微小型潜器空间运动建模与仿真(英文)

对自主式潜器空间运动进行精确建模和仿真对研究其操纵和控制特性有重要意义,本文以开发的"MAUV-Ⅱ"微小型潜器为对象,基于动量定理和动量矩定理建立了潜器空间运动的非线性数学模型,将潜器受力分解为各个模块并表达为矩阵形式.在运动非线性数学模型的基础上,结合虚拟现实技术建立了运动仿真系统,针对所研究潜器的特点,采用S面控制方法对此"MAUV-Ⅱ"水下运动的艏向控制和深度控制进行了仿真研究,同时进行了基于目标规划的长距离航行仿真试验.仿真结果反映了潜器具有较好的空间操纵性能,也验证了控制软件的可行性和可靠性.     

S~2 BHCA-Multiple AUVs cooperation oriented control architecture

Oceanographic survey, or other similar applications should be the applications of multiple AUVs. In this paper, the skill & simulation based hybrid control architecture (S2BHCA) as the controller's design reference was proposed. It is a multi-robot cooperation oriented intelligent control architecture based on hybrid ideas. The S BHCA attempts to incorporate the virtues of the reactive controller and of the deliberative controller by introducing the concept of the "skill". The additional online task simulation ability for cooperation is supported, too. As an application, a multiple AUV control system was developed with three "skills" for the MCM mission including two different cooperative tasks. The simulation and the sea trials show that simple task expression, fast reaction and better cooperation support can be achieved by realizing the AUV controller based on the S2BHCA.     

AUV自主收放装置结构及控制系统设计

AUV技术对于提高海洋资源环境的勘测和开采效率具有重要意义。在AUV收放过程中,传统的回收方式是在母船上起吊回收,人为参与完成挂钩任务,这种方式受风浪的影响较大。为了提高AUV的使用保障能力,需要针对AUV的自主收放技术展开研究。基于AUV良好的实时性、连续性及可移动性的特点,本文设计一套AUV自主收放装置,可用于AUV的自动布放及回收。该装置由固定架、控制台、吊机装置、绞车、定滑轮、钢丝绳、收放架等组成。设计各部分的机械结构,并通过系统校核验证结构设计的合理性。同时,设计AUV收放存储装置控制系统,实现对机械液压执行器的精密控制、传感器的数据采集、系统状态参数显示、试验参数调整、工作状态监控和安全报警等功能,能够对控制系统的控制流程进行辅助判断和安全保障。解决了传统AUV收放技术的难题,提高了AUV收放的智能化水平。     

S^2 BHCA Multiple AUVs cooperation oriented control architecture

Oceanographic survey, or other similar applications should be the applications of multiple AUVs. In this paper, the skill ＆ simulation based hybrid control architecture （S^2BHCA） as the controller＇s design reference was proposed. It is a multi-robot cooperation oriented intelligent control architecture based on hybrid ideas. The S^2BHCA attempts to incorporate the virtues of the reactive controller and of the deliberative controller by introducing the concept of the ＂skill＂. The additional online task simulation ability for cooperation is supported, too. As an application, a multiple AUV control system was developed with three ＂skills＂ for the MCM mission including two different cooperative tasks. The simulation and the sea trials show that simple task expression, fast reaction and better cooperation support can be achieved by realizing the AUV controller based on the S^2BHCA.     

Applying a semantic information Petri Net modeling method to AUV systems design

This paper informally introduces colored object-oriented Petri Nets(COOPN) with the application of the AUV system. According to the characteristic of the AUV system's running environment,the object-oriented method is used in this paper not only to dispart system modules but also construct the refined running model of AUV system,then the colored Petri Net method is used to establish hierarchically detailed model in order to get the performance analyzing information of the system. After analyzing the model implementation,the errors of architecture designing and function realization can be found. If the errors can be modified on time,the experiment time in the pool can be reduced and the cost can be saved.     

水下智能潜器分布式控制系统设计与实现

分布式控制系统是水下管能潜器的重要部分．本文采用分层控制结构，即执行级、协调级和组织级，实现了潜器的控制系统。文中首先介绍了控制系统的组成，然后分别介绍了执行级采用神经网络实现自适应控制的方法，协调级中实现全局和局部路径规划的方法，以及组织级中基于行为分解的任务规划方法。文中给出了系统的仿真和实验结果。     

基于强化学习的自主式水下潜器障碍规避技术（英文）

Obstacle avoidance becomes a very challenging task for an autonomous underwater vehicle(AUV) in an unknown underwater environment during exploration process. Successful control in such case may be achieved using the model-based classical control techniques like PID and MPC but it required an accurate mathematical model of AUV and may fail due to parametric uncertainties, disturbance, or plant model mismatch. On the other hand, model-free reinforcement learning(RL) algorithm can be designed using actual behavior of AUV plant in an unknown environment and the learned control may not get affected by model uncertainties like a classical control approach. Unlike model-based control model-free RL based controller does not require to manually tune controller with the changing environment. A standard RL based one-step Q-learning based control can be utilized for obstacle avoidance but it has tendency to explore all possible actions at given state which may increase number of collision.Hence a modified Q-learning based control approach is proposed to deal with these problems in unknown environment.Furthermore, function approximation is utilized using neural network(NN) to overcome the continuous states and large statespace problems which arise in RL-based controller design. The proposed modified Q-learning algorithm is validated using MATLAB simulations by comparing it with standard Q-learning algorithm for single obstacle avoidance. Also, the same algorithm is utilized to deal with multiple obstacle avoidance problems.     

某型AUV运载器的定位方法与误差分析

传统AUV依靠水下惯性导航设备自主定位的方法无法实时进行水下信息感知和系统控制。水声定位是AUV定位导航技术的一个研究领域，可用于水下运动目标定位与导航、水下静止目标勘测等。本文分析阐述三种经典AUV定位方法，进一步研究AUV快速定位解算原理，论证影响AUV运载器在深海工作时产生的定位误差来源并进行仿真试验分析，最终将研究成果应用在目前现有某型AUV运载器上，实现自身水下定位、导航与远程遥控。     

水下潜器改进S面控制及控制系统仿真(英文)

S surface controllers have been proven to provide effective motion control for an autonomous underwater vehicle (AUV). However, it is difficult to adjust their control parameters manually. Choosing the optimum parameters for the controller of a particular AUV is a significant challenge. To automate the process, a modified particle swarm optimization (MPSO) algorithm was proposed. It was based on immune theory, and used a nonlinear regression strategy for inertia weight to optimize AUV control parameters. A semi-physical simulation system for the AUV was developed as a platform to verify the proposed control method, and its structure was considered. The simulation results indicated that the semi-physical simulation platform was helpful, the optimization algorithm has good local and global searching abilities, and the method can be reliably used for an AUV.     

An integrated GPS/DR navigation system for AUV

GPS/Dead-reckoning navigation system for autonomous underwater vehicle （AUV） is introduced, which includes navigation overall architecture, hardware and software structure. Dead-reckoning theory is presented in details. And the strong tracking Kalman filter and Singer model are applied to handle the imprecise navigation mode, which can improve the navigation system＇s precision and reliability. Finally, the sea experiments which include autonomous search mission in an unknown area and long distance motion are conducted to demonstrate the reliability and feasibility of the navigation system.     

矢量推进方式下的自主式水下航行器纵向运动操纵性分析

提出一种针对无人自主式水下航行器的新型操纵方式--矢量推进方式;建立矢量推进方式下无人自主式水下航行器纵向运动方程.对矢量推进方式和普通推进方式下的水下航行器的操纵性进行对比性的操纵性仿真计算,计算结果表明,矢量推进方式可以满足水下航行器的操纵性要求.     

基于Matlab的AUV近水面运动模型的建立与仿真

该文运用矢量方法对自主式水下航行器(AUV)近水面的六自由度运动方程进行了推导，得到了一个适于在Matlab环境中仿真的高度矢量化的空间运动模型，并用在Matlab的仿真工具箱Simulink中建立的AUV近水面的六自由度运动仿真模块对AUV的近水面运动进行了仿真，在此基础上分析了波浪力对AUV的影响。该模型的建立和仿真为AUV近水面的稳定性分析和控制系统的设计提供了便利的工具。     

基于卷积神经网络的AUV水下识别算法设计与实现

自主式水下机器人(AUV)是应用于复杂海洋环境中的高智能化无人装备,其需要具备良好的环境感知能力进行自主导航,包括水下目标识别能力。随着人工智能的高速发展,卷积神经网络作为图像处理领域的深度学习架构,在图像特征提取和图像识别上有着强大的性能和卓越的优势。本文利用卷积神经网络,实现了自主式水下机器人水下目标的自主识别。同时,通过采用三段式全连接方式和增加卷积层深度的方式对卷积神经网络进行进一步改进,提高了卷积神经网络的训练速度、准确率和泛化能力。     

Power efficient formation configuration for centralized leader–follower AUVs control

Autonomous underwater vehicles (AUVs) have rapidly developed in the last few decades due to their autonomous properties in the investigation of an underwater environment. The goal of this paper is to develop a power efficient formation control for the cooperative motion of AUVs with a support vessel as a leader. In this paper, a kinematic algorithm for the joint motion of an AUV with a support vessel was developed and that algorithm was expanded for the formation of AUVs. The AUV yaw, surge and sway control loops were designed for that purpose. The complexing navigation system structure for the AUV was also developed. Simulation results demonstrated efficiency of the proposed kinematic algorithm for the joint motion of AUVs. Also, influence of lateral ocean current was considered. After development of the centralized leader?Cfollower formation control for the group of AUVs with a support vessel as a leader, we optimized a formation configuration in terms of power efficiency. Drag forces caused by AUV motion in the water can significantly influence power consumption. We investigated the relationship between the AUV's formation configuration, underwater coverage efficiency, communication quality and power consumption. As a result of research, we proposed a power efficient formation configuration for typical underwater operations. As a result, the effect of the AUV formation configuration on the power consumption was investigated and a trade-off solution for the optimal AUV positions in formation with minimal energy consumption, high coverage efficiency and small communication power consumption was derived.     

机载布放式AUV入水冲击仿真研究

机载布放式AUV是利用载机运送至特定海域上空,在一定条件下通过空投方式进入水下,完成预定工作的自主水下航行器。AUV入水时会受到巨大的载荷冲击,严重时会导致机体折断、元器件失灵,甚至引起弹道失控。为此,文章采用计算流体力学(Computational Fluid Dynamics,CFD)方法对机载布放式AUV的入水冲击问题进行了数值仿真研究。对不同入水速度、不同入水角度下AUV受力过程进行了计算,得出了不同入水条件下的速度响应曲线和压力响应曲线,可为机载布放式AUV的机体结构设计和投放条件研究提供参考。     

开发水下机器人控制器的MDA/MBSE方法的实用专业化研究（英文）

The model-driven architecture(MDA)/model-based systems engineering(MBSE) approach, in combination with the real-time Unified Modeling Language(UML)/Systems Modeling Language(SysML), unscented Kalman filter(UKF) algorithm, and hybrid automata, are specialized to conveniently analyze, design, and implement controllers of autonomous underwater vehicles(AUVs). The dynamics and control structure of AUVs are adapted and integrated with the specialized features of the MDA/MBSE approach as follows. The computation-independent model is defined by the specification of a use case model together with the UKF algorithm and hybrid automata and is used in intensive requirement analysis. The platform-independent model(PIM) is then built by specializing the real-time UML/SysML's features, such as the main control capsules and their dynamic evolutions, which reflect the structures and behaviors of controllers. The detailed PIM is subsequently converted into the platform-specific model by using open-source platforms to quickly implement and deploy AUV controllers. The study ends with a trial trip and deployment results for a planar trajectory-tracking controller of a miniature AUV with a torpedo shape.     

近壁面水动力干扰下的AUV运动控制研究

按自治式水下机器人(AUV)需要接近水下工作站并实现坐落的要求,依据平壁面对AUV水动力干扰的力学机理,建立了AUV在平壁面附近运动时的数学模型,并设计了五个自由度运动PID控制器.在海流影响下,通过系统仿真,实现了AUV的五自由度运动控制和准确坐落,仿真结果验证了控制策略的可行性.     

AUV fuzzy neural BDI

The typical BDI （belief desire intention） model of agent is not efficiently computable and the strict logic expression is not easily applicable to the AUV （autonomous underwater vehicle） domain with uncertainties. In this paper, an AUV fuzzy neural BDI model is proposed. The model is a fuzzy neural network composed of five layers ： input （ beliefs and desires）, fuzzification, commitment, fuzzy intention, and defuzzification layer. In the model, the fuzzy commitment rules and neural network are combined to form intentions from beliefs and desires. The model is demonstrated by solving PEG （pursuit-evasion game） , and the simulation result is satisfactory.     

AUV控制系统试验平台

随着AUV(自主式潜器)技术的不断发展,对其自主性能的要求越来越高.AUV控制系统试验平台可以实现各种自主控制、动态控制算法及软件的系统集成.文章以能够自主完成地形勘察使命的AUV为研究对象,设计了AUV控制系统试验平台,对AUV控制系统硬件系统和基于行为仲裁的分层递阶软件系统做了较全面的介绍,利用QNX操作系统的多线程和消息传递技术实现了任务协调算法.在半实物试验平台上进行的地形勘察使命仿真结果验证了控制系统试验平台硬件结构合理,算法及软件集成可实现.     

3D Track-keeping Method for Autonomous Underwater Vehicle

In this paper, 3D track-keeping control method for autonomous underwater vehicle (AUV) with and without the influence of ocean current is investigated. Because the system to be controlled is highly nonlinear and strong coupled, an approach is used to divide it into two subsystems. One is to control the heading and the track error on the horizontal plane. The other is to control the pitch and the track error on the vertical plane. The results of computer simulation show that the autopilot works properly, it can capture the current waypoint and turns to track the next path automatically.