Scene-adaptive radar tracking with deep reinforcement learning
Stephan M, Servadei L, Arjona-Medina J, Santra A, Wille R, Fischer G (2022)
Publication Type: Journal article
Publication year: 2022
Journal
Original Authors: Michael Stephan, Lorenzo Servadei, José Arjona-Medina, Avik Santra, Robert Wille, Georg Fischer
Pages Range: 100284
Article Number: 100284
DOI: 10.1016/j.mlwa.2022.100284
Abstract
Multi-target tracking with radars is a highly challenging problem due to detection artifacts, sensor noise, and interference sources. The traditional signal processing chain is, therefore, a complex combination of various algorithms with several tunable tracking-parameters. Usually, these are initially set by engineers and are independent of the scene tracked. For this reason, they are often non-optimal and generate poorly performing tracking. In this context, scene-adaptive radar processing refers to algorithms that can sense, understand and learn information related to detected targets as well as the environment and adapt its tracking-parameters to optimize the desired goal. In this paper, we propose a Deep Reinforcement Learning framework that guides the scene-adaptive choice of radar tracking-parameters towards an improved performance on multi-target tracking.
Authors with CRIS profile
Michael Stephan
Lehrstuhl für Technische Elektronik
Georg Fischer
Professur für Technische Elektronik
Involved external institutions
Germany (DE)
Austria (AT)How to cite
APA:
Stephan, M., Servadei, L., Arjona-Medina, J., Santra, A., Wille, R., & Fischer, G. (2022). Scene-adaptive radar tracking with deep reinforcement learning. Machine Learning with Applications, 100284. https://doi.org/10.1016/j.mlwa.2022.100284
MLA:
Stephan, Michael, et al. "Scene-adaptive radar tracking with deep reinforcement learning." Machine Learning with Applications (2022): 100284.
BibTeX: Download