Recorded recurrent deep reinforcement learning guidance laws for intercepting endoatmospheric maneuvering missiles

This work proposes a recorded recurrent twin delayed deep deterministic(RRTD3)policy gradient algorithm to solve the challenge of constructing guidance laws for intercepting endoatmospheric maneuvering missiles with uncertainties and observation noise.The attack-defense engagement scenario is modeled as a partially observable Markov decision process(POMDP).Given the benefits of recurrent neural networks(RNNs)in processing sequence information,an RNN layer is incorporated into the agent’s policy network to alleviate the bottleneck of traditional deep reinforcement learning methods while dealing with POMDPs.The measurements from the interceptor’s seeker during each guidance cycle are combined into one sequence as the input to the policy network since the detection frequency of an interceptor is usually higher than its guidance frequency.During training,the hidden states of the RNN layer in the policy network are recorded to overcome the partially observable problem that this RNN layer causes inside the agent.The training curves show that the proposed RRTD3 successfully enhances data efficiency,training speed,and training stability.The test results confirm the advantages of the RRTD3-based guidance laws over some conventional guidance laws.

Multiconstraint adaptive three-dimensional guidance law using convex optimization

The traditional guidance law only guarantees the accuracy of attacking a target. However, the look angle and acceleration constraints are indispensable in applications. A new adaptive three-dimensional proportional navigation(PN) guidance law is proposed based on convex optimization. Decomposition of the three-dimensional space is carried out to establish threedimensional kinematic engagements. The constraints and the performance index are disposed by using the convex optimization method. PN guidance gains can be obtained by solving the optimization problem. This solution is more rapid and programmatic than the traditional method and provides a foundation for future online guidance methods, which is of great value for engineering applications.

New three-dimensional guidance law for BTT missiles based on differential geometry and Lie-group

A new non-decoupling three-dimensional guidance law is proposed for bank-to-turn （BTT） missiles with the motion coupling problem. In this method, the different geometry is taken for theoretically modeling on B-IT missiles＇ motion within the threedimensional style without information loss, and meanwhile, Liegroup is utilized to describe the line-of-sight （LOS） azimuth when the terminal angular constraints are considered. Under these cir- cumstances, a guidance kinematics model is established based on differential geometry. Then, corresponding to no terminal angular constraint and terminal angular constraints, guidance laws are re- spectively designed by using proportional control and generalized proportional-derivative （PD） control in SO（3） group. Eventually, simulation results validate that this developed method can effectively avoid the complexity of pure Lie-group method and the information loss of the traditional decoupling method as well.

Three-dimensional suboptimal guidance law for fly-over and shoot-down smart ammunition via virtual target

An optimal burst height is required for the fly-over and shoot-down smart ammunition with an EFP warhead at the instant of explosion which brings a special requirement to the miss distance of the terminal guidance law. In this paper, a guidance law based on the virtual target scheme is proposed. First, the practical pursuit-evasion issue between the ammunition and the target with specific miss distance is transformed into a virtuai pursuit-evasion problem with zero miss distance. Secondly, a complete three-dimensional pursuit-evasion kinematics model is established without any simplifications. And then, a suboptimal guidance law is designed based on the θ-D method which has constraints of the elevation and azimuth angular velocity of the virtual line of sight （LOS）. Finally, in order to verify the performance of the proposed guidance law, three test cases are conducted. Numericai results show that under the proposed terminal guidance law, the smart ammunition not only can fly above the target with an optimal burst height but also have a smaller normal acceleration on the terminal trajectory.

Three-dimensional psychological guidance combined with evidencebased health intervention in patients with liver abscess treated with ultrasound

BACKGROUND Liver abscess is a common clinical liver disease mainly caused by suppurative bacteria or amoebae,with early clinical signs of chills,high fever,jaundice,and other symptoms.Establishing its early diagnosis is difficult,which may lead to misdiagnosis.AIM To observe the effects of psychological guidance combined with evidence-based health intervention in patients with liver abscess treated with ultrasound.METHODS A total of 120 patients with bacterial liver abscess admitted to our hospital from May 2018 to February 2021 were selected and divided into groups according to their intervention plan.RESULTS After the intervention,Self-Rating Depression Scale,Self-Rating Anxiety Scale,Self-Perceived Burden Scale(SPBS),and quality of life scores(physical functioning,role physical,bodily pain,general health,vitality,social functioning,role emotional,mental health)were lower than before the intervention in the two groups.The observation group had lower negative sentiment,SPBS,and quality of life scores than the control group.In the observation group,31 and 24 patients had good and general compliance,respectively,with a compliance rate of 91.67%,which was significantly higher than that in the control group.The observation group had significantly lower total incidence of incision infection,abdominal abscess,hemorrhage,and severe abdominal pain than the control group.CONCLUSION Three-dimensional psychological guidance combined with evidence-based health intervention in treating liver abscess can reduce patients’burden and negative emotions,improve patient compliance and quality of life,and reduce complications.

Three-dimensional nonlinear H_2/H_∞ guidance law based upon approach of solving the state feedback Nash balance point

Based upon the theory of the nonlinear quadric two-person nonzero-sum differential game,the fact that the time-limited mixed H2/H∞ control problem can be turned into the problem of solving the state feedback Nash balance point is mentioned. Upon this,a theorem about the solution of the state feedback control is given,the Lyapunov stabilization of the nonlinear system under this control is proved,too. At the same time,this solution is used to design the nonlinear H2/H∞ guidance law of the relative motion between the missile and the target in three-dimensional(3D) space. By solving two coupled Hamilton-Jacobi partial differential inequalities(HJPDI),a control with more robust stabilities and more robust performances is obtained. With different H∞ performance indexes,the correlative weighting factors of the control are analytically designed. At last,simulations under different robust performance indexes and under different initial conditions and under the cases of intercepting different maneuvering targets are carried out. All results indicate that the designed law is valid.

Development of A Three-Dimensional Guidance System for Long-Range Maneuvering of A Miniature Autonomous Underwater Vehicle

The present paper introduces a three-dimensional guidance system developed for a miniature Autonomous Underwater Vehicle（AUV）. The guidance system determines the best trajectory for the vehicle based on target behavior and vehicle capabilities. The dynamic model of this novel AUV is derived based on its special characteristics such as the horizontal posture and the independent diving mechanism. To design the guidance strategy, the main idea is to select the desired depth, presumed proportional to the horizontal distance of the AUV and the target. By connecting the two with a straight line, this strategy helps the AUV move in a trajectory sufficiently close to this line. The adjacency of the trajectory to the line leads to reasonably short travelling distances and avoids unsafe areas. Autopilots are designed using sliding mode controller. Two different engagement geometries are considered to evaluate the strategy＇s performance： stationary target and moving target. The simulation results show that the strategy can provide sufficiently fast and smooth trajectories in both target situations.

Fast fixed-time three-dimensional terminal guidance with non-concave trajectory constraint

Focusing on the non-concave trajectory constraint,a sliding-mode-based nonsingular feedback fast fixed-time three-dimensional terminal guidance of rotor unmanned aerial vehicle landing,planetary landing and spacecraft rendezvous and docking terminal phase with external disturbance is investigated in this paper.Firstly,a fixed-time observer based on real-time differentiator is developed to compensate for the external disturbance,whose estimation error can converge to zero after a time independent of the initial state.Then,a sliding surface ensuring fixed-time convergence is presented.This sliding surface can guarantee that the vehicle achieves a non-concave trajectory,which is better for avoiding collision and maintaining the visibility of the landing site or docking port.Next,the nonsingular guidance ensuring the fixed-time convergence of the sliding surface is proposed,which is continuous and chatter free.At last,three numerical simulations of Mars landing are performed to validate the effectiveness and correctness of the designed scheme.

Design of a robust guidance law via active disturbance rejection control

Focusing on the three-dimensional guidance problem in case of target maneuvers and response delay of the autopilot, the missile guidance law utilizing active disturbance rejection control （ADRC） is proposed. Based on the nonlinear three-dimensional missile target engagement kinematics, the guidance model is es- tablished, The target acceleration is treated as a disturbance and the dynamics of the autopilot is considered by using a first-order model. A nonlinear continuous robust guidance law is designed by using a cascaded structure ADRC controller. In this method the disturbance is estimated by using the extended state observer （ESO） and compensated during each sampling period. Simulation results show that the proposed cascaded loop structure is a viable solution to the guidance law design and has strong robustness with respect to target maneuvers and response delay of the autopilot.

Three-dimensional Electromagnetic Characteristics Analysis of Novel Linear Synchronous Motor under Lateral and Yaw Conditions of MAGLEV

Dynamic stability analysis of superconducting electro-dynamic maglev train under lateral and yawing motion condition is the key research content.The novel three-dimensional electromagnetic model of integrated linear synchronous motor in electro-dynamic maglev train with yawing operation condition is proposed,which can not only simultaneously achieve the propulsion,levitation and guidance performances of maglev vehicle,but also analyze the dynamic stability performance of train with yawing condition.The three-dimensional analytical method is introduced for analyzing the electromagnetic force characteristics of the linear synchronous motor with the yawing operation condition.Firstly,the topology structure and operation principle of the linear synchronous motor with yawing attitude are proposed.Secondly,the three-dimensional analytical model and expressions of electromagnetic characteristics are obtained by equivalent circuit method and Fourier decomposition method,such as levitation force,guidance force,propulsion force and yawing torque,etc.Finally,the three-dimensional electromagnetic characteristics of the linear synchronous motor are calculated under yawing operation conditions of maglev train,and the correctness of the analytical theory is verified by the finite element analysis and measured data on the test line.

通信速率约束下一体化角度协同制导控制方法

针对多飞行器协同拦截过程中的角度协同问题,设计了一种基于量化编码器的分布式一体化协同制导控制律。首先建立多飞行器协同制导与控制数学模型,并基于扩张状态观测器理论,对单个飞行器各状态进行观测。在此基础上考虑各飞行器间单次传输数据的字长、两次传输数据间隔的通信速率约束,采用量化器-编码器-解码器实现限制通信速率情况下的协同一体化制导控制设计。之后,通过严格的理论分析证明了满足强连通图有向通信网络下,多飞行器系统能够达成一致性且收敛到期望的相对视线角,并给出了满足收敛条件的参数选择范围。最后,通过数学仿真校验,验证了所提出的方法在较低的通信速率下能够完成协同。

Three-dimensional adaptive finite-time guidance law for intercepting maneuvering targets

To intercept maneuvering targets at desired impact angles, a three-dimensional terminal guidance problem is investigated in this study. Because of a short terminal guidance time, a finitetime impact angle control guidance law is developed using the fast nonsingular terminal sliding mode control theory. However, the guidance law requires the upper bound of lumped uncertainty including target acceleration, which may not be accurately obtained. Therefore, by adopting a novel reaching law, an adaptive sliding mode guidance law is provided to release the drawback. At the same time, this method can accelerate the convergence rate and weaken the chattering phenomenon to a certain extent. In addition, another novel adaptive guidance law is also derived; this ensures systems asymptotic and finite-time stability without the knowledge of perturbations bounds.Numerical simulations have demonstrated that all the three guidance laws have effective performances and outperform the traditional terminal guidance laws.

Three-dimensional cooperative guidance strategy and guidance law for intercepting highly maneuvering target

Cooperative interception of the target with strong maneuverability by multiple missiles with weak maneuverability in the three-dimensional nonlinear model is studied.Firstly,the three-dimensional nonlinear model of cooperative guidance is established.The three-dimensional reachable region is represented composed of lateral acceleration and longitudinal acceleration in the two-dimensional coordinate system.Secondly,the problem of the multiple missile’s reachable coverage area is transformed into the problem of cooperative coverage.A cooperative coverage strategy is proposed and an algorithm for quickly calculating the number of required missiles is designed.Then,the guidance law based on the cooperative coverage strategy is proposed,and it is proved that cooperative interception of the target can be achieved under the acceleration limit.Moreover,the relations among the number of missiles,the initial array position of terminal guidance and the coverage area of the target’s large maneuver are analyzed.The dynamic adjustment strategy of guidance parameters is proposed to reduce the guidance error.Finally,simulation results show that multiple missiles with low maneuverability can achieve effective interception of target with strong maneuverability through the proposed cooperative strategy and cooperative guidance method.

大气层外动能拦截器制导控制技术研究进展与展望

大气层外高速、大机动、多目标飞行器的拦截问题已成为当前空天防御体系构建面临的重大挑战和难点。首先,对近年来国外大气层外动能拦截器技术及飞行试验现状进行了梳理和总结;其次,对大气层外单一拦截器制导控制方法和多弹协同拦截制导控制方法的研究进展进行了综述;最后,对大气层外动能拦截器未来重点开展的关键技术进行了展望,以期为未来大气层外动能拦截器技术发展提供方向性参考和借鉴。

基于分层强化学习的低过载比拦截制导律

为解决低过载比和纯角度量测等约束下的三维机动目标拦截制导问题,提出了一种基于分层强化学习的拦截制导律。首先将问题建模为马尔科夫决策过程模型,并考虑拦截能量消耗与弹目视线角速率,设计了一种启发式奖赏函数。其次通过构建具有双层结构的策略网络,并利用上层策略规划阶段性子目标来指导下层策略生成所需的制导指令,实现了拦截交战过程中的视线角速率收敛,以保证能成功拦截机动目标。仿真结果验证了所提出的方法较增强比例导引具有更高的拦截精度和拦截概率,且拦截过程的需用过载更低。

拦截高超声速滑翔飞行器:制导进展与展望

聚焦于临近空间拦截制导关键技术,围绕中制导、中末制导交班及末制导等关键问题对临近空间拦截制导技术前景进行展望。首先对临近空间高超声速滑翔飞行器飞行特性进行仿真与分析,并给出防御系统在滑翔段拦截的优势所在;其次,围绕临近空间拦截系统面对高超声速滑翔飞行器时存在的瓶颈进行探讨,并对中制导离线弹道生成与在线弹道生成、中末制导交班及末制导等关键技术相关研究进展进行梳理与总结;最后,结合当前研究进展、面临的挑战及未来临近空间拦截需求,研究分析临近空间拦截制导技术的发展趋势,为后续防御系统的发展提供参考。

一种基于扰动补偿的机弹协同LOS主动防御制导律

随着无人技术和军事科技发展,无人近距空战引起了世界军事强国的广泛关注。面临高速大机动能力来袭导弹的威胁,传统的抛洒箔条或释放热焰弹等被动防御措施无法确保目标飞行器安全逃逸,通过发射拦截弹协同目标飞行器机动实施的主动防御是一种可行的方法。由于来袭导弹机动能力较强且加速度信息未知,是目标飞行器-拦截弹制导律协同设计的难点。提出一种基于扰动补偿的LOS主动防御拦截制导律,通过设计一种非线性扰动观测器来估计来袭弹产生的机动的影响,并在机弹协同LOS主动防御制导律设计中补偿。通过仿真算例验证了所提方法能够有效拦截具有未知机动能力的来袭导弹,为研究三体攻防问题提供了一定的参考。

基于预设性能的导弹拦截鲁棒智能制导律

针对具有模型不确定性的导弹拦截问题,研究了结合预设性能控制的复合学习方法。首先,建立了导弹拦截的制导控制一体化模型。为了保证对双方脱靶量的约束,基于预设性能函数来保证跟踪性能。考虑系统中的模型不确定性,为了提高系统在不确定性下的精度,构造了一种复合学习律来在线估计系统的未知非线性函数。最后,通过Lyapunov分析,证明了系统的稳定性。经过仿真验证,所提出的算法可保证成功拦截目标,并能保证跟踪误差在规定的性能曲线之内,证明了该算法的有效性。

基于视线协同和DMPC的载机-防御弹群协同主动防御制导策略

在目标-攻击弹-防御弹群(target-attacker-defenders,TADs)系统中,防御弹群通过与目标(载机)异构协同、弹群间同构协同以保护载机并降低单弹脱靶的风险。针对TADs系统在二维平面下的协同主动防御模型进行了研究,采用机/弹协同和防御弹群协同的两层制导策略。在机弹协同方面,防御弹领弹与载机进行异构协同,考虑载机及防御弹领弹的机动能力限制,采用协同视线制导律(cooperative line of sight guidance,CLOSG)分别得到载机和防御弹领弹的制导指令;在防御弹群协同方面,考虑单弹计算能力约束,拦截时间约束和加速度约束,设计出基于分布式模型预测控制(distributed model predictive control,DMPC)的算法实现弹群从弹和防御弹领弹协同同时抵达并拦截攻击弹。仿真结果表明,多防御弹协同一致拦截制导算法能够实现TADs系统中载机和防御弹群的异构协同主动防御,并实现防御弹群的一致性同时拦截,以降低单弹脱靶的风险。