臺灣博碩士論文加值系統

近年來，人口老化的問題日益嚴重，照顧銀髮族的生活起居成為一個重要的課題。隨著銀髮族年齡的增長，骨質疏鬆、膝關節退化、肌肉萎縮等相關老化問題相繼的產生，常會導致下肢行走不穩，甚至跌倒受傷等嚴重問題，所以如何輔助老年人行走就變成了一個重要的研究課題。隨著醫療科技的進步，各式各樣輔助老年人行走的助行器發展也越趨成熟，本論文開發了一台主動式智慧型助行器以用來應對銀髮族生活不便的困擾。在本論文中，我們透過一台微控制器整合智慧型助行器上面安裝的各式功能模組作為控制驅動層，以一台筆記型電腦作為處理核心，以分散式處理的概念對控制驅動層的微控制器下達命令，完成循跡導航、避障、意圖偵測、自我定位以及充電站這些功能。經實驗測試結果，循跡導航的成功率達到100%，行動意圖的辨識正確率也達到了99.97%，助行器也能夠準確的駛入充電站，充電模組偏移距離不超過±3mm，此助行器的平均反應時間約為0.95秒，考慮到使用者族群為年長者，助行器的延遲時間在可以接受的範圍內。在未來則希望可以將標線偵測的方式改進，並將處理核心的筆記型電腦轉換成平板電腦的形式以更加方便助行器的行走與使用者的操作。

In recent years, the problem of population aging is becoming more and more serious, caring for the life of the elderly is an important issues. With the growth of the age of the elderly, osteoporosis, knee degeneration, muscle atrophy, and other related aging problems, often lead to lower extremity walking instability, and even fall injured and other serious problems, so how to assist the old people to walk becomes an important research issues. With the development of medical science and technology, a variety of aids to help the elderly to walk more mature, this research developed an active intelligent Walker to deal with the problems of the elderly life. In this paper, we use a microcontroller to integrate the intelligent Help-line device installed on the various functional modules as a control drive layer, with a notebook computer as the processing core, the concept of distributed processing to control the driving layer of the microcontroller command, complete tracking navigation, avoid obstacles, intent to detect, Self-positioning and charging stations for these functions. Experimental results showed that the success rate of tracking navigation was 100%, the correct rate of action intention is also reached 99.97%, the help line can also accurately enter the charging station, charging module offset distance of not more than ±3mm, the average reaction time of this device is about 0.95 seconds, taking into account the user community for the elderly, The delay time of the support line is within an acceptable range. In the future, it is hoped that the way of marking detection can be improved, and the notebook computer that handles the core will be converted to the form of a tablet computer, so that the walker can walk more smoothly and facilitate the user's operation.

目 錄
摘 要 I
目 錄 II
表目錄 IV
圖目錄 V
第一章 導論 1
1.1. 研究動機 1
1.2. 研究目的 3
1.3. 論文結構 3
第二章 文獻探討 4
2.1 被動式智慧助行器 4
2.2 主動式智慧助行器 9
第三章 系統架構與功能控制流程 18
3.1 助行器平台與系統方塊圖 19
3.1. 人機介面層電腦控制流程圖 21
3.2 控制驅動層微處理器控制流程圖 25
第四章 智慧助行器功能設計 29
4.1 自主循跡導航 29
4.2 無線射頻識別自我定位 35
4.3 避障 37
4.4 使用者行動意圖偵測 40
4.5 無線感應式充電站 45
第五章 實驗與結果 50
5.1 系統操作介面介紹 50
5.2 循跡導航實驗 52
5.3 意圖偵測實驗 54
5.4 無線充電站實驗 56
5.5 實際整合測試 58
第六章 結論 61
參考文獻 63

表目錄

表1. 被動式助行器特點對照表 9
表2. 主動式助行器特點對照表 16
表3. 主要的控制模式與對應的控制訊號 25
表4. 雷射測距儀(URG-04LX)位置與資料對應[22] 39
表5. 無線充電發送/接收端技術參數[35] 47
表6. 弱分類器結果 56


圖目錄
圖1-1.市售助行器(圖片來源：網路) 2
圖1-2. 朝陽科技大學銀髮園實際測試 3
圖2-1. (a)RT-Walker (b)搭載伺服煞車器的後輪[6] 5
圖2-2. DFKI iWalker[7] 5
圖2-3. Rollator Walker[8] 6
圖2-4. 智慧助行器[9] 7
圖2-5. RT Walker[10] 8
圖2-6. Walkmate [11] 10
圖2-7. Walbot [12] 11
圖2-8.智慧助行器JARoW[13] 12
圖2-9. GaitAid Walker (a)PD使用者正在使用聽覺提示(b)視覺提式(c)按照指示開始復健行走[14] 13
圖2-10. UFES Smart Walker[15] 14
圖2-11. ISR-AIWALKER[16] 15
圖2-12. Standing assistive walker[17] 15
圖3- 1. 智慧助行器平台 19
圖3- 2. 系統方塊圖 21
圖3- 3. 人機介面層電腦端主系統流程圖 22
圖3- 4. 定位與目的地偵測事件流程圖 23
圖3- 5. 避障程式流程圖 24
圖3- 6. 控制驅動層Arduino微控制器控制流程 26
圖4- 1. 控制驅動層整合電路實際接線圖 30
圖4- 2. 控制驅動層整合電路實作結果 30
圖4- 3. 陣列循跡感測器[18] 31
圖4- 4. BS2微控制器[19] 31
圖4- 5. HB-25馬達控制器[20] 32
圖4- 6. 直流馬達輪組[21] 33
圖4- 7. 循跡導航的Arduino流程圖 35
圖4- 8. RFID讀取模組的連接電路圖 36
圖4- 9. RFID感測程式流程圖 37
圖4- 10. HOKUYO雷射測距儀(URG-04LX)[22] 38
圖4- 11. 雷射測距儀測量範圍[22] 38
圖4- 12. 雷射測距儀偵測範例 39
圖4- 13. 實體壓力感測器安裝示意圖 41
圖4- 14. 意圖偵測模組連接電路圖 41
圖4- 15. 意圖偵測模組程式流程圖 45
圖4- 16. 無線充電原理 46
圖4- 17. 無線感應充電模組[35]，(a)發送模組，(b)接收模組。 46
圖4- 18. 充電管理模組 47
圖4- 19. 金屬感應近接開關[38] 48
圖4- 20. 無線充電站，(a)充電站，(b)助行器上近接開關與充電接收模組，以及(c)無線充電示意圖 49
圖5- 1. 智慧助行器【設定】頁面的連結COM port部份。 51
圖5- 2. 智慧助行器【開始】頁面。 52
圖5- 3. 循跡導航測試連續影像 53
圖5- 4. 分類器訓練結果一 54
圖5- 5. 分類器訓練結果二 55
圖5- 6. 無線充電測試連續影像 57
圖5- 7朝陽銀髮園實驗場景平面圖與軌跡示意圖 58
圖5- 8. 智慧助行器實際測試影像 59

[1]The website of the Executive Yuan Economic development committee, 2017/05/19, [Online]. Available: http://www.cepd.gov.tw/.
[2]The website of the Ministry of Interior Accounting office, 2017/08/15, [Online]. Available: http://www.moi.gov.tw/stat/.
[3]Y. Hirata, S. Komatsuda and K. Kosuge, “Fall prevention control of passive intelligent walker based on human model,” IEEE/RSJ International Conference on Intelligent Robots and Systems, Sept 22-26 2008, Nice, France.
[4]W.-Y. Lee, S.-H. Lee, M.-S. Jang and E.-H. Lee, “A study on methods for improving the straightness of the intelligent walker to move on slope,” The 10th International Conference on Ubiquitous Robots and Ambient Intelligence, Oct 30-Nov 2 2013, Jeju, Korea(South).
[5]S. L. Grondin and Qingguo Li, “Intelligent control of a smart walker and its performance evaluation,” IEEE International Conference on Rehabilitation Robotics, June 24-26 2013, Seattle, Washington USA.
[6]S. Taghvaei, Y. Hirata, K. Kosuge, “Vision-based human state estimation to control an intelligent passive walker,” IEEE/SICE International Symposium on System Integration, Dec 21-22 2010, Sendai, Japan.
[7]M. Ibraheem, “Gyroscope-enhanced dead reckoning localization system for an intelligent walker,” International Conference on Information, Networking and Automation, Oct 18-19 2010, Kunming, China.
[8]Mitesh Patel, Jaime Valls Miro and Gamini Dissanayake , “A hierarchical hidden Markov model to support activities of daily living with an assistive robotic walker,” IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, June 24-27 2012, Roma, Italy.
[9]Georgia G. Chalvatzaki, Georgios Pavlakos, Kevis Maninis, “Towards an intelligent robotic walker for assisted living using multimodal sensorial data,” 2014 EAI 4th International Conference on Wireless Mobile Communication And Healthcare (Mobihealth), Nov 3-5 2014, Athens, Greece.
[10]Sajjad Taghvaei, Yasuhisa Hirata, Kazuhiro Kosuge, “Visual human action classification for control of a passive walker,” 2017 7th International Conference on Modeling Simulation, and Applied Optimization (ICMSAO), April 4-6 2017, Sharjah, United Arab Emirates.
[11]Fei Shi, Qixin Cao, Chuntao Leng and Hongbing Tan, “Based on force sensing-controlled human-machine interaction system for walking assistant robot,” The 8th World Congress on Intelligent Control and Automation, July 6-9 2010, Jinan, China.
[12]Kai-Tai Song, and Sin-Yi Jiang, “Force-cooperative guidance design of an omni-directional walking assistive robot,” IEEE International Conference on Mechatronics and Automation(ICMA), August 7 - 10 2011, Beijing, China.
[13]Geunho Lee, Takanori Ohnuma, Nak Young Chong, and Soon-Geul Lee, “Walking Intent-Based Movement Control for JAIST Active Robotic Walker,” IEEE Transactions On Systems, Man, And Cybernetics: Systems, Vol. 44, No. 5, pp. 665 - 672, May 2014.
[14]Chung Dial Lim, Chia-Ming Wang, Ching-Ying Cheng, “Sensory Cues Guided Rehabilitation Robotic Walker Realized by Depth Image-Based Gait Analysis,” IEEE Transactions On Automation Science And Engineering, Vol. 13, No. 1, pp. 171 - 180, January 2016.
[15]Carlos A. Cifuentes, Camilo Rodriguez, Anselmo Frizera-Neto, “Multimodal Human–Robot Interaction for Walker-Assisted Gait,” IEEE Systems Journal, Vol. 10, No. 3, pp. 933 – 943, Sep 2016.
[16]J. Paulo,L. Garrote and C. Premebida, “An innovative robotic walker for mobility assistance and lower limbs rehabilitation,” 2017 IEEE 5th Portuguese Meeting on Bioengineering (ENBENG), Feb 16-18 2017, Coimbra, Portugal.
[17]Shohei Kawazoe, Daisuke Chugo, Sho Yokota, “Development of standing assistive walker for domestic use,” 2017 IEEE International Conference on Industrial Technology (ICIT), March 22-25 2017, Toronto, Canada.
[18]QTR-8A Reflectance Sensor Array, Pololu Inc, 2017/05/19, [Online]. Available: https://www.pololu.com/docs/0J12.
[19]Basic stamp microcontrollers, Parallax Inc, 2017/05/19, [Online]. Available: https://www.parallax.com/catalog/microcontrollers/basic-stamp.
[20]HB-25 motor controller, Parallax Inc., 2017/05/19, [Online]. Available: https://www.parallax.com/product/910-29144.
[21]Motor mount and wheel kit, Parallax Inc., 2017/05/19, [Online]. Available: https://www.parallax.com/product/28962.
[22]URG-04LX-UG01 Scanning range finder, Hokuyo Inc., 2017/05/19, [Online]. Available: https://www.hokuyo-aut.jp/02sensor/07scanner/urg_04lx_ug01.html.
[23]Yu-Hong Chen, Hang-Ting Lin and Siou-Jing Lin, “Compare two methods of analyzing human intent in steering a passive walker,” 2013 International Conference on Advanced Robotics and Intelligent Systems (ARIS), May 31-June 2 2013, Tainan, Taiwan.
[24]Flexiforce Sensor, Parallax Inc., 2017/05/19, [Online]. Available: https://www.parallax.com/product/30056.
[25]Y. Freund and R. E. Schapire, “Experiments with a new boosting algorithm,” Proceedings of the 13th Conference on Machine Learning, July 03-06 1996, San Francisco, CA, USA.
[26]Y. Freund and R. E. Schapire, “A decision-Theoretic Generalization of on-line learning and an application to boosting,” Journal of Computer and System Science, Vol. 55, No. 1, pp. 119-139, December 1997.
[27]朝陽銀髮園, 2016/2/1, [Online]. Available: http://120.110.28.107/m_senior/.
[28]Ibrahim Al-Bahadly, Peter Murphy, Khalil Alkhumaisi, “Force based pain sensing in animals using stepping motor,” 2013 Seventh International Conference on Sensing Technology (ICST), Dec 3-5 2015, Wellington, New Zealand.
[29]W.-C. Cheng and D.-M. Jhan, “A Cascade Classifier Using Adaboost Algorithm and Support Vector Machine for Pedestrian Detection,” 2011 IEEE International Conference on Systems, Man and Cybernetics (SMC-IEEE2011), Oct. 9-11 2011, Alaska, USA.
[30]W.-C. Cheng and D.-M. Jhan, “Triaxial Accelerometer-Based Fall Detection Method Using a Self-Constructing Cascade-AdaBoost-SVM Classifier” IEEE Journal of Biomedical and Health Informatics, Vol. 17, no. 2, pp. 411 – 419, March 2013.
[31]W.-C. Cheng and D.-M. Jhan, “A self-constructing cascade classifier with AdaBoost and SVM for pedestriandetection,” Engineering Applications of Artificial Intelligence, Vol. 26, no. 3, pp. 1016-1028, August 2013.
[32]IRIN Bandyopadhyaya, Dennis Babu, Anirudh Kumar, Joydeb Roychowdhury, “Tactile sensing based softness classification using machine learning” 2014 IEEE International Conference on Advance Computing Conference (IACC), Feb. 21-22 2014, Durgapur, India.
[33]Michael Burke, Bruce Murphy, Dermot Geraghty, “Measurement of sub-bandage pressure during venous compression therapy using flexible force sensors,” 2014 IEEE International Conference on Sensors, Nov. 2-5 2014, Valencia, Spain.
[34]Anindya Nag, and Subhas Chandra Mukhopadhyay, “Occupancy Detection at Smart Home Using Real-Time Dynamic Thresholding of Flexiforce Sensor,” IEEE sensors journal, Vol. 15, no. 8, pp. 4457-4463, August 2015.
[35]青岛帕沃思智能科技有限公司, 2017/05/19, [Online]. Available: https://shop1466398073631.1688.com/.
[36]PBASIC Programming, 2017/05/19, [Online]. Available: https://en.wikibooks.org/wiki/PBASIC_Programming.
[37]電子工程世界, 2017/05/19, [Online]. Available: http://www.eeworld.com.cn/
[38]陽明電機股份有限公司, 2017/05/19, [Online]. Available: http://www.fotek.com.tw/
[39]長庚大學RFID資源中心, 2017/06/09, [Online]. Available: http://ee.cgu.edu.tw/bin/home.php
[40]樂齡網, 2017/12/04, [Online]. http://www.ez66.com.tw/