Multi-Target Radar Search and Track Using Sequence-Capable Deep Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913698578169856 |
|---|---|
| author | Ewers, Jan-Hendrik Cormack, David Gibbs, Joe Anderson, David |
| author_facet | Ewers, Jan-Hendrik Cormack, David Gibbs, Joe Anderson, David |
| contents | The research addresses sensor task management for radar systems, focusing on efficiently searching and tracking multiple targets using reinforcement learning. The approach develops a 3D simulation environment with an active electronically scanned array radar, using a multi-target tracking algorithm to improve observation data quality. Three neural network architectures were compared including an approach using fated recurrent units with multi-headed self-attention. Two pre-training techniques were applied: behavior cloning to approximate a random search strategy and an auto-encoder to pre-train the feature extractor. Experimental results revealed that search performance was relatively consistent across most methods. The real challenge emerged in simultaneously searching and tracking targets. The multi-headed self-attention architecture demonstrated the most promising results, highlighting the potential of sequence-capable architectures in handling dynamic tracking scenarios. The key contribution lies in demonstrating how reinforcement learning can optimize sensor management, potentially improving radar systems' ability to identify and track multiple targets in complex environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13584 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Target Radar Search and Track Using Sequence-Capable Deep Reinforcement Learning Ewers, Jan-Hendrik Cormack, David Gibbs, Joe Anderson, David Machine Learning Systems and Control The research addresses sensor task management for radar systems, focusing on efficiently searching and tracking multiple targets using reinforcement learning. The approach develops a 3D simulation environment with an active electronically scanned array radar, using a multi-target tracking algorithm to improve observation data quality. Three neural network architectures were compared including an approach using fated recurrent units with multi-headed self-attention. Two pre-training techniques were applied: behavior cloning to approximate a random search strategy and an auto-encoder to pre-train the feature extractor. Experimental results revealed that search performance was relatively consistent across most methods. The real challenge emerged in simultaneously searching and tracking targets. The multi-headed self-attention architecture demonstrated the most promising results, highlighting the potential of sequence-capable architectures in handling dynamic tracking scenarios. The key contribution lies in demonstrating how reinforcement learning can optimize sensor management, potentially improving radar systems' ability to identify and track multiple targets in complex environments. |
| title | Multi-Target Radar Search and Track Using Sequence-Capable Deep Reinforcement Learning |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2502.13584 |