Filters








6,929 Hits in 4.8 sec

A Decentralized Framework for Multi-Agent Robotic Systems

Andrés Jiménez, Vicente García-Díaz, Sandro Bolaños
2018 Sensors  
Over the past few years, decentralization of multi-agent robotic systems has become an important research area.  ...  To validate this framework, we use differential robotic agents and a monitoring agent to generate a topological map of an environment with the presence of obstacles.  ...  The biggest contribution of this article is the development of a framework for communications between multiple agents in a decentralized system.  ... 
doi:10.3390/s18020417 pmid:29389849 pmcid:PMC5855891 fatcat:3gj4toagandzpgcgkte6qypela

A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies [article]

Jan Blumenkamp, Steven Morad, Jennifer Gielis, Qingbiao Li, Amanda Prorok
2021 arXiv   pre-print
In this work, we present the design of a system that allows for fully decentralized execution of GNN-based policies. We create a framework based on ROS2 and elaborate its details in this paper.  ...  multi-robot system relying on Adhoc communication.  ...  In this paper, we provide a framework that facilitates the decentralized execution of GNN-based multi-robot policies.  ... 
arXiv:2111.01777v1 fatcat:bvwqavr4vndibnx2ktvzyzgasy

A distributed multi-agent production planning and scheduling framework for mobile robots

Stefano Giordani, Marin Lujak, Francesco Martinelli
2013 Computers & industrial engineering  
We propose a solution in terms of a two-level decentralized Multi-Agent System (MAS) framework: at the first, production planning level, agents are tasks which compete for robots (resources at this level  ...  An iterative auction based negotiation protocol is used at the first level while the second level solves a Multi-Robot Task Allocation (MRTA) problem through a distributed version of the Hungarian Method  ...  For all the above reasons and because mobile robots are autonomous entities with limited vision and communication capacities, in this paper we propose a decentralized two-level Multi-Agent System (MAS)  ... 
doi:10.1016/j.cie.2012.09.004 fatcat:w7tcotphfzgfthwolgqfxxlyhe

Learning Multi-Arm Manipulation Through Collaborative Teleoperation [article]

Albert Tung, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, Silvio Savarese
2020 arXiv   pre-print
for a maximum of two robot arms.  ...  We show that learning from such data consequently presents challenges for centralized agents that directly attempt to model all robot actions simultaneously, and perform a comprehensive study of different  ...  ACKNOWLEDGMENT We would like to thank Rohun Kulkarni and Margaret Tung for helping with data collection.  ... 
arXiv:2012.06738v1 fatcat:lawzan47v5elbbwrtd2exijt5a

A Decentralized Mobile Computing Network for Multi-Robot Systems Operations [article]

Jabez Leong Kit and David Mateo and Roland Bouffanais
2018 arXiv   pre-print
These systems offer a unique source of inspiration for the development of fault-tolerant and self-healing multi-robot systems capable of operating in dynamic environments.  ...  This Collective computing framework is applied to the complex task of collective mapping, in which multiple robots aim at cooperatively map a large area.  ...  To this aim, we are currently developing a fault-tolerant robust collective computing framework suited for multi-robot systems and with fully decentralized operations in dynamic environments.  ... 
arXiv:1810.05818v1 fatcat:bzidqla5x5cdhbah6xlxfq5skm

Decentralized navigation model for multiagent cooperative robotic systems

Andrés C. Jiménez, Vicente García-Díaz, Sandro Bolaños
2020 Journal of Ambient Intelligence and Smart Environments  
On November 20, 2018 at 11 am, Andrés Camilo Jiménez Alvarez defended his Ph.D. thesis entitled Decentralized navigation model for multiagent cooperative robotic systems at the Distrital University Francisco  ...  Andrés Camilo Jiménez Alvarez presented his dissertation in a public open event held in the "Wise Caldas Auditory", and was able to expose and defend all his research, it was approved by the committee.  ...  . / Decentralized navigation model for multiagent cooperative robotic systemsFig. 1. Five modular processes of the framework.  ... 
doi:10.3233/ais-200583 fatcat:do4l3n2eezb6lcjrmdmurhlnvi

Decentralized Cooperative Communication Framework for Heterogeneous Multi Agent System

Herdawatie Abdul Kadir, Mohd Rizal Arshad
2014 Journal of Communications  
The paper is organized as follows: Section II introduces communication framework for the proposed decentralized cooperative multi agent system. Section III deals with the new communication framework.  ...  In this communication framework, the multi agent communication must not be affected by the communication network failure between robots.  ...  We would also like to thank Abdul Sattar Din and Mohd Akmal Mohd Yusoff for their comments and suggestion.  ... 
doi:10.12720/jcm.9.2.163-170 fatcat:n2c5nfwcxfgtpptqmygu6qq4om

Guest editorial: Special issue on distributed robotics—from fundamentals to applications

Roderich Groß, Andreas Kolling, Spring Berman, Alcherio Martinoli, Emilio Frazzoli, Fumitoshi Matsuno
2018 Autonomous Robots  
scheme for formation control of uncertain homogeneous Lagrangian nonlinear multi-agent systems with a directed communication topology.  ...  This paper presents a decentralized hierarchical planning and coordination framework for cooperative multi-robot teams composed of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs).  ... 
doi:10.1007/s10514-018-9803-9 fatcat:7qovvvqmsbe7zez4kbujzmfs5e

Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning [article]

Pinxin Long, Tingxiang Fan, Xinyi Liao, Wenxi Liu, Hao Zhang, Jia Pan
2018 arXiv   pre-print
, collision-free paths for a large-scale robot system.  ...  We present a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity.  ...  Regarding multi-agent collision avoidance, the Optimal Reciprocal Collision Avoidance (ORCA) framework [1] has been popular in crowd simulation and multi-agent systems.  ... 
arXiv:1709.10082v3 fatcat:gr3rzog2fzglffmpgafqanyovy

Decentralized Supervision Of Mobile Sensor Networks Using Petri Net

Fatemeh Jafarinejad1
2018 Zenodo  
For such systems, this paper proposes a decentralized supervisory control system to accept or reject the human-issued commands so that undesirable executions never be performed.  ...  In the present approach, Petri nets are used to model the operated behaviors and to synthesize the decentralized supervisory system.  ...  Appling the decentralized approach of [17] we can disjoint the supervisor of each robot agent and construct a decentralized supervision for this MSN system.  ... 
doi:10.5281/zenodo.1287536 fatcat:mcsjmivytjauhnv4rut47zfr2a

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts [article]

Amanda Prorok, Jan Blumenkamp, Qingbiao Li, Ryan Kortvelesy, Zhe Liu, Ethan Stump
2021 arXiv   pre-print
Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales  ...  Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances.  ...  Decentralization is key to successful multi-agent systems, therefore decentralized mesh communication networks are required to operate multi-robot systems in the real world, which may pose additional challenges  ... 
arXiv:2107.12254v1 fatcat:tvmepyeftjeorivf332xgkky4m

Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network

Lin Chen, Yongting Zhao, Huanjun Zhao, Bin Zheng
2021 Sensors  
This paper presents a novel decentralized multi-robot collision avoidance method with deep reinforcement learning, which is not only suitable for the large-scale grid map workspace multi-robot system,  ...  According to the particularity of the workspace, we handcrafted a reward function, which considers both the collision avoidance among the robots and as little as possible change of direction of the robots  ...  We developed a novel decentralized multi-robot collision avoidance method with deep reinforcement learning, which is not only suitable for the large-scale grid map workspace multi-robot system, but also  ... 
doi:10.3390/s21030841 pmid:33513856 fatcat:5lf377ztrvhz3oadzzuf624xje

Decision-Making Under Uncertainty in Multi-Agent and Multi-Robot Systems: Planning and Learning

Christopher Amato
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
This paper discusses our work on developing principled models to represent these problems and planning and learning methods that can scale to realistic multi-agent and multi-robot tasks.  ...  Methods for real-world domains, such as robotics, must consider uncertainty and limited communication in order to generate high-quality, robust solutions.  ...  Acknowledgments I thank all of my collaborators for making this work possible. This work was partially supported by NSF award #1463945 and Air Force Contract #FA8721-05-C-0002.  ... 
doi:10.24963/ijcai.2018/805 dblp:conf/ijcai/Amato18 fatcat:tnwvrzq45rfmbdoda7oxn6u3fy

Decentralized Task and Path Planning for Multi-Robot Systems [article]

Yuxiao Chen, Ugo Rosolia, Aaron D. Ames
2020 arXiv   pre-print
We consider a multi-robot system with a team of collaborative robots and multiple tasks that emerges over time.  ...  Each robot agent follows the optimal policy synthesized for the Markov model and we propose a localized forward dynamic programming scheme that resolves conflicts between agents and avoids collisions.  ...  CONCLUSION We propose the decentralized task and path planning (DTPP) framework that is capable of task allocation and high-level path planning for a multi-robot system in a fully decentralized manner.  ... 
arXiv:2011.10034v1 fatcat:i4smqpsdxraw5h63aoowisod54

Hysteretic q-learning :an algorithm for decentralized reinforcement learning in cooperative multi-agent teams

Laetitia Matignon, Guillaume J. Laurent, Nadine Le Fort-Piat
2007 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Multi-agent systems (MAS) are a field of study of growing interest in a variety of domains such as robotics or distributed controls.  ...  The article focuses on decentralized reinforcement learning (RL) in cooperative MAS, where a team of independent learning robots (IL) try to coordinate their individual behavior to reach a coherent joint  ...  INTRODUCTION Learning in multi-agent systems (MAS) are a field of study of growing interest in a wide variety of domains, and especially in multi-robot systems [1] .  ... 
doi:10.1109/iros.2007.4399095 dblp:conf/iros/MatignonLF07 fatcat:dxhajv77b5e6zlnquch6wxjcba
« Previous Showing results 1 — 15 out of 6,929 results