Farsighted sensor management for feature-aided tracking

Angelia Nedich, Michael K. Schneider, Xinzhuo Shen, Djuana Lea

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We consider the sensor management problem arising in air-to-ground tracking of moving targets. The sensing-tracking system includes a radar and a feature-aided tracker. The radar collects target-signature data in high-resolution-radar (HRR) mode. The tracker is using the collected HRR-signature data to create and maintain target-track identification information. More specifically, the tracker is learning target-track profiles from the collected signature data, and is using these profiles to resolve the potential report-to-track or track-to-track association ambiguities. In this paper, we focus on the management of the HRR-signature data collection. Specifically, the sensor management problem is to determine where to collect signature data on targets in time so as to optimize the utility of the collected data. As with other sensor management problems, determining the optimal data collection is a hard combinatorial problem due to many factors including the large number of possible sensor actions and the complexity of the dynamics. The complexity of the dynamics stems in part from the presence of the sensor slew time. A distinguishing feature of the sensor management problem considered here is that the HRR-signature data collected during the learning phase has no immediate value. To optimize the data collections, a sensor manager must look sufficiently far into the future to adequately trade-off alternative plans. Here, we propose some farsighted algorithms, and evaluate them against a sequential scanning and a greedy algorithm. We present our simulation results obtained by applying these algorithms to a problem of managing a single sensor providing HRR-signature data.

Original languageEnglish (US)
Title of host publicationSignal Processing, Sensor Fusion, and Target Recognition XV
Volume6235
DOIs
StatePublished - 2006
Externally publishedYes
EventSignal Processing, Sensor Fusion, and Target Recognition XV - Kissimmee, FL, United States
Duration: Apr 17 2006Apr 19 2006

Other

OtherSignal Processing, Sensor Fusion, and Target Recognition XV
CountryUnited States
CityKissimmee, FL
Period4/17/064/19/06

Fingerprint

radar signatures
Radar
sensors
Sensors
high resolution
signatures
learning
radar
greedy algorithms
radar targets
profiles
stems
ambiguity
Managers
Scanning
scanning
air
Air
simulation

Keywords

  • Farsighted strategy
  • Feature-aided tracking
  • HRR-signature data collection
  • Sensor management
  • Stochastic dynamic programming

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Nedich, A., Schneider, M. K., Shen, X., & Lea, D. (2006). Farsighted sensor management for feature-aided tracking. In Signal Processing, Sensor Fusion, and Target Recognition XV (Vol. 6235). [62350D] https://doi.org/10.1117/12.665491

Farsighted sensor management for feature-aided tracking. / Nedich, Angelia; Schneider, Michael K.; Shen, Xinzhuo; Lea, Djuana.

Signal Processing, Sensor Fusion, and Target Recognition XV. Vol. 6235 2006. 62350D.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nedich, A, Schneider, MK, Shen, X & Lea, D 2006, Farsighted sensor management for feature-aided tracking. in Signal Processing, Sensor Fusion, and Target Recognition XV. vol. 6235, 62350D, Signal Processing, Sensor Fusion, and Target Recognition XV, Kissimmee, FL, United States, 4/17/06. https://doi.org/10.1117/12.665491
Nedich A, Schneider MK, Shen X, Lea D. Farsighted sensor management for feature-aided tracking. In Signal Processing, Sensor Fusion, and Target Recognition XV. Vol. 6235. 2006. 62350D https://doi.org/10.1117/12.665491
Nedich, Angelia ; Schneider, Michael K. ; Shen, Xinzhuo ; Lea, Djuana. / Farsighted sensor management for feature-aided tracking. Signal Processing, Sensor Fusion, and Target Recognition XV. Vol. 6235 2006.
@inproceedings{757ad852d4664a9e9205242f60cf7b27,
title = "Farsighted sensor management for feature-aided tracking",
abstract = "We consider the sensor management problem arising in air-to-ground tracking of moving targets. The sensing-tracking system includes a radar and a feature-aided tracker. The radar collects target-signature data in high-resolution-radar (HRR) mode. The tracker is using the collected HRR-signature data to create and maintain target-track identification information. More specifically, the tracker is learning target-track profiles from the collected signature data, and is using these profiles to resolve the potential report-to-track or track-to-track association ambiguities. In this paper, we focus on the management of the HRR-signature data collection. Specifically, the sensor management problem is to determine where to collect signature data on targets in time so as to optimize the utility of the collected data. As with other sensor management problems, determining the optimal data collection is a hard combinatorial problem due to many factors including the large number of possible sensor actions and the complexity of the dynamics. The complexity of the dynamics stems in part from the presence of the sensor slew time. A distinguishing feature of the sensor management problem considered here is that the HRR-signature data collected during the learning phase has no immediate value. To optimize the data collections, a sensor manager must look sufficiently far into the future to adequately trade-off alternative plans. Here, we propose some farsighted algorithms, and evaluate them against a sequential scanning and a greedy algorithm. We present our simulation results obtained by applying these algorithms to a problem of managing a single sensor providing HRR-signature data.",
keywords = "Farsighted strategy, Feature-aided tracking, HRR-signature data collection, Sensor management, Stochastic dynamic programming",
author = "Angelia Nedich and Schneider, {Michael K.} and Xinzhuo Shen and Djuana Lea",
year = "2006",
doi = "10.1117/12.665491",
language = "English (US)",
isbn = "0819462918",
volume = "6235",
booktitle = "Signal Processing, Sensor Fusion, and Target Recognition XV",

}

TY - GEN

T1 - Farsighted sensor management for feature-aided tracking

AU - Nedich, Angelia

AU - Schneider, Michael K.

AU - Shen, Xinzhuo

AU - Lea, Djuana

PY - 2006

Y1 - 2006

N2 - We consider the sensor management problem arising in air-to-ground tracking of moving targets. The sensing-tracking system includes a radar and a feature-aided tracker. The radar collects target-signature data in high-resolution-radar (HRR) mode. The tracker is using the collected HRR-signature data to create and maintain target-track identification information. More specifically, the tracker is learning target-track profiles from the collected signature data, and is using these profiles to resolve the potential report-to-track or track-to-track association ambiguities. In this paper, we focus on the management of the HRR-signature data collection. Specifically, the sensor management problem is to determine where to collect signature data on targets in time so as to optimize the utility of the collected data. As with other sensor management problems, determining the optimal data collection is a hard combinatorial problem due to many factors including the large number of possible sensor actions and the complexity of the dynamics. The complexity of the dynamics stems in part from the presence of the sensor slew time. A distinguishing feature of the sensor management problem considered here is that the HRR-signature data collected during the learning phase has no immediate value. To optimize the data collections, a sensor manager must look sufficiently far into the future to adequately trade-off alternative plans. Here, we propose some farsighted algorithms, and evaluate them against a sequential scanning and a greedy algorithm. We present our simulation results obtained by applying these algorithms to a problem of managing a single sensor providing HRR-signature data.

AB - We consider the sensor management problem arising in air-to-ground tracking of moving targets. The sensing-tracking system includes a radar and a feature-aided tracker. The radar collects target-signature data in high-resolution-radar (HRR) mode. The tracker is using the collected HRR-signature data to create and maintain target-track identification information. More specifically, the tracker is learning target-track profiles from the collected signature data, and is using these profiles to resolve the potential report-to-track or track-to-track association ambiguities. In this paper, we focus on the management of the HRR-signature data collection. Specifically, the sensor management problem is to determine where to collect signature data on targets in time so as to optimize the utility of the collected data. As with other sensor management problems, determining the optimal data collection is a hard combinatorial problem due to many factors including the large number of possible sensor actions and the complexity of the dynamics. The complexity of the dynamics stems in part from the presence of the sensor slew time. A distinguishing feature of the sensor management problem considered here is that the HRR-signature data collected during the learning phase has no immediate value. To optimize the data collections, a sensor manager must look sufficiently far into the future to adequately trade-off alternative plans. Here, we propose some farsighted algorithms, and evaluate them against a sequential scanning and a greedy algorithm. We present our simulation results obtained by applying these algorithms to a problem of managing a single sensor providing HRR-signature data.

KW - Farsighted strategy

KW - Feature-aided tracking

KW - HRR-signature data collection

KW - Sensor management

KW - Stochastic dynamic programming

UR - http://www.scopus.com/inward/record.url?scp=33748641002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748641002&partnerID=8YFLogxK

U2 - 10.1117/12.665491

DO - 10.1117/12.665491

M3 - Conference contribution

AN - SCOPUS:33748641002

SN - 0819462918

SN - 9780819462916

VL - 6235

BT - Signal Processing, Sensor Fusion, and Target Recognition XV

ER -