DAI Lab@RUC

[20210913] Welcome our new members to the lab.
[20210903] Our manuscript "Batch-Based Learning Consensus of Multi-Agent Systems With Faded Neighborhood Information" has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems. This work was done by Mr. Qu, Prof. Yu, and me.
[20210825] Prof. Xuhui Bu from Henan Polytechnic University has been invited to present a talk on event-triggered iterative learning control.
[20210820] We have been approved a Key Project from Beijing Natural Science Foundation with the topic of "Mathematical Theory of Distributed Artificial Intelligence and Its Applications in Financial Risk Perception".
[20210818] We have been approved a research fund from National Natural Science Foundation of China with the topic of "Framework and Techniques of Iterative Learning Control Based on System Cognition".
[20210817] The paper "Noisy Output Based Direct Learning Tracking Control with Markov Nonuniform Trial Lengths Using Adaptive Gains" has been accepted for publication in IEEE Transactions on Automatic Control.
[20210810] Prof. Jia Shi from Xiamen University has been invited to deliver a talk on learning control.
[20210716] Prof. Shen won Second Prize in The 12th Teaching Competition for Young Teachers in Beijing Universities.
[20210708] Prof. Xingmin Chen from Dalian University of Technology has been invited to deliver a talk on distributed stochastic optimization.
[20210629] The paper "Iterative learning control for impulsive multi-agent systems with varying trial lengths" has been accepted for publication in Nonlinear Analysis: Modelling and Control. This work was led by Prof. JinRong Wang.
[20210629] Prof. Ronghu Chi from Qingdao University of Science and Technology has been invited to deliver a talk on dynamic linearization technique.
[20210628] Prof. Dazi Li from Beijing University of Chemical Technology has been invited to deliver a talk on reinforcement learning.
[20210624] Prof. Xuefang Li from Sun Yat-sen University has been invited to deliver a talk on iterative learning control for nonlinear systems.
[20210624] Prof. Biqiang Mu from the Academy of Mathematics and Systems Science, Chinese Academy of Sciences, has been invited to deliver a talk on system identification.
[20210612] Congratulations to Ganggui Qu and Niu Huo, who have obtained their Master Degree in Engineering. Congratulations to Yanze Liu, who has obtaned his Bachelor Degree in Engineering. [Pic]
[20210604] Our papge "Learning Tracking Control Over Unknown Fading Channels Without System Information" has been officially assigned in an issue of IEEE Transactions on Neural Networks and Learning Systems (vol. 32, no. 6, pp. 2721-2732).
[20210529] Our paper "Averaging Techniques for Balancing Learning and Tracking Abilities Over Fading Channels" has been offcially assigned in an issue of IEEE Transactions on Automatic Control (vol. 66, no. 6, pp. 2636-2651).
[20210529] Our manuscript, titled "A Probabilistically Quantized Learning Control Framework for Networked Linear Systems", has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems.
[20210525] Our manuscript, titled "Convergence Analysis for Iterative Learning Control of Impulsive Linear Discrete Delay Systems", has been accepted for publication in Journal of Difference Equations and Applications. This worked was led by Prof. Jinrong Wang.
[20210407] Prof. Shen has won the First Prize of the 11th Teaching Competition for Young Teachers at RUC.
[20210401] Our manuscript, titled "Learning Control for Networked Stochastic Systems With Random Fading Communication", has been accepted for publication in IEEE Transactions on Systems, Man, and Cybernetics-Systems. This work is collaborated with Mr. Ganggui Qu and Assoc. Prof. Qijiang Song.
[20210326] Our manuscript, titled "An Efficient Algorithm for Collaborative Learning Model Predictive Control of Nonlinear Systems", has been accepted for publication in ISA Transactions. This work is collaborated with Mr. Yanze Liu.
[20210223] Our manuscript, titled "Iterative Learning Control for Output Tracking of Nonlinear Systems With Unavailable State Information", has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems. This work is led by Prof. Xuefang Li and collaborated with Prof. Beichen Ding from Sun Yat-Sen University.
[20210221] Our manuscript, titled "Iterative Learning Control: Practical Implementation and Automation", has been accepted for publication in IEEE Transactions on Industrial Electronics. This work is collaborated with Prof. Samer Saab.
[20210219] The paper "Iterative Learning Tracking for Multi-Sensor Systems: A Weighted Optimization Approach" has been assigned in an issue of IEEE Transactions on Cybernetics (vol. 51, no. 3, pp. 1286-1299).
[20210112] The paper "An Iterative Learning Control Algorithm with Gain Adaptation for Stochastic Systems" wins Outstanding Research Achievement Award of Renmin University of China. [PaperLink][NewsCover]
[20210102] The paper "Iterative Learning Control for Multi-Agent Systems with Impulsive Consensus Tracking" has been assigned in an issue of Nonlinear Analysis: Modelling and Control. [WebLink]
[20210101] Our annual report for 2020 has been released.
[20210101] We, DAI Lab, wish all of you Happy 2021.

Our recent focus is learning control with fading channels. A fading channel indicates the unreliable communication network that the transmitted signal would suffer multiplicative randomness. Such randomness is generally modeled by a random variable with its expectation away from 1; thus, the received signal is usually biased in the sense that its expectation is not the original signal. Consequently, a correction is necessary for the received signal before the following procedures. The primary issue in this direction is how to correct the received signals.
If the statistics information (especially the mean) of the fading channel is known, a direct correction can be made by multiplying the mean inverse to the received signals. The design and analysis are given in [TSMC: Syst-2021]. We notice that the corrected input is involved with large disturbances, which may significantly affect the dynamics of the plant. To address this issue, we proposed an iteration domain moving averaging operator for the received inputs. The results are elaborated in [TNNLS-2020]. Motivated by the averaging idea, we proceed to investigate how the averaging techniques affect the learning and tracking abilities of a conventional learning scheme, where the learning ability is reflected by the convergence rate and tracking ability is reflected by the final tracking precision. To this end, we studied three specific averaging techniques, namely, moving averaging, general average with all historical information, and forgetting-based average. The results demonstrate that the forgetting-based average operator-based scheme can connect the other two schemes by tuning the forgetting factor. The results are provided in [TAC-2021].
If the statistics information is unknown, a promising approach is to estimate the mean of the fading channel. This idea is conducted in [TNNLS-2021a], where an iterative estimation mechanism is proposed using a unit pilot signal in each iteration. This mechanism provides necessary statistical information such that the biased signals after transmission can be corrected before being utilized.
All the above advances assume that the system information is available for the control design. If both system information and fading statistics are unknown, a natural idea is to estimate them simulatenously. To this end, we propose an error transmission mode and an iterative gradient estimation method. Using the faded tracking error data only, the gradient for updating input is iteratively estimated by a random difference technique along the iteration axis. This gradient acts as the updating term of the control signal. The results are summarized in [TNNLS-2021b].

Dong SHEN (M'10-SM'17) received the B.S. degree in mathematics from Shandong University, Jinan, China, in 2005. He received the Ph.D. degree in mathematics from the Academy of Mathematics and Systems Science, Chinese Academy of Sciences (CAS), Beijing, China, in 2010 (supervised by Prof. Han-Fu Chen, IEEE Fellow, IFAC Fellow).

From 2010 to 2012, he was a Post-Doctoral Fellow with the Institute of Automation, CAS (advised by Prof. Fei-Yue Wang, IEEE Fellow, IFAC Fellow). From 2016 to 2017, he was a visiting scholar at National University of Singapore (with Prof. Jian-Xin Xu, IEEE Fellow). From 2019 July to August, he was a visiting scholar at RMIT University (with Prof. Xinghuo Yu, IEEE Fellow). From 2012 to 2019, he has been with College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China. Now, he is a Full Professor of Renmin University of China.

His current research interests include iterative learning control, stochastic control and optimization, machine learning and its applications. He has published more than 120 refereed journal and conference papers. He is the (co-)author of Iterative Learning Control for Systems with Iteration-Varying Trial Lengths (Springer, 2019), Iterative Learning Control with Passive Incomplete Information (Springer, 2018), Iterative Learning Control for Multi-Agent Systems Coordination (Wiley, 2017), and Stochastic Iterative Learning Control (Science Press, 2016, in Chinese), and co-editor of Service Science, Management and Engineering: Theory and Applications (Academic Press and Zhejiang University Press, 2012). Dr. Shen received the IEEE CSS Beijing Chapter Young Author Prize in 2014 and the Wentsun Wu Artificial Intelligence Science and Technology Progress Award in 2012. He is an Associate Editor of IEEE Access and IET Cyber-Systems and Robotics.