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

2026-03-11

AI Summary

This work addresses the challenge of agile control in quadrotor suspended-load systems under stringent attitude constraints—such as inverted flight—where hybrid nonsmooth dynamics and extreme reward sparsity hinder learning. To overcome these difficulties, the paper proposes the ASTER reinforcement learning framework, which incorporates a hybrid dynamics-guided state initialization strategy (HDSS) to alleviate reward sparsity and enhance exploration efficiency. By integrating model-free reinforcement learning with physically consistent kinematic inversion and a slack-taut cable phase-aware model, ASTER enables effective policy learning. The approach achieves, for the first time, autonomous inverted flight of a suspended-load quadrotor, demonstrating high-precision attitude alignment and complex trajectory tracking in both simulation and real-world experiments, along with zero-shot sim-to-real transfer capability.

Technology Category

• Intelligent Robots: State Estimation
• Multiagent Systems: Adversarial Agents
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• suspended-payload quadrotor
• attitude-constrained flight
• inverted flight
• hybrid dynamics
• reward sparsity

Innovation

• Reinforcement Learning
• Suspended-payload Quadrotor
• Inverted Flight
• Hybrid Dynamics
• Sim-to-Real Transfer