TY - JOUR

T1 - Information-Based Hierarchical Planning for a Mobile Sensing Network in Environmental Mapping

AU - Li, T.

AU - Tong, K.

AU - Xia, M.

AU - Li, B.

AU - De Silva, C.W.

N1 - ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2020/6/1

Y1 - 2020/6/1

N2 - This article investigates the problem of information-based sampling design and path planning for a mobile sensing network to predict scalar fields of monitored environments. A hierarchical framework with a built-in Gaussian Markov random field model is proposed to provide adaptive sampling for efficient field reconstruction. In the proposed framework, a nonmyopic planner is operated at a sink to navigate the mobile sensing agents in the field to the sites that are most informative. Meanwhile, a myopic planner is carried out on board each agent. A tradeoff between computationally intensive global optimization and efficient local greedy search is incorporated into the system. The mobile sensing agents can be scheduled online through an anytime algorithm to visit and observe the high-information sites. Experiments on both synthetic and real-world datasets are used to demonstrate the feasibility and efficiency of the proposed planner in model exploitation and adaptive sampling for environmental field mapping.

AB - This article investigates the problem of information-based sampling design and path planning for a mobile sensing network to predict scalar fields of monitored environments. A hierarchical framework with a built-in Gaussian Markov random field model is proposed to provide adaptive sampling for efficient field reconstruction. In the proposed framework, a nonmyopic planner is operated at a sink to navigate the mobile sensing agents in the field to the sites that are most informative. Meanwhile, a myopic planner is carried out on board each agent. A tradeoff between computationally intensive global optimization and efficient local greedy search is incorporated into the system. The mobile sensing agents can be scheduled online through an anytime algorithm to visit and observe the high-information sites. Experiments on both synthetic and real-world datasets are used to demonstrate the feasibility and efficiency of the proposed planner in model exploitation and adaptive sampling for environmental field mapping.

KW - Adaptive sampling

KW - environmental field mapping

KW - Gaussian Markov random fields (GMRFs)

KW - information-driven planning

KW - mobile sensing networks (MSNs)

KW - Global optimization

KW - Image segmentation

KW - Mapping

KW - Markov processes

KW - Motion planning

KW - Any-time algorithms

KW - Environmental fields

KW - Environmental mapping

KW - Field reconstruction

KW - Gaussian markov random field models

KW - Hierarchical planning

KW - Mobile sensing agents

KW - Mobile sensing networks

KW - Mobile agents

U2 - 10.1109/JSYST.2019.2939250

DO - 10.1109/JSYST.2019.2939250

M3 - Journal article

VL - 14

SP - 1692

EP - 1703

JO - IEEE Systems Journal

JF - IEEE Systems Journal

SN - 1932-8184

IS - 2

M1 - 8844270

ER -