Introspective Robot Perception Using Smoothed Predictions from Bayesian Neural Networks

Jianxiang Feng, Maximilian Durner, Zoltán Csaba Márton, Ferenc Bálint-Benczédi, Rudolph Triebel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations


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.

Original languageEnglish
Title of host publicationRobotics Research - The 19th International Symposium ISRR
EditorsTamim Asfour, Eiichi Yoshida, Jaeheung Park, Henrik Christensen, Oussama Khatib
PublisherSpringer Nature
Number of pages16
ISBN (Print)9783030954581
StatePublished - 2022
Event17th International Symposium of Robotics Research, ISRR 2019 - Hanoi, Viet Nam
Duration: 6 Oct 201910 Oct 2019

Publication series

NameSpringer Proceedings in Advanced Robotics
Volume20 SPAR
ISSN (Print)2511-1256
ISSN (Electronic)2511-1264


Conference17th International Symposium of Robotics Research, ISRR 2019
Country/TerritoryViet Nam


  • BNN
  • CRF
  • Introspective classification


Dive into the research topics of 'Introspective Robot Perception Using Smoothed Predictions from Bayesian Neural Networks'. Together they form a unique fingerprint.

Cite this