A Review of Differentiable Simulators

TL;DR

This paper provides a comprehensive review of differentiable simulators, covering their foundations, design choices, open-source tools, applications, limitations, and future research directions in physics-based simulation.

Contribution

It offers an in-depth synthesis of the current state-of-the-art in differentiable physics simulators, including practical guidance and contextualization of applications.

Findings

Summarizes core components and design trade-offs of differentiable simulators.

Reviews open-source tools and their applications in research.

Highlights current limitations and future research directions.

Abstract

Differentiable simulators continue to push the state of the art across a range of domains including computational physics, robotics, and machine learning. Their main value is the ability to compute gradients of physical processes, which allows differentiable simulators to be readily integrated into commonly employed gradient-based optimization schemes. To achieve this, a number of design decisions need to be considered representing trade-offs in versatility, computational speed, and accuracy of the gradients obtained. This paper presents an in-depth review of the evolving landscape of differentiable physics simulators. We introduce the foundations and core components of differentiable simulators alongside common design choices. This is followed by a practical guide and overview of open-source differentiable simulators that have been used across past research. Finally, we review and contextualize prominent applications of differentiable simulation. By offering a comprehensive review of the current state-of-the-art in differentiable simulation, this work aims to serve as a resource for researchers and practitioners looking to understand and integrate differentiable physics within their research. We conclude by highlighting current limitations as well as providing insights into future directions for the field.