Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs

Gaoxiang Cao, Wenke Yuan, Huasen He, Yunpeng Hou, Xiaofeng Jiang, Shuangwu Chen, Jian Yang

Abstract

Vehicular Ad-hoc Networks (VANETs) are the digital cornerstone of autonomous driving, yet they suffer from severe network fragmentation in urban environments due to physical obstructions. Unmanned Aerial Vehicles (UAVs), with their high mobility, have emerged as a vital solution to bridge these connectivity gaps. However, traditional Deep Reinforcement Learning (DRL)-based UAV deployment strategies lack semantic understanding of road topology, often resulting in blind exploration and sample inefficiency. By contrast, Large Language Models (LLMs) possess powerful reasoning capabilities capable of identifying topological importance, though applying them to control tasks remains challenging. To address this, we propose the Semantic-Augmented DRL (SA-DRL) framework. Firstly, we propose a fragmentation quantification method based on Road Topology Graphs (RTG) and Dual Connected Graphs (DCG). Subsequently, we design a four-stage pipeline to transform a general-purpose LLM into a domain-specific topology expert. Finally, we propose the Semantic-Augmented PPO (SA-PPO) algorithm, which employs a Logit Fusion mechanism to inject the LLM's semantic reasoning directly into the policy as a prior, effectively guiding the agent toward critical intersections. Extensive high-fidelity simulations demonstrate that SA-PPO achieves state-of-the-art performance with remarkable efficiency, reaching baseline performance levels using only 26.6% of the training episodes. Ultimately, SA-PPO improves two key connectivity metrics by 13.2% and 23.5% over competing methods, while reducing energy consumption to just 28.2% of the baseline.

Bridging Network Fragmentation: A Semantic-Augmented DRL Framework for UAV-aided VANETs

Abstract

Vehicular Ad-hoc Networks (VANETs) are the digital cornerstone of autonomous driving, yet they suffer from severe network fragmentation in urban environments due to physical obstructions. Unmanned Aerial Vehicles (UAVs), with their high mobility, have emerged as a vital solution to bridge these connectivity gaps. However, traditional Deep Reinforcement Learning (DRL)-based UAV deployment strategies lack semantic understanding of road topology, often resulting in blind exploration and sample inefficiency. By contrast, Large Language Models (LLMs) possess powerful reasoning capabilities capable of identifying topological importance, though applying them to control tasks remains challenging. To address this, we propose the Semantic-Augmented DRL (SA-DRL) framework. Firstly, we propose a fragmentation quantification method based on Road Topology Graphs (RTG) and Dual Connected Graphs (DCG). Subsequently, we design a four-stage pipeline to transform a general-purpose LLM into a domain-specific topology expert. Finally, we propose the Semantic-Augmented PPO (SA-PPO) algorithm, which employs a Logit Fusion mechanism to inject the LLM's semantic reasoning directly into the policy as a prior, effectively guiding the agent toward critical intersections. Extensive high-fidelity simulations demonstrate that SA-PPO achieves state-of-the-art performance with remarkable efficiency, reaching baseline performance levels using only 26.6% of the training episodes. Ultimately, SA-PPO improves two key connectivity metrics by 13.2% and 23.5% over competing methods, while reducing energy consumption to just 28.2% of the baseline.
Paper Structure (36 sections, 19 equations, 13 figures, 1 table, 4 algorithms)

This paper contains 36 sections, 19 equations, 13 figures, 1 table, 4 algorithms.

Table of Contents

  1. Introduction
  2. Related Works
  3. Connectivity of UAV Aided VANETs
  4. UAV Deployment Using DRL Methods
  5. UAVs Controlled by LLM Agents
  6. Contributions
  7. System Model
  8. Network Model
  9. Communication Model
  10. Graph-Theoretic Model of VANET Fragmentation
  11. Energy Consumption Model
  12. Problem Formulation
  13. Proposed Approach
  14. Key Elements of DRL
  15. Action Space
  16. ...and 21 more sections

Figures (13)

  • Figure 1: UAV Aided VANET Scenario.
  • Figure 2: The four-stage pipeline of the SA-DRL framework.
  • Figure 3: Schematic diagram of the LoRA fine-tuning mechanism.
  • Figure 4: Schematic diagram of the SA-PPO training and execution mechanism.
  • Figure 5: The RTG corresponding to the road network used in simulation.
  • ...and 8 more figures

Theorems & Definitions (5)

  • Definition 1: Road Topology Graph (RTG)
  • Definition 2: Connected Vertex (c-vertex)
  • Definition 3: Connected Edge (c-edge)
  • Definition 4: Connected Graph (c-graph)
  • Definition 5: Dual Connected Graph (DCG)