33 results about "Motor execution" patented technology

The invention discloses an irregular action recognition method, system and device for short-time sequence electroencephalogram and electromyography fusion, and the method comprises the steps: collecting electroencephalogram and electromyography signals from motor imagery to execution in an incomplete asynchronous manner through a wireless electroencephalogram signal collection device and a distributed wireless surface electromyography signal collection device; processing noise in the electroencephalogram signals and the surface electromyogram signals; in combination with electroencephalogram signals in a motor imagery period, extracting electroencephalogram signal space domain features in a motor execution period, extracting time domain features of surface electromyogram signals, and in combination with a mixed fusion mode of feature layer fusion and decision-making layer fusion, fusing short-time sequence electroencephalogram and electromyogram signals in the motor execution period; according to the method, the motion imagination period recognition result and the motion execution period recognition result are subjected to confidence analysis, irregular actions of the user are quickly and accurately recognized and serve as control instructions to be input into the exoskeleton robot, the exoskeleton robot is controlled to assist the user in completing the target actions, and the initiative of the user is effectively improved.

The invention discloses an electroencephalogram feature recognition method for motion intention prediction in a lower limb alternate stepping process. The electroencephalogram feature recognition method comprises the following steps: acquiring an electroencephalogram signal of a subject before the subject executes an action under the requirement of a lower limb alternate stepping motion execution normal form; preprocessing the electroencephalogram signal to obtain an initial signal, performing label labeling on the initial signal according to an action type, and forming a data set by a label and the initial signal; constructing a neural network model, wherein the neural network model comprises a multi-scale grouping space-time convolution module, a self-attention mechanism module for updating external memory based on Top-k gating and a grouping causal time convolution module; and training the neural network model in a supervised manner by using the data set to obtain a prediction model for predicting the action type. According to the method provided by the invention, the movement intention of the patient can be recognized by the movement brain-computer interface before the lower limb alternate movement, the control of the rehabilitation robot on the specific lower limb movement by the brain intention is realized, and the method has an important value on the clinical application of a brain-controlled rehabilitation robot system.

The invention discloses a robot remote control system based on augmented reality and visual feedback, and the system comprises a visual collection module of a sensing layer which obtains an environment image in real time through a built-in camera; a rocker control module and a video stream transmission module of the augmented reality control layer realize a rocker control function and a video stream transmission function; a WebSocket client module and a WebSocket server module of the communication relay layer are used for transferring and transmitting instructions and data; and the robot execution control layer comprises a chassis control module and a motion execution module, and the chassis control module is operated and managed by the master control computing platform Intel NUC and is used for completing execution of a motion instruction. The invention further discloses a robot remote control method based on augmented reality and visual feedback. The invention belongs to the technical field of augmented reality technology and humanoid robot remote control, and solves the problems that in the prior art, an operation interface of a humanoid robot is not visual, visual feedback delay is serious, and network adaptability is insufficient.

The invention discloses a motion execution mechanism error determination method and device, equipment and a storage medium. The method comprises the following steps: acquiring instruction data corresponding to a motion control instruction of a motion execution mechanism; collecting displacement data of the motion execution mechanism in the process of executing the motion control instruction; and determining the motion error of the motion execution mechanism according to the instruction data and the displacement data. According to the scheme, an error analysis mechanism based on the instruction data and the actual displacement data is introduced, so that the motion performance of the motion execution mechanism is accurately evaluated and quantified. According to the scheme, the positioning precision and the overall operation stability of the motion executing mechanism can be remarkably improved, and the requirements of scenes such as high-precision industrial automation, robot operation and precision machining can be met.

The ability to effectively communicate information to people without causing them any discomfort or unease. [Solution] The robot operation method includes a detection step in which a detection device detects human movement, and an operation step in which a plurality of robots perform actions in accordance with the movement detected by the detection device, wherein in the operation step, at least one of the plurality of robots performs an action that is deviated from the actions of the other robots.

This invention relates to the field of correction control technology, specifically to an automatic correction control system for cotton web width on a drawing frame. The system includes a position detection module, a main control unit module, an auxiliary algorithm module, a drive control module, a motor execution module, a human-machine interaction module, and a process database module. The position detection module is used to collect the position and width information of the fed sliver in real time and convert it into a pulse equivalent signal. This invention uses a position detection module with dual sensors symmetrically arranged to collect sliver position and width information in real time and convert it into a digital pulse equivalent signal, improving the accuracy and reliability of cotton web status detection and providing high-quality data support for subsequent intelligent calculations. The auxiliary algorithm module integrates feature extraction, similar working condition matching, benchmark value calculation, dynamic correction, and constraint verification to achieve adaptive matching of correction parameters with multiple working conditions and continuously improve the accuracy of cotton web process distance calculation and the rationality of correction actions.

A control device is for controlling an industrial machine. The control device has a display control unit that divides a screen displayed on a display unit into a plurality of regions and displays representations, on the regions, concerning respective motion executions of the machine, a detection unit that, when a plurality of the representations are displayed in a combination, detects operation of a user on the machine or detects a time period in which a display pattern indicating the combination of representations has been displayed without change, and a saving unit that, when the detected operation is a predetermined operation having been set in advance or the display time period of the detected display pattern is equal to or longer than a predetermined time period having been set in advance, saves the display pattern when the detection has been performed as an intended display pattern.

This disclosure relates to a method, apparatus, electronic device, and storage medium for configuring virtual object actions, belonging to the technical field of virtual model processing. The method includes: acquiring action material of a target virtual object output by a user; invoking an intelligent agent to determine a group of motion execution units reflecting the motion relationship chain of the target virtual object in the action material; determining a first motion model matching the motion execution unit group and a mapping unit group mapped by the motion execution unit group on the first motion model in a preset motion model library; and modifying the motion execution unit group relative to the mapping unit group according to the configuration parameters of the action indication output by the user on the mapping unit group to obtain the modified motion execution unit group.

The invention discloses a desktop self-balancing education programming robot based on AI interaction. The system comprises the following modules: A, a visual perception module; b, a voice module; d, data transmission; e, an attitude sensing unit; f, a balance control unit; and G, a motion execution unit. The method has the advantages that natural language instructions, visual programming card recognition and automatic logic generation are fused, human-like communication type programming interaction is achieved, the learning threshold is remarkably lowered, and the method is suitable for being used by all-age users, especially low-age users; through real-time visual identification of a specific programming card and dynamic combination with a voice instruction / programming task, a physical-digital fusion teaching mode which can be flexibly configured and is highly situational is created, and immersion and interactivity of learning are greatly enhanced.

The invention provides a precise sliding table module. The precise sliding table module comprises a supporting component and a sliding table, a motion execution assembly; the motion execution assembly is assembled on the supporting component, and at least part of the motion execution assembly can move on at least one part of the supporting component; a safety monitoring component; the safety monitoring component is arranged on the motion execution component, and the safety monitoring component is used for limiting the travel range of at least partial movement of the motion execution component on at least one part of the supporting component; a precision monitoring component; the precision monitoring component is mounted on the motion execution assembly to monitor the motion precision of the motion execution assembly at least partially within the travel range. According to the precise sliding table module, through the specific structural design, the motion execution assembly, the safety monitoring component and the precision monitoring component are adopted to form a closed-loop system, the motion stability and the motion precision of the precise sliding table module are effectively improved, and therefore the precise sliding table module has a profound influence on industrial modernization development and has a long-term market prospect.

1. Name of the design product: anthropomorphic robot with two arms. 2. Use of the design product: to imitate human arm movements to perform various operations. 3. Design features of the design product: in shape. 4. Picture or photograph best indicating the design features: perspective view.

The application is a kind of self-organizing diffusion method and system for perception-limited cluster robots, belonging to the field of robot technology. The method steps are as follows: installing each single computer perception module; starting diffusion instruction, triggering the motion execution module according to the signal sent by the perception module on the control center of the single computer; the motion execution module performs motion according to the simplified self-organizing diffusion model P=(v o ,ω o ,v l ,L) until there is no perception target within the perception distance of all robots in the cluster, i.e. the diffusion is completed. The application solves the self-organizing diffusion problem of cluster robots in complex environments such as water, which cannot communicate, has no global positioning ability, has very low perception ability, and has very low robot computing power. Whether there is a perception target in the range is used as the diffusion execution condition, which simplifies communication and control equipment, shortens response time, and ensures uniform coverage in the target area and the timeliness of diffusion.

The application provides a method for solving the problem of live tracking gimbal target loss: S1 acquires video image data; S2, tracking condition a: if the determination result is TRUE, directly enter the KCF tracking module, otherwise enter S3 judgment; S3 motor stop state: if TRUE, enter S4, otherwise continue to execute S1; S4 detection link; S5 tracking condition b: if the tracking condition b is TRUE, enter S6, otherwise continue S1; S6 tracking link: including KCF tracking module, tracking verification module, verification frequency setting module and updating tracking condition a; wherein the tracking verification mechanism composed of the tracking verification module and the verification frequency setting module adopts a local CNN human body detection algorithm, verifies the actual size of the human body frame and synchronously updates the KCF parameters, and only performs human body detection in the region of interest; S7, gimbal control link: including calculating gimbal control signal module, motor execution module, acquiring motor state module; and updating motor stop state. Solve the problem of tracking target loss.

The invention relates to the technical field of elderly mobility scooters, in particular to an intelligent elderly mobility scooter system integrating electroencephalogram and electromyographic signal monitoring and multi-mode control, comprising a signal acquisition module used for acquiring an electroencephalogram signal and an electromyographic signal of a user; the signal processing module is used for analyzing and processing the signal and generating control information representing the motion intention and the motion state of the user; the control decision module is used for generating a motion control instruction according to the control information, and limiting, adjusting or suppressing the instruction when it is detected that the electroencephalogram signal and the electromyographic signal do not meet a preset coordination condition; and the motion execution module is used for driving the elderly scooter to execute corresponding advancing, steering or braking operation according to the motion control instruction. Through collaborative acquisition and consistency judgment of the electroencephalogram signals and the electromyographic signals, direct and reliable capture and cross validation of the control intention of the user are achieved, an active safety barrier is constructed fundamentally, and the misoperation risk is remarkably reduced.

In some implementations, a ride control simulation system may receive a request to simulate a ride control system controlling a movement of a passenger vehicle on a ride system, wherein the request includes vehicle information regarding the passenger vehicle and ride system information regarding the ride system. The ride control simulation system may execute, based on the request, a computer model to simulate the ride control system controlling the movement of the passenger vehicle on the ride system. Executing the computer model comprises randomly selecting values from one or more data distributions. The computer model is executed using the first value, the second value, and the third value as inputs. The ride control simulation system may cause an adjustment to an operation of the ride system based on a result of executing the computer model.

The application discloses a motor driving sudden change friction characteristic modeling and feedforward compensation method, which realizes decoupling and independent description of non-sudden change characteristics and sudden change characteristics of friction, and constitutes a dynamic neural network friction model with a width neural network structure which integrates the width neural network structure characteristics and the dynamic recurrent neural network structure characteristics; and the motor control system feedforward control compensation based on the friction model: the motor rotation angle is used as the input signal of the friction model, the friction model obtains corresponding friction torque prediction and estimation, the output of the motor controller is corrected through the feedforward control compensation, and the influence of internal friction on the motor execution precision is offset.

The invention relates to the technical field of artificial intelligence, and discloses an interaction control method based on a spiking neural network, which comprises the following steps: acquiring a multi-modal signal, and preprocessing the multi-modal signal to generate a multi-modal data set; inputting the multi-modal data set into a pulse neural network, and outputting a motion execution instruction and a user intention feature; inputting the multi-modal data set into a pulse convolution capsule network, and outputting an emotion classification result; generating a multi-modal feedback strategy according to an emotion classification result and the user intention features through a pulse reinforcement learning engine; and controlling a robot and / or a mechanical arm to execute actions based on the motion execution instruction, and driving a virtual avatar module and a multi-sensory feedback module to execute an emotional operation in combination with a multi-modal feedback strategy. According to the method, EEG signals and robot sensor data are fused through the pulse neural network, emotion recognition, driving virtual avatar and multi-mode interaction are achieved, and high-emotional and low-burden accompanying experience is provided for the disabled and the like.

The invention discloses an intelligent exterior mirror target centering method based on deep learning. The method comprises the following steps: Step 1, starting a centering function; step 2, carrying out pixel equivalent calculation; step 3, detecting a surgical tool; step 4, carrying out physical offset calculation; and step 5, performing motion execution. The deep learning model is used for automatically detecting the surgical tools in the surgical field, calculating the physical offset and communicating to the manipulator, so that the steps of manual operation in the surgery are reduced, and the automation and intelligence level of the exterior mirror is improved. According to the method, a Base Line model architecture of deep learning is optimized and improved in multiple aspects, and the performance of the model is effectively improved.

The invention provides a control method, a model training method, a robot system and electronic equipment. The control method comprises the steps that terminal state information and environment perception information at the current moment are acquired; the end state information comprises the pose of the end effector in the task space; inputting the end state information and the environment perception information into an action prediction model, and generating action increment prediction of the end effector; wherein the action prediction model is obtained by training based on spatial alignment training data, and the spatial alignment training data is acquired by an acquisition device; based on the current pose and action increment prediction of the end effector in the task space, obtaining a joint space trajectory of the motion execution mechanism; and controlling a motion execution mechanism to execute an action corresponding to the joint space trajectory. The control method can improve the control efficiency of the robot system.

The invention discloses a mechanical arm end tool gravity compensation algorithm, system and device and a storage medium, which are applied to the field of system software, and the method comprises the following steps: obtaining the gravity of a robot end tool; obtaining a zero point value of a force sensor according to the gravity; judging whether the sampling time reaches preset time T or not; if the time T is reached, calculating zero point values within the time T, and taking an average value of the zero point values as a zero point value for starting the force sensor; if not, the zero point value of the force sensor is obtained again; subtracting the gravity and the starting zero point value of the force sensor from the reading of the force sensor to obtain a real external force value; and the mechanical arm moves to execute a corresponding task. According to the method, the mean value within a period of time after the power take-off sensor is started is taken as the zero point value of the starting, the zero point value is calculated once after each time of starting and is taken as the zero point value of the starting, and compared with the prior art that only one fixed zero point value is taken, the method is more accurate.

The invention relates to the field of gesture recognition interaction, in particular to a gesture interaction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a current virtual interaction object; if the left hand and the right hand are both in the preset gesture triggering state, acquiring first motion information of the left hand and the right hand, and determining a current motion execution state according to the first motion information; and based on the motion execution state, obtaining second motion information of the left hand and the right hand, and controlling the current virtual interaction object to move according to the second motion information. Compared with the prior art, judgment of the motion execution state and specific execution are separated, so that execution of specific motion can be carried out based on the currently determined motion execution state every time, and the situation that when the motion execution state and execution are carried out at the same time, the execution time is shortened is avoided. The situation that the motion execution state is misjudged due to shaking of the hands of the user is avoided, so that the interaction experience of the user is effectively improved.

The invention discloses a crown block operation control system which comprises a main program and a real-time processing core used for carrying out motion execution control on a crown block, the main program and the real-time processing core are communicated with a daemon program module, and the daemon program module monitors the operation states of the main program and the real-time processing core and sends the real-time processing core to the main program when it is determined that the main program operates abnormally. And closing the real-time processing core, and restarting the real-time processing core when it is determined that the real-time processing core runs abnormally. The running states of the main program and the real-time processing core are monitored by setting the daemon module, and when the main program is abnormal, the real-time processing core for controlling the crown block to run can be stopped immediately, so that wrong processing of the real-time processing core caused by the abnormality of the main program is avoided, the collision of the crown block can be greatly reduced, and the service life of the crown block is prolonged. And meanwhile, the abnormal condition of the real-time processing core can be timely found and processed, so that the reliable operation of the real-time processing core is effectively ensured.

The invention discloses a spasm detection system and method based on a rehabilitation robot. The system comprises a motion execution module; the information acquisition module is used for acquiring the actual position and the actual output force of the preset part of the motion execution module in the preset time; the motion planning module is used for sending a control signal to the motion execution module or the spasm detection module; the spasm detection module is used for calculating the comprehensive spasm degree of the patient according to the offset between the actual position and the preset position and the difference value between the actual output force and the preset maximum output force, and when the comprehensive spasm degree is larger than the preset comprehensive spasm degree, the motion execution module is controlled to take corresponding spasm treatment measures. The spasm detection module can judge whether the patient has spasm or not based on the offset between the actual position of the preset part and the preset position, so that the rehabilitation robot can be controlled to take corresponding measures, and secondary injury to the patient is avoided.

The invention discloses a rehabilitation robot control system and method in a voice interaction mode, and relates to the technical field of medical instruments.The system is characterized in that a voice interaction system receives and processes a voice instruction of a user to obtain an action instruction; the man-machine interaction system is used for filing according to input personal information, generating a motion gait track of a user, obtaining joint angle track information according to a motion instruction, sending the joint angle track information to the central computing control unit, and recording and displaying joint motor execution data; the central computing control unit receives and processes the joint angle track information, generates a motion task, transmits the motion task to each joint driving and control acquisition system, and feeds back execution data of a joint motor to the man-machine interaction system in real time; and the joint driving and control acquisition systems control the joint motors to execute actions according to the motion tasks and feed back execution data of the joint motors to the central computing control unit. The joint motor is controlled by voice to move according to the intention of a person, so that the dysfunctional person can walk freely.

The invention provides an Alzheimer's disease rehabilitation training system based on a sense-motion-cognition coupling mechanism, which comprises a sense guide module, a motion participation module, a cognition intervention module and a coupling regulation and control module, and is characterized in that the sense guide module is used for providing sense input related to a training task; the exercise participation module is used for guiding the subject to complete an exercise task matched with the sensory stimulation; the cognitive intervention module is used for embedding cognitive processing and task decision links in the sensory-motion interaction process; and the coupling regulation and control module is used for carrying out coordinated regulation on the action sequence, duration and task difficulty of each module according to the reaction state, participation degree or completion characteristics of the subject in the training process, so that a stable, continuous and adaptive coupling relationship is formed in the same training process by sensory input, motion execution and cognitive processing.

The invention discloses a spasm detection system and method based on a rehabilitation robot. The system comprises a motion execution module; the information acquisition module is used for acquiring the actual position and the actual output force of the preset part of the motion execution module in the preset time; the motion planning module is used for sending a control signal to the motion execution module or the spasm detection module; the spasm detection module is used for calculating the comprehensive spasm degree of the patient according to the offset between the actual position and the preset position and the difference value between the actual output force and the preset maximum output force, and when the comprehensive spasm degree is larger than the preset comprehensive spasm degree, the motion execution module is controlled to take corresponding spasm treatment measures. The spasm detection module can judge whether the patient has spasm or not based on the offset between the actual position of the preset part and the preset position, so that the rehabilitation robot can be controlled to take corresponding measures, and secondary injury to the patient is avoided.

To allow for automatically acquiring an instruction to cause a robot to perform basic actions even in situations where various specifications of the robot exist.SOLUTION: A method of automatically acquiring an instruction to an actuator for causing a mobile robot to perform basic actions includes: securing access to sensors by which the robot recognizes an environment, and a plurality elements of an actuator and enumerating combinations between presence / absence of respective control inputs to the plurality of elements and signal types of the control inputs (S41); causing the robot to perform a trial action by performing a control input to the actuator in each of the combinations (S45) and using outputs of the sensors before and after the trial action to identify movements of the robot before and after the trial action (S43, S46, S47); selecting movements corresponding to the basic actions from movements of the robot in the individual combinations (S51); and taking a combination of the selected movements corresponding to the basic actions as an instruction to the actuator for causing the robot to perform the basic actions.SELECTED DRAWING: Figure 4

The application provides a kind of hardware method and system for robot impedance self-adapting visual touch dual-channel control, comprising: obtaining visual data and tactile data, storing the visual data and tactile data and respectively pre-processing;Through convolutional neural network CNN, visual features are extracted and calculated by FPGA DSP unit acceleration, through graph neural network GNN, tactile features are extracted for graph convolution operation;Through the multi-head attention mechanism of Transformer architecture, the visual features and tactile features are weighted and fused to generate global features;According to the global features, control parameters are generated based on Actor-Critic architecture;Based on the control parameters, motor drive signals for robot motion are generated, and motion tasks are realized through motor execution control.The application converts the software operation process of multimodal visual and tactile information into FPGA parallel computing hardware circuit logic, and uses hardware circuit to implement data calculation of multimodal information, with high processing efficiency and less noise between signals.

The invention provides an XY scanning table driven by a magnetic axis. The XY scanning table driven by the magnetic axis comprises an XY scanning table mechanical structure module, an embedded motion control module and a host software system module. The XY scanning table mechanical structure module is used for achieving scanning movement in the X-axis direction and the Y-axis direction and collecting position feedback information in real time. The embedded motion control module is used for receiving a motion control instruction, driving the XY scanning table mechanical structure module to execute a corresponding action and feeding back real-time acquisition position feedback information to the host software system module; the host software system module is used for generating a corresponding motion control instruction according to a processing path or an operation task input by a user, sending the motion control instruction to the embedded motion control module, receiving real-time acquisition position feedback information, and performing analysis and abnormity judgment on a system state; the whole-process closed-loop control from instruction generation to motion execution to state feedback is realized, and the response speed, the positioning precision and the operation stability of the system are remarkably improved.

Exercise instruction systems and methods of use are provided.SOLUTION: A system for exercise instruction comprises a non-transitory computer readable medium configured to store instructions. The system further comprises a processor coupled to the non-transitory computer readable medium. The processor is configured to execute instructions to receive input data from a user, the input data including a plurality of images of the user performing an exercise, and extract pose data from the input data. The processor is configured to execute the instructions to determine whether a difference between the extracted posture data and a reference is less than a predetermined threshold, and in response to the difference being less than the predetermined threshold, determine muscle elongation information from the input data. The processor is configured to execute the instructions to determine feedback to provide to the user to increase a degree of muscle elongation during a subsequent performance of the exercise relative to the determined muscle elongation information.SELECTED DRAWING: Figure 1