自主移動機器人之人機互動控制的設計與實現

Design and Implementation of Human-Robot Interaction Control for an Autonomous Mobile Robot

張文龍(Wen-Lung Chang)

指導教授 ： 陳冠宇 ； 鄧治東

中原大學/工學院/機械工程學系/碩士(2007年)

https://doi.org/10.6840/cycu200700522

摘要

本文的研究目標為開發自主行動機器人的人機互動的控制系統。藉由視覺辨識系統，將原始影像資料進行目標顏色的篩選及辨識，讓使用者可以容易的經由簡單的肢體動作，對機器人下達指令，而且本系統適用於日常生活中的光源環境。本文發展顏色篩選和影像特徵辨識二個系統處理目標辨識與分類。首先，藉由理解目標顏色於色彩空間中的分佈，提出多重閥值及閥值自我調整的機制，取代過去常用的單一閥值顏色篩選方法。再者，傳統以像素為基底的形狀表示方法，目標分類的結果會受到物體旋轉或大小的影響甚大，本文使用邊緣特徵萃取演算法和傅立葉描述子的運算以描述物體輪廓特徵，可不受物體旋轉或大小的影響，再經由支持向量機器的非線性不可分離資料類型進行分類。透過上述二個系統的處理，本文提升了機器人視覺系統的目標辨識之準確率，並成功的在不同光源環境中對機器人進行人機互動控制。

關鍵字

傅立葉描述子 ； 自主行動機器人 ； 人機互動控制 ； 邊緣特徵萃取演算法 ； 支持向量機器

並列摘要

The purpose of the work documented in this thesis is to develop a human-robot interaction control system for an autonomous mobile robot. With the visual recognition system filtering and recognizing the target color in the raw image data, the user can send commands to the robot easily by using simple body motion. And this system is suitable for the environment of lighting in daily life. In this study, a color filter system and an image feature recognition system were developed to process image recognition and classification of the target. Firstly, through understanding the distribution of the target color in color space, the multi-threshold and the self-tuning threshold mechanisms were developed to replace the monotone color threshold method customarily used for screening target color. Secondly, the rotation or size of an object by using the conventional pixel-based shape representation method has a severe impact on the results of the image classification. In this study, the feature of an object was determined through the boundary extraction algorithm and the Fourier descriptors without having the results being affected by the rotation or size of the object. Subsequently, outline feature for the non-linear non-separable type of data was classified by using the support vector machines. In this dissertation, the accuracy of image recognition for the robot vision system has been enhanced by processing of the two systems as described above, and the human-robot interaction control of the robot has successfully used under various lighting environments.

並列關鍵字

human-robot interaction control ； autonomous mobile robot ； support vector machines ； boundary extraction algorithm ； Fourier descriptors

參考文獻

[2] G. D. Hager, W. C. Chang, and A. S. Morse, “Robot feedback control based on stereo vision: towards calibration-free hand-eye coordination,” IEEE International Conference on Robotics and Automation, Vol. 4, pp. 2850-5856, 1994.

[3] I. Baturone, F. J. Moreno-Velo, S. Sanchez-Solano, and A. Ollero, “Automatic design of fuzzy controllers for car-Like autonomous robots,” IEEE Transactions on Fuzzy Systems, Vol. 12, Issue 4, pp. 447-465, 2004.

[5] G. Z. Yang, and T. S. Huang, “Human Face Detection in a Complex Background,” Pattern Recognition, Vol. 27, pp. 53-63, 1994.

[6] S. Zhang; H. Qiao, “Face recognition with support vector machine,” in Proc. 2003 IEEE Int. Conf. Robotics, Intelligent Systems and Signal Processing, Vol. 2, pp. 726-730, 2003.

[7] A. Samal, and P. A Iyengar, “Human face detection using silhouettes,” Pattern Recognition and Artificial Intelligence, Vol. 9, No. 6, pp. 845-867, 1995.