基於ROS之人形機器人的影像定位與導航

本論文針對視覺自主之小型人形機器人提出一個基於機器人作業系統(Robot Operating System, ROS)之定位與導航的實現方法。在Linux環境下，以ROS建構人形機器人的軟體開發架構，在視覺系統中，本論文將影像中感興趣的顏色，以人工標記的方式標記作為特徵，並利用逆透視映射法(Inverse Perspective Mapping, IPM)計算出障礙物與機器人間的距離，以此作為定位的依據。在定位系統中，本論文建立一個有障礙物資訊的虛擬地圖，以機器人移動量做為位移資訊，並且以視覺影像做為系統觀測的資訊，再以蒙地卡羅(Monte Carlo)自我定位法搭配上結合粒子群最佳化法(Particle Swarm Optimization, PSO)之粒子濾波器(particle filter)演算法來推算小型人形機器人的位置。在導航系統中，本論文以改良式A*演算法來規劃一個具有較少轉折點的全域規劃路徑。由實驗結果可得知，本論文所設計之小型人形機器人的定位與導航系統，可使機器人在已知環境中具有自我定位及導航的能力，且安全的避開障礙物並順利抵達目的地。

關鍵字

影像定位；機器人作業系統；蒙地卡羅定位；粒子群最佳化法；粒子濾波器； A*演算法

並列摘要

In this thesis, a localization and navigation system is proposed to be implemented on Robot Operating System (ROS) for a vision-based autonomous small-sized humanoid robot. In the Linux environment, ROS is used to establish the software development framework for the humanoid robot system. In the vision system, some interested color blocks in the image are marked as features, and Inverse Perspective Mapping (IPM) is used to calculate the distance between the obstacle and robot. In the localization system, a virtual map with some obstacle information is established. The amount of movement of the robot is regarded as displacement information, and the visual image is regarded as observation information. Then a method based on the Monte Carlo self-localization method and the particle filter combined with Particle Swarm Optimization (PSO) algorithm is used to estimate the localization for the small-sized humanoid robot. In the path planning system, a modified A* algorithm is proposed to plan a global path planning which has less turning points. From the experimental results, we can see that the proposed localization and navigation system really lets the small-sized humanoid robot has the ability of self-localization and navigation in a known environment. Moreover, the robot can safely avoid obstacles and successfully reach the destination.

並列關鍵字

Image Localization ； Robot Operating System (ROS) ； Monte Carlo Localization ； Particle Swarm Optimization (PSO) ； Particle Filter ； A* Algorithm

參考文獻

[26] 溫泯毅，視覺自主人形機器人之定位與導航，淡江大學電機工程學系碩士論文（指導教授：翁慶昌、鄭吉泰），2016。

[27] 鄧宏志，結合粒子群最佳化法之雙層粒子濾波器於移動機器人的定位與地圖建置，淡江大學電機工程學系博士論文（指導教授：翁慶昌、許陳鑑），2012。

[1] N. Ayache and O. Faugeras, “Building, registrating, and fusing noisy visual maps,” International Journal of Robotics Research, Vol. 7, No.6, pp. 45-65, 1988.

[2] J. L. Crowley, “World modeling and position estimation for a mobile robot using ultrasonic ranging,” IEEE International Conference on Robotics and Automation, Vol. 2, pp. 674-680, 1989.

[3] R. Chatila and J. Laumond, “Position referencing and consistent world modeling for mobile robots,” IEEE International Conference on Robotics and Automation, Vol. 2, pp. 138-145, 1985.

國際替代計量

基於ROS之人形機器人的影像定位與導航

全文下載

主題瀏覽