Beyond Constant Parameters: Hyper Prediction Models and HyperMPC

TL;DR

This paper introduces Hyper Prediction Model (HyperPM), a neural network-based approach that enhances model predictive control by capturing unmodeled dynamics with time-varying parameters, improving long-term prediction accuracy and robustness.

Contribution

The paper presents HyperPM, a novel neural network-based method that projects unmodeled dynamics onto a time-dependent model, enabling better anticipation of phenomena in MPC.

Findings

Reduces long-horizon prediction errors in complex systems

Outperforms existing methods in real-world autonomous racing

Maintains computational efficiency and robustness

Abstract

Model Predictive Control (MPC) is among the most widely adopted and reliable methods for robot control, relying critically on an accurate dynamics model. However, existing dynamics models used in the gradient-based MPC are limited by computational complexity and state representation. To address this limitation, we propose the Hyper Prediction Model (HyperPM) - a novel approach in which we project the unmodeled dynamics onto a time-dependent dynamics model. This time-dependency is captured through time-varying model parameters, whose evolution over the MPC prediction horizon is learned using a neural network. Such formulation preserves the computational efficiency and robustness of the base model while equipping it with the capacity to anticipate previously unmodeled phenomena. We evaluated the proposed approach on several challenging systems, including real-world F1TENTH autonomous racing, and demonstrated that it significantly reduces long-horizon prediction errors. Moreover, when integrated within the MPC framework (HyperMPC), our method consistently outperforms existing state-of-the-art techniques.