本論文主要在討論一個基於人體姿態偵測之復健與機器人模仿系統之設計及建立。此系統之復健系統是利用kinect的肢體運動及關節變動之辨識技術進行復健工作,而在機器人模仿系統之設計上是利用kinect之人體姿態擷取功能以建立人形機器人可以做出和人一樣的動作及行為。基於復健系統我們建構復健系統流程圖並進行髖關節活動六種角度復健量測,肩關節活動度量測,膝關節活動度量測,髖部激勵動作,肘關節活度量測等並做一些測試結果之評估。而在機器人模仿系統中我們廣泛討論了人形機器人之結構,人型機器人之手足運動控制及人機介面設計等。 The Development of a Rehabilitation and Robot Imitative System Based on the Detection of Human Posture and Behavior. In this thesis it basically discusses the design and the development of a rehabilitation and robot imitative system based on the detection of human posture and behavior. The rehabilitation system is using the Kinect’sidentification system based on the limb kinetic and joint movement to perform the rehabilitationprocess while in the design of the robot imitative system it extracts the functions of the kinect’s human posture and behavior to build an imitative system to have the robot to perform the actions as close as to the human beings. Based on the rehabilitation system we setup a functional block diagram for the test of rehabilitationprocess in the hip joint movement in six angles, in the shoulder joint movement, knee movement, hip muscle movement and elbow movement and then make the evaluation of these tests. In the robot imitative system we discuss widely in the structure of the imitative robot system, the hand and foot movement control and the design of human-robot interface and human-computer interaction.