Deep Reinforcement Learning-Based Radar Network Target Assignment

Meng, Fanqing; Tian, Kangsheng; Wu, Changfei

doi:10.1109/jsen.2021.3074826

Cited by 28 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that optimizing the RTA in the general case, where multiple radars can be assigned to each target in a multi-target environment, is fundamental and essential, as highlighted in previous studies [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [23].…”

Section: Sub-problem 2: Multi-radar To Multi-target Assignmentmentioning

confidence: 98%

“…However, these algorithms were developed for different problem domains and may not be directly applicable to the MRMTA problem addressed in our work. Although some preliminary work has attempted to address this aspect [23], most studies have designed machine-learning (ML) models with fixed inputs, which may not be suitable for varying environmental factors such as changing numbers of radars or targets. Notably, Meng et al [23] have shown that MRMTA based on deep reinforcement learning outperforms random assignment methods and heuristic algorithms in terms of cumulative detection duration.…”

Section: B Motivations Of This Workmentioning

confidence: 99%

“…Although some preliminary work has attempted to address this aspect [23], most studies have designed machine-learning (ML) models with fixed inputs, which may not be suitable for varying environmental factors such as changing numbers of radars or targets. Notably, Meng et al [23] have shown that MRMTA based on deep reinforcement learning outperforms random assignment methods and heuristic algorithms in terms of cumulative detection duration. However, their approach may not be viable for scenarios with limited data due to the extensive training data required for deep reinforcement learning.…”

Section: B Motivations Of This Workmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Radar-Target Assignment in Low Probability of Intercept Radar Networks: A Machine-Learning Approach

Amiriara,

Andargoli,

Meghdadi

2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

To achieve low probability of intercept (LPI) in radar networks for multiple target detection, it is necessary to find the optimal assignment of distributed radars to targets. The multi-radar to multi-target assignment (MRMTA) problem aims to find the best radar combination, but its brute-force (BF)-based approach over all possible sensor combinations has exponential complexity, making it challenging to implement in networks with a large number of radars or targets. This limits the implementation of the BF approach in networks that prioritize low latency and complexity. To address this challenge, we propose a supervised machine-learning (ML)-based solution for the MRMTA problem. Our proposed implementation scheme performs the training procedure offline, leading to a significant reduction in assignment complexity and processing latency. We conducted extensive numerical simulations to design an ML structure with high accuracy, convergence speed, and scalability. Simulation results demonstrate the efficiency and effectiveness of our proposed ML-based MRMTA solution, which achieves near-optimal LPI performance with considerably lower computation time than benchmark schemes. Our proposed solution has the potential to optimize the assignment of distributed radars to targets in LPI radar networks and improve the performance of complex networks with low latency and complexity requirements.INDEX TERMS Multi-radar to multi-target assignment (MRMTA), supervised machine-learning (ML), low probability intercept radars, feed-forward neural network (FNN), radar network, information fusion.

show abstract

Section: Sub-problem 2: Multi-radar To Multi-target Assignmentmentioning

confidence: 98%

Section: B Motivations Of This Workmentioning

confidence: 99%

Section: B Motivations Of This Workmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Radar-Target Assignment in Low Probability of Intercept Radar Networks: A Machine-Learning Approach

Amiriara,

Andargoli,

Meghdadi

2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…In [17], a parameterised tracking error model of an HFV was derived considering some uncertainties that were approximated by an interval Type II fuzzy neural network. In [18], smooth functions and linear time-varying models were introduced to estimate the boundary of time-varying uncertainty, effectively compensate for the influence of faults, and achieve stable altitude and velocity tracking. In [19], for an uncertain HFV model, fault and hysterical actuators were used for high-performance adaptive controls.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Hybrid Compensation Control of Inertia Uncertainty and Disturbance for Variable Structure Hypersonic Vehicle

Hu,

Cheng,

Yang

2023

IEEE Access

View full text Add to dashboard Cite

This paper presents an adaptive hybrid compensation scheme for disturbances and uncertain inertia parameters of variable-structure hypersonic flight vehicles (HFV). A nominal nonlinear dynamic inverse (NDI) controller with variable-structure harmonic functions guarantees that the system outputs precisely follow the reference commands for a longitudinal HFV model with modelling errors. In the case of inertia uncertainty, a multi-learning law-adaptive NDI controller is proposed to directly compensate for its influence on the tracking performance, which makes the variable-structure HFV robust to inertia uncertainty and reduces the high vibration of velocity and attitude angles. Subsequently, an improved adaptive variable structure NDI controller with a sliding-mode disturbance observer is designed to actively compensate for sea-skimming disturbances and continuously ensure anti-disturbance flight quality. Finally, the active-passive hybrid adaptive control algorithms compensate for the inertia uncertainty and disturbance of the variable-structure HFV. The proposed method's efficacy was verified through a semi-physical system simulation, while Lyapunov functions demonstrated the system stability.

show abstract