国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁> 外文OA文獻(xiàn) >Online Learning for Robot Vision
【2h】

Online Learning for Robot Vision

機(jī)譯：機(jī)器人視覺在線學(xué)習(xí)

代理獲取
本網(wǎng)站僅為用戶提供外文OA文獻(xiàn)查詢和代理獲取服務(wù)，本網(wǎng)站沒有原文。下單后我們將采用程序或人工為您竭誠獲取高質(zhì)量的原文，但由于OA文獻(xiàn)來源多樣且變更頻繁，仍可能出現(xiàn)獲取不到、文獻(xiàn)不完整或與標(biāo)題不符等情況，如果獲取不到我們將提供退款服務(wù)。請知悉。
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

In tele-operated robotics applications, the primary information channel from the robot to its human operator is a video stream. For autonomous robotic systems however, a much larger selection of sensors is employed, although the most relevant information for the operation of the robot is still available in a single video stream. The issue lies in autonomously interpreting the visual data and extracting the relevant information, something humans and animals perform strikingly well. On the other hand, humans have great diculty expressing what they are actually looking for on a low level, suitable for direct implementation on a machine. For instance objects tend to be already detected when the visual information reaches the conscious mind, with almost no clues remaining regarding how the object was identied in the rst place. This became apparent already when Seymour Papert gathered a group of summer workers to solve the computer vision problem 48 years ago [35]. Articial learning systems can overcome this gap between the level of human visual reasoning and low-level machine vision processing. If a human teacher can provide examples of what to be extracted and if the learning system is able to extract the gist of these examples, the gap is bridged. There are however some special demands on a learning system for it to perform successfully in a visual context. First, low level visual input is often of high dimensionality such that the learning system needs to handle large inputs. Second, visual information is often ambiguous such that the learning system needs to be able to handle multi modal outputs, i.e. multiple hypotheses. Typically, the relations to be learned? are non-linear and there is an advantage if data can be processed at video rate, even after presenting many examples to the learning system. In general, there seems to be a lack of such methods. This thesis presents systems for learning perception-action mappings for robotic systems with visual input. A range of problems are discussed, such as vision based autonomous driving, inverse kinematics of a robotic manipulator and controlling a dynamical system. Operational systems demonstrating solutions to these problems are presented. Two dierent approaches for providing training data are explored, learning from demonstration (supervised learning) and explorative learning (self-supervised learning). A novel learning method fullling the stated demands is presented. The method, qHebb, is based on associative Hebbian learning on data in channel representation. Properties of the method are demonstrated on a vision-based autonomously driving vehicle, where the system learns to directly map low-level image features to control signals. After an initial training period, the system seamlessly continues autonomously. In a quantitative evaluation, the proposed online learning method performed comparably with state of the art batch learning methods.
機(jī)譯：在遠(yuǎn)程操作機(jī)器人技術(shù)應(yīng)用中，從機(jī)器人到操作員的主要信息通道是視頻流。然而，對于自主機(jī)器人系統(tǒng)，雖然在單個視頻流中仍可獲得與機(jī)器人操作最相關(guān)的信息，但傳感器的選擇要多得多。問題在于自主地解釋視覺數(shù)據(jù)并提取相關(guān)信息，這是人類和動物表現(xiàn)出色的表現(xiàn)。另一方面，人類非常有能力在低水平上表達(dá)他們實(shí)際想要的東西，適合直接在機(jī)器上實(shí)現(xiàn)。例如，當(dāng)視覺信息到達(dá)有意識的頭腦時，對象往往已經(jīng)被檢測到，幾乎沒有關(guān)于如何在第一位置識別對象的任何線索。當(dāng)48年前西摩·帕爾特（Seymour Papert）聚集了一批暑期工來解決計算機(jī)視覺問題時，這一點(diǎn)就已經(jīng)顯而易見[35]。人工學(xué)習(xí)系統(tǒng)可以克服人類視覺推理和低級機(jī)器視覺處理之間的差距。如果人類老師可以提供要提取的內(nèi)容的示例，并且學(xué)習(xí)系統(tǒng)能夠提取這些示例的要旨，則可以縮小差距。但是，對于學(xué)習(xí)系統(tǒng)，要使其在視覺環(huán)境中成功運(yùn)行，存在一些特殊要求。首先，低級視覺輸入通常是高維度的，因此學(xué)習(xí)系統(tǒng)需要處理大量輸入。第二，視覺信息常常是模棱兩可的，使得學(xué)習(xí)系統(tǒng)需要能夠處理多模態(tài)輸出，即多個假設(shè)。通常，要學(xué)習(xí)的關(guān)系是非線性的，并且即使可以在向?qū)W習(xí)系統(tǒng)展示許多示例之后，如果可以以視頻速率處理數(shù)據(jù)也存在優(yōu)勢。通常，似乎缺少這種方法。本文提出了一種用于學(xué)習(xí)具有視覺輸入的機(jī)器人系統(tǒng)的感知-動作映射的系統(tǒng)。討論了一系列問題，例如基于視覺的自動駕駛，機(jī)器人操縱器的逆運(yùn)動學(xué)和控制動力系統(tǒng)。提出了證明這些問題的解決方案的操作系統(tǒng)。探索了兩種提供訓(xùn)練數(shù)據(jù)的方法，即從示范學(xué)習(xí)（監(jiān)督學(xué)習(xí)）和探索性學(xué)習(xí)（自我監(jiān)督學(xué)習(xí)）。提出了一種滿足所述要求的新穎學(xué)習(xí)方法。 qHebb方法基于對通道表示中的數(shù)據(jù)的關(guān)聯(lián)Hebbian學(xué)習(xí)。該方法的特性在基于視覺的自動駕駛車輛上得到了證明，該系統(tǒng)在該系統(tǒng)上學(xué)會了直接將低級圖像特征映射到控制信號。經(jīng)過最初的培訓(xùn)后，系統(tǒng)將自動繼續(xù)無縫運(yùn)行。在定量評估中，所提出的在線學(xué)習(xí)方法與最新的批處理學(xué)習(xí)方法表現(xiàn)相當(dāng)。

著錄項(xiàng)

  • 作者

    ?fj?ll, Kristoffer;

  • 作者單位
  • 年度 2014
  • 總頁數(shù)
  • 原文格式 PDF
  • 正文語種 eng
  • 中圖分類

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
代理獲取

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號 ICP備案號：京ICP備15016152號-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號