本研究研發出一款具有五根軟性手指之機器手，軟性手指的結構是基於PneuNet氣動結構之軟性驅動器為基礎進行設計，並使用ANSYS模擬軟體對其結構進行優化，從而使彎曲性能大幅提升，利用氣壓源驅動手指彎曲，達到擁有五個自由度的軟性機器手的設計目標，此外本研究之軟性手指也搭配氣壓感測器、彎曲感測器這兩種感測器擷取軟性手指的內部壓力、彎曲角度，實現軟性手指壓力與彎曲角度控制。
其次，本研究創新地設計出一套氣動系統，該系統結合了針筒幫浦（Syringe Pump）和曲柄滑塊機構的概念，完成了一套針筒推桿驅動機構，解決傳統針筒幫浦以線性方式推動時，無法呈現線性的壓力曲線問題。這套氣動系統以氣體驅動方式實現軟性手指的彎曲，搭配氣壓感測器做氣壓控制，以線性化的壓力曲線，完成對軟性手指有更好的氣壓控制方法。結合本研究之軟性手指與氣動系統，實現具有五個自由度之軟性機器手。
本研究之軟性機器手可採用皮表肌電訊號進行控制，透過分析使用者皮膚表面的生理訊號來實現。本研究開發的肌電訊號擷取電路，以訊號處理、特徵提取等方法對肌電訊號做處理，並比較KNN、SVM、ANN等分類器的辨識效果，完成以肌電訊號辨識手勢的目標，此方式可使得軟性機器手能夠更加直覺地響應使用者的意圖。

This study presents the development of a robotic hand composed of five soft fingers. The structure of the soft finger was designed based on the soft actuator of the PneuNet pneumatic structure. Utilizing ANSYS simulation software, the structure was optimized to significantly enhance its bending performance. A pneumatic source was employed to drive the bending of the fingers, achieving the design goal of a soft robotic hand with five degrees of freedom. Additionally, this research incorporates pressure and flex sensors in the soft fingers to monitor internal pressure and bending angles, thereby enabling the control of pressure and bend in the fingers.
Furthermore, this study introduces an innovative pneumatic system combining the concepts of a syringe pump and a crank-slider mechanism. This design resulted in a syringe pump drive mechanism that addresses the issue of traditional syringe pumps failing to produce linear pressure curves when driven in a linear manner. The pneumatic system, using air as the driving force, enables the bending of the soft fingers. The system achieves a linearized pressure curve by integrating pressure sensors for pressure control, providing enhanced pneumatic control of the soft fingers. Combining the soft fingers with this pneumatic system, a soft robotic hand with a total of five degrees of freedom is realized.
Moreover, this soft robotic hand can be controlled using surface electromyographic (sEMG) signals by analyzing physiological signals from the user's skin surface. This research developed an EMG signal detection circuit that processes these signals using signal processing and feature extraction methods. It also compares the recognition performance of classifiers like KNN, SVM, and ANN to achieve the objective of gesture recognition via EMG signals. This methodology lets the soft robotic hand intuitively respond to the user's intent.

[1] B. Mosadegh, P. Polygerinos, C. Keplinger, S. Wennstedt, R. F. Shepherd, U. Gupta, J. Shim, K. Bertoldi, C. J. Walsh, and G. M. Whitesides, "Pneumatic Networks for Soft Robotics that Actuate Rapidly," Advanced Functional Materials, vol. 24, no. 15, pp. 2163-2170, 2014, doi: 10.1002/adfm.201303288.
[2] F. Yang, Q. Ruan, Y. Man, Z. Xie, H. Yue, B. Li, and R. Liu, "Design and Optimize of a Novel Segmented Soft Pneumatic Actuator," IEEE Access, vol. 8, pp. 122304-122313, 2020, doi: 10.1109/access.2020.3006865.
[3] S. Chen, F. Chen, Z. Cao, Y. Wang, Y. Miao, G. Gu, and X. Zhu, "Topology Optimization of Skeleton-Reinforced Soft Pneumatic Actuators for Desired Motions," IEEE/ASME Transactions on Mechatronics, vol. 26, no. 4, pp. 1745-1753, 2021, doi: 10.1109/tmech.2021.3071394.
[4] M. S. Xavier, C. D. Tawk, A. Zolfagharian, J. Pinskier, D. Howard, T. Young, J. Lai, S. M. Harrison, Y. K. Yong, M. Bodaghi, and A. J. Fleming, "Soft Pneumatic Actuators: A Review of Design, Fabrication, Modeling, Sensing, Control and Applications," IEEE Access, vol. 10, pp. 59442-59485, 2022, doi: 10.1109/access.2022.3179589.
[5] S. Kandasamy, M. Teo, N. Ravichandran, A. McDaid, K. Jayaraman, and K. Aw, "Body-Powered and Portable Soft Hydraulic Actuators as Prosthetic Hands," Robotics, vol. 11, no. 4, 2022, doi: 10.3390/robotics11040071.
[6] H. Su, X. Hou, X. Zhang, W. Qi, S. Cai, X. Xiong, and J. Guo, "Pneumatic Soft Robots: Challenges and Benefits," Actuators, vol. 11, no. 3, 2022, doi: 10.3390/act11030092.
[7] Lin Li-Ren and Huang Han-Pang, "Integrating Fuzzy Control of The Dexterous National Taiwan University (NTU) Hand," IEEE/ASME Transactions on Mechatronics, vol. 1, no. 3, pp. 216-229, 1996, doi: 10.1109/3516.537044.
[8] 劉立偉, "NTU-Hand 多手指人工義手指之研製與整合," 碩士論文, 國立台灣大學, 民國九十年.
[9] J. Wang, Y. Fei, and W. Pang, "Design, Modeling, and Testing of a Soft Pneumatic Glove With Segmented PneuNets Bending Actuators," IEEE/ASME Transactions on Mechatronics, vol. 24, no. 3, pp. 990-1001, 2019, doi: 10.1109/tmech.2019.2911992.
[10] N. Zhang, L. Ge, H. Xu, X. Zhu, and G. Gu, "3D printed, Modularized Rigid-Flexible Integrated Soft Finger Actuators for Anthropomorphic Hands," Sensors and Actuators A: Physical, vol. 312, 2020, doi: 10.1016/j.sna.2020.112090.
[11] S. Abondance, C. B. Teeple, and R. J. Wood, "A Dexterous Soft Robotic Hand for Delicate In-Hand Manipulation," IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 5502-5509, 2020, doi: 10.1109/lra.2020.3007411.
[12] C. B. Teeple, T. N. Koutros, M. A. Graule, and R. J. Wood, "Multi-Segment Soft Robotic Fingers Enable Robust Precision Grasping," The International Journal of Robotics Research, vol. 39, no. 14, pp. 1647-1667, 2020, doi: 10.1177/0278364920910465.
[13] Y. Yan, X. Chen, C. Cheng, and Y. Wang, "Design, Kinematic Modeling and Evaluation of a Novel Soft Prosthetic Hand with Abduction Joints," Medicine in Novel Technology and Devices, vol. 15, 2022, doi: 10.1016/j.medntd.2022.100151.
[14] H. Liu, C. Wu, S. Lin, Y. Li, and Y. Chen, "Double-Acting Soft Actuator for Soft Robotic Hand: A Bellow Pumping and Contraction Approach," Biomimetics (Basel), vol. 7, no. 4, Oct 20 2022, doi: 10.3390/biomimetics7040171.
[15] A. G. S. Rayo, L. H. H. Gómez, A. T. V. Sánchez, J. A. B. Fernández, J. A. F. Campos, G. U. Calderón, V. M. S. Rayo, and A. E. F. Peñaloza, "Design and Manufacturing of a Dry Electrode for EMG Signals Recording with Microneedles," in Improved Performance of Materials, (Advanced Structured Materials, 2018, ch. Chapter 22, pp. 259-267.
[16] N. Nasri, S. Orts-Escolano, F. Gomez-Donoso, and M. Cazorla, "Inferring Static Hand Poses from a Low-Cost Non-Intrusive sEMG Sensor," Sensors (Basel), vol. 19, no. 2, Jan 17 2019, doi: 10.3390/s19020371.
[17] J. Joo, M. Chen, and H. Liu, "Robot Arm Control Method Using Forearm EMG Signals," MATEC Web of Conferences, vol. 309, 2020, doi: 10.1051/matecconf/202030904007.
[18] S. R. M, P. Fiedler, N. Kuchler, P. D. R, C. Lopes, J. Borges, J. Haueisen, and F. Vaz, "Dry Electrodes for Surface Electromyography Based on Architectured Titanium Thin Films," Materials (Basel), vol. 13, no. 9, May 5 2020, doi: 10.3390/ma13092135.
[19] S. S. Ahmed, A. R. J. Almusawi, B. Yilmaz, and N. Dogru, "Design and Multichannel Electromyography System-Based Neural Network Control of a Low-Cost Myoelectric Prosthesis Hand," Mechanical Sciences, vol. 12, no. 1, pp. 69-83, 2021, doi: 10.5194/ms-12-69-2021.
[20] U. Muhammad, K. A. Sipra, M. Waqas, S. Tu, and A. Koubaa, "POSTER: Human-Robot Interaction: A Myo Armband Using EMG and IMU Signals," presented at the 2020 First International Conference of Smart Systems and Emerging Technologies (SMARTTECH), 2020.
[21] J. A. Ruvalcaba, M. I. Gutierrez, A. Vera, and L. Leija, "Wearable Active Electrode for sEMG Monitoring Using Two-Channel Brass Dry Electrodes with Reduced Electronics," J Healthc Eng, vol. 2020, p. 5950218, 2020, doi: 10.1155/2020/5950218.
[22] S. H. Yeon, T. Shu, E. A. Rogers, H. Song, T. H. Hsieh, L. E. Freed, and H. M. Herr, "Flexible Dry Electrodes for EMG Acquisition within Lower Extremity Prosthetic Sockets," Proc IEEE RAS EMBS Int Conf Biomed Robot Biomechatron, vol. 2020, pp. 1088-1095, Nov-Dec 2020, doi: 10.1109/BioRob49111.2020.9224338.
[23] K. Anam, H. Ismail, F. S. Hanggara, C. Avian, and S. B. Worsito, "Cross Validation Configuration on k-NN for Finger Movements using EMG signals," presented at the 2021 International Conference on Instrumentation, Control, and Automation (ICA), 2021.
[24] N. Malesevic, A. Olsson, P. Sager, E. Andersson, C. Cipriani, M. Controzzi, A. Bjorkman, and C. Antfolk, "A Database of High-Density Surface Electromyogram Signals Comprising 65 Isometric Hand Gestures," Sci Data, vol. 8, no. 1, p. 63, Feb 18 2021, doi: 10.1038/s41597-021-00843-9.
[25] M. Gomez-Correa and D. Cruz-Ortiz, "Low-Cost Wearable Band Sensors of Surface Electromyography for Detecting Hand Movements," Sensors (Basel), vol. 22, no. 16, Aug 9 2022, doi: 10.3390/s22165931.
[26] X. Hu, A. Song, J. Wang, H. Zeng, and W. Wei, "Finger Movement Recognition via High-Density Electromyography of Intrinsic and Extrinsic Hand Muscles," Sci Data, vol. 9, no. 1, p. 373, Jun 29 2022, doi: 10.1038/s41597-022-01484-2.
[27] M. Karrenbach, P. Preechayasomboon, P. Sauer, D. Boe, and E. Rombokas, "Deep Learning and Session-Specific Rapid Recalibration for Dynamic Hand Gesture ecognition from EMG," Front Bioeng Biotechnol, vol. 10, p. 1034672, 2022, doi: 10.3389/fbioe.2022.1034672.
[28] C.-H. Liu, L.-J. Chen, J.-C. Chi, and J.-Y. Wu, "Topology Optimization Design and Experiment of a Soft Pneumatic Bending Actuator for Grasping Applications," IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2086-2093, 2022, doi: 10.1109/lra.2022.3142910.
[29] H. Zhang, A. S. Kumar, F. Chen, J. Y. H. Fuh, and M. Y. Wang, "Topology Optimized Multimaterial Soft Fingers for Applications on Grippers, Rehabilitation, and Artificial Hands," IEEE/ASME Transactions on Mechatronics, vol. 24, no. 1, pp. 120-131, 2019, doi: 10.1109/tmech.2018.2874067.
[30] F. Chen, W. Xu, H. Zhang, Y. Wang, J. Cao, M. Y. Wang, H. Ren, J. Zhu, and Y. F. Zhang, "Topology Optimized Design, Fabrication, and Characterization of a Soft Cable-Driven Gripper," IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 2463-2470, 2018, doi: 10.1109/lra.2018.2800115.