植基於視覺式同步定位與建圖之移動式機器人合作操控與搬運系統

本論文提出一個採用視覺達成同步定位與建圖的移動式機器人合作操控與搬運系統，透過整合機器視覺、影像處理、同步定位與地圖重建、導航控制及機械手臂控制等跨領域技術建構一智慧型控制系統。本論文利用裝置於移動式機器人上的單支攝影機為感測器，藉SURF演算法擷取環境與搬運物的特徵，同時根據影像訊息求算特徵在空間中的三維位置，並以擴展型卡曼濾波器持續對特徵與機器人狀態做預測與更新，從而精準定位機器人與特徵及重建出具一致性的環境地圖。依據機器人與特徵位置，即可進行移動式機器人的路徑規劃與導航控制，驅動移動式機器人到達搬運處，再配合機械手臂運動學與動力學的計算結果，以執行合作操控與搬運任務。當移動式機器人進行合作操控與搬運任務時，輔以適當的順應控制方法，以避免搬運物於搬運途中脫落，保證任務確實完成。

關鍵字

順應控制；合作操控與搬運；機械手臂；移動式機器人；機器人導航；同步定位與地圖重建； SURF

並列摘要

A robot cooperative manipulation and transportation system based on visual simultaneous localization and mapping is proposed in this thesis. Machine vision, image processing, simultaneous localization and mapping, navigation control and manipulator control techniques are integrated to construct an intelligent control system. A single camera mounted on the mobile robot is used to observe unknown environment. SURF algorithm is employed to extract features of the environment and the object. Meanwhile, three-dimensional positions of the features in space are estimated according to the vision information. Then, the state of robot and features are updated using extended Kalman filter to obtain accurate robot pose and reconstruct a consistent environment map based on which path planning and robot navigation are further accomplished. Manipulator kinematics and dynamics are considered to implement cooperative manipulation and transportation task. When the mobile robot carries on the cooperative manipulation and transportation task, suitable compliance control method is employed to avoid dropping the object and ensure completing task successfully.

並列關鍵字

Compliance Control ； Cooperative Manipulation and Transportation ； Manipulator ； Mobile Robot ； Robot Navigation ； SLAM ； SURF

參考文獻

[1] K. Sakamoto K. Hosoda and M. Asada. Trajectory generation for obstacle avoidance of uncalibrated stereo visual servoing without 3d reconstruction. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 29–34, Pittsburgh, Pennsylvania, USA, Aug. 1995.

[2] A. Saxena J. Michels and A. Y. Ng. High speed obstacle avoidance using monocular vision and reinforcement learning. In Proc. of the 22nd International

[4] D. Murray and J. J. Little. Using real-time stereo vision for mobile robot navigation. Autonomous Robots, 8(2):161–171, 2000.

[5] A. Kosaka I. Ohya and A. Kak. Vision-based navigation by a mobile robot with obstacle avoidance using single-camera vision and ultrasonic sensing. IEEE Transactions on Robotics and Automation, 14(6):969–978, 1998.

[6] N. Molton A. J. Davison, I. Reid and O. Stasse. Monoslam: real-time single camera slam. IEEE Transactions on Pattern Analysis and Machine Intelligence,

國際替代計量

植基於視覺式同步定位與建圖之移動式機器人合作操控與搬運系統

未授權

主題瀏覽