Multi-robot Teams for Environmental Monitoring

Espina, Maria Valera; Grech, Reuben; Jager, Deon De; Remagnino, Paolo; Iocchi, Luca; Marchetti, Luca; Nardi, Daniele; Monekosso, Dorothy; Nicolescu, Mircea; King, Christopher

doi:10.1007/978-3-642-18278-5_8

Cited by 12 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main open issues include concurrent handling of multiple constraints, e.g. energy, network connectivity and routing strategy [84,62], or network lifetime, multi-hop connectivity, and target coverage [100], investigation of parameter sensitivity, interactions, and trade-offs [59,108,99], theoretical and experimental analyses of new scheduling methods [17,91], detailed evaluation of algorithm performance under real-world conditions [92,106,89,143,98,81,72,22], and from an applicationcentric perspective [136,143,129,66,20,22], and further general improvements of the proposed methods including generalization [17,81,19,148,137], specialization [69,106], and efficiency (e.g. parallelization [94,79]).…”

Section: Future Directions and Open Issuesmentioning

confidence: 99%

Review of nature-inspired methods for wake-up scheduling in wireless sensor networks

Musilek

Krömer

Bartoň

2015

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

Section: Future Directions and Open Issuesmentioning

confidence: 99%

Review of nature-inspired methods for wake-up scheduling in wireless sensor networks

Musilek

Krömer

Bartoň

2015

Swarm and Evolutionary Computation

View full text Add to dashboard Cite

“…where loss k ðiÞ represents the loss of agent i at time k. ðloss k ðtÞ À loss kÀ1 ðtÞÞ denotes the contribution of agent i to his target t to assist. As the selfishness of the agent, is used to control the frequency of agent reorganization, e depends on the result of the assistance, and its value, such as the equation (5), is discussed in detail in the next subsection e ¼ 1…”

Section: Reward Functionmentioning

confidence: 99%

“…Each agent's ability, attributes and structure are different, which provides a great space for multiagent collaboration. MAS have attracted many researchers to investigate the applicability of it in many pertinent areas closely related to human livelihood and industry such as security system [1], exploration and rescue [2], surveillance [3], humanitarian assistance [4], environment protection [5] [6] health care [7] [8]. Traditional SLAM has been considered as an independent behavior.…”

mentioning

confidence: 99%

Active collaboration in relative observation for multi-agent visual simultaneous localization and mapping based on Deep Q Network

Pei

Piao

Quan

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper proposes a unique active relative localization mechanism for multi-agent Simultaneous Localization and Mapping(SLAM),in which a agent to be observed are considered as a task, which is performed by others assisting that agent by relative observation. A task allocation algorithm based on deep reinforcement learning are proposed for this mechanism. Each agent can choose whether to localize other agents or to continue independent SLAM on it own initiative. By this way, the process of each agent SLAM will be interacted by the collaboration. Firstly, based on the characteristics of ORBSLAM, a unique observation function which models the whole MAS is obtained. Secondly, a novel type of Deep Q network(DQN) called MAS-DQN is deployed to learn correspondence between Q Value and state-action pair, abstract representation of agents in MAS are learned in the process of collaboration among

show abstract

“…These benefits have attracted many researchers from academia and industry to investigate the applicability of MRS in many pertinent areas of industrial and commercial importance such as intelligent security [1], search and rescue [2], surveillance [3], humanitarian demining [4], environment monitoring [5,6] and health care [7].…”

Section: Introductionmentioning

confidence: 99%

Multi-robot Task Allocation: A Review of the State-of-the-Art

Khamis

Hussein

Elmogy

2015

Studies in Computational Intelligence

351

193

View full text Add to dashboard Cite

Multi-robot systems (MRS) are a group of robots that are designed aiming to perform some collective behavior. By this collective behavior, some goals that are impossible for a single robot to achieve become feasible and attainable. There are several foreseen benefits of MRS compared to single robot systems such as the increased ability to resolve task complexity, increasing performance, reliability and simplicity in design. These benefits have attracted many researchers from academia and industry to investigate how to design and develop robust versatile MRS by solving a number of challenging problems such as complex task allocation, group formation, cooperative object detection and tracking, communication relaying and self-organization to name just a few. One of the most challenging problems of MRS is how to optimally assign a set of robots to a set of tasks in such a way that optimizes the overall system performance subject to a set of constraints. This problem is known as Multi-robot Task Allocation (MRTA) problem. MRTA is a complex problem especially when it comes to heterogeneous unreliable robots equipped with different capabilities that are required to perform various tasks with different requirements and constraints in an optimal way. This chapter provides a comprehensive review on challenging aspects of MRTA problem, recent approaches to tackle this problem and the future directions.

show abstract

Multi-robot Teams for Environmental Monitoring

Cited by 12 publications

References 31 publications

Review of nature-inspired methods for wake-up scheduling in wireless sensor networks

Review of nature-inspired methods for wake-up scheduling in wireless sensor networks

Active collaboration in relative observation for multi-agent visual simultaneous localization and mapping based on Deep Q Network

Multi-robot Task Allocation: A Review of the State-of-the-Art

Contact Info

Product

Resources

About