.png){kind=icon}
.png){kind=icon}
Return
Green Emergency Communications in RIS- and MA-Assisted Multi-UAV SAGINs: A Partially Observable Reinforcement Learning Approach
.png){kind=icon}
PRE
AI
L
Y
王
DOI：10.1109/tgcn.2026.3716272.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In post-disaster space–air–ground integrated networks (SAGINs), terrestrial infrastructure is often impaired, and unmanned aerial vehicles (UAVs) must rapidly restore connectivity for mission-critical ground terminals in cluttered non-line-of-sight (NLoS) urban environments. To enhance coverage, UAVs employ movable antennas (MAs), while reconfigurable intelligent surfaces (RISs) on surviving high-rise buildings redirect signals. The key challenge is communication-limited partial observability, leaving each UAV with a narrow, fast-changing neighborhood view that destabilizes value estimation. Existing multi-agent reinforcement learning (MARL) approaches are inadequate, in that non-communication methods rely on unavailable global critics, heuristic sharing is brittle and redundant, and learnable protocols (e.g., CommNet, DIAL) lose per-neighbor structure and aggravate non-stationarity under tight bandwidth. To address partial observability, we propose a spatiotemporal A2C where each UAV transmits prior-decision messages with local state, a compact policy fingerprint, and a recurrent belief, encoded per neighbor and concatenated. A spatial discount shapes value targets to emphasize local interactions, while analysis under one-hop-per-slot latency explains stable training with delayed views. Experimental results show our policy outperforms IA2C, ConseNet, FPrint, DIAL, and CommNet, achieving faster convergence, higher asymptotic reward, reduced temporal-difference(TD), advantage estimation errors, and a better communication throughput–energy trade-off.
Keywords:
Partial observability
multi-agent reinforcement learning
unmanned aerial vehicles
reconfigurable intelligent surfaces
movable antenna
Journal
I
IF:
6.7
Papers:
1.3K
Citations:
4.3K
Organization
Cited Papers