Towards Mitigating Sim2Real Gaps: A Formal Quantitative Approach

TL;DR

This paper introduces a formal method to quantify and mitigate the simulation-to-reality gap using simulation-gap functions and data-driven approaches, enabling reliable transfer of control strategies from simulation to real systems.

Contribution

It proposes a novel formal framework and data-driven approach to quantify simulation gaps, facilitating effective model-based control transfer from simulation to real-world systems.

Findings

Effective quantification of simulation gaps using simulation-gap functions.

Successful application on nonlinear pendulum and Turtlebot models.

Guarantees seamless transition from simulation to real-world control.

Abstract

In this paper, we introduce the notion of simulation-gap functions to formally quantify the potential gap between an approximate nominal mathematical model and the high-fidelity simulator representation of a real system. Given a nominal mathematical model alongside a quantified simulation gap, the system can be conceptualized as one characterized by bounded states and input-dependent disturbances. This allows us to leverage the existing powerful model-based control algorithms effectively, ensuring the enforcement of desired specifications while guaranteeing a seamless transition from simulation to real-world application. To provide a formal guarantee for quantifying the simulation gap, we develop a data-driven approach. In particular, we collect data using high-fidelity simulators, leveraging recent advancements in Real-to-Sim transfer to ensure close alignment with reality. We demonstrate the effectiveness of the proposed method through experiments conducted on a nonlinear pendulum system and a nonlinear Turtlebot model in simulators.