Real-time Uncertainty Decomposition for Online Learning Control

by   Jonas Umlauft, et al.

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.


page 11

page 12


The Unreasonable Effectiveness of Deep Evidential Regression

There is a significant need for principled uncertainty reasoning in mach...

Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation

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

Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

We introduce a simple but effective method for managing risk in model-ba...

Justification-Based Reliability in Machine Learning

With the advent of Deep Learning, the field of machine learning (ML) has...

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

In system development, epistemic uncertainty is an ever-present possibil...

An introduction to optimization under uncertainty – A short survey

Optimization equips engineers and scientists in a variety of fields with...

Please sign up or login with your details

Forgot password? Click here to reset