Knowledge Commons of Institute of Automation,CAS
Semantic Policy Network for Zero-Shot Object Goal Visual Navigation | |
Zhao, Qianfan1,2; Zhang, Lu1,2; He, Bin3; Liu, Zhiyong1,2 | |
发表期刊 | IEEE ROBOTICS AND AUTOMATION LETTERS |
ISSN | 2377-3766 |
2023-11-01 | |
卷号 | 8期号:11页码:7655-7662 |
摘要 | The task of zero-shot object goal visual navigation (ZSON) aims to enable robots to locate previously "unseen" objects by visual observations. This task presents a significant challenge since the robot must transfer the navigation policy learned from "seen" objects to "unseen" objects through auxiliary semantic information without training samples, a process known as zero-shot learning. In order to address this challenge, we propose a novel approach termed the Semantic Policy Network (SPNet). The SPNet consists of two modules that are deeply integrated with semantic embeddings: the Semantic Actor Policy (SAP) module and the Semantic Trajectory (ST) module. The SAP module generates actor network weight bias based on semantic embeddings, creating unique navigation policies for different target classes. The ST module records the robot's actions, visual features, and semantic embeddings at each step, and aggregates information in both the spatial and temporal dimensions. To evaluate our approach, we conducted extensive experiments using MP3D dataset, HM3D dataset, and RoboTHOR. Experimental results indicate that the proposed method outperforms other ZSON methods for both seen and unseen target classes. |
关键词 | Deep learning path planning reinforcement learning vision-based navigation |
DOI | 10.1109/LRA.2023.3320014 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100] ; NSFC[62206288] |
项目资助者 | National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Academy of Science ; NSFC |
WOS研究方向 | Robotics |
WOS类目 | Robotics |
WOS记录号 | WOS:001085222400013 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 机器人感知与决策 |
国重实验室规划方向分类 | 其他 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/54290 |
专题 | 多模态人工智能系统全国重点实验室 多模态人工智能系统全国重点实验室_机器人理论与应用 |
通讯作者 | Liu, Zhiyong |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodel Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 3.Tongji Univ, Coll Elect & Informat Engn, Shanghai 200070, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhao, Qianfan,Zhang, Lu,He, Bin,et al. Semantic Policy Network for Zero-Shot Object Goal Visual Navigation[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2023,8(11):7655-7662. |
APA | Zhao, Qianfan,Zhang, Lu,He, Bin,&Liu, Zhiyong.(2023).Semantic Policy Network for Zero-Shot Object Goal Visual Navigation.IEEE ROBOTICS AND AUTOMATION LETTERS,8(11),7655-7662. |
MLA | Zhao, Qianfan,et al."Semantic Policy Network for Zero-Shot Object Goal Visual Navigation".IEEE ROBOTICS AND AUTOMATION LETTERS 8.11(2023):7655-7662. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Zhao 等 - 2023 - Sema(1888KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论