D
Dongshu Wang
Researcher at Zhengzhou University
Publications - 36
Citations - 1276
Dongshu Wang is an academic researcher from Zhengzhou University. The author has contributed to research in topics: Computer science & Mobile robot. The author has an hindex of 6, co-authored 26 publications receiving 575 citations. Previous affiliations of Dongshu Wang include Michigan State University.
Papers
More filters
Journal ArticleDOI
Particle swarm optimization algorithm: an overview
Dongshu Wang,Dapei Tan,Lei Liu +2 more
TL;DR: Its origin and background is introduced and the theory analysis of the PSO is carried out, which analyzes its present situation of research and application in algorithm structure, parameter selection, topology structure, discrete PSO algorithm and parallel PSO algorithms, multi-objective optimization PSO and its engineering applications.
Journal ArticleDOI
Unknown environment exploration of multi-robot system with the FORDPSO
Dongshu Wang,Haitao Wang,Lei Liu +2 more
TL;DR: A formal analysis of RDPSO is presented and the influence of the coefficients on FORDPSO algorithm is studied, illustrating that biological and sociological inspiration is effective to meet the challenges of multi-robot system application in unknown environment exploration, and the exploration effect of the fuzzy adaptive FORD PSO is better than that of the fixed coefficient FORdPSO.
Journal ArticleDOI
Motivated Optimal Developmental Learning for Sequential Tasks Without Using Rigid Time-Discounts
TL;DR: This paper models reinforcement learning for hidden neurons in emergent networks for sequential tasks in dynamic scenarios using emergent representations and shows that the serotonin and dopamine systems speed up learning for sequential task, because not all events are equally important.
Journal ArticleDOI
Mobile robot navigation with the combination of supervised learning in cerebellum and reward-based learning in basal ganglia
TL;DR: A novel navigation model that realizes not only the two way communication between the cerebellum and basal ganglia, but also the co-development of them is proposed, which can enable the agent to autonomously development its intelligence through the hybrid learning.
Journal ArticleDOI
Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network
TL;DR: A novel way to provide the training samples for the neural network by leveraging the precise moving direction obtained by the fuzzy artificial potential field algorithm, which gets excellent path optimization ability.