Caging a novel object using multi-task learning method | |
Su, Jianhua1; Chen, Bin2; Qiao, Hong1; Liu, Zhi-yong1 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2019-07-25 | |
卷号 | 351页码:146-155 |
通讯作者 | Su, Jianhua(jianhua.su@ia.ac.cn) |
摘要 | Caging grasps provide a way to manipulate an object without full immobilization and enable dealing with the pose uncertainties of the object. Most previous works have constructed caging sets by using the geometric models of the object. This work aims to present a learning-based method for caging a novel object only with its image. A caging set is first defined using the constrained region, and a mapping from the image feature to the caging set is then constructed with kernel regression function. Avoiding the collection of large number of samples, a multi-task learning method is developed to build the regression function, where several different caging tasks are trained with a joint model. In order to transfer the caging experience to a new caging task rapidly, shape similarity for caging knowledge transfer is utilized. Thus, given only the shape context for a novel object, the learner is able to accurately predict the caging set through zero-shot learning. The proposed method can be applied to the caging of a target object in a complex real-world environment, for which the user only needs to know the shape feature of the object, without the need for the geometric model. Several experiments prove the validity of our method. (C) 2019 Elsevier B.V. All rights reserved. |
关键词 | Multi-task learning Grasping Kernel regression |
DOI | 10.1016/j.neucom.2019.03.063 |
关键词[WOS] | REGRESSION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Science and Technology on Space Intelligent Control Laboratory[HTKJ2019KL502013] ; NSFC[91848109] ; Beijing Natural Science Foundation[4182068] ; NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization[U1509212] ; NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization[U1509212] ; Beijing Natural Science Foundation[4182068] ; NSFC[91848109] ; Science and Technology on Space Intelligent Control Laboratory[HTKJ2019KL502013] |
项目资助者 | NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization ; Beijing Natural Science Foundation ; NSFC ; Science and Technology on Space Intelligent Control Laboratory |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000467803400015 |
出版者 | ELSEVIER SCIENCE BV |
七大方向——子方向分类 | 机器人感知与决策 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/24218 |
专题 | 复杂系统管理与控制国家重点实验室_机器人理论与应用 |
通讯作者 | Su, Jianhua |
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, Beijing 100190, 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 | Su, Jianhua,Chen, Bin,Qiao, Hong,et al. Caging a novel object using multi-task learning method[J]. NEUROCOMPUTING,2019,351:146-155. |
APA | Su, Jianhua,Chen, Bin,Qiao, Hong,&Liu, Zhi-yong.(2019).Caging a novel object using multi-task learning method.NEUROCOMPUTING,351,146-155. |
MLA | Su, Jianhua,et al."Caging a novel object using multi-task learning method".NEUROCOMPUTING 351(2019):146-155. |
条目包含的文件 | 条目无相关文件。 |
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