87 results about "Movement pattern" patented technology

The invention discloses an intelligent artificial limb movement intention recognition method based on multi-modal information and a D-S evidence theory, and belongs to the technical field of artificial intelligence, mode recognition and intelligent artificial limb control. According to the method, firstly, electromyographic signals and kinematics signals of user limbs and three-dimensional point cloud information of the terrain where the user limbs are located are synchronously collected; filtering, segmenting and time domain / frequency domain feature extraction are carried out on the physiological signals, rotation correction and dimension reduction are carried out on the environment point cloud, and a binary image is generated; using a deep learning model to identify a preliminary motion mode from the physiological features and identify a terrain category from the environment image; and finally, inputting the two recognition results as evidence bodies into an improved D-S evidence theory model for decision-level fusion, and outputting a final comprehensive motion intention recognition result. According to the method, the human physiological signal and the external environment information are fused, so that the ambiguity and uncertainty of single information source identification are effectively solved, and the intention identification accuracy and adaptability of the intelligent artificial limb in different complex scenes are remarkably improved.

Systems and methods for providing assessments of a disease using sensor data for a subject captured during day-to-day living are provided. The sensor data includes accelerometer data and is acquired by a sensor disposed on the subject's wrist while the subject performs both active and sedentary activities. The sensor data is analyzed for one or more bouts of activity; the sensor data is filtered, optionally rotated, and Fourier transformed. Spectral analysis parameters are then calculated from the transformed data to detect disease-relevant movement patterns. Movement distribution parameters for the accelerometer data associated with the disease-relevant movement patterns are calculated and compared to one or more disease scores to evaluate a progression of the disease or an efficacy of a treatment

The invention provides a virtual reality-based joint movement injury rehabilitation mode generation method and a virtual reality-based joint movement injury rehabilitation mode generation system, and relates to the technical field of virtual reality, and the method comprises the following steps: analyzing a rehabilitation path according to movement joint injury data of a user; performing rehabilitation limb posture decomposition based on the rehabilitation analysis path to generate a rehabilitation analysis view; a multi-modal sensor unit is used for collecting rehabilitation feedback actions of a user, and matching recognition of physiological parameters and rehabilitation constraints is carried out in a rehabilitation analysis view; and according to the posture deviation feedback, performing amplitude and muscle power guidance feedback of the rehabilitation limb posture, and synchronously performing virtual reality visual display. The technical problem that in the prior art, most VR rehabilitation systems mainly pay attention to visual feedback, so that only the motion appearance can be evaluated, and the compensatory motion mode cannot be recognized is solved, real-time monitoring and guidance on the force exerting correctness are achieved through combination of posture decomposition and physiological parameter projection, and the effect that the correctness of force exerting is improved is achieved. Therefore, the compensatory motion mode is effectively blocked.

Disclosed embodiments provide bot detection in a virtual environment that is based on avatar motion. The motion of an avatar within a virtual environment such as a metaverse is tracked. The tracked motion is separated into multiple movement segments. The movement segments are compared to a collection of movement patterns in a movement pattern database that are indicative of bots. A similarity metric is determined between the tracked motion and the database of bot motions. In response to the similarity metric exceeding a predetermined threshold, a list of at least one mitigation action is obtained, and the at least one mitigation action in the list is executed, thereby mitigating the adverse effects of bots in a virtual digital environment.

Device (12) for detecting a vegetation object (14) in the environment (16) of a vehicle (18), comprising: an input interface (26) for receiving sensor data from a radar sensor (20) with information about the vehicle's environment, wherein the sensor data includes scan points (32) with associated point velocities; a processing unit (28) for identifying an object in the vicinity of the vehicle based on a clustering of scan points according to the point velocities of the scan points; and an evaluation unit (30) for classifying the object based on an evaluation of the point velocities of the scan points assigned to the object, in order to distinguish between a vegetation object (14) and a living object (22), wherein the evaluation unit (30) is designed to calculate a frequency spectrum of the point velocities of the scan points assigned to the object (32) and to classify the object as a vegetation object (14) if the frequency spectrum does not include pronounced high points; to distinguish between a person, encompassing a pedestrian or a cyclist, and an animal based on the point velocities of the scan points (32) assigned to the object, if the object has been classified as a living object (22); and is trained to recognize typical movement patterns based on a comparison with predefined pattern data; and is trained to recognize a living object (22) that is in front of or behind a vegetation object (14).

In order to improve throughput in an environment where a plurality of moving bodies are operating, the present invention comprises: group setting units (102a, 102b) that set groups of a plurality of moving bodies M on the basis of positions and destinations of the moving bodies M; and movement rule setting units (103a, 103b) that set, for the moving bodies M belonging to a group set by the group setting units (102a, 102b), a movement rule (113) shared by the moving bodies M belonging to the group. The movement rule setting units (103a, 103b) set the movement rule (113) so that the moving bodies M belonging to the group move in the shared movement pattern.

A method and system for providing distance information from a sensor assembly to a flying target. The method comprises detecting the flying target and locking on the flying target by means of a tracking sensor. Directing a light beam at the detected flying target. Generating a movement pattern having a path around the detected flying target and controlling movements of the light beam so that the LOS of the light beam completes moving across the path of the selected movement pattern within a set timeframe. Generating distance information by measuring time- of-flight of the light beam, when being reflected from the flying target while moving the LOS of the light beam across the path of the movement pattern. The system comprises sensors and devices for performing the method.

A roll manufacturing apparatus includes a rotary device including a rotary encoder, a cutting tool stage that holds a spindle unit, which includes a rotatable cutting blade, reciprocatably in a radial direction of a roll and is movable in the radial direction of the roll, a signal generator that generates, based on signals output from the rotary encoder, a control waveform indicating a movement pattern to reciprocate the cutting blade at positions corresponding to predetermined cutting portions, and a controller that moves the cutting tool stage so that a cutting process of reciprocating the cutting blade in the radial direction of the roll while rotating the cutting blade, according to the control waveform, to perform cutting once or multiple times with the cutting blade at a predetermined cutting depth is performed multiple times.

This invention belongs to the technical field of rehabilitation robots, specifically relating to a continuous phase control method for a lower limb rehabilitation exoskeleton that adapts to user gait. It employs a multi-task learning model, simultaneously outputting user identity probability and movement pattern probability to generate a probability map representing the similarity between the current gait and a certain movement pattern of a sample user in a sample database. A gait phase variable parameter prediction model is used to predict gait phase variable parameters, employing angular velocity data from the initial stage of the current gait cycle and the matched movement pattern to predict the gait phase variable parameters for the current cycle. Finally, a pre-constructed relational constraint model corresponding to the matched sample user and their movement pattern is used to obtain the desired joint angles from the real-time gait phase, and the exoskeleton is tracked and controlled via a PD controller. This invention can adaptively adjust the exoskeleton's motion assistance mode according to the user's gait characteristics, and is suitable for rehabilitation training of patients with lower limb motor dysfunction.

The present invention provides a system for monitoring and improving toothbrushing effectiveness. The system comprises a camera device comprising a camera or similar visual sensor configured to capture real-time footage of a user brushing their teeth an AI-powered software module is designed to analyse the footage using object recognition, pose estimation, and motion tracking algorithms to detect the user's hand, toothbrush, and face, a feedback device that comprises a feedback interface that provides real-time visual, auditory, or haptic feedback based on brushing technique, including parameters such as angle, coverage, and movement speed and movement patterns. Wherein the feedback provided comprises instructions to the user to alter their toothbrushing technique to bring the parameters closer to a predetermined set of ideal values. Thereby providing a system operates independently of sensors, accelerometers, or physical markers embedded in or attached to the toothbrush.

Provided is technology that makes it possible to easily maintain the communication quality of the portable terminal of a user having a specific attribute. A core network system executes the following: a step in which portable terminal information and base station information are acquired; a step in which a movement pattern of a portable terminal is determined; (a) a step in which a movement route of the portable terminal in a future scheduled period is inferred, (b) a step in which one or more base stations estimated to communicate with the mobile terminal on the movement path are determined, and (c) a step in which a base station parameter is calculated, the steps (a), (b), and (c) being executed using a machine learning model generated by learning the movement pattern of the portable terminal; a step in which a setting time for setting the base station parameter in the base stations is determined; and a step in which the base station parameter is set in the one or more base stations at the setting time.

This invention relates to the field of parallel robot technology, specifically to a three-degree-of-freedom (DOF) parallel robot with two translational and two rotational degrees of freedom. Existing parallel robots mostly focus on rotational motion, with insufficient support for translational motion, making it difficult to fully simulate the natural movement patterns of the ankle. To address these problems, this invention provides a three-DOF parallel robot with two translational and two rotational degrees of freedom. Its topology includes a static platform, a moving platform, and hybrid branches I and II connecting the static and moving platforms. This topology realizes the two rotational degrees of freedom (inversion / eversion, dorsiflexion / plantarflexion) and two translational degrees of freedom required by the ankle joint, perfectly matching the natural movement patterns of the ankle. Compared to traditional parallel robots that only focus on rotational motion, this invention can more comprehensively simulate the complex movements of the ankle, providing a movement trajectory closer to the actual physiological state for rehabilitation training, thereby improving rehabilitation outcomes.

The disclosure relates in general to a method and a system for identifying a vehicle via a system. The system comprises at least one sensor, a system control device coupled to the sensor and the vehicle having a vehicle control device. A vehicle having at least one component is detected. The component is movable, can be detected by the sensor and is coupled to the vehicle control device. The system control device is coupled to the vehicle control device. An identifier is forwarded by the system control device to the vehicle control device. A movement pattern is executed by the at least one component of the vehicle based on the identifier. A movement pattern executed by the component of the vehicle is detected by the sensor. The vehicle is identified by the system control device (16) based on the detected movement pattern.

This invention relates to the field of lower limb rehabilitation data recognition and monitoring technology, specifically disclosing a method for recognizing lower limb rehabilitation movement postures and an intelligent ankle bracelet for preventing VTE, comprising: Step 1, real-time acquisition of three-dimensional spatial motion data and recognition of lower limb motion data, extracting kinematic parameter features; Step 2, identification of movement types based on kinematic parameter features, acquisition of movement pattern consistency scores, and determination of whether rehabilitation training is qualified; Step 3, acquisition of surface electromyographic signals of the rehabilitation participant's leg-raising force exertion movement during rehabilitation training and simultaneous acquisition of lower limb motion data, extraction of force exertion data, evaluation and analysis to generate a muscle activation efficiency score; Step 4, establishment of a mapping model based on historical hemodynamic data, inputting the extracted force exertion data into the mapping model to output a VTE prevention efficiency score; Step 5, calculation of the movement pattern consistency score, muscle activation efficiency score, and VTE prevention efficiency score through movement evaluation analysis to generate a movement evaluation quality coefficient.

The disclosure generally relates to a method (32) and a system (10) for identifying a vehicle (12) by means of a system (10). The system (10) comprises at least one sensor (14), a system control device (16) coupled to the sensor (14), and the vehicle (12) with a vehicle control device (24). A vehicle (12) with at least one component (28) is detected. The component (28) is movable, detectable by the sensor (14), and coupled to the vehicle control device (24). The system control device (16) is coupled to the vehicle control device (24). An identifier is transmitted from the system control device (16) to the vehicle control device (24). A movement pattern is executed by the at least one component (28) of the vehicle (12) based on the identifier. A movement pattern executed by the component (28) of the vehicle (12) is detected by the sensor (14).The vehicle (12) is identified by the system control device (16) based on the detected movement pattern.

The invention relates to a method for issuing an input to a computer from a head-mounted device, the head-mounted device comprising a processing unit and a memory as well as at least one position and / or movement sensor, the head-mounted device being in communication with the computer, the method being implemented while the head-mounted device is worn on a wearer's head.The method comprises steps of:acquisition of position and / or movement data representative of the movement of the wearer's head by the position and / or movement sensor,detection of a specific movement pattern based on said position and / or movement data, the specific movement pattern being taken from a library of movement patterns,determination of a specific input associated with the specific movement pattern in the library, andissuance of the specific input to the computer.

A method executed by a robot, including: starting, from a starting position, a work session in which the robot maps a workspace, wherein a front of the robot faces towards a forward direction in a frame of reference of the robot; the robot traversing, from the starting position, to a first position, a first distance from the starting position in a backward direction in the frame of reference of the robot; after traversing the first distance, the robot rotating; after rotating, the robot traversing a coverage path of at least one area of the workspace, the coverage path including a boustrophedon movement pattern; and the robot cleaning the at least one area of the workspace with a cleaning tool of the robot while traversing the coverage path.

A system for early detection of movement instability includes a wearable device affixed to a body part of a subject, featuring at least one electromyography (EMG) sensor for detecting electrical muscle activity and at least one motion sensor for detecting movement. A computing device, communicatively connected to the wearable device, receives EMG data from the EMG sensor and motion data from the motion sensor. The computing device identifies movement instability patterns using a machine-learning model trained on datasets of known stable and unstable muscle activity data and movement patterns. It determines impairment indicators based on the identified movement instability patterns and generates a user interface displaying these indicators. This system facilitates early detection and monitoring of movement instability.

The invention relates to a method for identifying a vehicle (22) in a traffic area by means of a traffic monitoring system having a transmitter for a signal (20), a receiver for receiving a signal (28) reflected by an object, and a control unit, a reflector (24) for the signal (20) being arranged on the vehicle (22) moving in the traffic area, the reflector (24) being pivotable about at least one axis, the reflection characteristic of the signal (20) depends on the direction; the method has the following steps: moving the reflector (24) about the at least one axis in a movement pattern associated with the vehicle (22), the movement pattern generating a defined signal characteristic of the signal (28) reflected by the reflector (24); acquiring, with a receiver, the signal (28) reflected by the reflector (24); a vehicle (22) is identified if a signal characteristic of the signal (28) reflected by the reflector (24) received by the receiver corresponds to a signal characteristic associated with the motion pattern and stored in the traffic monitoring system.

Medical instrument arrangement (1) for minimally invasive examination and / or treatment of a subject (20), comprising - a robot (8) for moving and manipulating a medical instrument (2) which can be inserted into the subject (20) and has a proximal control section (3) for moving and manipulating, at the control section (3), - an operator acquisition device (6) for acquiring operator movement patterns of the operating section (3) of the medical instrument (2), generated manually, in particular directly at the operating section (3), and - a control device (7), wherein the control device (7) comprises: - a control unit (9) for controlling the robot (8) according to control commands to generate control movements of the operating section (3), - a situation detection unit (12) for determining an intervention situation to be assigned to the operator movement patterns to be detected, - a storage unit (11) for storing, in particular operator-related, recorded operator movement patterns with the associated intervention situation in a storage means (29) of the control device (7), and - a situation unit (17) for automatically selecting and / or generating a control movement pattern from stored operator movement patterns depending on an intervention situation determined by the situation detection unit (12) and for providing the control movement pattern as control commands for controlling the robot (8) by means of the control unit (9).

Some examples of the disclosure are directed to systems and methods for moving virtual objects in three-dimensional environments in accordance with detected movement of the electronic device. In some examples, the electronic device detects movement according to a first or second movement pattern described in more detail herein. In some examples, in response to detecting the first movement pattern, the electronic device applies a first correction factor to movement of a virtual object in the environment. In some examples, in response to detecting the first movement pattern, the electronic device applies a first correction factor to movement of a virtual object in the environment.

A method for lower limb movement recognition based on surface electromyography (EMG) decoding using S-transform energy concentration is proposed. First, the raw EMG signal is preprocessed. The preprocessed signal is then truncated to a useful time segment using endpoint detection. Next, the signal within this time segment undergoes segmented S-transform and energy concentration calculation. Segmented operations are used to extract signal features of a specified dimension. Movement pattern classification is performed using SVM, and multi-channel signal features are fused and analyzed for lower limb movement recognition. This invention performs segmented S-transform on the signal to preserve its temporal information, while optimizing the energy concentration calculation process to improve movement classification accuracy. An SVM multi-classifier is built, and the accuracy of lower limb movement pattern recognition is further improved through S-transform energy concentration and feature fusion.

A robot movement control method and system are disclosed. According to an embodiment of the present disclosure, the robot movement control method may include: calculating, based on a movement pattern of a worker, a score for each of picking stations corresponding to locations respectively accommodating a plurality of items to be picked by at least one robot; setting a priority for each of the picking stations based on the respective scores of the picking stations; and controlling the at least one robot based on the respective priorities of the picking stations.

In a digital analysis of chewing, based on feedback principles and preferred optical marker position recognition, the interdependent movement patterns of maxillary and mandibular teeth are analyzed using bidirectional synchronization of tactile and motion image acquisition technologies, and their movements are recorded by a camera system. The camera system preferably integrates at least two systems, one on the right side of the mouth / face and the other on the left side, or one system is centered relative to the facial centerline. Each system has at least one (preferably three) camera, including at least one and preferably two monochrome or color cameras with a minimum resolution of 2.3 Mpx and a high frame rate of at least 1000 frames per second (FPS), equipped with dedicated optics / lenses, and at least one high-resolution and low-frame-rate color camera with a minimum resolution of 12 Mpx and a minimum frame rate of 25 FPS, capable of recording markers (M1) indirectly fixed by positioning patterns, or markers directly / independently (M2 – preferably using IPA technology) affixed to the veneer surface of the crown of the maxillary natural / artificial tooth, and markers independently affixed to the veneer surface of the crown of the natural / artificial tooth. Because of the connection between the camera and the trigger card, their operation is synchronized in time and is responsible for recording the position / movement of the upper crown with M1 and / or M2 markings relative to the lower crown with M1 and / or M2 markings, as well as the position / movement of the upper and lower crowns with M1 and / or M2 markings relative to the alveolar bone of the upper and lower jaws and the patient's face with M2 markings, the markings being affixed to facial feature anatomical points. This is all recorded synchronously in video film technology, and then the 3D scans of the upper and lower teeth with M1 and / or M2 markings are stitched into the video film, wherein the scans are obtained through intraoral or extraoral scanning technology. Furthermore, it can convert the repositioning of M1 and / or M2 markers. Movements during patient chewing assessment are recorded by a camera system, and the captured images are transcribed into a software environment. Digital acquisition of data from the M1 and / or M2 optical markers is submitted for further analysis in the software environment, enabling the conversion of these marker repositionings into the number of collisions between the upper and lower crowns, on which M1 and / or M2 markers are fixed. This is preferably read by a tactile device, preferably a tactile manipulator, to map / control the repositioning caused by these collisions via vibrations at a frequency between 1 and 4 kHz. The above arrangement enables the tracking of the amplitude of height changes in the collision angle, which is above / below 10 degrees between the upper and lower crown pairs with M1 and / or M2 markers, within a set time unit, divided into time intervals, preferably 0.001 seconds. Along the path of each movement phase / chewing cycle, the number of vibrations of the tactile manipulator during the set time unit represents the contact / collision moments of these crown pairs with M1 and / or M2 markers. The pattern on the crown of the natural / artificial tooth positioned on the implant consists of two separable components, including a prefabricated external component that extends out of the mouth and an internal component.The external component has at least three markings at its tip. The internal component is individually designed and customized to fit the veneer surface of the patient's tooth crowns. The digital chewing recorder, located within a single housing, simultaneously records the three-dimensional shape of the face from either the right or left side. Two sets of cameras are located at the two ends of the arched opening, independently or simultaneously recording both sides of the patient's mouth and face, as well as the visual markings M1 and / or M2 fixed to the crowns of the upper and lower teeth. Each camera set includes three cameras spaced at predetermined distances. Each set has two monochrome or color cameras with a maximum resolution of 2.3 Mbps and a high frame rate of at least 1000 FPS, equipped with dedicated optics / lenses, and one color camera with a minimum resolution of 12 Mbps.

This invention discloses an efficient gait control method for a quadruped robot dog based on biomechanical principles. By collecting and analyzing the gait characteristics of quadruped animals in nature, a more realistic reference can be provided for the design of the quadruped robot dog, making its gait closer to nature and improving the smoothness and stability of walking. By optimizing the gait model using simulation technology, an efficient and energy-saving gait pattern can be obtained, reducing energy consumption and improving walking speed and efficiency. At the same time, considering the hardware characteristics of the quadruped robot dog, the initial gait pattern is optimized through a gait generation algorithm to adapt it to different physical structures and movement capabilities, maintaining stable walking in complex environments. By applying specific calculation formulas and adjusting algorithm parameters, the energy consumption per step can be significantly reduced, improving overall energy efficiency. Multiple movement patterns can be generated to adapt to different environments and task requirements, effectively improving the robot dog's walking efficiency and reducing unnecessary energy consumption and movements.

The invention belongs to the related technical field of rehabilitation robots, and particularly relates to a user gait self-adaptive lower limb rehabilitation exoskeleton continuous phase control method, which adopts a multi-task learning model, outputs a user identity probability and a motion mode probability at the same time, generates a probability graph, and provides a user gait self-adaptive lower limb rehabilitation exoskeleton continuous phase control method. And representing the similarity between the current gait and a certain movement mode of a certain sample user in the sample library. And a gait phase variable parameter prediction model is adopted to predict a gait phase variable parameter, and the gait phase variable parameter of the current period is predicted by using the angular velocity data of the initial stage of the current gait period and the matched motion mode. And finally, obtaining an expected joint angle through a real-time gait phase by adopting a pre-constructed relation constraint model corresponding to the sample user obtained by matching and the motion mode of the sample user, and realizing tracking control of the exoskeleton through a PD controller. The motion assisting mode of the exoskeleton can be adjusted in a self-adaptive mode according to the gait characteristics of the user, and the method is suitable for rehabilitation training of patients with lower limb motion dysfunction.

Techniques for physiological monitoring using low sample rate accelerometer data are described and are implementable to generate insights related to user states during extended wear periods. In an example, low sample rate accelerometer data having a sample rate that is below a sample rate threshold is received from a wearable device mounted on a skin surface of a chest region of a user during a wear period. The low sample rate accelerometer data is processed to extract one or more motion-derived parameters that characterize temporal movement patterns of the user during the wear period. An insight for presentation related to a user state during the wear period is generated based on the one or more motion-derived parameters. The insights can include but are not limited to predictions of sleep states, active states, and inactive states, body angle and position determinations, and detection of device inversion events.

This radio wave sensor setting assistance device comprises: an acquisition unit that acquires a movement trajectory of one or more objects moving on a road including a crosswalk, the movement trajectory being detected by a radio wave sensor; an identification unit that identifies, from the movement trajectory of the one or more objects acquired by the acquisition unit, a target movement trajectory of a target object that moves continuously in a specific movement pattern; a first determination unit that determines, on the basis of the target movement trajectory in a coordinate space set in the radio wave sensor, a definition point that defines a detection area corresponding to the crosswalk in the coordinate space; and a second determination unit that determines the detection area in the coordinate space on the basis of the definition point determined by the first determination unit.

In accordance with various embodiments, a self-service checkout terminal can comprise: an image capture device configured to capture image data of a capture region; a product capture device for capturing a product identifier of a product in the capture region when the product is presented to the product capture device; a control device configured: for determining payment information on the basis of the product identifier; for determining a movement pattern on the basis of the image data, wherein the movement pattern represents a movement of a product in the capture region; for determining an indication about a trustworthiness of the payment information on the basis of the movement pattern.