ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learning

TL;DR

ASTER introduces a reinforcement learning framework that enables quadrotors with suspended payloads to perform inverted flights and complex maneuvers with high agility and robustness, overcoming traditional challenges of hybrid dynamics and reward sparsity.

Contribution

The paper presents a novel hybrid-dynamics-informed state seeding method that facilitates successful autonomous inverted flight for cable-suspended quadrotors using reinforcement learning.

Findings

Achieved the first autonomous inverted flight of a suspended-payload quadrotor.

Demonstrated high agility and precise attitude control in simulations and real-world tests.

Enabled robust zero-shot sim-to-real transfer across complex trajectories.

Abstract

Agile maneuvering of the quadrotor cable-suspended system is significantly hindered by its non-smooth hybrid dynamics. While model-free Reinforcement Learning (RL) circumvents explicit differentiation of complex models, achieving attitude-constrained or inverted flight remains an open challenge due to the extreme reward sparsity under strict orientation requirements. This paper presents ASTER, a robust RL framework that achieves, to our knowledge, the first successful autonomous inverted flight for the cable-suspended system. We propose hybrid-dynamics-informed state seeding (HDSS), an initialization strategy that back-propagates target configurations through physics-consistent kinematic inversions across both taut and slack cable phases. HDSS enables the policy to discover aggressive maneuvers that are unreachable via standard exploration. Extensive simulations and real-world experiments demonstrate remarkable agility, precise attitude alignment, and robust zero-shot sim-to-real transfer across complex trajectories.