Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian ProcessesDownload PDF

Published: 13 Sept 2021, Last Modified: 05 May 2023CoRL2021 PosterReaders: Everyone
Keywords: Robotic Introspection, Bayesian Deep Learning, Gaussian Processes
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.
Supplementary Material: zip
Poster: png
27 Replies

Loading