Search papers, labs, and topics across Lattice.
This paper introduces an energy-based regularization loss function for training neural networks to learn residual dynamics in Model Predictive Control (MPC) for omnidirectional aerial robots. The regularization encourages the neural network to make control corrections that stabilize the system's energy, addressing the limitations of neural models in understanding physical properties. Experimental results demonstrate a 23% improvement in positional mean absolute error (MAE) compared to analytical MPC and up to 15% lower MAE compared to a standard neural MPC, along with increased flight stability.
Stabilizing system energy with a novel regularization loss lets neural MPC outperform analytical methods for controlling omnidirectional aerial robots.
Data-driven Model Predictive Control (MPC) has lately been the core research subject in the field of control theory. The combination of an optimal control framework with deep learning paradigms opens up the possibility to accurately track control tasks without the need for complex analytical models. However, the system dynamics are often nuanced and the neural model lacks the potential to understand physical properties such as inertia and conservation of energy. In this work, we propose a novel energy-based regularization loss function which is applied to the training of a neural model that learns the residual dynamics of an omnidirectional aerial robot. Our energy-based regularization encourages the neural network to cause control corrections that stabilize the energy of the system. The residual dynamics are integrated into the MPC framework and improve the positional mean absolute error (MAE) over three real-world experiments by 23% compared to an analytical MPC. We also compare our method to a standard neural MPC implementation without regularization and primarily achieve a significantly increased flight stability implicitly due to the energy regularization and up to 15% lower MAE. Our code is available under: https://github.com/johanneskbl/jsk_aerial_robot/tree/develop/neural_MPC.
