Neural network based FastSLAM for autonomous robots in unknown environments
Li, Qing-Ling1; Song, Yu2; Hou, Zeng-Guang3
2015-10-01
发表期刊NEUROCOMPUTING
卷号2015期号:165页码:99-110
文章类型Article
摘要Map learning and self-localization based on perception of the environment's structure are fundamental capacities required for intelligent robots to realize true autonomy. Simultaneous Localization and Mapping (SLAM) is an effective technique for such robots, as it addresses the problem of incrementally building an environment map from noisy sensory data and tracking the robot's path with the built map. As a popular SLAM solution, FastSLAM suffers from limitation on error accumulation introduced by incorrect odometry model and inaccurate linearization of the SLAM nonlinear functions. To overcome the problem, a new Jacobian free neural network (NN) based FastSLAM algorithm is derived and discussed in this paper. The main contribution of the algorithm is twofold: on the one hand, the odometry error is online compensated by using a multilayer NN, and the NN is online trained during the SLAM process; on the other hand, the third-degree Cubature rule for Gaussian weighted integral, which calculates nonlinear transition density of Gaussian prior up to the 3rd order nonlinearity, is utilized to estimate the SLAM state (i.e., the robot path and environment map) and to online train the NN compensator. The performance of proposed SLAM is investigated and compared with that of popular FastSLAM2.0 in simulations and experiments. Results show that the proposed method improves the SLAM performance. (C) 2015 Elsevier B.V. All rights reserved.
关键词Autonomous Robot Simultaneous Localization And Mapping (Slam) Neural Network Particle Filter Gaussian Weighted Integral (Gwi) Cubature Rule
WOS标题词Science & Technology ; Technology
关键词[WOS]EXTENDED KALMAN FILTER ; NONHOLONOMIC MOBILE ROBOT ; SIMULTANEOUS LOCALIZATION ; TRACKING CONTROL ; SLAM PROBLEM ; ODOMETRY ; EFFICIENT ; ALGORITHM ; VISION ; ROBUST
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000356747700013
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/7907
专题复杂系统管理与控制国家重点实验室_先进机器人
作者单位1.China Univ Min & Technol, Sch Mech Elect & Informat Engn, Beijing, Peoples R China
2.Beijing Jiaotong Univ, Sch Elect & Informat Engn, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Li, Qing-Ling,Song, Yu,Hou, Zeng-Guang. Neural network based FastSLAM for autonomous robots in unknown environments[J]. NEUROCOMPUTING,2015,2015(165):99-110.
APA Li, Qing-Ling,Song, Yu,&Hou, Zeng-Guang.(2015).Neural network based FastSLAM for autonomous robots in unknown environments.NEUROCOMPUTING,2015(165),99-110.
MLA Li, Qing-Ling,et al."Neural network based FastSLAM for autonomous robots in unknown environments".NEUROCOMPUTING 2015.165(2015):99-110.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
27%7bNeural network (3788KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Qing-Ling]的文章
[Song, Yu]的文章
[Hou, Zeng-Guang]的文章
百度学术
百度学术中相似的文章
[Li, Qing-Ling]的文章
[Song, Yu]的文章
[Hou, Zeng-Guang]的文章
必应学术
必应学术中相似的文章
[Li, Qing-Ling]的文章
[Song, Yu]的文章
[Hou, Zeng-Guang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 27%7bNeural network based FastSLAM for autonomous robots in unknown environments%7d.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。