Real-to-Sim: Deep Learning with Auto-Tuning to Predict Residual Errors using Sparse Data

by   Alexander Schperberg, et al.

Achieving highly accurate kinematic 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 kinematic and/or simulator model and the real robot. This is achieved using auto-tuning and neural networks, where the parameters of a neural network are updated using an auto-tuning method that applies equations from 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/kinematic model by learning directly from hardware operation. We demonstrate our method on robotic hardware (e.g., manipulator arm), and show that with the learned residual errors, we can further close the reality gap between kinematic models, simulations, and the real robot.


page 1

page 3

page 6


Residual Model Learning for Microrobot Control

A majority of microrobots are constructed using compliant materials that...

Learning-based Observer Evaluated on the Kinematic Bicycle Model

The knowledge of the states of a vehicle is a necessity to perform prope...

Adaptive Identification of Legged Robotic Kinematic Structure

Model-based control usually relies on an accurate model, which is often ...

Auto-Calibrating Admittance Controller for Robust Motion of Robotic Systems

We demonstrate an admittance controller with auto-tuning that can be app...

Differentiable Moving Horizon Estimation for Robust Flight Control

Estimating and reacting to external disturbances is of fundamental impor...

Impact Intensity Estimation of a Quadruped Robot without Using a Force Sensor

Estimating the impact intensity is one of the significant tasks of the l...

Kinematic Resolutions of Redundant Robot Manipulators using Integration-Enhanced RNNs

Recently, a time-varying quadratic programming (QP) framework that descr...

Please sign up or login with your details

Forgot password? Click here to reset