Automated Guided Vehicle (AGV)

Assembly Line

Autonomous intralogistics from indoors to outdoors for a safe and seamless logistics chain

A simulation-based approach to design an automated high-mix low-volume manufacturing system


Authors: Koen Herps, Quang-Vinh Dang, Tugce Martagan, Ivo Adan

Topics: Simulation, Simulated Annealing, Automated Guided Vehicle

Organizations: Eindhoven University of Technology

In this paper, we address the profit optimization problem of an automated high-mix low-volume manufacturing system, which originates from a real-world problem at our industry partner. The manufacturing system includes buffer units from which jobs are automatically transported to workstations, i.e., using automated material handling devices. We consider three different automation concepts for the system: (1) a configuration with parallel buffers and a dedicated robot to work them, (2) a configuration that employs shared buffers that are tended to by automated guided vehicles (AGVs), and (3) a proposed hybrid configuration that takes elements of both aforementioned configurations. We propose a simulation-based approach, which uses simulated-annealing (SA), enriched with the reduced variable neighborhood search (RVNS), to determine the best system configuration for a high-mix, low-volume manufacturer. Decisions concern the choice of automation equipment and the capacity of both parallel and shared buffers. We illustrate the efficacy of the proposed hybrid concept and the proposed SA-RVNS approach with an industry case study using real-world data from our industry partner. Our analysis shows that the proposed concept increases the profit by around 10–30% compared to the others, and the AGV travel time plays an important factor in the proposed concept to yield its true potential.

Read more at ScienceDirect

Action-limited, multimodal deep Q learning for AGV fleet route planning


Author: Hang Liu

Topics: Automated Guided Vehicle, Reinforcement Learning

Organizations: Hitachi

In traditional operating models, a navigation system completes all calculations i.e., the shortest path planning in a static environment, before the AGVs start moving. However, due to constant incoming offers, changes in vehicle availability, etc., this creates a huge and intractable optimization problem. Meanwhile, an optimal navigation strategy for an AGV fleet cannot be achieved if it fails to consider the fleet and delivery situation in real-time. Such dynamic route planning is more realistic and must have the ability to autonomously learn the complex environments. Deep Q network (DQN), that inherits the capabilities of deep learning and reinforcement learning, provides a framework that is well prepared to make decisions for discrete motion sequence problems.

Read more at Industrial AI Blog

MiR robots improve productivity at Faurecia

AGV and AMR: What is the Actual Difference?


Topics: automated guided vehicle, autonomous mobile robot, intralogistics

Organizations: SYNOAS

In logistics centers and production halls, there are always a lot of pallets, crates, mesh boxes, racks and numerous other objects that must be transported. This task can be accomplished by forklifts with human operators behind the steering wheel. Increasingly, driverless transport systems (DTS) are being used to move goods autonomously from A to B.

These driverless transport vehicles include Automated Guided Vehicles (AGVs) and Autonomous Mobile Robots (AMRs). Although they both accomplish the same tasks, these abbreviations should not be used synonymously: the two vehicle types are different and each of them has specific characteristics.

The A in AGV stands for Automated, while the A in AMR stands for Autonomous: a small difference with major significance. As the name suggests, AMRs operate autonomously, for instance by evading obstacles that suddenly block their path. On the other hand, AGVs travel on fixed routes and can only accomplish pre-defined tasks by following automated instructions. In contrast, AMRs make their own decisions when a situation requires.

Read more at SYNAOS Blog

Start-ups Powering New Era of Industrial Robotics


Author: James Falkoff

Topics: robotics, automated guided vehicle, machine learning

Vertical: Machinery

Organizations: Ready Robotics, ArtiMinds, Realtime Robotics, RIOS, Vicarious

Much of the bottleneck to achieving automation in manufacturing relates to limitations in the current programming model of industrial robotics. Programming is done in languages proprietary to each robotic hardware OEM – languages “straight from the 80s” as one industry executive put it.

There are a limited number of specialists who are proficient in these languages. Given the rarity of the expertise involved, as well as the time it takes to program a robot, robotics application development typically costs three times as much as the hardware for a given installation.

Read more at Robotics Business Review

Highly flexible AGV solution in truck cabin production

Autonomous automation: Mobile robot system HelMo at Electrical Connectors