連續型機器人之視覺伺服與順應性運動控制設計

Abstract

本論文提出一種結合視覺伺服與順應性運動之連續型機器人運動控制設計。論文中首先針對自行設計之連續型機器人，推導其順向運動學及逆向運動學，藉由連續型機器人的弧參數計算出連續型機器人各軸之位移，進而控制末端點的位置。本研究在連續型機器人末端安置兩具內視鏡攝影機做為立體攝影機，經由Semi-global block-matching (SGBM)演算法得到深度資訊。論文中提出之視覺伺服系統包含由Speeded-up robust features (SURF)擷取目標物的特徵點，再以Nearest neighbor distance ratio (NNDR)做特徵點匹對，以Mean shift 演算法追蹤特徵點的移動。本論文提出一種順應性控制設計，透過連續型機器人末端周圍之壓力感測器，使連續型機器人能在受約束的環境中前進，完成移動任務。論文中先以MATLAB模擬運動學模型的正確性，再以實際硬體實驗驗證運動控制設計。實驗結果顯示本論文所提出的方法可以有效的使連續型機器人追蹤目標物，且在遇到障礙物時即時產生順應性運動控制，進行追蹤目標物。

This thesis develops a visual servoing and compliant motion control system of a continuum robot. The forward kinematics and inverse kinematics of the self-designed continuum robot are derived. The displacement of each axis of the continuum robot is calculated by arc parameters, and then the end point of the robot is controlled to the expected position. Two endoscopic cameras were installed at the top of the continuum robot to build a stereo camera. The depth information is obtained by using Semi-global block-matching (SGBM) algorithm. The visual servoing system proposed in this work includes the feature point extraction by using Speeded-up robust features (SURF), followed by feature point matching by using Nearest neighbor distance ratio (NNDR), and finally tracking of feature points by using Mean shift algorithm. Through the pressure sensor installed around at the front of the continuum robot, a compliant control design is proposed to make the robot to move in a constrained environment in order to complete the visual servoing task. The kinematics model was verified by MATLAB simulation. Multiple practical experiments show that the proposed method can effectively make the continuum robot to track the target and generate the adaptive motion when encountering an obstacle during visual servoing.