Adaptive Radar Detection in Gaussian Disturbance With Structured Covariance Matrix via Invariance Theory

Tang, Mengjiao; Rong, Yao; Maio, Antonio De; Chen, Chen; Zhou, Jie

doi:10.1109/tsp.2019.2941119

Cited by 25 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we consider the influence of Gaussian random noise on the observation. In most studies, these noises are considered white Gaussian distribution with zero means [26]. The noise we introduce includes a Gaussian noise with a variance correlated with distance and a Gaussian noise that is independent of distance.…”

Section: Problem Formulationmentioning

confidence: 99%

Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target

Zhu

Zhao

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

In missile guidance, pursuit performance is seriously degraded due to the uncertainty and randomness in target maneuverability, detection delay, and environmental noise. In many methods, accurately estimating the acceleration of the target or the time-to-go is needed to intercept the maneuvering target, which is hard in an environment with uncertainty. In this paper, we propose an assisted deep reinforcement learning (ARL) algorithm to optimize the neural network-based missile guidance controller for head-on interception. Based on the relative velocity, distance, and angle, ARL can control the missile to intercept the maneuvering target and achieve large terminal intercept angle. To reduce the influence of environmental uncertainty, ARL predicts the target’s acceleration as an auxiliary supervised task. The supervised learning task improves the ability of the agent to extract information from observations. To exploit the agent’s good trajectories, ARL presents the Gaussian self-imitation learning to make the mean of action distribution approach the agent’s good actions. Compared with vanilla self-imitation learning, Gaussian self-imitation learning improves the exploration in continuous control. Simulation results validate that ARL outperforms traditional methods and proximal policy optimization algorithm with higher hit rate and larger terminal intercept angle in the simulation environment with noise, delay, and maneuverable target.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target

Zhu

Zhao

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Invariance theory turned out to be useful in heterogeneous environments, characterized by Gaussian interference with spatially varying power, to derive a class of detection rules exhibiting specific symmetries that ensure the CFAR property [19]. In [20], detection of targets embedded in Gaussian disturbance sharing a block-diagonal covariance structure is addressed. A unified framework considering point-like, rangespread, and subspace targets is provided to model the general problem, and a new family of invariant detectors is proposed to overcome the unavailability of the GLRT in closed-form.…”

Section: Introductionmentioning

confidence: 99%

Design of Customized Adaptive Radar Detectors in the CFAR Feature Plane

Coluccia¹,

Fascista²,

Ricci³

2022

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

The paper addresses the design of adaptive radar detectors with desired behavior, in Gaussian disturbance with unknown statistics. Specifically, based on detection probability specifications for chosen signal-to-noise ratios and steering vector mismatch levels, a methodology for the design of customized constant false alarm rate (CFAR) detectors is devised in a suitable feature plane obtained from two maximal invariant statistics. To overcome the analytical and numerical intractability of the resulting optimization problem, a novel general reducedcomplexity algorithm is developed, which is shown to be effective in providing a feasible solution (i.e., fulfilling a constraint on the probability of false alarm) while controlling the behavior under both matched and mismatched conditions, so enabling the design of fully customized adaptive CFAR detectors.

show abstract

Development of Moment Quality Criterion and Polynomial Methods for Signals Detection and Distinction in Non-Gaussian Noise

Smirnov,

Zorin,

Palahina

et al. 2024

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Adaptive Radar Detection in Gaussian Disturbance With Structured Covariance Matrix via Invariance Theory

Cited by 25 publications

References 44 publications

Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target

Missile guidance with assisted deep reinforcement learning for head-on interception of maneuvering target

Design of Customized Adaptive Radar Detectors in the CFAR Feature Plane

Development of Moment Quality Criterion and Polynomial Methods for Signals Detection and Distinction in Non-Gaussian Noise

Contact Info

Product

Resources

About