This correspondence investigates the robust unmanned aerial vehicle (UAV) enabled covert communication system with active ground wardens of collusive detection and location uncertainty. The three-dimensional (3D) trajectory and transmit power of UAV are jointly optimized to maximize the average covert transmission rate subject to the worst-case covertness constraint. The problem is intractable due to its nonconvexity and semi-positive definite matrix constraint, and an iterative suboptimal algorithm is proposed based on the block coordinate descent, S-procedure and successive convex optimization to tackle it. Numerical results demonstrate that the proposed scheme is effective and robust for UAV-enabled covert communications against active wardens.