本論文以德國FESTO公司所開發的Robotino全向輪機器人為移動平台,並在Visual C++上搭配OpenCV函式實現人臉偵測,並取得人臉中心x座標值,將座標資訊傳送至LabVIEW,再根據系統的誤差,利用比例、微分控制運算出控制量,進而決定機器人左右旋轉角度。同時搭配雷射測距儀,掃描人體距離並當作模糊邏輯的輸入變數,經由模糊邏輯的推論可以得到機器人的速度,方可使機器人達到定距離的追蹤。再以紅外線感測器進行必要之閃避障礙物。避障模式是利用全向輪特性,一邊將鏡頭對準人臉,一邊使機器人與障礙物保持等距,對準人臉的目的在於確保隨時都能即時人臉追蹤。
In this study, Robotino, which is an omni-directional wheeled robot and developed by German FESTO company, is used to be the moving platform. Face detection algorithm is achieved by coding Visual C++ program and using the OpenCV functions. When the x coordinate value of the face center is obtained, the coordinate information is fedback to controller implemented in LabVIEW software. According to the deviation error of the face from the image center, a PD controller is used to calculate the control signal for suitably rotating the Robotino robot. In the meantime, a laser range finder is employed to detect the distance of human body which will be used as the input variable of fuzzy logic controller. The fuzzy logic controller can determine the robot speed so that cruise control can be obtained. In addition, obstacle avoidance is carried out by using the robot infrared sensors. Obstacle Avoidance algorithm is so designed that the robot always tracks the face and simultaneously wall follows the obstacle.