目前蛇型機器人的研究領域中，往往在研究許多最佳的公式來驅動蛇型機器人，而並非是讓蛇型機器人自主學習，來產生行進行為，在真實的世界裡擁有許多外在因素，並無法保證所有研究得出的最佳公式，都能夠套用在所有的環境，或是不出錯的展現出最佳的行進效能，因此本研究使用類分子神經系統當作自主學習的學習機制，產生角度值來控制蛇型機器人，並將設定不同目標點、不同最大馬達角度的實驗學習成果作為後續研究基礎，當需要時就可拿出並組合出許多種組合，也可以再學習新的成果以滿足更多行進需求，讓蛇型機器人能夠有彈性與適應度地到達任何目標。

In recent snake-like robot research, it often use the best formula to drive the snake-like robot. But it doesn't let snake-like robot learn how to move by itself. There are a lot of external factors in real life caused it can't guarantee that snake-like robot all the best formula derived from the research which can apply in all circumstances. Therefore this study use Artificial neuromolecular system as learning mechanism.to generate angle values to control the snake robots. And set different goals, learning outcomes at different limit angles as the cornerstone, it can combine a lot of possible combinations when you need, so the snake robot can be capable of flexibility and fitness to reach any goal.

摘要 i
Abstract ii
目錄 iii
表目錄 v
圖目錄 vi
壹、 緒論 1
1-1 研究背景與動機 1
1-2 研究目的 2
1-3 研究限制 2
貳、 文獻探討 3
2-1 蛇行運動 3
2-2 類分子神經系統（Artificial Neuromolecular System, ANM） 4
2-3 蛇型機器人 9
參、 研究方法與架構 10
3-1 研究架構 10
3-2 研究工具 11
3-2-1 蛇型機器人 11
3-2-2 類分子神經系統 13
3-3 資料擷取與處理 14
3-4 系統評估 17
3-5 實驗設計 17
3-6-1 目標點設計 17
3-6-2 馬達運轉角度設計 17
肆、 實驗 19
4-1 馬達不受限制 19
4-1-1 向左方向行進之學習 19
4-1-2 往前方向行進之學習 23
4-1-3 往右方向行進之學習 26
4-1-4 實驗小結 29
4-2 馬達受限制 30
4-2-1 往左方向行進之學習 30
4-2-2 向前方向行進之學習 33
4-2-3 往右方向行進之學習 36
4-2-4 實驗比較 39
4-2-5 實驗小結 43
4-3 動作組合 44
4-3-1 實驗動作組合 44
4-3-2 實驗小結 50
伍、 結論 51
5-1 研究總結 51
5-2 未來展望 51
參考文獻 52

Boxerbaum, A. S., Horchler, A. D., Shaw, K. M., Chiel, H. J., & Quinn, R. D. (2011, 25-30 Sept. 2011). A controller for continuous wave peristaltic locomotion. Paper presented at the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

Chen, J.-C. (1998). Problem Solving with a Perpetual Evolutionary Learning Architecture. Applied Intelligence, 8(1), 53-71. doi: 10.1023/A:1008220631455

Chen, J.-C., & Conrad, M. (1994a). Learning synergy in a multilevel neuronal architecture. Biosystems, 32(3), 111-142. doi: 10.1016/0303-2647(94)90036-1

Chen, J.-C., & Conrad, M. (1994b). A multilevel neuromolecular architecture that uses the extradimensional bypass principle to facilitate evolutionary learning. Physica D: Nonlinear Phenomena, 75(1-3), 417-437. doi: 10.1016/0167-2789(94)90295-X

Chen, L., Ma, S., Wang, Y., Li, B., & Duan, D. (2007). Design and modelling of a snake robot in traveling wave locomotion. Mechanism and Machine Theory, 42(12), 1632-1642. doi: http://dx.doi.org/10.1016/j.mechmachtheory.2006.12.003

Daltorio, K. A., Horchler, A. D., Shaw, K. M., Chiel, H. J., & Quinn, R. D. (2013). Biomimetic and Biohybrid Systems (N. F. Lepora, A. Mura, H. G. Krapp, P. F. M. J. Verschure & T. J. Prescott Eds.): Springer Berlin Heidelberg.

Gray, J. (1946). The mechanism of locomotion in snakes. Journal of experimental biology, 101-120

Hirose, S. (1993). Biologically Inspired Robots: Serpentile Locomotors and Manipulators: Oxford University Press.

Jayne, B. C. (1988). Muscular mechanisms of snake locomotion: an electromyographic study of the sidewinding and concertina modes of Crotalus cerastes, Nerodia fasciata and Elaphe obsoleta. Journal of experimental biology, 140, 1-33.

Liljebäck, P., K.Y.Pettersen, Stavdahl, Ø., & Gravdahl, J. T. (2012). A review on modelling, implementation, and control of snake robots. Robotics and Autonomous Systems, 60, 29-40.

Mahjoob, M. D. M. J. (2009). A modified serpenoid equation for snake robots. Paper presented at the International Conference on Robotics and Biomimetics, Bangkok.

Mann, E. E., Manna, D., Mettetal, M. R., May, R. M., Dannemiller, E. M., Chung, K. K., . . . Reddy, S. T. (2014). Surface micropattern limits bacterial contamination. Antimicrobial Resistance and Infection Control, 3. doi: 10.1186/2047-2994-3-28

Ostrowski, J., & Burdick, J. (1996, 22-28 Apr 1996). Gait kinematics for a serpentine robot. Paper presented at the Robotics and Automation, 1996. Proceedings., 1996 IEEE International Conference on.

Sato, M., Fukaya, M., & Iwasaki, T. (2002). Serpentine locomotion with robotic snakes. IEEE Control Systems, 22(1), 64-81. doi: 10.1109/37.980248

Shan, Y., & Koren, Y. (1993). Design and motion planning of a mechanical snake. IEEE Transactions on Systems, Man, and Cybernetics, 23(4), 1091-1100.
doi: 10.1109/21.247890

Shugen, M., Araya, H., & Li, L. (2001, 2001). Development of a creeping snake-robot. Paper presented at the Computational Intelligence in Robotics and Automation, 2001. Proceedings 2001 IEEE International Symposium on.

Wu, X., & Ma, S. (2010). CPG-based control of serpentine locomotion of a snake-like robot. Mechatronics, 20(2), 326-334.

張斐章, & 張麗秋. (2010). 類神經網路導論. 台中市: 滄海書局.