Zongliang Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zongliang Chen has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Shuguo Pan
State Key Laboratory of Comprehensive PNT Network and Equipment Technology, School of Instrument Science and Engineering, Southeast University, Nanjing, China
6 shared publications - Wang Gao
School of Instrument Science and Engineering, Southeast University, Nanjing, China
6 shared publications - Kegen Yu
China University of Mining and Technology
4 shared publications - Zhuoxuan Wang
State Key Laboratory of Comprehensive PNT Network and Equipment Technology, School of Instrument Science and Engineering, Southeast University, Nanjing, China
3 shared publications Baoguo Yu
The State Key Laboratory of Satellite Navigation System and Equipment Technology Shijiazhuang China
1 shared publicationHaonan Jia
The State Key Laboratory of Satellite Navigation System and Equipment Technology, Shijiazhuang, China
1 shared publication
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (7) , 10161-10173
Data-Driven Modeling With Deep Koopman Operator for Robust Path Tracking of Autonomous Vehicles
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 73 (7) , 10161-10173
Data-Driven Modeling With Deep Koopman Operator for Robust Path Tracking of Autonomous Vehicles
- 15 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9591-9598
Robust Data-Driven Path Tracking Control for Autonomous Vehicles: A Koopman Operator Approach With High-Order Super-Twisting Observer
Path tracking control is a critical component of autonomous driving technology. However, it faces significant challenges due to the inherent strong nonlinearity and dynamic uncertainties of autonomous vehicles (AVs), which remains a severe challenge in the field. To address the problem, this paper proposes a novel robust data-driven control framework designed to balance modeling accuracy with disturbance rejection performance. First, a control-oriented Deep Koopman model is constructed to map the nonlinear AV path-tracking error dynamics into a high-dimensional lifted space. Second, to address inevitable modeling residuals and external disturbances, a high-order super-twisting observer (HOSTO) is designed within the lifted space, which guarantees finite-time convergence of disturbance estimation, providing strong robust compensation. Finally, an approximate lifted-space MPC with Jacobian-based cost mapping is formulated as a standard Quadratic Program (QP), avoiding repeated nonlinear decoding during online optimization. The effectiveness of the proposed method is validated through comprehensive simulations and experiments, showing superior control accuracy and robustness against disturbances compared to existing algorithms.
- 15 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (8) , 9591-9598
Robust Data-Driven Path Tracking Control for Autonomous Vehicles: A Koopman Operator Approach With High-Order Super-Twisting Observer
Path tracking control is a critical component of autonomous driving technology. However, it faces significant challenges due to the inherent strong nonlinearity and dynamic uncertainties of autonomous vehicles (AVs), which remains a severe challenge in the field. To address the problem, this paper proposes a novel robust data-driven control framework designed to balance modeling accuracy with disturbance rejection performance. First, a control-oriented Deep Koopman model is constructed to map the nonlinear AV path-tracking error dynamics into a high-dimensional lifted space. Second, to address inevitable modeling residuals and external disturbances, a high-order super-twisting observer (HOSTO) is designed within the lifted space, which guarantees finite-time convergence of disturbance estimation, providing strong robust compensation. Finally, an approximate lifted-space MPC with Jacobian-based cost mapping is formulated as a standard Quadratic Program (QP), avoiding repeated nonlinear decoding during online optimization. The effectiveness of the proposed method is validated through comprehensive simulations and experiments, showing superior control accuracy and robustness against disturbances compared to existing algorithms.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (11) , 11992-11999
Reinforcement Learning-Based Adaptive Path Tracking Fusion Control Strategy for Intelligent Vehicles
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.
- 29 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (11) , 11992-11999
Reinforcement Learning-Based Adaptive Path Tracking Fusion Control Strategy for Intelligent Vehicles
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.
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 18906-18920
Fusion Control Tracking Strategy for Autonomous Vehicles: A Fast PPO Reinforcement Learning Based on Attention Mechanism and Physical Information
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.
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 18906-18920
Fusion Control Tracking Strategy for Autonomous Vehicles: A Fast PPO Reinforcement Learning Based on Attention Mechanism and Physical Information
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.
- 14 November 2024
- Published by Elsevier in ISA Transactions
- Vol. 156, 524-534
A composite fixed-time sliding mode control scheme for Unmanned Ground Vehicles affected by external disturbances
- 14 November 2024
- Published by Elsevier in ISA Transactions
- Vol. 156, 524-534
A composite fixed-time sliding mode control scheme for Unmanned Ground Vehicles affected by external disturbances
- 12 September 2024
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 34 (18) , 12257-12285
Design and application of finite‐time tracking control for autonomous ground vehicle affected by external disturbances
Path tracking plays a critical role in autonomous driving for autonomous ground vehicle (AGV). However, AGV faces challenges in accurate tracking and chatter reduction due to external disturbances, making it difficult to meet the tracking performance requirements. Currently, sliding mode control (SMC) and disturbances observer are primarily employed for disturbance estimation. However, ensuring finite‐time robust control remains a significant challenge. To ensure rapid convergence of tracking errors and effective disturbance rejection, this paper proposed a novel non‐singular fast terminal sliding mode (NFTSM) control scheme based on finite‐time disturbance observation (FDO). First, a novel NFTSM controller based on AGV dynamic model is developed to achieve fast convergence of tracking errors. Then, to mitigate disturbances effects and suppress chatter, an innovative FDO method is employed. Finally, based on FDO, the NFTSM‐FDO establishes a control scheme that enhances disturbances suppression and accelerates convergence. The simulation and experimental results demonstrate the innovation of the proposed method. Compared with other SMC methods, the results validate the effectiveness and advantages of the proposed approach, exhibiting fast convergence and superior tracking performance.
- 12 September 2024
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 34 (18) , 12257-12285
Design and application of finite‐time tracking control for autonomous ground vehicle affected by external disturbances
Path tracking plays a critical role in autonomous driving for autonomous ground vehicle (AGV). However, AGV faces challenges in accurate tracking and chatter reduction due to external disturbances, making it difficult to meet the tracking performance requirements. Currently, sliding mode control (SMC) and disturbances observer are primarily employed for disturbance estimation. However, ensuring finite‐time robust control remains a significant challenge. To ensure rapid convergence of tracking errors and effective disturbance rejection, this paper proposed a novel non‐singular fast terminal sliding mode (NFTSM) control scheme based on finite‐time disturbance observation (FDO). First, a novel NFTSM controller based on AGV dynamic model is developed to achieve fast convergence of tracking errors. Then, to mitigate disturbances effects and suppress chatter, an innovative FDO method is employed. Finally, based on FDO, the NFTSM‐FDO establishes a control scheme that enhances disturbances suppression and accelerates convergence. The simulation and experimental results demonstrate the innovation of the proposed method. Compared with other SMC methods, the results validate the effectiveness and advantages of the proposed approach, exhibiting fast convergence and superior tracking performance.
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 362-377
Dynamic Event-Triggered and Fast Natural Logarithmic Sliding Mode Path Tracking Control for Autonomous Ground Vehicles With the Experiment Validation
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
- 12 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (1) , 362-377
Dynamic Event-Triggered and Fast Natural Logarithmic Sliding Mode Path Tracking Control for Autonomous Ground Vehicles With the Experiment Validation
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
- 4 March 2022
- Published by Emerald Publishing in Industrial Robot: the international journal of robotics research and application
- Vol. 49 (5) , 973-980
An improved pure pursuit path tracking control method based on heading error rate
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.
- 4 March 2022
- Published by Emerald Publishing in Industrial Robot: the international journal of robotics research and application
- Vol. 49 (5) , 973-980
An improved pure pursuit path tracking control method based on heading error rate
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.