Automated Guided Vehicles Research Articles

Research on AGV path planning in new energy battery workshop

In recent years, more and more factories have begun to use automatic guided vehicles (AGVs) instead of manual work in production, transportation, and other links, which has broad application prospects and market prospects. This paper takes the new energy battery workshop as the research object, analyzes the AGV operation plan in the workshop according to the overall workflow of the workshop material distribution, and uses AnyLogic to simulate the map to complete the algorithm test. A* global algorithm is optimized and improved, and the optimal shortest route with more smoothness from the beginning of the AGV to the end of the AGV is planned, which greatly improves the operation efficiency of the whole scheduling and has high practicability.

A Novel Trajectory Tracking Control of AGV Based on Udwadia-Kalaba Approach

Several control approaches have been used in order to achieve the trajectory tracking control of automated guided vehicle (AGV). But they are all based on the D'Alembert principle which requires to determine the Lagrangian multipliers. Unlike those control methods, in this paper, a novel approach of trajectory tracking control is presented, which is based on Udwadia-Kalaba approach. This approach presents a novel, concise and explicit equation of motion for constrained mechanical systems with holonomic and/or nonholonomic constraints as well as constraints that may be ideal or non-ideal. The Udwadia-Kalaba equation is uncoupled and free from the Lagrangian multipliers. In this paper, we classify constraints into structural constraints and performance constraints. Structural constraints are set up regardless of trajectory control and we use structural constraints to establish the dynamic model. Then the desired trajectory is set as performance constraints and constraint torques are solved by analyzing Udwadia-Kalaba equation. For AGV, a nonholonomic mechanical system, second-order constraints are used to get constraint forces and the numerical simulation is conducted by using Matlab. The results show that the AGV's movement meets the requirement and the tracking trajectory is exact and perfect. Compared with other approaches, this approach requires very little computation. Through two cases of tracking a circle and a line, how to use Udwadia-Kalaba equation to realize trajectory tracking control is shown in detail.

LIFNS: Design of a novel Lidar-IMU fusion navigation system for AGVs in smart factories

Traditional Automated Guided Vehicle (AGV) robots commonly employ 2D plane navigation systems. However, with the expansion of AGV application scenarios and the increasing complexity of structures, the limitations of existing 2D navigation systems have become more pronounced, rendering them inadequate for addressing these challenges. To tackle this issue, this paper proposes a novel navigation system suitable for AGV robots composed of fused Lidar and Inertial Measurement Unit (IMU), named as Lidar-IMU Fusion Navigation System (LIFNS). LIFNS primarily comprises mapping, localization, and fused path planning modules. In the mapping module, a 3D point cloud map for precise 3D localization and a 2D grid map for path planning are constructed using multiple-line Lidar and IMU. For the localization module, a fusion localization approach is introduced, combining IMU data with Normal Distributions Transform (NDT) point cloud registration through Unscented Kalman Filtering (UKF). Finally, global path planning is executed using the A* algorithm on the grid map, while local path planning utilizes the Timed-Elastic Band (TEB) algorithm. The effectiveness and universality of LIFNS are validated through simulation experiments and real-world deployment tests. The experimental results demonstrate that LIFNS achieves centimeter-level accuracy in both mapping and localization, effectively alleviating the issues of low precision and significant limitations present in traditional AGV robots. This positions LIFNS with promising applications in enclosed settings such as smart factories, industrial parks, and healthcare facilities.

AGV Path Planning based on Improved Ant Colony Algorithm

With the widespread application of Automated Guided Vehicles (AGV) in industrial production and warehouse logistics, the challenges they face during operation are becoming increasingly apparent. Currently, the path planning problem of AGV has become one of the hot topics in academic research. This paper provides an in-depth analysis of the performance of AGV in real-world scenarios and utilizes grid-based methods to construct a map environment model. Subsequently, a detailed analysis of the movement of AGV in the environment is conducted, and an improved pheromone method is proposed based on the traditional ant colony algorithm, aiming to optimize the navigation path of AGV to determine the optimal travel route.

EGCY-Net: An ELAN and GhostConv-Based YOLO Network for Stacked Packages in Logistic Systems

Dispatching, receiving, and transporting goods involve a large amount of manual effort. Within a logistics supply chain, a wide variety of transported goods need to be handled, recognized, and checked at many different points. Effective planning of automated guided vehicle (AGV) transportation can reduce equipment energy consumption and shorten task completion time. As the need for efficient warehouse logistics has increased in manufacturing systems, the use of AGVs has also increased to reduce working time. These processes hold automation potential, which we can exploit by using computer vision techniques. We propose a method for the complete automation of box recognition, covering both the types and quantities of boxes. To do this, an ELAN and GhostConv-based YOLO network (EGCY-Net) is proposed with a Conv-GhostConv Stack (CGStack) module and an ELAN-GhostConv Network (EGCNet). To enhance inter-channel relationships, the CGStack module captures complex patterns and information in the image by using ghost convolution to increase the model inference speed while retaining the ability to capture spatial features. EGCNet is designed and constructed based on ELAN and the CGStack module to capture and utilize hierarchical features efficiently in layer aggregation. Additionally, the proposed methodology involves the creation of a dataset comprising images of boxes taken in warehouse settings. The proposed system is realized on the NVIDIA Jetson Nano platform, using an Arducam IMX477 camera. To evaluate the proposed model, we conducted experiments with our own dataset and compared the results with some state-of-the-art (SOTA) models. The proposed network achieved the highest detection accuracy with the fewest parameters compared to other SOTA models.

Indoor Positioning of AGVs Based on Multi-Sensor Data Fusion Such as LiDAR

In recent years, with the rapid growth in technology and demand for industrial robots, Automated Guided Vehicles (AGVs) have found widespread application in industrial workshops and smart logistics, emerging as a global hot research topic. Due to the volatile and complex working environments, the positioning technology of AGV robots is of paramount importance. To address the challenges associated with AGV robot positioning, such as significant accumulated errors in wheel odometer and Inertial Measurement Unit (IMU), susceptibility of Ultra Wide Band (UWB) positioning accuracy to Non Line of Sight (NLOS) errors, as well as the distortion points and drift in point clouds collected by LiDAR during robot motion, a novel positioning method is proposed. Initially, Weighted Extended Kalman Filter (W-EKF) is employed for the loosely coupled integration of wheel odometer and Ultra Wide Band (UWB) data, transformed into W-EKF pose factors. Subsequently, appropriate addition of W-EKF factors is made during the tight coupling of pre-integrated Inertial Measurement Unit (IMU) with 3D-LiDAR to counteract the distortion points, drift, and accumulated errors generated by LiDAR, thereby enhancing positioning accuracy. After experimentation, the algorithm achieved a final positioning error of only 6.9cm, representing an approximately 80% improvement in positioning accuracy compared to the loosely coupled integration of the two sensors.

Real-time AGV scheduling optimisation method with deep reinforcement learning for energy-efficiency in the container terminal yard

The increasing vessel size and automation level have shifted the productivity bottleneck of automated container terminals from the terminal side to the yard side. Operating an automated container terminal (ACT) yard with a big number of automated guided vehicles (AGV) is challenging due to the complexity and dynamics of the system, severely affecting the operational efficiency and energy use efficiency. In this paper, a hybrid multi-AGV scheduling algorithm is proposed to minimise the energy consumption and the total makespan of AGVs in an ACT yard. This framework first models the AGV scheduling process as a Markov decision process (MDP). Furthermore, a novel scheduling algorithm called MDAS is proposed based on multi-agent deep deterministic policy gradient (MADDPG) to facilitate online real-time scheduling decision-making. Finally, simulation experiments show that the proposed method can effectively enhance the operational efficiency and energy use performance of AGVs in ACT yards of various scales by comparing with benchmarking methods.

Real-time schedule adjustments for conflict-free vehicle routing

Conflict-Free Vehicle Routing Problems (CFVRPs) arise in manufacturing, transportation and logistics applications where Automated Guided Vehicles (AGVs) are utilized to move pallets and containers. A peculiar feature of these problems is that collision avoidance among vehicles must be considered explicitly. To make things more complex, the uncertainty affecting both travel times and machine ready times often results in vehicle delays or anticipations that require real-time modifications to the fleet nominal plan. In this paper, the determination of such modifications (schedule adjustment problem in CFVRPs) is modeled as a sequential decision problem for which we develop a tailored fast exact algorithm suitable for any objective function that is non-decreasing in the arrival times. Computational results show that optimal solutions can be found within at most 3.3 milliseconds for instances with up to 300 vehicles with improvements of various performance measures up to 74% compared to state-of-the-art solution algorithms.

A Hierarchical Trajectory Planning Algorithm for Automated Guided Vehicles in Construction Sites

Herein, to address the challenges faced by Automatic Guided Vehicles (AGVs) in construction site environments, including heavy vehicle loads, extensive road search areas, and randomly distributed obstacles, this paper presents a hierarchical trajectory planning algorithm that combines coarse planning and precise planning. In the first-level coarse planning, lateral and longitudinal sampling is performed based on road environment constraints. A multi-criteria cost function is designed, taking into account factors such as deviation from the road centerline, shortest path cost, and obstacle collision safety cost. An efficient dynamic programming algorithm is used to obtain the optimal path. Considering nonholonomic constraints of vehicles, eliminating inflection points using improved B-Spline path fitting, and a quadratic programming algorithm is proposed to enhance path smoothness, completing the coarse planning algorithm. In the second-level precise planning, the coarse planning path is used as a reference line, and small-range sampling is conducted based on AGV motion constraints, including lateral displacement and longitudinal velocity. Lateral and longitudinal polynomials are constructed. To address the impact of randomly appearing obstacles on vehicle stability and safety, an evaluation function is designed, considering factors such as jerk and acceleration. The optimal trajectory is determined through collision detection, ensuring both safe obstacle avoidance and AGV smoothness. Experimental results demonstrate the effectiveness of this method in solving the path planning challenges faced by AGVs in construction site environments characterized by heavy vehicle loads, extensive road search areas, and randomly distributed obstacles.

Energy-efficient path planning for a multi-load automated guided vehicle executing multiple transport tasks in a manufacturing workshop environment.

Automated guided vehicles (AGVs) are typical intelligent logistics equipment, and path planning plays a significant role in the efficient use of AGVs. To better utilize multi-load AGVs and enhance the sustainability of the logistics process, an energy-efficient path planning model is formulated for a multi-load AGV executing multiple transport tasks in a manufacturing workshop environment, with transport distance and energy consumption (EC) serving as optimization objectives. Furthermore, a two-stage approach is proposed to solve it. In the first stage, the optimal energy-efficient paths connecting any two different nodes are acquired based on the workshop transport network expressed as a topological map. Afterward, the non-dominated sorting genetic algorithm-II is adopted in the second stage to determine the optimal execution sequence of pickup and delivery operations related to the assigned transport tasks, as well as to select the optimal path from the first stage's output information to execute each operation simultaneously. Moreover, the experimental study validates the energy-saving effect of the established model and the effectiveness of the solution method, and the factors affecting the multi-load AGV EC are analyzed.

A dual population collaborative genetic algorithm for solving flexible job shop scheduling problem with AGV

With the increase in labor costs and the development of manufacturing automation technology, automatic guided vehicle (AGV) is widely used in various flexible workshop scenarios. The integrated scheduling of processing machines and AGV is of great significance in real-world workshop production. This article studies the integration problem of flexible job shop scheduling problem (FJSP) and AGV with minimizing the makespan, and proposes a novel mixed integer linear programming (MILP) model and a dual population collaborative genetic algorithm (DCGA). In DCGA, a two-layer encoding strategy based on machine selection and operation sequencing is used. Two decoding methods are designed to determine AGV selection, and each population uses a decoding method. Moreover, a population collaboration operation is designed. The feasibility and effectiveness of the MILP model and DCGA are verified through experimental simulation. Specifically, the DCGA improves 18 current best solutions for benchmarks in the existing studies.

A scheduling optimization method for multiple automated guided vehicle systems

When constructing a multiple automated guided vehicle (multi-AGV) system, it is essential to calculate the potential values of the system’s feature parameters. This article presents two time-cost calculators and an improved simulation platform for scientifically estimating the cost of constructing a multi-AGV system. By inputting the parameters of the number of automated guided vehicles (AGVs), the velocity of the AGV, the number of tasks, scheduling interval and path length, the designed calculator can output the system’s time expense when all tasks are completed. The designed simulation platform can display a specific multi-AGV system’s time cost and how the entire progress works in a visual interface. An advanced scheduling method based on handover mode and A* algorithm is used to solve task scheduling problems in a multi-AGV system. The overall performance of the newly integrated scheduling system is compared with other scheduling systems to validate its superiority and shortcomings in different corresponding work scenarios. The final results present a robust solution to improve a multi-AGV system’s effectiveness.

AI-driven warehouse automation: A comprehensive review of systems

This comprehensive review explores the profound impact of artificial intelligence (AI) on warehouse automation, providing an in-depth examination of various AI-driven systems. As industries increasingly embrace automation to enhance efficiency and streamline operations, the integration of AI technologies into warehouse management systems has become pivotal, reshaping the landscape of logistics and supply chain management. AI-driven warehouse automation systems leverage advanced algorithms to optimize various aspects of warehouse operations, from inventory management to order fulfillment. Machine learning algorithms play a key role in demand forecasting, allowing warehouses to predict and adapt to changing customer needs. Computer vision technologies enhance robotic vision, facilitating tasks such as item recognition, pick-and-place operations, and quality control. These advancements significantly contribute to increased accuracy, speed, and cost-effectiveness in warehouse processes. The review provides a detailed examination of the applications of AI in warehouse automation, encompassing autonomous mobile robots (AMRs), robotic arms, and automated guided vehicles (AGVs). AMRs equipped with AI algorithms navigate warehouse environments autonomously, optimizing pick routes and adapting to changes in the warehouse layout. Robotic arms, enhanced by AI, enable precise and adaptable material handling, contributing to the efficiency of tasks like packing and palletizing. AGVs, guided by AI, ensure seamless material transport within warehouses, enhancing overall operational agility. Recent trends in AI-driven warehouse automation systems underscore the dynamic evolution of this field. Edge computing solutions empower these systems to process data locally, reducing latency and enhancing real-time decision-making. Reinforcement learning algorithms enable robotic systems to learn and adapt their behavior based on changing environmental conditions, contributing to continuous improvement and efficiency gains. In conclusion, this review illuminates the pivotal role of AI in transforming warehouse automation systems, revolutionizing the way logistics and supply chain operations are conducted. The collaborative synergy between AI and warehouse automation promises to drive unprecedented advancements in efficiency, accuracy, and adaptability within the evolving landscape of modern warehouses.

Multi-AGV-Driven Pallet-Picking Scheduling Optimization (MADPSO): A Method for Flexible Multi-Level Picking Systems

In the context of increasingly competitive shipbuilding, the flexible multi-level picking system, composed of high-rise shelves, Automated Guided Vehicles (AGVs), and picking stations, has been of gradual interest because of its advantages in operation efficiency, system flexibility, and system robustness. Compared with other simple-level systems, the flexible multi-level picking system has a more complex coupling temporal relationship, which makes the scheduling optimization of shipbuilding automated collaborative order picking (SACOP) extremely difficult. In order to avoid the dilemma of finding a feasible and optimal collaborative scheduling scheme under the constraints of a complex temporal relationship, this paper proposed a multi-AGV-driven pallet-picking scheduling optimization (MADPSO) method, which takes the AGV scheduling scheme as the direct solution and modifies it to a feasible solution under the reasonably designed interaction strategy of stacker, AGV, and the interaction strategy of picking station, AGV. Furthermore, taking the minimum energy consumption and operation time as the optimization objectives, a multi-objective optimization mathematical model was established to describe MADPSO, and an improved NSGA-III algorithm was designed to solve the problem. Finally, several experiments were conducted in various scenarios and verified that using MADPSO can achieve a comprehensive optimization index improvement of 52.02–75.66% compared with traditional picking methods, which has a certain reference significance for shipyards.

Solving line balancing and AGV scheduling problems for intelligent decisions using a Genetic-Artificial bee colony algorithm

Due to the rapid advancement of technology, the demand for electronic devices in various sectors such as consumer electronics, automotive, telecommunications, healthcare, and industrial applications, as well as customized printed circuit board (PCB) products, has significantly increased. Balancing the PCB assembly line is crucial for improving productivity to meet market demand, which means balancing the workload distributed among various assembly stations on the assembly line. However, the workload balancing depends on material-handling systems in production environments that facilitate the transportation of raw materials to the buffer storage of the assembly stations. In the PCB assembly system, the material handling is carried out using automated guided vehicles (AGVs). This paper studies the assembly line balancing and AGV scheduling collectively because of their dependency on each other. A mixed integer linear programming (MILP) model is formulated to balance the workload distribution among stations and schedule the AGVs. An existing intelligent platform of the real-life PCB industry is considered to solve this integrated problem with intelligent decisions. The platform includes three layers modules: physical layer, data management layer and application service layer. A novel genetic artificial bee colony (GABC) algorithm is proposed and embedded with an application service layer to optimize the current problem and give optimum solutions for the real-life physical layer. The proposed GABC algorithm incorporates the operators of the genetic algorithm (GA) i.e., crossover and mutation into the search process of the ABC algorithm. Additionally, the greedy selection feature is employed in GABC which significantly enhances the exploitation capabilities, leading to faster convergence, higher-quality solutions, and improved robustness. The performance of the proposed GABC algorithm is tested based on different parameters by comparing the results with GA, ABC and PSO algorithms. Experimental analysis indicates that the proposed GABC algorithm outperforms the compared algorithms. Therefore, the yielded solutions in terms of prompt responses help managers to expedite the production through intelligent decision-making based on customer demands.

Automatic Guided Vehicle Scheduling in Automated Container Terminals Based on a Hybrid Mode of Battery Swapping and Charging

Automatic guided vehicles (AGVs) in the horizontal area play a crucial role in determining the operational efficiency of automated container terminals (ACTs). To improve the operational efficiency of an ACT, it is essential to decrease the impact of battery capacity limitations on AGV scheduling. To address this problem, this paper introduces battery swapping and opportunity charging modes into the AGV system and proposes a new AGV scheduling problem considering the hybrid mode. Firstly, this study describes the AGV scheduling problem of the automated container terminals considering both loading and unloading tasks under the hybrid mode of battery swapping and charging. Thereafter, a mixed-integer programming model is established to minimize the sum of energy costs and delay costs. Secondly, an effective adaptive large neighborhood search algorithm is proposed to solve the problem, in which the initial solution construction, destroy operators, and repair operators are designed according to the hybrid mode. Finally, numerical experiments are conducted to analyze the effectiveness of the model and the optimization performance of the algorithm. The results demonstrate that the hybrid mode of battery swapping and charging can effectively reduce the number of battery swapping times and scheduling costs compared to the existing mode.

A design of intelligent AGV system combined with a robotic arm for flexible production lines

Unmanned mobile robots have broad application prospects in industrial production. With the continuous deepening of Industry 4.0, the complexity of manufacturing workflows has skyrocketed, and researching robots suitable for flexible production is becoming a focus of development. With the rapid development of computer technology and sensor technology, the ability of robots to obtain their own state and environmental information has also been greatly expanded. Studying the work, path planning, and obstacle avoidance of robots has important practical significance. This article designs a flexible production robot that integrates Automated Guided Vehicle (AGV) with industrial robots. It has the ability to perceive the environment, make optimal decisions, and operate independently. It can achieve functions such as mobile transportation, flexible operation, and human-machine interaction and cooperation in the production line. This article uses Gazebo to construct a production environment and simulate robot movement. In addition, MATLAB is used to conduct simulation experiments on the operation of the UR10 robot. The results and planning path map validate the feasibility and effectiveness of this method. The mobile robot designed in this article combines a robotic arm with an AGV, which has certain application value in future flexible manufacturing factories and provides a certain reference value for flexible production.

Multi-AGV Scheduling under Limited Buffer Capacity and Battery Charging Using Simulation Techniques

In recent years, automated guided vehicles (AGVs) have been widely adopted to automate material handling procedures in manufacturing shopfloors and distribution centers. AGV scheduling is the procedure of allocating a transportation task to an AGV, which has large impacts on the efficiency of an AGV system with multiple AGVs. In order to optimize the operations of multi-AGV systems, AGV scheduling decisions should be made with consideration of practical issues such as buffer space limitations and battery charging. However, previous studies have often overlooked those issues. To fill this gap, this paper proposes a simulation-based multi-AGV scheduling procedure for practical shopfloors with limited buffer capacity and battery charging. Furthermore, we propose three kinds of rules: job selection rules, AGV selection rules, and charging station selection rules, for AGV scheduling in practical shopfloors. The performance of the rules is evaluated through multi-scenario simulation experiments. The FlexSim software v.2022 is used to develop a simulation model for the experiments, and the experimental findings indicate that the job selection rules have larger impacts on the average waiting time than the other kinds of rules.

Navigating Unstructured Space: Deep Action Learning-Based Obstacle Avoidance System for Indoor Automated Guided Vehicles

Automated guided vehicles (AGVs) have become prevalent over the last decade. However, numerous challenges remain, including path planning, security, and the capacity to operate safely in unstructured environments. This study proposes an obstacle avoidance system that leverages deep action learning (DAL) to address these challenges and meet the requirements of Industry 4.0 for AGVs, such as speed, accuracy, and robustness. In the proposed approach, the DAL is integrated into an AGV platform to enhance its visual navigation, object recognition, localization, and decision-making capabilities. Then DAL itself was introduced to combine the work of You Only Look Once (YOLOv4), speeded-up robust features (SURF), and k-nearest neighbor (kNN) and AGV control in indoor visual navigation. The DAL system triggers SURF to differentiate two navigation images, and kNN is used to verify visual distance in real time to avoid obstacles on the floor while searching for the home position. The testing findings show that the suggested system is reliable and fits the needs of advanced AGV operations.

Simulation of Heuristics for Automated Guided Vehicle Task Sequencing with Resource Sharing and Dynamic Queues

Automated guided vehicles (AGVs) stand out as a paradigmatic application of Industry 4.0, requiring the seamless integration of new concepts and technologies to enhance productivity while reducing labor costs, energy consumption, and emissions. In this context, specific industrial use cases can present a significant technological and scientific challenge. This study was inspired by a real industrial application for which the existing AGV literature did not contain an already well-studied solution. The problem is related to the sequencing of assigned tasks, where the queue formation dynamics and the resource sharing define the scheduling. The combinatorial nature of the problem requires the use of advanced mathematical tools such as heuristics, simulations, or a combination of both. A heuristic procedure was developed that generates candidate task sequences, which are, in turn, evaluated in a discrete-event simulation model developed in Simul8. This combined approach allows high-quality solutions to be generated and realistically evaluated, even graphically, by stakeholders and decision makers. A number of computational experiments were developed to validate the proposed method, which opens up some future lines of research, especially when considering stochastic settings.