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

by   Kong Yao Chee, et al.

In this work, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise dynamic models to achieve the desired closed-loop performance. However, the presence of uncertainties in complex systems and the environments they operate in poses a challenge in obtaining sufficiently accurate representations of the system dynamics. In this work, we make use of a deep learning tool, knowledge-based neural ordinary differential equations (KNODE), to augment a model obtained from first principles. The resulting hybrid model encompasses both a nominal first-principle model and a neural network learnt from simulated or real-world experimental data. Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data. To improve closed-loop performance, the hybrid model is integrated into a novel MPC framework, known as KNODE-MPC. Results show that the integrated framework achieves 73 14


page 1

page 5


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 ...

Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms

Model Predictive Control (MPC) has become a popular framework in embedde...

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

In this work, we consider the task of improving the accuracy of dynamic ...

Enhancing Sample Efficiency and Uncertainty Compensation in Learning-based Model Predictive Control for Aerial Robots

The recent increase in data availability and reliability has led to a su...

RAMP-Net: A Robust Adaptive MPC for Quadrotors via Physics-informed Neural Network

Model Predictive Control (MPC) is a state-of-the-art (SOTA) control tech...

A Gaussian Process Model for Opponent Prediction in Autonomous Racing

In head-to-head racing, performing tightly constrained, but highly rewar...

Data Set Description: Identifying the Physics Behind an Electric Motor – Data-Driven Learning of the Electrical Behavior (Part II)

A data set was recorded to evaluate different methods for extracting mat...

Please sign up or login with your details

Forgot password? Click here to reset