Online Dynamics Learning for Predictive Control with an Application to Aerial Robots
This work addresses the need for adaptive model-based control in robotics, particularly for aerial robots, by enabling online learning to improve robustness against disturbances, though it is incremental as it builds on existing methods like KNODE and transfer learning.
The authors tackled the problem of improving dynamic model accuracy for model predictive control (MPC) in an online setting, proposing a framework that continually adapts models during deployment using knowledge-based neural ODEs and transfer learning techniques, with results showing it can handle time-varying disturbances while maintaining good trajectory tracking performance in quadrotor simulations and experiments.
In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance.