由於人們對於人文科技的意識上揚，因此老人照護的問題也逐漸被重視，因此本論文所設計的機器人並針對長者陪伴設計情境，並且以雲端技術的方式建構多機器人的服務平台；長者陪伴機器人系統可分為伺服器端以及機器人端的開發設計，再伺服器端我們建構了兩種雲端服務： (1) 網頁監控管理服務：此項服務主要目的是為了提供使用者，便於網頁管理並監控機器人系統的服務。(2) 機器人多模互動運算服務：此項服務提供機器人聲音及影像運算的服務，例如：語音辨識、語者辨識、人臉身份辨識、語音合成。機器人端則開發使用伺服器所提供的服務以達到長者陪伴的應用，我們依照以上的架構實現了兩台機器人(達芬奇及羅伯特)，並且使用低成本、省電型之處理核心，配合無線網路與伺服器連結並可達到即時的人機互動服務，最後設計了五種長者陪伴的使用情境，並且於長者使用平分獲得4.24的分數(滿分為5分)。

Senior people often live along at home and have to be autonomous, and moreover, they often feel the lack of emotions or emotional interactions, such as loneliness, participations and insecurity in family and community. Thus, society and the community have to be prepared to face the phenomenon of aging society to allow senior people to live their life in the best possible conditions.
This paper presents a human-robot interactive system for senior companion based on cloud computing. The proposed multi-robot senior companion system (MRSCS) is implemented based on cloud information network. In the server side, two cloud services are proposed, 1) the web-based user remote management service (WURMS) for remote robot control and, 2) the robotic multimodal interactive computation services (RMICS) for the human-robot interactive interfaces. The human-robot interactive interfaces provide four interactive computations including speech/sound recognition, speaker identification, face identification and text to speech (TTS). In the robot client side, the specific behavior model is designed to use the WURMS and the RMICS services. The robots in this system design have the advantage in low-cost, low-power and low-computation, and achieve real-time human-robot interaction through cloud computing with wireless communication.
In experiments, the two robots, Robert and Davinci, are modified for the fixed area in small space and for living room in the house, respectively. For simulation, we also design five scenarios in the experiments to show how effective to improve the feeling emotions for senior people: home appliance control (improving autonomy and insecurity), spiritual companion (improving loneliness), medical service (improving autonomy and insecurity), daily information (improving loneliness and participation) and dual-robots application (improving loneliness and participation). Five users score these five scenarios with answer the question by five point scales to evaluate the Mean Opinion Score (MOS), and the final average MOS is 4.24. Therefore, the multi-robot senior companion system based on cloud computing is acceptable.

[1] Anthony Fleury, Michel Vacher, and Norbert Noury, “SVM-Based Multimodal Classification of Activities of Daily Living in Health Smart Home: Sensor, Algorithms, and First Experimental Results,” IEEE Transactions on Information Technology in Biomedicine, Vol. 14, pp. 274 - 283, March 2010.
[2] ABI research, “Personal Robotics,” Task, Security and Surveillance/Telepresence, Entertainment, Education Robots and Components https://www.abiresearch.com/research/1003675-Personal+Robotics?ll
[3] Kazuyoshi Wada and Takanori Shibata, “Living With Seal Robots—Its Sociopsychological and Physiological Influences on the Elderly at a Care House,” IEEE Transactions, Robotics, Vol.23, pp. 972 – 980, Oct. 2007.
[4] T. S. Perry, “Tools & toys: Pleo, the poop-free pet,” IEEE Spectr., vol. 45, pp. 24, Apr. 2008.
[5] R. M. Jiang, A. H. Sadka, and D. Crookes, “Multimodal Biometric Human Recognition for Perceptual Human–Computer Interaction,” IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, issue. 6, vol. 40, pp. 676-681, Nov 2010.
[6] V.Yu. Budkov, M.V. Prischepa, A.L. Ronzhin, A.A. Karpov. “Multimodal Human-Robot Interaction,” 2010 International Congress, International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), pp. 485 – 488, Oct. 18-20 2010
[7] Erico Guizzo, “Robots with their heads in the clouds,” IEEE Spectr., Robotics, issue. 3, vol. 48, March 2011.
[8] From Wikipedia, http://en.wikipedia.org/wiki/Paro_(robot)
[9] From Wikipedia, http://en.wikipedia.org/wiki/Pleo
[10] Hugo Pinto, Yorick Wilks, and Roberta Catizone, “The senior companion multiagent dialogue system,” to appear in Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multi-Agent Systems, Portugal, 2008
[11] Donglin Wang, Henry Leung, Ajeesh P. Kurian, Hye-Jin Kim, and Hosub Yoon, “A Deconvolutive Neural Network for Speech Classification With Applications to Home Service Robot,” IEEE Transactions, Instrumentation and Measurement, issue. 12, vol. 59, pp. 3237 – 3243, Dec. 2010
[12] K. Kawamura, R. T. Pack and M. Iskarous, “Design Philosophy for Service Robots,” IEEE International Conference, Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., vol. 4, pp. 3736 – 3741, 22-25 Oct 1995
[13] Gi Hyun Lim, Student Member, IEEE, Il Hong Suh, Senior Member, IEEE, and Hyowon Suh, “Ontology-Based Unified Robot Knowledge for Service Robots in Indoor Environments,” IEEE Transactions, Systems, Man and Cybernetics, Part A: Systems and Humans, issue. 3, vol. 41, pp. 492 – 509, May 2011
[14] Amazon ec2. amazon elastic compute cloud [online]. http://aws.amazon.com/ec2/, 2009.
[15] Google app engine [online]. http://code.google.com/appengine/, 2009.
[16] RoboEarth, http://www.roboearth.org/
[17] ASORO, http://www.asoro.a-star.edu.sg/
[18] David Gouaillier, Vincent Hugel, Pierre Blazevic, Chris Kilner, Jerome Monceaux, Pascal Lafourcade, Brice Marnier, Julien Serre, Bruno Maisonnier, “Mechatronic design of NAO humanoid,” IEEE International Conference, Robotics and Automation, 2009. ICRA '09., pp. 769 – 774, 12-17 May 2009.
[19] S. Knerr, L. Personnaz, and G. Dreyfus, “Single-layer learning revisited: A stepwise procedure for building and training a neural network,” in Neurocomputing: Algorithms, Architectures and Applications. Berlin, Germany: Springer-Verlag, 1990.
[20] P. Viola and M.J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," in Proceedings of the IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 511-518, Dec. 2001.
[21] T Yoshimura, K Tokuda, T Masuko, "Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis," in Proc EUROSPEECH-99, pp. 2374–2350, Sept. 1999.
[22] Jung-Yun Wu, ” Pitch Prediction Using Prosody Hierarchy and Dynamic Features for HMM-based Mandarin Speech Synthesis”, 2008
[23] Bicentennial Man (film) from Wikipedia, http://en.wikipedia.org/wiki/Bicentennial_Man_(film)