Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning
This addresses the challenge of kinematic complexity and environmental uncertainty in UAV flocking, offering a solution for autonomous drone coordination, though it appears incremental as it builds on existing DRL methods.
The paper tackles decentralized flocking and collision avoidance for a dynamic squad of fixed-wing UAVs by developing a deep reinforcement learning framework with a novel algorithm and embedding module, achieving policies that transfer directly to semi-physical simulation without parameter finetuning.
Developing the flocking behavior for a dynamic squad of fixed-wing UAVs is still a challenge due to kinematic complexity and environmental uncertainty. In this paper, we deal with the decentralized flocking and collision avoidance problem through deep reinforcement learning (DRL). Specifically, we formulate a decentralized DRL-based decision making framework from the perspective of every follower, where a collision avoidance mechanism is integrated into the flocking controller. Then, we propose a novel reinforcement learning algorithm PS-CACER for training a shared control policy for all the followers. Besides, we design a plug-n-play embedding module based on convolutional neural networks and the attention mechanism. As a result, the variable-length system state can be encoded into a fixed-length embedding vector, which makes the learned DRL policy independent with the number and the order of followers. Finally, numerical simulation results demonstrate the effectiveness of the proposed method, and the learned policies can be directly transferred to semi-physical simulation without any parameter finetuning.