Control of Perimeter Surveillance Wireless Sensor Networks via Partially Observable Marcov Decision Process

Krakow, Lucas W.; Chong, Edwin K. P.; Groomn, Kenneth N.; Harrington, John J.; Li, Yun; Rigdon, Brian

doi:10.1109/ccst.2006.313460

Cited by 10 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As pointed out in Section 5, exact optimal solutions are practically infeasible to compute. Therefore, recent effort has focused on obtaining approximate solutions, and a number of methods have been developed (e.g., sec [9, 13,14,18,22,23]). Our research contributes to the further development of this thrust by introducing a new approximation method, called nominal belief-state optimization, and applying it to the UAV guidance problem.…”

Section: Introductionmentioning

confidence: 99%

UAV Communication Management and Coordination for Multitarget Tracking

Miller¹,

Harris²,

Chong³

2009

View full text Add to dashboard Cite

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing aaia SOUIUHS. y^m^niy a,,u maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection ot information, including suggestions for reducing the burden, to the Department of Defense, Executive Service Directorate (0704-0188) Respondents should be aware that notwithstanding any other provision of law. no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR SPONSOR/MONITOR'S ACRONYM(S) AFOSR SPONSOR/MONITOR'S REPORT NUMBER(S) DISTRIBUTION/AVAILABILITY STATEMENTApproved for public release: distribution is unlimited. SUPPLEMENTARY NOTES ABSTRACTThe research conducted under this grant concerned the application of the theory of partially observable Markov decision processes (POMDPs) to the design of guidance algorithms for controlling the motion of unmanned aerial vehicles (UAVs) with on-board sensors to improve tracking of multiple ground targets. While POMDP problems are intractable to solve exactly, principled approximation methods can be devised based on the theory that characterizes optimal solutions. A new approximation method called nominal belief-state optimization (NBO) was proposed. When combined with other application-specific approximations and techniques within the POMDP framework, NBO produced a practical design that coordinated the UAVs to achieve good long-term mean-squared-error tracking performance in the presence of occlusions and dynamic constraints The flexibility of the design was demonstrated by extending the objective to reduce the probability of a track swap in ambiguous situations, with the positive side-effect of improving the mean-squared-error tracking performance as well.

show abstract

Section: Introductionmentioning

confidence: 99%

UAV Communication Management and Coordination for Multitarget Tracking

Miller¹,

Harris²,

Chong³

2009

View full text Add to dashboard Cite

show abstract

“…In our subsequent discussion of rollout, we focus on implementation of rollout using Monte Carlo simulation. For an application of the rollout method to sensor scheduling for target tracking, see [7], [8], [10], [16]. For an extension involving multiple base policies, see [6].…”

Section: Rolloutmentioning

confidence: 99%

“…We call this method completely observable (CO) rollout. It turns out that in certain applications, such as in sensor scheduling for target tracking, a CO-rollout base policy is naturally available (see [7], [8], [10], [16]). Note that we will still need to keep track of (or estimate) the actual belief state of the system, even if we use CO rollout.…”

Section: Rolloutmentioning

confidence: 99%

See 1 more Smart Citation

Monte-Carlo-based partially observable Markov decision process approximations for adaptive sensing

Chong

Kreucher

Hero

2008

2008 9th International Workshop on Discrete Event Systems

View full text Add to dashboard Cite

Abstract-Adaptive sensing involves actively managing sensor resources to achieve a sensing task, such as object detection, classification, and tracking, and represents a promising direction for new applications of discrete event system methods. We describe an approach to adaptive sensing based on approximately solving a partially observable Markov decision process (POMDP) formulation of the problem. Such approximations are necessary because of the very large state space involved in practical adaptive sensing problems, precluding exact computation of optimal solutions. We review the theory of POMDPs and show how the theory applies to adaptive sensing problems. We then describe Monte-Carlo-based approximation methods, with an example to illustrate their application in adaptive sensing. The example also demonstrates the gains that are possible from nonmyopic methods relative to myopic methods.

show abstract

“…Although we described our simulation-based approach in generic terms, the power of the methodology is realized when it is implemented on a high-fidelity simulator tailored to an application domain. An example of such a simulator is Umbra (see [27] for details). We have implemented our algorithm in Umbra to exploit and leverage the simulation capabilities that have already been embedded into it.…”

mentioning

confidence: 99%

Design tools for complex dynamic security systems.

Byrne¹,

Rigdon²,

Rohrer³

et al. 2007

Self Cite

View full text Add to dashboard Cite

The development of tools for complex dynamic security systems is not a straight forward engineering task but, rather, a scientific task where discovery of new scientific principles and math is necessary. For years, scientists have observed complex behavior but have had difficulty understanding it. Prominent examples include: insect colony organization, the stock market, molecular interactions, fractals, and emergent behavior. Engineering such systems will be an even greater challenge. This report explores four tools for engineered complex dynamic security systems: Partially Observable Markov Decision Process, Percolation Theory, Graph Theory, and Exergy/Entropy Theory. Additionally, enabling hardware technology for next generation security systems are described: a 100 node wireless sensor network, unmanned ground vehicle and unmanned aerial vehicle.3 Acknowledgment

show abstract

Control of Perimeter Surveillance Wireless Sensor Networks via Partially Observable Marcov Decision Process

Cited by 10 publications

References 20 publications

UAV Communication Management and Coordination for Multitarget Tracking

UAV Communication Management and Coordination for Multitarget Tracking

Monte-Carlo-based partially observable Markov decision process approximations for adaptive sensing

Design tools for complex dynamic security systems.

Contact Info

Product

Resources

About