Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning

TL;DR

This paper presents a decentralized deep reinforcement learning framework for flocking and collision avoidance in fixed-wing UAVs, enabling scalable and adaptable squad behavior under environmental uncertainties.

Contribution

It introduces a novel DRL algorithm PS-CACER and a plug-n-play embedding module that allows flexible, order-independent control policies for UAV flocking.

Findings

Effective in simulation for decentralized flocking and collision avoidance

Policies transferable to semi-physical environments without fine-tuning

Handles variable number and order of UAV followers

Abstract

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.