Unlock instant, AI-driven research and patent intelligence for your innovation.

A motion state recognition method for an upper limb-assisted exoskeleton robot

An exoskeleton robot and motion state technology, applied in the field of robotics, can solve the problems of low adaptability, weak electromyographic signals, and low signal accuracy, and achieve the effects of improving classification accuracy, good adaptability, and improving safety.

Active Publication Date: 2022-07-29
NORTHWESTERN POLYTECHNICAL UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, Tao Jun of Zhejiang University has done some research on the recognition method of exoskeleton motion state (Tao Jun. Research on Human-machine Cooperative Motion Control of Pneumatically Assisted Exoskeleton Robot [D]. Zhejiang University, 2018.), which assists the upper limb of exoskeleton Some use EMG signals and SVMs to identify and judge motion states, but human EMG signals are weak, and EMG sensors are easily interfered by external factors, and the signal accuracy is not high; in addition, the key parameters of SVMs are It is set in advance, and the best parameters cannot be selected according to various actions in the assisting process, and the adaptability is low
Invention patent CN112336340A discloses "a human body motion intention recognition method for a waist-assisted exoskeleton robot" that can accurately distinguish four motion states of bending over, standing upright, walking with the left leg and walking with the right leg, but does not consider the differences between the motion states Is there a security issue with conversion

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A motion state recognition method for an upper limb-assisted exoskeleton robot
  • A motion state recognition method for an upper limb-assisted exoskeleton robot
  • A motion state recognition method for an upper limb-assisted exoskeleton robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] like image 3 , using MATLAB / Simulink to carry out the experimental simulation analysis of the classification accuracy of the F-HSVM method.

[0071] In this example, the data is continuous motion data, and the motion state distribution sequence is 0→1→2→1→2→1→0 (0 represents the relaxed state, 1 represents the rotational assist state, and 2 represents the maintain assist state). exist Figure 4 and Figure 5 Among them, the abscissa represents the sampling point, the ordinate represents the classification label, "·" represents each sampling point and its corresponding actual state value, and "○" represents each sampling point and its corresponding predicted state value. By comparison, it can be seen that the recognition rate of the ovo-SVM algorithm for the relaxed state and the rotational assist state is not high, and it is easy to produce the phenomenon that the rotational assist is sometimes absent in practical applications. The F-HSVM method can accurately classi...

Embodiment 2

[0073] MATLAB / Simulink is used to test the processing ability of F-HSVM method for outliers, and simulation experiments are carried out on the data set with abnormal state transition.

[0074] In this example, the data is the exercise data added to the abnormal state transition, that is, the data of the relaxed state and the power-assisted state are communicated. The state distribution sequence is 0→1→2→0→2→1→0, where 0 (relaxed state) and 2 (keep assisting state) are forbidden to reach each other in the finite state machine. In this case, the algorithm should put the system The state is adjusted to 3 (warning state warning), and the system emergency stops when the number of consecutive warning states reaches a threshold (set to 20 in the experiment).

[0075] Depend on Figure 5 It can be obtained that the algorithm can accurately predict the motion state for the sampling points between 0 and 150. When the state of the provided sample point changes from 2 to 0, the transiti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a motion state recognition method of an upper limb-assisted exoskeleton robot, which combines a one-to-one support vector machine (ovo-SVM) optimized by harmony search (HS) with a finite state machine (FSM). The state machine FSM classifies the finite motion state of the robot exoskeleton, and formulates the finite motion state conversion relationship; then collects the robot data through sensors and classifies the robot state, and uses the majority voter mechanism for the data state in the sliding window along the time axis. , take the most as the estimated value of the current system state; then judge the accessibility of the state before and after the system, and use the HSVM algorithm to reclassify the same data state with the largest number in the current sliding window to determine the final robot motion state. The method of the invention can not only improve the classification accuracy, but also can change the parameter value according to the change of the situation, and has strong robustness and good adaptability to the uncertain factors of the system.

Description

technical field [0001] The invention belongs to the technical field of robots, and in particular relates to a method for identifying a motion state of a robot. Background technique [0002] The upper limb-assisted exoskeleton robot has made some progress in the mechanical structure and motion control algorithm, but how to effectively arrange the sensor network of the exoskeleton robot, how to collect the movement information of the exoskeleton in real time, and how to accurately measure the movement state of the exoskeleton in real time It is still the key and difficult point in the design process of the upper limb-assisted exoskeleton robot to ensure the smooth, stable and safe operation of the assisting process. [0003] At present, Tao Jun of Zhejiang University has done some research on the recognition method of exoskeleton motion state (Tao Jun. Research on Human-Machine Coordinated Motion Control of Pneumatic Assisted Exoskeleton Robot [D]. Zhejiang University, 2018.),...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): B25J9/16
CPCB25J9/1664B25J9/1615B25J9/1628
Inventor 袁小庆方甫君张家坤王文东赵艺林
Owner NORTHWESTERN POLYTECHNICAL UNIV