|
Prof.
SHEN's Group
Distributed
Artificial Intelligence Laboratory, ERC-FCDE, MoE
School of Mathematics, Renmin
University of China
|
Home | Research
| Honors
|
Teaching
|
Publications
| Members
| Future Students
| ILC DataBase
About us
Distributed
Artificial Intelligence Lab (DAI-Lab) was established at
the beginning of 2020. The lab now consists of four faculties, Prof. Dong
Shen, Prof. Hao Jiang, Assoc. Prof. Qijiang Song and Assit. Prof. Xiuqiong Chen (see our members). We focus on
distributed artificial
intelligence
and its application in novel intelligent control approaches.
News
[20241029] The manuscript
titled "Finite and Fixed-Time Learning Control for Continuous-Time Nonlinear Systems" has been accepted for
publication in IEEE Transactions on Systems, Man, and Cybernetics: Systems as a regular paper.
[20241029]
The manuscript titled "Accelerating Iterative Learning Control Using
Fractional-Proportional-type Update Rule" has been accepted for
publication in IEEE Transactions on Automatic Control as a technical note.
[20241023] The manuscript titled "Continuous Discrete Optimal Transportation Particle Filter" has been accepted for publication in The Asian Journal of Mathematics. This work was led by Assit. Prof. Xiuqiong Chen.
[20240926]
The manuscript titled "A Uniform Framework of Yau-Yau Algorithm Based
on Deep Learning with the Capability of Overcoming the Curse of
Dimensionality" has been accepted for publication in the top journal IEEE Transactions on Automatic Control as a full paper. This work was led by Assit. Prof. Xiuqiong Chen.
[20240917]
The manuscript titled "Synthesis of Safety and Ride Comfort Control for
Chassis of Maglev Trains" has been accepted for publication in IEEE Transactions on Intelligent Transportation Systems. This work was led by Prof. You.
[20240915]
The manuscript titled "Decentralized Learning Control for High-Speed
Trains With Unknown Time-Varying Speed Delays" has been accepted for
publication in Applied Mathematical Modelling.
[20240817]
The manuscript titled "Multi-View Data Clustering via Dynamical
Optimization of Consensus Laplacian Matrix" has been accepted for
publication in East Asian
Journal on Applied Mathematics.
[20240814]
The manuscript titled "Co-regularized Optimal High-Order Graph
Embedding for Multi-View Clustering" has been accepted for publication
in top journal Pattern
Recognition.
[20240805]
The manuscript titled "An Accelerated Adaptive Gain Design in
Stochastic Learning Control" has been accepted for publication in IEEE Transactions
on Cybernetics.
[20240731]
Congratulations! The manuscript "Fast iterative learning control
algorithms based on heavy ball with adaptive stepsize", which was
accpeted by CCC2024, won 2024 SCIS-CCC The
Honorable Mention of Poster Paper Award.
[20240727]
The manuscript titled "Zero-Error Tracking Control of Quantized
Iterative Learning for Differential Inclusion Systems with Channel
Fading" has been accepted for publication in Nonlinear Dynamics.
This work was led by Prof. Jinrong Wang.
[20240718]
Congratulations!
Our faculty member Jiang Hao has
been promoted to be a Full Professor.
[20240716] Congratulations!
Our paper "Data-driven learning control algorithms meeting unachievable
tracking problems", authored by Zeyi Zhang, Hao Jiang, Dong Shen, and
Samer S. Saab, has been indexed as a Highly Cited Paper
in Web of Science.
[20240629]
The manuscript "A Uniform Framework of Yau-Yau Algorithm Based on Deep
Learning with the Capability of Overcoming the Curse of Dimensionality"
has been accepted for publication in IEEE Transactions
on Automatic Control. This work was led by Assistant Prof.
Xiuqiong Chen.
[20240527]
The paper "Observer-based sampled-data event-triggered tracking for
nonlinear multi-agent systems with semi-Markovian switching topologies"
has been accepted for publication in Information
Sciences. This work was led by Prof. Wang.
[20240519]
Congratulations! Our paper "Iteration number bound for adaptive
learning control of nonlinear systems under specified approximation
error" with Dunsheng Huang as the first author has won the Best Poster Paper
Award of the 2024 IEEE 13th Data Driven Control and Learning Systems
Conference.
[20240513]
Congratulations! Our paper "Accelerated learning control for
point-to-point tracking systems", authored by Hao Jiang, Dong Shen,
Shunhao Huang, and Xinghuo Yu, has been indexed as a Highly Cited Paper
in Web of Science.
[20240507]
Congratulations!
Zihan Li has won the Wu Yuzhang
Scholarship Finalist Award.
[20240507] The manuscript
"Novel Quantized Iterative Learning Control Based on Spherical Polar
Coordinates" has been accepted for publication in International
Journal of Robust and Nonlinear Control.
[20240419] The paper
"scTPC: a novel semi-supervised deep clustering model for scRNA-seq
data" has been accepted for publication in Bioinformatics.
[20240417] The paper
"scEWE: High-order Element-wise Weighted Ensemble Clustering for
heterogeneity analysis of single cell RNA-sequencing data" has been
accepted for publication in Briefings in
Bioinformatics. This work was led by Assoc. Prof. Hao Jiang.
[20240415] The manuscript
"Time-varying Feedback Particle Filter" has been accepted for
publication in Automatica.
This work was led by Assistant Prof. Xiuqiong Chen.
[20240320]
Congratulations!
Our paper Practical
learning-tracking framework under unknown nonrepetitive channel
randomness won The 17th Beijing
Youth Outstanding Scientific and Technological Paper Award.
[20240307]
The manuscript "Iterative Learning based Convergence Analysis for
Nonlinear Impulsive Differential Inclusion Systems with Randomly
Varying Trial Lengths" has been accepted for publication in International
Journal of Adaptive Control and Signal Processing. This work was
led by Prof. Wang.
[20240224]
The manuscript "Data-Driven Distributed Learning Control for High-Speed
Trains Considering Quantization Effects and Measurement Bias" has been
accepted for publication in IEEE Transactions
on Vehicular Technology. This work was led by Prof. Deqing Huang.
[20240222]
The manuscript "A Multistage Update Rule Framework for Iterative
Learning Control Systems" has been accepted for publication in IEEE Transactions
on Automation Science and Engineering. This work was
collaborated with Prof. Yu.
[20240131]
The manuscript "Iterative Learning Control for Differential Inclusion
Systems with Random Fading Channels by Varying Average Technique" has
been accepted for publication in Chaos.
This work was led by Prof. Wang.
[20240103] The DAI Lab
Annual Report for 2023 has been released.
[20240101] We, DAI Lab,
wish you Happy 2024.
Research
Highlights: Learning
Control with
Fading Channels
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].
In addition, we have successfully extended the learning control scheme
to a distributed version for multi-agent systems, where each agent is
controlled by the input signal generated using the faded neighborhood
information (FDI). The iterationwise asymptotic consensus tracking is
strictly established for both linear and affine nonlinear multi-agent
systems. The results are provided in [TNNLS-2021c]
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].
Furthermore, we
consider the general case that the
fading channels' statistics, i.e., mean and covariance, are
nonrepetitive in the iteration domain.
This nonrepetitive randomness introduces non-stationary contamination
and drifts to the actual signals, yielding essential challenges in
signal processing and learning control. we propose a practical
framework constituted by an unbiased estimator of the mean inverse, a
signal correction mechanism, and learning control schemes. The
convergence and tracking performance are established for both constant
and decreasing step-lengths. If the statistics satisfy asymptotic repetitiveness
in the iteration domain, a consistent estimator applies to the
framework while retaining the framework's asymptotic properties. These
results are demonstrated in [TAC-2022].
All the above publications are regular papers in IEEE Transactions. For
a complete list, please refer to the LazyPack
under the Topic: ILC with fading
channels.
Annual
Reports
Lab Director: Wu
Yuzhang Distinguished Professor Dong Shen
Research
Interests: Iterative
learning control, machine learning and its applications, financial
mathematics and fintech, stochastic
approximation algorithms, multi-agent systems, distributed
and decentralized optimization algorithms.
Contact Information
Office
Address:
Room 207, No. 4
Teaching Building, Renmin University of China, No. 59
Zhongguancun Street, Haidian District, Beijing 100872
Mailing
Address:
School of
Mathematics, Renmin University of
China,
No. 59 Zhongguancun Street, Beijing 100872, P.R. China
Tel: 86-10-82507078
E-mail: dshen [at] ieee [dot] org
ORCID: 0000-0003-1063-1351
Education
2005.09-2010.07,
Ph.D. in Mathematics, Academy of Mathematics and Systems Sciences,
Chinese Academy of Sciences
2001.09-2005.07, B.S. in Mathematics, School of Mathematics, Shandong
University
Professional
Positions
2020.01-present,
Professor, School of Mathematics, Renmin University of China
2020.01-present, Professor, Eng. Res. Center of Finance
Computation and Digital Engineering, Ministry of Education
2020.01-present, Principal Investigator, Distributed Artificial Intelligence Lab.,
ERC-FCDE, MoE
2019.07-2019.08, Visiting Scholar, RMIT University, Australia
2012.06-2019.12,
Associate Professor, Beijing University of Chemical Technology
2016.02-2017.02, Visiting Scholar, National University of Singapore,
Singapore
2010.07-2012.05, Postdoctoral Fellow, Institute of Automation, CAS