920 results about "Exoskeleton" patented technology

The invention discloses a brain-computer interface upper limb motion recovery training system, and relates to the technical field of upper limb motion recovery training, the brain-computer interface upper limb motion recovery training system comprises a multi-modal neural signal acquisition module, a combined regulation and control module and a rehabilitation exoskeleton module, the multi-modal neural signal acquisition module is connected with the combined regulation and control module through a wireless Bluetooth protocol, and the combined regulation and control module is connected with the rehabilitation exoskeleton module. The combined regulation and control module is connected with the rehabilitation exoskeleton module through a CAN bus, and the combined regulation and control module is used for synchronously processing fNIRS blood flow signals, tDCS nerve regulation and control parameters and EEG electrophysiological characteristics and generating a closed-loop feedback instruction. By installing the signal fusion unit and the intention analysis unit, time-space complementary fusion of EEG and fNIRS signals is realized, the problem of low precision of traditional single-mode intention recognition is solved, and the motion intention decoding accuracy is improved.

The invention provides an exoskeleton man-machine motion intention cooperative control method and device and a storage medium, and relates to the technical field of robot motion control signal processing. According to the method, signal phase differences are acquired through energy buttons at human joints, and an original phase difference sequence is formed and preprocessed; calculating a cross correlation coefficient of the target and the associated joint based on the preprocessed sequence, and constructing a motion feature set in combination with the joint speed and acceleration; constructing a prediction model by using a long-short-term memory network, and outputting motion intention and joint position prediction information through multi-feature fusion training; and analyzing the prediction information by adopting a second-order linear impedance model, generating a driving torque instruction and sending the driving torque instruction to the servo motor for execution. According to the method, signal phase difference analysis, LSTM prediction and impedance control are fused, the problems of response lag and poor adaptability of a traditional exoskeleton are solved, the control real-time performance, accuracy and cooperative fluency are improved, and the use requirements of different users in different scenes are met.

The embodiment of the invention relates to the technical field of information, and discloses an intelligent data acquisition method and device, a medium and a product, the intelligent data acquisition method comprises the following steps: acquiring artificial demonstration data through an exoskeleton system, the artificial demonstration data comprising video stream data, motion data and force sense data; importing the video stream data into a first large language-vision model, segmenting the video stream data into a plurality of independent task fragments, and generating independent task fragment descriptions; importing the independent task fragment description into a large language model, and generating a task label based on natural language description; and exporting the independent task segments, the task labels and the corresponding motion data and force sense data to generate intelligent data. Therefore, a low-cost, high-efficiency and large-scale intelligent data acquisition and processing method is established, and automatic conversion from human operation data to high-quality VLA training data is realized.

The invention discloses a patient improvement effect analysis method for controlling spinal cord electrical stimulation through an implantable brain-computer interface, and relates to the technical field of medical rehabilitation, and the method comprises the steps: multi-dimensional collaborative data collection: implanting electrodes in a target brain region and below a spinal cord injury segment, installing a detection element at an exoskeleton key part, and carrying out multi-dimensional collaborative data collection; a sensor is attached to a lower limb preset muscle group, electroencephalogram signals, SCS stimulation parameters, EXS motion data and neuromuscular response data are synchronously collected, and time correlation marks are embedded; according to the method, the reliability of motion intention decoding is remarkably improved by adopting a mode of combining multi-source signal preprocessing and a multi-mode intention recognition model, and in the signal preprocessing stage, the self-adaptive filtering algorithm combining Kalman filtering and wavelet threshold denoising is applied, so that the motion intention decoding efficiency is improved. SCS electrical stimulation interference, EXS motor noise and physiological noise in the electroencephalogram signals are effectively removed.

The invention discloses a double-clutch variable-stiffness knee joint exoskeleton, and relates to the technical field of wearable lower limb exoskeletons.The double-clutch variable-stiffness knee joint exoskeleton comprises a gait sensing module arranged outside and a limb connecting arm module used for being connected with a human body, and an energy storage module is installed on one side of the limb connecting arm module; a sensor module is mounted on the other side of the limb connecting arm module; the limb connecting arm module comprises a limb connecting arm assembly I used for being connected with the thigh of the human body and a limb connecting arm assembly II used for being connected with the shank of the human body, the limb connecting arm assembly I and the limb connecting arm assembly II are each provided with a clutch unit, and the core speed increaser is installed between the limb connecting arm assembly I and the limb connecting arm assembly II. The energy storage module and the sensor module are arranged on the two sides of the core speed increaser, and the core speed increaser is connected with the energy storage module. The device has the advantages of compact structure, variable rigidity bandwidth and good motion adaptability, can realize high energy recovery efficiency in a multi-gait mode, and reduces the metabolic consumption of a human body.

The utility model discloses an outer skeleton, prefilter and water consuming system relates to prefilter technical field, wherein outer skeleton includes barrel frame and siphon runner, said siphon runner includes the side wall runner of said side frame and is provided the bottom runner of said chassis, said side wall runner is communicated with said bottom runner, said bottom runner is provided with said bottom runner, said side wall runner is provided with said side frame, said bottom runner is provided with said bottom runner, said bottom runner is provided with said bottom runner, said bottom runner is provided with said bottom runner. The side wall flow channel is provided with a siphon hole communicated with the inner cavity of the cylinder frame, and the siphon flow channel is provided with a first discharge port communicated with the outside of the cylinder frame. According to the scheme, the rotatable outer framework and the siphon flow channel are introduced, so that the filtering efficiency and the cleaning effect are improved, the maintenance process is simplified, and more convenient, efficient and economical use experience is brought to a user.

The invention discloses an exoskeleton attitude prediction system for building construction, particularly relates to the field of attitude prediction, and comprises a multi-dimensional sensing module, a data preprocessing module, an attitude prediction model module and a control decision module. A multi-dimensional sensing module collects joint movement, muscle movement and human-computer interaction force data through a nine-axis IMU, a surface myoelectricity sensor and a miniature strain type force sensor; the preprocessing module obtains standardized feature data through filtering, standardization and exception elimination; the attitude prediction model uses a CNN-LSTM hybrid architecture, and outputs a target attitude of 0.5-2 seconds; and the control decision module compares a prediction result with a safety threshold value, generates control instructions in three levels to drive exoskeleton correction, synchronous feedback and recording, solves the problem of response delay of a traditional exoskeleton, and improves the construction safety and efficiency.

The invention relates to the field of rehabilitation instruments, in particular to an intelligent pneumatic hand function rehabilitation training system which comprises a flexible exoskeleton glove provided with a pneumatic muscle array and used for assisting fingers of a user in grasping training. The fingertip position of the glove is connected with a magnetorheological damper through a flexible cable, and the magnetorheological damper is used for providing dynamic resistance in the training process. The electrical stimulation module is used for activating hand muscle groups in a targeted manner through a surface electrode and enhancing neuromuscular control; the sensor module is used for collecting physiological data of a user in real time; the physiological data comprises electromyographic signals and tissue blood oxygen saturation; the control unit is used for switching training modes, by means of the intelligent air pressure hand function rehabilitation training system, the training intensity can be matched with the real-time ability of a patient all the time, and the rehabilitation training effect is improved.

The invention relates to the technical field of rehabilitation robot control, and particularly discloses a gait prediction compensation admittance control method and system for lower limb rehabilitation exoskeleton, and the method comprises the steps: inputting a multi-dimensional motion vector into a time sequence prediction model, and outputting a prediction result of a gait phase at a future moment; if the maximum probability output by the time sequence prediction model is lower than a preset threshold value, automatically switching to a pre-constructed rule criterion to carry out gait phase recognition; an admittance control parameter matched with the gait phase prediction result is called from an admittance parameter mapping table, and a main control torque is calculated based on the called admittance control parameter; calculating a compensation torque based on the deviation between the actual human-computer interaction force and the expected interaction force; and the main control torque and the compensation torque are superposed to serve as a final torque driving instruction of the exoskeleton motor. Real-time gait prediction, admittance parameter self-adaptive adjustment and interaction force error dynamic compensation can be fused, and high-flexibility and high-safety man-machine collaborative rehabilitation training is achieved.

An exoskeleton system comprising a leg actuator unit that is configured to be coupled to a leg of a user. The leg actuator unit includes: an upper arm and a lower arm that are rotatably coupled via a rotatable joint, the rotatable joint configured to be positioned at a knee of the user with the upper arm coupled about an upper-leg portion of the user above the knee and with the lower arm coupled about a lower-leg portion of the user below the knee. The upper arm is configured to be coupled to the upper-leg portion above the knee via a first set of couplers that includes a first upper-leg coupler, the lower arm is configured to be coupled to the lower-leg portion below the knee via a second set of couplers that includes one or more lower-leg couplers associated with a lower-leg brace, and an actuator extends between the upper arm and lower arm, the actuator configurable to move the upper arm and lower arm.

The invention relates to the field of upper limb joint rehabilitation training, in particular to an upper limb joint rehabilitation training method and system based on an exoskeleton mechanical arm, and the method comprises the steps: collecting sEMG signals of a target muscle group of a user in real time in a training process; calculating the root mean square of the amplitude of the sEMG signal in the current time window; if the root mean square is smaller than a muscle force insufficient threshold value, a training mode is switched to a full-assistance mode; if the root mean square is not smaller than the muscle force insufficient threshold value and smaller than the normal muscle force threshold value, the training mode is switched to a semi-assistance mode; if the root mean square is larger than or equal to the normal muscle force threshold value, the training mode is switched to an anti-resistance training mode. The rehabilitation training effect of the upper limb joints can be effectively improved.

The present application relates to the field of medical devices, and provides a back plate adjustable exoskeleton, comprising: a column structure and a control module, the column structure is slidably connected with a back plate mechanism, and a lower limb exoskeleton connected with the back plate mechanism, and the back plate mechanism is provided with a back plate which can move up and down relative to the back plate mechanism; further comprising: a binding device arranged on the lower limb exoskeleton and a foot bottom exoskeleton, the foot bottom exoskeleton is provided with a pressure sensor. When the human body wears the exoskeleton and changes from a sitting posture to a standing posture, the back plate mechanism adjusts the back plate mechanism along the column structure to the height matched with the user according to different body shapes of the user; and when the user changes the posture in the walking process in the standing posture, the foot bottom exoskeleton detects the change of the foot bottom pressure, so that the control module can control the up and down movement of the back plate relative to the back plate mechanism according to the foot bottom pressure to adjust the human body posture.

An exoskeleton system comprising at least one leg actuator unit configured to be coupled to leg of a user, the leg actuator unit including: an upper arm and a lower arm that are rotatably coupled via a joint, the joint positioned at a knee of the user with the upper arm coupled about an upper leg portion of the user above the knee and with the lower arm coupled about a lower leg portion of the user below the knee, a leg-actuator-unit user interface comprising a plurality of input and feedback elements, and an actuator that extends between the upper arm and lower arms.

The invention belongs to the technical field of wearable exoskeletons, and particularly relates to a forearm power assisting device, a forearm power assisting method and an upper limb power assisting system. The forearm power assisting device comprises an angle transmission mechanism, an angle amplification mechanism, an elastic energy storage mechanism and a tension output mechanism; wherein the buckling angle of the front arm is transmitted through the angle transmission mechanism, and after the buckling angle is amplified through the angle amplification mechanism, the elastic energy storage mechanism is driven, so that the flexible traction cable outputs pulling force linked with the buckling angle of the front arm. The forearm power assisting device is a system based on the pure mechanical transmission and energy storage principle, forearm flexion and extension angle changes can be directly converted into self-adaptive tension linked with the forearm flexion and extension angle changes, and therefore forearm muscle fatigue in long-time fine operation can be effectively relieved without an external power source.

The invention relates to a virtual hand grasping perception and exoskeleton force feedback mapping method based on virtual-real interaction, and belongs to the technical field of virtual reality, the method comprises the following steps: building a hand exoskeleton, and reading joint data in real time; calculating the pose of each joint coordinate system of the virtual hand relative to the virtual world; according to the calculated poses of all the joints of the virtual hand, the virtual hand is driven to synchronously move with the hand exoskeleton in real time; collision and contact events of the virtual hand and the digital object are monitored in real time, and virtual interaction force generated when the virtual hand interacts with the digital object is calculated; calculating feedback torque required to be output by each hand exoskeleton motor of the hand exoskeleton, and driving the motors to output corresponding feedback force through a motor controller of the hand exoskeleton, so as to realize force feedback of the hand. According to the method, the interaction reality sense in the virtual reality application can be enhanced, the user can interact with the virtual environment more naturally in an immersive mode, and the user experience is improved.

The invention discloses a quasi-passive knee joint exoskeleton and a design method thereof, the knee joint exoskeleton comprises a transmission energy storage module, a power-assisted regulation and control module and a wearing module, and the power-assisted state is switched according to the gait stage of a human body. The transmission energy storage module transmits joint torque through an input gear, an intermediate gear and an output gear, and a pressing rod on an output shaft is used for driving a flexible hinge to deform, so that efficient energy storage and release in a small space are realized; the assistance regulation and control module controls a cam shaft to rotate, drives a swing shaft to push an intermediate gear to move and enables the gears to be meshed in the supporting phase, motion limiting is formed through contour matching of a cam shaft body and a swing shaft matching cambered surface, mechanical self-locking is achieved, locking force does not need to be additionally provided, and walking assistance is achieved. In the swing phase, the camshaft is controlled to rotate to enable the unlocking cambered surface to turn to the swing shaft, the swing shaft is unlocked, a driving pin of the camshaft drives the swing shaft to rotate, the gear is disengaged, and free swing is achieved. Compared with the prior art, the invention has the advantages of light weight and low power consumption.

Exemplary task-agnostic exoskeleton control system and method are disclosed that are task-agnostic utilizing instantaneous estimates of biological joint moments from deep neural networks to assist the user movements. The exemplary control system employs multiple body sections and joints in-the-loop estimation to provide multi-joint assistance operation, e.g., within an autonomous, clothing-integrated exoskeleton. The exemplary control system may deploy a deep domain adaptation (DDA) method configured to translate human movement data between a simulated sensor domain and a real sensor domain.

A system obtains high-resolution data of actual over-ground gait rehabilitation interactions through a custom-made wearable system for identifying abnormal gait patterns and the therapists' assistance strategies. The system implements an impedance learning algorithm with feature selection and a goal-directed attractor definition reproduces therapist assistance in a way that integrates clinical insights into the control of lower-limb exoskeletons.

The invention discloses a flexible knee joint exoskeleton for maintaining dynamic stability of knee joints in the technical field of lower limb rehabilitation, and the flexible knee joint exoskeleton comprises a control box, a control module and a power supply unit are integrated in the control box, and one side of the control box is fixed to the waist of a user through a bandage. The device further comprises a sensing unit, a tibia anterior movement limiting assembly and a support fixing assembly, the output end of the sensing unit is electrically connected with the input end of the control box, and the sensing unit is used for obtaining first movement information of a user and sending the first movement information to the control box; the control box identifies the walking trend and the knee joint state of the user based on the first motion information and an artificial intelligence algorithm, wherein the knee joint state is a six-degree-of-freedom kinematics state. According to the flexible knee joint exoskeleton, the Bowden cable and the tibia forward movement limiting assembly are cooperatively driven, human body lower limb kinematics information is collected in real time through the sensing unit, and the forward movement amplitude of the tibia of a user can be limited.

Various examples are provided related to gait kinematics. A methodology for human in the loop optimization (HILO) for use of a hip exoskeleton is presented. In one example, a method includes monitoring a gait phase of an exoskeleton and controlling switching time between admittance parameters associated with actuator control of the exoskeleton, where the switching time is controlled based upon the monitored gait phase. The admittance parameters can be predetermined and can be user specific. The time of the switching can be determined from use of the exoskeleton and can be determined using reinforcement learning.

A trajectory planning method for a lower limb exoskeleton includes: determining a state space equation corresponding to the lower limb exoskeleton using dynamic analysis; determining an objective function for trajectory planning of the lower limb exoskeleton according to the state space equation, wherein a phase variable corresponding to the objective function is a time-related phase variable; and performing trajectory planning of the lower limb exoskeleton according to the objective function to obtain a first gait trajectory corresponding to the lower limb exoskeleton, wherein the first gait trajectory is a gait trajectory corresponding to the time-related phase variable.

The invention relates to the technical field of intelligent control, and discloses a power-assisted control method of a lower limb pneumatic flexible exoskeleton and a lower limb pneumatic flexible exoskeleton system.The method comprises the steps that healthy side plantar pressure data are obtained, healthy side key gait event nodes are recognized, and the power-assisted control method of the lower limb pneumatic flexible exoskeleton is obtained according to the healthy side key gait event nodes and ankle joint angle data; estimating an uninjured side continuous gait phase, and calculating an affected side target gait phase according to the uninjured side continuous gait phase; according to the target gait phase of the affected side, auxiliary torque and tension are determined; according to the auxiliary torque and the pulling force, target air pressure for supporting the airbag and shrinking the airbag is determined, an electromagnetic valve is controlled to execute deflation or inflation operation according to the target air pressure, and the internal pressure of the airbag is controlled within a target range. The invention aims to provide flexible assistance conforming to the biomechanical characteristics of the ankle joint of a human body for people with ankle joint dysfunction, improve the walking ability and improve the safety and comfort of rehabilitation training.

The invention provides a dynamic walking exoskeleton control method and system based on man-machine complementary optimization, and the method comprises the steps: defining the step height and normal contact force of a contact point, and constructing a nonlinear complementary problem constraint and model; defining quantitative targets of nine types of motion tasks including contact point centroid position tracking, centroid linear velocity tracking, foot yaw angle alignment, frame attitude tracking, base quaternion derivative regularization, contact force regularization, joint regularization, swing height control and contact control regularization, and establishing a multi-task target function; a static nonlinear complementary problem is coupled with exoskeleton continuous dynamics, and a coupling system is constructed; solving the optimization objective function by adopting a neurodynamics algorithm to obtain the optimal control input of the exoskeleton-human body system; and the control input mapping obtained through optimization is converted into a driving instruction of a robot actuator, and a motion control closed loop is completed. According to the method, the complex movement requirements under strong coupling constraint interaction of the humanoid and the robot can be more accurately met.

An exoskeleton is provided and includes a garment to be worn by a user, an exoskeleton interface provided on a backside of the user when wearing the garment, and an exoskeleton mechanism adapted to be connected to the garment via the exoskeleton interface. The exoskeleton mechanism includes an actuator system having a spring-loaded assembly coupled a torso anchor and pivotally coupled to a waist anchor, and a resilient element connected to the casing. The spring-loaded assembly is operable to generate a force upon deformation or deflection of the resilient element. The exoskeleton mechanism also includes actuator links rotatably coupled between the waist anchor and respective thigh anchors. Each actuator link is operatively coupled to and adapted to operate the spring-loaded assembly upon rotation of the casing or the actuator links. The force generated upon operation of the spring-loaded assembly is transferred to the user via the exoskeleton interface and the garment to assist the user in performing a movement.

The invention relates to the technical field of power assisting equipment, in particular to an unmanned aerial vehicle operated upper limb power assisting exoskeleton which comprises an exoskeleton body, a main control device and a myoelectricity sensor. The exoskeleton body comprises a shoulder rest assembly matched with the shoulder and the back and arm assemblies matched with the arms, the two sides of the shoulder rest assembly are each provided with one arm assembly, and the two arm assemblies are connected through a first flexible connecting piece. The arm assembly is provided with a myoelectricity sensor, and signals of the myoelectricity sensor and rocker thrust signals of an unmanned aerial vehicle remote controller are transmitted to the master control device. The first fixing part and the second fixing part of the arm assembly are connected through the driving piece, the main control device can control the driving piece to drive the two to rotate relatively, and the rotating winding mechanism of the shoulder support assembly winds or releases the first connecting piece. The exoskeleton can accurately recognize operation intentions, cooperate with upper limb movement to provide targeted assistance, effectively relieve shoulder and elbow muscle loads, reduce arm shaking, delay fatigue and improve the control stability and operation durability of the unmanned aerial vehicle, and is suitable for long-time operation scenes such as electric power inspection and surveying and mapping.

The invention relates to the crossing field of medical rehabilitation and brain-computer interface technology, and particularly discloses a lower limb exoskeleton rehabilitation training system and method based on AR glasses and brain-computer interface control. According to the system, motor imagery electroencephalogram decoding is used as core driving force, lightweight AR visual guidance, lower limb exoskeleton mechanical assistance and functional electrical stimulation feedback are fused, and real-time information interaction among multiple modules is achieved through wireless communication; therefore, a closed-loop rehabilitation system integrating sensing, decoding, execution, multi-mode feedback and self-adaptive adjustment is constructed. Under the framework, the subjective motion intention of the patient not only can directly participate in the exoskeleton control process, but also can continuously adjust training parameters and interaction modes through dynamic monitoring of physiological signals and emotional states, so that a patient-centered lower limb rehabilitation training mode which better conforms to the neuroplastic law is achieved.

The utility model relates to an exoskeleton using flexible joints for walking aiding, which comprises a waist supporting mechanism, a hip bone supporting mechanism is arranged below the waist supporting mechanism, thighbone supporting components capable of deforming are arranged on two sides of the hip bone supporting mechanism, and the top of each thighbone supporting component is connected with a wire driving mechanism. A shank supporting assembly is hinged to the bottom of the thighbone supporting assembly, a deformable flexible joint assembly is further arranged between the bottom of the thighbone supporting assembly and the linear driving mechanism, and a driving rope is connected to the surface of the flexible joint assembly. One end of the driving rope is connected to the wire driving mechanism and the other end is connected to the top of the thighbone supporting assembly of the shank supporting assembly; according to the utility model, the traction of the driving rope and the adaptability of the elastic bandage are combined to form a bimodal power-assisted mechanism. Compared with a gear / motor driving mode of a traditional rigid exoskeleton, power consumption is remarkably reduced, and motion fluency is improved.

The invention relates to the technical field of cervical vertebra rehabilitation systems, and discloses an intelligent self-adaptive cervical vertebra rehabilitation system. The system comprises a multi-mode sensing unit which synchronously collects form data and soft tissue data of the cervical vertebra of a user through an optical mark point array and an ultrasonic probe array to generate a multi-source sensing data set; the intelligent analysis unit constructs a cervical vertebra dynamic mechanical model by using a graph convolutional neural network based on the multi-source sensing data set, analyzes a cervical vertebra joint coupling relation and stress distribution, and generates an analysis parameter set; the strategy generation unit generates a personalized rehabilitation strategy according to the analysis parameter set, the personalized rehabilitation strategy comprises an action sequence and an impedance adjustment parameter, and a strategy instruction set is formed; the dynamic control unit responds to the strategy instruction set and combines muscle activity data fed back by the electromyographic signal sensor in real time to adjust an execution strategy and generate a control command set; and the flexible driving unit drives the soft robot outer skeleton to perform multi-axis linkage rehabilitation training based on the control command set.

The invention relates to a robot agent evaluation system for a lower limb exoskeleton and a gait strategy training method corresponding to an agent, and belongs to the technical field of rehabilitation medical auxiliary equipment. The device comprises a humanoid robot, an exoskeleton, an auxiliary device and a detection element, the exoskeleton is connected with the humanoid robot through the auxiliary device, a first auxiliary structure is provided with a groove, a second auxiliary structure is provided with a protrusion, the groove is connected with the humanoid robot in a clamped mode, and the protrusion is detachably connected with the humanoid robot; the detection elements are installed on the soles of the humanoid robot. The gait of the humanoid robot is adjusted by using a gait strategy training method, so that the humanoid robot can simulate the walking postures of different healthy people or patients with different hemiplegia levels. By wearing the exoskeleton on the device and deploying different walking aid strategies, related data such as angle, torque and power change of each joint, total energy consumption and gait symmetry of the humanoid robot under different walking conditions are obtained, and an exoskeleton developer is assisted to better test and optimize an exoskeleton product.

The invention belongs to the technical field of robots, and provides a hip joint exoskeleton and a walking assistance control method.The hip joint exoskeleton comprises three active driving units, and a hip joint exoskeleton sagittal plane driving unit is used for achieving forward flexion / backward extension of a human hip joint; the hip joint exoskeleton coronal plane driving unit is used for realizing human hip joint adduction / abduction; the hip joint exoskeleton horizontal plane driving unit is used for realizing inward rotation / outward rotation of the hip joint of the human body; the hip joint exoskeleton sagittal plane driving unit, the hip joint exoskeleton coronal plane driving unit and the hip joint exoskeleton horizontal plane driving unit are connected through the remote rotating center mechanism, so that a rotating plane corresponding to the horizontal plane driving unit is aligned with a hip joint rotating center through a virtual axis. The hip joint exoskeleton is compact in structure and saves space. According to the control method, when the user wears the exoskeleton to walk, the exoskeleton can accurately assist the walking of the user without time delay.