Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes
Jongseok Lee, Jianxiang Feng, Matthias Humt, Marcus Gerhard Müller, Rudolph Triebel
Abstract
This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs). Our main contribution is a practical and principled combination of DNNs with sparse Gaussian Processes (GPs). We prove theoretically that DNNs can be seen as a special case of sparse GPs, namely mixtures of GP experts (MoE-GP), and we devise a learning algorithm that brings the derived theory into practice. In experiments from two different robotic tasks -- inverse dynamics of a manipulator and object detection on a micro-aerial vehicle (MAV) -- we show the effectiveness of our approach in terms of predictive uncertainty, improved scalability, and run-time efficiency on a Jetson TX2. We thus argue that our approach can pave the way towards reliable and fast robot learning systems with uncertainty awareness.
BibTeX
@inproceedings{
lee2021trust,
title={Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes},
author={Jongseok Lee and Jianxiang Feng and Matthias Humt and Marcus Gerhard M{\"u}ller and Rudolph Triebel},
booktitle={5th Annual Conference on Robot Learning },
year={2021},
url={https://openreview.net/forum?id=eIk6eBz3Wlt}
}