SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks | |
Zuo, Guoyu3; Pan, Tingting3; Zhang, Tielin2; Yang, Yang1 | |
刊名 | COGNITIVE COMPUTATION
![]() |
2020-03-06 | |
页码 | 14 |
关键词 | Cognitive planning SOAR Deep neural network Decision-making Robot grasping task |
ISSN号 | 1866-9956 |
DOI | 10.1007/s12559-020-09716-6 |
通讯作者 | Zuo, Guoyu(zuoguoyu@bjut.edu.cn) |
英文摘要 | Recently, artificial neural networks (ANNs) have been applied to various robot-related research areas due to their powerful spatial feature abstraction and temporal information prediction abilities. Decision-making has also played a fundamental role in the research area of robotics. How to improve ANNs with the characteristics of decision-making is a challenging research issue. ANNs are connectionist models, which means they are naturally weak in long-term planning, logical reasoning, and multistep decision-making. Considering that a small refinement of the inner network structures of ANNs will usually lead to exponentially growing data costs, an additional planning module seems necessary for the further improvement of ANNs, especially for small data learning. In this paper, we propose a state operator and result (SOAR) improved ANN (SANN) model, which takes advantage of both the long-term cognitive planning ability of SOAR and the powerful feature detection ability of ANNs. It mimics the cognitive mechanism of the human brain to improve the traditional ANN with an additional logical planning module. In addition, a data fusion module is constructed to combine the probability vector obtained by SOAR planning and the original data feature array. A data fusion module is constructed to convert the information from the logical sequences in SOAR to the probabilistic vector in ANNs. The proposed architecture is validated in two types of robot multistep decision-making experiments for a grasping task: a multiblock simulated experiment and a multicup experiment in a real scenario. The experimental results show the efficiency and high accuracy of our proposed architecture. The integration of SOAR and ANN is a good compromise between logical planning with small data and probabilistic classification with big data. It also has strong potential for more complicated tasks that require robust classification, long-term planning, and fast learning. Some potential applications include recognition of grasping order in multiobject environment and cooperative grasping of multiagents. |
资助项目 | Beijing Natural Science Foundation[4182008] ; National Natural Science Foundation of China[61806195] ; National Natural Science Foundation of China[61873008] ; Beijing Academy of Artificial Intelligence (BAAI) |
WOS关键词 | TREE ; MANIPULATION ; ARCHITECTURE |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:000562307600001 |
资助机构 | Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Beijing Academy of Artificial Intelligence (BAAI) |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/40536] ![]() |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Zuo, Guoyu |
作者单位 | 1.Peking Univ, Sch Software & Microelect, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Zuo, Guoyu,Pan, Tingting,Zhang, Tielin,et al. SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks[J]. COGNITIVE COMPUTATION,2020:14. |
APA | Zuo, Guoyu,Pan, Tingting,Zhang, Tielin,&Yang, Yang.(2020).SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks.COGNITIVE COMPUTATION,14. |
MLA | Zuo, Guoyu,et al."SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks".COGNITIVE COMPUTATION (2020):14. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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