36 results about "Motion dynamics" patented technology

The invention belongs to the field of track planning and intelligent control of a reusable vehicle, and relates to an intelligent track planning method for a cruise section of the reusable vehicle. The method comprises the following steps: constructing a three-degree-of-freedom centroid motion dynamics model of a cruise section vehicle, generating an offline optimal trajectory sample library covering wide working conditions based on a Gaussian pseudo-spectral method, designing a mapping relation between deep neural network learning task parameters and trajectory features, and outputting a high-quality trajectory planning initial value online. The distribution of collocation points is dynamically adjusted in combination with a self-adaptive collocation point method, a nonlinear programming problem is iteratively solved with a high-quality initial value as a starting point, and efficient and accurate optimization of the trajectory is achieved. Simulation results show that the method significantly reduces the sensitivity of online optimization to initial guess, still has fast response ability and high robustness under complex constraint and uncertainty working conditions, effectively improves the autonomous trajectory planning ability of the cruise section of the reusable vehicle, and ensures flight reliability and control precision.

The invention provides a design method of a two-wheeled wheel-legged robot, which relates to the field of wheeled robots, and comprises the following steps: determining a machine body of the two-wheeled wheel-legged robot, adopting a leg four-bar mechanism as a leg configuration, and taking the leg four-bar mechanism and the machine body as a five-bar mechanism together, a universal leg rod length parameter calculation method is deduced based on a planar five-connecting-rod model, key geometric parameters are determined, and robot structure design is completed; establishing a wheel type motion dynamical model and a leg type jump phase motion dynamical model, deducing a universal motor model selection method, calculating driving wheel and joint motor parameters, and completing wheel train design and whole machine motion simulation; carrying out finite element analysis and lightweight design on the key parts; and finally, an LQR control strategy is adopted, and cooperative control verification is completed through analysis and simulation software. Wheeled efficient movement and leg type terrain adaptive capacity are fused, limitation of a single movement mode is broken through, and the environment adaptive boundary of the robot is expanded.

The invention discloses a multi-target tracking method and related equipment, and the method comprises the steps: carrying out the target detection of a current frame, outputting a corresponding target detection frame result, carrying out the state transition operation through a target motion dynamics model, and generating a motion prediction frame corresponding to each potential target object in the current frame; based on the confidence of a target detection frame contained in the detection frame information, according to the target detection frame and the motion detection frame, generating a corresponding cost matrix, the cost matrix being a generalized symmetric intersection-to-union ratio or a symmetric overlapping score; and inputting the cost matrix into a Hungary matching system, generating an identity label corresponding to the target detection frame, and carrying out association matching on the identity label and the current activation track. According to the embodiment of the invention, the multi-target tracking processing efficiency can be improved, and the robustness, precision and application value of a multi-target tracking system in a complex dynamic environment can be remarkably improved. The method can be widely applied to the technical field of computer vision tracking.

This invention discloses a spacecraft obstacle avoidance control method integrating model predictive control and incremental safety constraints. The method includes: establishing a relative motion dynamics model of the spacecraft and obtaining current state information; generating nominal control inputs based on the current state information using model predictive control; acquiring environmental information within the spacecraft's current local perception range and constructing a local safe state region; generating an expert sample set within the local safe state region through safety reachability analysis and learning local control obstacle functions online; incrementally combining the newly learned local control obstacle functions with existing functions to form a global safety function; and constructing a safety filter based on the global safety function to correct the nominal control inputs, obtaining actual safety control inputs to drive the spacecraft's motion. This invention improves the robustness and real-time performance of obstacle avoidance control by generating dynamic safety constraints in real-time in unknown and complex environments through online learning and incremental combination of local control obstacle functions.

The invention discloses a synchronous orbit electric propulsion satellite short-range game control method based on differential game, which comprises the following steps: under an LVLH coordinate system, establishing a near-circular orbit relative motion dynamic model of spacecrafts of both pursuit and escape parties, and further determining a state space form in a spacecraft pursuit and escape game process; based on a state space form in a spacecraft pursuit game process, introducing a Hamiltonian function, and constructing a short-distance pursuit game model with optimal time; introducing a co-state equation, and describing a short-range pursuit game process as a two-point boundary value problem; and converting the problem into a parameter optimization problem, and carrying out optimization solution on the problem by utilizing an improved difference method so as to realize short-range game control.

The present invention sets forth techniques for predicting motion in a 3D model. The disclosed techniques include receiving one or more Gaussian primitives representing a 3D scene and receiving one or more control inputs describing one or more primary motions associated with one or more objects. The techniques also include generating, via a first trained machine learning model, a dynamic state based on the one or more control inputs, and generating, via a second trained machine learning model, one or more deformed Gaussian primitives based on the dynamic state and the one or more Gaussian primitives. The techniques further include generating a 2D representation of the 3D scene, and generating an output sequence based on the 2D representation, wherein the output sequence depicts both the primary motions associated with the one or more objects and one or more secondary motions associated with the one or more objects.

The present application relates to the field of aerospace technology, specifically to a kind of multi-pulse parallel construction method of gravitational wave detection formation considering timing optimization, each spacecraft of formation simultaneously departs from virtual center, each spacecraft is moved to the preset specified position by applying multiple pulses, so as to form a kind of spacecraft formation that can be used for space gravitational wave detection, by giving the steps of calculating the initial position and velocity of each spacecraft and applying initial control to reach the initial position and velocity, the state quantity of each spacecraft at each time in the formation construction process is calculated, so as to provide reference for the design of satellite formation task in actual engineering application, and the accuracy of the linearized relative motion dynamics model established by the multi-pulse parallel space gravitational wave detection formation is improved by differential correction, the error in the relative motion dynamics model is reduced, the initial state set in advance can be effectively reached, and the working efficiency of formation component is improved.

The application discloses a kind of distributed spacecraft in-orbit pursuit game control method and system based on vision, which comprises the following steps: S1, the orbit target image sequence is collected using the forward camera of multiple pursuit spacecraft, and the effective target area is screened out;S2, the feature points are extracted using SuperPoint, and the high-confidence matching point pair is output by SuperGlue structure semantic matching;S3, the intrinsic matrix is calculated and the nine-dimensional state vector is generated by fusing the estimation results of multiple spacecraft;S4, the nine-dimensional state vector is used to establish an orbit pursuit game model, and the optimal control law is solved by combining the relative motion dynamics equation to generate the expert strategy trajectory;S5, the trajectory is used to train the control strategy network;S6, the trained control strategy network is deployed to the attitude and orbit control system, and the orbit control instruction is output to form a perception-decision-control closed loop;The application realizes the efficient cooperative control of distributed spacecraft in-orbit pursuit through spacecraft visual perception, feature matching, game modeling and generative adversarial imitation learning.

The invention relates to the technical field of robot control, in particular to an exoskeleton terrain recognition control method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting multi-sensor data through a plurality of sensors installed on an exoskeleton, carrying out the preprocessing and feature extraction of the data, obtaining terrain geometric features and motion dynamics features, and carrying out the recognition of the terrain; and fusing and reinforcing the two types of features to obtain dynamic enhanced features, inputting dynamic enhanced feature vectors into a preset terrain classifier, outputting a new terrain category, and controlling the exoskeleton to generate an optimal joint control instruction matched with the human body motion gait parameters according to the new terrain category to realize exoskeleton joint control. The problems of terrain misjudgment, control lag, insufficient coupling of terrain information and control instructions and the like caused by dependence on a single sensor are solved, and the self-adaptive power assisting capacity of the exoskeleton under the complex terrain is improved.

The present application relates to a kind of multi-unmanned ship fixed time distributed formation control method based on backstepping technique, establishes the dynamic model of unmanned ship movement, and establishes the corresponding fixed time disturbance observer of each follower unmanned ship of pilot unmanned ship, for carrying out online observation and compensation;Further, the backstepping control method enabling multi-unmanned ship to form stable formation in fixed time is constructed, the controller of tracking sub-level system corresponding pilot unmanned ship is constructed by backstepping technique, for controlling pilot unmanned ship to track virtual pilot unmanned ship, and the controller of formation sub-level system corresponding each follower unmanned ship is constructed, for controlling each follower unmanned ship formation to track pilot unmanned ship, the two controllers designed have good convergence, can make the whole formation system stable and reach the expected performance requirement;And preset performance control technique is introduced in design, ensure that formation system still keeps good relative position deviation between unmanned ship under the condition of existing external interference, makes the overall formation configuration stable.

The invention relates to providing motion dynamics estimation. Aspects of the subject technology obtain sensor data from microphones and / or motion sensors in devices disposed on each side of a user's body. The sensor data is used to provide running dynamics estimates including estimates relating to differences between the motion characteristics of the right side of the user's body and the left side of the user's body. These estimates may also be used to provide feedback to the user regarding running style, running route, and injury information.

The invention relates to the technical field of intelligent education, in particular to an AI auxiliary training system for piano playing skill and style analysis, which comprises a multi-modal data synchronization module, an acoustic feature extraction module, a kinematics feature extraction module, a multi-modal feature alignment module, a style matching and deviation analysis module and a personalized training scheme generation module. Performing space-time registration on the audio data and the image data of the piano user to obtain time sequence data; performing high-resolution sound spectrum representation on the playing audio stream to obtain an acoustic skill feature matrix; performing kinematic dynamics reconstruction on the time series data to obtain a kinematic state tensor; performing cross-modal confrontation alignment on the acoustic skill feature matrix and the kinematic state tensor to obtain a composite playing feature tensor; mapping the composite playing feature tensor into a playing style feature library to obtain skill deviation data; and performing directional optimization on the playing style feature library to obtain a personalized correction training scheme. The piano skill improvement efficiency can be improved.

The invention relates to the technical field of tidal current energy utilization, and discloses an oscillating hydrofoil motion response and fluid-structure interaction deformation solving method, which comprises the steps of defining a hydrofoil motion mode and structure and fluid key parameters, and defining core characteristics of pitching given motion, free heaving motion and bending-torsion coupling deformation; establishing a heaving motion kinetic equation based on the Newton's second law, and constructing a bending-torsion coupling deformation control equation in combination with the structural mechanics principle; building a three-dimensional numerical simulation model containing block grids and boundary layer encryption design, and meeting calculation requirements through spanwise and time discretization processing; solving a fluid distribution load and a total lift force based on a Navier-Stokes equation; and a four-order Runge-Kutta method is adopted to solve the heaving motion response, and a Newmark-beta time integral method and a finite difference method are adopted to solve the bending-torsion coupling deformation. In this way, the strong coupling characteristics of hydrofoil movement and fluid-solid coupling deformation can be accurately captured, and technical support is provided for design optimization and performance improvement of the oscillating hydrofoil type tidal current energy device.

This invention relates to the fields of medical auxiliary diagnosis and computer vision technology, specifically to a multimodal video-assisted diagnostic method and system for Parkinson's disease based on Transformer and attention fusion. First, video data of the subject's hand pinching motion and linear back-and-forth walking motion are acquired and a unified sample label is established. Then, video preprocessing is completed through preprocessing, sliding time window segmentation, and data augmentation. Next, the preprocessed temporal image sequence is input into a spatiotemporal modeling network, where a visual Transformer is used to extract frame-level spatial features. A multi-layer long short-term memory network is then combined to capture long-term temporal motion dynamic information. Finally, a modality-level spatiotemporal attention fusion method adaptively learns modality weights and achieves feature fusion. Finally, the fused features are input into a classification network, outputting prediction results for Parkinson's disease patients or healthy controls. This invention comprehensively characterizes the motion features of the disease through multimodal fusion and accurate spatiotemporal modeling, improving diagnostic accuracy and robustness.

A smart glasses system, smart glasses, and a motion data analysis method. The smart glasses system comprises the smart glasses and a smart terminal connected to the smart glasses. The smart glasses are configured for acquiring motion data of a user by means of detecting the motion of the head of the user. The smart terminal is configured for acquiring the motion data transmitted by the smart glasses, obtaining motion dynamic characteristics of the user according to the motion data, and outputting the motion dynamic characteristics. The described smart glasses system, smart glasses, and motion data analysis method can conveniently and accurately measure the motion dynamic data of the user, thereby improving the accuracy of analyzing the motion dynamic characteristics of the user.

The application discloses an intelligent glasses system, intelligent glasses and a motion data analysis method. The intelligent glasses system comprises the intelligent glasses and a smart terminal connected with the intelligent glasses. The intelligent glasses are used for acquiring motion data of a user by detecting head motion of the user. The smart terminal is used for acquiring the motion data transmitted by the intelligent glasses, obtaining motion dynamic characteristics of the user according to the motion data, and outputting the motion dynamic characteristics. The intelligent glasses system, the intelligent glasses and the motion data analysis method can conveniently and accurately measure motion dynamic data of the user, and improve the accuracy of analyzing the motion dynamic characteristics of the user.

The application provides a pin shaft hole wear life prediction calculation method, comprising the following steps: establishing a suspension assembly motion dynamics model through simulation software, performing suspension dynamics simulation analysis calculation, calculating and extracting the maximum radial force value between the suspension swing arm pin shaft and the mounting seat; analyzing the position of the pin shaft with the maximum stress, performing contact finite element analysis calculation on the suspension swing arm pin shaft and the mounting seat, calculating and extracting the maximum shear stress value of the mounting seat hole; calculating the anti-wear times of the suspension swing arm pin shaft and the mounting seat hole according to the IBM wear calculation method in the tribology principle; calculating the wear life of the suspension swing arm pin shaft and the mounting seat hole according to the suspension natural frequency and the working time length. The application discretizes the continuous wear process, converts the complex dynamic problem into a simple quasi-static problem, has the characteristics of short period, low cost and the like, and can be repeatedly performed, and can effectively shorten the research and development period and reduce the research and development cost.

The invention relates to the technical field of video analysis and processing, and discloses a key frame extraction method based on decoupling multi-task feature learning and related equipment. The method comprises the following steps: performing frame sampling, size normalization and brightness standardization processing on an input video to obtain a standardized frame sequence; inputting the data into a time sequence convolution backbone network, and extracting multi-scale spatial-temporal features based on expansion causal convolution; splitting the features through decoupling branches of motion dynamics, scene composition and object semantics to obtain initial feature factors, and performing independence optimization through a factor separation discriminator to obtain independent motion feature factors, independent scene feature factors and independent object feature factors; encoding the scene description text into a scene vector, calculating the weight of each feature factor through an adaptive attention mechanism, and carrying out weighted fusion; and outputting the importance score of each frame by a multi-layer perceptron, and screening out a target key frame through time sequence non-maximum suppression. According to the method, the key frame extraction efficiency and accuracy are improved.

The present application belongs to the field of reusable launch vehicle trajectory planning and intelligent control, and relates to a reusable launch vehicle cruise phase intelligent trajectory planning method. By constructing a three-degree-of-freedom mass center motion dynamics model of the cruise phase launch vehicle, an offline optimal trajectory sample library covering a wide range of working conditions is generated based on the Gauss pseudospectral method, a deep neural network is designed to learn the mapping relationship between task parameters and trajectory features, and high-quality trajectory planning initial values are output online. In combination with the adaptive collocation method, the collocation distribution is dynamically adjusted, and the nonlinear programming problem is iteratively solved with the high-quality initial values as the starting point, thereby realizing efficient and accurate optimization of the trajectory. Simulation results show that the method significantly reduces the sensitivity of online optimization to initial guesses, still has fast response capability and high robustness under complex constraints and uncertain conditions, effectively improves the autonomous trajectory planning capability of the reusable launch vehicle cruise phase, and guarantees flight reliability and control accuracy.

The invention discloses a memory-driven spacecraft inertia estimation method and system and a related product, and belongs to the technical field of spacecraft control. The method provided by the invention comprises the following steps: establishing an attitude motion model containing inertia uncertainty based on a spacecraft attitude motion dynamics relationship; tracking error variables are introduced and reconstructed into an attitude tracking error system motion model; processing the signal by using a fixed parameter linear filtering operator and eliminating a differential term to obtain a first algebraic equation; transforming a regression signal based on the equation to construct an expansion algebraic model; and a historical information accumulation mechanism is introduced in combination with the extended memory regression amount to complete inertia parameter online estimation. According to the method, extra continuous external excitation is not needed, estimation can be achieved only by utilizing the normal attitude motion inherent signals of the spacecraft, meanwhile, the requirement for high-precision speed differential information is avoided, high precision and online real-time performance of inertia estimation are taken into consideration, on-orbit inertia dynamic changes can be effectively tracked, and attitude control stability is guaranteed.

An apparatus includes: a memory configured to store: a first dataset including kinematics data representing multiple human-guided movements of a robot; a second dataset including linguistic descriptors of multiple human-guided movements of the robot; and a processor configured to generate a third dataset based on the first and second datasets, wherein the third dataset includes multiple motion primitives of the robot.

This invention discloses a dual-channel event-triggered unmanned surface vessel (USV) control method with minimum time interval, belonging to the field of USV control technology. To address the communication redundancy problem between USVs and between the controller and actuators, this invention establishes the assumptions of a dual-channel event-triggered USV control method with minimum time interval. Each USV is divided into follower and leader, and the motion dynamics equations for each USV are established. A weighted graph is constructed for the communication topology between USVs. Then, based on the definition of convex hull and the Laplace matrix, an event-triggered position observer with minimum time interval constraints is designed for each USV. An event-triggered tracking controller with minimum time interval is designed for the follower. This invention can significantly reduce the overall system requirement for expensive sensors and reduce the design and implementation costs of multi-USV systems.

Aspects of the subject technology obtain sensor data from microphone and or movement sensors disposed in a device on each side of a user's body. The sensor data is used to provide running dynamics estimations including estimations involving differences between movement characteristics of the user's right side of the body versus the user's left side of the body. The estimations can further be used to provide feedback to the user regarding running style, running routes, and injury information.

The invention discloses a 360-degree video saliency prediction method and system based on spherical surface time-space-frequency domain feature fusion. According to the method, an improved spherical ConvLSTM (Long Short-Term Memory) network is combined with a multi-scale feature fusion mechanism, and combined modeling is carried out on the space structure, the motion dynamic state and the frequency domain energy distribution of a video. Through a multi-stage encoder-decoder structure, accurate capture of motion rhythm and structure change in a dynamic scene is realized, and a saliency map conforming to a human vision law is generated. The system shows better prediction precision and global consistency than a mainstream model in various 360-degree video scenes, and can be applied to the fields of virtual reality video transmission, view field prediction, content adaptive coding and the like.

This invention discloses a dynamic obstacle avoidance and intelligent game-playing method for spacecraft swarms, comprising: S1: establishing a coordinate system with a virtual spacecraft operating in a circular orbit as the reference spacecraft; S2: performing relative motion dynamics modeling on the spacecraft swarm and the target in the coordinate system to obtain a relative motion dynamics model describing the virtual spacecraft and the spacecraft swarm; S3: acquiring the coordinate data of each sub-spacecraft in the spacecraft swarm in the coordinate system; S4: determining the distance between each sub-spacecraft and the obstacle based on the motion dynamics model and the coordinate data; S5: determining whether there is a distance greater than a preset threshold; if so, proceed to S6; otherwise, proceed to S7; S6: driving the spacecraft swarm to achieve an encirclement state based on the gravitational relationship between each sub-spacecraft and the target and the repulsive relationship between each sub-spacecraft and the obstacle determined by the artificial potential field method; S7: using an intelligent encirclement strategy to encircle the target obstacle.

This application discloses a method, apparatus, device, medium, and product for determining three-channel events based on motion dynamic characteristics, relating to the field of data processing. The method includes: acquiring an event sequence; the event sequence is determined by multiple event information; each event information includes pixel position, timestamp of the event occurrence, and brightness change polarity information; encoding the event sequence to obtain a three-channel event; the three-channel event includes a three-channel structured feature map; the three-channel event is used for visual motion recognition; wherein the three-channel structured feature map includes: a first channel for dynamic rhythm encoding, a second channel for motion stability encoding, and a third channel for brightness change direction encoding. This application can improve the recognition accuracy of motion dynamic characteristics and enhance its versatility and robustness.

The invention discloses a weak supervision group behavior recognition method and system based on a double-branch space-time motion fusion network, and the method comprises the following steps: collecting a plurality of videos containing group behaviors, carrying out the preprocessing of the videos, obtaining a plurality of continuous video frame sequences, and constructing a training data set through the plurality of continuous video frame sequences; constructing a double-branch space-time motion fusion network which comprises a global motion dynamic module, a backbone network, a space-time fusion module and a prediction head; training the double-branch space-time motion fusion network by using the training data set, constructing a total loss function, and adjusting the double-branch space-time motion fusion network according to the total loss function to obtain a trained double-branch space-time motion fusion network; and deploying the trained double-branch space-time motion fusion network to an equipment end. According to the method, the problem of processing camera motion interference in a complex scene in group behavior recognition is solved, and the group behavior recognition precision and recognition efficiency are high.

This invention relates to a nonlinear time-domain aircraft ground motion stability analysis method, comprising the following steps: acquiring scene information data and aircraft parameters; performing force analysis on the aircraft based on the scene information data and aircraft parameters to construct a set of aircraft ground motion dynamic equations; simulating the aircraft ground motion dynamic equations, inputting aircraft taxiing speed and nose wheel steering angle parameters to obtain a time-domain plot of the aircraft's turning angular velocity, thereby obtaining the stability of the aircraft's ground motion. Compared with existing technologies, this invention employs a nonlinear time-domain analysis method based on independent tire forces, which has advantages such as high accuracy and high safety.

The application provides a train parameter uncertain anti-saturation adaptive neural network control method and system, and belongs to the technical field of train control. The technical scheme is: a train longitudinal motion dynamics model is established, mass uncertainty, resistance parameter uncertainty, additional resistance and unmodeled dynamics are taken as compound unknown dynamics; an actuator saturation constraint model and a saturation deviation auxiliary system are constructed to form a comprehensive error; an RBF neural network is used to online approximate the compound unknown dynamics, and an adaptive law with a leakage term correction and an adaptive anti-saturation control law are used to output actual control input. The beneficial effect is that the train displacement and speed tracking precision can be improved under the conditions of actuator saturation and parameter uncertainty, parameter drift can be inhibited, and the stability of closed-loop control can be enhanced.

The invention provides a video behavior identification method and system based on multilayer global-local collaborative features, and belongs to the field of computer vision. The method comprises the following steps: acquiring video data and performing frame sampling to obtain a video frame sequence; inputting each frame of image in the video frame sequence into a frozen CLIP visual encoder to obtain a frame-level multi-level feature set; inputting the multi-level feature embedding sequence into a global-local feature collaboration module, performing global semantic modeling and local motion dynamic enhancement on features of each layer, and outputting collaboration feature representation corresponding to each layer; and inputting the collaborative feature representation of each layer into a cross-layer Transform decoder, performing layer-by-layer interactive fusion through a video-level query mark to generate a final video feature representation, and outputting a prediction result of a video behavior by using a full-connection layer. According to the method, the problems of insufficient time sequence modeling and neglect of local motion when the method is directly applied to the video are effectively solved.