Obtaining JTF-Signature of Space-Debris From Incomplete and Phase-Corrupted Data

Bai, Xueru; Zhou, Feng; Ye, Hui

doi:10.1109/taes.2017.2667899

Cited by 26 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initialize ρ > 0, Z (0) , and B (0) ; 2. For n = 1 : N Update X (n) by (10); Update Z (n) by (13); Update B (n) by ( 12); End 3. Output X (N+1) by (10).…”

Section: Pnp 2d Admm Methodsmentioning

confidence: 99%

“…Typically, one stage consists of three layers, i.e., the reconstruction layer R •, •, •; ρ (n) ; the denoising layer D •, •; w (n) , where w is the network parameter; and the multiplier update layer U •, •, •; η (n) . The three layers correspond to (10), (13), and (12), respectively. In addition, (•) represents the inputs of each layer.…”

Section: Structure Of Panmentioning

confidence: 99%

“…The l 0 -norm optimization, such as orthogonal matching pursuit (OMP) [7] and smoothed L0 (SL0) [8] are sensitive to noise and prone to local optima. For l 1 -norm optimization, a fast iterative shrinkage-thresholding algorithm (FISTA) [9] and alternating direction method of multipliers (ADMM) [10] can guarantee the sparsest solution. However, these methods usually require careful tuning of the regularization parameters, which is still an open problem.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-Resolution ISAR Imaging Based on Plug-and-Play 2D ADMM-Net

Bai

Zhou

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

We propose a deep learning architecture, dubbed Plug-and-play 2D ADMM-Net (PAN), by combining model-driven deep networks and data-driven deep networks for effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging with various signal-to-noise ratios (SNR) and incomplete data scenarios. First, a sparse observation model of 2D ISAR imaging is established, and a 2D ADMM algorithm is presented. On this basis, using the plug and play (PnP) technique, PnP 2D ADMM is proposed, by combining the 2D ADMM algorithm and the deep denoising network DnCNN. Then, we unroll and generalize the PnP 2D ADMM to the PAN architecture, in which all adjustable parameters in the reconstruction layers, denoising layers, and multiplier update layers are learned by end-to-end training through back-propagation. Experimental results showed that the PAN with a single parameter set can achieve noise-robust ISAR imaging with superior reconstruction performance on incomplete simulated and measured data under different SNRs.

show abstract

“…Initialize ρ > 0, Z (0) , and B (0) ; 2. For n = 1 : N Update X (n) by (10); Update Z (n) by (13); Update B (n) by ( 12); End 3. Output X (N+1) by (10).…”

Section: Pnp 2d Admm Methodsmentioning

confidence: 99%

Section: Structure Of Panmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-Resolution ISAR Imaging Based on Plug-and-Play 2D ADMM-Net

Bai

Zhou

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…With growing scientific research and commercial applications in space, more and more malfunctioning satellites and space debris are occupying precious orbital resources which will bring a great threat to the safety of on-orbit spacecrafts [1,2]. In order to utilize or remove them, space robots have been studied and developed for many years [3].…”

Section: Introductionmentioning

confidence: 99%

Kinodynamic Trajectory Optimization of Dual-Arm Space Robot for Stabilizing a Tumbling Target

Lei

Yuan

et al. 2022

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

Capturing and stabilizing tumbling targets using dual-arm space robots are very crucial to on-orbit servicing task. However, it is still very challenging due to the complex dynamics coupling and closed-chain constraints between the manipulators, the base, and the target. In this paper, a kinodynamic trajectory optimization method is proposed to generate the motion of a dual-arm space robot for stabilizing the captured tumbling target, which is formulated and solved as a nonlinear programming problem using direct collocation. Instead of optimizing the trajectory of each joint with the dynamics model of space robot, this method optimizes the trajectory of the tumbling target while considering the kinematics and dynamics constraints between the two arms and the target simultaneously. The objective function of the optimization is defined as weighted detumbling time, base disturbance, and manipulability, in order to avoid singularity and save the energy of space robot for further manipulation. Several physical simulations are carried out to validate the proposed method.

show abstract

“…The l 0 -norm optimization, e.g., orthogonal MP (OMP) [8] and smoothed l 0 -norm method [9], cannot guarantee that the solution is sparsest and may converge to the local minima. The l 1norm optimization, e.g., the fast iterative shrinkage-thresholding algorithm (FISTA) [10,11] and alternating direction method of multipliers (ADMM) [12,13], is the convex approximation of the l 0 -norm [14]. However, the regularization parameter directly affects the performance and how to determine its optimum value remains an open problem [4].…”

Section: Introductionmentioning

confidence: 99%

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Bai

Zhou

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

A deep-learning architecture, dubbed as the 2D-ADMM-Net (2D-ADN), is proposed in this article. It provides effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging under scenarios of low SNRs and incomplete data, by combining model-based sparse reconstruction and data-driven deep learning. Firstly, mapping from ISAR images to their corresponding echoes in the wavenumber domain is derived. Then, a 2D alternating direction method of multipliers (ADMM) is unrolled and generalized to a deep network, where all adjustable parameters in the reconstruction layers, nonlinear transform layers, and multiplier update layers are learned by an end-to-end training through back-propagation. Since the optimal parameters of each layer are learned separately, 2D-ADN exhibits more representation flexibility and preferable reconstruction performance than model-driven methods. Simultaneously, it is able to better facilitate ISAR imaging with limited training samples than data-driven methods owing to its simple structure and small number of adjustable parameters. Additionally, benefiting from the good performance of 2D-ADN, a random phase error estimation method is proposed, through which well-focused imaging can be acquired. It is demonstrated by experiments that although trained by only a few simulated images, the 2D-ADN shows good adaptability to measured data and favorable imaging results with a clear background can be obtained in a short time.

show abstract

Obtaining JTF-Signature of Space-Debris From Incomplete and Phase-Corrupted Data

Cited by 26 publications

References 41 publications

High-Resolution ISAR Imaging Based on Plug-and-Play 2D ADMM-Net

High-Resolution ISAR Imaging Based on Plug-and-Play 2D ADMM-Net

Kinodynamic Trajectory Optimization of Dual-Arm Space Robot for Stabilizing a Tumbling Target

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Contact Info

Product

Resources

About