检索结果-南通市图书馆

基于多步信息辅助的Q-learning路径规划算法

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

系统仿真学报 2024年第9期36卷 2137-2148页

作者：王越龙王松艳晁涛哈尔滨工业大学控制与仿真中心黑龙江哈尔滨150001

为提升静态环境下移动机器人路径规划能力,解决传统Q-learning算法在路径规划中收敛速度慢的问题,提出一种基于多步信息辅助机制的Q-learning改进算法。利用ε-greedy策略中贪婪动作的多步信息与历史最优路径长度更新资格迹,使有效的资... 详细信息

为提升静态环境下移动机器人路径规划能力,解决传统Q-learning算法在路径规划中收敛速度慢的问题,提出一种基于多步信息辅助机制的Q-learning改进算法。利用ε-greedy策略中贪婪动作的多步信息与历史最优路径长度更新资格迹,使有效的资格迹在算法迭代中持续发挥作用,用保存的多步信息解决可能落入的循环陷阱;使用局部多花朵的花授粉算法初始化Q值表,提升机器人前期搜索效率;基于机器人不同探索阶段的目的,结合迭代路径长度的标准差与机器人成功到达目标点的次数设计动作选择策略,以增强算法对环境信息探索与利用的平衡能力。实验结果表明:该算法具有较快的收敛速度,验证了算法的可行性与有效性。

关键词：路径规划 Q-learning 收敛速度动作选择策略栅格地图

维普期刊数据库博看期刊

在线全文

学校读者我要写书评

暂无评论

变体飞行器变形策略与控制方法研究进展

战术导弹技术 2024年第4期 1-15页

作者：王帅晁涛韩宇辰杜鹤哈尔滨工业大学控制与仿真中心复杂系统建模与仿真全国重点实验室哈尔滨150001

变体飞行器可以根据任务需求改变自身气动特性和控制特性,具备跨空域、宽速域飞行能力,可适应多种复杂任务。针对变体飞行器的重要研究价值,整理了变体飞行器的发展历程,介绍常见的变体飞行器变形方式,并列举了各时期研制的代表性飞行... 详细信息

变体飞行器可以根据任务需求改变自身气动特性和控制特性,具备跨空域、宽速域飞行能力,可适应多种复杂任务。针对变体飞行器的重要研究价值,整理了变体飞行器的发展历程,介绍常见的变体飞行器变形方式,并列举了各时期研制的代表性飞行器。对变体飞行器变形策略进行归纳分析,对比了传统变形策略和智能变形策略的优劣。围绕变体飞行器的姿态控制方法,详细阐述了国内外主要研究成果和最新研究进展。最后对变体飞行器未来发展趋势进行梳理,并针对变体飞行器变形策略与控制技术目前研究成果的优缺点进行了总结。

关键词：变体飞行器传统变形策略智能变形策略线性控制非线性控制智能控制

结合对象单元和Transformer网络的城市功能区分类

在线全文

学校读者我要写书评

暂无评论

遥感学报 2024年第8期28卷 1927-1939页

作者：鲁伟鹏贺清康李佳铃李诗逸陶超中南大学地球科学与信息物理学院长沙410012 香港理工大学土地测量及地理资讯学系中国香港999077

准确识别各类城市功能区并全面掌握其分布情况,对合理规划和科学管理城市至关重要。针对该问题,本文提出一种结合对象单元和Transformer网络的城市功能区分类方法。该方法首先以多尺度分割所获得的过分割对象作为最小分析单元,以避免出... 详细信息

准确识别各类城市功能区并全面掌握其分布情况,对合理规划和科学管理城市至关重要。针对该问题,本文提出一种结合对象单元和Transformer网络的城市功能区分类方法。该方法首先以多尺度分割所获得的过分割对象作为最小分析单元,以避免出现同一分析单元包含多种城市功能区的情况。在此基础上,针对现有方法着重于对分析单元内部特征提取而忽略了分析单元之间的空间关系问题,提出利用Transformer框架和对象地理属性作为位置编码对不同分析单元之间的空间关系进行建模,从而实现兼顾分析单元内部特征和不同分析单元之间空间关系的城市功能区分类。结果表明,使用过分割对象作为最小分析单元能够更加准确地获取城市功能区地边界,从而避免基于规则格网单元所导致的锯齿状边缘及基于路网单元所导致地无法区分路网内不同功能区的问题;与仅考虑分析单元内部特征的传统方法相比,通过对不同分析单元之间的分析单元进行建模可有效提升城市功能区分类精度。

关键词：城市功能区遥感深度学习空间关系建模 Transformer网络

在线全文

学校读者我要写书评

暂无评论

飞行爬壁桥梁检测机器人的翼间气动干扰分析

科学技术与工程 2024年第11期24卷 4583-4590页

作者：王正杰刘朝涛王鑫鑫重庆交通大学机电与车辆工程学院重庆400047

为满足飞行爬壁桥梁检测机器人的功能特点,结构上,飞行爬壁机器人在飞行状态下时,四个旋翼不在同一平面而是处于一种纵列式排列。针对这种纵列式旋翼间存在的复杂气动干扰,先对单旋翼流场进行计算流体动力学(computational fluid dynami... 详细信息

为满足飞行爬壁桥梁检测机器人的功能特点,结构上,飞行爬壁机器人在飞行状态下时,四个旋翼不在同一平面而是处于一种纵列式排列。针对这种纵列式旋翼间存在的复杂气动干扰,先对单旋翼流场进行计算流体动力学(computational fluid dynamics,CFD)仿真并验证其可靠性。在此基础上分别对纵列式双旋翼在不同横间距、不同纵间距、不同转速的情况下进行气动仿真。然后根据仿真结果进行分析,得到横纵间距以及转速对前后旋翼以及整个系统的气动特性影响。仿真结果表明:横间距对纵列式旋翼间的气动干扰较大,而轴向间距相对较小,干扰程度与转速相关。可见本文结论可为飞行爬壁机器人的旋翼布局、转速、可行性等提供依据。

关键词：飞行爬壁桥梁检测机器人纵列式计算流体动力学(CFD) 气动干扰流体仿真

Modified rolling guidance law for single moving mass controlled reentry vehicle against maneuvering target with impact angle constraints

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第6期35卷 226-239页

作者： Guanlin LI Ming YANG Songyan WANG tao chao Control and Simulation Center Harbin Institute of TechnologyHarbin 150001China

This paper deals with the problem of guidance law design for the single moving mass controlled reentry vehicle when impact angle constraints and maneuvering target are taken into *** specifically,a modified rolling guidance law is proposed with the interactive virtual target and the landing point prediction ***,considering the fact that the roll channel can be controlled directly,the relative motion between the single moving mass controlled reentry vehicle and the target is described by the error angle between the relative velocity and the ***,a nonlinear error angle command is given to reduce the rotation *** satisfy impact angle constraints,an interactive virtual target is presented and the‘‘S”formed velocity of the virtual target is given to abate the error angle tracking difficulty at the final stage of the reentry ***,the landing point prediction strategy is employed and the motion variation trend is also taken into *** the maneuvering target is replaced with the predicted landing point,the error angle tracking difficulty caused by the target velocity decreases,which is helpful to meet impact angle constraints and improve guidance accuracy at the same ***,the finite-time rolling guidance law is proposed and proved via Lyapunov stability *** with the existing method,lower-speed rotation,smaller missing distance and less impact angle errors are obtained,which can be demonstrated by numerical simulations.

关键词： Reentry vehicles Guidance law Impact angle Maneuvering target Finite-time convergence

Linear-quadratic and norm-bounded differential game combined guidance strategy against active defense aircraft in three-player engagement

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2023年第8期36卷 331-350页

作者： tao chao Xintao WANG Songyan WANG Ming YANG Control and Simulation Center Harbin Institute of TechnologyHarbin 150080China

A new type of guidance strategy, combining linear quadratic and norm-bounded game theory, is proposed for the scenario of an attacker against active defense aircraft in three-player engagement. The problem involves three players, an attacker, a defender and a target. The differential game theory and the solution of Hamiltonian equation are utilized to obtain the combined guidance strategy for each player with arbitrary-order dynamics. The game process is divided into4 phases, C1-C4, according to the switching time. The linear quadratic differential game guidance scheme is employed to reduce the fuel cost in the game parts of C1 and C3. The norm-bounded game guidance strategy is adopted to satisfy the constraint of control input in the game stages C2 and C4. Furthermore, zero-effort miss distance is introduced to meet the constraints of game space and defender’s killing radius in the guidance strategy, which guarantees that the attacker is able to avoid the interception of the defender and hit the target with lower fuel cost and maximum acceleration. And it is proved that the proposed guidance strategy satisfies the Nash equilibrium condition. Finally, the feasibility and superiority of combined guidance strategy are respectively illustrated by nonlinear numerical simulation and verified by comparing with linear quadratic and norm-bounded differential game guidance strategies.

关键词： Activedefense aircraft Acceleration Energy optimization Game theory Three-player engagement

Robust spline-line energy management guidance algorithm with multiple constraints and uncertainties for solid rocket ascending

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第2期35卷 214-234页

作者： Songyan WANG Fei LIU tao chao Ming YANG Control and Simulation Center Harbin Institute of TechnologyHarbin 150001China

For the solid rocket with depletion shutdown system,effective energy management is significant to meet terminal constraints by exhausting excess *** traditional energy management algorithms cannot satisfy the altitude constraint and path constraints are not sufficiently *** velocity adjustment capability of these algorithms is limited and the uncertainties are not *** on the on-line programming of velocity capability curve,Spline-Line Energy Management(SLEM)guidance algorithm is *** introduces lateral maneuvers to further consume the available velocity on the basis of longitudinal energy *** expressing the constraints as several algebraic equations,the closed-loop guidance problem is converted to solving a system of nonlinear equations about the curve parameters in real *** advantage is that the altitude constraint can be satisfied *** overload and control variable change rate and amplitude constraints are also considered during the flight by constructing the feasible boundary of velocity capability *** improve the robustness,it is further extended by estimating the actual *** effectiveness and advantages of SLEM are demonstrated by simulations and comparisons with other energy management *** results show that the proposed approach can satisfy multiple constraints with high precision under the condition of uncertainties.

关键词： Ascent guidance Energy management Multiple constraints Solid rockets Uncertainty Velocity capability curve

在线全文

学校读者我要写书评

暂无评论

可变桨距四旋翼飞行器姿态控制教学设备

机械制造与自动化 2024年第4期53卷 224-229页

作者：方可霍炬杨明晁涛哈尔滨工业大学控制与仿真中心黑龙江哈尔滨150080

针对传统四旋翼飞行器为固定桨距变转速的控制方式,在实际教学中存在非线性、响应慢等问题,给学生完成控制实验带来困难。为达到更好的教学效果,设计与开发一个可变桨距四旋翼飞行器的姿态控制设备,实现了定转速变桨距的控制方式,并完... 详细信息

针对传统四旋翼飞行器为固定桨距变转速的控制方式,在实际教学中存在非线性、响应慢等问题,给学生完成控制实验带来困难。为达到更好的教学效果,设计与开发一个可变桨距四旋翼飞行器的姿态控制设备,实现了定转速变桨距的控制方式,并完成了基于串级PID的控制律设计与代码实现。设备搭载280级四旋翼,使用基于STM32单片机自行开发的飞行控制器,允许学生编程及嵌入自己的控制律。设备在自动控制专业本科生选修课中进行了应用,获得了理想的教学效果。

关键词：四旋翼飞行器可变桨距姿态控制设备串级PID STM32

Integrated guidance and control design method based on finite-time state observer

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2018年第6期29卷 1251-1262页

作者： MA Ping ZHANG Denghui WANG Songyan chao tao Control and Simulation Center Harbin Institute of Technology

A composited integrated guidance and control(IGC) algorithm is presented to tackle the problem of the IGC design in the dive phase for the bank-to-turn(BTT) vehicle with the inaccuracy information of the line-of-sight(LOS) rate. For the sake of theoretical derivation, an IGC model in the pitch plane is established. The high-order finite-time state observer(FTSO), with the LOS angle as the single input, is employed to reconstruct the states of the system online. Besides, a composited IGC algorithm is presented via the fusion of back-stepping and dynamic inverse. Compared with the traditional IGC algorithm, the proposed composited IGC method can attenuate effectively the design conservation of the flight control system, while the LOS rate is mixed with noise. Extensive experiments have been performed to demonstrate that the proposed approach is globally finite-time stable and strongly robust against parameter uncertainty.

关键词： integrated guidance and control(IGC) finite-time state observer(FTSO) back-to-turn(BTT) vehicle composited control