检索结果-南通市图书馆

Learning and fatigue inspired method for optimized HTN planning

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2012年第2期23卷 233-241页

作者： Wanpeng Zhang lincheng shen Jing Chen College of Mechatronic Engineering and Automation National University of Defense TechnologyChangsha 410073P.R.China

Learning is widely used in intelligent planning to shorten the planning process or improve the plan quality. This paper aims at introducing learning and fatigue into the classical hierarchical task network （HTN） planning process so as to create better high- quality plans quickly. The process of HTN planning is mapped during a depth-first search process in a problem-solving agent, and the models of learning in HTN planning is conducted similar to the learning depth-first search （LDFS）. Based on the models, a learning method integrating HTN planning and LDFS is presented, and a fatigue mechanism is introduced to balance exploration and exploitation in learning. Finally, experiments in two classical do- mains are carried out in order to validate the effectiveness of the proposed learning and fatigue inspired method.

关键词： hierarchical task network (HTN) planning learning fatigue.

Hybrid hierarchical trajectory planning for a fixed-wing UCAV performing air-to-surface multi-target attack

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2012年第4期23卷 536-552页

作者： Yu Zhang Jing Chen lincheng shen School of Mechatronics Engineering and Automation National University of Defense TechnologyChangsha 410073E R.China

This paper considers the problem of generating a flight trajectory for a single fixed-wing unmanned combat aerial vehicle （UCAV） performing an air-to-surface multi-target attack （A/SMTA） mission using satellite-guided bombs. First, this problem is formulated as a variant of the traveling salesman problem （TSP）, called the dynamic-constrained TSP with neighborhoods （DCT- SPN）. Then, a hierarchical hybrid approach, which partitions the planning algorithm into a roadmap planning layer and an optimal control layer, is proposed to solve the DCTSPN. In the roadmap planning layer, a novel algorithm based on an updatable proba- bilistic roadmap （PRM） is presented, which operates by randomly sampling a finite set of vehicle states from continuous state space in order to reduce the complicated trajectory planning problem to planning on a finite directed graph. In the optimal control layer, a collision-free state-to-state trajectory planner based on the Gauss pseudospectral method is developed, which can generate both dynamically feasible and optimal flight trajectories. The entire process of solving a DCTSPN consists of two phases. First, in the offline preprocessing phase, the algorithm constructs a PRM, and then converts the original problem into a standard asymmet- ric TSP （ATSP）. Second, in the online querying phase, the costs of directed edges in PRM are updated first, and a fast heuristic searching algorithm is then used to solve the ATSP. Numerical experiments indicate that the algorithm proposed in this paper can generate both feasible and near-optimal solutions quickly for online purposes.

关键词： hierarchical trajectory planning air-to-surface multi-target attack (A/SMTA) traveling salesman problem (TSP) proba-bilistic roadmap Gauss pseudospectral method unmanned com-bat aerial vehicle (UCAV).

Real-time trajectory planning for UCAV air-to-surface attack using inverse dynamics optimization method and receding horizon control

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2013年第4期26卷 1038-1056页

作者： Zhang Yu Chen Jing shen lincheng College of Mechatronics Engineering and Automation National University of Defense Technology

This paper presents a computationally efficient real-time trajectory planning framework for typical unmanned combat aerial vehicle （UCAV） performing autonomous air-to-surface （A/S） attack. It combines the benefits of inverse dynamics optimization method and receding horizon optimal control technique. Firstly, the ground attack trajectory planning problem is mathematically formulated as a receding horizon optimal control problem （RHC-OCP）. In particular, an approximate elliptic launch acceptable region （LAR） model is proposed to model the critical weapon delivery constraints. Secondly, a planning algorithm based on inverse dynamics optimization, which has high computational efficiency and good convergence properties, is developed to solve the RHCOCP in real-time. Thirdly, in order to improve robustness and adaptivity in a dynamic and uncer- tain environment, a two-degree-of-freedom （2-DOF） receding horizon control architecture is introduced and a regular real-time update strategy is proposed as well, and the real-time feedback can be achieved and the not-converged situations can be handled. Finally, numerical simulations demon- strate the efficiency of this framework, and the results also show that the presented technique is well suited for real-time implementation in dynamic and uncertain environment.

关键词： Air-to-surface attack Direct method Inverse dynamics Motion planning Real time control Receding horizon control Trajectory planning Unmanned combat aerial vehicles

Improving multi-target cooperative tracking guidance for UAV swarms using multi-agent reinforcement learning

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第7期35卷 100-112页

作者： Wenhong ZHOU Jie LI Zhihong LIU lincheng shen College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China

Multi-Target Tracking Guidance(MTTG)in unknown environments has great potential values in applications for Unmanned Aerial Vehicle(UAV)*** Multi-Agent Deep Reinforcement Learning(MADRL)is a promising technique for learning cooperation,most of the existing methods cannot scale well to decentralized UAV swarms due to their computational complexity or global information *** paper proposes a decentralized MADRL method using the maximum reciprocal reward to learn cooperative tracking policies for UAV *** method reshapes each UAV’s reward with a regularization term that is defined as the dot product of the reward vector of all neighbor UAVs and the corresponding dependency vector between the UAV and the *** the dependence between UAVs can be directly captured by the Pointwise Mutual Information(PMI)neural network without complicated aggregation ***,the experience sharing Reciprocal Reward Multi-Agent Actor-Critic(MAAC-R)algorithm is proposed to learn the cooperative sharing policy for all homogeneous *** demonstrate that the proposed algorithm can improve the UAVs’cooperation more effectively than the baseline algorithms,and can stimulate a rich form of cooperative tracking behaviors of UAV ***,the learned policy can better scale to other scenarios with more UAVs and targets.

关键词： Decentralized cooperation Maximum reciprocal reward Multi-agent actor-critic Pointwise mutual information Reinforcement learning

Formation flight of fixed-wing UAV swarms:A group-based hierarchical approach

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2021年第2期34卷 504-515页

作者： Hao CHEN Xiangke WANG lincheng shen Yirui CONG College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China

This paper investigates a formation control problem of fixed-wing Unmanned Aerial Vehicle(UAV) swarms. A group-based hierarchical architecture is established among the UAVs, which decomposes all the UAVs into several distinct and non-overlapping groups. In each group, the UAVs form hierarchies with one UAV selected as the group leader. All group leaders execute coordinated path following to cooperatively handle the mission process among different groups, and the remaining followers track their direct leaders to achieve the inner-group coordination. More specifically, for a group leader, a virtual target moving along its desired path is assigned for the UAV, and an updating law is proposed to coordinate all the group leaders’ virtual targets;for a follower UAV, the distributed leader-following formation control law is proposed to make the follower’s heading angle coincide with its direct leader, while keeping the desired relative position with respect to its direct leader. The proposed control law guarantees the globally asymptotic stability of the whole closed-loop swarm system under the control input constraints of fixed-wing UAVs. Theoretical proofs and numerical simulations are provided, which corroborate the effectiveness of the proposed method.

关键词： Control input constraints Coordinated path following Formation control Leader-following control Unmanned aerial vehicles swarms

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

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2011年第4期22卷 684-690页

作者： Shuangchun Peng Liang Pan Tianjiang Hu lincheng shen College of Mechatronic Engineering and Automation National University of Defense Technology Changsha 410073 P. R. China

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.

关键词： three-dimensional guidance law differential geometry,Lie-group control bank-to-turn (BTT).

Vector Field Based Sliding Mode Control of Curved Path Following for Miniature Unmanned Aerial Vehicles in Winds

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2018年第1期31卷 302-324页

作者： WANG Yajing WANG Xiangke ZHAO Shulong shen lincheng College of Mechatronic Engineering and Automation National University of Defense Technology

In this paper, a curved path following control algorithm for miniature unmanned aerial vehicles（UAVs） in winds with constant speed and altitude is developed. Different to the widely considered line or orbit following, the curved path to be followed is defined in terms of the arc-length parameter, which can be straight lines, orbits, B-splines or any other curves provided that they are smooth. The proposed path following control algorithm, named by VF-SMC, is combining the vector field（VF） strategy with the sliding mode control（SMC） method. It is proven that the designed algorithm guarantees the tracking errors to be a bounded ball in the presence of winds, with the aid of the Lyapunov method and the BIBO stability. The algorithm is validated both in Matlab-based simulations and high-fidelity semi-physical simulations. In Matlab-based simulations, the proposed algorithm is verified for straight lines, orbits and B-splines to show its wide usage in different *** high-fidelity semi-physical simulation system is composed of actual autopilot controller, ground station and X-Plane flight simulator in-loop. In semi-physical simulations, the proposed algorithm is verified for B-spline path following under various gain parameters and wind conditions *** experiments show the accuracy in curved path following and the excellent robustness to wind disturbances of the proposed algorithm.

关键词： Curved path following miniature UAVs sliding mode control vector field wind disturbance

Truthfully coordinating participation routes in informative participatory sensing

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第12期64卷 132-146页

作者： Shaofei CHEN Dengji ZHAO Alexandros ZENONOS Jing CHEN lincheng shen College of Intelligence Science and Technology National University of Defense Technology School of Information Science and Technology ShanghaiTech University School of Electronics and Computer Science University of Southampton

Participatory sensing is a promising approach with which people contribute sensory information to form a body of knowledge. In practice, people may have different ways to engage in a participatory sensing campaign. For example, there are several possible routes from a participant’s home to her office, where a route can be seen as a set of space-temporal coordinates, and measurements can be taken at these coordinates. To coordinate participation routes to collect more valuable information with a limited number of participants,a further concept, informative participatory sensing(IPS) has been developed recently. However, existing IPS systems lack incentive mechanisms to fight against the strategic behaviours of self-interested ***, we propose a formal model of IPS where a service provider can coordinate individual schedules of self-interested participants. As the problem of informative path coordination is NP-hard, the well-known mechanism, Vickrey-Clarke-Groves(VCG) will be computationally inefficient to solve our problem. Given this, we design a sequentially sorting mechanism(SSM) for the model to allocate the schedules and determine the bonuses for these participants, and we then theoretically prove that SSM is computationally efficient,individually rational, profitable and truthful. Furthermore, we empirically evaluate our route allocation method in simulations and show that it significantly outperforms several benchmark approaches.

关键词： coordinating participation routes Coordinating participation routes informative participatory sensing incentive mechanism computationally efficient

同方期刊数据库

Robust optimization of aircraft weapon delivery trajectory using probability collectives and meta-modeling

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2013年第2期26卷 423-434页

作者： Wang Nan shen lincheng Liu Hongfu Chen Jing Hu Tianjiang College of Mechatronic Engineering and Automation National University of Defense Technology Science and Technology on Aerospace Flight Dynamics Laboratory

Conventional trajectory optimization techniques have been challenged by their inability to handle threats with irregular shapes and the tendency to be sensitive to control variations of aircraft. Aiming to overcome these difficulties, this paper presents an alternative approach for trajectory optimization, where the problem is formulated into a parametric optimization of the maneuver variables under a tactics template framework. To reduce the size of the problem, global sensitivity analysis （GSA） is performed to identify the less-influential maneuver variables. The probability collectives （PC） algorithm, which is well-suited to discrete and discontinuous optimization, is applied to solve the trajectory optimization problem. The robustness of the trajectory is assessed through multiple sampling around the chosen values of the maneuver variables. Meta-models based on radius basis function （RBF） are created for evaluations of the means and deviations of the problem objectives and constraints. To guarantee the approximation accuracy, the meta-models are adaptively updated during optimization. The proposed approach is demonstrated on a typical airground attack mission scenario. Results reveal that the proposed approach is capable of generating robust and optimal trajectories with both accuracy and efficiency.

关键词： Meta-model Probability collectives Sensitivity analysis Tactics template Trajectory optimization