Poster Abstract: Emergency Networking Using UAVs: A Reinforcement Learning Approach with Large Language Model
Authors:
- 13 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 281-282
Abstract
Utilizing unmanned aerial vehicles (UAVs) as mobile access points can assist urban communication systems in establishing emergency networks in disaster scenarios. In this paper, to organize UAVs in large-scale environments for networking purposes, we propose a multi-agent reinforcement learning (MARL) model, in which the design of a selective parameter sharing mechanism and a grouping strategy enhances the model’s scalability. Furthermore, the model adopts a reward mechanism based on intrinsic motivation, using the Large Language Model (LLM), to accelerate the optimization process. Numerical results demonstrate that this algorithm outperforms existing alternatives.Keywords
Funding Information
- Tsinghua Shenzhen International Graduate School
This publication has 7 references indexed in Scilit:
- Path Generation for Wheeled Robots Autonomous Navigation on Vegetated TerrainIEEE Robotics and Automation Letters, 2023
- Scheduling UAV Swarm with Attention-based Graph Reinforcement Learning for Ground-to-air Heterogeneous Data Communication2023
- Privacy-preserving push-sum distributed cubature information filter for nonlinear target tracking with switching directed topologiesISA Transactions, 2022
- Cooperative Trajectory Design of Multiple UAV Base Stations With Heterogeneous Graph Neural NetworksIEEE Transactions on Wireless Communications, 2022
- DeliverSense: Efficient Delivery Drone Scheduling for Crowdsensing with Deep Reinforcement Learning2022
- TRACT: Towards Large-Scale Crowdsensing With High-Efficiency Swarm Path Planning2022
- Achieving air-ground communications in 802.11 networks with three-dimensional aerial mobility2013