Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Joint UAV-UGV Positioning and Trajectory Planning via Meta A3C for Reliable Emergency Communications

Ndagijimana Cyprien, Mehdi Sookhak, Hosein Zarini, Chandra N Sekharan, Mohammed Atiquzzaman

TL;DR

This work tackles emergency communications by jointly optimizing UAV-UGV positioning and trajectories to maximize network throughput while ensuring ground-user QoS. It formulates the problem as a non-convex MDP and proposes a Meta-A3C framework that integrates road-graph mobility and meta-learning (via MAML) for rapid adaptation to changing environments. The approach yields 13.1% higher throughput than A3C and 30.1% higher than DDPG, with lower computational complexity, and is demonstrated through 3D positioning and trajectory results that illustrate effective backhaul and access link management in disaster scenarios. The integration of road-graph constraints, LoS/NLoS channel modeling, and meta-learning enables real-time, robust operation suitable for rapid disaster response and resilient communications.

Abstract

Joint deployment of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) has been shown to be an effective method to establish communications in areas affected by disasters. However, ensuring good Quality of Services (QoS) while using as few UAVs as possible also requires optimal positioning and trajectory planning for UAVs and UGVs. This paper proposes a joint UAV-UGV-based positioning and trajectory planning framework for UAVs and UGVs deployment that guarantees optimal QoS for ground users. To model the UGVs' mobility, we introduce a road graph, which directs their movement along valid road segments and adheres to the road network constraints. To solve the sum rate optimization problem, we reformulate the problem as a Markov Decision Process (MDP) and propose a novel asynchronous Advantage Actor Critic (A3C) incorporated with meta-learning for rapid adaptation to new environments and dynamic conditions. Numerical results demonstrate that our proposed Meta-A3C approach outperforms A3C and DDPG, delivering 13.1\% higher throughput and 49\% faster execution while meeting the QoS requirements.

Joint UAV-UGV Positioning and Trajectory Planning via Meta A3C for Reliable Emergency Communications

TL;DR

This work tackles emergency communications by jointly optimizing UAV-UGV positioning and trajectories to maximize network throughput while ensuring ground-user QoS. It formulates the problem as a non-convex MDP and proposes a Meta-A3C framework that integrates road-graph mobility and meta-learning (via MAML) for rapid adaptation to changing environments. The approach yields 13.1% higher throughput than A3C and 30.1% higher than DDPG, with lower computational complexity, and is demonstrated through 3D positioning and trajectory results that illustrate effective backhaul and access link management in disaster scenarios. The integration of road-graph constraints, LoS/NLoS channel modeling, and meta-learning enables real-time, robust operation suitable for rapid disaster response and resilient communications.

Abstract

Joint deployment of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) has been shown to be an effective method to establish communications in areas affected by disasters. However, ensuring good Quality of Services (QoS) while using as few UAVs as possible also requires optimal positioning and trajectory planning for UAVs and UGVs. This paper proposes a joint UAV-UGV-based positioning and trajectory planning framework for UAVs and UGVs deployment that guarantees optimal QoS for ground users. To model the UGVs' mobility, we introduce a road graph, which directs their movement along valid road segments and adheres to the road network constraints. To solve the sum rate optimization problem, we reformulate the problem as a Markov Decision Process (MDP) and propose a novel asynchronous Advantage Actor Critic (A3C) incorporated with meta-learning for rapid adaptation to new environments and dynamic conditions. Numerical results demonstrate that our proposed Meta-A3C approach outperforms A3C and DDPG, delivering 13.1\% higher throughput and 49\% faster execution while meeting the QoS requirements.
Paper Structure (13 sections, 23 equations, 4 figures, 1 algorithm)

This paper contains 13 sections, 23 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. Mathematical Modeling of UGV Trajectories
  4. Mathematical Modeling of UAV Trajectories
  5. G2A and A2G Wireless Channel Models
  6. Problem Formulation
  7. Proposed META-A3C Approach
  8. Markov Decision Process (MDP) Reformulation
  9. A3C Algorithm
  10. Meta-Learning Integration
  11. Numerical Results
  12. Conclusion
  13. ACKNOWLEDGMENT

Figures (4)

  • Figure 1: UAV-Assisted Wireless Networks with UGV in an Emergency Situation.
  • Figure 2: (a) Convergence behavior of the considered approaches over epochs, (b) sum rate performance with varying number of users for the compared approaches, (c) Complexity analysis of the proposed approach and existing RL algorithms.
  • Figure 3: Optimal positioning of UAVs, UGVs, and users.
  • Figure 4: Optimal 3D trajectory for UAVs and UGVs.