Hybrid Gradient Vector Fields Based on Maneuver Space for Path-following Guidance

Yiyang Zhao,Deyun Zhou,Zhen Yang,Xiaoyang Li,Jichuan Huang,Xiaofeng Lv 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

Guidance path-planning and following are two important functionalities of unmanned aerial vehicles (UAVs), but only a few approaches deal with both. In this study, an innovative hybrid gradient vector fields algorithm based on maneuver space (HGVFs-MS) for path-following guidance is proposed to control fixed-wing UAVs to follow a generated guidance path and oriented target curves in three-dimensional space, which can be any combination of straight lines, arcs, and helixes as motion primitives. The strategies designed in earlier studies have flaws that prevent the UAV from following arcs that make its turning angle too large. The switching strategy proposed in this study solves this problem by introducing the concept of the virtual waypoints. Finally, the performance of the HGVFs-MS algorithm is verified by three representative simulation scenarios. The simulation considers the constraints of the aircraft, and its results indicate that the algorithm performs well in following both lateral and longitudinal control, particularly for curved paths.

Generation Method of Autonomous Evasive Maneuver Strategy in Air Combat

Lin Li,Zhen Yang,Zhixiao Sun,Guang Zhan,Haiyin Piao,Deyun Zhou 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

Air combat is usually a continuous process involving multiple rounds of missile attacks, UCAV(Unmanned Combat Aerial Vehicle) should consider the impact of maneuver on the entire air combat countermeasure mission rather than solely focusing on safety factors when evading incoming air to air missiles. In this paper, a method of generating autonomous evasive maneuver strategy in UCAV air combat is proposed under the condition of miss distance and energy dissipation. Firstly, the UCAV-missile three-dimensional space pursuit model and the UCAV autonomous evading state space, action space and reward function model are established. Dueling DDQN (Double Deep Q Network) algorithm is used to solve the model, which integrates Double DQN and Dueling DQN Network model. Simulation experiments and analysis show that the method proposed in this paper has significant effectiveness in solving the problem of autonomous evasive maneuvers in air combat under the conditions of miss distance and energy dissipation tactical requirements. The evasive maneuvers strategy obtained can reflect the two tactical requirements of air combat while ensuring the safety of UCAV itself.

Study on Cooperative Air-to-Ground Surveillance Planning and Controlling for Unmanned Aerial Vehicles

Shiyuan Chai,Zhen Yang,Jichuan Huang,Xiaoyang Li,Yiyang Zhao,Deyun Zhou 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

The use of unmanned aerial vehicles (UAVs) for air-to-ground mission in complex environments has increased considerably in recent years. The numerous studies on UAVs cooperative air-to-ground mission controlling have been reported, but few have considered the impact of the communication instability due to electromagnetic interference (EMI) which is common in many air-to-ground applications. Under the influence of EMI, the air-to-ground mission stages are represented as a dynamic combination of several communication-available and communication-unavailable stages. Traditional cooperative surveillance algorithms cannot handle such situations well. In this study, we presented a method which based on Voronoi diagrams to solve the impact of communication outages, and an attention mechanism ant-colony optimization (AACO) algorithm was proposed for UAV path-planning control in air-to-ground surveillance missions. The controlling strategy is adaptively updated by introducing an attention mechanism for regular instruction information, a priori information, and emergent information of the mission to satisfy the mission target. Simulation results show that the proposed algorithm achieves better search performance than traditional algorithms in scenarios which include communication-available and communication-unavailable situations.

Three-dimensional Multi-missile Cooperative Guidance Law with Time and Space Constraints

Jian Meng,Zhen Yang,Jichuan Huang,Haiyin Piao,Yiyang Zhao,Deyun Zhou 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

This study focuses on the problem of multiple air-to-air missiles coordinated intercepting maneuvering targets in three-dimensional (3-D) space. A fixed time cooperative interception law with attack time and line-of-sight (LOS) angle limitations is proposed. Firstly, we extended the commonly used two-dimensional (2-D) space guidance model to 3-D space, and constructs a 3-D missile-target relative motion model. Secondly, the missile guidance model is decoupled to along and perpendicular to the LOS, and in the LOS direction, a cooperative guiding law based on fixed-time consistency theory is intended to guarantee that all missiles strikes the target at the same moment. Moreover, in the LOS normal direction, an adaptive approach rule is created, and the LOS angle of each missile is regulated to reaching to a given value in a defined time. According to the proposed fixed time fast non-singular terminal sliding mode surface, and spatial coordination is accomplished. In addition, based on Lyapunov stability theory, a detailed fixed time stability analysis is given. In the end, simulation is used to verify the feasibility and efficacy of the guideline law.

A Maneuver Control Method for Stealthy Engagement in Beyond-visual-range Air Combat Based on Sliding Mode Control

Yue Liu,Zhen Yang,Jichuan Huang,Guang Zhan,Xiaoyang Li,Deyun Zhou 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

A S-type engagement of beyond-visual-range (BVR) air combat tactical method based on sliding mode control is proposed, which is aiming at the problem of Doppler pulse (PD) radar blind zone. By introducing the Electronic Support Measures (ESM), the whole tactical process is divided into two sub-processes: quick engagement and stealthy engagement. This paper designs a stealthy engagement process controller based on the double power sliding mode control, and a quick engagement process controller based on the back-stepping second order sliding mode. The simulation experiment shows that our aircraft can use EMS to judge the enemy radar detection information and switch the strategy. And it can successfully enter the enemy radar blind zone through S-type maneuver, occupy the dominant area, which can effectively complete the stealthy engagement.

Online Recognition Method for Target Maneuver in UAV Autonomous Air Combat

Yicong Li,Zhen Yang,Xiaofeng Lv,Jichuan Huang,Yiyang Zhao,Deyun Zhou 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

In unmanned aerial vehicle (UAV) autonomous air combat, target maneuver online recognition is beneficial to predict the tactical intention of the target, which is of great significance to air combat situational awareness and decision-making assistance. However, the target trajectory data acquired by our airborne sensors may contain one or more maneuvers. The existing research methods mainly focus on the recognition of single maneuver trajectory which has been segmented according to maneuver segments or the segmentation of target maneuver trajectory by introducing human experience. The above methods can not meet the requirements of online recognition of the unknown continuous multi-segment maneuvers trajectory in autonomous air combat. In this paper, the online recognition problem of target maneuver is transformed into three classification problems, which are maneuver switch subsequence recognition problem, maneuver switch point localization problem and single maneuver recognition problem. The cascaded classification networks based on Long Short-Term Memory (LSTM) temporal feature extraction is used to map maneuver trajectory to maneuver category sequence. The algorithm proposed in this paper is tested by randomly selecting target trajectories, which can automatically segment the trajectories and recognize the correct categories. The average sequence similarity between the predicted maneuver category sequence and the real maneuver category sequence after segmentation and recognition on the test set is above 0.9. The feasibility and effectiveness of the proposed algorithm are verified.