MineralMiner

An active sensing simulation environment

Adam Eck, Leen-Kiat Soh

Research output: Contribution to journalArticle

Abstract

One important problem in multiagent systems is determining how to gather information through sensing to support agent reasoning. This problem commonly arises in real-world applications such as robotics, mixed initiative systems, and others. One promising solution is to use active sensing to explicitly reason about the benefits (e.g., information gain, accuracy) and costs (e.g., resource use, knowledge corruption) of sensing actions, then proactively sense to maximize benefits and/or minimize costs. However, properties of complex environments make active sensing more difficult, necessitating further research and evaluation before deploying such solutions. In this paper, we describe MineralMiner, a novel simulation environment that extends previous environments to provide eight common complex environment properties in order to enable the effective study of active sensing. These properties can be fine-tuned using several simulation parameters in order to properly mimic environments likely to occur in real-world applications, allowing for insightful and successful pre-deployment testing, evaluation, and debugging of active sensing solutions, as well as on-going research into active sensing. Furthermore, we describe how several applications of sensing problems benefiting from active sensing can be abstracted and studied within MineralMiner, demonstrating the breadth and depth of its applicability to active sensing research.

Original languageEnglish (US)
Pages (from-to)197-206
Number of pages10
JournalMultiagent and Grid Systems
Volume9
Issue number3
DOIs
StatePublished - Dec 1 2013

Fingerprint

Multi agent systems
Costs
Robotics
Testing

Keywords

  • Active sensing
  • complex environments
  • multiagent systems
  • simulation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

MineralMiner : An active sensing simulation environment. / Eck, Adam; Soh, Leen-Kiat.

In: Multiagent and Grid Systems, Vol. 9, No. 3, 01.12.2013, p. 197-206.

Research output: Contribution to journalArticle

@article{aaa40e7f56e44e8da48dc1fd7f17a1fa,
title = "MineralMiner: An active sensing simulation environment",
abstract = "One important problem in multiagent systems is determining how to gather information through sensing to support agent reasoning. This problem commonly arises in real-world applications such as robotics, mixed initiative systems, and others. One promising solution is to use active sensing to explicitly reason about the benefits (e.g., information gain, accuracy) and costs (e.g., resource use, knowledge corruption) of sensing actions, then proactively sense to maximize benefits and/or minimize costs. However, properties of complex environments make active sensing more difficult, necessitating further research and evaluation before deploying such solutions. In this paper, we describe MineralMiner, a novel simulation environment that extends previous environments to provide eight common complex environment properties in order to enable the effective study of active sensing. These properties can be fine-tuned using several simulation parameters in order to properly mimic environments likely to occur in real-world applications, allowing for insightful and successful pre-deployment testing, evaluation, and debugging of active sensing solutions, as well as on-going research into active sensing. Furthermore, we describe how several applications of sensing problems benefiting from active sensing can be abstracted and studied within MineralMiner, demonstrating the breadth and depth of its applicability to active sensing research.",
keywords = "Active sensing, complex environments, multiagent systems, simulation",
author = "Adam Eck and Leen-Kiat Soh",
year = "2013",
month = "12",
day = "1",
doi = "10.3233/MGS-130206",
language = "English (US)",
volume = "9",
pages = "197--206",
journal = "Multiagent and Grid Systems",
issn = "1574-1702",
publisher = "IOS Press",
number = "3",

}

TY - JOUR

T1 - MineralMiner

T2 - An active sensing simulation environment

AU - Eck, Adam

AU - Soh, Leen-Kiat

PY - 2013/12/1

Y1 - 2013/12/1

N2 - One important problem in multiagent systems is determining how to gather information through sensing to support agent reasoning. This problem commonly arises in real-world applications such as robotics, mixed initiative systems, and others. One promising solution is to use active sensing to explicitly reason about the benefits (e.g., information gain, accuracy) and costs (e.g., resource use, knowledge corruption) of sensing actions, then proactively sense to maximize benefits and/or minimize costs. However, properties of complex environments make active sensing more difficult, necessitating further research and evaluation before deploying such solutions. In this paper, we describe MineralMiner, a novel simulation environment that extends previous environments to provide eight common complex environment properties in order to enable the effective study of active sensing. These properties can be fine-tuned using several simulation parameters in order to properly mimic environments likely to occur in real-world applications, allowing for insightful and successful pre-deployment testing, evaluation, and debugging of active sensing solutions, as well as on-going research into active sensing. Furthermore, we describe how several applications of sensing problems benefiting from active sensing can be abstracted and studied within MineralMiner, demonstrating the breadth and depth of its applicability to active sensing research.

AB - One important problem in multiagent systems is determining how to gather information through sensing to support agent reasoning. This problem commonly arises in real-world applications such as robotics, mixed initiative systems, and others. One promising solution is to use active sensing to explicitly reason about the benefits (e.g., information gain, accuracy) and costs (e.g., resource use, knowledge corruption) of sensing actions, then proactively sense to maximize benefits and/or minimize costs. However, properties of complex environments make active sensing more difficult, necessitating further research and evaluation before deploying such solutions. In this paper, we describe MineralMiner, a novel simulation environment that extends previous environments to provide eight common complex environment properties in order to enable the effective study of active sensing. These properties can be fine-tuned using several simulation parameters in order to properly mimic environments likely to occur in real-world applications, allowing for insightful and successful pre-deployment testing, evaluation, and debugging of active sensing solutions, as well as on-going research into active sensing. Furthermore, we describe how several applications of sensing problems benefiting from active sensing can be abstracted and studied within MineralMiner, demonstrating the breadth and depth of its applicability to active sensing research.

KW - Active sensing

KW - complex environments

KW - multiagent systems

KW - simulation

UR - http://www.scopus.com/inward/record.url?scp=84893749844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893749844&partnerID=8YFLogxK

U2 - 10.3233/MGS-130206

DO - 10.3233/MGS-130206

M3 - Article

VL - 9

SP - 197

EP - 206

JO - Multiagent and Grid Systems

JF - Multiagent and Grid Systems

SN - 1574-1702

IS - 3

ER -