Zongliang Chen

Zongliang Chen

Auto-generated profile, based on publicly available information

Zongliang Chen

State Key Laboratory of Comprehensive PNT Network and Equipment Technology, School of Instrument Science and Engineering, Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
4 March 2022 in Industrial Robot: the international journal of robotics research and application
Verified
Journal Article
Closed access
Lihui WangLihui Wang
Lihui Wang
ZCZongLiang Chen
ZongLiang Chen
WZWenxing Zhu
Wenxing Zhu
Purpose: In path tracking, pure pursuit (PP) has great superiority due to its simple control. However, when in agricultural applications, the performance and accuracy of PP are not so well; it cannot be tracked in time has slow convergence, and low tracking accuracy. Furthermore, in some severe driving scenarios, PP is insufficient to convey the effects of the tracking error. This paper aims to propose an autonomous driving controller to improve the PP model based on heading error rate (Improved PP-improved search strategy ant colony optimization [ISSACO]). Design/methodology/approach: First, the heading error rate is added as the control method in the PP model. Second, the predicted heading error was selected as the objective function; the ISSACO is used to obtain the minimum value of the predicted heading error. A PP controller is integrated with the heading error rate by ISSACO to better deal with tracking error by trading off between PP and heading error rate. Third, the ISSACO was used to obtain the optimal values of PP and heading error rate weight. Finally, the error feedback adaptive dynamic adjustment of the improved algorithm is realized to reduce the convergence time and tracking error. Findings: The proposed method was tested on a four-wheeled vehicle robot, and the effectiveness of its convergence was proved. Experiments show that the proposed method can effectively reduce the tracking error, increase convergence, then improve the robot’s working quality. Originality/value: An adaptive improved PP path tracking control is proposed, which considers both heading error rate and parameter uncertainties. The new autonomous controller has a simple structure and is easy to implement. It can be adjusted according to the path tracking status to improve the adaptability of the system.

12 September 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
ZCZongliang Chen
Zongliang Chen
Shuguo PanShuguo Pan
Shuguo Pan
KYKegen Yu
Kegen Yu
XTXinhua Tang
Xinhua Tang
WGWang Gao
Wang Gao
ZZZhengyang Zhou
Zhengyang Zhou
Effective path tracking control plays a pivotal role in Unmanned Ground Vehicles (UGVs). However, UGVs systems face difficulties in fast convergence and overshooting when subject to actuator communication burden and execution wear. To improve the actuator wear and achieve fast convergence, this paper proposed a fast natural logarithmic sliding mode (FLnSM) control scheme based on the dynamic event-triggered (DET) mechanism. First, a novel FLnSM is developed to enhance convergence speed and reduce chatter. By employing the fast natural logarithmic function, it is possible to achieve high gains at the equilibrium point of the UGVs system. This method exhibits enhanced tracking accuracy and higher convergence speeds compared to other SMC methods. Secondly, a DET mechanism with an adjustable threshold is introduced to mitigate the communication burden and reduce actuator execution loss. Furthermore, as the update frequency of the controller is reduced, the chatter of the sliding mode surface is effectively diminished. Compared to most existing event-triggering methods with a static threshold, the proposed DET mechanism adaptively updates the triggering threshold online to achieve enhanced resource efficiency and avoid the Zeno phenomenon. With only a few parameters requiring tuning, and given that the natural logarithm function is easy to integrate into many UGVs systems, implementing the proposed DET-FLnSM in UGVs systems becomes effortless. Finally, a composite control scheme that integrates DET with FLnSM is proposed to achieve fast convergence, suppress chattering phenomenon, and reduce communication resource consumption of the UGVs system. The excellent performance of the proposed DET-FLnSM control strategy is demonstrated through numerical simulations and experimental results

14 November 2024 in ISA Transactions
Verified
Journal Article
Closed access
ZCZongliang Chen
Zongliang Chen
Shuguo PanShuguo Pan
Shuguo Pan
KYKegen Yu
Kegen Yu
XTXinhua Tang
Xinhua Tang
WGWang Gao
Wang Gao
HJHaonan Jia
Haonan Jia

18 September 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
ZCZongliang Chen
Zongliang Chen
Shuguo PanShuguo Pan
Shuguo Pan
KYKegen Yu
Kegen Yu
YWYuting Wu
Yuting Wu
WGWang Gao
Wang Gao
Xiaolin MengXiaolin Meng
Xiaolin Meng
Accurate path tracking control is crucial for the performance of autonomous vehicle (AV). However, a single control algorithm struggles to adapt to complex dynamic scenarios with varying error states and path curvatures, leading to challenges in slow convergence and poor tracking performance. To address this, this paper proposes an adaptive fusion control scheme termed AMPIPPO that integrates an attention mechanism and a physical information model into Proximal Policy Optimization (PPO). First, FLnSM and NMPC are combined through PPO by balancing the two controllers. Then, the attention mechanism is incorporated to utilize error information and path curvature as state inputs for generating action outputs, significantly enhancing the adaptability of PPO. Additionally, physical information (PI) is implemented to strengthen both model-driven and data-driven approaches, achieving an accurate model estimation. Furthermore, this paper demonstrates the convergence of policy iterations in the AMPIPPO algorithm. Finally, a control scheme FLnSM-NMPC-AMPIPPO is proposed to achieve accurate tracking and enhance the adaptability of AV in dynamic scenarios. Compared to single controllers, the FLnSM-NMPC-AMPIPPO method exhibits higher tracking accuracy and faster convergence. Compared to other RL, AMPIPPO demonstrates superior performance in sparse data scenarios and significantly enhances AV prediction accuracy. The proposed FLnSM-NMPC-AMPIPPO demonstrates excellent performance through numerical simulations and experiments.

12 September 2024 in International Journal of Robust and Nonlinear Control
Verified
Journal Article
Closed access
ZCZongliang Chen
Zongliang Chen
SPShuguo Pan
Shuguo Pan
XTXinhua Tang
Xinhua Tang
XMXiaolin Meng
Xiaolin Meng
WGWang Gao
Wang Gao
BYBaoguo Yu
Baoguo Yu

29 September 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
YWYuting Wu
Yuting Wu
Shuguo PanShuguo Pan
Shuguo Pan
ZCZongliang Chen
Zongliang Chen
ZWZhuoxuan Wang
Zhuoxuan Wang
WGWang Gao
Wang Gao
XTXianlu Tao
Xianlu Tao
Path tracking control is a crucial technology for intelligent vehicles (IVs) to achieve accurate tracking. However, a single controller struggles to track precisely in complex environments due to respective advantages and applicable scenarios. To improve tracking performance for IVs, this letter proposes an adaptive fusion control strategy through reinforcement learning (RL), allowing multiple controllers to cooperate more efficiently in path tracking. Firstly, autonomous steering is modeled by the Pure Pursuit (PP) with foresight and the nonlinear model predictive control (NMPC) with prediction. Secondly, by integrating PP with NMPC through Proximal Policy Optimization (PPO), the control weights are dynamically adjusted to balance the contributions of both controllers. The method incorporates road information and error data as state inputs, enhancing PPO’s generalization and addressing the challenge of adaptive control in complex environments. Compared to other RL methods, PPO is insensitive to hyperparameters and has a better generalizability performance. Therefore, the PPO approach results in less training time and simpler application in IV systems. Finally, a fusion control strategy that integrates PP and NMPC into the PP-PPO-NMPC framework is proposed to achieve accurate tracking and enhance the adaptability of IVs in complex scenarios. The strategy is thoroughly validated by extensive simulation and practical tests against baseline algorithms. The results confirm that the fusion PP-PPO-NMPC algorithm exhibits superior adaptability and tracking performance in complex environments.