Online Dynamics Learning for Predictive Control with an Application to Aerial Robots

by   Tom Z. Jiahao, et al.

In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Even though 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. After the model is trained to a desired accuracy, it is then deployed in a model predictive controller. 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 robot, and verify the framework in both simulations and physical experiments. Results show that the proposed approach is able to account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance.


page 1

page 2

page 3

page 4


KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robots

In this work, we consider the problem of deriving and incorporating accu...

Learning-enhanced Nonlinear Model Predictive Control using Knowledge-based Neural Ordinary Differential Equations and Deep Ensembles

Nonlinear model predictive control (MPC) is a flexible and increasingly ...

Offline-Online Learning of Deformation Model for Cable Manipulation with Graph Neural Networks

Manipulating deformable linear objects by robots has a wide range of app...

Online Learning in Planar Pushing with Combined Prediction Model

Pushing is a useful robotic capability for positioning and reorienting o...

Deep Learning with Predictive Control for Human Motion Tracking

We propose to combine model predictive control with deep learning for th...

Learning References with Gaussian Processes in Model Predictive Control applied to Robot Assisted Surgery

One of the key benefits of model predictive control is the capability of...

Learning Adaptive Control for SE(3) Hamiltonian Dynamics

Fast adaptive control is a critical component for reliable robot autonom...

Please sign up or login with your details

Forgot password? Click here to reset