31 results about "Time trajectory" patented technology

The invention discloses an industrial safety detection method combining time alignment and motion consistency, and belongs to the technical field of industrial safety monitoring. According to the method, through seven steps of multi-camera data acquisition and preprocessing, target feature extraction, coordinate projection, instantaneous speed estimation, multi-dimensional similarity fusion, soft matching optimization and model training and target trajectory generation, the problem of space-time inconsistency during multi-camera cooperative detection in an industrial scene is solved. A camera clock offset parameter is innovatively introduced to correct a cross-camera time difference, appearance, geometry and time prior multi-dimensional similarity are fused, a multi-loss function optimization model is constructed, and cross-camera target accurate matching and long-time trajectory tracking are realized. High-precision technical support is provided for personnel safety monitoring and equipment abnormal behavior detection in an industrial scene, and the industrial production safety protection capability is improved.

The invention provides a Markov jump-based mechanical arm preset time trajectory tracking control method, which comprises the following steps of: calculating a trajectory tracking error by establishing a two-degree-of-freedom mechanical arm dynamic model with a Markov jump characteristic; a trajectory tracking error is subjected to nonlinear transformation, a nonsingular terminal sliding mode surface is constructed in combination with a preset convergence time upper limit function, and then a control torque is synthesized through an equivalent control item and a robust switching item containing a sliding mode surface sign function and a switching gain to drive a mechanical arm. And the trajectory tracking error is difficult to converge in the preset time.

The invention discloses an intelligent robot trajectory planning method and system based on visual inspection. The method comprises the following steps: acquiring obstacle motion state data through a sensor array, performing time alignment and multi-modal fusion, and constructing an initial state vector; iteratively updating the state by adopting a particle filter algorithm, and generating a smooth trajectory sequence through continuity correction and time sequence integration; determining a potential collision area based on polynomial fitting, and performing extension to obtain a predicted collision boundary; extracting passable grids to construct a dynamic risk map, screening low-risk routes, and sequencing to determine an optimized path; performing correction according to deviation feedback by simulating a forward verification path to generate a final execution instruction; state deviation is continuously monitored in the execution process, and the control scheme is dynamically adjusted. According to the invention, real-time trajectory planning and intelligent path optimization of the robot in a dynamic obstacle environment are realized, and the movement safety of the robot is remarkably improved.

This application relates to a predetermined-time tracking control method for a free-floating space manipulator system, and pertains to the field of trajectory tracking control technology for manipulator systems. The aim is to address the poor stability and low robustness of free-floating space manipulator systems when facing model uncertainties and external disturbances. This application establishes a dynamic model of the space manipulator in free-floating mode; designs a nonlinear disturbance observer based on predetermined-time convergence; constructs piecewise continuous sliding mode variables based on the dynamic model; constructs a non-singular predetermined-time sliding mode controller based on the dynamic model, the nonlinear disturbance observer, and the piecewise continuous sliding mode variables; and utilizes the non-singular predetermined-time sliding mode controller to perform predetermined-time trajectory tracking control on the free-floating space manipulator system.

A kind of double-runner dehumidification energy-saving optimization control method for multivariate collaborative regulation, comprising: obtaining the state observation data and equipment limit value of each measuring point, generating material regeneration demand estimation curve and desorption boundary threshold set.According to material regeneration demand estimation curve and desorption boundary threshold set, calculate the regeneration heat trajectory and residence time trajectory required for desorption, generate a set of safe operation constraints.Based on regeneration heat trajectory, residence time trajectory and a set of safe operation constraints, combined with the decision quantity corresponding to the set optimization target, determine the control setting sequence and reference path at the current time.The control setting sequence is issued to the execution unit, and the execution unit is scheduled according to the reference path, and the actual execution record and execution deviation data are monitored and output in real time.Based on actual execution record and execution deviation data, update the estimated value of material adsorption capacity and desorption temperature, and correct the regeneration heat trajectory and residence time trajectory in adjacent rolling time window.

The invention discloses an intelligent ocean vessel scheduling method and system based on AIS space-time trajectory data, and the method comprises the steps: obtaining the AIS space-time trajectory data of a plurality of vessels in a target sea area, constructing a space-time correlation structure of the plurality of vessels in the dimensions of course, speed and arrival time, and constructing a vessel group cooperative behavior mode based on the space-time correlation structure; identifying a space-time area where the ship tends to decelerate, stay or converge intensively in a preset time window, and dynamically generating a virtual anchor ground area according to the stability and continuity of group behaviors in the space-time area; taking the virtual anchor ground area as an implicit navigation constraint condition, forming a joint constraint in combination with a ship group collaborative behavior mode, and performing potential navigation path prediction on a ship with an AIS signal missing or abnormal state; and adjusting the scheduling of the ocean vessels based on the predicted trajectory to obtain a scheduling decision scheme. According to the invention, the congestion risk and waiting time are reduced, and the marine traffic efficiency and the scheduling intelligence level are improved.

The application relates to the field of space-time trajectory calculation, in particular to a space-time trajectory completion method and device based on big data, equipment and medium, wherein the method comprises the following steps: acquiring trajectory data of a specified target, wherein the trajectory data comprises position information and time information; generating a to-be-completed trajectory coordinate graph based on the position information; if there is a blank trajectory in the to-be-completed trajectory coordinate graph, calculating the similarity between the to-be-completed trajectory and an approximate trajectory in a historical trajectory based on a disconnected point of the blank trajectory; completing the blank trajectory according to the approximate trajectory with a similarity within a specified threshold; and performing matching degree calculation based on the completed trajectory, and retaining the completed trajectory with the highest matching degree. The method disclosed by the application can draw a reasonable complete trajectory under the condition that the position information is lost, and has low calculation complexity and high calculation performance.

The embodiment of the invention relates to the technical field of body intelligence, and provides a space-time trajectory splicing method and device of a robot, electronic equipment and a medium, and the method comprises the steps: obtaining current observation data and current absolute time when a target robot executes a current action sequence; determining a residual expected action sequence based on a time node corresponding to the current absolute time in the current action sequence; estimating a planning state starting point on the expected action sequence based on the current observation data, the current absolute time and the estimation model reasoning time; inputting the current observation data and the planning state starting point into a vision-language-action model, and outputting a target action sequence through the vision-language-action model; and the target action sequence is spliced to the expected action sequence according to the time sequence, and a space-time trajectory splicing result of the target robot is generated. Therefore, asynchronous, continuous and smooth real-time action output under large model reasoning delay is realized, and pause, jitter and impact are eliminated.

The embodiment of the invention relates to the technical field of transmission, in particular to a mover control method of a transmission line, which comprises the following steps: controlling a target mover in the transmission line to move according to a preset position and time trajectory diagram to obtain an actual position and time trajectory diagram; according to the actual position and time trajectory diagram and the preset position and time trajectory diagram, performing position ring adjustment processing on the target mover to obtain a target position and time trajectory diagram; controlling the target rotor to move according to the target position and the time trajectory diagram to obtain an actual speed and time trajectory diagram; according to the actual speed and time trajectory diagram and a preset speed and time trajectory diagram corresponding to the target rotor, performing speed ring adjustment processing on the target rotor to obtain a target speed and time trajectory diagram; and obtaining a first control parameter according to the target speed and the time trajectory diagram. According to the invention, through layered adjustment of the position ring and the speed ring, double optimization of the motion accuracy and smoothness of the rotor is realized, and finally, the control stability of the rotor under load change is improved.

The application provides a screening method and device for associated target archives, comprising: obtaining a space-time trajectory corresponding to a reference archive and a space-time trajectory corresponding to a to-be-associated archive, the reference archive being an archive of a known target; calculating a first similarity value of the space-time trajectory corresponding to the to-be-associated archive and the space-time trajectory corresponding to the reference archive; determining a same-trip probability according to the number of same position collection points in the space-time trajectory corresponding to the reference archive and the space-time trajectory corresponding to the to-be-associated archive, the number of position collection points included in the space-time trajectory corresponding to the reference archive, and the number of position collection points included in the space-time trajectory corresponding to the to-be-associated archive; determining an association parameter according to the first similarity value and the same-trip probability; and when the association parameter is greater than or equal to a first preset threshold, classifying the to-be-associated archive into an associated target archive library corresponding to the known target. Through the method, the problems that the current method is only applicable to judging same-trip targets, has a small range of action, and has low archive screening efficiency are solved.

A double-rotating-wheel dehumidification energy-saving optimization control method oriented to multivariable cooperative regulation comprises the steps that state observation data and equipment limiting values of all measuring points are obtained, and a material regeneration demand estimation curve and a desorption boundary threshold set are generated; and according to the material regeneration demand estimation curve and the desorption boundary threshold set, calculating a regeneration heat trajectory and a residence time trajectory required by desorption, and generating a safe operation constraint set. And based on the regenerative heat trajectory, the residence time trajectory and the safe operation constraint set, determining a control setting sequence and a reference path at the current moment in combination with a decision amount corresponding to a set optimization target. And issuing the control setting sequence to an execution unit, controlling the execution unit to perform feedforward scheduling according to the reference path, and monitoring and outputting actual execution records and execution deviation data in real time. And based on the actual execution record and the execution deviation data, updating the estimated values of the adsorption capacity and the desorption temperature of the material, and correcting the regeneration heat track and the retention time track in the adjacent rolling time window.

The application provides a multi-sensor fusion robot grasping path planning method and device, and relates to the field of automation. The method comprises the following steps: constructing a first time correction relationship based on multi-source sensor observation parameters; inputting hardware timestamps synchronized to a master clock source into an extended state estimation model based on the first time correction relationship; iteratively updating the multi-source sensor observation parameters based on the extended state estimation model, and constructing a second time correction relationship according to the updated multi-source sensor observation parameters; constructing a pose continuous time trajectory function corresponding to a target robot based on the second time correction relationship; taking the continuous time trajectory function and the multi-source sensor observation parameters as inputs, and outputting a grasping path corresponding to the target robot through a joint optimization model with a time sequence consistency constraint; and controlling the target robot to perform a grasping operation based on the grasping path. The application solves the problem of low precision of the robot grasping path in the prior art.

The application discloses an unmanned ship scheduled time trajectory tracking method based on asymmetric preset performance, which comprises the following steps: S1, a kinematics model and a dynamics model of a three-degree-of-freedom unmanned ship are established based on an Euler-Lagrange method, and the kinematics model and the dynamics model are expressed as a state equation of the unmanned ship system; S2, a system structure with scheduled time convergence characteristics is constructed, and stable convergence of the state of the unmanned ship system within scheduled time is realized; and S3, an asymmetric preset performance function is designed, trajectory tracking errors of the unmanned ship system are constrained, a dynamic evolution process of the errors is limited, and the errors are guaranteed to meet preset performance indexes. The application has the beneficial effects that a novel asymmetric preset performance function is constructed, the dynamic evolution process of system errors can be effectively constrained, the state errors of the system are always kept within preset performance boundaries, and therefore, the stability and control precision of the trajectory tracking process of the unmanned ship are improved.

The application discloses a kind of ocean-going ship intelligent scheduling method and system based on AIS space-time trajectory data, method includes: obtaining the AIS space-time trajectory data of multiple ships in target sea area, constructs the space-time association structure of multiple ships in the dimension of heading, speed and arrival time, constructs ship group cooperative behavior mode based on space-time association structure;Identify the space-time region that ship presents convergence deceleration, stay or dense convergence in predetermined time window, and dynamically generate virtual anchor area according to the stability and persistence of group behavior in space-time region;Virtual anchor area is used as implicit navigation constraint condition, and combined with ship group cooperative behavior mode to form joint constraint, potential navigation path prediction is carried out to ship with AIS signal missing or abnormal;Based on predicted trajectory, the scheduling of ocean-going ship is adjusted, and scheduling decision scheme is obtained.The application reduces the congestion risk and waiting time, improves the efficiency of maritime traffic and the intelligent level of scheduling.

The invention discloses an agricultural robot intelligent scheduling method based on big data and space-time coupling, and the method comprises the following steps: collecting agricultural data and agricultural robot data, and generating an agricultural state data set; generating an agricultural operation irreversible constraint set; mapping the agricultural operation irreversible constraint set into an irreversible barrier map, and generating a barrier map constraint representation; generating a candidate scheduling scheme set; mapping each candidate scheduling scheme into a scheme spatio-temporal trajectory, and generating a barrier avoidance verification result; when at least one barrier node is triggered, a shortest counter-example trajectory is generated, a minimum contradiction substructure is extracted, a non-executable certificate is generated and bound, and when any barrier node is not triggered, an executable certificate is generated and bound, and an intelligent scheduling result of the agricultural robot is formed. According to the method, by constructing the irreversible barrier map and verifying the spatial-temporal trajectory of the scheduling scheme, pre-judgment screening of the agricultural robot scheduling scheme is achieved, and the method has the advantages of being high in execution reliability and low in rework risk.

A method, apparatus, non-transitory computer readable medium, and system for performing an accelerated denoising process includes obtaining a noise map from a noise distribution. Embodiments then compute, using an image generation model, a denoising vector based on an accelerated denoising trajectory, where the accelerated denoising trajectory accelerates a denoising rate based on a diffusion timestep. Then, embodiments generate, using the image generation model, a synthetic image by denoising the noise map based on the denoising vector.

The invention discloses an unmanned aerial vehicle formation real-time trajectory planning method based on a time coordination strategy. The method comprises the following steps that information interaction is established between different unmanned aerial vehicles; for any unmanned aerial vehicle, according to the obtained interaction information, planning state information of the tail end of the first prediction time domain; for any other unmanned aerial vehicle, the prediction time domain is progressively increased, the unmanned aerial vehicle plans the state information of the unmanned aerial vehicle at the end moment of the prediction time domain according to the state information obtained through interaction until the state information meets a preset threshold value, and a second prediction time domain is obtained; obtaining a second prediction time domain of all unmanned aerial vehicles, and obtaining an average residual number of iterations; and any unmanned aerial vehicle acquires state information of other unmanned aerial vehicles at each moment, and plans state information and control information at different moments in an average prediction time domain, so that the aircraft is controlled by the acquired control information to complete time cooperative flight. The method disclosed by the invention can ensure that the multi-unmanned aerial vehicle system can simultaneously arrive at the specified target position to complete the synchronous implementation of task execution.

The invention relates to the technical field of process engine control, and discloses a training planning process control method and system based on an Activity process engine. The method comprises the following steps: extracting an instance state snapshot from a process engine, analyzing to construct a time trajectory map of process evolution, marking a key path and a branch point, and generating a process evolution mode template library; and the current evolution stage is accurately determined by matching the real-time process with the template. And then dynamically loading a corresponding control strategy, analyzing the rule to generate a node-level operation instruction, and converting the node-level operation instruction into a model adjustment command which can be identified by an engine. Synchronously monitoring the synchronization state of the resource consumption and the flow track, and automatically calculating a resource quota adjustment scheme when deviation occurs. And finally, cooperatively scheduling a model adjustment command and a resource scheme, forming a control instruction set, and distributing the control instruction set to an engine and a resource manager to realize efficient and adaptive evolution of a flow according to an expected path. According to the invention, the intelligent level of process management and the resource utilization efficiency are improved.

The invention relates to the technical field of exercise training, in particular to a real-time trajectory deviation correction method of a virtual-real fusion training system, which comprises the following steps: predicting a behavior trajectory of an operator in a future first time period through a first prediction model, and predicting an intention trajectory of the operator in the future first time period based on a physiological signal, and finally fusing the behavior track and the intention track. Calculating a proficiency score according to historical performance data of the operator, and dynamically adjusting parameters of a correction algorithm based on the proficiency score; compared with the prior art which mainly depends on single motion sensor data to carry out hysteresis trajectory tracking and has the defects of large response delay and late intervention opportunity, the neural intention decoding based on the electromyographic signals and the behavior trajectory prediction based on the motion sensor are fused; advanced perception and prediction of the motion intention of the operator are realized, so that the system can carry out early intervention before deviation occurs, and the real-time performance and foresight of correction are remarkably improved.

The present application belongs to the technical field of trajectory tracking, and particularly relates to a robot online strict on-time trajectory tracking method based on arc length driving, steps of which comprise: collecting environment input information; calculating arc length increment of adjacent discrete points and arc length node sequence; in each sampling control period, adopting fixed time sliding mode control to correct expected linear velocity, controlling robot to move with the corrected expected linear velocity; obtaining linear velocity amplitude and expected heading angle; designing angular velocity control law to realize heading adjustment; estimating instantaneous curvature, applying discrete first-order change rate constraint to the limited expected linear velocity and uniformized angular velocity to obtain smooth instruction to control robot to move; when the remaining arc length is less than the arc length threshold, adopting linear interpolation to gradually lower the linear velocity to the lower limit of linear velocity, and repeatedly executing the control flow in each sampling control period until the robot reaches the target position. The present application can consider on-time arrival and path geometry invariance, and has small calculation cost.

The invention discloses a multi-modal spatial-temporal trajectory fusion method, device and equipment, a medium and a program product. The method comprises the following steps: acquiring multi-modal spatio-temporal trajectory data to be processed; based on a preset time threshold value and a preset space threshold value, determining a co-occurrence relation pair which is adjacent in time and space between the to-be-processed space-time trajectory data of each mode; edges are established according to the co-occurrence relation pairs so as to construct a heterogeneous connection graph between the modal nodes, and attributes carried by each edge comprise space-time co-occurrence features and association strength features of the corresponding co-occurrence relation pairs; inputting the heterogeneous connection graph into the trained graph convolutional neural network to generate a target embedded vector; and performing clustering fusion on the target embedded vector according to a preset similarity threshold value to obtain a trajectory fusion result. The spatial-temporal trajectory is mapped into the spatial-temporal topological graph, so that the graph convolutional neural network can be successfully applied to the field of trajectory fusion, efficient and accurate trajectory fusion is realized, and meanwhile, the method can be well adapted to multi-modal data and sparse data.

The invention belongs to the technical field of data mining, and particularly relates to a method for discovering personnel periodic occurrence probability and main activity based on a multi-dimensional spatio-temporal trajectory. The method comprises the following steps: S1, preparing data and environment; s2, data preprocessing; s3, calculating a main activity place of the personnel; s4, business screening and list output; and S5, ending. S3, taking a periodic occurrence weighted probability P value as a benchmark, and according to a multi-level inverted sequence arrangement mode of administrative administration levels, calculating to obtain a main activity place, a working place and a living place of the personnel to be more practical; and S4, business screening and list output are carried out, in the process, according to specific business requirements, a weighted probability P appears according to a period, and the P value considers the distribution uniformity of personnel trajectories in a time dimension, the acquisition time freshness, the spatial distribution characteristics of different administrative regions and the overall probability distribution condition of hierarchical administrative regions. According to the method, the mastering ability of the population data is improved through data mining and processing under the condition of not additionally increasing administrative organization acquisition data.

The application discloses a preset time trajectory tracking control method for a planetary probe under input saturation. The method comprises the following steps: establishing an initial dynamic model of the planetary probe in an atmospheric entry section; setting a reference radial distance of the planetary probe; determining an initial height tracking compensation error and a first-order height tracking compensation error of the planetary probe based on an actual radial distance in the initial dynamic model and the reference radial distance; obtaining a second-order height tracking compensation error based on the initial dynamic model, the initial height tracking compensation error and the first-order height tracking compensation error; and setting an initial sliding mode variable, processing the initial sliding mode variable, and obtaining a first-order sliding mode variable. The application solves the technical problem that the planetary probe cannot achieve high-precision landing within a preset time in a complex space environment.

The invention discloses a spatial-temporal trajectory information-based source item inversion prior construction method, which comprises the following steps of: firstly, acquiring abnormal radionuclide concentration monitoring data through a stepwise processing flow, dividing the abnormal radionuclide concentration monitoring data into a non-zero measuring point and a zero measuring point, and then respectively generating a corresponding source item-receptor sensitivity matrix (SRSM) by utilizing back diffusion simulation; the method comprises the following steps: firstly, calculating a non-zero track accumulated quantity n (x, y, t) based on a non-zero measuring point, calculating a penalty coefficient lambda (x, y, t) based on a zero measuring point, then fusing and constructing a space-time track matrix Mst (x, y, t), extracting a time priori function Ptime (t) and a space priori function Plocation (x, y), and inputting the time priori function Ptime (t) and the space priori function Plocation (x, y) into an inversion algorithm as priori distribution. The structured spatio-temporal trajectory information processing method can constrain the release time and the release position at the same time, so that the inversion result has higher accuracy and stability in time and space dimensions.

This invention discloses a sliding mode control method for predefined time trajectory tracking of a robotic arm, belonging to the field of robot industrial assembly. First, the desired trajectory information of the robotic arm is obtained; an n-DOF robotic arm dynamic model is established and its form is transformed to obtain the transformed n-DOF robotic arm dynamic model; a predefined time extended state observer is designed to obtain estimated disturbance and actual velocity information; a non-singular predefined time sliding surface is designed; and a predefined time sliding controller is designed based on the sliding surface and the obtained estimated disturbance and velocity information, resulting in a predefined time sliding control law that achieves trajectory tracking control of the robotic arm within a predefined time. This invention can effectively achieve accurate trajectory tracking of the robotic arm and meets the requirement of predefined time convergence of the robotic arm system.

The invention discloses a humanoid robot control method based on a time sequence track and impedance control. The method comprises the following steps: constructing X, Y and Z axis sine and cosine time sequence track baselines associated with a gait cycle; sensing the reaction force and speed of the foot end in real time, and deducing mechanical parameters; constructing an adaptive impedance coefficient Z (t) containing proportional, differential and integral gains, and dynamically adjusting the gains; correcting the track based on Z (t); and through electro-hydraulic servo execution and closed-loop feedback optimization, control input is generated, and stability is evaluated. A double-channel cooperative control framework with the self-adaptive impedance coefficient Z (t) as the core is constructed, the contradiction of insufficient track rigidity and environment adaptability in a traditional humanoid robot control method is solved, the limitation of traditional gain adjustment and track correction splitting is broken through, two adjustment channels can be driven at the same time, and the control precision is improved. The system response speed is adjusted and optimized through dynamic gain, environment impact is avoided through track real-time correction, and the dual control effect of flexible response and active adaptation is achieved.

The application discloses a kind of multi-modal space-time trajectory fusion method, device, equipment, medium and program product.The method comprises: obtaining multi-modal to-be-processed space-time trajectory data;Determine the co-occurrence relationship pair of adjacent in space-time between each modality to-be-processed space-time trajectory data based on preset time threshold and preset space threshold;According to co-occurrence relationship pair, edge is established to construct the heterogeneous connection graph between each modality node, and each edge carries attribute, including the space-time co-occurrence feature and the correlation intensity feature of corresponding co-occurrence relationship pair;The heterogeneous connection graph is input into trained graph convolutional neural network to generate target embedding vector;According to preset similarity threshold, target embedding vector is clustered and fused to obtain trajectory fusion result.Through mapping space-time trajectory into space-time topology graph, so that graph convolutional neural network can be successfully applied in trajectory fusion field, to realize efficient, accurate trajectory fusion, while can well adapt to multi-modal data and sparse data.

The application provides a 5DOF ship crane fixed-time trajectory tracking control method with error constraint, relates to the ship crane control technical field, and comprises the following steps: based on the dynamics model of the ship crane, a state and disturbance observer is constructed to estimate the unmeasurable state and lumped disturbance of the crane within a fixed time; based on the estimated unmeasurable state and lumped disturbance, a fixed-time control instruction is generated to make the trajectory tracking error of the crane converge within a preset fixed time; in the process of generating the control instruction, an error constraint mechanism is introduced to limit the trajectory tracking error and load swing angle within a preset safety boundary in the whole control process. The method can accurately perceive the system state and disturbance within a fixed time, realize convergence within a fixed time, and ensure safety in the whole control process.