基於類神經網路實作具情感模型與制約模型之寵物機器人

Emotional and Conditional Model for Pet Robot based on Neural Network

許家銘(Chia-Ming Hsu)

指導教授 ： 賀嘉生

中原大學/工學院/資訊工程研究所/碩士(2014年)

https://doi.org/10.6840/cycu201400887

摘要

近年來越來越多寵物機器人 (Pet Robot) 的產品出現，顯示寵物機器人逐步進展成為下一代電子玩具，而研究指出產品的創新性有助於提高消費者的接受度，未來寵物機器人將具備更多的變化性與趣味性，於是在智慧型機器人的研究中，如何使機器人能與人類在同一環境下共同活動，融入人類的生活而不顯得冰冷生硬，已成為學者們努力實現的目標。事實上，所有的傳統機器人產品都需要面對兩大問題，一是使用者只有短暫的熱情，在熟悉系統後便會覺得無趣而不再使用，二是傳統機器人之行為完全受控於指令操作，如此直接的操作行為模式使得使用者無法脫離正在與機器人互動的想法。本研究為了使機器人表現的更加自然，設計以寵物機器人為對象之簡化系統原型，加入制約模型 (Conditional Model) 使得每個寵物機器人擁有獨特的互動模式，其中，制約模型之學習機制以古典制約 (Classical Conditioning) 為理論基礎，計算模型則使用聯想神經網路 (Associative Neural Network) 與霍伯學習法則 (Hebbian Learning Rule)，可實現習得 (Acquisition)、遺忘 (Extinction)、再習得效應 (Reacquisition Effects) 等基本特性，以及阻斷 (Blocking) 和部份的二級制約 (Secondary Conditioning) 等延伸特性。情緒方面，本系統加入情緒模型 (Emotional Model)，仿照實際生物的內分泌與情緒間的影響關係，組成八種基本情緒，同時亦利用情緒 (Emotion) 及感受 (Feeling) 的概念，採用情緒驅動的方式來決定最後的表現行為，並於文內展示兩個方面的成果，第一為制約學習影響寵物機器人之情緒，第二為情緒影響寵物機器人之行為。期望它如同生物般學習、像生物般地表現自我，令使用者可從與寵物機器人的互動中感受到多一點生命性，獲得更自然與信賴的體驗，藉以改善傳統機器人之兩大問題。

關鍵字

寵物機器人 ； 古典制約反應 ； 類神經網路 ； 情緒模型

並列摘要

Recently more and more pet robot products are launched, which showing the increasing market demand for pet robots, and a plenty of researches have pointed out that the product innovativeness can encourage consumers’ acceptance, the pet robot will be made with more variability, more versatility, and more interesting in each generation. To make the robots do common activities in the same environment with human and integrate it to human’ life is the target of those researchers who were studying in the field of intelligent robot. As a matter of fact, all traditional robots have to face with two major issues: one is the user limitation of patience and passion, and the other is the users cannot escape from the thought of “interacting with a hard and cold robot machine”. This research is aimed at making the pet robots perform more naturally; therefore a simplified prototype system has been designed, it is composed of conditional model and emotional model. The conditional model can make every pet robot have unique interactive style, its theoretical foundation of learning method is based on classical conditioning. And the computational model is binding up with associative neural network and Hebbian learning rule, it can implements acquisition, extinction, and reacquisition effects as basic characteristics, and other extensive characteristics, such as blocking and secondary conditioning. On the other hand, the emotional model was modeled on the impact of the actual biological relationship between endocrine and emotion, which was built up eight basic emotions; apart from this, the concepts of emotion and feeling have also been adopted, thus determine the final performance behavior by using mood-driven approach. In this research, two aspects of achievement will be demonstrated: the first is how the learning method affects the emotion of pet robot, and the second is how the emotion affects the behavior of pet robot. Hopefully, the pet robot can learn like a human, performing biological self-expression, making people think the pet robot is animated machine, and people will get more trusting experience while they are interacting with each other.

並列關鍵字

Classical Conditioning ； Emotional Model ； Neural Network ； Pet Robot

參考文獻

[72] 周書暉, & 林祐全. (2011). 結合情境與情緒: 人機互動理論沿革與發展. 傳播與管理研究, 11(1), 29-68.

[7] Shibata, T., Tashima, T., & Tanie, K. (1999). Emergence of emotional behavior through physical interaction between human and robot. In Robotics and Automation, 1999. Proceedings. 1999 IEEE International Conference on (Vol. 4, pp. 2868-2873). IEEE.

[8] Lövheim, H. (2012). A new three-dimensional model for emotions and monoamine neurotransmitters. Medical hypotheses, 78(2), 341-348.

[12] Jee, E. S., Park, S. Y., Kim, C. H., & Kobayashi, H. (2009, September). Composition of musical sound to express robot's emotion with intensity and synchronized expression with robot's behavior. In Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium on (pp. 369-374). IEEE.

[17] I-Tsen Liu. (2012). The Role of Emotion between Emotional and Symbolic Expression (Department of Visual Communication Design Shu-Te University).