Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Semantic Communication for UAV/UGV Cooperative Path Planning

Fangzhou Zhao, Yao Sun, Jianglin Lan, Lan Zhang, Xuesong Liu, Muhammad Ali Imran

TL;DR

The paper addresses reliable UAV/UGV cooperative path planning under unstable wireless links by shifting from raw data transmission to semantic-aware communication. It introduces Path-SC, a dynamic, sparsity-aware SemCom transceiver that prioritizes path-planning semantics via a DynamicViT-based encoder and a semantically guided transmission strategy. A theoretical framework identifies which path-perturbations most affect planning accuracy (Proposition 1) and a Monte Carlo locally centrality approach (MC-LBC-RT) directs resource allocation to high-impact regions, with offline precomputation and windowed online updates to keep complexity manageable. The Path-SC system demonstrates substantial reductions in data volume and maintained or improved path-planning accuracy across AWGN and Rayleigh channels, highlighting practical benefits for robust UAV/UGV collaboration in challenging environments. Together, these results advance task-oriented SemCom for autonomous multi-robot systems and lay groundwork for scalable, multimodal extensions.

Abstract

Effective path planning is fundamental to the coordination of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) systems, particularly in applications such as surveillance, navigation, and emergency response. Combining UAVs' broad field of view with UGVs' ground-level operational capability greatly improve the likelihood of successfully achieving task objectives such as locating victims, monitoring target areas, or navigating hazardous terrain. In complex environments, UAVs need to provide precise environmental perception information for UGVs to optimize their routing policy. However, due to severe interference and non-line-of-sight conditions, wireless communication is often unstable in such complex environments, making it difficult to support timely and accurate path planning for UAV-UGV coordination. To this end, this paper proposes a semantic communication (SemCom) framework to enhance UAV/UGV cooperative path planning under unreliable wireless conditions. Unlike traditional methods that transmit raw data, SemCom transmits only the key information for path planning, reducing transmission volume without sacrificing accuracy. The proposed framework is developed by defining key semantics for path planning and designing a transceiver for meeting the requirements of UAV-UGV cooperative path planning. Simulation results show that, compared to conventional SemCom transceivers, the proposed transceiver significantly reduces data transmission volume while maintaining path planning accuracy, thereby enhancing system collaboration efficiency.

Adaptive Semantic Communication for UAV/UGV Cooperative Path Planning

TL;DR

The paper addresses reliable UAV/UGV cooperative path planning under unstable wireless links by shifting from raw data transmission to semantic-aware communication. It introduces Path-SC, a dynamic, sparsity-aware SemCom transceiver that prioritizes path-planning semantics via a DynamicViT-based encoder and a semantically guided transmission strategy. A theoretical framework identifies which path-perturbations most affect planning accuracy (Proposition 1) and a Monte Carlo locally centrality approach (MC-LBC-RT) directs resource allocation to high-impact regions, with offline precomputation and windowed online updates to keep complexity manageable. The Path-SC system demonstrates substantial reductions in data volume and maintained or improved path-planning accuracy across AWGN and Rayleigh channels, highlighting practical benefits for robust UAV/UGV collaboration in challenging environments. Together, these results advance task-oriented SemCom for autonomous multi-robot systems and lay groundwork for scalable, multimodal extensions.

Abstract

Effective path planning is fundamental to the coordination of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) systems, particularly in applications such as surveillance, navigation, and emergency response. Combining UAVs' broad field of view with UGVs' ground-level operational capability greatly improve the likelihood of successfully achieving task objectives such as locating victims, monitoring target areas, or navigating hazardous terrain. In complex environments, UAVs need to provide precise environmental perception information for UGVs to optimize their routing policy. However, due to severe interference and non-line-of-sight conditions, wireless communication is often unstable in such complex environments, making it difficult to support timely and accurate path planning for UAV-UGV coordination. To this end, this paper proposes a semantic communication (SemCom) framework to enhance UAV/UGV cooperative path planning under unreliable wireless conditions. Unlike traditional methods that transmit raw data, SemCom transmits only the key information for path planning, reducing transmission volume without sacrificing accuracy. The proposed framework is developed by defining key semantics for path planning and designing a transceiver for meeting the requirements of UAV-UGV cooperative path planning. Simulation results show that, compared to conventional SemCom transceivers, the proposed transceiver significantly reduces data transmission volume while maintaining path planning accuracy, thereby enhancing system collaboration efficiency.

Paper Structure

This paper contains 17 sections, 1 theorem, 25 equations, 6 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Wireless Communication in Cooperative UAV/UGV Systems
  4. Advances in Wireless SemCom Systems
  5. SemCom Framework for UAV/UGV Cooperative Path Planning
  6. UGV Path Planning
  7. SemCom Model
  8. Transmission Strategy for Path Planning Critical Regions
  9. Problem Formulation
  10. Problem Solution
  11. Adaptive SemCom Transceiver for Path Planning
  12. Structure of the Semantic Encoder and Decoder
  13. Training Process
  14. Simulation Results and Discussion
  15. Simulation Setup
  16. ...and 2 more sections

Key Result

Proposition 1

In the Gaussian case, the impact of reducing $\sigma^2_{\mathbf{p}_{t}^{j}}$ on $\mathbf{Q}(\mathbf{p}_t^* = \hat{\mathbf{p}}_t^*)$ is maximized when

Figures (6)

  • Figure 1: The proposed SemCom framework for UAV/UGV cooperative path planning.
  • Figure 2: Dynamic Sparsification ViT Based SemCom encoder and decoder network.
  • Figure 3: Comparison of Path-SC, DeiT-SC and MAE-SC reconstructed images and path planning result under SNR=12 dB.
  • Figure 4: Total weight error of Path-SC and two other benchmarks under AWGN and Rayleigh fading channels under different SNR.
  • Figure 5: Number of times the planned path traverses non-traversable region of Path-SC and two other benchmarks under AWGN and Rayleigh fading channels under different SNR.
  • ...and 1 more figures

Theorems & Definitions (2)

  • Proposition 1
  • proof