibration strategy, and in cooperation with a modularly integrated hardware device, the problems of low positioning precision, large attitude deviation and poor docking robustness in the prior art are solved; and centimeter-level positioning, stable descending, real-time attitude correction and reliable physical docking of the unmanned aerial vehicle are realized.

The application discloses a kind of based on sparrow optimization algorithm's time optimal trajectory planning method of grabbing arm, belongs to grabbing machine mechanical arm control technical field.The method is first by standard D-H parameter method to construct grabbing arm kinematics model, deduces gripper end posture parameter;Again, 3-5-3 subsection polynomial is used to design trajectory interpolation function, angle, angular velocity, angular acceleration continuity and limit constraint are determined and coefficient is solved;Based on improved sparrow optimization algorithm, the optimal trajectory parameter is searched, and the optimization performance is improved by chaos mapping, Lévy flight and multi-element information guiding strategy;Finally, through transient dynamics simulation analysis boom stress and stick stress, verify trajectory safety.The application forms " modeling-design-optimization-checking" complete technical link, realizes time optimal motion under the premise of meeting various constraints, gives consideration to motion stability and structural reliability, effectively improves the operating efficiency of grabbing machine, and provides strong support for intelligent upgrading of grabbing machine.

The invention discloses an unmanned ship trajectory planning method and system. The method comprises the following steps: S1, obtaining a historical state data sequence of the unmanned ship under the influence of environmental disturbance; s2, on the basis of the historical state data sequence, training is carried out by adopting a neural network model based on Transform to obtain a coupled hydrodynamic model; s3, taking the coupled hydrodynamic model as a state transition model in a reinforcement learning training environment, and training a reinforcement learning agent to obtain an optimal trajectory planning strategy in the reinforcement learning training environment based on a preset state space, an action space and a reward function; and S4, generating a navigation track by using the optimal track planning strategy according to the current state and the target information of the unmanned ship. According to the method, complex hydrodynamic characteristics are learned in a data driving mode and fused into the reinforcement learning planner, a safe, dynamic and feasible track can be generated, and the accessibility of the track, the target point precision and the overall navigation safety are remarkably improved.

The invention discloses a PINN-based reentry gliding end-speed near-optimal trajectory planning method and system, and aims to solve the problems that the reentry gliding trajectory planning of a defense aircraft is subjected to complex constraints (process, control, space-time full state and end-speed near-optimal) and the solving efficiency is low under near space remote strong confrontation. The core of the method comprises the steps of end speed near-optimal longitudinal planning (parameterized terminal speed, multi-parameter resistance acceleration profile, voyage and time analysis prediction and SQP optimization), PINN-based dual-stage adaptive lateral planning (course adjustment / maintenance and PINN rapid prediction of terminal state), three-degree-of-freedom trajectory correction and generation (lateral large maneuvering voyage and time correction, and final speed near-optimal longitudinal planning (parameterized terminal speed, multi-parameter resistance acceleration profile, voyage and time analysis prediction). The system comprises a task scene construction module, a problem modeling module and the like. The method meets the requirements of near-optimal end speed and time-space full-state constraint, is high in terminal precision and low in calculation time consumption, and is suitable for a remote front-out strong confrontation task.

The invention relates to an optimal trajectory planning method for a cable parallel spraying robot, and aims to improve the smoothness, stability and controllability of the trajectory of the robot and optimize the operation efficiency, energy consumption and residual vibration at the same time. According to the method, on the basis of improved quintic B-spline interpolation, by introducing a jerk boundary constraint condition, residual vibration at the starting moment and the ending moment of a track is effectively restrained. And virtual control points are introduced at the starting position and the ending position of the path, and nodes are redistributed, so that the dynamic response characteristics of the system are further optimized. Besides, a time-energy-vibration optimization model is constructed, and time parameters are globally optimized by adopting a quantum particle swarm optimization algorithm, so that high efficiency, stability and smoothness of the trajectory are realized. Simulation experiments show that compared with a traditional B-spline interpolation method, the method achieves remarkable optimization effects in the aspects of running time, energy consumption, jerk variance and the like, and an effective trajectory planning solution is provided for application of the cable parallel spraying robot in a complex working environment.

The invention provides a snakelike mechanical arm rope driving space optimal trajectory planning method and related equipment, and belongs to the technical field of mechanical arm trajectory planning. The method comprises the steps that a unified kinematics model is constructed according to physical structure information of the snakelike mechanical arm; the unified kinematic model comprises a first mapping relation and a second mapping relation; the first mapping relation is the mapping relation between the joint parameters and the position posture of the tail end of the mechanical arm; the second mapping relation is the mapping relation between the joint parameters and the lengths of the driving ropes; based on the unified kinematics model, in the process that the mechanical arm moves from the initial joint state to the target joint state, the total length variation of all the driving ropes is defined as a to-be-minimized optimization target; and solving the optimization target to obtain a joint space movement track with the minimum total length variation. Uniform kinematics model description of snakelike mechanical arms of different structural forms can be achieved, and optimal trajectory planning of the relative slippage amount of the rope is achieved.

The invention discloses a motion trajectory planning and evaluation method and related equipment based on a humanoid robot world model, and the method comprises the steps: obtaining multi-modal sensor data of a current operation scene, and generating global visual angle state real-time information; inputting the global visual angle state real-time information into a strategy network to obtain action track anchor points, generating real-time state-action pairs according to the global visual angle state real-time information and the action track anchor points, and respectively inputting the real-time state-action pairs into a humanoid robot world model, prediction state-action pairs corresponding to the real-time state-action pairs are obtained and are scored by a scoring prediction network; and according to an evaluation result, a target action track is executed by the humanoid robot. According to the embodiment of the invention, the global state can be modeled through the multi-modal data, the future action-state can be predicted through the world model, and the optimal trajectory planning in the dynamic environment can be realized through the multi-dimensional evaluation of the scoring network. The method can be widely applied to the technical field of humanoid robots.

The application relates to a GA-SQP-based time-optimal trajectory planning method for a rope-towing parallel robot, which comprises the following steps: establishing a robot kinematics model; transforming the positions of each key path point in the robot Cartesian space into corresponding rope lengths; establishing a time-optimal trajectory planning model based on cubic spline interpolation; pre-solving the time-optimal trajectory planning model by using a genetic algorithm (GA) to obtain a pre-solution result; taking the pre-solution result as an initial value for iterative solving of a sequential quadratic programming (SQP) algorithm, solving by using the SQP algorithm, and obtaining a time-optimal trajectory of the rope-towing parallel robot under a speed constraint condition. The application can obtain a robot motion trajectory with good smoothness, improves the motion stability of the robot, reduces the working time of the robot, thereby improving the working efficiency of the robot, has strong robustness, does not need a large amount of complex calculation, obtains a global optimal solution with high time efficiency, and has good real-time performance.

The application discloses a method and system for optimal trajectory planning of an unmanned surface vehicle (USV) in a complex environment, wherein the method steps include: state initialization of a target to obtain initial state information; construction of a system model based on the initial state information; construction of a threat-based knowledge graph and reasoning to obtain threat degree information; construction of evaluation indexes in combination with multi-target posterior Cramer-Rao lower bound and the threat degree information; and optimal trajectory planning based on the evaluation indexes. The application combines target and ocean current movement situation to construct a knowledge graph based on marine threats. The threat semantic information in the graph is reasoned through a reinforcement learning method, which effectively solves the shortcomings of traditional threat evaluation methods lacking self-learning ability for threat characteristics and can deeply mine the correlation between evaluation indexes. The application can effectively avoid target threats and ocean current disturbances while optimizing target tracking effect.

The invention provides a trajectory planning model training method and device, a trajectory planning method and electronic equipment. The trajectory planning model training method comprises the steps of performing iterative training on a pre-trained trajectory planning network based on a trajectory planning fine adjustment data set to obtain an optimal trajectory planning prediction strategy; wherein the trajectory planning fine tuning data set comprises a trajectory planning fine tuning real strategy; based on the optimal trajectory planning prediction strategy, updating the trajectory planning fine tuning real strategy, and obtaining an updated trajectory planning fine tuning data set; on the basis of the updated trajectory planning fine adjustment data set, continuing to carry out the next round of iterative training on the pre-trained trajectory planning network to obtain a trajectory planning network; wherein the trajectory planning network is used for predicting a trajectory planning strategy.