應用於室內自然環境且可與人自然溝通之居家服務機器人--子計畫三:居家服務機器人之即時動態導航與定位學習之設計與實現(II)

No Thumbnail Available

Date

2012-07-31

Authors

許陳鑑
簡忠漢

Journal Title

Journal ISSN

Volume Title

Publisher

行政院國家科學委員會

Abstract

本計畫之主要目的在於研究居家服務機器人即時動態導航與定位之設計與實現,包 含:環境感知、導航(robot navigation)、以及迴避障礙等功能,使居家服務機器人能具有 自主認知與熟習環境的能力,以協助各個子計畫達成希望執行的任務。配合總計畫第 一、二年預定完成RoboCup@home 基礎及進階指定競賽項目的目標,本計畫將以:(1) 多感測器之障礙物偵測系統、(2)感測器資料融合、(3)虛擬環境地圖建立與定位、(4)自 主避障、以及(5)動態路徑規劃等項目為研究重點,完成:(1)建立一多重感知障礙物偵 測系統,整合各種異質感測器之量測資訊,提供可靠之環境障礙物資訊,(2)利用多種數 據融合(sensor fusion)技術實現感測器資料融合,以提供可靠的量測結果,作為建圖、定 位與避障之依據,(3)利用多種地圖建置(map building)與自我定位技術,建立並更新未知 環境之虛擬地圖以及準確估測機器人的姿態,作為機器人自主導航的依據,(4)以多種啟 引式演算法(heuristic)以及演化計算法(evolutionary computation)實現最佳路徑之規劃,使 機器人能據以行動,快速且安全到達目的地,(5)依據多重感知障礙物偵測的結果以及目 標物移動方向之估測,實現自主避障之功能,使機器人能安全行進。並與其他子計畫整 合,使居家機器人能夠完成RoboCup@home 所指定之基礎及進階競賽項目。第三年的 目標主要是要延伸居家服務機器人的功能,針對適合台灣居家環境之機器人的相關項目 進行研發,包含:(1)利用影像式定位法配合目標物特徵辨識技術對障礙物進行偵測,以 確定目標物之空間座標位置,(2)提供居家空間多重輔助定位,包含超音波、RFID、以 及影像式輔助定位,以校準機器人位置,提供機器人精確定位,(3)利用多重感測數據融 合資料實現3D 地圖建立與圖形化介面設計,精確呈現障礙物空間資訊,(4)以嵌入式系 統軟硬體協同設計(Hardware/Software Co-design)觀念實現各種演算法,期使運算速度能 夠大幅提升,達到即時處理之需求,全面提升機器人之導航及避障性能。
The objective of this project is to investigate the design and implementation of dynamic navigation and self-localization systems for home service robots, including environment sensing, robot navigation, and obstacle avoidance, to equip the robot with the capabilities of autonomy for exploring the environment under consideration. Related sub-projects can benefit from the information provided by this project, including accurate position of the robot and optimal paths between the robot and the destination, in performing desired tasks set out in the RoboCup@home. According to the objectives to be achieved, the first and second years will focus on the preparation of primitive and advanced competitions of RoboCup@home. As a result, this project will investigate the following major items: (1) multi-sensing obstacle detection, (2) sensor fusion, (3) map buiding and localization, (4) obstacle avoidance, and (5) dynamic path planning. It is hoped that, after the completion of the first two years, we can: (1) establish a multi-sensing obstacle detection system, integrating all of the heterogeneous sensors for providing reliable measurement, (2) use various sensor fusion techniques to provide reliable information for subsequent map building and obstacle avoidance, (3) use various techniques for map building to establish an environment map for an unknown environment, upon which robot navigation relies. (4) adopt A* and D* algorithms as well as evolution computation to derive optimal paths between the robot and the destination for safe and fast robot navigation, (5) based on the information obtained from sensor fusion and prediction of moving objects, implement a fuzzy obstacle avoidance controller. The objective in the third year of this project is to develop items related to the development of a localized home service robot suitable for use here in Taiwan, including (1) multiple auxiliary localization schemes, including ultrasonic-, RFID-, and image-based localization for providing extra position information for the robot, (2) 3D mapping for integration into a GUI interface to accurately describe the environment,(3) implementation of the proposed algorithms for localization, path planning, and obstacle avoidance, etc, on a SOPC platform to improve the overall performance of the robot.

Description

Keywords

Citation

Collections