Existing approaches for transporting and manipulating cable-suspended loads using multiple UAVs along reference trajectories typically rely on either centralized control architectures or reliable inter-agent communication. In this work, we propose a novel machine learning-based method for decentralized kinodynamic planning that operates effectively under partial observability and without inter-agent communication. Our method leverages imitation learning to train a decentralized student policy for each UAV by imitating a centralized kinodynamic motion planner with access to privileged global observations. The student policy generates smooth trajectories using physics-informed neural networks that respect the derivative relationships in motion. During training, the student policies utilize the full trajectory generated by the teacher policy, leading to improved sample efficiency. Moreover, each student policy can be trained in under two hours on a standard laptop. We validate our method in both simulation and real-world environments to follow an agile reference trajectory, demonstrating performance comparable to that of centralized approaches.

Successful aerial manipulation largely depends on how effectively a controller can tackle the coupling dynamic forces between the aerial vehicle and the manipulator. However, this control problem has remained largely unsolved as the existing control approaches either require precise knowledge of the aerial vehicle/manipulator inertial couplings, or neglect the state-dependent uncertainties especially arising during the interaction phase. This work proposes an adaptive control solution to overcome this long standing control challenge without any a priori knowledge of the coupling dynamic terms. In addition, in contrast to the existing adaptive control solutions, the proposed control framework is modular, that is, it allows independent tuning of the adaptive gains for the vehicle position subdynamics, the vehicle attitude subdynamics, and the manipulator subdynamics. Stability of the closed loop under the proposed scheme is derived analytically, and real-time experiments validate the effectiveness of the proposed scheme over the state-of-the-art approaches.

Quadrotors can carry slung loads to hard-to-reach locations at high speed. Given that a single quadrotor has limited payload capacities, using a team of quadrotors to collaboratively manipulate the full pose of a heavy object is a scalable and promising solution. However, existing control algorithms for multilifting systems only enable low-speed and low-acceleration operations because of the complex dynamic coupling between quadrotors and the load, limiting their use in time-critical missions such as search and rescue. In this work, we present a solution to substantially enhance the agility of cable-suspended multilifting systems. Unlike traditional cascaded solutions, we introduce a trajectory-based framework that solves the whole-body kinodynamic motion planning problem online, accounting for the dynamic coupling effects and constraints between the quadrotors and the load. The planned trajectory is provided to the quadrotors as a reference in a receding-horizon fashion and is tracked by an onboard controller that observes and compensates for the cable tension. Real-world experiments demonstrate that our framework can achieve at least eight times greater acceleration than state-of-the-art methods to follow agile trajectories. Our method can even perform complex maneuvers such as flying through narrow passages at high speed. In addition, it exhibits high robustness against load uncertainties and wind disturbances and does not require adding any sensors to the load, demonstrating strong practicality.

An inherent fragility of quadrotor systems stems from model inaccuracies and external disturbances. These factors hinder performance and compromise the stability of the system, making precise control challenging. Existing model-based approaches either make deterministic assumptions, utilize Gaussian-based representations of uncertainty, or rely on nominal models, all of which often fall short in capturing the complex, multimodal nature of real-world dynamics. This work introduces DroneDiffusion, a novel framework that leverages conditional diffusion models to learn quadrotor dynamics, formulated as a sequence generation task. DroneDiffusion achieves superior generalization to unseen, complex scenarios by capturing the temporal nature of uncertainties and mitigating error propagation. We integrate the learned dynamics with an adaptive controller for trajectory tracking with stability guarantees. Extensive experiments in both simulation and real-world flights demonstrate the robustness of the framework across a range of scenarios, including unfamiliar flight paths and varying payloads, velocities, and wind disturbances. Project page: https://sites.google.com/view/dronediffusion.

Enabling vertical-stack proximal cooperation between multirotor flying robots can facilitate the execution of complex aerial manipulation tasks. However, vertical-stack proximal flight is commonly regarded as a dangerous condition that should be avoided because of persistent and intense downwash interference generated between flying robots^1,2. Here we propose a cooperative aerial manipulation system, called FlyingToolbox, that can work stably with sub-centimetre-level docking accuracy under vertical-stack flight conditions. The system consists of a toolbox micro-aerial vehicle (MAV) and a manipulator MAV. The robotic arm of the manipulator MAV can autonomously dock with a tool carried by the toolbox MAV, in which the docking accuracy reaches 0.80 ± 0.33 cm in the presence of downwash airflow of up to 13.18 m s⁻¹. By enabling midair tool exchange in proximity, FlyingToolbox resolves the paradox between flight proximity and manipulation accuracy, suggesting a new model for heterogeneous and interactive flying robot cooperation in diverse applications^{3, 4–5}.

This study presents a motion control system for a coaxial tilt-rotor (CTR) unmanned aerial vehicle (UAV) equipped with two CTR modules and a tail rotor. The existing adaptive control strategies for CTRUAVs fail to guarantee the theoretical convergence of estimated parameters to their true values. Additionally, the existing mixer requires frequent and inefficient adjustments of the tilt angles for motion control. To address these issues, this work proposes a control strategy that integrates a robust integral of the sign of the error (RISE)-based immersion and invariance (I&I) adaptive controller with segmented gains and an improved mixer. The RISE-based adaptive controller is theoretically capable of estimating and compensating for external disturbance torques and forces with bounded derivatives. Furthermore, a model of the CTR module that accounts for differences between the upper and lower rotors is introduced, and the proposed mixer is designed to realize efficient control at varying tilt angles of the CTR modules. Experimental results demonstrate that the proposed control scheme significantly improves stability, transient response speed, disturbance rejection performance, and parameter estimation accuracy compared to existing control strategies for the CTRUAV.