Yunfei Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yunfei Cui has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Fei Huang
Hainan University
14 shared publications Zheping Yan
10 shared publicationsDi Wu
9 shared publications- Jian Xu
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China
6 shared publications Jian Xu
5 shared publicationsTao Chen
4 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 22244-22255
Hierarchical Cooperative Formation Containment Control for Underactuated Multi-AUV Systems Incorporating Auxiliary Variable and Disturbance Observer
In this paper, a disturbance-resistant formation containment control architecture with two-layer coordination of guidance and control is proposed for an underactuated multi-AUV system with model uncertainty, input saturation and unknown disturbances. In the guidance layer, the motion of the underactuated AUV is decoupled based on auxiliary variable methods, and distributed formation tracking guidance law and containment guidance law are constructed respectively, which can guide the control layer of the system to achieve the desired formation containment. To ensure smooth transmission of guidance instructions to control instructions, a tracking differentiator is introduced to establish a bridge between the guidance layer and the control layer. In the control layer, a disturbance observer is designed to provide real-time estimation and compensation for unknown composite disturbances in the system. Secondly, to tackle the problem of actuator input saturation, an auxiliary regulation system is established to suppress the impact of saturation characteristics on control performance. Finally, by combining the estimation information of the disturbance observer with the adjustment effect of the auxiliary system, the control laws with both anti-saturation and anti-disturbance characteristics suitable for the underactuated multi-AUV system is designed. And stability analysis proves that the formation tracking error and containment error of the multi-AUV system are uniformly ultimately bounded. The numerical simulation results verify the effectiveness of the proposed control method.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (10) , 22244-22255
Hierarchical Cooperative Formation Containment Control for Underactuated Multi-AUV Systems Incorporating Auxiliary Variable and Disturbance Observer
In this paper, a disturbance-resistant formation containment control architecture with two-layer coordination of guidance and control is proposed for an underactuated multi-AUV system with model uncertainty, input saturation and unknown disturbances. In the guidance layer, the motion of the underactuated AUV is decoupled based on auxiliary variable methods, and distributed formation tracking guidance law and containment guidance law are constructed respectively, which can guide the control layer of the system to achieve the desired formation containment. To ensure smooth transmission of guidance instructions to control instructions, a tracking differentiator is introduced to establish a bridge between the guidance layer and the control layer. In the control layer, a disturbance observer is designed to provide real-time estimation and compensation for unknown composite disturbances in the system. Secondly, to tackle the problem of actuator input saturation, an auxiliary regulation system is established to suppress the impact of saturation characteristics on control performance. Finally, by combining the estimation information of the disturbance observer with the adjustment effect of the auxiliary system, the control laws with both anti-saturation and anti-disturbance characteristics suitable for the underactuated multi-AUV system is designed. And stability analysis proves that the formation tracking error and containment error of the multi-AUV system are uniformly ultimately bounded. The numerical simulation results verify the effectiveness of the proposed control method.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 36604-36616
Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar
This article investigates the application of deep reinforcement learning (RL) in the reactive collision avoidance control of an autonomous underwater vehicle (AUV) using multibeam forward-looking sonar (MBFLS). First, an efficient encoding method based on prior knowledge is proposed, which can extract low dimensional representations of obstacles from massive MBFLS detection data, thereby reducing the inference time of the reactive collision avoidance control policy represented by a neural network and improving their collision avoidance effect. On this basis, a state space, action space, and multiobjective reward function are customized for the reactive collision avoidance task of the AUV, and a simulation training environment is constructed. Considering that the contradiction between policy training and deployment is caused by unknown total disturbances, disturbance estimators based on the extended state observer is constructed, and a deployment scheme is designed to compensate for disturbances through both feedforward and feedback channels, ensuring that the policy learned in simulation can be applied to an actual AUV. Finally, combining the above components, a novel reactive collision avoidance method based on deep RL is proposed, and the effectiveness of the proposed method for obstacles of various shapes (both static and dynamic) is fully verified in three different unknown environments.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (17) , 36604-36616
Deep-Reinforcement-Learning-Based Reactive Collision Avoidance Controller for an Underactuated AUV Using Multibeam Forward-Looking Sonar
This article investigates the application of deep reinforcement learning (RL) in the reactive collision avoidance control of an autonomous underwater vehicle (AUV) using multibeam forward-looking sonar (MBFLS). First, an efficient encoding method based on prior knowledge is proposed, which can extract low dimensional representations of obstacles from massive MBFLS detection data, thereby reducing the inference time of the reactive collision avoidance control policy represented by a neural network and improving their collision avoidance effect. On this basis, a state space, action space, and multiobjective reward function are customized for the reactive collision avoidance task of the AUV, and a simulation training environment is constructed. Considering that the contradiction between policy training and deployment is caused by unknown total disturbances, disturbance estimators based on the extended state observer is constructed, and a deployment scheme is designed to compensate for disturbances through both feedforward and feedback channels, ensuring that the policy learned in simulation can be applied to an actual AUV. Finally, combining the above components, a novel reactive collision avoidance method based on deep RL is proposed, and the effectiveness of the proposed method for obstacles of various shapes (both static and dynamic) is fully verified in three different unknown environments.
- 7 April 2023
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 360 (8) , 5728-5758
A general motion control framework for an autonomous underwater vehicle through deep reinforcement learning and disturbance observers
- 7 April 2023
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 360 (8) , 5728-5758
A general motion control framework for an autonomous underwater vehicle through deep reinforcement learning and disturbance observers
- 25 January 2023
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 360 (4) , 2867-2892
Event-triggered adaptive target tracking control for an underactuated autonomous underwater vehicle with actuator faults
- 25 January 2023
- Published by Elsevier in Journal of the Franklin Institute
- Vol. 360 (4) , 2867-2892
Event-triggered adaptive target tracking control for an underactuated autonomous underwater vehicle with actuator faults
- 16 November 2022
- Published by Elsevier in Ocean Engineering
- Vol. 266
Anti-disturbance cooperative formation containment control for multiple autonomous underwater vehicles with actuator saturation
- 16 November 2022
- Published by Elsevier in Ocean Engineering
- Vol. 266
Anti-disturbance cooperative formation containment control for multiple autonomous underwater vehicles with actuator saturation
- 1 November 2022
- Published by Elsevier in Ocean Engineering
- Vol. 266
Anti-disturbance fault-tolerant formation containment control for multiple autonomous underwater vehicles with actuator faults
- 1 November 2022
- Published by Elsevier in Ocean Engineering
- Vol. 266
Anti-disturbance fault-tolerant formation containment control for multiple autonomous underwater vehicles with actuator faults