no code implementations • ICML 2020 • Jongseok Lee, Matthias Humt, Jianxiang Feng, Rudolph Triebel
As a result, we show that the information form of MND can be scalably applied to represent model uncertainty in MND.
no code implementations • 31 Oct 2023 • Matthias Humt, Dominik Winkelbauer, Ulrich Hillenbrand, Berthold Bäuml
We present a novel, fast, and high fidelity deep learning pipeline consisting of a shape completion module that is based on a single depth image, and followed by a grasp predictor that is based on the predicted object shape.
1 code implementation • 1 Aug 2023 • Matthias Humt, Dominik Winkelbauer, Ulrich Hillenbrand
We train on this dataset and test each method in shape completion and prediction of uncertain regions for known and novel object instances and on synthetic and real data.
no code implementations • 18 Oct 2022 • JongSeok Lee, Ribin Balachandran, Konstantin Kondak, Andre Coelho, Marco De Stefano, Matthias Humt, Jianxiang Feng, Tamim Asfour, Rudolph Triebel
This article presents a novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments.
no code implementations • 20 Sep 2021 • JongSeok Lee, Jianxiang Feng, Matthias Humt, Marcus G. Müller, Rudolph Triebel
This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs).
no code implementations • 7 Jul 2021 • Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, JongSeok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler, Xiao Xiang Zhu
Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications.
no code implementations • 30 Oct 2020 • Matthias Humt, JongSeok Lee, Rudolph Triebel
In robotics, deep learning (DL) methods are used more and more widely, but their general inability to provide reliable confidence estimates will ultimately lead to fragile and unreliable systems.
no code implementations • 15 Jul 2020 • Kashmira Shinde, Jong-Seok Lee, Matthias Humt, Aydin Sezgin, Rudolph Triebel
This paper presents an end-to-end multi-modal learning approach for monocular Visual-Inertial Odometry (VIO), which is specifically designed to exploit sensor complementarity in the light of sensor degradation scenarios.
no code implementations • 20 Jun 2020 • Jongseok Lee, Matthias Humt, Jianxiang Feng, Rudolph Triebel
We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known as the information form.