A Real 3D Embodied Dataset for Robotic Active Visual Learning

doi:10.1109/LRA.2022.3157028

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	A Real 3D Embodied Dataset for Robotic Active Visual Learning
	Zhao, Qianfan 1,2; Zhang, Lu1,2 ; Wu, Lingxi 2,4; Qiao, Hong1,2 ; Liu, Zhiyong1,2,3
发表期刊	IEEE ROBOTICS AND AUTOMATION LETTERS
ISSN	2377-3766
	2022-07-01
卷号	7 期号:3 页码:6646-6652
通讯作者	Liu, Zhiyong(zhiyong.liu@ia.ac.cn)
摘要	Active 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.
关键词	Data sets for robotic vision deep learning for visual perception reinforcement learning
DOI	10.1109/LRA.2022.3157028
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 ChineseAcademy of Science[XDB32050100] ; NSFC, China[61627808] ; NSFC, China[2019622101001]
项目资助者	National Key Research and Development Plan of China ; Strategic Priority Research Program of ChineseAcademy of Science ; NSFC, China
WOS研究方向	Robotics
WOS类目	Robotics
WOS记录号	WOS:000805161600004
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49564
专题	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 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
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,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.