TY - GEN
T1 - Digital Twin-Driven Reinforcement Learning for Dynamic Path Planning of AGV Systems
AU - Lee, Donggun
AU - Kang, Yong Shin
AU - Do Noh, Sang
AU - Kim, Jaeung
AU - Kim, Hijun
N1 - Publisher Copyright:
© IFIP International Federation for Information Processing 2024.
PY - 2024
Y1 - 2024
N2 - With the digitalization of industries, manufacturing systems are becoming increasingly complex and diverse. There is a growing focus on production flexibility and automation, leading to active research on production logistics (PL) systems that can effectively address these challenges. PL systems significantly influences the quality and productivity of products, and the proper design and optimization of path planning for logistics robots are crucial. This paper proposes a novel approach, Digital Twin (DT)-driven reinforcement learning (RL) for dynamic path planning of automated guided vehicles (AGVs) systems. The complex real-world path planning problem is represented as a Markov Decision Process (MDP) and a DT-based Q learning algorithm that can solve the represented path planning problem is proposed. To validate the effectiveness and adaptability of the proposed approach, a system is implemented and applied to an actual manufacturing site.
AB - With the digitalization of industries, manufacturing systems are becoming increasingly complex and diverse. There is a growing focus on production flexibility and automation, leading to active research on production logistics (PL) systems that can effectively address these challenges. PL systems significantly influences the quality and productivity of products, and the proper design and optimization of path planning for logistics robots are crucial. This paper proposes a novel approach, Digital Twin (DT)-driven reinforcement learning (RL) for dynamic path planning of automated guided vehicles (AGVs) systems. The complex real-world path planning problem is represented as a Markov Decision Process (MDP) and a DT-based Q learning algorithm that can solve the represented path planning problem is proposed. To validate the effectiveness and adaptability of the proposed approach, a system is implemented and applied to an actual manufacturing site.
KW - Automated Guided Vehicles (AGVs)
KW - Digital Twin (DT)
KW - Digital Twin (DT)-driven Reinforcement Learning (RL)
KW - Dynamic Path Planning
KW - Q-learning
KW - Reinforcement Learning (RL)
UR - https://www.scopus.com/pages/publications/85204643622
U2 - 10.1007/978-3-031-71633-1_25
DO - 10.1007/978-3-031-71633-1_25
M3 - Conference contribution
AN - SCOPUS:85204643622
SN - 9783031716324
T3 - IFIP Advances in Information and Communication Technology
SP - 351
EP - 365
BT - Advances in Production Management Systems. Production Management Systems for Volatile, Uncertain, Complex, and Ambiguous Environments - 43rd IFIP WG 5.7 International Conference, APMS 2024, Proceedings
A2 - Thürer, Matthias
A2 - Riedel, Ralph
A2 - von Cieminski, Gregor
A2 - Romero, David
PB - Springer Science and Business Media Deutschland GmbH
T2 - 43rd IFIP WG 5.7 International Conference on Advances in Production Management Systems, APMS 2024
Y2 - 8 September 2024 through 12 September 2024
ER -
