Distributed multi-robot coordination combining semantics and real-time scheduling

Lujak, Marin; Fernandez, Alberto

doi:10.1109/cisti.2015.7170599

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There exist several work that addressed different constraints in task allocation such as resource constraints [32], [33], time and spatial constraints [34]- [36], and envy minimization [37]. Previous attempts at addressing communication constraints in multiagent algorithms can be classified into two categories.…”

Section: Related Workmentioning

confidence: 99%

Communication-Aware Consensus-Based Decentralized Task Allocation in Communication Constrained Environments

2022

View full text Add to dashboard Cite

This paper presents a deep reinforcement learning framework in which agents learn how to schedule and censor themselves amongst the other agents competing for access to a limited communication medium. In particular, the process learns to schedule the communication between agents to improve the performance of task allocation in environments with constrained communication in terms of limited bandwidth and message collision. The proposed approach, called Communication-Aware Consensus-Based Bundle Algorithm (CA-CBBA), extends the previous CBBA [1] in that the learned communication policy enables efficient utilization of the shared medium by prioritizing agents with messages that are important for the mission. Furthermore, agents in denser parts of the network are censored appropriately to alleviate the message collision and hidden node problems. We evaluate our approach in various task assignment scenarios, and the results show that CA-CBBA outperforms CBBA in terms of convergence time, rate of conflict resolution, and task allocation reward. Moreover, we show that CA-CBBA yields a policy that generalizes beyond the training set to handle larger team sizes. Finally, the results on time-critical problems, such as a search-and-rescue mission, show that CA-CBBA also outperforms the baselines considered (e.g., CBBA, MCDGA [2], and ACBBA [3]) in terms of number of unassigned and conflicted tasks in most of the scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Communication-Aware Consensus-Based Decentralized Task Allocation in Communication Constrained Environments

2022

View full text Add to dashboard Cite

show abstract

“…En [5], se presenta una modificación del algoritmo A*, para ser utilizado en la coordinación de un sistema multirobot que ejecuta la tarea de transporte: se adiciona un componente de tiempo al algoritmo, que es importante para la predicción de la posición de los vehículos que actúan en el sistema. Finalmente, en [6] se propone una arquitectura de coordinación distribuida para un sistema multirobot, donde los individuos tienen capacidades parcialmente solapadas.…”

Section: Introductionunclassified

Coordinación emergente en sistemas multi-robots

Gil¹,

Aguilar²,

Rivas³

et al. 2019

revuin

View full text Add to dashboard Cite

ResumenEn la naturaleza se encuentran sociedades de seres vivos que coordinan sus acciones de forma no centralizada. Por ejemplo, en las colonias de hormigas ocurren procesos emergentes, que combinan las acciones de los individuos en función de un objetivo común. En este trabajo, se describe una capa de gestión que facilita los procesos de coordinación emergente en los sistemas multirobots. Esta capa en particular permite la aparación de la emergencia y la autoorganización en el sistema. En conjunto con las capas de gestión individual y de gestión del conocimiento, manejan los procesos necesarios para el funcionamiento del sistema multirobot.Palabras clave: arquitectura; coordinación; emergencia; auto-organización; sistemas multirobots. AbstractIn nature there are societies of living beings that coordinate their actions in a non-centralized way. For example, emergent processes that combine the actions of individuals in the achievement of a common goal occur in ant colonies. This paper describes a management layer that facilitates emerging coordination processes in multi-robot systems, which together with other two layers (one of individual management and another of knowledge management), manage the processes necessary for the operation of the multi-robot system. In particular, this layer allows the appearance of emergency and self-organization in the system.

show abstract

Overview of Semantic Information Applications for Robots

Liu

Dai

et al. 2019

2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA)

View full text Add to dashboard Cite

Distributed multi-robot coordination combining semantics and real-time scheduling

Cited by 3 publications

References 12 publications

Communication-Aware Consensus-Based Decentralized Task Allocation in Communication Constrained Environments

Communication-Aware Consensus-Based Decentralized Task Allocation in Communication Constrained Environments

Coordinación emergente en sistemas multi-robots

Overview of Semantic Information Applications for Robots

Contact Info

Product

Resources

About