Cost-aware Bayesian sequential decision-making for domain search and object classification

Wang, Y.; Hussein, Islam I.; Brown, Donald R.; Erwin, R. Scott

doi:10.1109/cdc.2010.5717743

Cited by 6 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This result, however, is based on the assumption that the sensor may miss targets, but does not provide for false positives. In the controls community Hussein et al [18] also consider the problem of searching for an unknown number of targets, and they also use information entropy in order to formulate search decisions like where to search next and when to stop. Their formulation, however, relies on uniform grid representations and does not consider sensors with variable performance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Searching for multiple targets using Probabilistic Quadtrees

Carpin

Burch²,

Chung³

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-We consider the problem of searching for an unknown number of static targets inside an assigned area. The search problem is tackled using Probabilisitic Quadtrees (PQ), a data structure we recently introduced. Probabilistic quadtrees allow for a variable resolution representation and naturally induce a search problem where the searcher needs to choose not only where to sense, but also the sensing resolution. Through a Bayesian approach accommodating faulty sensors returning both false positives and missed detections, a posterior distribution about the location of the targets is propagated during the search effort. In this paper we extend our previous findings by considering the problem of searching for an unknown number of targets. Moreover, we substitute our formerly used heuristic with an approach based on information gain and expected costs. Finally, we provide some convergence results showing that in the worst case our model provides the same results as uniform grids, thus guaranteeing that the representation we propose gracefully degrades towards a known model. Extensive simulation results substantiate the properties of the method we propose, and we also show that our variable resolution method outperforms traditional methods based on uniform resolution grids.

show abstract

Section: Related Workmentioning

confidence: 99%

“…These assumptions are coherent with indications provided by search and rescue teams. We use the stopping criterion proposed in [18]. Let the quantity U be defined as follows:…”

Section: Stopping the Search And Formulating A Search Decisionmentioning

confidence: 99%

Searching for multiple targets using Probabilistic Quadtrees

Carpin

Burch²,

Chung³

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

Bayesian‐Based Domain Search Using Multiple Autonomous Vehicles with Intermittent Information Sharing

Wang¹,

Hussein²

2012

Asian Journal of Control

View full text Add to dashboard Cite

This paper focuses on the development of Bayesian-based domain search strategies using distributed multiple autonomous vehicles with intermittent communications. Multi-sensor fusion based on observations from neighboring vehicles is implemented via binary Bayesian filtering. We prove theoretically that, under appropriate sensor models, the belief of whether there exists an object at every discretized cell in the domain will converge to the true state. An uncertainty map representing the entropies associated with these probabilities is constructed to guide the vehicles' motion for domain exploration. Under the proposed strategies, all objects in the search domain will be detected. Different motion control schemes are numerically tested to confirm the effectiveness of the proposed search strategies.

show abstract