Xinhua Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinhua Wang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Huajun Gong
Nanjing University of Aeronautics and Astronautics
5 shared publications - Guanyu Chen
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
2 shared publications - Ziyuan Ma
Nanjing University of Aeronautics and Astronautics
2 shared publications - Congwei Zhao
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
1 shared publication - Ju Jiang
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
1 shared publication - Jun Xiong
School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China
1 shared publication
Latest Publications
- Open Access
Design of a Reinforcement Learning-Based Speed Compensator for Unmanned Aerial Vehicle in Complex Environments
Due to the complexity of the marine environment and the uncertainty of ship movements, altitude control of UAV is particularly important when approaching and landing on the deck of a ship. This paper focuses on unmanned helicopters as its research subject. Conventional altitude control systems may have difficulty in ensuring fast and stable landings under certain extreme conditions. Therefore, designing a new UAV altitude control method that can adapt to complex sea conditions has become a current problem to be solved. Designing a reinforcement learning based rotational speed compensator for UAV as a redundant controller to optimise UAV altitude control performance for the above problem. The compensator is capable of adjusting the UAV’s rotational speed in real time to compensate for altitude deviations due to external environmental disturbances and the UAV’s own dynamic characteristics. By introducing reinforcement learning algorithms, especially the DDPG algorithm, this compensator is able to learn the optimal RPM adjustment strategy in a continuous trial-and-error process, which improves the UAV’s rapidity and stability during the landing process.
Open AccessDesign of a Reinforcement Learning-Based Speed Compensator for Unmanned Aerial Vehicle in Complex Environments
Due to the complexity of the marine environment and the uncertainty of ship movements, altitude control of UAV is particularly important when approaching and landing on the deck of a ship. This paper focuses on unmanned helicopters as its research subject. Conventional altitude control systems may have difficulty in ensuring fast and stable landings under certain extreme conditions. Therefore, designing a new UAV altitude control method that can adapt to complex sea conditions has become a current problem to be solved. Designing a reinforcement learning based rotational speed compensator for UAV as a redundant controller to optimise UAV altitude control performance for the above problem. The compensator is capable of adjusting the UAV’s rotational speed in real time to compensate for altitude deviations due to external environmental disturbances and the UAV’s own dynamic characteristics. By introducing reinforcement learning algorithms, especially the DDPG algorithm, this compensator is able to learn the optimal RPM adjustment strategy in a continuous trial-and-error process, which improves the UAV’s rapidity and stability during the landing process.
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (24) , 40532-40546
Mission Planning of UAVs and CAVs Based on Graph Neural Network Transformer Model
Efficient mission planning, including task allocation and path planning, is crucial for the successful operation of unmanned aerial vehicles (UAVs) and connected autonomous vehicles (CAVs) in complex scenarios. This article introduces an innovative mission planning approach that employs a collaborative model combining graph neural networks (GNNs) and Transformers to meet the intricate requirements of coordinating UAVs and CAVs. Our model excels in dynamic task allocation and accurate path planning, thereby boosting operational efficiency and reducing computational demands. We outline the shortcomings of current methods, notably their limited adaptability to dynamic changes and their substantial computational costs. By utilizing GNNs to capture complex interrelations and Transformers for effective information processing, our approach achieves greater adaptability and scalability. Experimental results demonstrate that our model surpasses leading methods, showing a 12% improvement in task allocation accuracy for UAVs and 10% for CAVs. Furthermore, we assess the model’s performance under various conditions, confirming its robustness and adaptability. This research provides a holistic solution for mission planning in UAV and CAV systems, setting the stage for future enhancements in autonomous vehicle coordination across logistics, surveillance, and disaster management sectors.
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (24) , 40532-40546
Mission Planning of UAVs and CAVs Based on Graph Neural Network Transformer Model
Efficient mission planning, including task allocation and path planning, is crucial for the successful operation of unmanned aerial vehicles (UAVs) and connected autonomous vehicles (CAVs) in complex scenarios. This article introduces an innovative mission planning approach that employs a collaborative model combining graph neural networks (GNNs) and Transformers to meet the intricate requirements of coordinating UAVs and CAVs. Our model excels in dynamic task allocation and accurate path planning, thereby boosting operational efficiency and reducing computational demands. We outline the shortcomings of current methods, notably their limited adaptability to dynamic changes and their substantial computational costs. By utilizing GNNs to capture complex interrelations and Transformers for effective information processing, our approach achieves greater adaptability and scalability. Experimental results demonstrate that our model surpasses leading methods, showing a 12% improvement in task allocation accuracy for UAVs and 10% for CAVs. Furthermore, we assess the model’s performance under various conditions, confirming its robustness and adaptability. This research provides a holistic solution for mission planning in UAV and CAV systems, setting the stage for future enhancements in autonomous vehicle coordination across logistics, surveillance, and disaster management sectors.
- 2 August 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (8) , 2624-2632
Integral Event-triggered Time-varying Formation Tracking for UAV Swarm Systems With Switching Directed Topologies
- 2 August 2024
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 22 (8) , 2624-2632
Integral Event-triggered Time-varying Formation Tracking for UAV Swarm Systems With Switching Directed Topologies
- Open Access
Fault-Tolerant Event-Triggrred Control for Multiple UAVs with Predefined Tracking Performance
This paper proposes an event-triggered fault-tolerant time-varying formation control method dedicated to multiple unmanned aerial vehicles (UAVs). We meticulously design a formation-tracking controller with a predefined tracking performance to accommodate the presence of actuator faults and external disturbances. Firstly, the formation-tracking controller acquires the desired heading using the line-of-sight algorithm. Secondly, in the presence of actuator faults and external disturbances, we introduce the radial basis function neural network (RBFNN) and adaptive law tracking control to effectively compensate for their effects. Additionally, we design adaptive tracking controllers and event-triggering conditions to increase the computational frequency. The predefined tracking performance, implemented via a Lyapunov function, ensures the convergence of the tracking error over time. Finally, we conduct a thorough analysis of the system’s stability, successfully eliminating the possibility of Zeno behavior. The simulation results thoroughly validate the effectiveness of the theoretical analysis.
Open AccessFault-Tolerant Event-Triggrred Control for Multiple UAVs with Predefined Tracking Performance
This paper proposes an event-triggered fault-tolerant time-varying formation control method dedicated to multiple unmanned aerial vehicles (UAVs). We meticulously design a formation-tracking controller with a predefined tracking performance to accommodate the presence of actuator faults and external disturbances. Firstly, the formation-tracking controller acquires the desired heading using the line-of-sight algorithm. Secondly, in the presence of actuator faults and external disturbances, we introduce the radial basis function neural network (RBFNN) and adaptive law tracking control to effectively compensate for their effects. Additionally, we design adaptive tracking controllers and event-triggering conditions to increase the computational frequency. The predefined tracking performance, implemented via a Lyapunov function, ensures the convergence of the tracking error over time. Finally, we conduct a thorough analysis of the system’s stability, successfully eliminating the possibility of Zeno behavior. The simulation results thoroughly validate the effectiveness of the theoretical analysis.
- 20 December 2023
- Published by Springer Nature
- p. 40-48
Multi UAV Trajectory Tracking Optimization Method Based on Fuzzy Graph Convolution Neural Network
- 20 December 2023
- Published by Springer Nature
- p. 40-48
Multi UAV Trajectory Tracking Optimization Method Based on Fuzzy Graph Convolution Neural Network
- 20 December 2023
- Published by Springer Nature
- p. 279-294
Research on AR Adaptive Deck Motion Prediction Technology Based on Forgetting Factor
- 20 December 2023
- Published by Springer Nature
- p. 279-294
Research on AR Adaptive Deck Motion Prediction Technology Based on Forgetting Factor
- Open Access
Formation Transformation Based on Improved Genetic Algorithm and Distributed Model Predictive Control
In order to solve the problem of multiple aircraft formation transformation to a designated formation, a distributed formation transformation algorithm that decomposes the formation transformation problem into target-matching problems and trajectory-planning problems was studied. According to the actual formation transformation requirements, the target allocation index was proposed, and the improved genetic algorithm which is 23% better than other algorithms was used to achieve target matching. The adaptive cross-mutation probability was designed, and the population was propagated without duplicates by the hash algorithm. The multi-objective algorithm of distributed model predictive control was used to design smooth and conflict-free trajectories for the UAVs in formation transformation, and the trajectory-planning problem was transformed into a quadratic programming problem under inequality constraints. Finally, point-to-point collision-free offline trajectory planning was realized by simulation.
Open AccessFormation Transformation Based on Improved Genetic Algorithm and Distributed Model Predictive Control
In order to solve the problem of multiple aircraft formation transformation to a designated formation, a distributed formation transformation algorithm that decomposes the formation transformation problem into target-matching problems and trajectory-planning problems was studied. According to the actual formation transformation requirements, the target allocation index was proposed, and the improved genetic algorithm which is 23% better than other algorithms was used to achieve target matching. The adaptive cross-mutation probability was designed, and the population was propagated without duplicates by the hash algorithm. The multi-objective algorithm of distributed model predictive control was used to design smooth and conflict-free trajectories for the UAVs in formation transformation, and the trajectory-planning problem was transformed into a quadratic programming problem under inequality constraints. Finally, point-to-point collision-free offline trajectory planning was realized by simulation.
- Open Access
Aerial Target Tracking Algorithm Based on Faster R-CNN Combined with Frame Differencing
We propose a robust approach to detecting and tracking moving objects for a naval unmanned aircraft system (UAS) landing on an aircraft carrier. The frame difference algorithm follows a simple principle to achieve real-time tracking, whereas Faster Region-Convolutional Neural Network (R-CNN) performs highly precise detection and tracking characteristics. We thus combine Faster R-CNN with the frame difference method, which is demonstrated to exhibit robust and real-time detection and tracking performance. In our UAS landing experiments, two cameras placed on both sides of the runway are used to capture the moving UAS. When the UAS is captured, the joint algorithm uses frame difference to detect the moving target (UAS). As soon as the Faster R-CNN algorithm accurately detects the UAS, the detection priority is given to Faster R-CNN. In this manner, we also perform motion segmentation and object detection in the presence of changes in the environment, such as illumination variation or “walking persons”. By combining the 2 algorithms we can accurately detect and track objects with a tracking accuracy rate of up to 99% and a frame per second of up to 40 Hz. Thus, a solid foundation is laid for subsequent landing guidance.
Open AccessAerial Target Tracking Algorithm Based on Faster R-CNN Combined with Frame Differencing
We propose a robust approach to detecting and tracking moving objects for a naval unmanned aircraft system (UAS) landing on an aircraft carrier. The frame difference algorithm follows a simple principle to achieve real-time tracking, whereas Faster Region-Convolutional Neural Network (R-CNN) performs highly precise detection and tracking characteristics. We thus combine Faster R-CNN with the frame difference method, which is demonstrated to exhibit robust and real-time detection and tracking performance. In our UAS landing experiments, two cameras placed on both sides of the runway are used to capture the moving UAS. When the UAS is captured, the joint algorithm uses frame difference to detect the moving target (UAS). As soon as the Faster R-CNN algorithm accurately detects the UAS, the detection priority is given to Faster R-CNN. In this manner, we also perform motion segmentation and object detection in the presence of changes in the environment, such as illumination variation or “walking persons”. By combining the 2 algorithms we can accurately detect and track objects with a tracking accuracy rate of up to 99% and a frame per second of up to 40 Hz. Thus, a solid foundation is laid for subsequent landing guidance.