A Rapid Search Method for Scheduling Delivery of Multiple Automated Guided Vehicles

In this study, a method was developed to address the automated guided vehicle (AGV) transportation scheduling problem. For deliveries in factories and warehouses, it is necessary to quickly plan a feasible transportation schedule without delay within a specified time. This study focused on obtaining a transport schedule without delay from the specified time while maintaining the search for a better solution during the execution of the transport task. Accordingly, a method was developed for constructing a solution with a two-dimensional array of delivery tasks for each AGV, arranged in the order in which they are executed, as well as for searching for a schedule by performing exchange and insertion operations. For the exchange and insertion, a method that considers the connectivity between the end point of a task and the start point of the next task was adopted. To verify the effectiveness of the proposed method, numerical simulations were performed assuming an actual transportation task.

Concept of a Dual Energy Storage System for Sustainable Energy Supply of Automated Guided Vehicles

Due to the growing number of automated guided vehicles (AGVs) in use in industry, as well as the increasing demand for limited raw materials, such as lithium for electric vehicles (EV), a more sustainable solution for mobile energy storage in AGVs is being sought. This paper presents a dual energy storage system (DESS) concept, based on a combination of an electrical (supercapacitors) and an electro-chemical energy storage system (battery), used separately depending on the required transport distance. Each energy storage unit (ESU) in this DESS is capable of supplying the AGV completely. The concept takes into account requirements for a complex material flow as well as minimizing the energy storage capacity required for the operation of the AGV. An energy flow analysis is performed and further used as a basis to derive three possible circuit concepts for the technical realization. The circuit concepts are compared to other approaches from related work, differentiating the functionality to hybrid energy storage systems (HESS). The functionality of the concepts was validated by mapping the energy flow states to active circuit components. Finally, an approach for implementing the control strategy as a state machine is given, and conclusions for further investigations are drawn.

Techno-Economic Evaluation of 5G Technology for Automated Guided Vehicles in Production

The fifth generation of mobile communication (5G) is expected to bring immense benefits to automated guided vehicles by improving existing respectively enabling 5G-distinctive network control systems, leading to higher productivity and safety. However, only 1% of production companies have fully deployed 5G yet. Most companies currently lack an understanding of return on investment and of technical use-case benefits. Therefore, this paper analyses the influence of 5G on an automated guided vehicle use case based on a five-step evaluation model. The analysis is conducted with a use case in the Digital Experience Factory in Aachen. It shows a difference of net present value between 4G and 5G of 1.3 M€ after 10 years and a difference of return of investment of 66%. Furthermore, analysis shows an increase of mobility (13%), productivity (20%) and safety (136%). This indicates a noticeable improvement of a 5G-controlled automated guided vehicle compared to a 4G-controlled automated guided vehicle.

Human identification and tracking using ultra-wideband-vision data fusion in unstructured environments

<p class="Abstract">Nowadays, the importance of working in changing and unstructured environments such as logistics warehouses through the cooperation between Automated Guided Vehicles (AGV) and the operator is increasingly demanded. The challenge addressed in this article aims to solve two crucial functions of autonomy: operator identification, and tracking. These tasks are necessary to enable an AGV to follow the selected operator along his path. This paper presents an innovative, accurate, robust, autonomous, and low-cost operator real-time tracking system, leveraging the inherent complementarity of the uncertainty regions (2D ellipses) between ultra-wideband (UWB) transceivers and cameras. The test campaign shows how the UWB system has higher uncertainty in the angular direction. In contrast, in the case of the vision system, the uncertainty is predominant along the radial coordinate. Due to the nature of the data, a sensor fusion demonstrates improvement in the accuracy and goodness of the final tracking.</p>

Development of an IoT Architecture Based on a Deep Neural Network against Cyber Attacks for Automated Guided Vehicles

This paper introduces an integrated IoT architecture to handle the problem of cyber attacks based on a developed deep neural network (DNN) with a rectified linear unit in order to provide reliable and secure online monitoring for automated guided vehicles (AGVs). The developed IoT architecture based on a DNN introduces a new approach for the online monitoring of AGVs against cyber attacks with a cheap and easy implementation instead of the traditional cyber attack detection schemes in the literature. The proposed DNN is trained based on experimental AGV data that represent the real state of the AGV and different types of cyber attacks including a random attack, ramp attack, pulse attack, and sinusoidal attack that is injected by the attacker into the internet network. The proposed DNN is compared with different deep learning and machine learning algorithms such as a one dimension convolutional neural network (1D-CNN), a supported vector machine model (SVM), random forest, extreme gradient boosting (XGBoost), and a decision tree for greater validation. Furthermore, the proposed IoT architecture based on a DNN can provide an effective detection for the AGV status with an excellent accuracy of 96.77% that is significantly greater than the accuracy based on the traditional schemes. The AGV status based on the proposed IoT architecture with a DNN is visualized by an advanced IoT platform named CONTACT Elements for IoT. Different test scenarios with a practical setup of an AGV with IoT are carried out to emphasize the performance of the suggested IoT architecture based on a DNN. The results approve the usefulness of the proposed IoT to provide effective cybersecurity for data visualization and tracking of the AGV status that enhances decision-making and improves industrial productivity.

Scheduling of AGVs in Automated Container Terminal Based on the Deep Deterministic Policy Gradient (DDPG) Using the Convolutional Neural Network (CNN)

In order to improve the horizontal transportation efficiency of the terminal Automated Guided Vehicles (AGVs), it is necessary to focus on coordinating the time and space synchronization operation of the loading and unloading of equipment, the transportation of equipment during the operation, and the reduction in the completion time of the task. Traditional scheduling methods limited dynamic response capabilities and were not suitable for handling dynamic terminal operating environments. Therefore, this paper discusses how to use delivery task information and AGVs spatiotemporal information to dynamically schedule AGVs, minimizes the delay time of tasks and AGVs travel time, and proposes a deep reinforcement learning algorithm framework. The framework combines the benefits of real-time response and flexibility of the Convolutional Neural Network (CNN) and the Deep Deterministic Policy Gradient (DDPG) algorithm, and can dynamically adjust AGVs scheduling strategies according to the input spatiotemporal state information. In the framework, firstly, the AGVs scheduling process is defined as a Markov decision process, which analyzes the system’s spatiotemporal state information in detail, introduces assignment heuristic rules, and rewards the reshaping mechanism in order to realize the decoupling of the model and the AGVs dynamic scheduling problem. Then, a multi-channel matrix is built to characterize space–time state information, the CNN is used to generalize and approximate the action value functions of different state information, and the DDPG algorithm is used to achieve the best AGV and container matching in the decision stage. The proposed model and algorithm frame are applied to experiments with different cases. The scheduling performance of the adaptive genetic algorithm and rolling horizon approach is compared. The results show that, compared with a single scheduling rule, the proposed algorithm improves the average performance of task completion time, task delay time, AGVs travel time and task delay rate by 15.63%, 56.16%, 16.36% and 30.22%, respectively; compared with AGA and RHPA, it reduces the tasks completion time by approximately 3.10% and 2.40%.