15 results about "Movement pattern" patented technology

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.

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 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.

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).

The invention relates to a steam leak detection system (1) for detecting process steam that the steam trap cannot hold and leak in a line comprising a steam trap, having a control body (10) having a first extension (11) and a second extension (12) through which condensate, steam and flash steam pass, and comprising an inlet orifice (111) through which condensate, steam and flash steam enter into said first extension (11), and an outlet orifice (121) through which condensate, steam and flash steam exit from said second extension (12). The characterizing feature is that it comprises at least one moving object (15) positioned in the flow path of condensate, steam and flash steam between the first extension (11) and the second extension (12), a detector unit (80) having at least one movement detector (81) that detects the movement pattern of said moving object (15), and a processor unit (60) that enables the generation of a warning signal to be transmitted to at least one warning unit (90) when said movement detector (81) detects that the moving object (15) is moving in a way that is outside a reference movement pattern.

The indoor cat exerciser is an innovative exercise system for indoor cats that combines interactive play with treat dispensing and auditory stimuli. The system includes a track for a toy, adjustable speeds, and the ability to customize the layout with various track sections and add-ons. It supports the natural hunting instincts of cats and can be mounted on walls to save space. Key features include self-starting, stopping and random movement patterns in a sensory-rich environments with real or artificial grass, carpeted shelves for claws and audio clips.

This invention discloses a method and apparatus for motion pattern recognition of a target object. The method includes the following steps: A thermal image sequence of a moving part moving within a designated area is acquired in real-time using an infrared sensor array unit in a first distance mode. The thermal image sequence is frame-by-frame, with each frame containing a two-dimensional temperature matrix. It is then determined whether a second distance mode is in effect and whether to switch to it. Spatial features are extracted from each frame of thermal image using a lightweight convolutional neural network. The spatial features from multiple consecutive frames are input into a lightweight recurrent neural network or a one-dimensional convolutional network to capture the temporal dynamic information of the moving part. In the steps of extracting spatial features and capturing dynamic information, different network model branches or parameter sets are loaded according to different distance modes. The temporal modeling results are classified in real-time using an edge-deployed AI inference engine, and the motion pattern of the moving part is output. This motion pattern is used to generate corresponding control commands. The advantages of this technical solution are: high robustness and anti-interference capability; high-precision motion part recognition; and seamless switching between near and far distances.

A portable two-axis perturbation device includes two separated X-Y plane motion platforms controlled by respective motor pairs that may be independently controlled with respect to frequency, amplitude, and variation of movement patterns to create “bottom-up” unpredictable movement patterns more closely resembling real world environmental interactions. By reproducing the amplitude, frequency, direction and variability of external stimuli that may disrupt human balance, the device provides a novel way to train, rehabilitate, reproduce, manipulate and ultimately improve reactive balance reflexes, proprioception and kinesthetic awareness in a way that “top down” perturbation cannot.

Techniques for object detection based on sensor data are discussed herein. In some cases, the techniques described herein include receiving lidar data and radar data associated with an environment of a vehicle, wherein the lidar data comprises a first set of lidar points associated with a first portion of the environment. The techniques further include determining, based on the radar data, a first subset of the first set that is associated with a dynamic movement pattern; determining a first ratio based on the first subset and the first set. Further, the techniques include, based at least in part on determining that the first ratio exceeds a threshold, determining that the first portion is associated with a dynamic object in the environment. In some examples, the vehicle can be controlled based on the dynamic object.

A method and system for quantifying movement patterns in a subject includes receiving motion data representing voluntary and involuntary movements of the subject from a sensor device worn or held by the subject. A signal indicative of involuntary movement deviations occurring in a plane diverging from a voluntary movement trajectory is extracted and associated to a current position of the voluntary movement trajectory. Peaks within the extracted signal are identified, wherein each peak corresponds to a local maximum of involuntary movement magnitude. A probability density function (PDF) of the identified peaks is estimated and a symptom severity score is computed based on one or more quantiles of the estimated PDF. Feedback is provided to a user via a user interface based on the symptom severity score to adjust a parameter of a therapeutic device.

A lighting fixture includes a light source, an exit lens, and an XY beam manipulating system coupled to the exit lens. The XY beam manipulating system is configured to move the exit lens within a plane and with two degrees of freedom, thereby causing an exiting light beam of the lighting fixture to move in accordance with a selected movement pattern.

The invention relates to a method for operating an assistance system (2) of a motor vehicle (1) that is at least partially assisted, comprising the steps of: detecting at least one dynamic object (6) in an environment (5) of the motor vehicle (1) by means of a detection device (3) of the assistance system (2); specifying a target movement pattern of the dynamic object (6) by means of an electronic computing device (4) of the assistance system (2); determining a current actual movement pattern (8) of the dynamic object (6) by means of the electronic computing device (4); comparing the target movement pattern with the actual movement pattern (8) by means of the electronic computing device (4); generating a confidence value (9) for the object (6) as a function of the comparison by means of the electronic computing device (4);and adapting an assistance parameter for at least partially assisted operation with regard to a behavior towards the object (6) depending on the confidence value (9) by means of the electronic computing device (4). Furthermore, the invention relates to a computer program product and an assistance system (2).

The invention relates to method for calibrating a head-mounted device (1), the head-mounted device (1) comprising a frame (2) and at least one sensor (4) mounted on the frame (2), for measuring position and / or motion, the method being implemented while the head-mounted device (1) is worn on a wearer's head, the method comprising steps of: —detection (DET) of a known repetitive movement pattern of the wearer's head by the sensor (4), —acquisition (ACQ) of three-dimensional motion data by the sensor (4), —selection (SEL) of data relative to the movement pattern from the motion data, —numerical treatment (NUM) of the selected data to obtain a reference base relative to the wearer's head, and —calibrating (CAL) the sensor (4) based on the obtained reference base.

A method (20) for controlling a vehicle (100) is disclosed, wherein monitoring of a vehicle environment (U, 110) is carried out by several sensors (11, 12) of the vehicle (100) (21), wherein during the monitoring, movement patterns and / or characteristics of persons (14) inside the vehicle (100) and / or in the external vehicle environment (U) of the vehicle (100) are detected (22), wherein detected movement patterns and / or characteristics of persons (14) are compared (23) with movement patterns and / or characteristics stored in a database (15), wherein, in the event of a positive comparison based on the movement patterns and characteristics of persons (14), at least one person (14) is authorized (24) and at least one control signal is generated (26) based on the detected movement pattern. A vehicle (100) is also disclosed.

This invention belongs to the field of computer vision and pattern recognition technology, specifically relating to a method and system for predicting energy consumption during fitness activities based on vision and deep learning. It aims to address the problem that existing vision-based general energy consumption prediction models suffer from severe feature interference and limited prediction accuracy due to neglecting biomechanical differences between different movement patterns. The invention includes: acquiring video stream data and extracting key human body points to construct a skeleton sequence tensor; identifying movement pattern categories using a spatiotemporal graph convolutional network; extracting associated kinematic feature time series based on movement categories; inputting the features into an energy consumption prediction regression model with an independent parameter space, encoding temporal dependencies based on a self-attention mechanism, and outputting predicted values ​​of body activity intensity. This invention, through a hierarchical architecture of identification followed by prediction, effectively improves the accuracy and robustness of energy consumption prediction across movement patterns.