Intelligent Acquisition of Dynamic Targets via Multi-Source Information: A Fusion Framework Integrating Deep Reinforcement Learning with Evidence Theory.
Saved in:
| Title: | Intelligent Acquisition of Dynamic Targets via Multi-Source Information: A Fusion Framework Integrating Deep Reinforcement Learning with Evidence Theory. |
|---|---|
| Authors: | Yu, Jiyao1 (AUTHOR), Zhu, Bin1 (AUTHOR) zhubin@nudt.edu.cn, Chen, Yi1 (AUTHOR), Xie, Bo1 (AUTHOR), Feng, Xuanling1 (AUTHOR), Yan, Hongfei1 (AUTHOR), Zeng, Jian1 (AUTHOR), Wang, Runhua1 (AUTHOR) |
| Source: | Remote Sensing. Mar2026, Vol. 18 Issue 5, p689. 26p. |
| Subjects: | Multisensor data fusion, Target acquisition, Monte Carlo method, Decision making, Detectors, Uncertainty (Information theory), Reinforcement learning |
| Abstract: | Highlights: What are the main findings? Novel Framework: We propose the Evidence–Reinforcement Learning-based Decision and Control (ERL-DC) framework, a closed-loop architecture that innovatively integrates Dempster–Shafer (D–S) evidence theory for uncertainty-aware decision-level fusion with Deep Reinforcement Learning (DRL) for adaptive sensor control. Key Capability: The framework effectively addresses the challenge of real-time spatiotemporal association and confidence fusion between heterogeneous sensor data in dynamic, noisy environments. Superior Performance: Multiple Monte Carlo simulation runs demonstrate that, compared to the conventional threshold logic method combined with Model Predictive Control (MPC), the proposed ERL-DC framework reduces the Average Decision Time (ADT) from 7.51 s to 4.53 s, corresponding to a relative reduction of 39.68%. Statistical results indicate that it also improves the Net Discrimination Accuracy (NDA) from 57.8% to 95.6%, which corresponds to an absolute increase of 37.8 percentage points. What are the implications of the main findings? Provides a unified solution for intelligent multi-source data correlation, uncertainty-aware fusion, and adaptive sensor control. Supplies a new paradigm from post hoc fusion to active, decision-guided information acquisition, offering insights for constrained remote sensing resource scheduling and robust decision-making under uncertainty. Accurate acquisition of low-observable targets with a minimal radar cross-section (RCS) poses a significant challenge for multi-source remote sensing systems, such as integrated radar–electro-optical (REO) platforms, particularly in complex electromagnetic environments characterized by strong noise interference and a high false-alarm rate. Conventional methods, which often treat data association and fusion from heterogeneous sensors as separate, offline processes, struggle with the dynamic uncertainties and real-time decision requirements of such scenarios. To address these limitations, this paper proposes a novel Evidence–Reinforcement Learning-based Decision and Control (ERL-DC) framework. It operates through a closed-loop architecture consisting of three core modules: A static assessment model for initial target prioritization, a Dempster–Shafer (D–S) evidence-based multi-source data decision generator for dynamic information fusion and uncertainty-aware target selection, and a Deep Reinforcement Learning (DRL) controller for noise-robust sensor steering. A high-fidelity simulation environment was developed to model the multi-source data stream, encompassing radar detection with clutter and false targets, as well as the physical constraints of the electro-optical (EO) servo system. Based on the averaged results from multiple Monte Carlo simulations, the proposed ERL-DC framework reduced the Average Decision Time (ADT) from 7.51 s to 4.53 s, corresponding to an absolute reduction of 2.98 s when compared to the conventional method integrating threshold logic with Model Predictive Control (MPC). Furthermore, the Net Discrimination Accuracy (NDA), derived from the statistical outcomes across all the simulation runs, exhibited an absolute increase of 37.8 percentage points, rising from 57.8% to 95.6%. These results indicate that ERL-DC achieves a more favorable trade-off in terms of scheduling efficiency, decision robustness, and resource utilization. The primary contribution is an intelligent, closed-loop architecture that tightly couples high-level evidential reasoning for multi-source data fusion with low-level adaptive control. Within the simulated environment characterized by clutter, false targets, and angular measurement noise, ERL-DC demonstrates improved target discrimination accuracy and decision efficiency compared to conventional methods. Future work will focus on online parameter adaptation and validation on physical platforms. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? Novel Framework: We propose the Evidence–Reinforcement Learning-based Decision and Control (ERL-DC) framework, a closed-loop architecture that innovatively integrates Dempster–Shafer (D–S) evidence theory for uncertainty-aware decision-level fusion with Deep Reinforcement Learning (DRL) for adaptive sensor control. Key Capability: The framework effectively addresses the challenge of real-time spatiotemporal association and confidence fusion between heterogeneous sensor data in dynamic, noisy environments. Superior Performance: Multiple Monte Carlo simulation runs demonstrate that, compared to the conventional threshold logic method combined with Model Predictive Control (MPC), the proposed ERL-DC framework reduces the Average Decision Time (ADT) from 7.51 s to 4.53 s, corresponding to a relative reduction of 39.68%. Statistical results indicate that it also improves the Net Discrimination Accuracy (NDA) from 57.8% to 95.6%, which corresponds to an absolute increase of 37.8 percentage points. What are the implications of the main findings? Provides a unified solution for intelligent multi-source data correlation, uncertainty-aware fusion, and adaptive sensor control. Supplies a new paradigm from post hoc fusion to active, decision-guided information acquisition, offering insights for constrained remote sensing resource scheduling and robust decision-making under uncertainty. Accurate acquisition of low-observable targets with a minimal radar cross-section (RCS) poses a significant challenge for multi-source remote sensing systems, such as integrated radar–electro-optical (REO) platforms, particularly in complex electromagnetic environments characterized by strong noise interference and a high false-alarm rate. Conventional methods, which often treat data association and fusion from heterogeneous sensors as separate, offline processes, struggle with the dynamic uncertainties and real-time decision requirements of such scenarios. To address these limitations, this paper proposes a novel Evidence–Reinforcement Learning-based Decision and Control (ERL-DC) framework. It operates through a closed-loop architecture consisting of three core modules: A static assessment model for initial target prioritization, a Dempster–Shafer (D–S) evidence-based multi-source data decision generator for dynamic information fusion and uncertainty-aware target selection, and a Deep Reinforcement Learning (DRL) controller for noise-robust sensor steering. A high-fidelity simulation environment was developed to model the multi-source data stream, encompassing radar detection with clutter and false targets, as well as the physical constraints of the electro-optical (EO) servo system. Based on the averaged results from multiple Monte Carlo simulations, the proposed ERL-DC framework reduced the Average Decision Time (ADT) from 7.51 s to 4.53 s, corresponding to an absolute reduction of 2.98 s when compared to the conventional method integrating threshold logic with Model Predictive Control (MPC). Furthermore, the Net Discrimination Accuracy (NDA), derived from the statistical outcomes across all the simulation runs, exhibited an absolute increase of 37.8 percentage points, rising from 57.8% to 95.6%. These results indicate that ERL-DC achieves a more favorable trade-off in terms of scheduling efficiency, decision robustness, and resource utilization. The primary contribution is an intelligent, closed-loop architecture that tightly couples high-level evidential reasoning for multi-source data fusion with low-level adaptive control. Within the simulated environment characterized by clutter, false targets, and angular measurement noise, ERL-DC demonstrates improved target discrimination accuracy and decision efficiency compared to conventional methods. Future work will focus on online parameter adaptation and validation on physical platforms. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18050689 |
