Learning Hybrid Dynamics Models With Simulator-Informed Latent States

TL;DR

This paper introduces a hybrid dynamics modeling approach that combines learned models with simulator-informed latent states, using observers to infer and correct latent states over time, improving prediction accuracy and physical meaningfulness.

Contribution

It proposes a novel method that integrates a black-box simulator with learned models through observer-based inference of latent states, addressing errors and inaccuracies in hybrid modeling.

Findings

Enhanced prediction stability over time

Reduced error accumulation in dynamics predictions

Effective correction of model mismatch using the simulator

Abstract

Dynamics model learning deals with the task of inferring unknown dynamics from measurement data and predicting the future behavior of the system. A typical approach to address this problem is to train recurrent models. However, predictions with these models are often not physically meaningful. Further, they suffer from deteriorated behavior over time due to accumulating errors. Often, simulators building on first principles are available being physically meaningful by design. However, modeling simplifications typically cause inaccuracies in these models. Consequently, hybrid modeling is an emerging trend that aims to combine the best of both worlds. In this paper, we propose a new approach to hybrid modeling, where we inform the latent states of a learned model via a black-box simulator. This allows to control the predictions via the simulator preventing them from accumulating errors. This is especially challenging since, in contrast to previous approaches, access to the simulator's latent states is not available. We tackle the task by leveraging observers, a well-known concept from control theory, inferring unknown latent states from observations and dynamics over time. In our learning-based setting, we jointly learn the dynamics and an observer that infers the latent states via the simulator. Thus, the simulator constantly corrects the latent states, compensating for modeling mismatch caused by learning. To maintain flexibility, we train an RNN-based residuum for the latent states that cannot be informed by the simulator.