Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filter

TL;DR

This paper introduces a learning-based approach combining neural networks and an Unscented Kalman Filter to predict residual errors in robotic models, enabling more accurate simulation-to-real transfer with limited data.

Contribution

It presents a novel method that effectively models residual errors between dynamic models and real robots using sparse data and a neural network with UKF, improving simulation accuracy.

Findings

Reduces reality gap in robotic models

Effective with small data samples

Improves model-based control accuracy

Abstract

Achieving highly accurate dynamic or simulator models that are close to the real robot can facilitate model-based controls (e.g., model predictive control or linear-quadradic regulators), model-based trajectory planning (e.g., trajectory optimization), and decrease the amount of learning time necessary for reinforcement learning methods. Thus, the objective of this work is to learn the residual errors between a dynamic and/or simulator model and the real robot. This is achieved using a neural network, where the parameters of a neural network are updated through an Unscented Kalman Filter (UKF) formulation. Using this method, we model these residual errors with only small amounts of data -- a necessity as we improve the simulator/dynamic model by learning directly from real-world operation. We demonstrate our method on robotic hardware (e.g., manipulator arm, and a wheeled robot), and show that with the learned residual errors, we can further close the reality gap between dynamic models, simulations, and actual hardware.