Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter

doi:10.1017/S0263574722000297

	Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter
	Lu, Ning 2; Cai, Yinghao 1; Lu, Tao 1; Cao, Xiaoge 1; Guo, Weiyan 1; Wang, Shuo 1,3
刊名	ROBOTICA
	2022-03-25
页码	16
关键词	saliency Detection robot Learning push-grasp target-oriented Grasping deep Q Network
ISSN号	0263-5747
DOI	10.1017/S0263574722000297
通讯作者	Lu, Tao(tao.lu@ia.ac.cn)
英文摘要	"Picking out the impurities" is a typical scenario in production line which is both time consuming and laborious. In this article, we propose a target-oriented robotic push-grasping system which is able to actively discover and pick the impurities in dense environments with the synergies between pushing and grasping actions. First, we propose an attention module, which includes target saliency detection and density-based occluded-region inference. Without the necessity of expensive labeling of semantic segmentation, our attention module can quickly locate the targets in the view or predict the candidate regions where the targets are most likely to be occluded. Second, we propose a push-grasp synergy framework to sequentially select proper actions in different situations until all targets are picked out. Moreover, we introduce an active pushing mechanism based on a novel metric, namely Target-Centric Dispersion Degree (TCDD) for better grasping. TCDD describes whether the targets are isolated from the surrounding objects. With this metric, the robot becomes more focused on the actions around the targets and push irrelevant objects away. Experimental results on both simulated environment and real-world environment show that our proposed system outperforms several baseline approaches,which also has the capability to be generalized to new scenarios.
资助项目	National Key R&D Program of China[2019YFB1311901] ; National Natural Science Foundation of China[U1713222] ; National Natural Science Foundation of China[61773378]
WOS关键词	MODEL
WOS研究方向	Robotics
语种	英语
出版者	CAMBRIDGE UNIV PRESS
WOS记录号	WOS:000773134800001
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48189]
专题	智能机器人系统研究
通讯作者	Lu, Tao
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.China Waterborne Transport Res Inst, Beijing 100088, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Lu, Ning,Cai, Yinghao,Lu, Tao,et al. Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter[J]. ROBOTICA,2022:16.
APA	Lu, Ning,Cai, Yinghao,Lu, Tao,Cao, Xiaoge,Guo, Weiyan,&Wang, Shuo.(2022).Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter.ROBOTICA,16.
MLA	Lu, Ning,et al."Picking out the Impurities: Attention-based Push-Grasping in Dense Clutter".ROBOTICA (2022):16.