Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Efficient Domain-Adaptive Policy Learning via Kernel Representation with Application to Quadrotor Control under Non-Stationary Disturbances

About

We present an algorithm for efficient domain-adaptive policy learning via kernel representations. Learning domain-adaptive policies is challenging since it requires an environment representation that is both sufficiently expressive to model complex sim-to-real gaps during offline training, and computationally efficient enough to support rapid online adaptation during deployment. For instance, a quadrotor may encounter time-varying, non-stationary disturbances, such as sudden gusts of wind, payload shifts, or transitions between distinct flight regimes with and without ground effects. To address these challenges, we model unknown disturbances using a differentiable kernel approximation based on random Fourier features. During the offline training phase, we randomly sample kernel coefficients and bandwidth parameters to generate a rich diversity of disturbance profiles. We then optimize the control policy via differentiable simulation with analytical gradients, a process that takes only 50 seconds of training time on an RTX 4090 GPU. During hardware deployment, the policy adapts to non-stationary environments in real time by updating both the kernel coefficients and bandwidth through online least-squares estimation. We evaluate our method on quadrotor trajectory tracking tasks across high-fidelity numerical simulations and hardware experiments using Crazyflie, subjected to various disturbances, including complex aerodynamic effects, wind, ground effects, and payload fluctuations.

Hongyu Zhou, Mingtian Tan, Vasileios Tzoumas• 2026

Related benchmarks

TaskDatasetResultRank
Trajectory trackingCrazyflie Hardware Ground Disturbance v1 (Experiment)
RMSE (cm)6.41
7
Trajectory trackingCrazyflie Wind Disturbance v1 (Hardware Experiment)
RMSE (cm)8.8
7
Trajectory trackingCrazyflie Hardware Payload Disturbance v1
RMSE (cm)6.68
7
Trajectory trackingNumerical Simulation Aerodynamic
RMSE3.17
7
Trajectory trackingNumerical Simulation Aerodynamic + Sinusoidal
RMSE4.1
7
Trajectory trackingNumerical Simulation Aerodynamic + Switching
RMSE4.11
7
Trajectory trackingNumerical Simulation Aerodynamic + Quadratic-Phase Sinusoidal
RMSE4
7
Showing 7 of 7 rows

Other info

Follow for update