Deep reinforcement learning based AGVs real-time scheduling with mixed rule for flexible shop floor in industry 4.0
زمانبندی مبتنی بر یادگیری تقویتی عمیق مبتنی بر AGV با قاعده مختلط برای کف انعطاف پذیر در صنعت 4.0-2020
Driven by the recent advances in industry 4.0 and industrial artificial intelligence, Automated Guided Vehicles (AGVs) has been widely used in flexible shop floor for material handling. However, great challenges aroused by the high dynamics, complexity, and uncertainty of the shop floor environment still exists on AGVs real-time scheduling. To address these challenges, an adaptive deep reinforcement learning (DRL) based AGVs real-time scheduling approach with mixed rule is proposed to the flexible shop floor to minimize the makespan and delay ratio. Firstly, the problem of AGVs real-time scheduling is formulated as a Markov Decision Process (MDP) in which state representation, action representation, reward function, and optimal mixed rule policy, are described in detail. Then a novel deep q-network (DQN) method is further developed to achieve the optimal mixed rule policy with which the suitable dispatching rules and AGVs can be selected to execute the scheduling towards various states. Finally, the case study based on a real-world flexible shop floor is illustrated and the results validate the feasibility and effectiveness of the proposed approach.
Keywords: Automated guided vehicles | Real-time scheduling | Deep reinforcement learning | Industry 4.0
Sustainable supply chain management in the digitalisation era: The impact of Automated Guided Vehicles
مدیریت زنجیره تامین پایدار در دوران دیجیتالیزاسیون: تاثیر وسایل نقلیه راهنمایی خودکار-2017
Internationalization of markets and climate change introduce multifaceted challenges for modern supply chain (SC) management in the todays digitalisation era. On the other hand, Automated Guided Vehicle (AGV) systems have reached an age of maturity that allows for their utilization towards tackling dynamic market conditions and aligning SC management focus with sustainability considerations. However, extant research only myopically tackles the sustainability potential of AGVs, focusing more on addressing network optimization problems and less on developing integrated and systematic methodological ap proaches for promoting economic, environmental and social sustainability. To that end, the present study provides a critical taxonomy of key decisions for facilitating the adoption of AGV systems into SC design and planning, as these are mapped on the relevant strategic, tactical and operational levels of the natural hierarchy. We then propose the Sustainable Supply Chain Cube (S2C2), a conceptual tool that integrates sustainable SC management with the proposed hierarchical decision-making framework for AGVs. Market opportunities and the potential of integrating AGVs into a SC context with the use of the S2C2 tool are further discussed.
Keywords:Automated Guided Vehicles |Sustainable supply chain management| Literature taxonomy| Decision-making framework |Sustainable Supply Chain Cube (S2C2) tool