This research presents an innovative application of deep reinforcement learning (DRL) for multi-objective mission planning in UAV swarms, a subject at the forefront of emerging technologies. An in-depth exploration of existing models, strategies, and primary principles of DRL regarding UAV swarm mission planning is undertaken. The paper then introduces a cutting-edge approach to the multi-objective mission planning of UAV swarms, which includes rigorous problem definition, state and action space design, reward function configuration, DRL model formulation, and the creation of multi-objective optimization strategies. The performance and reliability of the proposed model were extensively evaluated using various simulation environments and diverse datasets. The outcomes show that our model surpasses traditional methods in planning UAV swarm missions, providing a groundbreaking perspective on integrating DRL into swarm robotics. Despite its strengths, the model also presents areas that warrant further investigation and enhancement, outlined in future research directions. This work contributes significantly to the understanding and application of efficient UAV swarm mission planning, with potentially far-reaching implications across numerous fields, including defense, agriculture, and environmental surveillance.
Multi-Objective Mission planning for UAV Swarm Based on Deep Reinforcement Learning
13.10.2023
495817 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|