Efficient Path Planning in Multi-Agent Environment of AAVs With Payloads

The development of Autonomous Aerial Vehicle (AAV) technology is considered promising for applications such as product delivery, surveillance, and search and rescue operations. However, efficient navigation through unknown and dynamic environments is one of the major challenges for such systems. Especially when AAVs are armed with payloads, one needs to consider additional factors like capacity, weight, fuel consumption, etc, which further fosters the complexity of the problem. This research proposes a multi-path framework to improve the intelligence-of-path planning algorithm for AAVs while navigating through new terrain to achieve their missions successfully. The proposed framework integrates a Constrained A* (CA*) algorithm for path planning, a Constraint Tree (CT), and a Conflict Avoidance Table (CAT) for resolving conflicts. Integrating conflict avoidance principles enables intelligent and proactive AAV behavior, allowing for the wide deployment of multi-AAV systems in various operational scenarios. This model adapts dynamic path adjustments based on real-time environmental data and predictive modeling to suit AAV trajectories under changing conditions. The performance evaluation demonstrates that the proposed model surpasses the state-of-the-art algorithms, especially in unknown environments.