Autonomous sensor manager agents (ASMA)

Osadciw, Lisa Ann

doi:10.1117/12.542246

Cited by 2 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A priori knowledge may be used to initialize these random variables and their distributions but the SM must be able to learn and automatically adapt these distributions as the system operates. Since sensor control decisions are being based on the optimization of the performance measures, the global sensor network performance measures must completely quantify success for the application [18]. The global performance value is a weighted sum of multiple global performance parameters as defined in the SM.…”

Section: A New Paradigm For Sensor Managementmentioning

confidence: 99%

See 1 more Smart Citation

A controllable sensor management algorithm capable of learning

Osadciw

Veeramacheneni

2005

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Sensor management technology progress is challenged by the geographic space it spans, the heterogeneity of the sensors, and the real-time timeframes within which plans controlling the assets are executed. This paper presents a new sensor management paradigm and demonstrates its application in a sensor management algorithm designed for a biometric access control system. This approach consists of an artificial intelligence (AI) algorithm focused on uncertainty measures, which makes the high level decisions to reduce uncertainties and interfaces with the user, integrated cohesively with a bottom up evolutionary algorithm, which optimizes the sensor network's operation as determined by the AI algorithm. The sensor management algorithm presented is composed of a Bayesian network, the AI algorithm component, and a swarm optimization algorithm, the evolutionary algorithm. Thus, the algorithm can change its own performance goals in real-time and will modify its own decisions based on observed measures within the sensor network. The definition of the measures as well as the Bayesian network determine the robustness of the algorithm and its utility in reacting dynamically to changes in the global system.

show abstract

Section: A New Paradigm For Sensor Managementmentioning

confidence: 99%

“…This prolongs the life of the sensor network. Also, the optimization algorithm works with the sensor models and cost function to choose parameters that can expand sensor coverage to meet the requirements [18]. If the requirements call for an expansion in one area of one type of coverage, this can automatically happen in SM.…”

Section: Introductionmentioning

confidence: 99%

A controllable sensor management algorithm capable of learning

Osadciw

Veeramacheneni

2005

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…The values at the i th dimension can be 1, 2, 3 depending upon the radar that is chosen to track the i th target. Once a solution is decided upon, the fitness of the particle can be evaluated using equations (6)(7)(8)(9). The algorithm is repeated for a fixed number of iterations to achieve the optimal solution.…”

Section: A Particle Swarm Optimizer Maximizing Coveragementioning

confidence: 99%

“…A particle swarm optimization based algorithm has been used to solve various multi objective problems in sensor management [5,6]. In this paper the PSO is being used to arrive at the optimal dwell assignment for multiple radars with in a region.…”

Section: Introductionmentioning

confidence: 99%

Multiple Sectors, Multi Function, Multi Radar Dwell Time Management using Particle Swarm Optimization (M3RTM)

Veeramachaneni

Osadciw

2006 IEEE Conference on Radar

View full text Add to dashboard Cite

In this paper a particle swarm optimization algorithm based approach is presented for dwell time management of multiple multi function radars monitoring multiple sectors. Each radar can perform two functions, which are Normal Surveillance (NS) or Search and Track targets. Multiple radars are used to perform these functions for multiple sectors. A particle swarm optimization based algorithm evolves the optimal dwell time management. The dwell management affects the probability of detection of targets, as well as the surveillance coverage range. The first objective of the paper is to optimally allocate the dwell time of multiple radars to surveillance and track tasks to achieve the maximum coverage of the sector while achieving the required probability of detection for all the targets. In the second case, beams from multiple radars are used to track targets and improve the probability of detection. The objective is to optimize the coverage of each region as well maximize the probability of detection of different targets. The decisions of using radar resources, which are its dwell time and energy, have to be made in real time and arriving at optimal configuration is non trivial. The particle swarm optimization algorithm covers the targets by varying the range which each of the radar will cover in each sector. Particle swarm optimization is proposed to intelligently search and find the optimal time management. The ability of particle swarm to achieve and quickly converge to an optimal solution, which is a pattern of assigning functions to dwells and simultaneously setting the sector's instrumented range for the multiple radars, is presented.

show abstract

Autonomous sensor manager agents (ASMA)

Cited by 2 publications

References 13 publications

A controllable sensor management algorithm capable of learning

A controllable sensor management algorithm capable of learning

Multiple Sectors, Multi Function, Multi Radar Dwell Time Management using Particle Swarm Optimization (M3RTM)

Contact Info

Product

Resources

About