Deep Reinforcement Learning-Based Framework for Path Planning of AUAVs

The Soft Actor-Critic (SAC) method is a cutting-edge deep reinforcement learning (DRL) technique designed to determine the best feasible path for Autonomous Unmanned Aerial Vehicles (AUAVs) in static and dynamic environment. In this study, we present a unique framework that not only tackles the major difficulties of AUAV path planning, but also provides the basis for future research and development in AUAV navigation utilising advanced DRL approaches. This paper explores the application of SAC in AUAV navigation, focussing on how an entropy-regularized target may be used to balance exploration and exploitation. During training, the AUAV interacts with the environment across multiple episodes, select actions based on the current policy, and store the resulting state transitions and rewards. Through this iterative process, SAC effectively enhances the AUAV’s navigation strategy, achieving efficient path planning with improved obstacle avoidance and path optimization. Overall, the findings of this study show the effectiveness of deep reinforcement learning in finding the optimal path for AUAVs. By employing the DRL-based solution in AUAV path planning the complicated nature of the issue can be resolved and the efficiency of the process can be increased. Furthermore, this study provides an outline for future research in the area of path planning.