Scollr summary
What this paper is about
Results indicate that the learned policy can maintain effective interception performance when transferred to larger engagement scales without retraining, and indicate that the learned policy can maintain effective interception performance when transferred to larger engagement scales without retraining.
Full abstract
Read the full abstract
This paper investigates the multi-target interception problem of unmanned aerial vehicle (UAV) swarms. Existing studies commonly rely on global information, inter-UAV communication, or predefined coordination mechanisms, limiting their applicability in communication-constrained and dynamically changing environments. A communication-free multi-target interception model and a Transformer-Enhanced Decentralized Swarm Guidance (TEDSG) framework are proposed. A centralized expert generates coordinated demonstrations using global information, while TEDSG learns to map local observations directly to guidance actions. During execution, each interceptor makes decisions independently without inter-UAV communication or centralized assignment information. Simulation results show that the policy trained in the 5-versus-5 scenario achieves a 90.8% target destruction rate in the unseen 20-versus-20 scenario without retraining. These results indicate that the learned policy can maintain effective interception performance when transferred to larger engagement scales without retraining.
Direct answer
What can I do from this paper page?
Use this page to scan "Communication-Free Multi-Target Interception of UAV Swarms via Transformer-Based Imitation Learning" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Guidance and Control Systems research, save the paper, or map adjacent work.
Research areas
Follow related topics
Citation
BibTeX
@article{You2026Communication,
title = {Communication-Free Multi-Target Interception of UAV Swarms via Transformer-Based Imitation Learning},
author = {Zhutairong You and Chaowang Li and Tianyu Liu and Hao Luo and Zhuo Liu and Feigao Fan and Xuanqi Sun and Xingyong Gao},
journal = {Drones},
year = {2026},
doi = {10.3390/drones10110835},
url = {https://doi.org/10.3390/drones10110835}
}
FAQ
Using this paper in a discovery workflow
How do I find related work for this paper?
Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.
How can I keep up with new Guidance and Control Systems research papers?
Follow Guidance and Control Systems research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.
Can I cite this paper from this page?
This page includes a static BibTeX block for Communication-Free Multi-Target Interception of UAV Swarms via Transformer-Based Imitation Learning. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.
Follow this research in Scollr
Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.
Get the app