Input-Constrained Visual Servoing Formation Control for Quadrotors Using Off-Policy Reinforcement Learning

In this article, an input-constrained visual servoing formation controller is proposed for multiple quadrotor systems operating without intervehicle communication or relative position measurements. The aerial formation control is achieved by formulating image-based leader-follower dynamics using a virtual camera framework and sphere-based image moments. An adaptive velocity observer is developed for the follower quadrotor to estimate the relative velocity with respect to the leader quadrotor in communication-free environments. Input-constrained visual servoing and attitude controllers are proposed using an off-policy reinforcement learning (RL) algorithm to handle visibility and attitude constraints, without relying on accurate system model parameters. The stability of the closed-loop system is theoretically analyzed, and the effectiveness of the proposed controller is demonstrated through case studies.