Transporte multi-AGV de una carga: estado del arte y propuesta centralizada

Santos

2022

Expert Systems

Section: Introductionmentioning

confidence: 99%

Combining reinforcement learning and conventional control to improve automatic guided vehicles tracking of complex trajectories

Santos

2022

Expert Systems

“…Un área fuera del ámbito de este trabajo es el problema de los multi-AGVs, y los retos asociados de coordinación, navegación, control, planificación de rutas, etc (Yuan et al, 2020;Espinosa, Santos, & Sierra-García, 2021;Guney & Raptis, 2020).…”

Section: Estado Del Arteunclassified

“…En el ámbito industrial se utilizan con frecuencia Vehículos de Guiado Automático (AGV) para el transporte de mercancía puntual, normalmente sustituyendo a los medios de transporte manuales o a las cintas transportadoras, para reducir costes operativos y errores humanos (Wu, 2019;Espinosa, Santos, Sierra-García, 2021;Abderrahim et al, 2020).…”

Section: Introductionunclassified

Modelado de un AGV híbrido triciclo-diferencial

Sánchez

Rev. iberoam. autom. inform. ind.

Santos

2021

En el ámbito industrial se utilizan con frecuencia Vehículos de Guiado Automático (AGV) para el transporte de mercancía puntual, normalmente sustituyendo a los medios de transporte manuales o a las cintas transportadoras, para así reducir costes operativos y errores humanos. Para aumentar el rendimiento de estos sistemas industriales y que puedan realizar funcionalidades más avanzadas, es fundamental desarrollar modelos orientados al control que permitan probar nuevas estrategias y técnicas de control que los hagan más eficientes y seguros. Para ello, en este trabajo se desarrolla un modelo cinemático y dinámico orientado al control de un AGV. El principal objetivo del trabajo es conseguir una representación matemática de la compleja dinámica del AGV Easybot, un vehículo híbrido triciclo-diferencial, que permita estudiar los efectos de carga remolcada y la interacción rueda-suelo. Para ello se ha desarrollado el modelo cinemático de la parte diferencial y del triciclo, y se han combinado ambos entre sí y con el desarrollo de la dinámica del vehículo. Se ha descompuesto el AGV en sus distintos módulos y se han aplicado las ecuaciones de Newton-Euler para obtener las ecuaciones de su comportamiento dinámico. El modelo se ha validado en simulación para diferentes trayectorias, variando la carga y la velocidad.

“…They are widely applied to transport parts and assets in industrial manufacturing processes and automotive assembly plants, among others. The ability to control these AGVs remotely has increased the flexibility and safety of the logistic solutions, thus, allowing operators to manage multiple vehicles simultaneously in a centralized and reactive manner [ 12 ]. However, to make it possible, a reliable communication system with minimum latency for multiple AGVs is required.…”

Section: Introductionmentioning

confidence: 99%

Transformers for Multi-Horizon Forecasting in an Industry 4.0 Use Case

Vakaruk

Karamchandani

et al. 2023

Sensors

Recently, a novel approach in the field of Industry 4.0 factory operations was proposed for a new generation of automated guided vehicles (AGVs) that are connected to a virtualized programmable logic controller (PLC) via a 5G multi-access edge-computing (MEC) platform to enable remote control. However, this approach faces a critical challenge as the 5G network may encounter communication disruptions that can lead to AGV deviations and, with this, potential safety risks and workplace issues. To mitigate this problem, several works have proposed the use of fixed-horizon forecasting techniques based on deep-learning models that can anticipate AGV trajectory deviations and take corrective maneuvers accordingly. However, these methods have limited prediction flexibility for the AGV operator and are not robust against network instability. To address this limitation, this study proposes a novel approach based on multi-horizon forecasting techniques to predict the deviation of remotely controlled AGVs. As its primary contribution, the work presents two new versions of the state-of-the-art transformer architecture that are well-suited to the multi-horizon prediction problem. We conduct a comprehensive comparison between the proposed models and traditional deep-learning models, such as the long short-term memory (LSTM) neural network, to evaluate the performance and capabilities of the proposed models in relation to traditional deep-learning architectures. The results indicate that (i) the transformer-based models outperform LSTM in both multi-horizon and fixed-horizon scenarios, (ii) the prediction accuracy at a specific time-step of the best multi-horizon forecasting model is very close to that obtained by the best fixed-horizon forecasting model at the same step, (iii) models that use a time-sequence structure in their inputs tend to perform better in multi-horizon scenarios compared to their fixed horizon counterparts and other multi-horizon models that do not consider a time topology in their inputs, and (iv) our experiments showed that the proposed models can perform inference within the required time constraints for real-time decision making.