Behavior Decision-making Cognitive Model of Mobile Robot Based on State Transfer Learning

NAVIGATE

Table of Contents

STATISTICS

Viewed2085

Downloads735

Behavior Decision-making Cognitive Model of Mobile Robot Based on State Transfer Learning

[HTML] PDF下载 (735)

[1]Wang Dongjun,Yang Kai,Behavior Decision-making Cognitive Model of Mobile Robot Based 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]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 42 Number of periods: 2021 06 Page number: 8-14 Column: Public date: 2021-11-10

Title:: Behavior Decision-making Cognitive Model of Mobile Robot Based on State Transfer Learning

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

Keywords:: behavior decision-making; state transfer; developmental neural network; continuous learning; adaptability

CLC:: TP242. 6

DOI:: 10.13705/j.issn.1671-6833.2021.04.012

Abstract:: Due to the small sample size of traditional neural networks, the error rate of the recognition of the scene was very high, and it could not continuously learn during the execution of the task. This would lead to poor adaptability of traditional neural networks to unfamiliar environments. In response to these problems, a bionic robot behavior decision-making cognitive computing model was proposed. The algorithm used semi-supervised and state transition learning methods. Firstly, a small number of training samples were used to train the developmental neural network, so that it could have some basic behavioral decision-making capabilities. When the robot was exploring in the actual environment, it could continuously learn new unlearned scene data. When the robot completed the task, the network model would recall the specific scene it had experienced according to a certain probability, and combined the state transfer mechanism to continuously adjusted its own decision-making effect. This method could make the network model quickly converge to a stable state, and had strong adaptability in unknown environments. In order to verify the feasibility of the model, a real robot operating environment was designed, and the RIKIROBOT was used for navigation testing. Experimental results showed that this developmental model could converge to a stable state after 3 to 5 decision-making adjustments in an unknown environment, and the decision-making effect was continuously improved. Robots could deal with various complex environments by continuously accumulating knowledge, and had strong adaptability in unknown environments.

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

Similar References:

Memo

Last Update: 2021-12-17