Jianhe Lei

Research on the Surface EMG Signal for Human Body Motion Recognizing Based on Arm Wrestling Robot

In this paper, the surface electromyographic (EMG) signals is acquired from the upper limb when the experimenter competes with the arm wrestling robot (AWR) which is integrated with mechanical arm, elbow/wrist force sensors, servo motor, encoder, 3D MEMS accelerometer, and USB camera. The arm wrestling robot (AWR) is intended to play arm wrestling game with human on a table with pegs for entertainment and human upper limbs muscle modeling. As the EMG signal is a measurement of the anatomical and physiological characteristic of the given muscle, the macroscopical movement patterns of the human body can be classified and recognized. By using the method of wavelet packet transformation (WPT), the high-frequency noises can be eliminated effectively and the characteristics of EMG signals can be extracted. Auto-regressive (AR) model is adopted to effectively simulate the stochastic and non-stationary time sequences using a series of AR coefficients with a typical order. Artificial neural network (ANN) is utilized to distinguish the different force levels and game grades in the scenario of arm-wrestling. To advance the training speed and accurate rate of the motion pattern classification, back-propagation (BP) neural network based on adaptive learning rate algorithm (ALR) is introduced. The advantage of ALR algorithm compared with standard BP algorithm is confirmed by experiments

Application of Neural Network to Nonlinear Static Decoupling of Robot Wrist Force Sensor

The static coupling of wrist force sensor is a major influencing factor to its measuring precision. Aiming at resolving the disadvantages such as low decoupling precision of the traditional method, we put forward a nonlinear decoupling method based on neural network. The major idea applied is to use the BP network to realize the mapping from input to output of the sensor. Owing to BP networks good nonlinear mapping ability, the decoupling result can reach an arbitrary precision theoretically. The effectiveness of this method was verified in the calibration of wrist force sensor of a force sensing system for an underwater robot gripper. The decoupling results demonstrate the validation of neural network method

Prediction of Human Elbow Torque from EMG Using SVM Based on AWR Information Acquisition Platform

In this paper a novel prediction method of elbow torque from EMG signal using SVM is proposed. How to model the relations between EMG signals and various kinematical aspects of the movement behavior is a difficult problem in the researches of neurophysiology and biomechanics. Traditional prediction methods include using neural networks to model the relations. However, these methods suffer from several problems, such as local minima, the difficulty of the selection of the model, etc. To address these problems, support vector machine is adopted to construct the nonlinear model. The efficiency of our proposed method is proved by experiment results.

Multi-Camera Based Robot Visual Servoing System

A multi-camera based robot visual servoing system is proposed. It consists of a puma 562 robot manipulator with a camera attached on the end-effector and an active stereovision rig over the head of the robot manipulator. The models of camera-manipulator of the visual servoing system are derived. Simulations are conducted in support of the theoretical analysis. A visual servoing system is constructed by real robot platform

Design, Fabrication and Application of ARm Wrestling Robot

This paper presents a novel 2 DOF robotic arm wrestling system integrated with mechanical arm, elbow/wrist force sensors, servo motor, encoder, 3-D MEMS accelerometer, and USB camera. The arm wrestling robot (AWR) is used to play arm wrestling game with human for entertainment. Based on the force testing equipment, we acquire the data of surface electromyographic (EMG) signals form target muscle when a real player competes with the robot. Wavelet transform and neural network are applied to extract the characteristics of EMG signals and estimate the joint torque. Experiment results have proved the validation of the wavelet neural network method

Application of SVM in intelligent robot information acquisition and processing: a survey

SVM (support vector machines) is a new machine learning technique developed on statistical learning theory and has attracted more and more attentions. For machine learning tasks involving pattern classification, multi sensors information fusion, non-linear system control, etc, SVMs have become increasingly popular tools. In this paper, we survey the recent new development on the research and application of SVM in intelligent robot information acquisition and processing. Some important issues and the directions of further research are pointed out also.

The Design and Implementation of Arm Wrestling Robot

In this paper, we develop a 2-DOF robot system for arm wrestling with human. By using the sensor system, we analyze the changes in surface electromyographic (EMG) signal associated with V, a, angle of players response to forced actions. The joint elbow torque is estimated by artificial neural network. We also propose a humanoid algorithm using torque estimated via ANN and the effectiveness of the method is confirmed

Recognition method of throwing force of athlete based on multi-class SVM

A novel recognition method of throwing force of athlete combined with wavelet and multi-class support vector machine is introduced in the paper, which is based on the analysis of motion characters of gliding shot put. Utilizing the digital shot based on a three dimensional accelerometer, we get the three dimensional throwing forces in real time. Through wavelet transform, the general characteristics of force information are picked up. Then the general characteristics are input into the classifier for recognition of throwing force curves. The analysis provides the scientific basis for the motion training and instruction of shot put. The experiment shows that the method not only has high anti-noise ability and improves the recognition efficiency, but also decreases the burden of system and improves the recognition speed.

Analysis of GRF by Means of Wavelet Transform for the Performance Diagnosis of Weight Lifter

Weightlifting is one of the most physically demanding sports. A successful lift is influenced by many factors. Among them, the ground reaction force (GRF) which is exerted on weight lifers during the motion process is crucial to the performance of a weight lifer, so the acquisition and analysis of GRF is very important to the scientific research of weightlifting. This paper describes GRF acquisition using a force platform and analysis by means of wavelet transform (WT) for the performance diagnosis of weight lifters. The differences of GRF between the skilled weight lifters and the learners are reported. The method allows to detect and to quantify details not easily perceivable by coaches through traditional techniques. By wavelet transform of the GRF, it is possible for biomechanics experts to analysis mechanical behaviours of athletes and to direct them to improve their skills. GRF acquisition and analysis provides a very important tool for modern athletes training.

Research on a Throwing Multidimensional Force Sensing System for Advanced Training of Shot-Put Athletes

In this paper, we develop a novel digital-shot system for sensing the throwing force information of shot-put athletes in real time. The digital-shot has been designed and manufactured with the same external dimensions and weight as the normal shot for open females. The three axes integrated accelerometer, as a crucial device in the force sensing system, can acquire the kinetics data along three orthogonal directions with reasonably high accuracy. By using the method of wavelet transformation, the characteristics of acceleration signals during the shot-put period can be extracted. Artificial neural network is adopted to recognise the movement pattern in different phases of shot throwing. For supplying more effective training instruction, with the help of six axes ground reaction force measuring apparatus, high-speed photography and surface electromyographic signal remote measuring device etc, an integrated platform of shot-put athlete biomechanical information acquisition is constructed. Based on the fusion of multi-targets and multi-parameters information, the shot-put athletes coaching system is proposed, which not only can supply constructive guidance for athletes to improve their skills, but also provide a new research platform of motion human modeling.