Joint Communication Scheduling and Velocity Control for Multi-UAV-Assisted Post-Disaster Monitoring: An Attention-Based In-Context Learning Approach

2025-10-07

AI Summary

To address high sensor data packet loss rates in post-disaster multi-UAV cooperative monitoring, this paper jointly optimizes UAV communication scheduling and flight velocity, proposing an Attention-Enhanced In-Context Learning method (AIC-VDS). AIC-VDS is the first to introduce attention-based in-context learning into real-time multi-UAV control—requiring no offline training and enabling rapid decision-making solely via natural-language prompts and few-shot examples. It dynamically fuses heterogeneous real-time information, including sensor battery levels, queue lengths, channel states, and UAV trajectories. Simulation results demonstrate that AIC-VDS significantly reduces packet loss compared to Deep Q-Networks and maximum channel gain baselines, thereby enhancing both emergency response timeliness and communication reliability. Its core innovation lies in eliminating the simulation-to-reality gap and high computational overhead inherent in deep reinforcement learning, achieving zero-shot task adaptation.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Multiagent Systems: Agent Communication

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recently, Unmanned Aerial Vehicles (UAVs) are increasingly being investigated to collect sensory data in post-disaster monitoring scenarios, such as tsunamis, where early actions are critical to limit coastal damage. A major challenge is to design the data collection schedules and flight velocities, as unfavorable schedules and velocities can lead to transmission errors and buffer overflows of the ground sensors, ultimately resulting in significant packet loss. Meanwhile, online Deep Reinforcement Learning (DRL) solutions have a complex training process and a mismatch between simulation and reality that does not meet the urgent requirements of tsunami monitoring. Recent advances in Large Language Models (LLMs) offer a compelling alternative. With their strong reasoning and generalization capabilities, LLMs can adapt to new tasks through In-Context Learning (ICL), which enables task adaptation through natural language prompts and example-based guidance without retraining. However, LLM models have input data limitations and thus require customized approaches. In this paper, a joint optimization of data collection schedules and velocities control for multiple UAVs is proposed to minimize data loss. The battery level of the ground sensors, the length of the queues, and the channel conditions, as well as the trajectories of the UAVs, are taken into account. Attention-Based In-Context Learning for Velocity Control and Data Collection Schedule (AIC-VDS) is proposed as an alternative to DRL in emergencies. The simulation results show that the proposed AIC-VDS outperforms both the Deep-Q-Network (DQN) and maximum channel gain baselines.

Problem

• Optimizing UAV communication scheduling and flight velocities
• Minimizing data packet loss in post-disaster monitoring scenarios
• Addressing simulation-reality mismatch in urgent tsunami monitoring

Innovation

• Attention-based in-context learning for UAV control
• Joint optimization of communication scheduling and velocity
• LLM adaptation for emergency monitoring without retraining