淡江大學機構典藏:Item 987654321/103074
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62822/95882 (66%)
Visitors : 4028090      Online Users : 594
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
    •  Adv. Search
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/103074


    Title: 人形機器人的步態學習系統之設計與實現
    Other Titles: Design and Implementation of Learning System for Biped Walking Robots
    Authors: 鄭吉泰
    Contributors: 淡江大學電機工程學系
    Keywords: 人形機器人;學習系統;中樞模式產生器;行走步態;Humanoid Robot;Learning System;Central Pattern Generator;Walking Gait
    Date: 2012-08
    Issue Date: 2015-05-18 14:18:28 (UTC+8)
    Abstract: 本計畫擬實現一個透過人形機器人實際行走經驗來找到平衡協調感的步態學習系 統。計畫將延續實驗室目前小型人形機器人之成果，從六個主題來進行：(1)彈性腳掌的 設計、(2)行走學習機台的設計、(3)模擬與實際機器人誤差縮小設計、(4)行走步態設計、 (5)參數最佳化演算法設計與(6)機器人線上最佳化設計。第一個部份的機器人彈性腳掌 設計將以扭力彈簧與壓力感測器完成具有類似人類腳掌彈力及擴張性特質的腳掌。接 著，第二個主題則是以建構一套具視覺並能依照機器人行走速度來調速的行走學習機 台。由於擬執行之計畫為機器人線上最佳化設計，因此會先透過模擬方式將可能危害機 器人動作加以排除，所以在第三個主題中，則是利用行走學習機台上的視覺系統來調整 機器人實際中因為馬達及機構問題與模擬中的參數差異，以提高模擬效果。第四個主題 則是利用中樞模式產生器(Central Pattern Generator)的人形機器人步態產生方式來設計 機器人的步態軌跡。接著在第五個主題中利用遺傳演算法來設計可參數化的演化流程。 最後，透過事前模擬過濾掉可能危害機器人的參數後，在第六個主題中搭配行走學習機 台來完成機器人線上學習的設計。
    A learning system for biped walking robots is proposed in this proposal. The humanoid robot, which is built by our lab, is able to find out its rhythm of walking gait by learning from the proposed system. Six issues including: 1. the elastic foot, 2. design of the learning platform, 3. error reducing for the simulation, 4. walking trajectory, 5. optimization problem of the parameters, and 6. on-line learning will be implemented in this project. The torsion springs and the force sensors will be mounted on the robot’s foot to accomplish the elastic ability. A vision based learning system will be built in the second sub-issue for the robot. All of the motions will be simulated in the computer first. Only the motion which is not dangerous will be sent to the robot. In order to reduce the difference of the simulation and real robot, an error reducing method will be proposed in this project. For the walking trajectory, Central Pattern Generator (CPG) method will be used in the project for generating the walking gait. Besides, GA algorithm is applied to optimize the parameters of the proposed learning system. The integrated system is able to help the robot to determine its rhythm of walking gait by leaning automatically.
    Appears in Collections:[Graduate Institute & Department of Electrical Engineering] Research Paper

    Files in This Item:

    There are no files associated with this item.

    All items in 機構典藏 are protected by copyright, with all rights reserved.

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback