期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 7, 期 2, 页码 2819-2826出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3144787
关键词
Machine learning for robot control; model learning for control; model predictive control
类别
资金
- NSF IIS [1910308]
- DSO National Laboratories, 12 Science Park Drive, Singapore
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1910308] Funding Source: National Science Foundation
This letter presents a method to enhance the dynamic models used in model predictive control (MPC) for quadrotor control using deep learning. By integrating a first-principle model and a neural network, the hybrid model can accurately predict the quadrotor dynamics and demonstrates improved performance in closed-loop control.
In this letter, 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 letter, 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 60.2% improvement in simulations and more than 21% in physical experiments, in terms of trajectory tracking performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据