AI Plannig and Scheduling are a classical problem of Artificial Intelligene. It is a highlight of AI for it' s significance in many application domains. Recenctly,dramatic advances have been made in this field. In...AI Plannig and Scheduling are a classical problem of Artificial Intelligene. It is a highlight of AI for it' s significance in many application domains. Recenctly,dramatic advances have been made in this field. In this paper,we introduce our study on Graphplan which is one of the best methods and it's descendent technologys. First,we will analyse Graphplan's algorithm and it's key for success, then briefly introduce it's descendants,at the end of the paper,we suggest areas for future research.展开更多
Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined pr...Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined problems in need of attention in AGV applications comprehensively.In this paper,several key issues and essential models are presented.First,the advantages and disadvantages of centralized and decentralized AGVs systems were compared;second,warehouse layout and operation optimization were introduced,including some omitted areas,such as AGVs fleet size and electrical energy management;third,AGVs scheduling algorithms in chessboardlike environments were analyzed;fourth,the classical route-planning algorithms for single AGV and multiple AGVs were presented,and some Artificial Intelligence(AI)-based decision-making algorithms were reviewed.Furthermore,a novel idea for accelerating route planning by combining Reinforcement Learning(RL)andDijkstra’s algorithm was presented,and a novel idea of the multi-AGV route-planning method of combining dynamic programming and Monte-Carlo tree search was proposed to reduce the energy cost of systems.展开更多
文摘AI Plannig and Scheduling are a classical problem of Artificial Intelligene. It is a highlight of AI for it' s significance in many application domains. Recenctly,dramatic advances have been made in this field. In this paper,we introduce our study on Graphplan which is one of the best methods and it's descendent technologys. First,we will analyse Graphplan's algorithm and it's key for success, then briefly introduce it's descendants,at the end of the paper,we suggest areas for future research.
文摘Automated Guided Vehicles(AGVs)have been introduced into various applications,such as automated warehouse systems,flexible manufacturing systems,and container terminal systems.However,few publications have outlined problems in need of attention in AGV applications comprehensively.In this paper,several key issues and essential models are presented.First,the advantages and disadvantages of centralized and decentralized AGVs systems were compared;second,warehouse layout and operation optimization were introduced,including some omitted areas,such as AGVs fleet size and electrical energy management;third,AGVs scheduling algorithms in chessboardlike environments were analyzed;fourth,the classical route-planning algorithms for single AGV and multiple AGVs were presented,and some Artificial Intelligence(AI)-based decision-making algorithms were reviewed.Furthermore,a novel idea for accelerating route planning by combining Reinforcement Learning(RL)andDijkstra’s algorithm was presented,and a novel idea of the multi-AGV route-planning method of combining dynamic programming and Monte-Carlo tree search was proposed to reduce the energy cost of systems.
