A two-layer fuzzy kernel regression (TLFKR) model is proposed for understanding human emotional intention in human-robot interaction, where TLFKR model consists of two layers, including fuzzy c-means (FCM) with kernel...
详细信息
A two-layer fuzzy kernel regression (TLFKR) model is proposed for understanding human emotional intention in human-robot interaction, where TLFKR model consists of two layers, including fuzzy c-means (FCM) with kernel ridge regression (Kernel 1) for information analysis layer, fuzzy support vector regressions (FSVR) (Kernel 2) for intention understanding layer. TLFKR model represents the weight impact for each emotional information and aims to improve smooth human-robot interaction by endowing robot with human emotional intention understanding capability. Experimental Results show that the proposal obtains an intention understanding accuracy of 65.67%/68.33%/80.67% with the clusters number c=2/3/6 (according to different genders/ages/nationalities), which are 7.34%/7.18%/8.67% and 18.67%/21.33%/33.67% higher than that of TLFSVR and SVR, respectively. Additionally, preliminary application experiments are performed in the developing emotional social robot system, where two mobile robots and volunteers experience a scenario of "drinking at a bar", and social robots are able to express basic emotions and understand human order intention.
The purpose of this study was to investigate the features of muscle fatigue extracted from surface electromyography (sEMG) signals of lower limbs, and then to present an evaluation method of lower-limb rehabilitation ...
详细信息
The purpose of this study was to investigate the features of muscle fatigue extracted from surface electromyography (sEMG) signals of lower limbs, and then to present an evaluation method of lower-limb rehabilitation to provide physical basis for the training effect of rehabilitation. Four healthy young university students were invited to perform a pedaling exercise for 40 days. The sEMG signals of four lower-limb muscles are recorded and processed using a Butterworth filter and a Daubechies 10 wavelet. Then, the change of the ratios of the spectrums of Types I and II muscle fibers to the total number of the spectrum along the exercise are examined. The time of the first intersection of the ratios for Types I and II for each muscle is used as a performance index. The increase in the time at the beginning and the end of the training period indicates the improvement of motor function, and thus it verifies the effectiveness of the rehabilitation.
Music-playing robots have been gradually applied to art performance, music education and so on. This paper introduces a special robot playing dulcimer, a kind of Chinese traditional musical instrument. With mechanical...
详细信息
ISBN:
(纸本)9781509015740;9781509015733
Music-playing robots have been gradually applied to art performance, music education and so on. This paper introduces a special robot playing dulcimer, a kind of Chinese traditional musical instrument. With mechanical characteristics taken into accounted, an assignment method of performance task and an inverse kinematics control algorithm of redundant robot manipulators are proposed in this paper. Based on these studies, a performance controlsystem is developed, which can parse a given MIDI file, perform task allocation, and control the dual mechanical arms holding bamboo hammers to strike the strings of dulcimer. The experimental test shows that the performance controlsystem is able to control the dulcimer music-playing robot to complete music performance in real-time in a humanized way.
Data mining is one hot orientation in today’s research *** activity recognition is meaningful in our daily living and is a significant aspect in data *** previously research is almost based on tri-axial *** paper pre...
详细信息
ISBN:
(纸本)9781509009107
Data mining is one hot orientation in today’s research *** activity recognition is meaningful in our daily living and is a significant aspect in data *** previously research is almost based on tri-axial *** paper presents a novel method to collect data from both accelerometer and gyroscope using *** daily activities including Walking,Running,Upstairs,Downstairs,Standing,Sitting and Cycling,a total of seven categories are *** raw data from MEMS are recorded by smartphone according to different daily *** improve the accuracy of classification for daily activities,this paper combines time-series features with wavelet coefficients to extract *** recognize these activities,the support vector machine is used to finish this ***,we compare the accuracy with other machine learning methods,such as k-nearest neighbor algorithm and neural network or decision *** result indicates that our method can achieve nearly 96%classification accuracy for the seven kinds of daily activities.
The controller parameters can not perform well in the combustion process of coke oven, caused by the fluctuating calories of fuel gas, the changes of coking time and many other exogenous disturbances. In this paper, a...
详细信息
ISBN:
(纸本)9781509015740;9781509015733
The controller parameters can not perform well in the combustion process of coke oven, caused by the fluctuating calories of fuel gas, the changes of coking time and many other exogenous disturbances. In this paper, an optimal method based on performance monitoring by using the trend extraction method, is raised to adjust the parameters of the controllers in the combustion process of coke oven. Firstly, because of the mixture of different kinds of error, the trend extraction method is used to separate trend component from original signal. Secondly, the monitoring indices are designed to examine whether the monitored controller parameters are suitable in the current situation. Then, the performance monitoring result is utilized to choose the decision vector of optimization and determine whether optimization is needed. Finally, simulation results demonstrate that our method performs well in the optimization for combustion process of coke oven in spite of massive changes in the calories of fuel gas.
In this paper, the problem of mean square exponential stabilization for sampled-data Markovin jump systems is studied. A time-scheduled Lyapunov functional consisting of a exponential-type looped function is construct...
详细信息
In this paper, the problem of mean square exponential stabilization for sampled-data Markovin jump systems is studied. A time-scheduled Lyapunov functional consisting of a exponential-type looped function is constructed using segmentation technology and linear interpolation. Based on this new Lyapunov functional, a less conservative mean square exponential stability criterion is obtained such that a bigger maximum decay rate can be easily calculated. Meanwhile, the quantitative relationship among some system parameters, maximum sampling period, and decay rate is established. Moreover, a time-dependent state feedback sample-data controller is designed. Significant improvements of the proposed exponential-type time-scheduled Lyapunov functional method over some existing ones are verified by numerical examples.
Coordinated target tracking for a team of two heterogeneous Unmanned Aerial Vehicles(UAVs) is *** order to study the coordinated relationship by means of distances of UAV-to-target and UAV-to-UAV,a constraint of dista...
详细信息
ISBN:
(纸本)9781509009107
Coordinated target tracking for a team of two heterogeneous Unmanned Aerial Vehicles(UAVs) is *** order to study the coordinated relationship by means of distances of UAV-to-target and UAV-to-UAV,a constraint of distances coordination is *** from the traditional studies that focus on angular separation or communication connectivity for UAVs,this constraint takes the effect of geometric configuration for two UAVs coordination into ***,the constraint only applies to follower UAV,aiming to obtain its optimal coordinated distance to *** this way,accuracy of target state estimation and optimal geometric configuration of target tracking for UAVs are *** Information filter is used to estimate the target location on a 2-D plane,and a receding horizon approach is applied to generate the optimal control policy for two UAVs' *** results illustrated the effectiveness.
In a drilling process, stick-slip vibrations are one of the main resources resulting in unstable motions or drillstring failures. In this paper, combined with a LuGre bit-rock interaction, the drillstring system is mo...
详细信息
ISBN:
(纸本)9781509015740;9781509015733
In a drilling process, stick-slip vibrations are one of the main resources resulting in unstable motions or drillstring failures. In this paper, combined with a LuGre bit-rock interaction, the drillstring system is modeled as lumped parameters to capture the main features of stick-slip vibrations. Then, a novel control configuration involving five modules is developed in order to track a desired speed while suppressing the vibration, where the equivalent-input-disturbance method is skilfully employed to suppress such vibrations. In such five modules, the state observer is combined with the friction estimator to obtain the equivalent friction torques, which are corresponding to downhole frictions, on the surface control platform. In addition, the internal model and the state feedback are utilized to get the speed tracking torques so as to guarantee the desired tracking precision. Based on the dual conversion and two quadratic performances, the closed-loop stability is guaranteed by appropriate design of the controller and observer's gain matrices. Simulation is conducted to compare our method with an LQR method, showing our method's superiority and effectiveness.
To solve the problem of the visual navigation for mobile robot in dynamic environment,a visual navigation system for mobile robot with Kinect camera is ***,the improved RBPF(RAO Blackwellized particle filters) algorit...
详细信息
ISBN:
(纸本)9781509009107
To solve the problem of the visual navigation for mobile robot in dynamic environment,a visual navigation system for mobile robot with Kinect camera is ***,the improved RBPF(RAO Blackwellized particle filters) algorithm is used to build the 2D grid map of the indoor environment and on the basis of this map operation of inflating obstacles is applied to build the global grid map considering the actual size of the ***,cost map using motion primitives is built while using this cost map,anytime Repairing A*(ARA*) global path planning algorithm,which has property of anytime algorithm,is combined with Dynamic Window Approach(DWA) local path planning algorithm to plan a smooth path from start point to target point and generate the optimal control input for robot ***,the adaptive monte carlo localization method(KLD-Sampling) is used to locate the robot and then a visual navigation system for mobile robot with Kinect camera is *** indoor mobile robot navigation experiment results show that the designed robot navigation system can plan a smooth path which is in accordance with robot kinematics and autonomously avoid the static and moving obstacles in the environment.
To solve the robot visual servoing problem in the natural scene,a robot visual sliding servoing method using SIFT features in the framework of epipolar-geometry-based visual servoing is ***,corresponding image feature...
详细信息
ISBN:
(纸本)9781509009107
To solve the robot visual servoing problem in the natural scene,a robot visual sliding servoing method using SIFT features in the framework of epipolar-geometry-based visual servoing is ***,corresponding image feature points from the current image feature and the desired image are obtained by SIFT algorithm;Then the features error of the whole robot visual servoing system are calculated according to the corresponding points;Finally,considering characteristics of epipolar geometry for robot visual servoing system,the rotation sliding mode controller and translation sliding mode controller are sequentially designed to calculate the rotation movement and translation movement of the robot *** positioning experiments on a 6DOF industrial robot demonstrate that the proposed method can effectively locate an object in the natural scene.
暂无评论