Mission Planning of UAVs and CAVs Based on Graph Neural Network Transformer Model

Efficient mission planning, including task allocation and path planning, is crucial for the successful operation of unmanned aerial vehicles (UAVs) and connected autonomous vehicles (CAVs) in complex scenarios. This article introduces an innovative mission planning approach that employs a collaborative model combining graph neural networks (GNNs) and Transformers to meet the intricate requirements of coordinating UAVs and CAVs. Our model excels in dynamic task allocation and accurate path planning, thereby boosting operational efficiency and reducing computational demands. We outline the shortcomings of current methods, notably their limited adaptability to dynamic changes and their substantial computational costs. By utilizing GNNs to capture complex interrelations and Transformers for effective information processing, our approach achieves greater adaptability and scalability. Experimental results demonstrate that our model surpasses leading methods, showing a 12% improvement in task allocation accuracy for UAVs and 10% for CAVs. Furthermore, we assess the model’s performance under various conditions, confirming its robustness and adaptability. This research provides a holistic solution for mission planning in UAV and CAV systems, setting the stage for future enhancements in autonomous vehicle coordination across logistics, surveillance, and disaster management sectors.

I. Introduction

The rapid development of low-altitude transportation and industry has revolutionized urban traffic management and logistics through the deployment of unmanned aerial vehicles (UAVs) and connected autonomous vehicles (CAVs). These technologies play crucial roles in various applications, including logistics delivery, urban surveillance, power line inspection, meteorological monitoring, traffic control, communication relay, agricultural operations, and law enforcement. However, managing and coordinating UAVs and CAVs in complex geographical environments, such as urban and mountainous regions, presents significant challenges, particularly in mission planning, which includes both task allocation and path planning [1], [2], [3]. In urban environments, UAVs must navigate through dense building structures, avoid dynamic obstacles, such as moving vehicles and pedestrians, and manage airspace restrictions, while performing tasks like package delivery, real-time traffic monitoring, and infrastructure inspection. CAVs, on the other hand, contend with congested roads, traffic signals, and variable traffic conditions for tasks, such as automated delivery, ride-sharing services, and emergency response. The interaction between UAVs and CAVs in urban settings necessitates sophisticated coordination to prevent collisions and ensure efficient route planning [4], [5], [6]. In mountainous regions, UAVs face varied terrains with hills, valleys, and forests, requiring advanced navigation systems to handle elevation changes and avoid natural obstacles, performing tasks, such as environmental monitoring, search and rescue operations, and geological surveying. CAVs in these areas must traverse narrow, winding roads often affected by weather conditions, tasked with transporting supplies to remote areas, assisting in disaster relief, and providing connectivity in otherwise inaccessible locations [7], [8]. Both environments demand precise and adaptive mission planning to ensure UAVs and CAVs perform efficiently and safely, especially in scenarios requiring real-time decision making and coordination among multiple agents, such as disaster response or urban traffic management, where effective mission planning optimizes resource allocation and task completion [9], [10].