Regardless of whether it is a general manufacturing industry or a dock warehouse, material handling and handling are one of the elements of logistics, and the cost ratio in the logistics system is also high. In the process of industrial production in the United States, loading, unloading and handling costs account for 20-30% of the cost, German logistics companies’ material handling costs account for 35% of the turnover, and Japan’s logistics and handling costs account for 10%. In my country’s production logistics, loading, unloading and handling costs account for about 20% of the processing cost. %, so the company has always been in the most perfect automation and intelligent handling technology and equipment. AGV robot is a flexible and intelligent logistics handling robot. It has been used in the warehousing industry in foreign countries since the 1950s. It has been widely used in manufacturing, ports, docks and other fields. In China, some enterprises have gradually attached importance to and applied AGV to Complete some simple carrying tasks. Let's briefly analyze the I-SO intelligent AGV robot and the application of modern intelligent logistics.
I-SO AGV的显著特点是无人驾驶，I-SO AGV上装备有自动导向系统，可以保障系统在不需要人工引航的情况下就能够沿预定的路线自动行驶，将货物或物料自动从起始点运送到目的地。I-SO AGV的另一个特点是柔性好，自动化程度高和智能化水平高，I-SO AGV的行驶路径可以根据仓储货位要求、生产工艺流程等改变而灵活改变，并且运行路径改变的费用与传统的输送带和刚性的传送线相比非常低廉。I-SO AGV一般配备有装卸机构，可以与其他物流设备自动接口，实现货物和物料装卸与搬运全过程自动化。此外，I-SO AGV还具有清洁生产的特点，I-SO AGV依靠自带的蓄电池提供动力，运行过程中无噪声、无污染，可以应用在许多要求工作环境清洁的场所。
The distinctive feature of I-SO AGV is that it is unmanned. The I-SO AGV is equipped with an automatic guidance system, which can ensure that the system can automatically drive along the predetermined route without manual piloting, and automatically start the goods or materials from the starting point. Shipping from origin to destination. Another feature of I-SO AGV is good flexibility, high degree of automation and high level of intelligence. The driving path of I-SO AGV can be flexibly changed according to changes in storage space requirements, production process flow, etc., and the cost of changing the operating path Very inexpensive compared to traditional conveyor belts and rigid conveyor lines. I-SO AGV is generally equipped with a loading and unloading mechanism, which can automatically interface with other logistics equipment to realize the automation of the whole process of loading, unloading and handling of goods and materials. In addition, I-SO AGV also has the characteristics of clean production. I-SO AGV relies on its own battery to provide power. It is noise-free and pollution-free during operation, and can be used in many places that require a clean working environment.
1). I-SO电磁感应引导式AGV （由于这种技术相对落后和性能缺陷，一般环境下I-SO智能 AGV很少采用）
2). I-SO激光引导式AGV （适合高附加值，高环境要求行业生产制造使用）
I-SO视觉引导式AGV 是我们正在快速发展和成熟的AGV，该AGV上装有CCD摄像机和传感器，在车载计算机中设置有AGV欲行驶路径周围环境图像数据库。AGV行驶过程中摄像机动态获取车辆周围环境图像信息并与图像数据库进行比较，从而确定当前位置并对下一步行驶做出决策。 这种AGV由于不要求人为设置任何物理路径，因此在理论上具有最佳的引导柔性，随着计算机图像采集、储存和处理技术的飞速发展，能够识别物品和行人（如盘子.碗.顾客）该种AGV的实用性越来越强。
4).I-SO磁带导引AGV (通用型，适合所有行业使用)I-SO磁带导引AGV 在工作区间地板上铺设磁带，AGV通过磁场传感器检测磁带信号控制走行，这种技术目前成本最低，施工简单可快速更改路径，不受环境影响可靠性高，可满足大部分行业要求，I-SO磁带导引AGV 在站点设置上突破了传统技术自主开发了AGV专用RFID隐藏式站标和读写器，让行驶线路设置更加柔性。
Types of I-SO Intelligent AGV
AGV has a history of 50 years since its invention. With the expansion of application fields, its types and forms have become diverse. We divide AGVs into the following types according to the way of navigation during the automatic driving of I-SO AGVs:
1. I-SO electromagnetic induction guided AGV (due to the relatively backward technology and performance defects of this technology, I-SO intelligent AGV is rarely used in general environment)
Electromagnetic induction guidance is generally on the ground, and wires are buried along a preset driving path. When high-frequency current flows through the wires, an electromagnetic field is generated around the wires. Two electromagnetic sensors are installed symmetrically on the AGV. The difference in the strength of the electromagnetic signal can reflect the degree to which the AGV deviates from the path. The automatic control system of the AGV controls the steering of the vehicle according to this deviation, and the continuous dynamic closed-loop control can ensure the stable and automatic operation of the AGV on the set path. Due to the complicated installation and construction of this electromagnetic induction-guided navigation method, the AGV driving path cannot be updated at any time, and it is easily interfered by the electromagnetic environment. At present, some domestic AGV manufacturers are still using it on commercial AGVs, especially for large and medium-sized AGVs. AGV.
2. I-SO laser-guided AGV (suitable for high value-added, high environmental requirements industries production and use)
A rotatable laser scanner is installed on the I-SO laser-guided AGV, and highly reflective positioning marks are installed on the walls or pillars along the running path. The AGV relies on the laser scanner to emit a laser beam, and then receives the surrounding positioning marks. With the reflected laser beam, the on-board computer calculates the current position and direction of movement of the vehicle, and corrects the orientation by comparing it with the built-in digital map, thereby realizing automatic handling.
At present, the application range of I-SO laser-guided AGV is widespread, and according to the same guiding principle, if the laser scanner is replaced with an infrared transmitter or an ultrasonic transmitter, the laser-guided AGV can become an infrared-guided AGV and an ultrasonic-guided AGV. type AGV. The cost of I-SO laser-guided AGV is relatively high, and it is less recommended in ordinary manufacturing industries. It is suitable for use in high value-added industries such as biochemical pharmaceuticals, tobacco, and chips.
3. I-SO vision-guided AGV
The I-SO vision-guided AGV is our rapidly developing and mature AGV. The AGV is equipped with CCD cameras and sensors, and the on-board computer is provided with an image database of the surrounding environment of the AGV's desired path. During the driving process of the AGV, the camera dynamically obtains the image information of the surrounding environment of the vehicle and compares it with the image database, so as to determine the current position and make a decision on the next driving. Since this AGV does not require any physical path to be set manually, it has the best guiding flexibility in theory. With the rapid development of computer image acquisition, storage and processing technology, it can identify items and pedestrians (such as plates, bowls, customers) The practicability of this kind of AGV is getting stronger and stronger.
4. I-SO tape-guided AGV (universal, suitable for all industries)
I-SO tape-guided AGV lays tape on the floor of the work area, and the AGV controls the running by detecting the tape signal through the magnetic field sensor. This technology is currently the lowest cost , The construction is simple, the path can be changed quickly, and it is not affected by the environment. Writer to make the driving route setting more flexible.
In addition, there are various forms of AGV such as ferromagnetic gyro inertial-guided AGV and optically-guided AGV.
2. AGV Applications
(3) Post offices, libraries, port terminals and airports;
(4) Tobacco, medicine, food, chemical industry;
(5) Hazardous Locations and Specialty Industries.
1． 数学规划方法 ：为AGV选择最佳的任务及最佳路径，可以归纳为一个任务调度问题。数学规划方法是求解调度问题最优解的传统方法，该方法的求解过程实际上是一个资源限制下的寻优过程。实用中的方法主要有整数规划、动态规划、petri方法等。在小规模调度情况下，这类方法可以得到较好的结果，但是随着调度规模的增加，求解问题耗费的时间呈指数增长，限制了该方法在负责、大规模实时路线优化和调度中应用。
The method and research and development direction of route optimization and real-time scheduling in the use of I-SO intelligent AGV:
1. Mathematical programming method: Selecting the best task and the best path for AGV can be summarized as a task scheduling problem. Mathematical programming method is a traditional method to solve the optimal solution of scheduling problem. The solution process of this method is actually an optimization process under resource constraints. Practical methods mainly include integer programming, dynamic programming, and petri methods. In the case of small-scale scheduling, this kind of method can get better results, but with the increase of the scheduling scale, the time spent to solve the problem increases exponentially, which limits the application of this method in responsible, large-scale real-time route optimization and scheduling .
2. Simulation method: The simulation method simulates the implementation of a scheduling scheme of AGV by modeling the actual scheduling environment. We use simulation to test, compare, and monitor certain scheduling schemes to change and choose scheduling strategies. The methods used in practice include discrete event simulation method, object-oriented simulation method and 3D simulation technology. There are many softwares that can be used for AGV scheduling simulation. Among them, Witness software can quickly establish simulation model and realize 3D demonstration of simulation process and results. Analytical processing.
3. Artificial intelligence method: The artificial intelligence method describes the scheduling process of AGV as a process of searching for the optimal solution in the solution set that satisfies the constraints. It uses knowledge representation techniques to include human knowledge, and uses various search techniques to try to give a satisfactory solution. Specific methods include expert system method, genetic algorithm, heuristic algorithm, neural network algorithm. Among them, the expert system method is mostly used in practice. It abstracts the experience of scheduling experts into scheduling rules that the system can understand and execute, and uses conflict resolution technology to solve the problem of rule expansion and conflict in large-scale AGV scheduling.
Because the neural network has the advantages of parallel operation, knowledge distribution and storage, and strong adaptability, it is a promising method for solving large-scale AGV scheduling problems. At present, the TSP-NP problem has been successfully solved by the neural network method. During the solution, the neural network can convert the solution of the combinatorial optimization problem into an energy function of a discrete dynamic system, and obtain the optimization problem by minimizing the energy function. untie.
Genetic algorithm is an optimization solution method formed by simulating the heredity and variation in the process of biological evolution in nature. When the genetic algorithm solves the optimal scheduling problem of AGV, it first expresses a certain number of possible scheduling schemes into appropriate chromosomes through coding, and calculates the fitness of each chromosome (such as the shortest running path), and repeats, crosses, and mutates through repetition. Find the chromosome with large fitness, that is, the optimal solution of the AGV scheduling problem.
Using a single method to solve the scheduling problem often has certain defects. At present, it is a research hotspot to integrate multiple methods to solve the AGV scheduling problem. For example, the expert system and genetic algorithm are integrated, and the knowledge of experts is integrated into the formation of the initial chromosome group to speed up the solution speed and quality.