9 results about "Motor processes" patented technology

The application discloses a pinch-proof current threshold calculation method, system and device, and a storage medium. The pinch-proof current threshold calculation method comprises the following steps: dividing the whole Hall stroke into multiple Hall regions according to current characteristics; collecting current data in a complete motor motion process multiple times in each Hall region to obtain multiple sets of current data of each Hall region; setting a pinch-proof current threshold of each Hall region according to the multiple sets of current data of each Hall region; in each motor motion process, calculating a current average current value of each motor motion through a corresponding Hall region, and judging whether the current average current value changes relative to the last average current value; if the current average current value changes, the pinch-proof current threshold of the Hall region is recalculated and updated; otherwise, the pinch-proof current threshold does not change. The application can dynamically adjust the pinch-proof current threshold, and solves the problem that the motor current characteristics change with the use time, resulting in the failure of the pinch-proof function.

System and method for guiding a user in activating biological motor units (MUs) are disclosed. A method includes presenting instructions for performing a movement associated with activation of MUs, and graphical elements associated with the activation of the MUs. The method includes, in response to detecting an activation of the MUs, determining, based on biopotential sensor data captured during performance of the movement an additional movement to be performed by the user and a change to the graphical elements. The method includes presenting additional instructions for performing the additional movement, and the change to the graphical elements. The method includes, in response to detecting an additional activation of the MUs, in accordance with a determination that additional biopotential sensor data captured during performance of the additional movement satisfies a threshold, associating the additional biopotential sensor data with biopotential-based gestures, and presenting an additional change to the graphical elements.

The application discloses a device and method for detecting mouse motion learning behavior, and belongs to the field of animal behavior detection. The device comprises a mouse motion runway, a dark box at the terminal of the runway, and a camera for recording the motion process of the mouse. The runway is provided with a plurality of replaceable metal rods in the transverse direction. The metal rods are composed of any one or both of white metal rods and black metal rods. The runway composed of the black metal rods and the white metal rods is provided with any one of the metal rods for electrification, and the electrified metal rods are discontinuously arranged. The mouse is shocked by stepping on the electrified metal rods. The method of the application replaces the metal rods to form different runways, trains the mouse to reach the dark box through the different runways, and obtains the motion learning behavior ability of the mouse at different stages. The process of motion learning is simulated through programmed training. The role of the brain regions in the process of motion learning behavior is determined by regulating the regions of the substantia nigra or the striatum corresponding to the motion learning.

The application discloses a motion skill action posture intelligent evaluation method and system, adopts a multi-view camera array to synchronously collect a motion process video, extracts a human body skeleton two-dimensional key point through an improved algorithm, combines multi-view geometric constraints and Kalman filtering to reconstruct a three-dimensional human body posture sequence, constructs a standard action posture template library, realizes posture alignment of an evaluation object and a standard template through body proportion normalization processing, completes action stage division and phased posture evaluation through a dynamic time warping algorithm, calculates posture deviation and generates a graded deviation diagnosis report, and finally realizes superimposed visual feedback of evaluation postures and standard postures through augmented reality technology. The application can realize high-precision, quantifiable and phased intelligent evaluation of motion postures, eliminate the interference of individual morphological differences on evaluation results, accurately locate action deviation nodes, and provide intuitive interactive correction guidance.

The utility model relates to the technical field of humanoid robots, in particular to a parallel flexible driving humanoid lower limb mechanism and system. A parallel flexible driving human lower limb simulating mechanism comprises a thigh assembly, a first driving mechanism, a second driving mechanism, a driving mechanism and a driving mechanism, wherein the thigh assembly comprises a first motor and a thigh support connected with the output end of the first motor; the shank assembly comprises a second motor and a shank support connected with the output end of the second motor, the shank support is hinged to the thigh support, and the second motor is arranged at the hinged position of the shank support and the thigh support; the foot assembly comprises a third motor and a foot plate, the foot plate is hinged to the shank support, and the output end of the third motor is hinged to the foot plate. The lower limbs can move through cooperative use of all the components. The peak torque of the second motor is reduced in the movement process by adjusting the spring stiffness, so that a servo motor with smaller peak torque is allowed to be selected, the quality of the humanoid lower limb is reduced, the electric energy efficiency is improved, and the working time is prolonged.

This invention relates to a method and system for motor parameter tuning. The method includes: inducing a motor to perform a first tuning movement according to predetermined first configuration conditions to automatically redetermine the motor's tuning parameter values; acquiring at least one performance evaluation data of the motor based on the tuning parameter values, and determining whether the performance evaluation data meets the corresponding preset target; when the performance evaluation data does not meet the corresponding preset target, inducing the motor to perform a second tuning movement according to second configuration conditions and tuning parameter values, acquiring the motor's performance evaluation data during the second tuning movement, and adjusting the motor's tuning parameter values ​​according to the performance evaluation data to make the performance evaluation data meet the corresponding preset target; and taking the tuning parameter value when all performance evaluation data meet the corresponding preset target as the target tuning result. In some implementations, this method can improve the motor tuning effect.

According to the discrete muscle loss detection and analysis integrated system, method and equipment and the medium provided by the invention, the state evaluation and detection of the muscle in the movement process can be deepened from simple in-vitro scale detection, and the evaluation of the muscle loss is more accurate; meanwhile, compared with other analysis technologies related to physiological parameters, the system directionally collects electrophysiological signals and motion posture data of thigh muscles of left and right legs in a power bicycle training scene through an integrated sensor of two-channel myoelectricity and an inertial navigation chip, so that multi-dimensional correlation analysis of a force exerting state and a motion track is realized; and local pertinence and data precision of leg muscle loss assessment are improved. The system is specially designed for a power bicycle training scene, the sensor is attached to the thigh muscle, a personalized and controllable motion form can be achieved, and therefore the muscle state can be better activated, and more accurate myoelectricity and muscle sound information can be obtained.

The application discloses a kind of automobile seat anti-pinch method, device and storage medium, method includes perception step, decision step and execution step, as follows: S1 perception: the current data of motor movement in seat system is collected, current data is processed, and current data I n It is obtained;The current data obtained after processing is converted into current rate of change ΔI;Collect the hall sensor data in seat system, obtain hall pulse count, integral conversion is absolute position P, and then obtain speed rate of change ΔV;S2 decision: set current change threshold ΔI t , set speed change threshold ΔV t Only when ΔI> ΔI t And ΔV> ΔV t , it is judged that seat system needs to enter anti-pinch state;S3 execution: after judging that anti-pinch needs to be triggered, execution module controls corresponding motor reverse operation, until reverse operation distance reaches the set value, then seat system exits anti-pinch state.The application solves the stability problem of anti-pinch algorithm, and reduces the false reverse rate in motion process.

The invention discloses a gesture and force synchronous recognition method for realizing nerve driving through feature enhancement based on VMD denoising processing, and the method comprises the steps: collecting an upper limb muscle activity signal in the motion process of a subject, and carrying out the denoising processing of the upper limb muscle activity signal, so as to obtain an initial signal; decomposing the initial signal into a motion unit discharge sequence, and extracting data features in the motion unit discharge sequence to obtain neural driving features corresponding to the motion process; enhancing the neural drive features among different force levels using a geodesic flow accounting method to obtain enhanced features; and inputting the enhanced features into a pre-trained classifier to identify corresponding gestures and force levels. The invention further provides a gesture and force synchronous recognition device. According to the method provided by the invention, high precision and strong robustness in gesture control of the unmanned aerial vehicle can be realized, and the problems that noise interferes with real signals and gestures and force level interfere with each other in signal acquisition are solved.