基於ROS在靜態環境之自主機器人的模糊導航系統

Fuzzy Navigation System for ROS Based Autonomous Robot in Static Environment

辛柏凱(Pushkar Kumar Singh)

指導教授 ： 李祖添 ； 翁慶昌

淡江大學/工學院/電機工程學系機器人工程碩士班/碩士(2019年)

https://doi.org/10.6846/TKU.2019.00465

摘要

本論文設計和實現軌跡追蹤和規劃控制器，為使用模糊邏輯來用於移動型與人形機器人之自動化機器人，並在靜態的環境中導航。透過建立自動化機器人之差動驅動滾輪的運動學方程實現運動學模型。當機器人使用攝影機獲取即時影像時，透過影像處理中使用色彩模型的色彩表來進行物件分割來顯示影像二值化。最後，機器人使用模糊邏輯控制器來追蹤預設路徑並透過控制驅動的速度和轉向角度來避開未知的障礙物。已經考慮了線路追蹤與避障的方法。控制器為雙輸入和雙輸出的系統，其是更適合室內使用的追蹤式車輛。模糊控制系統於Ubuntu 16.01之機器人作業系統中設計與實現，並且在Gazebo模擬中進行測試。最後，一些實驗與結果證明了模糊邏輯控制系統對自動化機器人的有效性。

關鍵字

模糊邏輯 ； Gazebo ； 人形機器人 ； 導航 ； 機器人作業系統 ； 軌跡規劃

並列摘要

This paper describes the design and implementation of a trajectory tracking and planning controller using Fuzzy logic for autonomous robots including both mobile and humanoid to navigate in the static environment. The kinematic model has been created for the autonomous robot using the kinematics equations of the differential driving rolling wheel. As the robot uses webcam to get the live image, image binarization has been shown using the object segmentation method by using the color code table of color model in the image processing. Finally, the robot uses a fuzzy logic controller to follow a planned path and avoid unknown obstacles by controlling the velocity and steering angle of the drive unit. Both line following and obstacle avoidance approach has been considered. The controller is a two input and two output system. It is a tracked vehicle which is more suitable for indoor use. The fuzzy control system has been designed and implemented in Robot Operating System (ROS) under Ubuntu 16.01 operating system and tested under Gazebo simulation. Finally, several experiments and results have been presented to demonstrate the effectiveness of fuzzy logic control system on the autonomous robots.

並列關鍵字

Fuzzy Logic ； Gazebo ； Humanoid Robot ； Navigation ； Robot Operating System (ROS) ； Trajectory Planning

參考文獻

[1] URL: https://en.wikipedia.org/wiki/Robot

[2] Intelligent identification and control for autonomous guided vehicles using adaptive fuzzy-based algorithms; C. J. Harris & C. G. Moore, Eng. Application of AI, Vol. 2, December '8

[3] R. Frizera Vassallo, H. J. Schneebeli, J. Santos-Victor, Visual navigation: combining visual servoing and appearance based methods, 6th International Symposium on Intelligent Robotic Systems, SIRS’98, Edinburgh, Scotland, July 1998

[4] J. Santos-Victor, G. Sandini, F. Curotto, S. Garibaldi, Divergent stereo in autonomous navigation: from bees to robots, International Journal of Computer Vision 14 (1995) 159–177.

[5] R. Carelli, C. Soria, O. Nasisi, E. Freire, Stable AGV corridor navigation with fused vision-based control signals, Conference of the IEEE Industrial Electronics Society, IECON, Sevilla, Spain, November 5–8, 2002