臺灣博碩士論文加值系統

　　教育代理人（Pedagogical Agent）是目前智慧型機器人研究中的一個重要發展方向，我們將教育代理人視為應用在教學領域上的虛擬角色（Virtual Characters）；在過去種種相關的研究都指出虛擬角色的確在教學上有所助益，但也由於虛擬角色往往被侷限在平面的電腦當中，部分使用者認為虛擬角色不過是一台電腦，造成使用者與虛擬角色之間的互動不夠真實，因而對互動功能與服務有所排斥，使得本來虛擬角色應該產生的幫助因此減少或消失，故近幾年來虛擬角色的發展漸漸朝向實體化發展。

　　虛擬角色朝向實體化發展雖能改善應有的效果，但相關研究也指出，不論虛擬角色是否實體化成機器人，由於其內建的行為模式固定，並無法像人一樣有豐富的行為變化，在經過一段時間後使用者便會對其失去興趣，將虛擬角色丟棄一旁；　因此，許多研究人員投入相關的研究，希望讓使用者與虛擬角色能建立更長久的關係。

　　本研究期望能設計一教育代理人與學生的互動方式，透過其有意義及豐富的互動變化，讓學生能對虛擬角色的行為產生回應，並能與之建立更長久關係，進而達到輔助學習的目的。

　　Pedagogical Agent is an important development of intelligent robot research. Many related various researching point out that the Virtual Character certainly has quite assist in teaching and learning. However the virtual character has been restricted on the computer platform, so some of the user may consider the victual character is merely a computer and reject to accept the function and service it supplied. For the reason, some of the benefit it provides is reduce and disappear. Therefore, the development of victual character is to make it materialization. To make victual character materialization will improve the problem. But related research had point out that in spite of the victual character is material or not, human will be uninterested and put it away as time pass through because of its invariable actions. Therefore, the objective of this research is not only make victual character can be accepted, but design a standard rule to keep a long relationship between robot victual character and student.

目錄
書名頁﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅰ
論文口試委員審定書﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅱ
授權書﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅲ
中文提要﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅳ
英文提要﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅴ
致謝﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅵ
目錄﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅶ
表目錄﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅸ
圖目錄﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒Ⅸ
第一章　緒論
１.１　研究背景﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒1
１.２　研究動機﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒2
１.３　研究目標﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒6
１.４　研究流程﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒7
１.５　研究架構﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒8
第二章　相關研究
２.１　數位遊戲的設計﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒9
２.２　如何使虛擬角色的行為有意義﹒﹒﹒﹒﹒﹒﹒﹒﹒9
２.３　如何使使用者對虛擬角色有道德感﹒﹒﹒﹒﹒﹒﹒10
２.４　合作學習﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒11
２.５　機器學習﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒11
第三章　研究問題與研究假設
３.１　研究問題﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒12
３.２　研究假設 （research hypotheses）﹒﹒﹒﹒﹒﹒12
３.３　研究問題與量測數據﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒13
第四章　系統設計
４.１　系統資源﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒14
４.２　系統架構﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒16
４.３　活動流程﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒17
４.４　智慧型代理人架構﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒23
４.５　人工智慧設計﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒24
第五章　實驗
５.１　實驗對象﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒28
５.２　實驗流程﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒28
５.３　實驗方法﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒29
５.４　實驗結果﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒30
５.５　實驗結果分析﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒39
５.６　實驗畫面﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒40
第六章　結論與建議﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒42
參考文獻﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒43
附錄﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒45

表目錄
表一　量測變項表﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒13
表二　AIBO操作動作表﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒19
表三　Concept Learning的正例與反例﹒﹒﹒﹒﹒﹒﹒﹒﹒24
表四　互動次數統計表﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒31
表五　實驗一問卷﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒33
表六　拒絕次數統計表﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒34
表七　實驗二問卷（信任度）﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒35
表八　實驗三問卷﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒38
表九　實驗三問卷２﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒38

圖目錄
圖一　　熱門的智慧型代理人﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒3
圖二　　研究動機示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒5
圖三　　研究流程圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒7
圖四　　機器狗AIBO結構圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒15
圖五　　活動場景示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒16
圖六　　質數山攀爬方式示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒17
圖七　　互動方式示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒18
圖八　　遠端控制介面 ﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒18
圖九　　兒童端的遊戲介面﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒21
圖十　　遊戲動畫小狗圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒22
圖十一　代理人系統架構圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒23
圖十二　質數判斷方式的示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒26
圖十三　質數學習方式的示意圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒27
圖十四　實驗流程圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒28
圖十五　學生與具有學習能力的AIBO互動次數﹒﹒﹒﹒﹒﹒31
圖十六　學生與不具有學習能力的AIBO互動次數﹒﹒﹒﹒﹒31
圖十七　學生與AIBO互動次數之比較圖﹒﹒﹒﹒﹒﹒﹒﹒﹒32
圖十八　AIBO選擇了質數，學生拒絕其選擇的頻率﹒﹒﹒﹒34
圖十九　AIBO選擇了非質數，學生拒絕其選擇的頻率﹒﹒﹒35
圖二十　活動實景圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒40
圖二十一　實驗場景圖﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒﹒41

1.A. Gulz, M. Haake, Virtual pedagogical agents – design guidelines regarding visual appearance and pedagogical roles, Current Developments in Technology-Assisted Education (2006), p1848-1852.
2.Bargh, J. A. & Schul, Y, On the cognitive benefits of teaching. Journal of Educational Psychology (1980), v72, n5, p593-604.
3.Barry Kort, Rob Reilly, Rosalind Picard, An affective model of the interplay between emotions and learning.
4.Baylor A. (2001) Permutations of control: Cognitive guidelines for agent-based learning environment. Journal of Interactive Learning Research 12, 403 – 425.
5.Bickmore, T. and Picard, R, Establishing and Maintaining Long-Term Human-Computer Relationships, ACM Transactions on Computer-Human Interaction, Vol. 12, No. 2, June 2005, Pages 293–327.
6.Bickmore, T., Caruso, L., Clough-Gorr, K., and Heeren, T. (2005) “It’s just like you talk to a friend” – Relational Agents for Older Adults” Interacting with Computers.
7.Bickmore, T. and Picard, R, “Towards Caring Machines.” CHI’04, Vienna.
8.Ball & Breese (2000), Modeling a user''s emotion and personality in a computer user interface.
9.Conati, C., 2002. Probabilistic assessment of user''s emotions in educational games, Applied AI 16 7–8, pp. 555–576.
10.G. E. Hall & S. M. Hord, Change in Schools : Facilitating the Process, p.60.
11.James C. Lester, Animated Pedagogical Agents: Face-to-Face Interaction in Interactive Learning Environments. International Journal of Artificial Intelligence in Education (2000) 11,47-78.
12.K. Ryokai, C. Vaucelle, J. Cassell (2003), Virtual Peers As Partners In Storytelling And Literacy Learning.
13.Kaplan et al., Taming robots with clicker training: A solution for teaching complex behaviors, in: Proceedings of the European Workshop on Learning Robots, 2001.
14.Melson, Gail F., Peter H. Kahn, Jr., Alan M. Beck, Batya Friedman, Trace Roberts, and Erik Garrett. “Robots as Dogs? – Children’s Interactions with the Robotic Dog AIBO and a Live Australian Shepherd.” CHI 2005. ACM, 2005: 1649-52.
15.Oviatt, S. and B. Adams (2000). Designing and evaluating conversational interfaces with animated characters. Embodied Conversational Agents. J. Cassell, J. Sullivan, S. Prevost and E. Churchill. MIT Press.
16.Prensky, M. (2001). Digital Game-Based Learning. New York: McGraw-Hill.
17.R. Luckin, D. Connolly, L. Plowman & S. Airey, Children''s interactions with interactive toy technology. Volume 19 Issue 2 Page 165-176, June 2003.
18.Thomas J. Berndt, Children''s Friendships: Shifts Over a Half-Century in Perspectives on Their Development and Their Effects. Journal article by Thomas J. Berndt; Merrill-Palmer Quarterly, Vol. 50, 2004
19.Tom M. Mitchell, CH2: concept learning and the general-to-specific ordering, in Machine Learning, P20-51.
20.張霄亭 (1995), 教學媒體與教學新科技。