柔性作业车间多自动导引小车和机器的集成调度

针对含有AGV的柔性作业车间调度问题,提出基于时间窗和Dijkstra算法的混合遗传算法。建立了AGV/机器的双资源调度数学模型;采用3种解决策略处理多AGV路径规划冲突和碰撞;为了将机器和AGV调度集成考虑,设计了三链式编码结构及AGV编码链的交叉、变异算子,同时在遗传算法的解码操作中将Dijkstra算法与时间窗原理相结合,以精确地为任务小车规划出一条无碰撞无冲突的最短路径;算例对比验证了该算法的可行性、有效性和优越性。     

自动化分拣仓库中多AGV调度与路径规划算法

自动化分拣仓库由多自动导引小车(AGV)同时作业,对大量包裹进行快速分拣。如何为AGV确定搬运包裹序列并规划无冲突的路径,是分拣作业的关键所在。为提高分拣效率,以最小化最大搬运完成时间为目标,定义了冲突AGV的优先级,提出一种生成无路径冲突的路径规划算法;进而,综合考虑AGV调度和路径规划,提出一种改进差分进化算法,算法采用反学习方法生成初始种群,运用自适应的变异和交叉概率进行进化操作,设计动态差分进化策略来提高收敛速度,并设计交换邻域和基于关键AGV的插入邻域进行局部搜索。通过数据实验验证了算法的有效性,并对关键问题参数进行了分析。     

考虑任务行程时间的多载量自动导引车系统防死锁任务调度

针对多载量自动导引车（AGV）系统的任务调度和缓冲区死锁问题,提出了考虑任务行程时间的防死锁任务调度方案。以最小化延迟率和交通负荷不均衡度为目标,建立了任务调度模型;分析了任务调度中的实际约束,并在任务行程时间约束下构建了预测模型;针对任务调度模型,提出了一种基于人工免疫-灰狼优化（AI-GWO）算法的多目标防死锁任务调度方法,利用死锁避免规则禁止即将引发工位缓冲区死锁的任务运行,并融合AI-GWO算法对任务执行顺序进行多目标优化;最后,根据AGV负载均衡度进行AGV任务分配。仿真结果表明,上述任务行程时间预测模型具有较高的准确率,任务调度模型及防死锁调度方法具有较好的优化性能和计算效率,从而显著提高了物流系统的任务准时率和路径网络的交通负荷均衡度。     

自动导向小车与加工设备多目标集成调度的聚类遗传算法

针对AGV与加工设备的集成调度问题,在考虑AGV无冲突路径规划的情况下,建立了以最大完工时间、AGV运行时间及机器总负荷为优化目标的调度优化模型,提出一种基于时间窗和Dijk-stra算法的多目标自适应聚类遗传算法.根据算法在不同迭代时期的特点,提出一种包含自适应个体交叉概率的交叉重组策略;设计了自适应种群变异概率;引...     

Object oriented modelling and development of a dispatching algorithm for automated guided vehicles

The main problem for an automated guided vehicle (AGV) dispatching system is to assign vehicles to transport demands which optimise some predetermined objectives of a manufacturing shop. This paper presents a framework for an AGV dispatching system based on an object oriented approach using the unified modelling language (UML), and the development of a dispatching algorithm to facilitate a human controller to dispatch efficiently a fleet of AGVs in response to calls from any shop floor (or machine) operator. The main reason for this work is to model an AGV dispatching system as well as to develop a dispatching algorithm which can record details of the AGV position and movement and ensure their allocation of new orders. The provision of both immediate and pre-booked orders for an AGV is also incorporated in the proposed AGVs dispatching system. The underlying AGV dispatching system and algorithm are capable of dispatching a vehicle automatically to handle a call at the required time. In order to overcome difficulties associated with tackling immediate orders, pre-booked orders, and processing of information related to AGVs, a comprehensive dispatching algorithm is developed which aims to minimise lateness, traveling time and distance of empty vehicles in a simulated job-shop scenario. The effectiveness of the proposed framework for an AGV dispatching system is shown through a test problem.     

An algorithm for deadlock avoidance in an AGV System

In this paper, a simple and easily adaptable deadlock avoidance algorithm for an automated guided vehicle (AGV) system is presented. This algorithm uses the graph-theoretic approach. Unlike Petri-net-based methods, which are complex and static, it is easy to modify the existing model as the configuration of the system changes. Therefore, it is suitable for the AGV system in a flexible manufacturing system (FMS) and a retail or postal distribution center. Moreover, because it is very simple, it is appropriate for real-time control mechanisms.This paper consists of two parts: the first part presents an AGV deadlock avoidance algorithm that uses the graph-theoretic approach, and the second suggests appropriate routing strategies based on the proposed algorithm. The results show that this deadlock avoidance algorithm can be modified easily whenever the configuration of an FMS changes and provide high-performance on the deadlock avoidance. Finally, experimental results that confirm the validity of this approach are provided.     

An algorithm for deadlock avoidance in an AGV System

In this paper, a simple and easily adaptable deadlock avoidance algorithm for an automated guided vehicle (AGV) system is presented. This algorithm uses the graph-theoretic approach. Unlike Petri-net-based methods, which are complex and static, it is easy to modify the existing model as the configuration of the system changes. Therefore, it is suitable for the AGV system in a flexible manufacturing system (FMS) and a retail or postal distribution center. Moreover, because it is very simple, it is appropriate for real-time control mechanisms.This paper consists of two parts: the first part presents an AGV deadlock avoidance algorithm that uses the graph-theoretic approach, and the second suggests appropriate routing strategies based on the proposed algorithm. The results show that this deadlock avoidance algorithm can be modified easily whenever the configuration of an FMS changes and provide high-performance on the deadlock avoidance. Finally, experimental results that confirm the validity of this approach are provided.     

基于混合区域控制模型的多AGV系统调度研究与实现

为降低多AGV系统调度过程的复杂性,提出了一种混合区域控制模型,在模型中采用基于任务等待时间最短原则的SwT调度策略,优化了系统效率和整体运行时间;并提出一种分布式协调控制机制,解决了多AGV在线运行的冲突和死锁问题。最后,搭建了多AGV系统调度的硬件仿真平台,结合具体的加工实例进行了仿真实验,实验结果证明了模型的有效性和可行性。     

面向多运输任务的节能单负载AGV路径规划研究

节能路径规划已被证明是提高自动导引运输车(automated guided vehicle, AGV)使用过程能效,促进生产车间节能的一种可行方法。目前从路径规划角度开展的AGV能耗优化研究主要面向单项运输任务,很少涉及多项运输任务。为此,以单负载AGV为研究对象,建立了面向多运输任务,以运输距离和能耗为优化目标的节能AGV路径规划模型,进而提出了一种两阶段模型求解方法：阶段1针对各运输任务关联的负载运输阶段和可能的空载运输阶段进行节能路径规划,搜索其最优运输路径;阶段2利用非支配排序遗传算法确定最佳的运输任务执行顺序和各运输阶段的最佳运输路径。最后,案例研究验证了模型节能效果。     

基于数字地图的AGV自主避障技术研究

采用精确标志块来标定摄像机以及手动引导AGV生成比较精确的数字地图,由数字地图在起始点和终点均已知的情况下生成起点到终点的最短路径,并由此确立目标点组和观测点组,再生成对应于每个观测点的距离轮廓图。AGV在自动导引中结合数字地图以及对应于观测点组的距离轮廓图可以实现灵活的自主导向和避障。此方法应用比较简单且导引效果将和运行精度较高。     

基于混合蜜獾算法的机械臂最优运动规划方法

针对六自由度机械臂末端执行器路径及关节空间下轨迹的规划问题,提出一种基于混合蜜獾算法和 3-5-3 分段多项 式插值的最优运动规划方法,实现机械臂末端执行器运动路径最短及关节运动时间最优,并有效降低优化路径与规划路径的差 异。 首先,以标准蜜獾算法框架为基础,在初始化、全局寻优与局部探索中采用混沌反向学习、转移算子、正弦余弦算子以及自 适应扰动系数策略,提高最优解质量与寻优能力,并据此设计机械臂末端执行器无碰撞、最短路径规划方法,引导关节轨迹规划 过程;其次,在关节空间下,利用混合蜜獾算法寻找各关节最优运动时间,在此基础上,利用 2 次 3-5-3 分段多项式插值算法, 在满足各关节位移、速度、加速度约束的条件下,完成机械臂关节平滑且时间最优的轨迹规划;最后,通过与其他规划方法仿真 对比,验证提出的方法能够使规划路径长度缩短,关节运动时间减少,优化路径与规划路径差异较小,并以 UR5 机械臂抓取实 验为例检验了该方法的可行性。     

Agent technology for collaborative process planning: a review

Agent technology has been considered as a promising approach for developing process planning systems and optimizing process plans in a distributed environment. A number of researchers have attempted to use agent technology in process planning for the purpose of integrating systems, tools and algorithms which are geographically distributed. In this paper, the historical background of agent technology is systematically reviewed. A comprehensive review of agent technology and its applications in manufacturing is presented including the applications of agent in scheduling, control, and enterprise integration and supply chain management. The focus of the paper is on how agent technology can be further developed in the support of collaborative process planning as well as its future research issues and directions in process planning. The current research directions in computer aided process planning (CAPP) and issues in traditional CAPP approaches are also discussed. Three agent-based approaches for process planning are presented. Finally, the key issues in developing agent-based collaborative process planning systems are summarized.     

New hybrid vision-based control approach for automated guided vehicles

Automated guided vehicles (AGVs) are a common choice made by many companies for material handling (MH) in manufacturing systems. AGV-based internal transport of raw materials, goods, and parts is becoming improved with advances in technology. Demands for fast, efficient, and reliable transport imply the usage of the flexible AGVs with onboard sensing and special kinds of algorithms needed for daily operations. So far, the majority of these transport solutions have not considered the modern techniques for visual servoing, monocular SLAM, and consequently, the usage of camera as onboard sensor for AGVs. In this research, a new hybrid control of AGV is proposed. The main control algorithm consists of two independent control loops: position-based control (PBC) for global navigation and image based visual seroving (IBVS) for fine motions needed for accurate steering towards loading/unloading point. By separating the initial transportation task into two parts (global navigation towards the goal pose near the loading/unloading point and fine motion from the goal pose to the loading/unloading point), the proposed hybrid control bypasses the need for artificial landmarks or accurate map of the environment. The state estimation of the robot pose is determined in terms of monocular SLAM, via extended Kalman filter coupled with feedforward neural network—the neural extended Kalman filter (NEKF). NEKF is used to model unknown disturbances and to improve the robot state transition model. The integration of the new hybrid control and NEKF has been tested in laboratory with the mobile robot and simple camera. Experimental results present the effectiveness of the proposed hybrid control approach.     

基于嵌入式操作系统μC／OS-Ⅱ的多路径AGV设计

传统AGV一般只能沿单一路径行驶,当需要完成各具有指定路径的多任务时,几台AGV在同一工况下则较难有效实现响应功能,常规的AGV不能适应现代化物流系统中的多地、多路径以及多任务的工作需求。嵌入式操作系统凭借其进程调度的高效性和实时性在诸多控制系统应用中发挥了巨大作用。将嵌入式实时操作系统μC／OS-Ⅱ移植到MSP430F149芯片上。较大程度地发挥嵌入式系统的特性,通过触摸屏实现良好的人机交互,较为方便地在两台或多台AGV的使用过程中实现多路径。     

基于改进RRT算法的套管柔性针运动规划

运动规划是运动控制的基础,然而套管柔性针穿刺软组织的运动规划问题面临着巨大的挑战:一方面由于套管柔性针的运动是个非完整约束运动,另一方面要求套管柔性针绕过人体的某些生理结构障碍和敏感组织准确穿刺靶点。基于分析现有运动规划算法存在的不足,提出基于改进的快速探索随机树(RRT)的套管柔性针运动规划算法。提出贪婪启发策略并结合可达引导策略来改进传统RRT算法;引入直线段路径,采用直线、曲线结合的路径形式;同时考虑入射姿态的规划。基于套管柔性针的运动学模型,分别在二维和三维有障碍环境下进行仿真研究。结果表明,所提出的运动规划算法不论是在运算速度和收敛性上还是在路径形式和搜索的鲁棒性上都优于目前普遍采用的运动规划算法。这些优势为将来的实时运动规划奠定基础。最后对规划的路径进行了穿刺实验,结果证明实验路径与规划路径十分吻合,验证了所提出的路径规划算法的正确性和规划路径的可行性。     

基于改进A*算法的AGV路径研究

路径规划能力是AGV(Automated Guided Vehicle,自动导引运输车)系统智能化程度的体现。在众多算法中,A~*算法使用代价消耗估算方式达到较快的计算能力,被广泛应用于AGV的路径规划中,但仍存在局部最优的规划问题,规划的路径上存在冗余节点和较多不必要拐点。为减少运输路径中的总能耗,缩短路径总长度和减少AGV转弯次数,采用分裂和筛选的方案对传统A~*算法进一步优化,提出改进A~*算法,使其在实际工作环境中搜索更加迅速、考虑更加周密。在传统A~*算法基础上,在未知节点的启发函数里增加转弯权值,可以在计算规划过程中考虑转向所带来的消耗,从而减少转弯次数。使用任务分裂方案可以尽可能多地选择出较优路径,其中的最优解能够实现得转弯较少,展现出比较平滑的线路。基于Ubuntu下ROS系统版本进行仿真,对比实验结果表明,改进A~*算法在规划时间、总行程以及转弯消耗等方面都优于传统A~*算法,提升了AGV的实际运行效率,减少了AGV小车的耗能,可以缩短路径搜索规划时间,更符合工厂环境对AGV的需求。     

制造系统中多智能体AGV运输子系统体系结构设计

在论述制造控制系统常用体系结构的基础上,提出了AGV运输子系统的体系结构,并详细阐述了其中的三个主要模块:操作者模块、决策模块和AGV智能体模块。该体系结构有助于充分发挥AGV的灵活性。     

基于模糊神经网络控制的AGV避障路径规划仿真

自动导引车(AGV)作为一种现代化物流设备,在许多领域得到了越来越广泛的应用。AGV在行进过程中的主要任务是避障及路径规划。针对AGV的避障路径规划问题,定义了AGV的行驶环境,提出了AGV避障路径规划的模糊神经网络控制方法,设计了模糊神经网络控制器,并用Matlab进行了仿真。仿真结果表明该模糊神经网络控制器满足控制要求,该研究为进一步精确控制AGV奠定了基础。     

A production order-driven AGV control model with object-oriented implementation

To effectively manage the material handling in Flexible Manufacturing Systems (FMS), where a large amount of data is required in the dynamic decision-making, integrated control is needed to consider the overall production schedule. The focus of this research is on the development of an integrated Automated Guided Vehicle System (AGVS) control model that includes essential features like dynamic vehicle path determination and conflict-free routing. An object-oriented implementation of the AGVS model is proposed that forms the basis of systems integration with a production planning module such as MRP. Static and dynamic informational and functional models of the AGVS are developed. The system incorporates: (i) conflict-free shortest path routing procedures, and (ii) vehicle assignment rules or scheduling strategies. A prototype version of each of these has been developed for demonstrative purposes. This object-oriented modelling methodology provides the capability of rapid development and change. The approach has been demonstrated for a real manufactured product through simulation studies which confirm the superior performance of anticipatory AGVS control rules, even in a production orderdriven environment.     

Integrated manufacturing process planning and control based on intelligent agents and multi-dimension features

Dynamic manufacturing environments require a flexible process planning and control system in response to changing manufacturing resource availability, production uncertainty, and dynamic machining conditions. To address these issues, this paper proposes a novel integrated process planning and control method based on intelligent software agents and multi-dimension manufacturing features. An integration framework with three modules including generic process planning, shop floor process planning, and online process control is developed. An intelligent agent-based approach is adopted for achieving intelligence and autonomy of individual software modules and components. An ontology-based multi-dimension manufacturing feature model is proposed to facilitate the communication and collaboration between process planning and control, as well as to speed up the decision-making of intelligent agents. The feasibility and flexibility of the proposed method are validated through a proof-of-concept implementation.