Resource optimization for RIS-UAV integrated air-ground cooperative semantic communication driven by deep reinforcement learning
- 1Center for Target Cognition Information Processing Science and Technology, and Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, Beijing Information Science and Technology University, Beijing, China
- 2Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China
Abstract
To meet the 6G semantic transmission requirements, this paper proposes an air-ground dual-mode semantic transmission architecture for Reconfigurable Intelligent Surface (RIS)-aided Unmanned Aerial Vehicle (UAV) networks. By dynamically assigning RIS-reflected links to users with long packets and direct UAV line-of-sight (LOS) links to users with short packets, we jointly optimize semantic symbols, RIS phase shifts, UAV three-dimensional (3D) trajectory, and transmit power to maximize the system-level semantic Quality of Experience (QoE). To efficiently solve the formulated non-convex mixed-integer optimization problem, we present an Action Space Decoupled Hybrid Deep Reinforcement Learning (ASD-HDRL) framework, which employs the Dueling Double Deep Q-Network (D3QN) for discrete semantic resource decision-making and Deep Deterministic Policy Gradient (DDPG) for continuous control optimization. Simulation results verify that the proposed ASD-HDRL achieves superior system-level semantic QoE performance.
Related
- The resource cost of cooperative invasion
- Real-time integrated spectrum tunable underwater illumination-imaging and wireless optical communication system using a RGB-LED array
- Atmospheric Turbulence-Aware Optimization of Generalized Kennedy Receivers for Coherent-State BPSK Quantum Communication
- Optimization of fluid mixing by reinforcement learning using limit cycles of a dynamical system
- A Novel Scheme for Inter-Satellite Integrated Laser Ranging and Communication in Space-Based GW Detection
BibTeX
@article{dai2026resource,
title = {{Resource optimization for RIS-UAV integrated air-ground cooperative semantic communication driven by deep reinforcement learning}},
author = {Yufei Dai and Yuanyuan Yao and Sai Huang and Xinwei Yue},
journal = {Frontiers in Physics},
year = {2026},
month = oct,
doi = {10.3389/fphy.2026.1988637},
url = {https://doi.org/10.3389/fphy.2026.1988637},
note = {CC BY},
}
RIS
TY - JOUR
TI - Resource optimization for RIS-UAV integrated air-ground cooperative semantic communication driven by deep reinforcement learning
AU - Yufei Dai
AU - Yuanyuan Yao
AU - Sai Huang
AU - Xinwei Yue
PY - 2026
DA - 2026/10/26
JO - Frontiers in Physics
DO - 10.3389/fphy.2026.1988637
UR - https://doi.org/10.3389/fphy.2026.1988637
AB - To meet the 6G semantic transmission requirements, this paper proposes an air-ground dual-mode semantic transmission architecture for Reconfigurable Intelligent Surface (RIS)-aided Unmanned Aerial Vehicle (UAV) networks. By dynamically assigning RIS-reflected links to users with long packets and direct UAV line-of-sight (LOS) links to users with short packets, we jointly optimize semantic symbols, RIS phase shifts, UAV three-dimensional (3D) trajectory, and transmit power to maximize the system-level semantic Quality of Experience (QoE). To efficiently solve the formulated non-convex mixed-integer optimization problem, we present an Action Space Decoupled Hybrid Deep Reinforcement Learning (ASD-HDRL) framework, which employs the Dueling Double Deep Q-Network (D3QN) for discrete semantic resource decision-making and Deep Deterministic Policy Gradient (DDPG) for continuous control optimization. Simulation results verify that the proposed ASD-HDRL achieves superior system-level semantic QoE performance.
SN - 2296-424X
ER -