Filters








61 Hits in 5.5 sec

Neural Flocking: MPC-based Supervised Learning of Flocking Controllers [article]

Shouvik Roy, Usama Mehmood, Radu Grosu, Scott A. Smolka, Scott D. Stoller, Ashish Tiwari
2020 arXiv   pre-print
By learning a symmetric distributed neural flocking controller from a centralized MPC-based flocking controller, we achieve the best of both worlds: the neural controllers have high performance (on par  ...  Our approach is based on supervised learning, with the centralized controller providing the training data to the learning agent, i.e., the synthesized distributed controller.  ...  In this paper, we present Neural Flocking (NF), a new approach to the flocking problem that uses Supervised Learning to learn a symmetric and fully distributed flocking controller from a centralized MPC-based  ... 
arXiv:1908.09813v2 fatcat:rbz3y7vdo5hjdatwjia65majzm

Neural Flocking: MPC-Based Supervised Learning of Flocking Controllers [chapter]

Usama Mehmood, Shouvik Roy, Radu Grosu, Scott A. Smolka, Scott D. Stoller, Ashish Tiwari
2020 Lecture Notes in Computer Science  
By learning a symmetric and distributed neural flocking controller from a centralized MPC-based one, we achieve the best of both worlds: the neural controllers have high performance (on par with the MPC  ...  Our approach is based on Supervised Learning, with the centralized controller providing the training data, in the form of trajectories of state-action pairs.  ...  Flocking: MPC-based Supervised Learning of Flocking Controllers  ... 
doi:10.1007/978-3-030-45231-5_1 fatcat:blmtsikgc5d2xilfwicx4dym5e

Machine Learning Methods for Management UAV Flocks - a Survey

Rina Azoulay, Yoram Haddad, Shulamit Reches
2021 IEEE Access  
For each issue, we survey several machine learning-based methods that have been suggested in the literature to handle the associated challenges.  ...  Several computational challenges arise in UAV flock management, which can be solved by using machine learning (ML) methods.  ...  Flocking control can be performed by the learning-based model predictive control (LBMPC), developed by Aswani et al. [10] .  ... 
doi:10.1109/access.2021.3117451 fatcat:f6xli6srencw3ezqg5fyzwmuie

Iterative Learning for Model Reactive Control: Application to Autonomous Multi-agent Control

Omar Shrit, David Filliat, Michele Sebag
2021 2021 7th International Conference on Automation, Robotics and Applications (ICARA)  
In this paper, a decentralized autonomous controller aimed to control a fleet of quadrotors is designed, based on the iterative generation and exploitation of logged traces.  ...  In the exploitation phase, a policy is learned from the traces generated in the previous phase, and the policy is iteratively refined, to achieve a robust reactive control of each quadrotor agent.  ...  and the GNN is replaced by supervised learning neural network.  ... 
doi:10.1109/icara51699.2021.9376454 fatcat:kej7zblnunelbc4wiggigdk5vy

Fifth-Generation District Heating and Cooling Substations: Demand Response with Artificial Neural Network-Based Model Predictive Control

Simone Buffa, Anton Soppelsa, Mauro Pipiciello, Gregor Henze, Roberto Fedrizzi
2020 Energies  
This work presents new strategies for improving the operation of these energy transfer stations by means of a model predictive control (MPC) method based on recurrent artificial neural networks.  ...  The results show that, under simple time-of-use utility rates, the advanced controller outperforms a rule-based controller for smart charging of the domestic hot water (DHW) thermal energy storage under  ...  neural network-based model predictive control (ANN-MPC).  ... 
doi:10.3390/en13174339 fatcat:dwejhyvxgfbhpk2zoqbvtvevh4

Learning Distributed Controllers for V-Formation [article]

Shouvik Roy, Usama Mehmood, Radu Grosu, Scott A. Smolka, Scott D. Stoller, Ashish Tiwari
2020 arXiv   pre-print
over the MPC-based controller.  ...  We show how a high-performing, fully distributed and symmetric neural V-formation controller can be synthesized from a Centralized MPC (Model Predictive Control) controller using Deep Learning.  ...  We employ Supervised Learning to train our neural controller with the trajectories obtained from CAMPC.  ... 
arXiv:2006.00680v1 fatcat:cwjdumrjojeqthni6iocxlvs64

Formation Control for a Fleet of Autonomous Ground Vehicles: A Survey

Aakash Soni, Huosheng Hu
2018 Robotics  
At present, most of the developments target standalone autonomous vehicles, which can sense the surroundings and control the vehicle based on this perception, with limited or no driver intervention.  ...  In other words, many distributed and decentralized approaches of vehicle formation control are studied and their implementations are discussed.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/robotics7040067 fatcat:wo7eomrs75dmleum5o6tvltgmu

Thorough state-of-the-art analysis of electric and hybrid vehicle powertrains: Topologies and integrated energy management strategies

Dai-Duong Tran, Majid Vafaeipour, Mohamed El Baghdadi, Ricardo Barrero, Joeri Van Mierlo, Omar Hegazy
2019 Renewable & Sustainable Energy Reviews  
Achieving an energy-efficient powertrain requires tackling several conflicting control objectives such as the drivability, fuel economy, reduced emissions, and battery state of charge preservation, which  ...  A R T I C L E I N F O Keywords: Plug-in hybrid electric vehicle Full-electric vehicle Energy management strategy optimisation Online EMS Offline EMS Optimal control strategy A B S T R A C T Hybrid and  ...  We also acknowledge Flanders Make and VLAIO for the support of our research group.  ... 
doi:10.1016/j.rser.2019.109596 fatcat:ybks774km5htvb6f7foyetum7m

Recent Advances in Formations of Multiple Robots

Saar Cohen, Noa Agmon
2021 Current Robotics Reports  
new architectures and tools (e.g., ML-based formation control).  ...  For instance, consensus-based control and collision avoidance are usually intertwined together for the sake of reaching a consensus in a manner which is collision-free.  ...  The three basic machine learning paradigms of supervised learning, unsupervised learning and reinforcement learning are widely utilized for the sake of formation creation and maintaining it.  ... 
doi:10.1007/s43154-021-00049-2 fatcat:xu4xzhaqpvduljk6pvf34z6fva

Virtual Inertia Control Methods in Islanded Microgrids

Vjatseslav Skiparev, Ram Machlev, Nilanjan Roy Chowdhury, Yoash Levron, Eduard Petlenkov, and Juri Belikov
2021 Energies  
Some of the reviewed methods are the coefficient diagram method, H-infinity-based methods, reinforcement-learning-based methods, practical-swarm-based methods, fuzzy-logic-based methods, and model-predictive  ...  Among the numerous studies on frequency stability, one key approach is based on integrating an additional loop with virtual inertia control, designed to mimic the behavior of traditional synchronous machines  ...  Reinforcement Learning-Based Controller Reinforcement learning (RL) is an agent-based and model-free machine learning algorithm [84] .  ... 
doi:10.3390/en14061562 fatcat:6fcls2c75nfwfkvvzxnfobxxfy

Towards Self-Aware Multirotor Formations

Dennis Kaiser, Veronika Lesch, Julian Rothe, Michael Strohmeier, Florian Spieß, Christian Krupitzer, Sergio Montenegro, Samuel Kounev
2020 Computers  
The evaluation of this work shows that the proposed framework is able to use self-awareness to learn about its environment, avoid obstacles, and can successfully move a platoon of drones through multiple  ...  Since multirotors define a general category of unmanned aerial vehicles, the focus of this thesis are quadcopters, platforms with four rotors.  ...  Several authors present works based on MPC, e.g., hierarchical MPC controllers [16] [17] [18] [19] , leader-follower approaches [20] , a distributed MPC based collision avoidance controller [21] , local  ... 
doi:10.3390/computers9010007 fatcat:pvmyyrp2hbewvpsakg25zg3rty

Table of Contents

2021 IEEE Robotics and Automation Letters  
Wagner 1304 BADGR: An Autonomous Self-Supervised Learning-Based Navigation System . . . . . . G. Kahn, P. Abbeel, and S.  ...  Kheddar 1840 Semi-Supervised Gated Recurrent Neural Networks for Robotic Terrain Classification . , and N.  ... 
doi:10.1109/lra.2021.3072707 fatcat:qyphyzqxfrgg7dxdol4qamrdqu

Cooperative control in production and logistics

László Monostori, Paul Valckenaers, Alexandre Dolgui, Hervé Panetto, Mietek Brdys, Balázs Csanád Csáji
2015 Annual Reviews in Control  
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,  ...  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)  ...  Machine Learning (ML) is divided into 3 main paradigms, namely: (a) supervised learning (such as neural networks, kernel machines, and Bayes classifiers); (b) self-organized or unsupervised learning (such  ... 
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  
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,  ...  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)  ...  Machine Learning (ML) is divided into 3 main paradigms, namely: (a) supervised learning (such as neural networks, kernel machines, and Bayes classifiers); (b) self-organized or unsupervised learning (such  ... 
doi:10.3182/20140824-6-za-1003.01026 fatcat:kcbnlnahgjajfbtzqdq2y4ljim

Modelling and control of hybrid electric vehicles (A comprehensive review)

Wisdom Enang, Chris Bannister
2017 Renewable & Sustainable Energy Reviews  
Index Terms: -Heuristic control, Hybrid electric vehicle, Regenerative braking, Optimization of brake energy recovery, dynamic programming, optimal control, HEV control, vehicle modelling, Parallel HEV  ...  The challenge in developing an HEV control strategy lies in the satisfaction of often conflicting control constraints involving fuel consumption, emissions and driveability without over-depleting the battery  ...  This form of supervised learning is facilitated by the back propagation method. The adaptive structure of neural network makes it suitable for HEV energy management applications.  ... 
doi:10.1016/j.rser.2017.01.075 fatcat:dpad3l3svvbpde4waugurx65jm
« Previous Showing results 1 — 15 out of 61 results