在機器人研究領域中，許多研究者已在研究開發和人類互動並能執行日常家庭工作任務的服務型機器人。為了能使不同的開發人員和終端使用者之間共享和重複使用機器人程式碼，本論文利用標準的Web界面與服務導向機制來創建一套可重用與分享的機器人服務模式。研究架構包括上層提供知識本體論的服務規劃組合和下層使用類神經網路的學習策略進行機器人控制。除此之外，也開發了服務發現、服務選擇、服務組合和服務重新配置等相關服務的功能，以利機器人自動化服務。
在本論文中所提出的上層知識本體論，不僅提供了機器人面臨家庭環境的空間知識，也為機器人處理日常家庭生活任務提供行動準則。而使用高效率的階層式規劃方法 (HTN)，規劃器可以利用相關的領域知識和本體論中定義的相關技術來實現所應用的任務。另一方面，使用遞迴式類神經網路（RNN）來建立下層的機器人控制器並利用服務描述語言將它包裝成新的服務以供上層服務規劃組合使用。也就是說，首先以示範的方式教導機器人進行動作程序，收集機器人表現出的行為序列資料，然後使用遞迴式類神經網路建立機器人的行為模式控制器。在整合上下層的方法後，一個以服務導向框架為基礎並能快速建構機器人服務的雛型系統開發完成。
本研究的實驗中，驗證了所提出的機器人服務導向架構不僅可以應用於機器人控制，也可以用於建構機器人服務。而使用本體論的規劃方式能比傳統的人工智慧規劃方式更快速的組合使用者所需的機器人服務。

Many researchers are working on developing robots able to interact and work with people at home. To enable the sharing and reuse of robot code between different developers and end-users, we present a service-based approach that exploits the standard web interface to create reusable robotic services. Our approach includes high-level knowledge ontology planning and low-level neural network learning strategies for robot control. In addition, several service functions, including service discovery, selection, composition, and reconfiguration, have been developed for operating these services.
In this dissertation, the proposed high-level knowledge ontology provides not only spatial knowledge but also a guide to action for daily home tasks. With the efficient HTN planning method, the planner can exploit domain knowledge and the related techniques defined within the ontology to achieve the application task. On the other hand, a low-level recurrent neural networks (RNN) approach has been implemented for new service creation. That is, we present a procedure of programming-by-demonstration to collect the behavior sequence data of the robot as expression profiles, and then employ our network-modeling framework to infer controllers. More briefly, we present a service-oriented robotic framework to enable the rapid prototyping of robotic services.
Experiments have been conducted to verify the proposed framework, and the results show that our approach can not only be applied to robot control, but can also be used to build robotic services.

論文審定書 i
誌 謝 ii
摘 要 iii
Abstract iv
List of Figures viii
List of Tables x
Chapter 1. Introduction 1
1.1 Background 1
1.2 Motivation 3
1.3 Purpose 5
1.4 Outline 7
Chapter 2. Related work 8
2.1 SOA/C in Robotics 8
2.1.1 Service-Oriented Architecture / Computing 8
2.1.2 SOA/C Actions in Robotics 9
2.2 Ontology 11
2.2.1 OWL-S 11
2.2.2 Protégé 13
2.2.3 Ontology in Robotics 15
2.3 Robotics Middleware 17
2.3.1 Player/Stage/Gazebo 17
2.3.2 Microsoft Robotics Studio 18
2.3.3 Robot Operating System (ROS) 19
2.3.4 OpenRAVE 20
2.4 Learning Robotics Controllers 23
2.4.1 Learning from Neural Networks 23
2.4.2 Learning from Demonstration 26
Chapter 3. A Service-Oriented Approach for Robot Control 29
3.1 System Overview 31
3.2 Using Knowledge Ontology to Identify Robot Tasks 33
3.3 Service Functions 37
3.3.1 Service Discovery 39
3.3.2 Service Selection 42
3.3.3 Service Composition 44
3.3.4 Service Reconfiguration 50
3.4 Creating New Services 52
3.4.1 Modeling RNN for Robot Control 53
3.4.2 Learning Algorithm for Constructing RNN Controllers 55
3.4.3 Robot Programming by Demonstration 57
3.4.4 Machine Learning for Adapting Imbalance 59
3.4.5 Creating Services 60
Chapter 4. Experiments and Results 63
4.1 Service Composition through Task Planning 65
4.1.1 Service composition and reconfiguration of the “Give” task 65
4.1.2 Service composition and reconfiguration of the “Clean” task 70
4.2 The Evaluation of System Performance 78
4.2.1 The Generation of Datasets 78
4.2.2 The System Performance Results 81
4.3 Service Creation through Robot Learning 86
4.3.1 Modeling Recurrent Neural Network 86
4.3.2 Learning RNN for robot control 88
4.3.3 Automatic behavior correction 95
Chapter 5. Conclusion 100
5.1 Contributions 102
5.2 Future work 103
Reference 105

Amoretti, M., & Reggiani, M. (2010). Architectural paradigms for robotics applications. Advanced Engineering Informatics, 24(1), 4-13.
An, M., Taura, T., & Shiose, T. (2007). A study on acquiring underlying behavioral criteria for manipulator motion by focusing on learning efficiency. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 37(4), 445-455.
Beer, R. D., & Gallagher, J. C. (1992). Evolving dynamical neural networks for adaptive behavior. Adaptive behavior, 1(1), 91-122.
Belouaer, L., Bouzid, M., & Mouaddib, A. (2010). Ontology based spatial planning for human-robot interaction. Paper presented at the Temporal Representation and Reasoning (TIME), 2010 17th International Symposium on.
Bentley, P. J. (2009). Methods for improving simulations of biological systems: systemic computation and fractal proteins. Journal of The Royal Society Interface, 6(Suppl 4), S451-S466.
Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: O'reilly.
Blake, M. B., Remy, S. L., Wei, Y., et al. (2011). Robots on the web. Robotics & Automation Magazine, IEEE, 18(2), 33-43.
Blasi, M. F., Casorelli, I., Colosimo, A., et al. (2005). A recursive network approach can identify constitutive regulatory circuits in gene expression data. Physica A: Statistical Mechanics and its Applications, 348, 349-370.
Box, D., Ehnebuske, D., Kakivaya, G., et al. (2000). Simple object access protocol (SOAP) 1.1.
Bruyninckx, H. (2008). Robotics software: The future should be open [position]. Robotics & Automation Magazine, IEEE, 15(1), 9-11.
Calinon, S., Guenter, F., & Billard, A. (2007). On learning, representing, and generalizing a task in a humanoid robot. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 37(2), 286-298.
Chandrasekaran, B., Josephson, J. R., & Benjamins, R. (1998). The Ontology of Tasks and Methods. Paper presented at the Proceedings of 11th Banff Knowledge Acquisition for Knowledge-Based System Workshop, Canada.
Chen, C.-C., & Zhong, S. (2008). Inferring gene regulatory networks by thermodynamic modeling. BMC genomics, 9(Suppl 2), S19.
Christensen, E., Curbera, F., Meredith, G., et al. (2001). Web services description language (WSDL) 1.1.
Diankov, R., & Kuffner, J. (2008). Openrave: A planning architecture for autonomous robotics. Robotics Institute, Pittsburgh, PA, Tech. Rep. CMU-RI-TR-08-34, 79.
Erl, T. (2005). Service-oriented architecture (Vol. 8): Prentice Hall New York.
Fellbaum, C. (2010). WordNet. Theory and Applications of Ontology: Computer Applications, 231-243.
Fielding, R. T. (2000). Architectural styles and the design of network-based software architectures. University of California.
Gerkey, B., Vaughan, R. T., & Howard, A. (2003). The player/stage project: Tools for multi-robot and distributed sensor systems. Paper presented at the Proceedings of the 11th international conference on advanced robotics.
Grimes, D. B., & Rao, R. P. (2008). Learning nonparametric policies by imitation. Paper presented at the Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International Conference on.
Gruber, T. R. (1993). A translation approach to portable ontology specifications. Knowledge acquisition, 5(2), 199-220.
Gupta, M. M., Jin, L., & Homma, N. (2004). Static and dynamic neural networks: from fundamentals to advanced theory: John Wiley & Sons.
Ha, Y. G., Sohn, J. C., Cho, Y. J., et al. (2007). A robotic service framework supporting automated integration of ubiquitous sensors and devices. Information Sciences, 177(3), 657-679.
IFR. (2013). Service Robots. Retrieved March 13, 2013, from http://www.ifr.org/service-robots/
Ijspeert, A. J. (2008). Central pattern generators for locomotion control in animals and robots: a review. Neural Networks, 21(4), 642-653.
Jackson, J. (2007). Microsoft robotics studio: A technical introduction. Robotics & Automation Magazine, IEEE, 14(4), 82-87.
Jacobs, R. A. (1988). Increased rates of convergence through learning rate adaptation. Neural Networks, 1(4), 295-307.
Japkowicz, N., & Stephen, S. (2002). The class imbalance problem: A systematic study. Intelligent data analysis, 6(5), 429-449.
Jeon, H., Kim, T., & Choi, J. (2008). Ontology-based user intention recognition for proactive planning of intelligent robot behavior. Paper presented at the Multimedia and Ubiquitous Engineering, 2008. MUE 2008. International Conference on.
Karlebach, G., & Shamir, R. (2008). Modelling and analysis of gene regulatory networks. Nature Reviews Molecular Cell Biology, 9(10), 770-780.
Khondoker, M. R., & Mueller, P. (2010). Comparing ontology development tools based on an online survey.
Kim, B. K., Miyazaki, M., Ohba, K., et al. (2005). Web services based robot control platform for ubiquitous functions.
Knublauch, H., Fergerson, R. W., Noy, N. F., et al. (2004). The Protégé OWL plugin: An open development environment for semantic web applications The Semantic Web–ISWC 2004 (pp. 229-243): Springer.
Laubenbacher, R., & Stigler, B. (2004). A computational algebra approach to the reverse engineering of gene regulatory networks. Journal of theoretical biology, 229(4), 523-537.
Lecue, F., & Mehandjiev, N. (2011). Seeking quality of web service composition in a semantic dimension. Knowledge and Data Engineering, IEEE Transactions on, 23(6), 942-959.
Lee, W.-P., Jong, J.-S., & Yang, T.-H. (2010). Evolving behavior sequences for a humanoid entertainment robot. Artificial Life and Robotics, 15(3), 341-346.
Lee, W.-P., & Tzou, W.-S. (2009). Computational methods for discovering gene networks from expression data. Briefings in bioinformatics, 10(4), 408-423.
Lemaignan, S., Ros, R., Mosenlechner, L., et al. (2010). ORO, a knowledge management platform for cognitive architectures in robotics. Paper presented at the Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on.
Lim, G. H., Suh, I. H., & Suh, H. (2011). Ontology-based unified robot knowledge for service robots in indoor environments. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 41(3), 492-509.
Liu, X.-Y., Wu, J., & Zhou, Z.-H. (2009). Exploratory undersampling for class-imbalance learning. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 39(2), 539-550.
Martin, D., Burstein, M., Hobbs, J., et al. (2004). OWL-S: Semantic markup for web services. W3C member submission, 22, 2007-2004.
Mokarizadeh, S., Grosso, A., Matskin, M., et al. (2009). Applying Semantic Web Service Composition for Action Planning in Multi-robot Systems.
Muhlig, M., Gienger, M., Hellbach, S., et al. (2009). Task-level imitation learning using variance-based movement optimization. Paper presented at the Robotics and Automation, 2009. ICRA'09. IEEE International Conference on.
Nakaoka, S. i., Nakazawa, A., Kanehiro, F., et al. (2007). Learning from observation paradigm: Leg task models for enabling a biped humanoid robot to imitate human dances. The International Journal of Robotics Research, 26(8), 829-844.
Nau, D., Au, T., Ilghami, O., et al. (2003). SHOP2: An HTN planning system. Journal of Artificial Intelligence Research, 20(1), 379-404.
Niles, I., & Pease, A. (2001). Towards a standard upper ontology. Paper presented at the Proceedings of the international conference on Formal Ontology in Information Systems-Volume 2001.
Nolfi, S., Floreano, D., & Floreano, D. (2000). Evolutionary robotics: The biology, intelligence, and technology of self-organizing machines (Vol. 26): MIT press Cambridge.
Noman, N., & Iba, H. (2007). Inferring gene regulatory networks using differential evolution with local search heuristics. IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), 4(4), 634-647.
Osentoski, S., Jay, G., Crick, C., et al. (2011). Robots as web services: Reproducible experimentation and application development using rosjs. Paper presented at the Robotics and Automation (ICRA), 2011 IEEE International Conference on.
Papazoglou, M. P. (2003). Service-oriented computing: Concepts, characteristics and directions. Paper presented at the Web Information Systems Engineering, 2003. WISE 2003. Proceedings of the Fourth International Conference on.
Papazoglou, M. P., Traverso, P., Dustdar, S., et al. (2007). Service-oriented computing: State of the art and research challenges. Computer, 40(11), 38-45.
Quigley, M., Conley, K., Gerkey, B., et al. (2009). ROS: an open-source Robot Operating System. Paper presented at the ICRA workshop on open source software.
Rao, J., & Su, X. (2005). A survey of automated web service composition methods. Semantic Web Services and Web Process Composition, 43-54.
Remy, S. L., & Blake, M. B. (2011). Distributed service-oriented robotics. Internet Computing, IEEE, 15(2), 70-74.
Ricci, F., Rokach, L., & Shapira, B. (2011). Introduction to recommender systems handbook Recommender Systems Handbook (pp. 1-35): Springer.
Rizzolatti, G., & Craighero, L. (2004). The mirror-neuron system. Annu. Rev. Neurosci., 27, 169-192.
Schafer, J. B., Frankowski, D., Herlocker, J., et al. (2007). Collaborative filtering recommender systems The adaptive web (pp. 291-324): Springer.
Shon, A. P., Grochow, K., & Rao, R. P. (2005). Robotic imitation from human motion capture using gaussian processes. Paper presented at the Humanoid Robots, 2005 5th IEEE-RAS International Conference on.
Sirin, E., Parsia, B., Wu, D., et al. (2004). HTN planning for web service composition using SHOP2. Web Semantics: Science, Services and Agents on the World Wide Web, 1(4), 377-396.
Steil, J. J., Röthling, F., Haschke, R., et al. (2004). Situated robot learning for multi-modal instruction and imitation of grasping. Robotics and Autonomous Systems, 47(2), 129-141.
Stewart, F., Taylor, T., & Konidaris, G. (2005). Metamorph: Experimenting with genetic regulatory networks for artificial development Advances in Artificial Life (pp. 108-117): Springer.
Tenorth, M., & Beetz, M. (2009). KnowRob—knowledge processing for autonomous personal robots. Paper presented at the Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on.
Trefzer, M. A., Kuyucu, T., Miller, J. F., et al. (2010). Evolution and analysis of a robot controller based on a gene regulatory network Evolvable Systems: From Biology to Hardware (pp. 61-72): Springer.
van Riel, N. A. (2006). Dynamic modelling and analysis of biochemical networks: mechanism-based models and model-based experiments. Briefings in bioinformatics, 7(4), 364-374.
Vaughan, R. T., & Gerkey, B. P. Really reusable robot code and the player/stage project. Software Engineering for Experimental Robotics, 267-289.
Vohradsky, J. (2001). Neural network model of gene expression. The FASEB Journal, 15(3), 846-854.
Vu, T. T., & Vohradsky, J. (2002). Genexp—a genetic network simulation environment. Bioinformatics, 18(10), 1400-1401.
Waibel, M., Beetz, M., Civera, J., et al. (2011). RoboEarth. Robotics & Automation Magazine, IEEE, 18(2), 69-82.
Werbos, P. J. (1990). Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 78(10), 1550-1560.
Xu, B., Luo, S., Yan, Y., et al. (2012). Towards efficiency of QoS-driven semantic web service composition for large-scale service-oriented systems. Service Oriented Computing and Applications, 6(1), 1-13.
Xu, R., Venayagamoorthy, G. K., & Wunsch II, D. C. (2007). Modeling of gene regulatory networks with hybrid differential evolution and particle swarm optimization. Neural Networks, 20(8), 917-927.
Yachir, A., Tari, K., Chibani, A., et al. (2008). Towards an automatic approach for ubiquitous robotic services composition.
Zentall, T. R. (2006). Imitation: definitions, evidence, and mechanisms. Animal cognition, 9(4), 335-353.