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> 外文期刊>Journal of Mechanical Science and Technology >Self-learning navigation algorithm for vision-based mobile robots using machine learning algorithms
【24h】

Self-learning navigation algorithm for vision-based mobile robots using machine learning algorithms

機(jī)譯:使用機(jī)器學(xué)習(xí)算法的基于視覺的移動(dòng)機(jī)器人自學(xué)習(xí)導(dǎo)航算法

獲取原文
獲取原文并翻譯 | 示例

摘要

Many mobile robot navigation methods use, among others, laser scanners, ultrasonic sensors, vision cameras for detecting obstacles and following paths. However, humans use only visual (e.g. eye) information for navigation. In this paper, we propose a mobile robot control method based on machine learning algorithms which use only camera vision. To efficiently define the state of the robot from raw images, our algorithm uses image-processing and feature selection steps to choose the feature subset for a neural network and uses the output of the neural network learned through supervised learning. The output of the neural network uses the state of a reinforcement learning algorithm to learn obstacle-avoiding and path-following strategies using camera vision image. The algorithm is verified by two experiments, which are line tracking and obstacle avoidance.
機(jī)譯:除其他外,許多移動(dòng)機(jī)器人導(dǎo)航方法都使用激光掃描儀,超聲波傳感器,視覺相機(jī)來檢測障礙物和跟隨路徑。但是,人類僅將視覺(例如眼睛)信息用于導(dǎo)航。在本文中,我們提出了一種基于機(jī)器學(xué)習(xí)算法的移動(dòng)機(jī)器人控制方法,該算法僅使用相機(jī)視覺。為了從原始圖像有效地定義機(jī)器人的狀態(tài),我們的算法使用圖像處理和特征選擇步驟來選擇神經(jīng)網(wǎng)絡(luò)的特征子集,并使用通過監(jiān)督學(xué)習(xí)獲得的神經(jīng)網(wǎng)絡(luò)的輸出。神經(jīng)網(wǎng)絡(luò)的輸出使用強(qiáng)化學(xué)習(xí)算法的狀態(tài)來使用相機(jī)視覺圖像學(xué)習(xí)避障和路徑遵循策略。通過兩個(gè)實(shí)驗(yàn)驗(yàn)證了算法的有效性,分別是線跟蹤和避障。

著錄項(xiàng)

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

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