Introspective Robot Perception Using Smoothed Predictions from Bayesian Neural Networks

Jianxiang Feng*1,2 , Maximilian Durner*1,2 , Zoltán-Csaba Márton1 , Ferenc Bálint-Benczédi3, Rudolph Triebel1,2

⋆ Equal Contribution.

1: Institute of Robotics and Mechatronics, German Aerospace Center (DLR)

2: Department of Informatics, Technical University of Munich (TUM)

3: Institute for Artificial Intelligence, University of Bremen

Abstract

This work focuses on improving uncertainty estimation in the field of object classification from RGB images and demonstrates its benefits in two robotic applications. We employ a Bayesian Neural Network (BNN), and evaluate two practical inference techniques to obtain better uncertainty estimates, namely Concrete Dropout (CDP) and Kronecker-factored Laplace Approximation (LAP). We show a performance increase using more reliable uncertainty estimates as unary potentials within a Conditional Random Field (CRF), which is able to incorporate contextual information as well. Furthermore, the obtained uncertainties are exploited to achieve domain adaptation in a semi-supervised manner, which requires less manual efforts in annotating data. We evaluate our approach on two public benchmark datasets that are relevant for robot perception tasks.