GustPilot: A Hierarchical DRL-INDI Framework for Wind-Resilient Quadrotor Navigation

• URL: http://arxiv.org/abs/2603.19966v1
• Date: Fri, 20 Mar 2026 14:06:11 GMT
• Title: GustPilot: A Hierarchical DRL-INDI Framework for Wind-Resilient Quadrotor Navigation
• Abstract summary: GustPilot is a wind-resilient navigation stack for lightweight quadrotors.<n>Wind disturbances remain a key barrier to reliable autonomous navigation for lightweight quadrotors.<n>We evaluate GustPilot in real flights on a 50g quad-copter platform.
• Score: 2.0325612651874305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wind disturbances remain a key barrier to reliable autonomous navigation for lightweight quadrotors, where the rapidly varying airflow can destabilize both planning and tracking. This paper introduces GustPilot, a hierarchical wind-resilient navigation stack in which a deep reinforcement learning (DRL) policy generates inertial-frame velocity reference for gate traversal. At the same time, a geometric Incremental Nonlinear Dynamic Inversion (INDI) controller provides low-level tracking with fast residual disturbance rejection. The INDI layer achieves this by providing incremental feedback on both specific linear acceleration and angular acceleration rate, using onboard sensor measurements to reject wind disturbances rapidly. Robustness is obtained through a two-level strategy, wind-aware planning learned via fan-jet domain randomization during training, and rapid execution-time disturbance rejection by the INDI tracking controller. We evaluate GustPilot in real flights on a 50g quad-copter platform against a DRL-PID baseline across four scenarios ranging from no-wind to fully dynamic conditions with a moving gate and a moving disturbance source. Despite being trained only in a minimal single-gate and single-fan setup, the policy generalizes to significantly more complex environments (up to six gates and four fans) without retraining. Across 80 experiments, DRL-INDI achieves a 94.7% versus 55.0% for DRL-PID as average Overall Success Rate (OSR), reduces tracking RMSE up to 50%, and sustains speeds up to 1.34 m/s under wind disturbances up to 3.5 m/s. These results demonstrate that combining DRL-based velocity planning with structured INDI disturbance rejection provides a practical and generalizable approach to wind-resilient autonomous flight navigation.

Related papers

• Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach [33.68706070829591]
  Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control.<n>A massive cloud-based LLM deployed on a High-Altitude Platform Station manages slow-timescale global load balancing.<n> lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals to execute collision-free, handover-aware trajectories.
  arXiv  Detail & Related papers  (2026-07-21T00:34:42Z)
• Disturbance-Aware Flight for Aerial Robots in Narrow Space [18.124392684552998]
  This paper presents a disturbance-aware planning and control framework that integrates online disturbance estimation into the planning-control loop for quadrotor flight in narrow space.<n> Experiments demonstrate that a quadrotor with a diagonal length of 0.39m can traverse straight, sloped, and curved tunnels as narrow as 0.6m, outperforming human pilots in both success rate and flight efficiency.
  arXiv  Detail & Related papers  (2026-07-20T01:58:05Z)
• Wind-Aware Reinforcement Learning Control of a Small Quadrotor Using Learned Onboard Wind Estimation in Simulated Atmospheric Turbulence [2.878288301715711]
  Small multirotor aircraft are increasingly tasked with operations in the atmospheric boundary layer.<n>This work illustrates a two-stage learning pipeline that first estimates the local wind from onboard kinematics and dynamics.
  arXiv  Detail & Related papers  (2026-07-01T22:59:18Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• Spatially-Aware Adaptive Trajectory Optimization with Controller-Guided Feedback for Autonomous Racing [74.83272587893508]
  We present a framework for autonomous raceline optimization that combines NURBS-based trajectory representation, CMA-ES global trajectory optimization, and controller-guided spatial feedback.<n>In simulation, our approach achieves a 17.38% lap time reduction compared to a controller parametrized with maximum static acceleration.<n>On real hardware, tested with different tire compounds ranging from high to low friction, we obtain a 7.60% lap time improvement without explicitly parametrizing friction.
  arXiv  Detail & Related papers  (2026-02-17T15:10:44Z)
• Design and Implementation of a High-Precision Wind-Estimation UAV with Onboard Sensors [4.9295028416281985]
  This paper proposes a real-time wind estimation method based solely on onboard sensors.<n>System is validated through comprehensive experiments in wind tunnels, indoor and outdoor flights.
  arXiv  Detail & Related papers  (2025-12-11T08:39:55Z)
• Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning [45.51804571136028]
  Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs)<n>We introduce Slow-Fast Policy Optimization (SFPO), a simple yet efficient framework to address these limitations via decomposing each step into three stages.<n>SFPO consistently improves stability, reduces rollouts, and accelerates convergence of reasoning RL training.
  arXiv  Detail & Related papers  (2025-10-05T07:22:54Z)
• Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seeking [39.407739937584104]
  We study the use of robust model independent bounded extremum seeking (ES) feedback control to improve the robustness of deep reinforcement learning controllers.<n>We present a numerical study of a general time-varying system and a combined ES-DRL controller for automatic tuning of the Low Energy Beam Transport section at the Los Alamos Neutron Science Center linear particle accelerator.
  arXiv  Detail & Related papers  (2025-10-02T18:53:02Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Navigation in a simplified Urban Flow through Deep Reinforcement Learning [0.9217021281095907]
  Unmanned aerial vehicles (UAVs) in urban environments require a strategy to minimize their environmental impact. Our goal is to develop DRL algorithms capable of enabling the autonomous navigation of UAVs in urban environments.
  arXiv  Detail & Related papers  (2024-09-26T15:05:15Z)
• AirPilot: Interpretable PPO-based DRL Auto-Tuned Nonlinear PID Drone Controller for Robust Autonomous Flights [0.046873264197900916]
  AirPilot is a nonlinear Deep Reinforcement Learning (DRL) - enhanced Proportional Integral Derivative (PID) drone controller.<n>AirPilot controller combines the simplicity and effectiveness of traditional PID control with the adaptability, learning capability, and optimization potential of DRL.<n>Airpilot is capable of reducing the navigation error of the default PX4 PID position controller by 90%, improving effective navigation speed of a fine-tuned PID controller by 21%.
  arXiv  Detail & Related papers  (2024-03-30T00:46:43Z)
• Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds [96.74836678572582]
  We present a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly achieves precise flight control with substantially smaller tracking error than state-of-the-art nonlinear and adaptive controllers.
  arXiv  Detail & Related papers  (2022-05-13T21:55:28Z)

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.