驾驶机器人油门机械腿模糊自整定PID控制方法

为了实现驾驶机器人油门机械腿控制的平滑、准确、迅速性,提出了一种油门机械腿模糊自整定PID控制方法.介绍了驾驶机器人油门机械腿的结构.在模糊控制器中确定输入量与输出量的隶属度函数,并且制定了模糊控制规则.利用Simulink进行仿真,并且通过驾驶机器人对车辆进行自动驾驶试验,结果表明油门机械腿模糊自整定PID控制方法具有超调小,响应迅速,鲁棒性强的优点,能够平滑、准确、快速地控制油门机械腿,达到跟踪车速的目的.     

基于深度强化学习的无信号灯交叉路口车辆控制

利用深度强化学习技术实现无信号灯交叉路口车辆控制是智能交通领域的研究热点。现有研究存在无法适应自动驾驶车辆数量动态变化、训练收敛慢、训练结果只能达到局部最优等问题。文中研究在无信号灯交叉路口,自动驾驶车辆如何利用分布式深度强化方法来提升路口的通行效率。首先,提出了一种高效的奖励函数,将分布式强化学习算法应用到无信号灯交叉路口场景中,使得车辆即使无法获取整个交叉路口的状态信息,只依赖局部信息也能有效提升交叉路口的通行效率。然后,针对开放交叉路口场景中强化学习方法训练效率低的问题,使用了迁移学习的方法,将封闭的8字型场景中训练好的策略作为暖启动,在无信号灯交叉路口场景继续训练,提升了训练效率。最后,提出了一种可以适应所有自动驾驶车辆比例的策略,此策略在任意比例自动驾驶车辆的场景中均可提升交叉路口的通行效率。在仿真平台Flow上对TD3强化学习算法进行了验证,实验结果表明,改进后的算法训练收敛快,能适应自动驾驶车辆比例的动态变化,能有效提升路口的通行效率。     

人工智能在车辆自动驾驶中的应用

本文提出了一种新的基于人工智能的感知／计划／动作agent结构实现智能车辆自动驾驶的方案。首先通过描述该结构的原理说明该结构可以解决自动驾驶中存在的一些问题,接着通过建立自动驾驶知识库阐述如何具体实现自动驾驶,最后通过仿真实验验证了该方法能够为智能车辆实现自动或辅助驾驶提供一种非常有效的机制。     

基于神经网络的自动驾驶模型及其虚拟实现

文章提出了一种基于人工神经网络的自动驾驶控制模型,并利用计算机虚拟技术模拟实现车辆的运行环境及其运行行为,并对自动驾驶控制模型进行了测试。试验表明这种自动驾驶模型能有效地指挥车辆的驾驶。     

分数阶PID仿人智能控制算法在车辆自动驾驶系统中的应用

车辆自动驾驶系统处于非常复杂的环境当中,无法用精确的数学模型加以描述,利用传统控制理论来进行设计,很难达到理想的设计指标.为了解决这一问题,文章提出了一种分数阶PID仿人智能控制算法,将传统控制理论与人工智能相融合,实现了一种基于分数阶PID仿人智能控制的车辆自动驾驶系统,在运行控制级方面,通过该算法设计了自动驾驶系统的运动控制器,并在设计的直角弯道轨迹上,进行了软件仿真实验,仿真结果表明:分数阶PID仿人智能控制器优于传统的PID控制器,具有更好的的鲁棒性和控制精度.     

自动驾驶车辆道路跟驰与状态一致性控制

针对含有未知输入和外部干扰的非线性自动驾驶车辆时变跟驰队列系统,研究系统部分状态可测情况下的车辆道路跟驰和状态一致性控制问题.基于车辆跟驰和二自由度动力学模型,得到含有外部干扰和未知输入的离散化状态方程,利用前导跟驰特性,得到自动驾驶车辆跟驰队列系统;利用比例积分状态观测器解决系统部分状态不可测问题,提出一种基于观测器实现含有未知输入和外部干扰的自动驾驶车辆状态一致性控制协议;将观测器估计效果和一致性控制问题转化为误差系统的稳定性问题,由此构造Lyapunov-Krasovkii函数,利用离散系统稳定性理论推导出一个充分条件;通过求解线性矩阵不等式(linear matrix inequality, LMI)得到跟驰系统的增益矩阵和参数矩阵,利用H_∞性能指标分析系统鲁棒性.仿真结果表明:所设计观测器能够估计未知输入、外部干扰和系统状态,并且基于观测器设计能够使自动驾驶车辆道路跟驰和状态达到一致.     

一种自动驾驶车的环境感知系统

我们提出了一种自动驾驶车辆环境感知方案,此方案支持车辆在特定路况的自动驾驶功能,方案中采用毫米波雷达实现障碍物距离、速度及方位探测;采用摄像头实现车道线及车辆识别;应用激光雷达实现道路边沿及其他障碍物目标探测,通过超声波雷达感知车辆近距离目标,通过GPS/IMU实现车辆的精准定位,此方案通过实车验证,满足实际自动驾驶环境感知应用需求。     

智能汽车自动驾驶的控制方法研究

为了解决智能汽车在无人驾驶的情况下自动跟随前方车辆行驶的问题,在预瞄跟随理论基础上提出一种自动驾驶的控制方法;该方法适用于控制一列智能车队,智能汽车通过接收前车发送的行驶状态来计算出前方路况,通过模糊自适应PID控制器来控制车辆驾驶;首先基于预瞄跟随理论设计一个汽车自动跟随模型,并指明需要跟随的物理量;然后,设计了一个模糊PID控制器来实现对给定物理量的跟踪;最后在dSPACE和飞思卡尔模型小车所搭建的实验环境下去验证控制方法的可行性;仿真实验结果表明该方法能够保证智能汽车具有良好的路况计算和车辆跟踪的精度,且具有较好的鲁棒性。     

城市交叉口车辆速度与交通信号协同优化控制

为了降低城市交通中的行车延误与燃油消耗,针对人类驾驶车辆与自动驾驶车辆混合交通环境,提出一种基于交通信息物理系统(TCPS)的车辆速度与交通信号协同优化控制方法.首先,综合考虑路口交通信号、人类驾驶车辆、自动驾驶车辆三者之间的相互影响,设计一种适用于自动驾驶车辆与人类驾驶车辆混合组队特性的过路口速度规划模型;其次,针对车辆速度规划单一应用时的局限性,即无法减少车辆路口通行延误且易出现无解情况,提出一种双目标协同优化模型,能够综合考虑车辆速度规划与路口交通信号控制,同时降低车辆燃油消耗与路口平均延误.由于双目标优化问题求解的复杂性,设计一种遗传算法-粒子群算法混合求解策略.基于SUMO的仿真实验验证了所提出方法的有效性.     

结合目标检测与双目视觉的三维车辆姿态检测

随着城市规模的发展,车辆的需求在与日俱增,同时对自动驾驶技术的需求也在不断提高.为了增强自动驾驶系统对路面车辆的信息掌握能力,提出一种车辆姿态检测方法.首先利用基于深度学习的目标检测方法获取车辆在二维图片上的信息,结合深度相机利用双目视觉获取车辆的关键三维空间信息;然后综合二维与三维信息建立三维空间坐标,经过计算后实现车辆的三维边框绘制,绘制的三维边框能辅助区分出车辆在空间上的方位.文中方法为端对端方法,不需要其他额外的输入信息,能够实时展示在相机中.实验结果表明,该方法针对常见的路面停车场景有较好的识别效果,对自动驾驶系统有较好的辅助作用;对比目前流行的三维边框计算方法也展示了其准确性.     

On some idea of a neuro-fuzzy controller

The paper presents a neuro-fuzzy technique for the design of controllers. This technique can effectively deal with two main types of knowledge which usually describe the control strategy for complex systems, that is, a qualitative, linguistic, fuzzy knowledge usually expressed in the form of linguistic rules, and a quantitative, nonfuzzy information in the form of measurements and other numerical data. The proposed technique combines artificial neural networks with fuzzy logic yielding a structure that can be called a neuro-fuzzy controller or, broadly speaking, a fuzzy neural network. The paper presents a general structure of a neuro-fuzzy controller and two essential phases of its design, that is, a learning phase and a functioning phase. In turn, a numerical example which illustrates how the proposed controller works is presented. Finally, the paper describes an application of a neuro-fuzzy control to inverter drive systems for electric vehicles. The results of simulation and experimental investigations carried out on the laboratory model of an inverter drive system are also provided.     

Modeling and control of non-linear systems using soft computing techniques

This work is an attempt to illustrate the utility and effectiveness of soft computing approaches in handling the modeling and control of complex systems. Soft computing research is concerned with the integration of artificial intelligent tools (neural networks, fuzzy technology, evolutionary algorithms, …) in a complementary hybrid framework for solving real world problems. There are several approaches to integrate neural networks and fuzzy logic to form a neuro-fuzzy system. The present work will concentrate on the pioneering neuro-fuzzy system, Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS is first used to model non-linear knee-joint dynamics from recorded clinical data. The established model is then used to predict the behavior of the underlying system and for the design and evaluation of various intelligent control strategies.     

Neuro-fuzzy position control of demining tele-operation system based on RNN modeling

The paper considers the neuro-fuzzy position control of multi-finger robot hand in tele-operation system—an active master–slave hand system (MSHS) for demining. Recently, fuzzy control systems utilizing artificial intelligent techniques are also being actively investigated in robotic area. Neural network with their powerful learning capability are being sought as the basis for many adaptive control systems where on-line adaptation can be implemented. Fuzzy logic on the other hand has been proved to be rather popular in many control system applications providing a rule-base like structure. In this paper, the design and optimization process of fuzzy position controller is supported by learning techniques derived from neural network where a radial basis function (RBF) neural network is implemented to learn fuzzy rules and membership functions with predictor of recurrent neural network (RNN) model. The results of experiment show that based on the predictive capability of RNN model neuro-fuzzy controller with good adaptation and robustness capability can be designed.     

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.     

Neuro-fuzzy knowledge processing in intelligent learning environments for improved student diagnosis

In this paper, a neural network implementation for a fuzzy logic-based model of the diagnostic process is proposed as a means to achieve accurate student diagnosis and updates of the student model in Intelligent Learning Environments. The neuro-fuzzy synergy allows the diagnostic model to some extent “imitate” teachers in diagnosing students' characteristics, and equips the intelligent learning environment with reasoning capabilities that can be further used to drive pedagogical decisions depending on the student learning style. The neuro-fuzzy implementation helps to encode both structured and non-structured teachers' knowledge: when teachers' reasoning is available and well defined, it can be encoded in the form of fuzzy rules; when teachers' reasoning is not well defined but is available through practical examples illustrating their experience, then the networks can be trained to represent this experience. The proposed approach has been tested in diagnosing aspects of student's learning style in a discovery-learning environment that aims to help students to construct the concepts of vectors in physics and mathematics. The diagnosis outcomes of the model have been compared against the recommendations of a group of five experienced teachers, and the results produced by two alternative soft computing methods. The results of our pilot study show that the neuro-fuzzy model successfully manages the inherent uncertainty of the diagnostic process; especially for marginal cases, i.e. where it is very difficult, even for human tutors, to diagnose and accurately evaluate students by directly synthesizing subjective and, some times, conflicting judgments.     

自适应神经模糊控制器及其在炉温控制系统中的应用

将自适应模糊控制技术与神经网络技术相结合,提出了一种自适应神经模糊控制器的实现方法,并用一种改进的快速ＢＰ算法来训练网络。该方法和算法用于炉温控制系统,获得了满意的控制效果,验证了方法和算法的有效性。     

基于RBF网络的参数自学习模糊控制的研究

模糊控制以其自适应性、鲁棒性和易于实现等优点得到广泛应用。然而模糊控制规则的获得通常由专家经验给出,这就存在诸如控制规则不够客观、专家经验难以获得等问题。在模糊控制系统中,模糊规则库的构建是至关重要的,因此研究模糊规则的自动生成有着重要的理论和应用价值。本文首先以模糊控制理论和RBF神经网络理论为基础,提出了一种能够有效表达模糊系统可解释性的RBF网络结构;然后详细讨论在此网络结构下提取模糊规则的学习算法;最后依据上述方法进行仿真实验,实验结果表明,这种根据测量数据自动提取模糊规则的方法是有效的。     

Survey of Intelligent Control Techniques for Humanoid Robots

This paper focusses on the application of intelligent control techniques (neural networks, fuzzy logic and genetic algorithms) and their hybrid forms (neuro-fuzzy networks, neuro-genetic and fuzzy-genetic algorithms) in the area of humanoid robotic systems. It represents an attempt to cover the basic principles and concepts of intelligent control in humanoid robotics, with an outline of a number of recent algorithms used in advanced control of humanoid robots. Overall, this survey covers a broad selection of examples that will serve to demonstrate the advantages and disadvantages of the application of intelligent control techniques.     

A neuro-fuzzy hybrid scheme for design and simulation of human machine systems

In this article, a new neuro-fuzzy hybrid approach to human workplace design and simulation is proposed. Problems related to human workplace design such as human-machine modeling, measurement and analysis, workplace layout design and planning, workplace evaluation and simulation are discussed in detail. The complex human-machine interactions in workplace design are described with human and workstation parameters within a comprehensive human-machine system model. Based on this model, procedures and algorithms for workplace design, ergonomic evaluation, and optimization are presented in an integrated framework. With a combination of individual neural and fuzzy techniques, the neuro-fuzzy hybrid scheme implements fuzzy if-then rules block for workplace design and evaluation by trainable neural network architectures. For training and test purposes, simulated assembly tasks are carried out on a self-built multiadjustable laboratory workstation with a flexible PEAK Motus motion measurement and analysis system. The trained fuzzy neural networks are capable of predicting the operator's posture and joint angles of motion associated with a range of workstation configurations. They can also be used for design/layout and adjustment of manual assembly workstations. The developed system provides a unified, intelligent computational framework for human-machine system design and simulation. In the end, case studies for workplace design and simulation are presented to validate and illustrate the developed neuro-fuzzy design scheme and system.