[1]王东署,杨凯.基于状态转移学习的机器人行为决策认知模型[J].郑州大学学报(工学版),2021,42(06):8-14.[doi:10.13705/j.issn.1671-6833.2021.04.012]
　Wang Dongjun,Yang Kai,Behavior Decision-Making Cognitive Model of Mobile Robot ba＜x＞sed on State Transfer Learning[J].Journal of Zhengzhou University (Engineering Science),2021,42(06):8-14.[doi:10.13705/j.issn.1671-6833.2021.04.012]
点击复制

基于状态转移学习的机器人行为决策认知模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42
期数:
2021年06期
页码:
8-14
栏目:
出版日期:
2021-11-10

文章信息/Info

Title:
Behavior Decision-Making Cognitive Model of Mobile Robot ba＜x＞sed on State Transfer Learning
作者:
王东署; 杨凯
郑州大学电气工程学院;

Author(s):
Wang Dongjun; Yang Kai;
School of Electrical Engineering, Zhengzhou University;

关键词:
Keywords:
分类号:
TP242. 6
DOI:
10.13705/j.issn.1671-6833.2021.04.012
文献标志码:
A
摘要:
模拟人脑认知发育的过程，提出一种新的机器人行为决策认知模型。使用少量样本对发育网络进行训练，使其具备一些基本的行为决策能力。在每次执行任务结束后，机器人进入非工作状态，此时会触发状态转移学习机制。网络内部产生很多环境和决策的状态组合。通过评价机制可以找出能够针对某种环境采取合适决策的状态组合，网络经过对各种状态组合的学习，提高了在各种环境状态下的决策能力。通过发育网络中间层神经元的侧向激励机理，，记忆的知识量不断增多。该方法克服了传统机器人在未知环境中的适应性差以及针对不同的环境需要重新编程等问题。实验结果表明，这种发育模型能明显地改善机器人在未知环境下的适应性，使机器人可以通过不断积累经验应对各种复杂环境，提高行为决策的效果。
Abstract:
To simulate the process of human brain cognitive development, a new robot behavior decision cognitive model was proposed. Using a small number of samples to train the development network, it has some basic behavioral decision-making capabilities. After each execution of the task, the robot enters off-task process, at which time the state transition learning mechanism is triggered. There are many combinations of states and decisions within the network. Through the evaluation mechanism, it is possible to find the combination of states that can take appropriate decisions for a certain environment. The network learns various combinations of states to improve its decision-making ability in various environmental states. Through the development of the lateral stimulation mechanism of the neurons in the middle la＜x＞yer of the network, the amount of memory is constantly increasing. This method overcomes the problems of poor adaptability of traditional robots in unknown environments and the need to reprogram for different environments. Experimental results show that this development model can significantly improve the adaptability of robots in unknown environments, so that robots can accumulate experience to deal with various complex environments and improve the effect of behavioral decision-making

参考文献/References:

［1］ 常玉林，汪小渟，张鹏．改进蚁群算法在交通分配模 型中的应用［J］．郑州大学学报( 工学版) ，2017，38 ( 2) : 41－44，49． 

［2］ 蔡婉贞，黄翰．基于 BP-ＲBF 神经网络的组合模型预 测港口物流需求研究［J］．郑州大学学报( 工学版) ， 2019，40( 5) : 85－91． 
［3］ PATLE B K，PAＲHI D Ｒ K，JAGADEESH A，et al． Matrix-binary codes based genetic algorithm for path planning of mobile robot［J］． Computers ＆ electrical engineering，2018，67: 708－728． 
［4］ 徐霜，万强，余琍．基于学习理论的改进粒子群优化 算法［J］． 郑 州 大 学 学 报 ( 工 学 版) ，2019，40 ( 2) : 29－34． 
［5］ SHANAHAN M．A cognitive architecture that combines internal simulation with a global workspace ［J］． Consciousness and cognition，2006，15( 2) : 433－449． 
［6］ WENG J，MCCLELLAND J，PENTLAND A，et al． Artificial intelligence: autonomous mental development by robots and animals ［J］． Science，2001，291 ( 5504) : 599－600． 
［7］ DIＲAFZOON A，LOBATON E．Topological mapping of unknown environments using an unlocalized robotic swarm［C］/ /2013 IEEE/ＲSJ International Conference on Intelligent Ｒobots and Systems． Piscataway: IEEE， 2013: 5545－5551． 
［8］ LIU D，CONG M，DU Y，et al． Ｒobotic autonomous behavior selection using episodic memory and attention system［J］． Industrial robot: an international journal， 2017，44( 3) : 353－362． 
［9］ KAWAMUＲA K，GOＲDON S．From intelligent control to cognitive control ［C］/ /2006 World Automation Congress．Piscataway: IEEE，2006: 1－8． 
［10］ ISLAM N，HASEEB K，ALMOGＲEN A，et al．A frame- 
work for topological based map building: a solution to autonomous robot navigation in smart cities［J］．Future generation computer systems，2020，111: 644－653． 
［11］ OLCAY E，SCHUHMANN F，LOHMANN B．Collective navigation of a multi-robot system in an unknown environment［J］．Ｒobotics and autonomous systems，2020， 132: 103604． 
［12］ ZENG T P，TANG F Z，JI D X，et al． Neuro bayes SLAM: neurobiologically inspired bayesian integration of multisensory information for robot navigation［J］． Neural networks，2020，126: 21－35． 
［13］ WENG J． Artificial intelligence: autonomous mental development by robots and animals［J］．Science，2001， 291( 5504) : 599－600． 
［14］ SCASSELLATI B．Theory of mind for a humanoid robot ［J］．Autonomous robots，2002，12( 1) : 13－24． 
［15］ WANG D S，WANG J H，LIU L．Developmental network: an internal emergent object feature learning［J］．Neural processing letters，2018，48( 2) : 1135－1159． 
［16］ WANG D S，XIN J B．Emergent spatio-temporal multimodal learning using a developmental network［J］． Applied intelligence，2019，49( 4) : 1306－1323．
 ［17］ TAKEDA M． Brain mechanisms of visual long-term memory retrieval in primates ［J］． Neuroscience research，2019，142: 7－15． 
［18］ SOLGI M，LIU T S，WENG J Y．A computational developmental model for specificity and transfer in perceptual learning［J］． Journal of vision，2013，13 ( 1) : 1－23

更新日期/Last Update: 2021-12-17