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

• URL: http://arxiv.org/abs/2603.10715v1
• Date: Wed, 11 Mar 2026 12:40:29 GMT
• Title: ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learning
• Abstract summary: This paper presents ASTER, a robust RL framework that achieves, to our knowledge, the first successful autonomous inverted flight for the cable-suspended system.<n>We show remarkable agility, precise attitude alignment, and robust zero-shot sim-to-real transfer across complex trajectories.
• Score: 6.13534373131836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping [6.344868277741761]
  We propose Spring-loaded Reinforcement Learning (SRL), which integrates SLIP-based feedforward control signals with RL-driven real-time feedback.<n>SRL exhibits robust adaptability to various task requirements and environmental complexities, underscoring its potential for real-world deployment.
  arXiv  Detail & Related papers  (2026-06-17T02:41:53Z)
• Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learning [8.39070114446824]
  We present an RL-based framework for autonomous fall recovery of a quadrotor from arbitrary ground attitudes to stable hover using only lightweight onboard sensors.<n>We show that agile quadrotor fall recovery can be achieved without explicit state estimation using only limited and unreliable onboard sensing.
  arXiv  Detail & Related papers  (2026-06-15T10:15:10Z)
• Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension [0.9612340765846284]
  ERNEST is a four-wheeled planetary rover concept equipped with a two-degree-of-freedom Active Gimbal Suspension.<n>A single neural network controller is trained to track a desired path across challenging terrain.
  arXiv  Detail & Related papers  (2026-06-05T00:20:50Z)
• Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation [63.11032720821731]
  textitSAGE is a framework that enables agents to learn within a physics-grounded semantic abstraction rather than a photorealistic simulation.<n>We demonstrate that textitSAGE significantly improves planner-assisted embodied navigation, achieving a 53.21% LLM-Match Success Rate on A-EQA.
  arXiv  Detail & Related papers  (2026-05-11T07:34:30Z)
• Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control [50.28263951510334]
  We propose a hybrid hierarchical control framework for reactive dexterous grasping.<n>The proposed framework explicitly decouples high-level spatial intent from low-level joint execution.<n>We extensively validate the proposed framework through a rigorous simulation-to-reality pipeline.
  arXiv  Detail & Related papers  (2026-05-05T04:49:38Z)
• Onboard MuJoCo-based Model Predictive Control for Shipboard Crane with Double-Pendulum Sway Suppression [7.645323708488569]
  Transferring heavy payloads in maritime settings relies on efficient crane operation, limited by hazardous payload sway.<n>Existing control methods struggle in such settings, often relying on simplified analytical models.<n>We show a complete real-time control pipeline centered on the MuJoCo MPC framework.
  arXiv  Detail & Related papers  (2026-03-17T11:43:52Z)
• RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking [50.200035833530876]
  RobotDancing is a simple, scalable framework that predicts residual joint targets to explicitly correct dynamics discrepancies.<n>It can track multi-minute, high-energy behaviors (jumps, spins, cartwheels) and deploys zero-shot to hardware with high motion tracking quality.
  arXiv  Detail & Related papers  (2025-09-25T03:30:34Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulation [13.319344167881383]
  We introduce a dual-stage AV-centric simulation framework that conducts imitation learning pre-training in a data-driven simulator.<n>We then learn fine-tuning in a physics-based simulator to enhance style-level controllability.<n>In the fine-tuning stage, we propose RIFT, a novel group-relative RL fine-tuning strategy.
  arXiv  Detail & Related papers  (2025-05-06T09:12:37Z)
• Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows [0.0]
  We propose a model-based reinforcement learning (MBRL) approach by incorporating a novel reduced-order model as a surrogate for the full environment.<n>The accuracy and robustness of the model are demonstrated in the scenario of a pitching airfoil within a highly disturbed environment.<n>An application to a vertical-axis wind turbine in a disturbance-free environment is discussed in the Appendix.
  arXiv  Detail & Related papers  (2024-08-26T23:21:44Z)
• DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control [62.24301794794304]
  Deep Adaptive Trajectory Tracking (DATT) is a learning-based approach that can precisely track arbitrary, potentially infeasible trajectories in the presence of large disturbances in the real world. DATT significantly outperforms competitive adaptive nonlinear and model predictive controllers for both feasible smooth and infeasible trajectories in unsteady wind fields. It can efficiently run online with an inference time less than 3.2 ms, less than 1/4 of the adaptive nonlinear model predictive control baseline.
  arXiv  Detail & Related papers  (2023-10-13T12:22:31Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.