USA flag logo/image

An Official Website of the United States Government

Parameter Adaptation for Target Recognition in LADAR (PATROL)

Award Information

Agency:
Department of Defense
Branch:
Air Force
Award ID:
67787
Program Year/Program:
2004 / SBIR
Agency Tracking Number:
F041-230-0530
Solicitation Year:
N/A
Solicitation Topic Code:
N/A
Solicitation Number:
N/A
Small Business Information
Charles River Analytics Inc.
625 Mount Auburn Street Cambridge, MA 02138-
View profile »
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No
 
Phase 1
Fiscal Year: 2004
Title: Parameter Adaptation for Target Recognition in LADAR (PATROL)
Agency / Branch: DOD / USAF
Contract: FA8650-04-M-1658
Award Amount: $99,855.00
 

Abstract:

Automatic Target Recognition (ATR) algorithms are extremely sensitive to differences between the operating conditions under which they are trained and the extended operating conditions in which the fielded algorithms operate. For ATR algorithms to robustly recognize targets while retaining low false alarm rates, they must be able to identify the conditions under which they are operating and tune their parameters on the fly. In this proposal, we present a method for tuning the parameters of a model based ATR algorithm using estimates of the current operating conditions. The problem has two components: 1) identifying the current operating conditions and 2) using that information to tune parameters to improve performance. In this project, we will explore the use of a learning technique called Q-learning for parameter adaptation. In Q-learning, we first define a set of valid states describing the world (the operating conditions of interest, such as the level of obscuration). Next, actions (or parameter settings used by the ATR) are defined that are applied when in that state. Parameter settings for each operating condition are learned using an off-line reinforcement learning feedback loop. The result is a lookup table to select the optimal parameter settings for each operation condition.

Principal Investigator:

Mark R. Stevens
Principal Scientist
6174913474
mstevens@cra.com

Business Contact:

Paul G. Gonsalves
Vice President
6174913474
pgonsalves@cra.com
Small Business Information at Submission:

CHARLES RIVER ANALYTICS, INC.
625 Mount Auburn Street Cambridge, MA 02138

EIN/Tax ID: 042803764
DUNS: N/A
Number of Employees:
Woman-Owned: No
Minority-Owned: No
HUBZone-Owned: No