7.1 結論
本論文主要目的在於設計一個機器人召喚系統,讓機器人偵測到使用者召喚 訊號後,機器人可以不受環境距離、障礙物等影響,順利找到使用者,並且移動 到使用者面前。
首先,本論文採用 CC2431 定位引擎來進行室內定位,透過交叉式的參考點 佈置,估測出使用者位置,讓機器人透過自主導航系統來前往使用者,實驗結果 顯示,在 8 個參考點的定位環境下,CC2431 定位引擎的平均定位誤差為 1.3 公 尺左右,此距離已經足夠讓 Kinect 感測器擷取到使用者,並且透過影像來追蹤 使用者。
本論文提出的自我定位系統,整合里程計與 CC2431 定位引擎之定位資訊,
可以改善機器人因為移動過久、運作時間過長所產生的定位誤差,實驗結果顯 示,在 13 個參考點的定位環境下,機器人移動 60 公尺後的平均定位誤差為 68 公 分,表示自我定位系統可以有效地減少機器人自身定位的誤差,對於需要尋找長 距離的使用者之情況下,機器人不會迷失自身座標,有助於召喚任務之達成。
透過 Kinect 感測器所提供的深度影像,使用使用者產生器來偵測使用者人 形,並且計算使用者人形的質心座標,同時,透過 Kinect 感測器所提供的彩色 影像,使用 Haar-Like Features 人臉偵測與人臉膚色密度來偵測使用者人臉,並 且計算使用者人臉的中心座標與人臉寬度,將這些影像資料進行整合後,透過本 論文設計的影像追蹤控制器,讓機器人可以修正自身方向來朝向使用者前進,並 且在適當的距離下,停在使用者面前。
本論文將導航控制系統當作基礎,整合自我定位系統與影像追蹤控制器,讓 機器可以閃避環境中的障礙物,並且有效地降低機器人自身定位的誤差,還能影 像偵測使用者,讓機器人可以修正自身方向來朝向使用者前進,在適當的距離 下,停在使用者面前,實驗結果顯示,在 12 個參考點的定位環境下,機器人可
以找到距離 35 公尺的使用者,並且機器人停在使用者面前的平均距離為 68 公 分,而機器人面對使用者正面的平均角度差為 30°,表示機器人能順利找到使用 者,並且停在使用者面前,完成召喚任務。
7.2 未來工作
機器人召喚系統還有一些地方值得進一步研究:
在影像方面,機器人雖然可以偵測出多個使用者,但是卻無法知道哪位使用 者才是真正召喚機器人的使用者,所以可以進一步整合影像辨識功能,讓機器人 在多人環境下,可以找出真正召喚機器人的使用者。此外,加入使用者側面或是 使用者的背後等影像偵測,可以幫助機器人找到不同站姿的使用者。
在自我定位系統方面,機器人雖然透過 CC2431 定位引擎所提供的絕對座標 來修正自身座標,但是卻沒有絕對角度來修正機器人的朝向角θ,所以可以使用 影像校正方式,讓機器人每次任務結束後,回到休息站來進行影像校正機器人的 朝向角θ。此外,對於融合里程計與 CC2431 定位引擎之定位資訊是透過模糊邏 輯系統來決定融合數值,這是一種經驗法則,不是最佳比例的融合數值,所以使 用 Extended Kalman Filter 來找出最佳比例的融合數值,可以使得自我定位系統達 到最佳化。
使用同時定位與地圖建立(Simultaneous Localization And Mapping, SLAM)技 術於機器人自我定位,其定位誤差會比使用無線感測網路定位機器人來得小許 多,不僅解決機器人自我定位問題,透過建立環境地圖也幾乎解決機器人導航問 題,所以使用 SLAM 技術,可以讓機器人自我定位更準確,順利導航到使用者 身邊,有助於召喚任務之達成。此外,機器人有了環境地圖後,加入一個實用的 路徑規劃系統,可以幫助機器人在複雜環境下,快速找到使用者。
參考文獻
[1] Kai-Tai Song, Chi-Yi Tsai, Fu-Sheng Huang, Jung-Wei Hong, Chen-Yang Lin, Chun-Wei Chen and Zhi-Sheng Lin, “Development of the robot of living aid:
RoLA,” in Proc. of IEEE International Conference on Automation and Logistics (IEEE ICAL),pp. 443-448, Qingdao, China, Sep. 2008.
[2] Yoo Oh, Jae Yoon, Ji Park, Mina Kim and Hong Kim, “A name recognition based call-and-come service for home robots,” in IEEE Transactions Consumer Electronics, vol.54, no.2, pp.247-253, May 2008.
[3] B. C. Park, K. D. Ban, K. C. Kwak, and H. S. Yoon, “Sound source localization based on audio-visual information for intelligent service robots,” Int. Symposium on Advanced Intelligent Systems, pp.364-367, Sep. 2007.
[4] Suk Lee, Kyoung Nam Ha and Kyung Chang Lee, "A pyroelectric infrared sensor-based indoor location-aware system for the smart home," in IEEE Transactions Consumer Electronics, vol.52, no.4, pp.1311-1317, Nov. 2006.
[5] Guangming Song, Jun Zhang, Xiaofeng Ye, Yanpeng Niu and Aiguo Song,
"Wireless sensor and actuator network system for calling home robots," in Proc.
of IEEE International Conference Information and Automation (IEEE ICIA), pp.1553-1558, Harbin, China, June 2010.
[6] Guolin Sun, Jie Chen, Wei Guo and K. J. Ray Liu, "Signal processing techniques in network-aided positioning: a survey of state-of-the-art positioning designs," in IEEE Signal Processing Magazine, vol.22, no.4, pp.12-23, July 2005.
[7] F. Gustafsson and F. Gunnarsson, "Mobile positioning using wireless networks:
possibilities and fundamental limitations based on available wireless network measurements," in IEEE Signal Processing Magazine, vol.22, no.4, pp.41-53, July 2005.
[8] Dae Geun Hwang, Jae Ho Hwang, Sung Jeen Jang and Jae Moung Kim, "A fast ToA position estimation technique based on MHP pulse," in Proc. of International Symposium Communications and Information Technology(ISCIT), pp.1472-1476, Korea, Sep. 2009.
[9] F. Gustafsson and F. Gunnarsson, "Positioning using time-difference of arrival measurements," in 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.6, pp. VI- 553-6, April 2003.
[10] Rong Peng and M.L. Sichitiu, "Angle of arrival localization for wireless sensor networks," in 2006 3rd Annual IEEE Communications Society on Sensor and Ad Hoc Communications and Networks, Reston, pp.374-382, VA, USA, Sep. 2006.
[11] Jeffrey Hightower and Gaetano Borriello, “A Survey and Taxonomy of Location Sensing Systems for Ubiquitous Computing”, Technical Report UW CSE 01-08-03, University of Washington, Department of Computer Science and Engineering, Washington, 2001.
[12] P. Bahl and V. N. Padmanabhan, "RADAR: an in-building RF-based user location and tracking system ," in Proc. of IEEE INFOCOM 2000. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies, pp.775-784, Tel Aviv, 2000.
[13] K. Kaemarungsi and P. Krishnamurthy, "Properties of indoor received signal strength for WLAN location fingerprinting," in Proc. of The First Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services, Boston, Massachusetts, pp.14-23, USA, Aug. 2004.
[14] B. Li, J. SALTER, A. G. DEMPSTER and C. RIZOS, "Indoor positioning techniques based on Wireless LAN," in Wireless Broadband & Ultra Wideband Communications, pp.13-16, March 2006.
控制工程研究所碩士論文,2005.
[16] K. Aamodt, "CC2431 Location Engine," Texas Instruments, July 2006.
[17] "A True System-on-Chip solution for 2.4 GHz IEEE 802.15.4 / ZigBee datasheet," Texas Instruments, 2009.
[18] Li Wenzhong, “ZigBee 2006 wireless networks and wireless location Combat,”
Beijing University of Aeronautics and Astronautics Press, 2008.
[19] Liyuan Li, Hoe J. K. E., Shuicheng Yan, and Xinguo Yu, "ML-fusion based multi-model human detection and tracking for robust human-robot interfaces," in Applications of Computer Vision, pp.1-8, Dec. 2009.
[20] Keita Itoh, Takashi Kikuchi, Hiroshi Takemura and Hiroshi Mizoguchi,
"Development of a person following mobile robot in complicated background by using distance and color information," in The 32nd Annual Conference of the IEEE Industrial Electronics Society, pp.3839-3844, Paris, Nov. 2006.
[21] 台灣 Kinect 官網
http://www.xbox.com/zh-TW/Kinect
[22] Kinect technical details
http://www.play.com/Games/Xbox360/4-/10296372/Project-Natal/Product.html
[23] Open NI
http://openni.org/
[24] 透過 OpenNI / NITE 分析人體骨架
http://kheresy.wordpress.com/2011/01/28/detecte_skeleton_via_openni_part1/
[25] OpenCV
http://sourceforge.net/projects/opencvlibrary/
[26] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. I-511-I-518, 2001.
[27] Rainer Lienhart and Jochen Maydt. “An Extended Set of Haar-like Features for Rapid Object Detection,” in Proc. of International Conference on Image Processing, pp. 900-903, 2002.
[28] M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, “Skin detection in video under changing illumination conditions,” in Proc. of 15th International Conference on Pattern Recognition, pp. 839-842, Istanbul, Turkey, 2000.
[29] C. C. Chiang, W. K. Tai, M. T. Yang, Y. T. Huang and C. J. Huang, “A Novel Method for Detecting Lips, Eyes and Faces in Real Time,” Real-Time Imaging, vol. 9, no. 4, pp. 277-287, 2003.