Fixed-time adaptive consensus control for multi-quadrotor subject to external disturbances via deep reinforcement learning

Formation control of quadrotors is particularly challenging under external disturbances and dynamic mission requirements. This paper introduces a hybrid control framework that combines fixed-time control with deep reinforcement learning (DRL) to achieve adaptive and robust multi-quadrotor formation control. A fixed-time disturbance observer (FTDO) is designed to accurately estimate disturbances, while a fully distributed fast nonsingular terminal sliding mode controller ensures fixed-time convergence of both translational and rotational dynamics without singularities. To enhance adaptivity, a DRL-based mechanism enables online parameter tuning, thereby improving flight performance without compromising system stability. Both simulations and real-world experiments validate the effectiveness of the proposed framework, showing an average 50 % reduction in consensus tracking error compared with non-adaptive baselines.