Real-time Uncertainty Decomposition for Online Learning Control

10/06/2020
by   Jonas Umlauft, et al.
0

Safety-critical decisions based on machine learning models require a clear understanding of the involved uncertainties to avoid hazardous or risky situations. While aleatoric uncertainty can be explicitly modeled given a parametric description, epistemic uncertainty rather describes the presence or absence of training data. This paper proposes a novel generic method for modeling epistemic uncertainty and shows its advantages over existing approaches for neural networks on various data sets. It can be directly combined with aleatoric uncertainty estimates and allows for prediction in real-time as the inference is sample-free. We exploit this property in a model-based quadcopter control setting and demonstrate how the controller benefits from a differentiation between aleatoric and epistemic uncertainty in online learning of thermal disturbances.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 11

page 12

08/01/2019

Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation

We present a sampling-free approach for computing the epistemic uncertai...
10/10/2017

Incorporating Epistemic Uncertainty into the Safety Assurance of Socio-Technical Systems

In system development, epistemic uncertainty is an ever-present possibil...
04/13/2021

Multivariate Deep Evidential Regression

There is significant need for principled uncertainty reasoning in machin...
10/18/2021

Set-based State Estimation with Probabilistic Consistency Guarantee under Epistemic Uncertainty

Consistent state estimation is challenging, especially under the epistem...
04/18/2019

Safety-margin-based design and redesign considering mixed epistemic model uncertainty and aleatory parameter uncertainty

At the initial design stage engineers often rely on low-fidelity models ...
11/18/2019

Justification-Based Reliability in Machine Learning

With the advent of Deep Learning, the field of machine learning (ML) has...
07/06/2021

Intrinsic uncertainties and where to find them

We introduce a framework for uncertainty estimation that both describes ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.