水下狭窄环境中ROV的自主返回控制

为满足缆控水下机器人（remotely operated vehicle,ROV）在水下狭窄环境中作业完毕后的顺利回收需求,研究仿真ROV的路径跟踪以及动力定位系统。基于非对称ROV构建数学模型,利用李雅普诺夫函数,采用反向递推和反馈线性化,设计了基于反步法的自适应控制器。该控制器通过反馈线性化,将已知非线性参数转化成线性参数,不确定的非线性参数应用自适应控制律进行放宽。通过仿真对该控制器应用于ROV的可行性进行验证表明:基于反步自适应控制以及视线导引的算法,ROV在水下狭窄环境中路径跟踪效果良好,动力定位稳定,鲁棒性良好,能够很好地解决ROV模型的不确定性与非线性问题。该控制器为ROV在水下狭窄环境中的回收作业提供了很好的解决方案。     

基于多深度对抗网络的ROV水下目标检测

有缆水下机器人ROV是水下工程作业的重要工具，但由于不同水质特性及水中散射折射的影响，ROV水下图像普遍存在失真模糊、分辨率低等问题。为此构建深度分离可变形卷积代替原始卷积，采用高效表达稀疏性的特征提取结构实现对ROV水下目标的特征提取；再运用多深度机制的改进GAN网络生成器和类似马尔可夫架构的判别器建立数据集，增强水下图像；最后构建多项损失函数，提升网络的泛化性能并实现对ROV目标的快速检测。水下实验结果表明，该水下图像增强方法提高了ROV目标检测精度，符合预期要求。     

深海ROV伺服控制方法研究及其仿真

针对深海水下机器人(ROV) 处于深海环境中受到外界干扰的伺服控制这一问题, 首先建立推进器推力分配结构, 推导得出作用在ROV本体上相应的实际推力; 然后依据PID 原理和模糊规则, 构造模糊PID 控制器, 实现ROV消除外界干扰恢复静止稳定状态的伺服控制; 最后通过仿真实验表明了所构造的模糊PID 控制具有较好的动态性能和稳态性能, 显示出良好的伺服控制性能.

     

作业型遥控水下运载器的多变量backstepping鲁棒控制

针对作业型遥控水下运载器（ROV）存在复杂外干扰、参数不确定性以及强非线性耦合的特性,提出了作业型ROV的多变量backstepping控制方法．使用Lyapunov稳定性分析方法,证明了当存在系统参数不确定性和未知常值外干扰的情况时,系统的局部渐近稳定性．以及跟踪误差的局部渐近收敛性．针对作业型ROV在动力定位时的特点,得到了系统动力定位时的四自由度简化模型．仿真结果表明,所提出的多变量backstepping鲁棒控制器具有比常规PID控制器更好的控制品质和鲁棒性能．     

基于Arduino的小型ROV的设计与实现

该文设计了一款可实现上浮下潜、转弯等功能小型的ROV.该系统是基于Arduino Mega 2560为核心控制器,控制六个推进器实现ROV的基本运动,并搭载水下LED和水下摄像头作为视频传输模块,以数字压力传感器作为水深探测,以及搭载温度传感器进行温度的测试,所有信号通过有线脐带缆与上位机通信.该小型ROV可实现基本运...     

自主轮式机器人THMR－V的混合模糊逻辑控制

轮式机器人的控制问题是控制研究的关键问题之一，对高速自主导航的轮式机器人，控制器的实时性、精确性和鲁棒性要求很高．在本文中，根据PID控制和模糊逻辑控制的各自优点，将传统的PID控制与模糊逻辑控制结合起来，提出了一种混合模糊逻辑控制算法. 经实验检验，该算法具有很高的实时性、控制精度和鲁棒性，能够满足机器人高速自主导航的需要．     

一种基于人工免疫原理的最优模糊神经网络控制器

提出了一种基于人工免疫原理的最优RBF模糊神经网络控制器设计方案．首先给出了控制器结构，其次将免疫进化算法用于控制器参数的优化，设计了一种满足二次型性能指标的最优RBF模糊神经网络控制器．将该控制器用于控制实际倒立摆系统，并采用状态变量合成方法以大大减少模糊规则的数目，实验结果验证了该控制器的有效性．     

模糊自适应卡尔曼滤波技术研究

本文提出了一种基于模糊自适应卡尔曼滤波技术的组合导航的新方法．这一方法主 要应用于自主式机动飞行器．用模糊逻辑自适应控制器对卡尔曼滤波器的噪声方差进行“在 线”修正,将卡尔曼滤波器调整到最优状态,从而提高组合导航系统的精度．通过对GPS/IN S组合导航系统的仿真,验证了模糊自适应卡尔曼滤波器比常规卡尔曼滤波器具有更高的精 度．该方法的研究对飞行器的导航与制导具有重要意义．     

基于模糊逻辑的自适应卡尔曼滤波在GPS/INS组合导航中的应用

提出了一种利用模糊逻辑控制器来在线调节卡尔曼滤波器的自适应数据融合方法,并着重研究了其在GPS/INS组合导航中的应用．根据位置误差系数和卡尔曼滤波器的新息的统计信息，采用模糊逻辑控制器对卡尔曼滤波器进行连续修正，将卡尔曼滤波器调整到最优状态，从而提高组合导航系统的精度．仿真结果证明这种方法比标准卡尔曼滤波具有更高的精度．     

基于超短基线的缆控水下机器人动力定位

动力定位 (DynamicPositioning(DP) )技术是水下机器人的关键技术之一。因此针对当前动力定位主要在缆控水下机器人 (ROV)中应用的情况 ,给出了ROV动力定位技术的实施方法。通过声学定位技术确定ROV的坐标 ,计算出与期望位姿的差 ,将其作为神经网络控制器的输入量来控制ROV ,从而进行动力定位。同时还重点研究了ROV动力定位中的主要研究内容即水声定位技术和定位控制技术的构建。     

基于模糊神经网络水下机器人直接自适应控制

提出了基于广义动态模糊神经网络的水下机器人直接自适应控制方法, 该控制方法既不需要预先知道模糊神经结构, 也不需要预先的训练阶段, 完全通过在线自适应学习算法构建水下机器人的逆动力学模型. 首先, 本文提出了基于这种网络结构的水下机器人直接自适应控制器, 然后, 利用 Lyapunov 稳定理论, 证明了基于该控制器的水下机器人控制系统闭环稳定性, 最后, 采用某水下机器人模型仿真验证了该控制方法的有效性.     

Combined depth and heading control and experiment of ROV under the influence of residual buoyancy,current disturbance,and control dead zone

To improve the underwater control effect of a Remotely Operated Vehicle (ROV) with residual buoyancy, current disturbance, and control dead zone, the depth and heading combined control of ROV is studied to improve the control accuracy of the control system. First, the heading control with fixed depth is divided into heading control and depth control. The tanh-sigmoid-surface control laws for designed degrees of freedom are designed by using tanh function. To suppress the influence of residual buoyancy and control law dead zone in depth control, and to offset the influence of control law dead zone of ROV thruster control, a reserved control quantity is introduced to map the depth deviation and control dead zone with residual buoyancy into a control deviation quantity. An adaptive amplification factor method is proposed for the amplification factors of depth control, speed control, and heading control. The proportional coefficient is adopted to make that the balance among rise time, convergence speed, and overshoot can be achieved by adjusting the proportional coefficient. Then the corresponding tanh-sigmoid-surface controller module is designed in MOOS-IvP environment to track the desired heading and depth. The proposed controller refines fuzzy rules and reduces the complexity of parameter adjustment. Compared with the classical proportional, integral, and derivative control method, the experiment results show that the proposed method can resist the influence of residual buoyancy, current disturbance, and control dead zone and has a better control effect with less control error in depth and heading determination.     

基于极大后验估计和模糊控制的水下无源定位技术

针对高海况条件下因海流扰动的影响导致观测噪声方差未知时变的特点, 基于模糊控制技术提出一种基于FCMAP-UKF 滤波技术的水下无源组合导航系统状态估计方法. 该方法在滤波迭代过程中引入模糊自适应因子, 对未知观测噪声方差阵进行动态调节, 提高了系统的自适应能力和鲁棒性. 滤波结果表明, 该系统在达到传统方法精度的同时, 能够克服自主导航过程中不确定的噪声和随机干扰的影响而进行有效的定位导航.     

Development of a stable localized visual inspection system for underwater structures

To avert potential crisis from Japan’s aging infrastructure and declining birth rate, the Japanese Government is planning to introduce robotic technology for the inspection of social infrastructure (such as pipes, dams, and bridges). Recording underwater positions is a difficult task for human divers who undertake conventional dam inspections. This study presents the Anchor Diver 5.2 system for efficient and effectual dam inspection. Anchor Diver 5.2 is based on an extended-tether-maneuvered remotely operated vehicle (ROV) equipped with cameras. The ROV is lowered into water by a hoist system from a boat and implements a visual survey of the concrete underwater structure. To improve the visibility of the ROV in murky and cloudy water, a novel concept named Water Loupe is proposed. In addition, a simple boat-fixing method is proposed to provide a stable base on the water surface, and the underwater position of the ROV, which cannot be accessed by global positioning systems, is recorded using a feasible localization method. Finally, the developed system was evaluated in field experiments conducted in the Amagase Dam, Japan, and its merits and problems are discussed.     

Virtual-environment-based navigation and control of underwatervehicles

A remotely operated underwater vehicle (ROV) the Phantom S2, is being converted to an autonomous underwater vehicle (AUV) for shallow-water and coastal environments. After an overview of issues associated with designing and implementing an automated monitoring system, we provide justification and motivation for our research and define ecosystems and ecosystem management. We then discusses how the ROV to AUV conversion is being done by using mostly commercially available of-the-shelf hardware and software technologies. We then present the fundamentals of the three-layer fuzzy-logic navigation scheme for the underwater vehicle, as well as details pertaining to the virtual-reality-based environment modeling approach     

遥控水下机器人（ROV）分布式控制系统

本文阐述了我国自行研制的６００ｍ水深作业型缆控水下机器人（ＲＯＶ）Ｂｉｔｂｕｓ（位总线）分布式控制系统的硬件结构和软件体系。     

Depth control of ROV in nuclear power plant based on fuzzy PID and dynamics compensation

Depth control is very important for underwater robot in nuclear power plant, especially when the robot needs to perform special tasks at specific depths under the water. Aiming to realize the depth control for the nuclear environment, the paper proposes a depth control strategy combining fuzzy PID with dynamics compensation based on the fact that the water in the reactor pool is very calm. Firstly, we conducted the hydrodynamics analysis of the developed remotly operated vehilcle (ROV) using ANSYS FLUENT software to get the relationship between moving velocity and water resistance in heave direction. Then, field experiments were conducted to compensate the dynamics errors using least square method according to the real-time depth values collected by depth gauge. After that, the fuzzy PID controller was designed to tune the PID parameters using fuzzy rules based on the compensated relationship between outputs of propellers and depth values. Experiments were conducted with results showing that accuracy of the depth control strategy combing fuzzy PID with dynamics compensation can reach within 3 cm, which can fully meet the requirements of practical application in the reactor pool. The highlight of the paper is that we combine the fuzzy PID algorithm with compensated dynamics equation, which is very suitable to realize the depth control for ROV in nuclear power plant.

     

水下机器人递阶－分散式控制系统研究

本文给出了水下机器人（ＲＯＶ）的一种递阶－分散式计算机控制系统。通过计算机硬件和软件的并行处理技术，解决了ＲＯＶ控制的实现问题。实际应用表明，该系统具有结构简单，运算速度快等特点．     

Fuzzy-Logic Based Navigation of Underwater Vehicles

A fuzzy logic based general purpose modular control architecture is presented for underwater vehicle autonomous navigation, control and collision avoidance. Three levels of fuzzy controllers comprising the sensor fusion module, the collision avoidance module and the motion control module are derived and implemented. No assumption is made on the specific underwater vehicle type, on the amount of a priori knowledge of the 3-D undersea environment or on static and dynamic obstacle size and velocity. The derived controllers account for vehicle position accuracy and vertical stability in the presence of ocean currents and constraints imposed by the roll motion. The main advantage of the proposed navigation control architecture is its simplicity, modularity, expandability and applicability to any type of autonomous or semi-autonomous underwater vehicles. Extensive simulation studies are performed on the NPS Phoenix vehicle whose dynamics have been modified to account for roll stability.