Search Results for author:
Found 48 papers, 19 papers with code
Estimating Model Uncertainty of Neural Network in Sparse Information Form
As a result, we show that the information form of MND can be scalably applied to represent model uncertainty in MND.
3D Scene Reconstruction from a Single Viewport
To overcome the problem of reconstructing regions in 3D that are occluded in the 2D image, we propose to learn this information from synthetically generated high-resolution data.
Towards Explaining Uncertainty Estimates in Point Cloud Registration
The results of the experiment show that this explanation method can reasonably explain the uncertainty sources, providing a step towards robots that know when and why they failed in a human interpretable manner
Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients
Out-of-distribution detection is commonly proposed as a solution for ensuring reliability in real-world deployment.
Single-Shot Metric Depth from Focused Plenoptic Cameras
Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment.
How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?
We investigate the efficacy of data augmentations to close the domain gap in spaceborne computer vision, crucial for autonomous operations like on-orbit servicing.
FFHFlow: A Flow-based Variational Approach for Learning Diverse Dexterous Grasps with Shape-Aware Introspection
We further achieve performance gain by fusing this information with a discriminative grasp evaluator, facilitating a novel hybrid way for grasp evaluation.
Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments
Perceptual aliasing and weak textures pose significant challenges to the task of place recognition, hindering the performance of Simultaneous Localization and Mapping (SLAM) systems.
A Flow-based Credibility Metric for Safety-critical Pedestrian Detection
Safety is of utmost importance for perception in automated driving (AD).
A Safety-Adapted Loss for Pedestrian Detection in Automated Driving
As common evaluation metrics are not an adequate safety indicator, recent works employ approaches to identify safety-critical VRU and back-annotate the risk to the object detector.
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required.
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks.
Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly
Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP) need to be introspective on the predicted solutions, i. e. whether they are feasible or not, to circumvent potential efficiency degradation.
Out-of-Distribution Detection for Adaptive Computer Vision
It is well known that computer vision can be unreliable when faced with previously unseen imaging conditions.
6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics
We present a novel technique to estimate the 6D pose of objects from single images where the 3D geometry of the object is only given approximately and not as a precise 3D model.
Efficient and Feasible Robotic Assembly Sequence Planning via Graph Representation Learning
With GRACE, we are able to extract meaningful information from the graph input and predict assembly sequences in a step-by-step manner.
Fusing Visual Appearance and Geometry for Multi-modality 6DoF Object Tracking
In this work, we develop a multi-modality tracker that fuses information from visual appearance and geometry to estimate object poses.
Ranked #1 on
6D Pose Estimation
on YCB-Video
Virtual Reality via Object Pose Estimation and Active Learning: Realizing Telepresence Robots with Aerial Manipulation Capabilities
This article presents a novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments.
RECALL: Rehearsal-free Continual Learning for Object Classification
Our approach is called RECALL, as the network recalls categories by calculating logits for old categories before training new ones.
Ranked #1 on
Classification
on HOWS long
A Multi-body Tracking Framework -- From Rigid Objects to Kinematic Structures
Our approach focuses on methods that employ Newton-like optimization techniques, which are widely used in object tracking.
Ranked #1 on
3D Object Tracking
on RTB
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects
Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision.
Ranked #2 on
6D Pose Estimation
on OPT
A Model for Multi-View Residual Covariances based on Perspective Deformation
In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups.
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World
Finally, we use a pre-rendered sparse viewpoint model to create a joint posterior probability for the object pose.
Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning
Our method enhances the exploration capability of RL algorithms, by taking advantage of the SRL setup.
Making Curiosity Explicit in Vision-based RL
Our method enhances the exploration capability of the RL algorithms by taking advantage of the SRL setup.
Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networks
This work focuses on improving uncertainty estimation in the field of object classification from RGB images and demonstrates its benefits in two robotic applications.
Bayesian Active Learning for Sim-to-Real Robotic Perception
While learning from synthetic training data has recently gained an increased attention, in real-world robotic applications, there are still performance deficiencies due to the so-called Sim-to-Real gap.
Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes
This paper presents a probabilistic framework to obtain both reliable and fast uncertainty estimates for predictions with Deep Neural Networks (DNNs).
Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions
In contrast to most other approaches, our framework can also handle rotation-only motions that are particularly challenging for monocular odometry systems.
A Survey of Uncertainty in Deep Neural Networks
Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications.
Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes
Our novel grasp representation treats 3D points of the recorded point cloud as potential grasp contacts.
Unknown Object Segmentation from Stereo Images
This has the major advantage that instead of a noisy, and potentially incomplete depth map as an input, on which the segmentation is computed, we use the original image pair to infer the object instances and a dense depth map.
Learning to Localize in New Environments from Synthetic Training Data
Our approach outperforms the 5-point algorithm using SIFT features on equally big images and additionally surpasses all previous learning-based approaches that were trained on different data.
"What's This?" -- Learning to Segment Unknown Objects from Manipulation Sequences
Furthermore, while the motion of the manipulator and the object are substantial cues for our algorithm, we present means to robustly deal with distraction objects moving in the background, as well as with completely static scenes.
Bayesian Optimization Meets Laplace Approximation for Robotic Introspection
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.
DOT: Dynamic Object Tracking for Visual SLAM
In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments.
Gaussian Process Gradient Maps for Loop-Closure Detection in Unstructured Planetary Environments
Loop closures are verified by leveraging both the spatial characteristic of the elevation maps (SE(2) registration) and the probabilistic nature of the GP representation.
Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
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.
Effective Version Space Reduction for Convolutional Neural Networks
In active learning, sampling bias could pose a serious inconsistency problem and hinder the algorithm from finding the optimal hypothesis.
Ranked #107 on
Image Classification
on STL-10
Estimating Model Uncertainty of Neural Networks in Sparse Information Form
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.
Segmentation of Surgical Instruments for Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks
Nevertheless, one of the caveats of this approach is that the model is unable to generalize well to other surgical instruments with a different shape from the one used for training.
Visual-Inertial Telepresence for Aerial Manipulation
This paper presents a novel telepresence system for enhancing aerial manipulation capabilities.
Self-Supervised Object-in-Gripper Segmentation from Robotic Motions
Accurate object segmentation is a crucial task in the context of robotic manipulation.
Representing Model Uncertainty of Neural Networks in Sparse Information Form
This paper addresses the problem of representing a system's belief using multi-variate normal distributions (MND) where the underlying model is based on a deep neural network (DNN).
Non-Parametric Calibration for Classification
Many applications of classification methods not only require high accuracy but also reliable estimation of predictive uncertainty.
Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization.
Ranked #1 on
6D Pose Estimation using RGBD
on T-LESS
Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks
We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces.
