A Real 3D Embodied Dataset for Robotic Active Visual Learning
Zhao, Qianfan1,2; Zhang, Lu1,2; Wu, Lingxi2,4; Qiao, Hong1,2; Liu, Zhiyong1,2,3
Source PublicationIEEE ROBOTICS AND AUTOMATION LETTERS
ISSN2377-3766
2022-07-01
Volume7Issue:3Pages:6646-6652
Corresponding AuthorLiu, Zhiyong(zhiyong.liu@ia.ac.cn)
AbstractActive interaction with environments is one of the striking characteristics of robotic active vision, which allows robots to move to facilitate visual tasks. Recently, several embodied AI platforms have been proposed as the synthetic environments to study robotic active vision, without needing to interact in real world. However, by using synthetic data, model trained on these platforms will suffer performance degradation when applied in reality. In this letter, a real 3D embodied dataset is proposed for robotic active visual learning. The proposed dataset consists of real point cloud data densely collected in 7 real-world indoor scenes. In our embodied dataset, researchers are able to simulate the movements and interactions of robots in indoor environments and obtain real visual data, which will not lead to performance degradation in reality. Furthermore, we proposed a 3D divergency policy that can guide robots to move and collect data to improve visual performance in novel environments. The proposed policy is designed following a simple fact: a good 3D detector should produce consistent 3D detection results for the same object from different viewpoints. Therefore, our policy encourages the robot to explore the area where the detector generates different 3D bounding boxes for the same object and helps the robot improve its visual performance in novel scenes.
KeywordData sets for robotic vision deep learning for visual perception reinforcement learning
DOI10.1109/LRA.2022.3157028
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of ChineseAcademy of Science[XDB32050100] ; NSFC, China[61627808] ; NSFC, China[2019622101001]
Funding OrganizationNational Key Research and Development Plan of China ; Strategic Priority Research Program of ChineseAcademy of Science ; NSFC, China
WOS Research AreaRobotics
WOS SubjectRobotics
WOS IDWOS:000805161600004
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/49564
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Corresponding AuthorLiu, Zhiyong
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
4.Univ Calif Santa Barbara, Dept Math, Coll Letters & Sci, Santa Barbara, CA 93106 USA
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhao, Qianfan,Zhang, Lu,Wu, Lingxi,et al. A Real 3D Embodied Dataset for Robotic Active Visual Learning[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2022,7(3):6646-6652.
APA Zhao, Qianfan,Zhang, Lu,Wu, Lingxi,Qiao, Hong,&Liu, Zhiyong.(2022).A Real 3D Embodied Dataset for Robotic Active Visual Learning.IEEE ROBOTICS AND AUTOMATION LETTERS,7(3),6646-6652.
MLA Zhao, Qianfan,et al."A Real 3D Embodied Dataset for Robotic Active Visual Learning".IEEE ROBOTICS AND AUTOMATION LETTERS 7.3(2022):6646-6652.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Qianfan]'s Articles
[Zhang, Lu]'s Articles
[Wu, Lingxi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Qianfan]'s Articles
[Zhang, Lu]'s Articles
[Wu, Lingxi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Qianfan]'s Articles
[Zhang, Lu]'s Articles
[Wu, Lingxi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.