[1]张珂,陈奇.基于非受限路径自然语言处理中的机器人导航[J].智能系统学报,2017,(04):482-490.[doi:10.11992/tis.201607016]
 ZHANG Ke,CHEN Qi.Robot navigation based on non-restricted route natural language processing[J].CAAI Transactions on Intelligent Systems,2017,(04):482-490.[doi:10.11992/tis.201607016]
点击复制

基于非受限路径自然语言处理中的机器人导航(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
期数:
2017年04期
页码:
482-490
栏目:
出版日期:
2017-08-25

文章信息/Info

Title:
Robot navigation based on non-restricted route natural language processing
作者:
张珂 陈奇
华北电力大学 电子与通信工程系, 河北 保定 071003
Author(s):
ZHANG Ke CHEN Qi
Department of Electronic and Communication, North China Electric Power University Code, Baoding 071003, China
关键词:
语义角色标注路径自然语言语块分析依存句法分析机器人问路导航
Keywords:
semantic role labelingroute natural languagechunkingdependency parsingrobot navigation by asking the way
分类号:
TP18
DOI:
10.11992/tis.201607016
摘要:
为了实现使用自然语言控制机器人完成自主导航任务,提出一种基于语义角色标注(SRL)的语义提取方法,用于提高机器人对路径自然语言理解的准确率。首先,收集了一个非受限的路径自然语言语料库,在深入研究路径自然语言语料库的基础上,提出了8个语块对语料进行语块分析,完成语义角色标注;然后,对语料进行依存句法分析,完成语义角色标注;接着,结合语块分析和依存句法分析,提出了一种基于语块分析和依存句法分析的语义角色标注方法,实验结果得到的准确率、召回率、F1-值分别达到了98.22%、98.48%和98.35%;最后,基于语义提取结果在机器人Nao平台上完成了机器人问路导航任务。
Abstract:
In order to use a natural-language controlled robot to complete autonomous navigation, this paper proposes a semantic extraction method based on semantic role labeling (SRL), which is used to enhance the understanding of route natural language for robots. First, a non-restricted route natural language corpus is constructed. Then, based on thorough study of this corpus, eight chunks are put forward to analyze the data, which lays the foundation for SRL. Finally, an SRL based on chunking and dependency parsing is proposed. The experimental results of precision, recall, and F1-measurements were 98.22%, 98.48%, and 98.35%, respectively. Using the proposed SRL method, the robot Nao was able to accomplish navigation tasks by asking the way.

参考文献/References:

[1] WEI Y, BRUNSKILL E, KOLLAR T, et al. Where to go:Interpreting natural directions using global inference[C]//IEEE International Conference on Robotics and Automation. Kobe, Japan, 2009:3761-3767.
[2] KOLLAR T, TELLEX S, ROY D, et al. Toward understanding natural language directions[C]//20105th ACM/IEEE International Conference on Human-Robot Interaction(HRI). Osaka, Japan, 2010:259-266.
[3] SKUBIC M, PERZANOWSKI D, BLISARD S, et al. Spatial language for human-robot dialogs[J]. IEEE transactions on systems, man, and cybernetics, part c:applications and reviews, 2004, 34(2):154-167.
[4] SKUBIC M, HUO Z, ALEXENKO T, et al. Testing an assistive fetch robot with spatial language from older and younger adults[C]//RO-MAN, 2013 IEEE. Gyeongju, South Korea, 2013:697-702.
[5] SKUBIC M, HUO Z, CARLSON L A, et al. Human-driven spatial language for human-robot interaction[C]//AAAI Conference on Human-Robot Interaction in Elder Care. San Francisco, USA, 2011:32-34.
[6] LI X, HUANG X, DEZERT J, et al. A successful applicat ion of DSmT in sonar grid map building and comparison with DST-based approach[J]. International journal of innovative computing, information and control, 2007, 3(3):539-549.
[7] LI X, DEZERT J, SMARANDACHE F, et al. Evidence support ing measure of similarity for reducing the complexity in informat ion fusion[J]. Information sciences, 2011, 181(10):1818-1835.
[8] 石朝侠,洪炳镕,周彤,等. 大规模环境下的拓扑地图创建与导航[J]. 机器人, 2007, 29(5):433-438.SHI Chaoxia, HONG Bingrong, ZHOU Tong, et al. Topological map building and navigation in large-scale environment ents[J]. Robot, 2007, 29(5):433-438.
[9] 庄严,徐晓东,王伟.移动机器人几何-拓扑混合地图的构建及自定位研究[J]. 控制与决策, 2005, 20(7):815-818.ZHUANG Yan, XU Xiaodong, WANG Wei. Mobile robot geometric-topological map building and self-localization[J]. Control and decision, 2005, 20(7):815-818.
[10] 张秀龙,李新德,戴先中.基于组块分析的路径自然语言语义角色标注方法[J]. 东南大学学报:自然科学版, 2012, 42(z1):127-131.ZHANG Xiulong, LI Xingde, DAI Xianzhong. Semantic role labeling method for route natural language based on chunk parsing[J]. Journal of southeast university:natural science edition, 2012, 42(zl):127-131.
[11] 李新德, 张秀龙, 戴先中.一种基于受限自然语言处理的移动机器人视觉导航方法[J]. 机器人, 2011, 33(6):742-749.LI Xingde, ZHANG Xiulong, DAI Xianzhong. A visual navigation method of mobile robot based on constrained natural language processing[J]. Robot, 2011, 33(6):742-749.
[12] 李新德, 张秀龙.一种面向室内智能机器人导航的路径自然语言处理方法[J]. 自动化学报, 2012, 40(2):289-305.LI Xinde, ZHANG Xiulong. A route instruction method using natural language processing for indoor intelligent robot navigation[J]. Acta automatica sinica, 2012, 40(2):289-305.
[13] ABNEY S P. Parsing by chunks[M]//Principle-Based Parsing. Springer Netherlands, 1991:257-278.
[14] 周强,孙茂松,黄昌宁.汉语句子的组块分析体系[J]. 计算机学报, 1999, 22(11):1158-1165.ZHOU Qiang,SUN Maosong, HUANG Changning. Chunk parsing scheme for Chinese sentences[J]. Chinese journal of computers, 1999, 22(11):1158-1165.
[15] 李素建,刘群.汉语组块的定义和获取[C]//全国计算语言学联合学术会议. 苏州,中国, 2003:110-115.LI SUJIAN, LIU QUN. Research on definition and acquisition of chunk[C]//CCL 2016. Suzhou, China, 2003:110-115.
[16] 孙宏林, 俞士汶.浅层句法分析方法概述[J]. 当代语言学, 2000, 2(2):74-83.SUN HONGLIN, YU SHIWEN. A summary of shallow parsing methods[J]. Contemporary linguistics, 2000, 2(2):74-83.
[17] 计峰, 邱锡鹏. 基于序列标注的中文依存句法分析方法[J]. 计算机应用与软件, 2009, 26(10):133-135.JI FENG, QIU XIPENG. A new Chinese dependence analysis method based on sequence labeling model[J]. Computer applications and software, 2009, 26(10):133-135.

备注/Memo

备注/Memo:
收稿日期:2016-07-18。
基金项目:国家自然科学基金项目(61302163,61302105);河北省自然科学基金项目(Ff2015502062);中央高校基本科研经费项目(2016MS99).
作者简介:张珂,男,1980年生,副教授,人工智能学会会员,计算机学会会员。主要研究方向为电力智能信息处理、图像处理、自然语言处理、机器人认知;陈奇,男,1992年生,硕士研究生,主要研究方向为自然语言处理。
通讯作者:张珂,E-mail:zhangke41616@126.com.
更新日期/Last Update: 2017-08-25