67 results about "Motion direction" patented technology

The invention relates to a pure vision autonomous navigation method for a mobile robot based on ground structure line guidance. The method comprises the following steps: binocular-inertia joint perception and state estimation; carrying out ground area constraint and two-dimensional line segment extraction; performing line segment screening and geometric fitting based on motion direction constraint; carrying out three-dimensional parametric modeling and category discrimination on multiple types of ground structure lines; calculating a pose error of a relative structure line and constructing a reference trajectory; performing closed-loop motion control based on the Lapunov stability; carrying out key position judgment and motion decision making based on an image template; compared with the prior art, by introducing a visual guidance mechanism based on a ground structure line and fully utilizing natural ground structure characteristics such as a space structure boundary line, stable autonomous navigation of the mobile robot is realized without depending on artificial markers such as a high-precision map, GNSS (Global Navigation Satellite System) positioning, a two-dimensional code and a magnetic stripe; the dependence of the system on complex sensors and environment modification is effectively reduced, and the deployment and maintenance cost is remarkably reduced; meanwhile, through unified modeling of multi-type structural line features, the adaptive capacity and robustness of the navigation method in various application scenes such as warehouse logistics, park inspection, in-plant transportation and semi-structured roads are improved, high navigation stability and reliability can be kept in tasks such as fixed route inspection, lane keeping and back-and-forth running, and the navigation method is suitable for large-scale popularization and application. And the method has good engineering practical value and popularization and application prospects.

The invention discloses a salamander-imitating robot omni-directional motion control method and system based on reinforcement learning, and belongs to the field of electromechanical system control. The method comprises the following steps: acquiring robot state information and a motion instruction; a periodic phase variable is generated through a phase integration module, and target actions of all joints are output through a track generator; designing a reward function based on behavior constraint, and constraining motion directivity and attitude stability; the morphological symmetry of the body structure of the salamander-imitating robot is utilized to symmetrically enhance the state-action sample so as to expand training data; and a reinforcement learning algorithm is adopted, and a stable and efficient omnidirectional motion control model is obtained according to a reward feedback and symmetric enhancement data iteration updating control strategy. The method can realize the generation of the omni-directional motion strategy driven by reinforcement learning without presetting a gait model, has the advantages of natural motion mode, high control precision and strong adaptability, and can be widely applied to the fields of complex terrain detection, intelligent inspection and the like.

The invention discloses an object tracking method and device and electronic equipment, and relates to the technical field of vehicles and the technical field of automatic driving. The method comprises the following steps: acquiring historical state data, a current prediction state and to-be-matched data corresponding to a scene object; based on the historical state data, the current prediction state and the to-be-matched data, determining the motion direction similarity between the tracking frame and the candidate frame; calculating a region overlapping degree between the tracking frame and the candidate frame by using the current prediction state and the to-be-matched data; performing matching analysis on the tracking frame and the candidate frame according to the motion direction similarity and the region overlapping degree to obtain a matching result; and determining the candidate frame as the tracking frame matched with the scene object at the current moment in response to the fact that the matching result indicates that the tracking frame is successfully matched with the candidate frame. According to the invention, the technical problems of easy mismatching and low tracking accuracy of an object tracking method in the prior art are solved.

A display method and an electronic device, which are applicable to the technical field of display, and can reduce the risk of motion sickness caused by the inconsistency between motion information seen by eyes and motion information perceived by other organs of the body. The electronic device moves along with the movement of a vehicle. The method comprises: determining a motion state of a vehicle, wherein the motion state indicates a motion direction and / or a motion speed of the vehicle, and the motion direction comprises a horizontal direction and a vertical direction; and then displaying, in a preset area in a display interface of an electronic device, a dynamic effect corresponding to the motion state. A dynamic effect corresponding to a motion state of a vehicle is displayed in a preset area in a display interface of an electronic device, and the motion state of the vehicle is simulated, so that motion information seen by eyes of a user is consistent with motion information perceived by other organs of the body.

The invention provides a course rapid initial alignment method and device for vehicle-mounted integrated navigation, and relates to the technical field of navigation calibration, and the method comprises the following steps: based on three-axis acceleration data, eliminating a component of gravitational acceleration in a horizontal direction through attitude compensation, and obtaining a horizontal longitudinal acceleration measurement value; carrying out plane coordinate projection based on the GNSS positioning data to obtain a track point sequence; determining the horizontal displacement length of the current track point and other track points in the track point sequence; on the basis of the horizontal longitudinal acceleration measurement value and the track point sequence, the motion direction is judged through the speed change trend and the horizontal acceleration direction, the current track angle is corrected, and a corrected course angle is obtained; and based on the corrected course angle and the Z-axis angular velocity of the gyroscope measured by the IMU module, estimating the course angle error and the zero offset of the gyroscope by adopting an adaptive Kalman filtering algorithm, and outputting the corrected course angle. According to the invention, fast and accurate course initialization of combined navigation in a low-speed equipment operation scene can be realized.

The application provides a crane group boom anti-collision early warning method and system based on digital twinning, which comprises the following steps: based on the data collected by a rotary encoder, an angle sensor, an inertial measurement unit, a laser radar and a ship body attitude measuring device, a dynamic three-dimensional digital twinning model is constructed and updated in real time; in the model, real-time path planning is performed on each crane boom, the spatial interference risk with the bulkhead, hatch coaming and other booms is evaluated, and a collision-free optimal action path is generated; the path nodes are dynamically risk evaluated, the minimum distance, relative speed, motion direction angle and ship body swing disturbance are comprehensively considered, and a collision risk score is generated; according to the score, hierarchical intervention control is implemented, the collision is avoided, and the attitude stability of the suspended goods is maintained. The application realizes the safety early warning and intelligent regulation and control of multi-machine cooperative operation under high dynamic sea conditions, and effectively improves the operation efficiency and safety.

The invention discloses a task-aware robot availability prediction method based on retrieval enhancement and cross-image alignment. The method comprises the following steps: constructing an accessibility memory bank containing object appearance characterization and interaction prior; performing semantic filtering on the memory bank based on the task tag, and retrieving a reference sample according to appearance similarity; a prediction process is divided into two parts, namely static contact point positioning and dynamic action direction prediction, contact points are correspondingly positioned by querying dense features of an image and a reference sample, and an action direction is regressed by a retrieval-enhanced cross-image alignment model; the model performs action vector modulation on the reference features, and performs gating cross-attention fusion with the query image features, and the fusion weight is jointly determined by the similarity and the learnable weight; and finally, the two-dimensional contact point and the action direction are lifted into a three-dimensional pose and a three-dimensional trajectory, and executable grabbing and post-contact actions are generated. According to the method, cross-category robust generalization under the condition of few samples can be realized, and the operation success rate of the robot is improved.

A method, a device (800), a medium for controlling the movement of a virtual body (107), including: a target determining step, in the first frame, based on the moving direction and position of the virtual body (107), selecting a virtual object (103) in a predetermined area as a virtual target (202); a dynamic adjusting step, calculating a horizontal moving direction (302a) of the virtual body (107), a direction of a connecting line between a vertical projection (107′a) of the virtual body (107) on the horizontal plane and a vertical projection of the virtual target on the horizontal plane, and an included angle (θ1) between the horizontal moving direction (302a) of the virtual body (107) and the direction of the connecting line in each frame, and controlling the horizontal moving direction (302a) of the virtual body (107) based on the included angle (θ1) (204).

To provide a working device capable of controlling the position of a moving body while accurately detecting the moving amount of the moving body in the moving direction with an inexpensive constitution.SOLUTION: Height detector 45 of component placing device 1 including rising and falling body 41 and height detector 45 that detects the height of rising and falling body 41 includes mark member 52 that rises and falls together with rising and falling body 41 and includes the plurality of slits 60 disposed along the rising and falling direction, and two mark detectors 53 that detect the presence or absence of slit 60 at each of two detection positions (first detection position KP1 and second detection position KP2) set in movement path R of the plurality of slits 60 that rise and fall according to the movement of mark member 52. Counter 16c counts the number of changes in the combination of the presence or absence of slits 60 detected by each of two mark detectors 53 and height calculator 16d calculates the height of lift 41 based on the counted number of changes in the combination of the presence or absence of slits 60.SELECTED DRAWING: Figure 7

Embodiments of the present application disclose a collision behavior prediction method and device, electronic equipment and medium. The method comprises: predicting the movement direction and trajectory of a target according to the movement correlation information of the target; wherein the target comprises a first target and a second target; determining the blind area of the target at a prediction time according to the movement direction and trajectory of the target; wherein the prediction time is any time after the current time; determining a collision behavior prediction result according to the positional relationship between the blind area of the first target and the blind area of the second target at the prediction time, and the positional relationship between the blind area of the second target and the blind area of the first target at the prediction time; wherein the blind area of the first target is the blind area corresponding to the first target, and the blind area of the second target is the blind area corresponding to the second target. Through the above technical solution, the collision behavior of the second target and the first target can be accurately predicted, and the timeliness and accuracy of the collision behavior prediction are improved.

The invention relates to a driver control method and device and computer equipment. The method is applied to an ultrasonic endoscope, the ultrasonic endoscope comprises a driver, and the method comprises the steps that motion parameters of the driver are obtained; under the condition that the motion parameters meet preset conditions, the motion direction of the driver is controlled to be switched from the first motion direction to the second motion direction; the first movement direction is opposite to the second movement direction. By adopting the method, the phenomenon that the shape of the bourdon tube connected with the driver does not conform to the expectation due to the fact that the driver always moves in the fixed direction can be avoided, so that the image distortion phenomenon caused by the phenomenon that the shape of the bourdon tube does not conform to the expectation can be avoided, and the imaging quality of the ultrasonic endoscope is remarkably improved.

The invention discloses a ship automatic driving method capable of automatically avoiding obstacles, which comprises the following steps of: partitioning images shot in four directions of a ship in the driving process of the ship, capturing the contours of all constituent elements, and analyzing the change condition and the movement direction of each contour in adjacent time intervals; the ship automatically sails through a set coping method based on each condition, collision avoidance and automatic driving are carried out on obstacles through a method of combining vision with radar detection, the judgment on the obstacles is more accurate, and the detection distance is farther.

This application discloses a sensor-based intelligent prediction method, device, and medium for accompanying robots, belonging to the technical field of accompanying robots. The method includes: collecting user behavior, visual, and environmental data; filtering and standardizing the data using a Kalman filter algorithm to generate standard data; processing the standard data using an action recognition algorithm to determine user behavior; constructing a digital model based on standard environmental data, and combining this model with a preset target and reward function to select a navigation path; predicting the user's next position and direction of movement based on historical environmental data and a parallel interactive multi-model Kalman filter algorithm; and calculating the accompanying robot's motion commands based on the navigation strategy and user prediction information. This application effectively integrates data from multiple sensors, improves the accuracy of user behavior recognition, and enables the development of flexible and efficient navigation strategies.

The application discloses a multi-person redirection walking and position prediction method based on an artificial potential field, and belongs to the technical field of virtual reality and robot navigation. In view of the problems of fixed repulsion force weight, high collision risk, frequent resetting and short-term position prediction accuracy deficiency leading to collision in the traditional redirection walking algorithm in a multi-user dynamic scene, a dynamic potential field weight optimization mechanism is used to adjust the weight distribution of repulsion force between the environment and the user in real time according to the user density, to enhance the repulsion force intensity when the user approaches an obstacle or a dense area, and to introduce a safety distance and a direction perception mechanism, to analyze the user motion direction and the obstacle angle, to preferentially guide the deviation from a high-risk area, and to reduce the number of invalid resets. A prediction model adopts an encoder-decoder architecture, and a multi-layer long short-term memory network is embedded with an attention mechanism to dynamically capture key timing features in the space-time trajectory, and to improve the short-term position prediction accuracy.

This invention discloses a speed-controlled inertial force cancellation system and its cancellation method, comprising a worktable mounted on a frame, a worktable drive unit, a movable compensation unit, and a control unit. The worktable drive unit drives the worktable to accelerate and decelerate along a preset trajectory. The movable compensation unit is a moving body independent of the worktable drive unit, with a constant mass, and moves in the opposite direction to the worktable's motion direction under the control of the control unit. The control unit calculates the velocity and acceleration of the movable compensation unit based on the worktable's mass, real-time velocity and acceleration, and the movable compensation unit's mass, and calculates the movable compensation unit's velocity and acceleration based on the law of conservation of momentum, thereby driving the movable compensation unit to generate a compensation force equal in magnitude and opposite in direction to the worktable's inertial force, thus suppressing vibration transmitted to the frame. This invention can effectively cancel the worktable's inertial force without increasing the mechanism's or the overall weight, thus suppressing frame vibration.

The application discloses a path planning method, a path planning device, a self-moving device and a computer storage medium. The method is applied to the self-moving device, the self-moving device comprises a first front wheel and a second front wheel, the first front wheel and the second front wheel are arranged in a non-parallel manner, and the method comprises the following steps: when it is detected that the self-moving device is located on a slope, the direction of the slope is determined according to the current posture of the self-moving device; the first angle between the direction of the slope and the first front wheel and the second angle between the direction of the slope and the second front wheel are determined; the target motion direction of the self-moving device is determined according to the first angle and the second angle; the slope moving path is planned according to the target motion direction, and the self-moving device is controlled to move along the slope moving path. The method can improve the climbing ability of the self-moving device, and further improve the operation coverage and operation effect.

The invention discloses a two-dimensional correction method for a photoelectric coding disc of a translation rotating platform. The invention relates to the technical field of engineering measurement, and aims to solve the problem that errors generated by a photoelectric coding disc of a translation rotating platform in the vertical direction cannot be compensated in the prior art. According to the invention, coding array images and precision measurement light spot images on the photoelectric coding disc are acquired through the camera. And identifying a coarse precision absolute position according to the coding array image. And the light spot gravity center is extracted based on the light spot image, and the column pixel variation in the movement direction is calculated to obtain accurate displacement or angle. The line pixel variation in the vertical movement direction is calculated, and the axial movement and pitching error amount is determined. And the positioning result is compensated and corrected by using the error amount. According to the invention, not only can position displacement or angle be accurately measured in the movement direction, but also normal position movement and pitching bounce values of a translation or rotation plane can be accurately measured, so that positioning errors caused by the displacement or angle can be compensated.

The invention relates to an object motion detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a model corresponding to a scene where an object is located, and enabling the model to have a collision grid; acquiring a blocking direction corresponding to the collision grid of the model, wherein the blocking direction is used for indicating a motion direction when the object is blocked by the corresponding collision grid in a motion state; voxelization processing is carried out on the collision grid based on the blocking direction corresponding to the collision grid to obtain voxel data corresponding to the scene, each voxel in the voxel data carries a type identifier, and the type identifier is determined based on the blocking direction of the collision grid corresponding to the voxel; acquiring a motion route of the object in the scene; based on the voxel data and the motion route, the motion process of the object in the scene is detected, a detection result is obtained, and the detection result is used for indicating whether the object is blocked or not in the process of moving along the motion route. The application scene of motion detection of the object is expanded.

The embodiment of the invention discloses a camera movement detection method and device, computer equipment and a storage medium, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining continuous image frames collected by a camera; dividing a shooting view field of the image frame into a plurality of areas; selecting feature points in the region; on the basis of the continuous image frames, motion features of the feature points are determined, and the motion features comprise motion amplitudes and motion directions; and judging whether the camera moves or not based on the motion features of the feature points. The shooting view field is divided into a plurality of areas and the feature points are selected in each area, so that the comprehensive coverage of the detection range is realized, and a monitoring blind area is avoided. According to the invention, high-accuracy and high-reliability identification of the moving state of the camera is realized.

The application relates to a numerical control machine tool motion shaft cutting force error dynamic measurement method and device, and belongs to the technical field of machine tool error measurement, wherein the method comprises the following steps: constructing a machine tool three-dimensional coordinate system, determining the machine tool feeding shaft motion direction and the machine tool feeding shaft stress direction under the machine tool three-dimensional coordinate system according to a machine tool machining experiment; acquiring real-time error data and real-time cutting force data according to the machine tool feeding shaft motion direction and the machine tool feeding shaft stress direction; determining the machine tool motion shaft dynamic geometric error influence type caused by the cutting force according to the difference relationship between the real-time error data and the error data when the machine tool is in the idle state, combining the cutting force direction and the numerical value; compensating the geometric error type according to the real-time cutting force data, and determining the machine tool motion shaft dynamic error. The application solves the technical problem that real-time dynamic error measurement cannot be carried out in the actual machining state in the prior art, so that the geometric error compensation value caused by the machine tool cutting force cannot be accurately acquired.

The application discloses an augmented reality environment-based auxiliary assembly human factor ergonomics evaluation method and system based on hand trajectory, converts three-dimensional coordinates of hand joints collected from an operator into a coordinate system with the head of the operator as an origin to obtain hand centroid coordinates, divides the hand movement trajectory into a plurality of discrete action segments based on the motion speed and the motion direction change of the hand centroid at each time; for each action segment, hand movement characteristic indexes are calculated, including an eye-hand unit vector, an actual extension distance, a motion amplitude and smoothness; based on the hand movement characteristic indexes, the operation visibility, the reachability and the posture load score of each action segment of the operator and the overall posture load of the task are comprehensively calculated to perform real-time human factor ergonomics quantitative evaluation. The application can provide technical support for real-time objective quantitative evaluation of human factor ergonomics of assembly operation, action characteristic analysis and process flow optimization.

The invention provides a motion control method and device, computing equipment, a storage medium and a program product, current motion data of a virtual character is acquired, the current motion data comprises a current path, a current motion speed and a current orientation of the virtual character, and the current motion speed and the current orientation of the virtual character are calculated according to the motion step length of the current path. The motion speed and the motion direction of the virtual character are gradually adjusted in a mode of determining the corresponding target acceleration and the motion tangent vector for the virtual character, and the target acceleration and the motion tangent vector are determined based on the motion step length in the motion process, so that the speed and the motion direction are adjusted by taking the motion step length as a unit; the motion state of the virtual character can be smoothly changed, so that the control of the motion of the virtual character on the path is no longer the reset of speed and direction or the rigid adjustment of directly modifying parameters, and the motion process of the virtual character on the path better conforms to the real physical law; and the user can obtain more real experience when controlling the virtual character to move on the path.

The invention provides a positioning data processing method, system and device based on an intelligent rope belt adjusting device, relates to the technical field of high-precision positioning, and particularly relates to a rope belt data management platform which preprocesses received positioning data, stores effective information and carries out trajectory prediction according to the received data when communication is interrupted, so that the positioning data can be accurately positioned. The positioning fault problem caused by data missing is effectively avoided, the continuity of the motion track is guaranteed, deviation is monitored and predicted in real time by means of the speed-motion direction coupling anomaly, track anomaly can be accurately recognized even if noise interference exists, an optimization mechanism is triggered in time to prevent error accumulation, and the accuracy of the motion track is improved. The method comprises the following steps of: receiving off-line positioning data stored by an intelligent rope belt adjusting device in an interruption period, comparing and analyzing the actually measured data and the predicted trajectory after communication is recovered, realizing dynamic iteration of a prediction algorithm, and finally maintaining high reliability and accuracy of the positioning data in a complex abnormal scene.

This invention discloses a prediction residual-driven multi-target tracking method, belonging to the field of computer vision technology. First, target detection is performed on the current frame. Based on the updated model transition matrix and model probabilities from the previous frame, multiple motion models are used to predict existing target trajectories in parallel within a unified state space, and the prediction results are weighted and fused to obtain the target prediction state. Motion constraints are constructed using the motion uncertainty index from the previous frame, and together with geometric overlap and motion direction consistency, they form an association cost, realizing data association between the trajectory prediction state and the detection boxes. Kalman filtering is performed on the successfully associated detection boxes to update the data, and the prediction residual is calculated. Based on the prediction residual, the model transition matrix is ​​adaptively adjusted, and an equivalent prediction residual is constructed to quantify the target motion uncertainty index for data association in subsequent frames. This method improves the robustness and stability of multi-target tracking in complex scenes without relying on appearance features.

The invention relates to the technical field of mine safety, and discloses a mine underground personnel positioning method based on artificial intelligence, and the method comprises the steps: 1, constructing a tunnel grid unit model according to the three-dimensional structure and slope information of an underground tunnel; collecting dynamic data of the personnel and the vehicle in real time, wherein the dynamic data comprises position coordinates, movement speed and movement direction; 2, predicting the future movement trend of the person and the vehicle according to the collected movement speed and movement direction; and on the basis of the roadway grid unit model and the movement trend, the predicted remaining time required for the person and the vehicle or the vehicle and the workshop to enter the same grid unit for the first time is calculated in real time. The prediction remaining time calculation based on the motion trend is adopted, the human-vehicle collision risk is pre-judged in advance, effective early warning is given out in time, and the defects that in the prior art, the real-time fusion analysis capability is lacked, and the high-frequency meeting collision risk cannot be pre-judged are overcome.

The application discloses a potential dangerous target detection method and device, which are used for accurately and quickly detecting a potential dangerous target and guaranteeing automobile driving safety. The method comprises the following steps: acquiring at least two continuous images, the at least two continuous images being obtained by image acquisition on scenes on both sides of the automobile; determining an ROI region in a first image and determining motion information of each feature point included in the ROI region, the motion information of each feature point comprising a motion direction of the feature point; the first image being any one of the at least two images; clustering each feature point included in the ROI region according to the motion information of each feature point, so as to obtain at least one target located in the ROI region; determining a motion direction of each target according to the motion direction of at least one feature point included in each target; and determining a target with the same motion direction as the driving direction of the automobile in the at least one target as a potential dangerous target.

The application discloses a control instruction driven motion pair implementation method for virtual simulation of an equipment digital twin system, supports a control instruction driven motion mode of mapping twin data collected from an actual device, and is characterized in that the instruction driven motion pair has two aspects of definition, one is a simulation motion implementation aspect, including a relative motion trajectory and a motion direction of the motion pair, and the other is a data driving aspect, including data corresponding to driving instructions and parameters of an actual equipment. The application provides a quick and accurate determination method for supporting collected data to implement an equipment digital twin system, the method normatively expresses motion pair information required by virtual simulation of the equipment, and can one-to-one correspond to collected instruction data, so as to form a normative definition method of an equipment simulation system.

An active and passive information association method based on a target motion direction and an amplitude change rate. For a sensing system using a radar device and an electronic reconnaissance device for joint detection, a target motion direction is determined by means of radar track information, a received signal amplitude change rate is provided by means of electronic reconnaissance data, and the relationship between the target motion direction and the signal amplitude change rate is associated, thereby achieving association between radar detection data and electronic reconnaissance data.

The embodiment of the invention is suitable for the technical field of display, provides a display method and electronic equipment, and can reduce the risk of motion sickness caused by different motion information seen by eyes and motion information perceived by other organs of a body. Comprising the steps that the motion state of a vehicle is determined, the motion state indicates the motion direction and / or the motion speed of the vehicle, the motion direction comprises the horizontal direction and the vertical direction, and then a dynamic effect corresponding to the motion state is displayed in a preset area in a display interface of the electronic equipment. The dynamic effect corresponding to the motion state of the vehicle is displayed in the preset area in the display interface of the electronic equipment, and the motion state of the vehicle is simulated, so that the motion information seen by the eyes of a user can accord with the motion information perceived by other organs of the body.

This invention relates to the fields of vibration control and nonlinear mechanics, and provides a programmable method for generating two-dimensional nonlinear forces. The method includes: responding to a two-dimensional nonlinear force generation request; acquiring the structure and structural parameters of a mechanical realization device; determining the trajectory of the center point of a rolling component during motion based on mechanical equilibrium relationships, and acquiring the geometric expression of the rolling component's trajectory surface; and, based on the geometric dimensions of the rolling component, performing equidistant mapping along the normal direction on the rolling component's trajectory surface, causing the rolling component to adhere to and roll along a three-dimensional guide surface, thereby generating a nonlinear force corresponding to a target nonlinear force function. This method not only generates nonlinear forces of arbitrary continuous form based on a preset target force function and supports personalized customization of nonlinear stiffness characteristics, but also generates nonlinear forces that meet target requirements in two mutually orthogonal motion directions.