中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Model-Agnostic Metalearning-Based Text-Driven Visual Navigation Model for Unfamiliar Tasks

文献类型:期刊论文

作者Xue TF(薛天放)1,2,3,4; Yu HB(于海斌)1,2,4
刊名IEEE ACCESS
出版日期2020
卷号8页码:166742-166752
关键词Navigation Task analysis Visualization Adaptation models Semantics Robots Feature extraction Mapless-visual navigation semantic segmentation text-driven model-agnostic meta-learning
ISSN号2169-3536
产权排序1
英文摘要

As vision and language processing techniques have made great progress, mapless-visual navigation is occupying uppermost position in domestic robot field. However, most current end-to-end navigation models tend to be strictly trained and tested on identical datasets with stationary structure, which leads to great performance degradation when dealing with unseen targets and environments. Since the targets of same category could possess quite diverse features, generalization ability of these models is also limited by their visualized task description. In this article we propose a model-agnostic metalearning based text-driven visual navigation model to achieve generalization to untrained tasks. Based on meta-reinforcement learning approach, the agent is capable of accumulating navigation experience from existing targets and environments. When applied to finding a new object or exploring in a new scene, the agent will quickly learn how to fulfill this unfamiliar task through relatively few recursive trials. To improve learning efficiency and accuracy, we introduce fully convolutional instance-aware semantic segmentation and Word2vec into our DRL network to respectively extract visual and semantic features according to object class, creating more direct and concise linkage between targets and their surroundings. Several experiments have been conducted on realistic dataset Matterport3D to evaluate its target-driven navigation performance and generalization ability. The results demonstrate that our adaptive navigation model could navigate to text-defined targets and achieve fast adaption to untrained tasks, outperforming other state-of-the-art navigation approaches.

WOS关键词SEARCH
资助项目National Key Research and Development Program of China[2018YFB1700200] ; National Natural Science Foundation of China[61803368] ; National Natural Science Foundation of China[61533015] ; National Natural Science Foundation of China[61972389] ; National Natural Science Foundation of China[61903356] ; China Postdoctoral Science Foundation[2019M661156] ; Liaoning Provincial Natural Science Foundation of China[20180540114] ; Liaoning Provincial Natural Science Foundation of China[20180520029] ; Youth Innovation Promotion Association CAS ; Independent Subject of State Key Laboratory of Robotics
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000572972100001
资助机构National Key Research and Development Program of China [2018YFB1700200] ; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61803368, 61533015, 61972389, 61903356] ; China Postdoctoral Science FoundationChina Postdoctoral Science Foundation [2019M661156] ; Liaoning Provincial Natural Science Foundation of China [20180540114, 20180520029] ; Youth Innovation Promotion Association CAS ; Independent Subject of State Key Laboratory of Robotics
源URL[http://ir.sia.cn/handle/173321/27689]  
专题沈阳自动化研究所_工业控制网络与系统研究室
通讯作者Yu HB(于海斌)
作者单位1.Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
推荐引用方式
GB/T 7714
Xue TF,Yu HB. Model-Agnostic Metalearning-Based Text-Driven Visual Navigation Model for Unfamiliar Tasks[J]. IEEE ACCESS,2020,8:166742-166752.
APA Xue TF,&Yu HB.(2020).Model-Agnostic Metalearning-Based Text-Driven Visual Navigation Model for Unfamiliar Tasks.IEEE ACCESS,8,166742-166752.
MLA Xue TF,et al."Model-Agnostic Metalearning-Based Text-Driven Visual Navigation Model for Unfamiliar Tasks".IEEE ACCESS 8(2020):166742-166752.

入库方式: OAI收割

来源:沈阳自动化研究所

浏览0
下载0
收藏0
其他版本

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。