Scholarlink

<p>Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) play a vital role in various applications, including military operations, disaster response, hazardous environment navigation, and surveillance. Effective bidirectional communication between UAVs and UGVs is essential for seamless coordination and successful task execution. However, traditional routing protocols primarily focus on either UAV-to-UAV or UGV-to-UGV communication, often lacking adaptability to dynamic network conditions such as mobility, interference, and congestion. To address these limitations, this paper presents the design, implementation, and optimization of an adaptive routing protocol tailored for UAV-UGV coordinated networks. The proposed protocol enables bi-directional communication between UAV and UGV and also integrates Greedy Perimeter Stateless Routing (GPSR) with Deep Reinforcement Learning (DRL) to optimize packet routing in real-time, improved throughput, reduced latency and minimal packet loss as compared to traditional routing protocol. Simulations conducted in Python demonstrate that the DRL-based routing protocol effectively establishes efficient communication paths between UAVs and UGVs, dynamically selecting the shortest and most reliable routes. This research advances AI-driven communication architectures for UAV-UGV networks, enhancing their robustness and efficiency in mission-critical operations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and Simulation of DRL Based Routing Protocol for Bidirectional Communication Between UAV and UGV Networks

  • 期刊论文

  • 发表日期：

    2026年2月4日

查看全文
  • Prabhakar Saxena,
  • Gayatri Phade

摘要

Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) play a vital role in various applications, including military operations, disaster response, hazardous environment navigation, and surveillance. Effective bidirectional communication between UAVs and UGVs is essential for seamless coordination and successful task execution. However, traditional routing protocols primarily focus on either UAV-to-UAV or UGV-to-UGV communication, often lacking adaptability to dynamic network conditions such as mobility, interference, and congestion. To address these limitations, this paper presents the design, implementation, and optimization of an adaptive routing protocol tailored for UAV-UGV coordinated networks. The proposed protocol enables bi-directional communication between UAV and UGV and also integrates Greedy Perimeter Stateless Routing (GPSR) with Deep Reinforcement Learning (DRL) to optimize packet routing in real-time, improved throughput, reduced latency and minimal packet loss as compared to traditional routing protocol. Simulations conducted in Python demonstrate that the DRL-based routing protocol effectively establishes efficient communication paths between UAVs and UGVs, dynamically selecting the shortest and most reliable routes. This research advances AI-driven communication architectures for UAV-UGV networks, enhancing their robustness and efficiency in mission-critical operations.