Quantification of Sim2Real Gap via Neural Simulation Gap Function

TL;DR

This paper introduces neural simulation gap functions to quantify the difference between mathematical models and high-fidelity simulators, enabling better transfer of controllers from simulation to real-world systems.

Contribution

It proposes a formal neural network-based method to quantify the Sim2Real gap with guarantees across the entire state space, including unseen data.

Findings

Formal guarantees on the simulation gap function.

Effective quantification of Sim2Real gap in case studies.

Use of high-fidelity data for accurate gap estimation.

Abstract

In this paper, we introduce the notion of neural simulation gap functions, which formally quantifies the gap between the mathematical model and the model in the high-fidelity simulator, which closely resembles reality. Many times, a controller designed for a mathematical model does not work in reality because of the unmodelled gap between the two systems. With the help of this simulation gap function, one can use existing model-based tools to design controllers for the mathematical system and formally guarantee a decent transition from the simulation to the real world. Although in this work, we have quantified this gap using a neural network, which is trained using a finite number of data points, we give formal guarantees on the simulation gap function for the entire state space including the unseen data points. We collect data from high-fidelity simulators leveraging recent advancements in Real-to-Sim transfer to ensure close alignment with reality. We demonstrate our results through two case studies - a Mecanum bot and a Pendulum.