Experimental Validation of Speech Improvement-Based Stratified Adaptive Finite-Time Saturation Control of Omnidirectional Service Robot

Hwang, Chih‐Lyang; Weng, Fan-Chen; Wang, Dingsheng; Wu, Fan

doi:10.1109/tsmc.2020.3018789

Cited by 11 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(iii) After the preprocessing of the speech command, SRCN-WSCR is similar to SRCN-DFER. Furthermore, the confusion matrices with background noises and without background noise confirm its superiority in comparison to some previous research (e.g., multiclass SVM [19]). (iv) The implementation of human-robot collaboration confirms the practicality and feasibility of the proposed method.…”

Section: Introductionsupporting

confidence: 79%

“…The experimental setup of the omnidirectional service robot (ODSR) in Fig. 1(a) consists of the following five parts [19]: (i) three dc servomotors, (ii) one motion control module, (iii) a laptop for image processing, (iv) a stereo camera system, and (v) a Bluetooth earphone. The adaptive stratified finite-time saturated control (ASFTSC) ut, i = 1,2,3 [18], [19] is computed in the Intel® Atom N2600.…”

Section: Experimental Setup and Problem Description A Experimental Setupmentioning

confidence: 99%

“…If a face candidate exists, the detected face using Haar Cascade feature descriptor is cropped as a suitable size to recognize his/her face emotions. If not, the strategy to approach the above pose region is achieved by the stereo vision based localization [16]- [17] and an stratified finitetime saturated control [18], [19]. Subsequently, the facial emotion is recognized by the SRCN-DFER.…”

Section: Introductionmentioning

confidence: 99%

“…At the outset, the sampled speech command is transferred into the frequency domain signal by Short-Time Fourier Transform (STFT) with suitable window length and hop length. Multiplying the power spectrum of STFT signal by Mel filter matrix obtains the logarithm of Mel-Spectrogram [19], which is set as the input signal of SRCN-WSCR. Since the video sequence for facial emotion is limited, the large amount of facial emotion images is applied to train the CNN, which is the first part of SRCN.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Human–Robot Collaboration Using Sequential-Recurrent-Convolution-Network-Based Dynamic Face Emotion and Wireless Speech Command Recognitions

Hwang

Deng

2023

IEEE Access

View full text Add to dashboard Cite

The proposed sequential recurrent convolution network (SRCN) includes two parts: one convolution neural network (CNN) and a sequence of long short-term memory (LSTM) models. The CNN is to achieve the feature vector of face emotion or speech command. Then, a sequence of LSTM models with the shared weight reflects a sequence of inputs provided by a (pre-trained) CNN with a sequence of input sub-images or spectrograms corresponding to face emotion and speech command, respectively. Simply put, one SRCN for dynamic face emotion recognition (SRCN-DFER) and another SRCN for wireless speech command recognition (SRCN-WSCR) are developed. The proposed approach not only effectively tackles the recognitions of dynamic mapping of face emotion and speech command with average generalized recognition rate of 98% and 96.7% but also prevents the overfitting problem in a noisy environment. The comparisons among mono and stereo visions, Deep CNN, and ResNet50 confirm the superiority of the proposed SRCN-DFER. The comparisons among SRCN-WSCR with noise-free data, SRCN-WSCR with noisy data, and multiclass support vector machine validate its robustness. Finally, the human-robot collaboration (HRC) using our developed omnidirectional service robot, including human and face detections, trajectory tracking by the previously designed adaptive stratified finite-time saturated control, face emotion and speech command recognitions, and music play, validates the effectiveness, feasibility, and robustness of the proposed method.

show abstract

Section: Introductionsupporting

confidence: 79%

Section: Experimental Setup and Problem Description A Experimental Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human–Robot Collaboration Using Sequential-Recurrent-Convolution-Network-Based Dynamic Face Emotion and Wireless Speech Command Recognitions

Hwang

Deng

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Two lemmas describing the fixed-time strategy, the linearly parameterized of RNN's approximation error, and mathematical description of directed graph among agents are discussed in this subsection. Lemma 1 ([22], [32]- [46]): Consider a dynamic system ( ) ( ),…”

Section: A Mathematical Preliminariesmentioning

confidence: 99%

Recurrent Neural Network With Fractional Learning-Based Fixed-Time Formation Tracking Constrained Control for a Group of Quadrotors

et al. 2021

Self Cite

View full text Add to dashboard Cite

In this paper, each agent is modeled by the mechanical motion dynamics with the velocity transformation between quadrotor and world coordinates such that trajectory planning and obstacle avoidance are easily accomplished. It is assumed that at least one follower tracks the leader with a specific position, and the other followers maintain the relative position among each other or the leader. If obstacles hinder the motion of the original formation, a piecewise straight-line formation is employed to avoid these obstacles. To fulfill these tasks under the uncertain dynamics, the recurrent neural network with fractional learning-based fixed-time formation tracking constrained control (RNNFL-FTFTCC) is designed by nonlinear filtering error with dynamic fraction order, time-varying switching gain, and recurrent neural network learning compensation of dynamic lumped uncertainties in each quadrotor. The simulations with the initial formation error, the formation change in a narrow space, and the target point approach validate the effectiveness and robustness of the proposed formation control. Moreover, the comparisons among nonadaptive, RNN, and multilayer perceptron network (MLPN) compensations confirm the effectiveness and efficiency of fractional learning.

show abstract

Cooperation of robot manipulators with motion constraint by real-time RNN-based finite-time fault-tolerant control

Hwang

2023

Neurocomputing

View full text Add to dashboard Cite

Experimental Validation of Speech Improvement-Based Stratified Adaptive Finite-Time Saturation Control of Omnidirectional Service Robot

Cited by 11 publications

References 35 publications

Human–Robot Collaboration Using Sequential-Recurrent-Convolution-Network-Based Dynamic Face Emotion and Wireless Speech Command Recognitions

Human–Robot Collaboration Using Sequential-Recurrent-Convolution-Network-Based Dynamic Face Emotion and Wireless Speech Command Recognitions

Recurrent Neural Network With Fractional Learning-Based Fixed-Time Formation Tracking Constrained Control for a Group of Quadrotors

Cooperation of robot manipulators with motion constraint by real-time RNN-based finite-time fault-tolerant control

Contact Info

Product

Resources

About