Filters








20,876 Hits in 8.9 sec

Decentralized Multi-AGV Task Allocation based on Multi-Agent Reinforcement Learning with Information Potential Field Rewards [article]

Mengyuan Li, Bin Guo, Jiangshan Zhang, Jiaqi Liu, Sicong Liu, Zhiwen Yu, Zhetao Li, Liyao Xiang
2021 arXiv   pre-print
However, the traditional centralized approaches make high demands on the control center's computing power and real-time capability.  ...  Automated Guided Vehicles (AGVs) have been widely used for material handling in flexible shop floors. Each product requires various raw materials to complete the assembly in production process.  ...  The multi-variety, small-batch, and customized production mode results in more logistics tasks and higher real-time demands.  ... 
arXiv:2108.06886v1 fatcat:ldu7xvqkfjej7mrezgjjsdus7a

Context and implications of learning in Evolvable Production Systems

Pedro Neves, Joao Ferreira, Mauro Onori, Jose Barata
2011 IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society  
This paper presents an exploratory discussion on the topic of agent-based learning applied in a modern production paradigm such as Evolvable Production Systems (EPS). I.  ...  Modular and distributed control structures are nowadays a consensual way, common to the majority of modern paradigms, to deal with unpredictability and volatility of markets.  ...  It introduces an adaptive control approach that evolves in time to achieve a combination between global production optimization and agile reaction to disturbances.  ... 
doi:10.1109/iecon.2011.6119745 fatcat:y4huu6oqw5gbpak5teyxvj46me

Cooperative control in production and logistics

László Monostori, Paul Valckenaers, Alexandre Dolgui, Hervé Panetto, Mietek Brdys, Balázs Csanád Csáji
2015 Annual Reviews in Control  
Two case studies are also discussed: i) a holonic, PROSA-based approach to generate short-term forecasts for an additive manufacturing system by means of a delegate multi-agent system (D-MAS); and ii)  ...  Standard results as well as recent advances from control theory, through cooperative game theory, distributed machine learning to holonic systems, cooperative enterprise modelling, system integration,  ...  ACKNOWLEDGMENTS The authors from Hungary express their thanks to the Hungarian Scientific Research Fund (OTKA) for its support (Project No.: 113038).  ... 
doi:10.1016/j.arcontrol.2015.03.001 fatcat:jiowstx4dvd3phmbxrhy37fr2a

Cooperative Control in Production and Logistics

László Monostori, Paul Valckenaers, Alexandre Dolgui, Hervé Panetto, Mietek Brdys, Balázs Csanád Csáji
2014 IFAC Proceedings Volumes  
Two case studies are also discussed: i) a holonic, PROSA-based approach to generate short-term forecasts for an additive manufacturing system by means of a delegate multi-agent system (D-MAS); and ii)  ...  Standard results as well as recent advances from control theory, through cooperative game theory, distributed machine learning to holonic systems, cooperative enterprise modelling, system integration,  ...  ACKNOWLEDGMENTS The authors from Hungary express their thanks to the Hungarian Scientific Research Fund (OTKA) for its support (Project No.: 113038).  ... 
doi:10.3182/20140824-6-za-1003.01026 fatcat:kcbnlnahgjajfbtzqdq2y4ljim

Cooperative Control of Mobile Robots with Stackelberg Learning [article]

Joewie J. Koh, Guohui Ding, Christoffer Heckman, Lijun Chen, Alessandro Roncone
2020 arXiv   pre-print
To accomplish this goal, we propose a method named SLiCC: Stackelberg Learning in Cooperative Control.  ...  Using a bi-robot cooperative object transportation problem, we validate the performance of SLiCC against centralized multi-agent Q-learning and demonstrate that SLiCC achieves better combined utility.  ...  ACKNOWLEDGMENT We thank the anonymous reviewers and our colleagues for their insightful comments and suggestions which helped improve this manuscript.  ... 
arXiv:2008.00679v1 fatcat:ql2djgialbdzxidorg7uma7jka

MSDF: A Deep Reinforcement Learning Framework for Service Function Chain Migration [article]

Ruoyun Chen, Hancheng Lu, Yujiao Lu, Jinxue Liu
2019 arXiv   pre-print
Further, a novel multi-agent cooperative framework, called MSDF, is proposed to address the challenge of considering multiple SFC migration on the basis of single SFC migration.  ...  In this paper, we formulate the SFC migration problem as a minimization problem with the objective of total network operation cost under constraints of users' quality of service.  ...  The other one is the RM [6] , which performs real-time migration with the target to reduce the end-to-end delay of SFCs under the resource constraint of function nodes.  ... 
arXiv:1911.04801v2 fatcat:ryh3mxy6djggzpff6j6jicimmu

A holonic approach to dynamic manufacturing scheduling

Paulo Leitão, Francisco Restivo
2008 Robotics and Computer-Integrated Manufacturing  
In this scheduling and control approach, the scheduling mechanism evolves dynamically to combine optimized scheduling, achieved by central entities, and distributed scheduling, improving its responsiveness  ...  This paper presents a holonic approach to manufacturing scheduling, which in opposite to traditional approaches, distributes the scheduling functions over several entities, combining their calculation  ...  It achieves optimal local schedule plans, but due to the lack of global information, may not lead to an optimal global schedule.  ... 
doi:10.1016/j.rcim.2007.09.005 fatcat:4vjfchjo5fd33ji6nox6tftpay

An adaptive real-time scheduling method for flexible job shop scheduling problem with combined processing constraint

Haihua Zhu, Ming Chen, Zequn Zhang, Dunbing Tang
2019 IEEE Access  
On this basis, a novel adaptive real-time scheduling method for MAS is further proposed for better adaptability and performance.  ...  In this approach, the scheduling process is modeled as contextual bandit, so that each job agent can select the most suitable dispatching rules according to the environment state after learning to achieve  ...  FLEXIBLE JOB SHOP SCHEDULING PROBLEM This paper is to evaluate an adaptive real-time scheduling method for FJSP with combined processing constraint.  ... 
doi:10.1109/access.2019.2938548 fatcat:7b7xcgt2ufej5hx74kqstp6sx4

Collaborative control theory for e-Work, e-Production, and e-Service

S.Y. Nof
2007 Annual Reviews in Control  
The purpose of this article is to review design principles and collaborative control theory guiding these new developments.  ...  Recent developments in collaborative control theory and e-Work influence the emergence of e-Production and e-Service.  ...  Special thanks to my colleagues and students at the PRISM Lab and the PRISM Global Research Network, and in IFAC Committee CC5 for Manufacturing and Logistics Systems, who have collaborated with me to  ... 
doi:10.1016/j.arcontrol.2007.08.002 fatcat:qz7f57t335gbfmtsqz624geh3m

A multi-agent based system with big data processing for enhanced supply chain agility

Mihalis Giannakis, Michalis Louis
2016 Journal of Enterprise Information Management  
Practical implications: The proposed information system provides integrated capabilities for production, supply chain event and disruption risk management under a collaborative basis Originality/value.  ...  Research limitations/implications: The study shows how the multi-agent systems can assist to overcome the trade-off between supply chain agility and complexity of global supply chains.  ...  Under the constraints of production and supplier lead times, production capacity (Pc), and customer's required delivery time (Dt), it generates the production plan.  ... 
doi:10.1108/jeim-06-2015-0050 fatcat:tjr4wksbxbedbjlbeqbvdlxd6q

Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication [article]

Jianyu Su, Stephen Adams, Peter A. Beling
2020 arXiv   pre-print
In this study, we develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent.  ...  We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment.  ...  One challenge of MARL is the uncertainty of other agents' strategies through out the training process, making it hard for agents to understand the inter-plays and achieve cooperation.  ... 
arXiv:2004.00470v2 fatcat:4jzk2hjmxzempnjs5wfwn5lgci

Energy Management Based on Multi-Agent Deep Reinforcement Learning for A Multi-Energy Industrial Park [article]

Dafeng Zhu, Bo Yang, Yuxiang Liu, Zhaojian Wang, Kai Ma, Xinping Guan
2022 arXiv   pre-print
A novel reward is designed by Lagrange multiplier method to ensure the capacity constraints of energy storage.  ...  contributing agents to learn better policies, soft actor-critic for improving robustness and exploring optimal solutions.  ...  In addition to observation, the state also contains the time and energy price. • Action: For battery agent, its task is to control the charging or discharging state of the battery, which should comply  ... 
arXiv:2202.03771v1 fatcat:vvohb5g5vvba3ioz3cih6tyeim

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey [article]

Tianxu Li, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Qihui Wu, Yang Zhang, Bing Chen
2022 arXiv   pre-print
The issues consist of network access, transmit power control, computation offloading, content caching, packet routing, trajectory design for UAV-aided networks, and network security issues.  ...  Each entity may need to make its local decision to improve the network performance under dynamic and uncertain network environments.  ...  As a consequence, QMIX estimates the global Q-function by inputting the individual Q-functions of each agent to a designed mixing network under the defined monotonicity constraint in order to make the  ... 
arXiv:2110.13484v2 fatcat:u2o5uxms65gmnp3q7xbh35l5oi

Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review

Ioannis Antonopoulos, Valentin Robu, Benoit Couraud, Desen Kirli, Sonam Norbu, Aristides Kiprakis, David Flynn, Sergio Elizondo-Gonzalez, Steve Wattam
2020 Renewable & Sustainable Energy Reviews  
Acknowledgements The authors would like to acknowledge the support of the Energy Technology Partnership Scotland (ETP) through their Industry Doctorates scheme and our industrial sponsor Upside Energy.  ...  [287] 2018 Approximate Q-learning Residential EV charging management system under real-time electricity pricing scheme. Design of pricing/incentive schemes 29 Liyan Jia et al.  ...  consumption in a DR scenario for real-time pricing.  ... 
doi:10.1016/j.rser.2020.109899 fatcat:wgpj4awq35dfzdq7ugumtrvo7q

Adaptive scheduling based on self-organized holonic swarm of schedulers

Paulo Leitao, Jose Barbosa
2014 2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE)  
In particular, in the ramp-up phase of small lot-sizes of complex products, scheduling is more demanding, e.g. due to late requests and immature technology products and processes.  ...  This paper presents the principles of a distributed scheduling architecture based on holonic and swarm principles and implemented using multi-agent system technology.  ...  ACKNOWLEDGMENTS The research leading to these results has received funding from the European Union Seventh Framework Programme FP7 ARUM project, under grant agreement n° 314056.  ... 
doi:10.1109/isie.2014.6864872 dblp:conf/isie/LeitaoB14 fatcat:lmsut7jghredbkvztfplgeb4be
« Previous Showing results 1 — 15 out of 20,876 results