Research map / Graph learning / Knowledge and temporal graphs
Resilient UAV Swarm with Fast Connectivity Recovery and Extensive Coverage
Yabin Peng, Chenyu Zhou, Hainan Cui, Tong Duan, Haoyang Chen, Fan Zhang, Shaoxun Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add inter-subnetwork translation (IST) via multipartite graph convolution (ablation) | R2C · Random deployment, 60% failure | REC: 0.477 -> 0.204 | Improved |
| add inter-subnetwork translation (IST) (ablation) | R2C · Random deployment, 80% failure | connectivity restoration: w/o IST fails to recover (–) vs 0.625 | Improved |
| add intra-subnetwork expansion (ISE) via buffered virtual force (ablation) | R2C · Random deployment, 60% failure | COV: 0.896 -> 0.951 | Improved |
| add intra-subnetwork expansion (ISE) (ablation) | R2C · Random deployment, 80% failure | COV: 0.611 -> 0.681 | Improved |
| add adaptive weighted fusion (AWF) instead of fixed 0.5 weights (ablation) | R2C · Random deployment, 60% failure | REC: 0.257 -> 0.204 | Improved |
| add adaptive weighted fusion (AWF) (ablation) | R2C · Uniform deployment, 60% failure | REC: 0.192 -> 0.181 | Improved |
| add adaptive weighted fusion (AWF) (ablation) | R2C · Random deployment, 20% failure | REC: 0.023 -> 0.023 | No clear effect |
| add intra-subnetwork expansion (ISE) on top of IST only (ablation) | R2C · Random deployment, 20% failure | REC: 0.046 -> 0.023 | Improved |
| add IST on top of ISE (ablation) | R2C · Uniform deployment, 80% failure | COV: 0.704 -> 0.668 | Hurt |
| use R2C instead of MDSG-APF | UAV swarm self-healing, random deployment · Random deployment, avg runtime | runtime: 0.681 -> 1.542 s | Hurt |
| use R2C instead of MDSG-GC | UAV swarm self-healing, random deployment · Random deployment, avg REC | REC: 0.339 -> 0.231 | Improved |
| use R2C instead of MDSG-GC | UAV swarm self-healing, random deployment · Random deployment, avg runtime | runtime: 5.234 -> 1.542 s | Improved |
Closest papers by meaning
- U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks (AAAI 2026 · similarity 0.80)
- ResMAS: Resilience Optimization in LLM-based Multi-agent Systems (AAAI 2026 · similarity 0.79)
- RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.79)
- RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation (ICML 2026 · similarity 0.79)
- Exact Algorithms for Multiagent Path Finding with Communication Constraints on Tree-Like Structures (AAAI 2025 · similarity 0.79)
- Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning (ICLR 2025 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
