Loading [MathJax]/extensions/MathZoom.js
Train Offline, Refine Online: Improving Cognitive Tracking Radar Performance With Approximate Policy Iteration and Deep Neural Networks | IEEE Journals & Magazine | IEEE Xplore

Train Offline, Refine Online: Improving Cognitive Tracking Radar Performance With Approximate Policy Iteration and Deep Neural Networks


Abstract:

A cognitive tracking radar continuously acquires, stores, and exploits knowledge from its target environment in order to improve kinematic tracking performance. In this w...Show More

Abstract:

A cognitive tracking radar continuously acquires, stores, and exploits knowledge from its target environment in order to improve kinematic tracking performance. In this work, we apply a reinforcement learning (RL) technique, API-DNN, based on approximate policy iteration (API) with a deep neural network (DNN) policy to cognitive radar tracking. API-DNN iteratively improves upon an initial base policy using repeated application of rollout and supervised learning. This approach can appropriately balance online versus offline computation in order to improve efficiency and can adapt to changes in problem specification through online replanning. Prior state-of-the-art cognitive radar tracking approaches either rely on sophisticated search procedures with heuristics and carefully selected hyperparameters or deep RL (DRL) agents based on exotic DNN architectures with poorly understood performance guarantees. API-DNN, instead, is based on well-known principles of rollout, Monte Carlo simulation, and basic DNN function approximation. We demonstrate the effectiveness of API-DNN in cognitive radar simulations based on a standard maneuvering target tracking benchmark scenario. We also show how API-DNN can implement online replanning with updated target information.
Published in: IEEE Transactions on Radar Systems ( Volume: 3)
Page(s): 57 - 70
Date of Publication: 17 December 2024
Electronic ISSN: 2832-7357

Funding Agency:

Author image of Brian W. Rybicki
Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA
U.S. Naval Research Laboratory, Washington, DC, USA
Brian W. Rybicki (Member, IEEE) received the B.S. and M.S. degrees in electrical engineering from Penn State University, University Park, PA, USA, in 2006 and 2008, respectively. He is currently pursuing the Ph.D. degree in electrical and computer engineering with George Mason University, Fairfax, VA, USA.
From 2008 to 2012, he was an Associate Staff Member with the MIT Lincoln Laboratory, Lexington, MA, USA. From 2012 to ...Show More
Brian W. Rybicki (Member, IEEE) received the B.S. and M.S. degrees in electrical engineering from Penn State University, University Park, PA, USA, in 2006 and 2008, respectively. He is currently pursuing the Ph.D. degree in electrical and computer engineering with George Mason University, Fairfax, VA, USA.
From 2008 to 2012, he was an Associate Staff Member with the MIT Lincoln Laboratory, Lexington, MA, USA. From 2012 to ...View more
Author image of Jill K. Nelson
Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA
Jill K. Nelson (Senior Member, IEEE) received the B.S. degree in electrical engineering and the BA degree in economics from Rice University, Houston, TX, USA, in 1998, and the M.S. and Ph.D. degrees in electrical engineering from the University of Illinois at Urbana–Champaign, Urbana, IL, USA, in 2001 and 2005, respectively.
She spent three years as the Program Director of the Division of Undergraduate Education, National ...Show More
Jill K. Nelson (Senior Member, IEEE) received the B.S. degree in electrical engineering and the BA degree in economics from Rice University, Houston, TX, USA, in 1998, and the M.S. and Ph.D. degrees in electrical engineering from the University of Illinois at Urbana–Champaign, Urbana, IL, USA, in 2001 and 2005, respectively.
She spent three years as the Program Director of the Division of Undergraduate Education, National ...View more

Author image of Brian W. Rybicki
Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA
U.S. Naval Research Laboratory, Washington, DC, USA
Brian W. Rybicki (Member, IEEE) received the B.S. and M.S. degrees in electrical engineering from Penn State University, University Park, PA, USA, in 2006 and 2008, respectively. He is currently pursuing the Ph.D. degree in electrical and computer engineering with George Mason University, Fairfax, VA, USA.
From 2008 to 2012, he was an Associate Staff Member with the MIT Lincoln Laboratory, Lexington, MA, USA. From 2012 to 2015, he was an Electrical Engineer with Applied Technology, Inc., King George, VA, USA. Since 2015, he has been an Electronics Engineer with the U.S. Naval Research Laboratory (NRL), Washington, DC, USA. His research interests include machine learning, radar systems, optimal control, and signal processing.
Mr. Rybicki was selected for the NRL Edison Memorial Graduate Training Program in 2016. He received the Alan Berman Award for outstanding publication at NRL in 2021.
Brian W. Rybicki (Member, IEEE) received the B.S. and M.S. degrees in electrical engineering from Penn State University, University Park, PA, USA, in 2006 and 2008, respectively. He is currently pursuing the Ph.D. degree in electrical and computer engineering with George Mason University, Fairfax, VA, USA.
From 2008 to 2012, he was an Associate Staff Member with the MIT Lincoln Laboratory, Lexington, MA, USA. From 2012 to 2015, he was an Electrical Engineer with Applied Technology, Inc., King George, VA, USA. Since 2015, he has been an Electronics Engineer with the U.S. Naval Research Laboratory (NRL), Washington, DC, USA. His research interests include machine learning, radar systems, optimal control, and signal processing.
Mr. Rybicki was selected for the NRL Edison Memorial Graduate Training Program in 2016. He received the Alan Berman Award for outstanding publication at NRL in 2021.View more
Author image of Jill K. Nelson
Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA
Jill K. Nelson (Senior Member, IEEE) received the B.S. degree in electrical engineering and the BA degree in economics from Rice University, Houston, TX, USA, in 1998, and the M.S. and Ph.D. degrees in electrical engineering from the University of Illinois at Urbana–Champaign, Urbana, IL, USA, in 2001 and 2005, respectively.
She spent three years as the Program Director of the Division of Undergraduate Education, National Science Foundation (NSF), Alexandria, VA, USA. She is currently an Associate Professor of Electrical and Computer Engineering and the Associate Dean of Undergraduate Programs with the College of Engineering and Computing, George Mason University, Fairfax, VA, USA. Her disciplinary research lies in statistical signal processing, specifically detection, and estimation for applications in sonar, target tracking, and physical layer communications. She also studies machine intelligence as it applies to automating active sonar and developing collaborative intelligent radio networks.
Dr. Nelson was a recipient of the NSF CAREER Award in 2010 and the Mac Van Valkenburg Early Career Teaching Award from the IEEE Education Society in 2014. She is a Member at Large of the IEEE Education Society Board of Governors and a member of Phi Beta Kappa, Tau Beta Pi, and Eta Kappa Nu.
Jill K. Nelson (Senior Member, IEEE) received the B.S. degree in electrical engineering and the BA degree in economics from Rice University, Houston, TX, USA, in 1998, and the M.S. and Ph.D. degrees in electrical engineering from the University of Illinois at Urbana–Champaign, Urbana, IL, USA, in 2001 and 2005, respectively.
She spent three years as the Program Director of the Division of Undergraduate Education, National Science Foundation (NSF), Alexandria, VA, USA. She is currently an Associate Professor of Electrical and Computer Engineering and the Associate Dean of Undergraduate Programs with the College of Engineering and Computing, George Mason University, Fairfax, VA, USA. Her disciplinary research lies in statistical signal processing, specifically detection, and estimation for applications in sonar, target tracking, and physical layer communications. She also studies machine intelligence as it applies to automating active sonar and developing collaborative intelligent radio networks.
Dr. Nelson was a recipient of the NSF CAREER Award in 2010 and the Mac Van Valkenburg Early Career Teaching Award from the IEEE Education Society in 2014. She is a Member at Large of the IEEE Education Society Board of Governors and a member of Phi Beta Kappa, Tau Beta Pi, and Eta Kappa Nu.View more

Contact IEEE to Subscribe

References

References is not available for this document.