cs.ROMar 20, 2026

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

Authors: Amir Atef Habel, Roohan Ahmed Khan, Fawad Mehboob, Clement Fortin, Dzmitry Tsetserukou

Organizations: Intelligent Space Robotics Laboratory, Center for Digital Engineering, Skolkovo Institute of Science and Technology, Moscow, Russia.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Fig. 1: GustPilot during real-flight gate traversal under distributed and concentrated fan-generated wind disturbances.
Fig. 2: Overview of the GustPilot hierarchical guidance-control architecture.
ParameterValue
KvK_{v} (outer)[3.519,  3.519,  31.481] s−1[3.519,\;3.519,\;31.481]~\mathrm{s}^{-1}
KiK_{i} (outer)[0.037,  0.037,  5.556] s−2[0.037,\;0.037,\;5.556]~\mathrm{s}^{-2}
KξK_{\xi} (inner)[4.643,  4.643,  46.08]×109 s−2[4.643,\;4.643,\;46.08]\times 10^{9}~\mathrm{s}^{-2}
KωK_{\omega} (inner)[7.857,  7.857,  5.530]×108 s−1[7.857,\;7.857,\;5.530]\times 10^{8}~\mathrm{s}^{-1}
αOuter\alpha_{\text{Outer}} , αInner\alpha_{\text{Inner}}1.01.0
Torque saturation[0.0,  0.000949] N⋅m[0.0,\;0.000949]~\mathrm{N\cdot m}
TABLE I: Controller Tuning Parameters and Filter Cutoffs.
CategoryParameterRange/Value
Domain Randdmind_{\text{min}} , dmaxd_{\text{max}} (m)1.0, 5.0
Jet GeometryRtubeR_{\text{tube}} (m)U(0.25,1.00)\mathcal{U}(0.25,1.00)
LtubeL_{\text{tube}} (m)U(0.2,1.5)\mathcal{U}(0.2,1.5)
Wind Modelu0u_{0} (m/s) (jet strength)1.0–10.0
x0x_{0} (m) (virtual origin)0.20
σ0\sigma_{0} (m) (initial jet width)0.10
TABLE II: Simulation Environment Parameters
Fig. 3: Reward colormap for drone positions relative to the gate.
ParameterValue
AlgorithmPPO
Total training steps4.5×1074.5\times 10^{7}
Number of environments16
Rollout length2048
Batch size256
Discount factor ( γ\gamma )0.99
TABLE III: Training Parameters
Fig. 4: Training metrics for policies learned with INDI and PID low-level controllers.
Fig. 5: 2-D trajectory comparisons for the four real-flight scenarios (DRL–INDI vs. DRL–PID).
ScenarioControllerOSR (%)PPhhffMax SpeedTimeClosest GateClosest FanAirspeedRMSEMAEMax AbsRMSE Vel.
      (m/s)(s)(m)(m)(m/s)(m)(m)(m)(m/s)
IINDI98.811101.337140.065——0.1270.1210.1800.170
PID88.96891.000240.096——0.1900.2200.2100.200
IIINDI97.223101.347140.040 a0.7002.440.1190.1110.1840.163
PID0.020200—————1.700 b——0.400 c
IIIINDI92.545101.12290.077 d0.4503.50.1100.0970.1730.177
TABLE IV: Comprehensive Experimental Results: OSR, Missed Gates ( PP ), Gate Hits ( hh ), Completed Trials ( ff ), Closest Approaches, and Tracking Errors.
More in this topic

UAV Navigation

Unmanned aerial vehicle (UAV) navigation develops methods for locating and guiding drones safely through known, unknown, and changing environments.

See all 265 papers

Explore similar work

CardsList
Oct 8, 2026

WAND: Learning Robust Navigation under Complex Wind Disturbances and Dense Obstacles for Quadrotors

Robust navigation in cluttered environments remains a fundamental challenge for quadrotors, particularly when strong wind disturbances arise, which perturb vehicle dynamics, limit control authority, and substantially increase collision risk. Existing learning-based navigation policies typically rely on obstacle perception and proprioceptive observations, requiring the policy to infer time-varying disturbance effects implicitly and thereby limiting robustness under partial observability. This paper proposes WAND (Wind-Aware Navigation with Disturbance Estimation), a reinforcement learning framework for navigation under time-varying wind disturbances in dense obstacle fields. Specifically, WAND estimates wind-induced disturbance acceleration from historical proprioceptive states using a Temporal Convolutional Network (TCN). This estimation is integrated into the policy via a zero-initialized residual module, WindAdapter, while simultaneously providing feedforward compensation for low-level control. The dual use of the estimate couples disturbance-conditioned navigation with feedforward disturbance rejection. Across 12 wind-disturbed simulation settings, WAND improved the observed success rate by 8.3 percentage points on average relative to feedforward compensation alone. Controlled opposite-crosswind experiments further showed wind-direction-dependent trajectory adaptation. In indoor fan-induced flight tests, WAND succeeded in 18 of 20 trials, demonstrating the feasibility of real-time onboard navigation.

Zhonghan Tang, Chenhui Li, Shuai Liang +5

Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China · Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China · Northwestern Polytechnical University, Xi’an 710072, China +1

Disturbance RejectionRobot NavigationQuadrotor ControlRobust ControlRobust RL
AskPDF
Sep 9, 2026

Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control

Reinforcement-learning quadrotor controllers are usually trained under simplified wind models, yet the impact of wind-field fidelity, as opposed to magnitude, on policy robustness remains unquantified. This paper compares five disturbance-fidelity levels, from wind-free flight and discrete 1-cosine gusts through statistical turbulence and synthetic coherent structures to large-eddy-simulation fields of the atmospheric boundary layer, in a full cross-fidelity train test evaluation of proximal policy optimization (PPO) agents, with cascaded PID and geometric SE(3) controllers as training-free references, over a 0-12 m/s wind sweep. Before any controller comparison is made, all disturbance data are validated: every synthetic generator is checked quantitatively against its analytical or certification-standard reference, and the large-eddy-simulation fields against the imposed log law. On a racing-class quadrotor in hover, the train test matrix is remarkably flat, and the cheapest structured training wind, which is discrete-gust domain randomization, ranks first in every test column, a ranking replicated on a wind-sensitive 27 g platform; a once-tuned geometric controller brackets the learned PPO policies at zero crash rate. Mechanism diagnostics show that control authority, not wind realism, bounds robustness, so wind-fidelity investment should scale with platform wind sensitivity.

Xun Huang

State Key Laboratory of Turbulence and Complex Systems, Department of Aeronautics and Astronautics, Peking University, Beijing, 100871, People’s Republic of China

Quadrotor ControlRobust RLDomain RandomizationProximal Policy Optimization
AskPDF
Oct 2, 2026

DR-IPC: Disturbance-Resilient Integrated Planning and Control for LiDAR-Based Quadrotor Navigation

LiDAR-based quadrotor navigation in cluttered environments remains challenging under external disturbances, particularly when obstacle-aware motion generation and disturbance-rejection control are handled in separate layers. This article presents disturbance-resilient integrated planning and control (DR-IPC), which combines lightweight path guidance with nonlinear model predictive control (NMPC) to directly generate angular velocity and thrust. An interconnected extended Kalman filter and nonlinear disturbance observer jointly provide filtered state estimates and reconstructed disturbances for NMPC prediction. The resulting formulation unifies nonlinear quadrotor dynamics, actuator constraints, local motion generation, and penalised safe-flight-corridor residuals without requiring a separate trajectory-optimization stage. Gazebo and MARSIM simulations, together with indoor and outdoor experiments, validate DR-IPC under wind, suspended payloads, narrow passages, ball impacts and reactive avoidance of a dynamic obstacle. In multi-goal navigation with disturbances, DR-IPC increases the number of completed missions from 1/10 to 9/10 in Gazebo and reduces the altitude RMSE from 0.34 to 0.01 m in experiments. The complete system operates onboard at 100 Hz. Supplementary videos are available on the project page https://drpp316.github.io/DR-IPC-Page/, and the source code will be released.

Peng Liu, Jingyan Wang, Qipeng Ye +5

School of Automation, Key Laboratory of Measurement and Control of CSE, Ministry of Education, Institute of Intelligent Unmanned Systems, Southeast University, Nanjing 210096, China. · School of Electrical Engineering and Automation, Xiamen University of Technology, Xiamen 361024, China. · Department of Computer Science, University College London, London, WC1E 6BT, UK.

Disturbance RejectionUAV NavigationQuadrotor ControlRobust ControlNonlinear MPC
AskPDF