Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quantum-Driven State-Reduction for Reliable UAV Trajectory Optimization in Low-Altitude Networks

Zeeshan Kaleem, Muhammad Afaq, Chau Yuen, Octavia A. Dobre, John M. Cioffi

TL;DR

The paper tackles reliable UAV trajectory optimization in dense, interference-prone, low-altitude networks. It introduces GC-QAP, a quantum-inspired graph condensation method that reduces the waypoint state space to a radio-aware set $\mathcal{C}$, preserving interference structure, and embeds this in an outage-aware Markov decision process solved via independent Q-learning on the condensed graph. Key contributions include a QA-based condensation objective $L(\mathbf{c}_j)$ with quantum jumps and cooling, a priority-aware reward shaping for outage minimization, and empirical evidence showing significantly lower outages and faster convergence than baselines. The approach demonstrates practical, real-time viability and scalability for UAV-assisted wireless networks, with potential to leverage real quantum annealers in future work.

Abstract

This letter introduces a Graph-Condensed Quantum-Inspired Placement (GC-QAP) framework for reliability-driven trajectory optimization in Uncrewed Aerial Vehicle (UAV) assisted low-altitude wireless networks. The dense waypoint graph is condensed using probabilistic quantum-annealing to preserve interference-aware centroids while reducing the control state space and maintaining link-quality. The resulting problem is formulated as a priority-aware Markov decision process and solved using epsilon-greedy off-policy Q-learning, considering UAV kinematic and flight corridor constraints. Unlike complex continuous-action reinforcement learning approaches, GC-QAP achieves stable convergence and low outage with substantially and lower computational cost compared to baseline schemes.

Quantum-Driven State-Reduction for Reliable UAV Trajectory Optimization in Low-Altitude Networks

TL;DR

The paper tackles reliable UAV trajectory optimization in dense, interference-prone, low-altitude networks. It introduces GC-QAP, a quantum-inspired graph condensation method that reduces the waypoint state space to a radio-aware set , preserving interference structure, and embeds this in an outage-aware Markov decision process solved via independent Q-learning on the condensed graph. Key contributions include a QA-based condensation objective with quantum jumps and cooling, a priority-aware reward shaping for outage minimization, and empirical evidence showing significantly lower outages and faster convergence than baselines. The approach demonstrates practical, real-time viability and scalability for UAV-assisted wireless networks, with potential to leverage real quantum annealers in future work.

Abstract

This letter introduces a Graph-Condensed Quantum-Inspired Placement (GC-QAP) framework for reliability-driven trajectory optimization in Uncrewed Aerial Vehicle (UAV) assisted low-altitude wireless networks. The dense waypoint graph is condensed using probabilistic quantum-annealing to preserve interference-aware centroids while reducing the control state space and maintaining link-quality. The resulting problem is formulated as a priority-aware Markov decision process and solved using epsilon-greedy off-policy Q-learning, considering UAV kinematic and flight corridor constraints. Unlike complex continuous-action reinforcement learning approaches, GC-QAP achieves stable convergence and low outage with substantially and lower computational cost compared to baseline schemes.
Paper Structure (8 sections, 6 equations, 2 figures, 1 algorithm)

This paper contains 8 sections, 6 equations, 2 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Problem Formulation
  4. Markov Decision Process (MDP) Representation of Problem
  5. Proposed Quantum-inspired Condensed Nodes Computation
  6. Proposed Graph Condensation (GC) via Quantum–Annealing Placement (QAP) for Trajectory Optimization
  7. Simulation Results
  8. Conclusion

Figures (2)

  • Figure 1: Performance evaluation under different schemes: (a) reward vs. episode, (b) User outage comparison, and (c) Optimized UAV trajectory, (d) outage vs. priority-penalty weight $\mu_{\rm pr}$.
  • Figure 2: UAV trajectory optimization phase for the proposed GC-QAP scheme, (a) 3D association, (b) trajectory optimization.