Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network
Wang, Yunpeng; Cheng, Long; Hou, ZengGuang; Yu, Junzhi; Tan, Min
2016-02-01
发表期刊IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷号27期号:2页码:322-333
文章类型Article
摘要The optimal formation problem of multirobot systems is solved by a recurrent neural network in this paper. The desired formation is described by the shape theory. This theory can generate a set of feasible formations that share the same relative relation among robots. An optimal formationmeans that finding one formation from the feasible formation set, which has the minimum distance to the initial formation of the multirobot system. Then, the formation problem is transformed into an optimization problem. In addition, the orientation, scale, and admissible range of the formationcan also be considered as the constraints in the optimization problem. Furthermore, if all robots are identical, their positions in the system are exchangeable. Then, each robot does not necessarily move to one specific position in the formation. In this case, the optimal formation problem becomes a combinational optimization problem, whose optimal solution is very hard to obtain. Inspired by the penalty method, this combinational optimization problem can be approximately transformed into a convex optimization problem. Due to the involvement of the Euclidean norm in the distance, the objective function of these optimization problems are nonsmooth. To solve these nonsmooth optimization problems efficiently, a recurrent neural network approach is employed, owing to its parallel computation ability. Finally, some simulations and experiments are given to validate the effectiveness and efficiency of the proposed optimal formation approach.
关键词Combinational Optimization Problem Multirobot System Optimal Formation Recurrent Neural Network Shape Theory
WOS标题词Science & Technology ; Technology
DOI10.1109/TNNLS.2015.2464314
关键词[WOS]NONLINEAR VARIATIONAL-INEQUALITIES ; CONVEX-OPTIMIZATION PROBLEMS ; NONHOLONOMIC MOBILE ROBOTS ; CONSTRAINED OPTIMIZATION ; COOPERATIVE CONTROL ; PREDICTIVE CONTROL ; STRATEGIES
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61370032 ; Beijing Nova Program(Z121101002512066) ; 61422310 ; 61375102 ; 61225017 ; 61421004)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000372020500011
引用统计
被引频次:27[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/173211/11370
专题复杂系统管理与控制国家重点实验室_先进机器人
通讯作者Cheng, Long
作者单位State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714
Wang, Yunpeng,Cheng, Long,Hou, ZengGuang,et al. Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2016,27(2):322-333.
APA Wang, Yunpeng,Cheng, Long,Hou, ZengGuang,Yu, Junzhi,&Tan, Min.(2016).Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,27(2),322-333.
MLA Wang, Yunpeng,et al."Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 27.2(2016):322-333.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
50-Optimal Formation(2069KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Yunpeng]的文章
[Cheng, Long]的文章
[Hou, ZengGuang]的文章
百度学术
百度学术中相似的文章
[Wang, Yunpeng]的文章
[Cheng, Long]的文章
[Hou, ZengGuang]的文章
必应学术
必应学术中相似的文章
[Wang, Yunpeng]的文章
[Cheng, Long]的文章
[Hou, ZengGuang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 50-Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。