Learning to Throw: Agile and Accurate Cable-Suspended Payload Delivery with a Quadrotor

2026-06-25

AI Summary

This work addresses the limited accuracy and agility of quadrotor UAVs during dynamic cable-suspended payload deployment, which stems from oversimplified models and the difficulty of faithfully modeling flexible cables. To overcome these challenges, the authors propose a high-fidelity hybrid simulation framework that couples analytical quadrotor dynamics with a physics-engine-based flexible cable solver, enabling end-to-end training of a deep reinforcement learning policy from visual observations alone. This approach achieves, for the first time, dynamic precision dropping using only visual input, substantially breaking the trade-off between accuracy and agility: compared to conventional model-based baselines, it reduces landing error by up to 50% and shortens drop time by 30%. Remarkably, the vision-based policy matches the performance of full-state feedback methods and demonstrates zero-shot transfer to real-world hardware.

Abstract

Quadrotors offer the agility needed to rapidly transport suspended payloads during time-critical applications, including search-and-rescue and medical delivery. While suspended-payload transport and traversal for these missions are well studied, the highly dynamic targeted release of the payload remains comparatively underexplored. State-of-the-art approaches typically rely on model-based trajectory optimization and tracking; however, these methods often yield sub-optimal performance due to conservative feasibility constraints, tracking errors, and the inherent difficulty of analytically modeling flexible rope dynamics. To overcome these limitations, we propose a hybrid simulation framework that couples a high-fidelity analytical quadrotor model with a physics solver for complex rope and payload interactions. By exchanging forces between the two domains at every step, we obtain a physically accurate simulation of the suspended-payload system. Leveraging this environment, we train a deep reinforcement learning (RL) policy that executes agile, accurate payload throws to designated targets. Deployed zero-shot on hardware, our RL policy pushes the boundary of the agility-accuracy trade-off, outperforming the model-based baseline by reducing the landing error by up to 50% and the throw duration by up to 30%. Ablation studies confirm that the coupled simulation is the key enabler of these gains. We further show that the same pipeline trains a policy driven by visual observations rather than an explicit state estimate, achieving accuracy comparable to that of the state-based policy. To accelerate future research in dynamic aerial manipulation, we open-source the simulator to the community upon acceptance.

Problem

• suspended payload delivery
• quadrotor
• dynamic release
• rope dynamics
• aerial manipulation

Innovation

• deep reinforcement learning
• hybrid simulation
• cable-suspended payload
• quadrotor manipulation
• zero-shot transfer