Gerhard Neumann

research

∙ 08/01/2023

DMFC-GraspNet: Differentiable Multi-Fingered Robotic Grasp Generation in Cluttered Scenes

Robotic grasping is a fundamental skill required for object manipulation...

0 Philipp Blättner, et al. ∙

research

∙ 07/01/2023

SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation

Detecting objects and estimating their 6D poses is essential for automat...

0 Fabian Duffhauss, et al. ∙

research

∙ 06/22/2023

MP3: Movement Primitive-Based (Re-)Planning Policy

We introduce a novel deep reinforcement learning (RL) approach called Mo...

0 Fabian Otto, et al. ∙

research

∙ 06/21/2023

Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

Bayesian deep learning (BDL) is a promising approach to achieve well-cal...

0 Florian Seligmann, et al. ∙

research

∙ 04/11/2023

Curriculum-Based Imitation of Versatile Skills

Learning skills by imitation is a promising concept for the intuitive te...

0 Maximilian Xiling Li, et al. ∙

research

∙ 04/03/2023

Swarm Reinforcement Learning For Adaptive Mesh Refinement

Adaptive Mesh Refinement (AMR) is crucial for mesh-based simulations, as...

0 Niklas Freymuth, et al. ∙

research

∙ 03/27/2023

Information Maximizing Curriculum: A Curriculum-Based Approach for Training Mixtures of Experts

Mixtures of Experts (MoE) are known for their ability to learn complex c...

0 Denis Blessing, et al. ∙

research

∙ 02/23/2023

Grounding Graph Network Simulators using Physical Sensor Observations

Physical simulations that accurately model reality are crucial for many ...

0 Jonas Linkerhägner, et al. ∙

research

∙ 02/19/2023

LapGym – An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery

Recent advances in reinforcement learning (RL) have increased the promis...

0 Paul Maria Scheikl, et al. ∙

research

∙ 02/10/2023

Reinforcement Learning from Multiple Sensors via Joint Representations

In many scenarios, observations from more than one sensor modality are a...

0 Philipp Becker, et al. ∙

research

∙ 10/18/2022

Deep Black-Box Reinforcement Learning with Movement Primitives

-based reinforcement learning (ERL) algorithms treat reinforcement learn...

5 Fabian Otto, et al. ∙

research

∙ 10/17/2022

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning

Improved state space models, such as Recurrent State Space Models (RSSMs...

0 Philipp Becker, et al. ∙

research

∙ 10/17/2022

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Humans intuitively solve tasks in versatile ways, varying their behavior...

0 Niklas Freymuth, et al. ∙

research

∙ 10/04/2022

ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives

Movement Primitives (MPs) are a well-known concept to represent and gene...

3 Ge Li, et al. ∙

research

∙ 09/23/2022

A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models

Variational inference with Gaussian mixture models (GMMs) enables learni...

0 Oleg Arenz, et al. ∙

research

∙ 09/22/2022

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

Sensor fusion can significantly improve the performance of many computer...

0 Fabian Duffhauss, et al. ∙

research

∙ 08/01/2022

MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network

Estimating 6D poses of objects is an essential computer vision task. How...

11 Fabian Duffhauss, et al. ∙

research

∙ 07/31/2022

Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination

Learning robotic tasks in the real world is still highly challenging and...

1 Abdalkarim Mohtasib, et al. ∙

research

∙ 06/29/2022

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Recurrent State-space models (RSSMs) are highly expressive models for le...

1 Vaisakh Shaj, et al. ∙

research

∙ 05/27/2022

End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

It is well-known that inverse dynamics models can improve tracking perfo...

0 Moritz Reuss, et al. ∙

research

∙ 05/24/2022

Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control

Most successful stochastic black-box optimizers, such as CMA-ES, use ran...

0 Maximilian Hüttenrauch, et al. ∙

research

∙ 03/15/2022

Reactive Motion Generation on Learned Riemannian Manifolds

In recent decades, advancements in motion learning have enabled robots t...

3 Hadi Beik-Mohammadi, et al. ∙

research

∙ 03/09/2022

What Matters For Meta-Learning Vision Regression Tasks?

Meta-learning is widely used in few-shot classification and function reg...

10 Ning Gao, et al. ∙

research

∙ 02/28/2022

Hierarchical Policy Learning for Mechanical Search

Retrieving objects from clutters is a complex task, which requires multi...

0 Oussama Zenkri, et al. ∙

research

∙ 12/08/2021

Specializing Versatile Skill Libraries using Local Mixture of Experts

A long-cherished vision in robotics is to equip robots with skills that ...

0 Onur Celik, et al. ∙

research

∙ 11/29/2021

Human-machine Symbiosis: A Multivariate Perspective for Physically Coupled Human-machine Systems

The notion of symbiosis has been increasingly mentioned in research on p...

0 Jairo Inga, et al. ∙

research

∙ 11/16/2021

Switching Recurrent Kalman Networks

Forecasting driving behavior or other sensor measurements is an essentia...

0 Giao Nguyen-Quynh, et al. ∙

research

∙ 11/15/2021

Versatile Inverse Reinforcement Learning via Cumulative Rewards

Inverse Reinforcement Learning infers a reward function from expert demo...

0 Niklas Freymuth, et al. ∙

research

∙ 10/10/2021

Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning

Cognitive cooperative assistance in robot-assisted surgery holds the pot...

0 Paul Maria Scheikl, et al. ∙

research

∙ 08/06/2021

A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning

Deep Reinforcement Learning (DRL) is a promising approach for teaching r...

0 Abdalkarim Mohtasib, et al. ∙

research

∙ 07/08/2021

Navigate-and-Seek: a Robotics Framework for People Localization in Agricultural Environments

The agricultural domain offers a working environment where many human la...

0 Riccardo Polvara, et al. ∙

research

∙ 06/10/2021

Differentiable Robust LQR Layers

This paper proposes a differentiable robust LQR layer for reinforcement ...

0 Ngo Anh Vien, et al. ∙

research

∙ 06/08/2021

Learning Riemannian Manifolds for Geodesic Motion Skills

For robots to work alongside humans and perform in unstructured environm...

12 Hadi Beik-Mohammadi, et al. ∙

research

∙ 06/08/2021

Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

While classic control theory offers state of the art solutions in many p...

0 Alireza Ranjbar, et al. ∙

research

∙ 01/22/2021

Differentiable Trust Region Layers for Deep Reinforcement Learning

Trust region methods are a popular tool in reinforcement learning as the...

0 Fabian Otto, et al. ∙

research

∙ 10/20/2020

Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning

Estimating accurate forward and inverse dynamics models is a crucial com...

14 Vaisakh Shaj, et al. ∙

research

∙ 08/10/2020

Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space

This work adds on to the on-going efforts to provide more autonomy to sp...

0 RB Ashith Shyam, et al. ∙

research

∙ 08/08/2020

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

Many modern methods for imitation learning and inverse reinforcement lea...

0 Oleg Arenz, et al. ∙

research

∙ 02/26/2020

Probabilistic approach to physical object disentangling

Physically disentangling entangled objects from each other is a problem ...

0 Joni Pajarinen, et al. ∙

research

∙ 01/23/2020

Expected Information Maximization: Using the I-Projection for Mixture Density Estimation

Modelling highly multi-modal data is a challenging problem in machine le...

0 Philipp Becker, et al. ∙

research

∙ 07/10/2019

Trust-Region Variational Inference with Gaussian Mixture Models

Many methods for machine learning rely on approximate inference from int...

5 Oleg Arenz, et al. ∙

research

∙ 05/17/2019

Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces

In order to integrate uncertainty estimates into deep time-series modell...

0 Philipp Becker, et al. ∙

research

∙ 02/07/2019

Compatible Natural Gradient Policy Search

Trust-region methods have yielded state-of-the-art results in policy sea...

0 Joni Pajarinen, et al. ∙

research

∙ 11/16/2018

An Algorithmic Perspective on Imitation Learning

As robots and other intelligent agents move from simple environments and...

0 Takayuki Osa, et al. ∙

research

∙ 08/31/2018

Adaptation and Robust Learning of Probabilistic Movement Primitives

Probabilistic representations of movement primitives open important new ...

0 Sebastián Gómez-González, et al. ∙

research

∙ 08/20/2018

Towards Fine Grained Network Flow Prediction

One main challenge for the design of networks is that traffic load is no...

0 Patrick Jahnke, et al. ∙

research

∙ 07/17/2018

Deep Reinforcement Learning for Swarm Systems

Recently, deep reinforcement learning (RL) methods have been applied suc...

0 Maximilian Hüttenrauch, et al. ∙

research

∙ 09/21/2017

Learning Complex Swarm Behaviors by Exploiting Local Communication Protocols with Deep Reinforcement Learning

Swarm systems constitute a challenging problem for reinforcement learnin...

0 Maximilian Hüttenrauch, et al. ∙

research

∙ 09/18/2017

Guided Deep Reinforcement Learning for Swarm Systems

In this paper, we investigate how to learn to control a group of coopera...

0 Maximilian Hüttenrauch, et al. ∙

research

∙ 11/10/2016

Policy Search with High-Dimensional Context Variables

Direct contextual policy search methods learn to improve policy paramete...

0 Voot Tangkaratt, et al. ∙

Gerhard Neumann

Featured Co-authors