Zhinan Peng

Prof. Zhinan Peng

School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Zhinan PengZhinan Peng
Zhinan Peng
RLRui Luo
Rui Luo
Jiangping HuJiangping Hu
Jiangping Hu
Kaibo ShiKaibo Shi
Kaibo Shi
SNSing Kiong Nguang
Sing Kiong Nguang
BGBijoy Kumar Ghosh
Bijoy Kumar Ghosh
In this article, a novel reinforcement learning (RL) method is developed to solve the optimal tracking control problem of unknown nonlinear multiagent systems (MASs). Different from the representative RL-based optimal control algorithms, an internal reinforce Q-learning (IrQ-L) method is proposed, in which an internal reinforce reward (IRR) function is introduced for each agent to improve its capability of receiving more long-term information from the local environment. In the IrQL designs, a Q-function is defined on the basis of IRR function and an iterative IrQL algorithm is developed to learn optimally distributed control scheme, followed by the rigorous convergence and stability analysis. Furthermore, a distributed online learning framework, namely, reinforce-critic-actor neural networks, is established in the implementation of the proposed approach, which is aimed at estimating the IRR function, the Q-function, and the optimal control scheme, respectively. The implemented procedure is designed in a data-driven way without needing knowledge of the system dynamics. Finally, simulations and comparison results with the classical method are given to demonstrate the effectiveness of the proposed tracking control method.

1 May 2019 in Information Sciences
Verified
Journal Article
Closed access
Zhinan PengZhinan Peng
Zhinan Peng
YZYiyi Zhao
Yiyi Zhao
Jiangping HuJiangping Hu
Jiangping Hu
BGBijoy Kumar Ghosh
Bijoy Kumar Ghosh

1 March 2020 in Applied Mathematics and Computation
Verified
Journal Article
Closed access
Zhinan PengZhinan Peng
Zhinan Peng
JHJiangping Hu
Jiangping Hu
KSKaibo Shi
Kaibo Shi
RLRui Luo
Rui Luo
RHRui Huang
Rui Huang
JHJiuke Huang
Jiuke Huang

2 June 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
Zhinan PengZhinan Peng
Zhinan Peng
RLRui Luo
Rui Luo
Jiangping HuJiangping Hu
Jiangping Hu
Kaibo ShiKaibo Shi
Kaibo Shi
BGBijoy Ghosh
Bijoy Ghosh
In this paper, an event-triggered optimal tracking control of discrete-time multi-agent systems is addressed by using reinforcement learning. In contrast to traditional reinforcement learning-based methods for optimal coordination and control of multi-agent systems with a time-triggered control mechanism, an event-triggered mechanism is proposed to update the controller only when the designed events are triggered, which reduces the computational burden and transmission load. The stability analysis of the closed-loop multi-agent systems with event-triggered controller is described. Further, to implement the proposed scheme, an actor-critic neural network learning structure is proposed to approximate performance indices and to on-line learn the event-triggered optimal control. During the training process, event-triggered weight tuning law has been designed, wherein the weight parameters of the actor neural networks are adjusted only during triggering instances compared with traditional methods with fixed updating periods. Further, a convergence analysis of the actor-critic neural network is provided via Lyapunov method. Finally, two simulation examples show the effectiveness and performance of the obtained event-triggered reinforcement learning controller.

10 February 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
RLRui Luo
Rui Luo
Zhinan PengZhinan Peng
Zhinan Peng
Jiangping HuJiangping Hu
Jiangping Hu
This paper reviews recent progress in model identification-based learning and optimal control and its applications to multi-agent systems (MASs). First, a class of learning-based optimal control method, namely adaptive dynamic programming (ADP), is introduced, and the existing results using ADP methods to solve optimal control problems are reviewed. Then, this paper investigates various kinds of model identification methods and analyzes the feasibility of combining the model identification method with the ADP method to solve optimal control of unknown systems. In addition, this paper expounds the current applications of model identification-based ADP methods in the fields of single-agent systems (SASs) and MASs. Finally, some conclusions and some future directions are presented.

1 May 2020
Verified
Conference Paper
Closed access
Zhinan PengZhinan Peng
Zhinan Peng
RLRui Luo
Rui Luo
RHRui Huang
Rui Huang
JHJiangping Hu
Jiangping Hu
KSKecheng Shi
Kecheng Shi
BGBijoy Kumar Ghosh
Bijoy Kumar Ghosh
Lower limb exoskeleton (LLE) has received considerable interests in strength augmentation, rehabilitation and walking assistance scenarios. For walking assistance, the LLE is expected to have the capability of controlling the affected leg to track the unaffected leg’s motion naturally. An important issue in this scenario is that the exoskeleton system needs to deal with unpredictable disturbance from the patient, which requires the controller of exoskeleton system to have the ability to adapt to different wearers. This paper proposes a novel Data-Driven Reinforcement Learning (DDRL) control strategy to adapt different hemiplegic patients with unpredictable disturbances. In the proposed DDRL strategy, the interaction between two lower limbs of LLE and the legs of hemiplegic patient are modeled in the context of leader-follower framework. The walking assistance control problem is transformed into a optimal control problem. Then, a policy iteration (PI) algorithm is introduced to learn optimal controller. To achieve online adaptation control for different patients, based on PI algorithm, an Actor-Critic Neural Network (ACNN) technology of the reinforcement learning (RL) is employed in the proposed DDRL. We conduct experiments both on a simulation environment and a real LLE system. Experimental results demonstrate that the proposed control strategy has strong robustness against disturbances and adaptability to different pilots.