以??經網?為基礎之教導機械人模仿人?動作的機制; A Neural-Network-based Mechanism for Teaching Robots to Imitate Human Actions

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/61613

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/61613

Title:	以??經網?為基礎之教導機械人模仿人?動作的機制;A Neural-Network-based Mechanism for Teaching Robots to Imitate Human Actions
Authors:	林士傑;Lin,Shih-Chieh
Contributors:	資訊工程學系
Keywords:	最佳化;群體智慧;模仿機器人;模仿中學習;??經;SOM;optimization;swarm intelligence;imitating robot;imitating robot;neural networks;SOM,
Date:	2013-08-30
Issue Date:	2013-10-08 15:23:42 (UTC+8)
Publisher:	國立中央大學
Abstract:	個人化機器人被設計?在居家環境中能協助或娛?人們，並且被期待能夠與人們互動，因此，越?越吸引?自各?域的人們的注意?，而機器人能夠模仿人?動作則被視為能與人?在動作上互動的第一步。本篇?文提出一個以??經網?為基礎的機制，得以讓機器人即時模仿人?動作。主要由三個步驟組成：1)建?人體基本動作單元、2)針對每個人體基本動作單元，?用最佳化演算法找出相對應的機械人關節的馬達角?、3)?用前述步驟之結果，設計以??經網?為基礎的機械人關節角?控制器。首先由收集的多種人體動作序?，?用分群演算法找出基本動作單元。由於人體基本動作單元?未知，我們採用非監督式的自我組織特徵映射圖(SOM)方法，藉由人體動作資?的?樸分佈，找出基本人體動作單元。第二步是針對這些基本動作單元，找出對應的機械人關節馬達角?，使得機器人的能作出與人體基本動作最相似的動作，此問題可被視為一個在高維?空間中尋找一個最佳解(亦即最佳之馬達角?組合)的最佳化問題，會隨著機器人之馬達?目的增加而大大增加其複雜?。針對此最佳化問題，本?文特別發展?一個以鴿子覓食機制為構想的最佳化演算法─鴿子群體最佳化演算法(Dove Swarm Optimization)，希望透過此鴿子群體最佳化演算法得以快速找到好的機械人馬達關節角?組合。第三步則是以上述找到之機械人馬達關節角?對應之資?集作為訓?資?，訓?一個監督式的? ?經網?做為機械人關節角?控制器。本?文比較多層感知機網?以及放射?基底函?網?的結果，最後選用多層感知機網?作為控制器。在實驗結果部份，本?文與線性對應(linear mapping)的方法比對差 ??、方均根誤差以及時間，結果發現整體效能平均提升約10%，而對於在線性對應方式中表現特別?好的人體姿態，其改進比?則為13%，而在線性對應方式中已表現很好的姿態則無太大之改進。 Personal service robots are designed to assist or entertain people in domestic environments and expected to engage in social-human interactions therefore, they are gaining more and more attentions from many different fields. A robot that can imitate human actions can be regarded as the first step for interacting with humans from the viewpoint of actions. This dissertation presents a neural-network-based imitation mechanism for teaching a robot to imitate human actions. The proposed mechanism involves in the following three steps: 1) the generation of basic human motion units, 2) the mapping between basic human motion units and robot joint motor angles, and 3) the construction of a NN-based controller. First of all, we collected several human motion sequences consisted of many different human activities and then used a clustering algorithm to cluster the collected human actions into a set of basic human motion units. Since the number of basic human motion units is unknown, we decided to adopt the self-organized feature map (SOM) as the clustering tool to generate basic human motion units. Secondly, for each basic human action unit, we need to find a combination of robot joint motor angles to make the robot pose be similar to the corresponding human pose. The problem can be regarded as an optimization problem of which goal is to find an optimized solution (i.e., the best combination of robot joint motor angles) in a multi-dimensional space. The complexity of the optimization problem greatly increases as the number of robot joint motors. To provide a good solution to the optimization problem, this dissertation also proposes the new optimal algorithm called dove swarm optimization (DSO), which is motivated by the doves’ foraging behavior. The proposed DSO is adopted to affectively find the best combination of robot joint motor angles corresponding to each basic human motion unit. In the third step, the data set generated in the previous step is adopted as the training data set to construct a NN-based controller. From our simulations, we found that controller performance achieved by the multilayer perceptrons (MLP) outperformed the radial basis function network (RBFN) therefore, we decided to adopt the MLP to construct the NN-based controller. The proposed mechanism was compared with the most straightforward linear mapping method based on the root mean squared error and computational time. In simulation results, we found that the proposed imitation mechanism could promote the performance about 10% on average. The worst one hundred basic human actions achieved by the linear mapping method, the imitation performance could be improved to 13% by our mechanism. As for the best one hundred basic human actions achieved by the linear mapping method, our imitation mechanism did not clearly improve the imitation performance.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	653	View/Open

社群 sharing

Loading...