KIT - Karlsruher Institut für Technologie

Publications

A collection of our research papers, conference proceedings, and journal articles.

2026

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Tai Hoang, Alessandro Trenta*, Alessio Gravina*, Niklas Freymuth, Philipp Becker, Davide Bacciu, Gerhard Neumann
ICLR · 2026
PDF
Smooth Sampling-Based Model Predictive Control Using Deterministic Samples

Smooth Sampling-Based Model Predictive Control Using Deterministic Samples

Markus Walker, Marcel Reith-Braun, Tai Hoang, Gerhard Neumann, Uwe D Hanebeck
Preprint · 2026
PDF

2025

Scaffolding Dexterous Manipulation with Vision-Language Models

Scaffolding Dexterous Manipulation with Vision-Language Models

Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum, Onur Celik, Aleksandar Taranovic, Denis Blessing, Gerhard Neumann, Jeannette Bohg, Dorsa Sadigh
Preprint · 2025
PDF
TROLL: Trust Regions improve Reinforcement Learning for Large Language Models

TROLL: Trust Regions improve Reinforcement Learning for Large Language Models

Philipp Becker, Niklas Freymuth, Serge Thilges, Fabian Otto, Gerhard Neumann
Preprint · 2025
PDF
End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler

End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler

Denis Blessing, Xiaogang Jia, Gerhard Neumann
Preprint · 2025
PDF
Underdamped diffusion bridges with applications to sampling

Underdamped diffusion bridges with applications to sampling

Denis Blessing, Julius Berner, Lorenz Richter, Gerhard Neumann
Preprint · 2025
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

Denis Blessing, Julius Berner, Lorenz Richter, Carles Domingo-Enrich, Yuanqi Du, Arash Vahdat, Gerhard Neumann
Preprint · 2025
Dime: Diffusion-based maximum entropy reinforcement learning

Dime: Diffusion-based maximum entropy reinforcement learning

Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
ICML · 2025
MaNGO — Adaptable Graph Network Simulators via Meta-Learning

MaNGO — Adaptable Graph Network Simulators via Meta-Learning

Philipp Dahlinger, Tai Hoang, Denis Blessing, Niklas Freymuth, Gerhard Neumann
NeurIPS · 2025
PDF
Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning

Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning

Philipp Dahlinger, Niklas Freymuth, Tai Hoang, Tobias Würth, Michael Volpp, Luise Kärger, Gerhard Neumann
TMLR · 2025
Diffusion for Multi-Embodiment Grasping

Diffusion for Multi-Embodiment Grasping

Roman Freiberg, Alexander Qualmann, Ngo Anh Vien, Gerhard Neumann
IEEE Robotics and Automation Letters · 2025
AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth, Tobias Würth, Nicolas Schreiber, Balázs Gyenes, Andreas Boltres, Johannes Mitsch, Aleksandar Taranovic, Tai Hoang, Philipp Dahlinger, Philipp Becker, Luise Kärger, Gerhard Neumann
NeurIPS · 2025
PDF
Towards a Multi-Embodied Grasping Agent

Towards a Multi-Embodied Grasping Agent

Roman Freiberg, Alexander Qualmann, Ngo Anh Vien, Gerhard Neumann
Preprint · 2025
Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom

Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom

Balázs Gyenes, Nikolai Franke, Paul Maria Scheikl, Pit Henrich, Rayan Younis, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich
IEEE Robotics and Automation Letters · 2025
Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Tai Hoang, Huy Le, Philipp Becker, Vien Anh Ngo, Gerhard Neumann
ICLR · 2025 Oral
PDF
PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Xiaogang Jia, Qian Wang, Anrui Wang, Han A Wang, Balázs Gyenes, Emiliyan Gospodinov, Xinkai Jiang, Ge Li, Hongyi Zhou, Weiran Liao, others
Preprint · 2025
X-il: Exploring the design space of imitation learning policies

X-il: Exploring the design space of imitation learning policies

Xiaogang Jia, Atalay Donat, Xi Huang, Xuan Zhao, Denis Blessing, Hongyi Zhou, Han A Wang, Hanyi Zhang, Qian Wang, Rudolf Lioutikov, others
Preprint · 2025
Iris: An immersive robot interaction system

Iris: An immersive robot interaction system

Xinkai Jiang, Qihao Yuan, Enes Ulas Dincer, Hongyi Zhou, Ge Li, Xueyin Li, Julius Haag, Nicolas Schreiber, Kailai Li, Gerhard Neumann, others
Preprint · 2025
Beyond Task Performance: Human Experience in Human-Robot Collaboration

Beyond Task Performance: Human Experience in Human-Robot Collaboration

Sean Kille, Jan Heinrich Robens, Philipp Dahlinger, Alejandra Rodriguez-Velasquez, Simon Rothfuß, Balint Varga, Andreas Lindenmann, Gerhard Neumann, Sven Matthiesen, Andrea Kiesel, others
Preprint · 2025
Learning Boltzmann Generators via Constrained Mass Transport

Learning Boltzmann Generators via Constrained Mass Transport

Christopher von Klitzing, Denis Blessing, Henrik Schopmans, Pascal Friederich, Gerhard Neumann
Preprint · 2025
Enhancing Exploration With Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation

Enhancing Exploration With Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation

Huy Le, Tai Hoang, Miroslav Gabriel, Gerhard Neumann, Ngo Anh Vien
IEEE Robotics and Automation Letters · 2025
Beyond Visuals: Investigating Force Feedback in Extended Reality for Robot Data Collection

Beyond Visuals: Investigating Force Feedback in Extended Reality for Robot Data Collection

Xueyin Li, Xinkai Jiang, Philipp Dahlinger, Gerhard Neumann, Rudolf Lioutikov
Preprint · 2025
Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation

Vlearn: Off-Policy Learning with Efficient State-Value Function Estimation

Fabian Otto, Philipp Becker, Vien Anh Ngo, Gerhard Neumann
ICLR · 2025
Identifying individual cost-balancing strategies when self-organizing task switching.

Identifying individual cost-balancing strategies when self-organizing task switching.

Irina Monno, Philipp Dahlinger, Jeff Miller, Gerhard Neumann, Andrea Kiesel
Journal of Experimental Psychology: Human Perception and Performance · 2025
Chunking the critic: A transformer-based soft actor-critic with N-step returns

Chunking the critic: A transformer-based soft actor-critic with N-step returns

Dong Tian, Ge Li, Hongyi Zhou, Onur Celik, Gerhard Neumann
Preprint · 2025
Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Tobias Würth, Niklas Freymuth, Gerhard Neumann, Luise Kärger
NeurIPS · 2025 Spotlight
PDF
Towards safe and efficient learning in the wild: guiding RL with constrained uncertainty-aware movement primitives

Towards safe and efficient learning in the wild: guiding RL with constrained uncertainty-aware movement primitives

Abhishek Padalkar, Freek Stulp, Gerhard Neumann, João Silvério
IEEE Robotics and Automation Letters · 2025

2024

Kalmamba: Towards efficient probabilistic state space models for rl under uncertainty

Kalmamba: Towards efficient probabilistic state space models for rl under uncertainty

Philipp Becker, Niklas Freymuth, Gerhard Neumann
Preprint · 2024
Neural Contractive Dynamical Systems

Neural Contractive Dynamical Systems

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Nadia Figueroa, Gerhard Neumann, Leonel Rozo
ICLR · 2024
Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling

Denis Blessing, Xiaogang Jia, Johannes Esslinger, Francisco Vargas, Gerhard Neumann
ICML · 2024
Beyond Shortest-Paths: A Benchmark for Reinforcement Learning on Traffic Engineering

Beyond Shortest-Paths: A Benchmark for Reinforcement Learning on Traffic Engineering

Andreas Boltres, Niklas Freymuth, Patrick Jahnke, Gerhard Neumann
· 2024
Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics

Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics

Andreas Boltres, Niklas Freymuth, Patrick Jahnke, Holger Karl, Gerhard Neumann
Preprint · 2024
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Onur Celik, Aleksandar Taranovic, Gerhard Neumann
ICML · 2024
Sequential controlled langevin diffusions

Sequential controlled langevin diffusions

Junhua Chen, Lorenz Richter, Julius Berner, Denis Blessing, Gerhard Neumann, Anima Anandkumar
Preprint · 2024
Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations

Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations

Niklas Freymuth, Philipp Dahlinger, Tobias Würth, Philipp Becker, Aleksandar Taranovic, Onno Grönheim, Luise Kärger, Gerhard Neumann
Preprint · 2024
Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker, Stefan Geyer, Gerhard Neumann
Preprint · 2024
PointPatchRL--Masked Reconstruction Improves Reinforcement Learning on Point Clouds

PointPatchRL--Masked Reconstruction Improves Reinforcement Learning on Point Clouds

Balázs Gyenes, Nikolai Franke, Philipp Becker, Gerhard Neumann
CORL · 2024
Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud

Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud

Pit Henrich, Balázs Gyenes, Paul Maria Scheikl, Gerhard Neumann, Franziska Mathis-Ullrich
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision · 2024
Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning

Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning

Maximilian Hüttenrauch, Gerhard Neumann
JMLR · 2024
MaIL: Improving Imitation Learning with Mamba

MaIL: Improving Imitation Learning with Mamba

Xiaogang Jia, Qian Wang, Atalay Donat, Bowen Xing, Ge Li, Hongyi Zhou, Onur Celik, Denis Blessing, Rudolf Lioutikov, Gerhard Neumann
CORL · 2024
The role of an ontology-based knowledge backbone in a circular factory

The role of an ontology-based knowledge backbone in a circular factory

Constantin Hofmann, Steffen Staab, Michael Selzer, Gerhard Neumann, Kai Furmans, Michael Heizmann, Jürgen Beyerer, Gisela Lanza, Julius Pfrommer, Tobias Düser, others
at-Automatisierungstechnik · 2024
A Comprehensive User Study on Augmented Reality-Based Data Collection Interfaces for Robot Learning

A Comprehensive User Study on Augmented Reality-Based Data Collection Interfaces for Robot Learning

Xinkai Jiang, Paul Mattes, Xiaogang Jia, Nicolas Schreiber, Gerhard Neumann, Rudolf Lioutikov
Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction · 2024
MuTT: A Multimodal Trajectory Transformer for Robot Skills

MuTT: A Multimodal Trajectory Transformer for Robot Skills

Claudius Kienle, Benjamin Alt, Onur Celik, Philipp Becker, Darko Katic, Rainer Jäkel, Gerhard Neumann
IROS · 2024
Multi Time Scale World Models

Multi Time Scale World Models

Vaisakh Shaj Kumar, SALEH Gholam Zadeh, Ozan Demir, Luiz Douat, Gerhard Neumann
NeurIPS · 2024
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

Ge Li, Hongyi Zhou, Dominik Roth, Serge Thilges, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann
ICLR · 2024
Top-erl: Transformer-based off-policy episodic reinforcement learning

Top-erl: Transformer-based off-policy episodic reinforcement learning

Ge Li, Dong Tian, Hongyi Zhou, Xinkai Jiang, Rudolf Lioutikov, Gerhard Neumann
Preprint · 2024
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

Puze Liu, Jonas Günster, Niklas Funk, Simon Gröger, Dong Chen, Haitham Bou-Ammar, Julius Jankowski, Ante Marić, Sylvain Calinon, Andrej Orsula, others
NeurIPS · 2024
Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions

Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions

Hadi Beik Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo
Preprint · 2024
Efficient Off-Policy Learning for High-Dimensional Action Spaces

Efficient Off-Policy Learning for High-Dimensional Action Spaces

Fabian Otto, Philipp Becker, Ngo Anh Vien, Gerhard Neumann
Preprint · 2024
Lens Capsule Tearing in Cataract Surgery using Reinforcement Learning

Lens Capsule Tearing in Cataract Surgery using Reinforcement Learning

Rebekka Charlotte Peter, Steffen Peikert, Ludwig Haide, Doan Xuan Viet Pham, Tahar Chettaoui, Eleonora Tagliabue, Paul Maria Scheikl, Johannes Fauser, Matthias Hillenbrand, Gerhard Neumann, others
ICRA · 2024
Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes

Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes

Tobias Würth, Niklas Freymuth, Clemens Zimmerling, Gerhard Neumann, Luise Kärger
Preprint · 2024
Variational distillation of diffusion policies into mixture of experts

Variational distillation of diffusion policies into mixture of experts

Hongyi Zhou, Denis Blessing, Ge Li, Onur Celik, Xiaogang Jia, Gerhard Neumann, Rudolf Lioutikov
NeurIPS · 2024

2023

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

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

Oleg Arenz, Philipp Dahlinger, Zihan Ye, Michael Volpp, Gerhard Neumann
TMLR · 2023
Air Hockey Challenge 2023: Air-HocKIT Team Report

Air Hockey Challenge 2023: Air-HocKIT Team Report

Vincent de Bakker, Mustafa Enes Batur, Atalay Donat Yagmurlu, Marcus Fiedler, Zeqi Jin, Dongxu Yang, Hongyi Zhou, Xiaogang Jia, Onur Celik, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann
· 2023
Reinforcement Learning from Multiple Sensors via Joint Representations

Reinforcement Learning from Multiple Sensors via Joint Representations

Philipp Becker, Sebastian Markgraf, Fabian Otto, Gerhard Neumann
Reinforcement Learning Conference (RLC) · 2023
Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills

Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills

Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Xiling Li, Rudolf Lioutikov, Gerhard Neumann
NeurIPS · 2023
Reinforcement Learning of Diverse Skills using Mixture of Deep Experts

Reinforcement Learning of Diverse Skills using Mixture of Deep Experts

Onur Celik, Aleksandar Taranovic, Gerhard Neumann
Intrinsically-Motivated and Open-Ended Learning Workshop @NeurIPS2023 · 2023
PDF
Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization

Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization

Philipp Dahlinger, Philipp Becker, Maximilian Hüttenrauch, Gerhard Neumann
Preprint · 2023
SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation

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

Fabian Duffhauss, Sebastian Koch, Hanna Ziesche, Ngo Anh Vien, Gerhard Neumann
IEEE Robotics and Automation Letters · 2023
Swarm Reinforcement Learning for Adaptive Mesh Refinement

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Niklas Freymuth, Philipp Dahlinger, Tobias Daniel Würth, Simon Reisch, Luise Kärger, Gerhard Neumann
NeurIPS · 2023
PDF
Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

Xiaogang Jia, Denis Blessing, Xinkai Jiang, Moritz Reuss, Atalay Donat, Rudolf Lioutikov, Gerhard Neumann
ICLR · 2023
SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects

SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects

Ning Gao, Vien Anh Ngo, Hanna Ziesche, Gerhard Neumann
CORL · 2023
Enhancing Interpretable Object Abstraction via Clustering-based Slot Initialization

Enhancing Interpretable Object Abstraction via Clustering-based Slot Initialization

Ning Gao, Bernard Hohmann, Gerhard Neumann
BMVC · 2023
A User Study on Augmented Reality-Based Robot Learning Data Collection Interfaces

A User Study on Augmented Reality-Based Robot Learning Data Collection Interfaces

Xinkai Jiang, Paul Mattes, Xiaogang Jia, Gerhard Neumann, Rudolf Lioutikov
Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@ CoRL2023 · 2023
Curriculum-Based Imitation of Versatile Skills

Curriculum-Based Imitation of Versatile Skills

Maximilian Xiling Li, Onur Celik, Philipp Becker, Denis Blessing, Rudolf Lioutikov, Gerhard Neumann
ICRA · 2023
Grounding Graph Network Simulators using Physical Sensor Observations

Grounding Graph Network Simulators using Physical Sensor Observations

Jonas Linkerhägner, Niklas Freymuth, Paul Maria Scheikl, Franziska Mathis-Ullrich, Gerhard Neumann
ICLR · 2023
Neural Contractive Dynamical Systems

Neural Contractive Dynamical Systems

Hadi Beik Mohammadi, Søren Hauberg, Georgios Arvanitidis, Nadia Figueroa, Gerhard Neumann, Leonel Rozo
ICLR · 2023
MP3: Movement Primitive-Based (Re-) Planning Policy

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

Fabian Otto, Hongyi Zhou, Onur Celik, Ge Li, Rudolf Lioutikov, Gerhard Neumann
Preprint · 2023
LapGym--An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery

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

Paul Maria Scheikl, Balázs Gyenes, Rayan Younis, Christoph Haas, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich
Preprint · 2023
Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects

Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects

Paul Maria Scheikl, Nicolas Schreiber, Christoph Haas, Niklas Freymuth, Gerhard Neumann, Rudolf Lioutikov, Franziska Mathis-Ullrich
Robotics Automation Letters (RAL) · 2023
Beyond Deep Ensembles--A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

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

Florian Seligmann, Philipp Becker, Michael Volpp, Gerhard Neumann
NeurIPS · 2023
Adversarial Imitation Learning with Preferences

Adversarial Imitation Learning with Preferences

Aleksandar Taranovic, Andras Gabor Kupcsik, Niklas Freymuth, Gerhard Neumann
ICLR · 2023
Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference

Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference

Michael Volpp, Philipp Dahlinger, Philipp Becker, Christian Daniel, Gerhard Neumann
ICLR · 2023

2022

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

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

Philipp Becker, Gerhard Neumann
TMLR · 2022
Reactive Motion Generation on Learned Riemannian Manifolds

Reactive Motion Generation on Learned Riemannian Manifolds

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo
Preprint · 2022
Specializing Versatile Skill Libraries using Local Mixture of Experts

Specializing Versatile Skill Libraries using Local Mixture of Experts

Onur Celik, Dongzhuoran Zhou, Ge Li, Philipp Becker, Gerhard Neumann
CORL · 2022
Meta-Learning Regrasping Strategies for Physical-Agnostic Objects

Meta-Learning Regrasping Strategies for Physical-Agnostic Objects

Ruijie Chen, Ning Gao, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann
Preprint · 2022
FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

Fabian Duffhauss, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann
ECCV · 2022
MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network

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

Fabian Duffhauss, Tobias Demmler, Gerhard Neumann
IROS · 2022
Learning Inductive Object-Centric Slot Initialization via Clustering

Learning Inductive Object-Centric Slot Initialization via Clustering

Ning Gao, Bernard Hohmann, Gerhard Neumann
· 2022
Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Niklas Freymuth, Nicolas Schreiber, Philipp Becker, Aleksander Taranovic, Gerhard Neumann
CORL · 2022
What Matters For Meta-Learning Vision Regression Tasks?

What Matters For Meta-Learning Vision Regression Tasks?

Ning Gao, Hanna Ziesche, Ngo Anh Vien, Michael Volpp, Gerhard Neumann
CVPR · 2022
Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control

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

Maximilian Hüttenrauch, Gerhard Neumann
Preprint · 2022
Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Vaisakh Shaj Kumar, D Büchler, R Sonker, Philipp Becker, Gerhard Neumann
ICLR · 2022
Category-Agnostic 6D Pose Estimation with Conditional Neural Processes

Category-Agnostic 6D Pose Estimation with Conditional Neural Processes

Yumeng Li, Ning Gao, Hanna Ziesche, Gerhard Neumann
Preprint · 2022
ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives

ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitives

Ge Li, Zeqi Jin, Michael Volpp, Fabian Otto, Rudolf Lioutikov, Gerhard Neumann
IEEE Robotics and Automation Letters · 2022
Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination

Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination

Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayáhuitl
IROS · 2022
Deep Black-Box Reinforcement Learning with Movement Primitives

Deep Black-Box Reinforcement Learning with Movement Primitives

Fabian Otto, Onur Celik, Hongyi Zhou, Hanna Ziesche, Ngo Anh Vien, Gerhard Neumann
CORL · 2022
End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

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

Moritz Reuss, Niels van Duijkeren, Robert Krug, Philipp Becker, Vaisakh Shaj, Gerhard Neumann
Robotics: Science and Systems · 2022
Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning

Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning

BARIS SERHAN, HARIT PANDYA, AYSE KUCUKYILMAZ, GERHARD NEUMANN
ICRA · 2022
Hierarchical Policy Learning for Mechanical Search

Hierarchical Policy Learning for Mechanical Search

Oussama Zenkri, Ngo Anh Vien, Gerhard Neumann
ICRA · 2022

2021

Learning Riemannian Manifolds for Geodesic Motion Skills

Learning Riemannian Manifolds for Geodesic Motion Skills

Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo
Preprint · 2021
Coordinate ascent MORE with adaptive entropy control for population-based regret minimization

Coordinate ascent MORE with adaptive entropy control for population-based regret minimization

Maximilian Hüttenrauch, Gerhard Neumann
Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2021
Versatile Inverse Reinforcement Learning via Cumulative Rewards

Versatile Inverse Reinforcement Learning via Cumulative Rewards

Niklas Freymuth, Philipp Becker, Gerhard Neumann
Preprint · 2021
Human-machine Symbiosis: A Multivariate Perspective for Physically Coupled Human-machine Systems

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

Jairo Inga, Miriam Ruess, Jan Heinrich Robens, Thomas Nelius, Sean Kille, Philipp Dahlinger, Roland Thomaschke, Gerhard Neumann, Sven Matthiesen, Sören Hohmann, others
Preprint · 2021
Intent-Aware Predictive Haptic Guidance and its Application to Shared Control Teleoperation

Intent-Aware Predictive Haptic Guidance and its Application to Shared Control Teleoperation

Kim Tien Ly, Mithun Poozhiyil, Harit Pandya, Gerhard Neumann, Ayse Kucukyilmaz
IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) · 2021
A study on dense and sparse (visual) rewards in robot policy learning

A study on dense and sparse (visual) rewards in robot policy learning

Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayáhuitl
Annual Conference Towards Autonomous Robotic Systems · 2021
Differentiable Trust Region Layers for Deep Reinforcement Learning

Differentiable Trust Region Layers for Deep Reinforcement Learning

Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche, Gerhard Neumann
ICLR · 2021
Deep Reinforcement Learning for Attacking Wireless Sensor Networks

Deep Reinforcement Learning for Attacking Wireless Sensor Networks

Juan Parras, Maximilian Hüttenrauch, Santiago Zazo, Gerhard Neumann
Sensors · 2021
Switching Recurrent Kalman Networks

Switching Recurrent Kalman Networks

Giao Nguyen-Quynh, Philipp Becker, Chen Qiu, Maja Rudolph, Gerhard Neumann
Preprint · 2021
Navigate-and-Seek: a Robotics Framework for People Localization in Agricultural Environments

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

Riccardo Polvara, Francesco Del Duchetto, Gerhard Neumann, Marc Hanheide
IEEE Robotics and Automation Letters · 2021
Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

Alireza Ranjbar, Ngo Anh Vien, Hanna Ziesche, Joschka Boedecker, Gerhard Neumann
Preprint · 2021
Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning

Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning

Paul Maria Scheikl, Balázs Gyenes, Tornike Davitashvili, Rayan Younis, André Schulze, Beat P Müller-Stich, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich
IROS · 2021
Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Vaisakh Shaj, Dieter Büchler, Rohit Sonker, Philipp Becker, Gerhard Neumann
ICLR · 2021
Autonomous Robots for Space: Trajectory Learning and Adaptation Using Imitation

Autonomous Robots for Space: Trajectory Learning and Adaptation Using Imitation

Ashith Shyam, Zhou Hao, Umberto Montanaro, Shilp Dixit, Arunkumar Rathinam, Yang Gao, Gerhard Neumann, Saber Fallah
Frontiers in Robotics and AI · 2021
Differentiable Robust LQR Layers

Differentiable Robust LQR Layers

Ngo Anh Vien, Gerhard Neumann
Preprint · 2021
Bayesian Context Aggregation for Neural Processes

Bayesian Context Aggregation for Neural Processes

Michael Volpp, Fabian Flürenbrock, Lukas Grossberger, Christian Daniel, Gerhard Neumann
ICLR · 2021

2020

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

Non-Adversarial Imitation Learning and its Connections to Adversarial Methods

Oleg Arenz, Gerhard Neumann
Preprint · 2020
Trust-Region Variational Inference with Gaussian Mixture Models.

Trust-Region Variational Inference with Gaussian Mixture Models.

Oleg Arenz, Mingjun Zhong, Gerhard Neumann
J. Mach. Learn. Res. · 2020
Expected information maximization: Using the i-projection for mixture density estimation

Expected information maximization: Using the i-projection for mixture density estimation

Philipp Becker, Oleg Arenz, Gerhard Neumann
ICLR · 2020
Haptic-guided shared control grasping: collision-free manipulation

Haptic-guided shared control grasping: collision-free manipulation

Soran Parsa, Disha Kamale, Sariah Mghames, Kiyanoush Nazari, Tommaso Pardi, Aravinda Srinivasan, Gerhard Neumann, Marc Hanheide, Amir Ghalamzan Esfahani, others
International Conference on Automation Science and Engineering (CASE) · 2020
Next-Best-Sense: a multi-criteria robotic exploration strategy for RFID tags discovery

Next-Best-Sense: a multi-criteria robotic exploration strategy for RFID tags discovery

Riccardo Polvara, Manuel Fernandez-Carmona, Gerhard Neumann, Marc Hanheide
IEEE Robotics and Automation Letters · 2020
Sim-to-Real quadrotor landing via sequential deep Q-Networks and domain randomization

Sim-to-Real quadrotor landing via sequential deep Q-Networks and domain randomization

Riccardo Polvara, Massimiliano Patacchiola, Marc Hanheide, Gerhard Neumann
Robotics · 2020
Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning

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

Vaisakh Shaj, Philipp Becker, Dieter Buchler, Harit Pandya, Niels van Duijkeren, C James Taylor, Marc Hanheide, Gerhard Neumann
CORL · 2020
Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space

Imitation Learning for Autonomous Trajectory Learning of Robot Arms in Space

RB Shyam, Zhou Hao, Umberto Montanaro, Gerhard Neumann
Preprint · 2020
Haptic-Guided Teleoperation of a 7-DoF Collaborative Robot Arm with an Identical Twin Master

Haptic-Guided Teleoperation of a 7-DoF Collaborative Robot Arm with an Identical Twin Master

Jayant Singh, Aravinda Ramakrishnan Srinivasan, Gerhard Neumann, Ayse Kucukyilmaz
IEEE Transactions on Haptics · 2020
Enhancing Grasp Pose Computation in Gripper Workspace Spheres

Enhancing Grasp Pose Computation in Gripper Workspace Spheres

Mohamed Sorour, Khaled Elgeneidy, Marc Hanheide, M Abdalmjed, A Srinivasan, G Neumann
· 2020

2019

A haptic shared-control architecture for guided multi-target robotic grasping

A haptic shared-control architecture for guided multi-target robotic grasping

Firas Abi-Farraj, Claudio Pacchierotti, Oleg Arenz, Gerhard Neumann, Paolo Robuffo Giordano
IEEE transactions on haptics · 2019
Projections for approximate policy iteration algorithms

Projections for approximate policy iteration algorithms

Riad Akrour, Joni Pajarinen, Jan Peters, Gerhard Neumann
ICML · 2019
Learning Replanning Policies With Direct Policy Search

Learning Replanning Policies With Direct Policy Search

Florian Brandherm, Jan Peters, Gerhard Neumann, Riad Akrour
IEEE Robotics and Automation Letters · 2019
Characterising 3D-printed Soft Fin Ray Robotic Fingers with Layer Jamming Capability for Delicate Grasping

Characterising 3D-printed Soft Fin Ray Robotic Fingers with Layer Jamming Capability for Delicate Grasping

Khaled Elgeneidy, Peter Lightbody, Simon Pearson, Gerhard Neumann
IEEE International Conference on Soft Robotics (RoboSoft) · 2019
Deep Reinforcement Learning for Swarm Systems

Deep Reinforcement Learning for Swarm Systems

Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann
JMLR · 2019
The kernel Kalman rule

The kernel Kalman rule

Gregor HW Gebhardt, Andras Kupcsik, Gerhard Neumann
Machine Learning · 2019
A systematic review of Underactuated robotic systems

A systematic review of Underactuated robotic systems

Pengcheng Liu, Khaled Elgeneidy, M Nazmul Huda, Gerhard Neumann, Li Sun, Hongnian Yu
· 2019
Grasping unknown objects based on gripper workspace spheres

Grasping unknown objects based on gripper workspace spheres

Mohamed Sorour, Khaled Elgeneidy, Aravinda Srinivasan, Marc Hanheide, Gerhard Neumann
IROS · 2019
Improving Local Trajectory Optimisation using Probabilistic Movement Primitives

Improving Local Trajectory Optimisation using Probabilistic Movement Primitives

RB Shyam, Peter Lightbody, Gautham Das, Pengcheng Liu, Sebastian Gomez-Gonzalez, Gerhard Neumann
IEEE/RSJ IROS · 2019
Compatible natural gradient policy search

Compatible natural gradient policy search

Joni Pajarinen, Hong Linh Thai, Riad Akrour, Jan Peters, Gerhard Neumann
Machine Learning · 2019
Learning Kalman Network: A deep monocular visual odometry for on-road driving

Learning Kalman Network: A deep monocular visual odometry for on-road driving

Cheng Zhao, Li Sun, Zhi Yan, Gerhard Neumann, Tom Duckett, Rustam Stolkin
Robotics and Autonomous Systems · 2019

2018

Model-Free Trajectory-based Policy Optimization with Monotonic Improvement

Model-Free Trajectory-based Policy Optimization with Monotonic Improvement

Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann, others
JMLR · 2018
Efficient Gradient-Free Variational Inference using Policy Search

Efficient Gradient-Free Variational Inference using Policy Search

Oleg Arenz, Mingjun Zhong, Gerhard Neumann
ICML · 2018
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces

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

Philipp Becker, Harit Pandya, Gregor HW Gebhardt, Cheng Zhao, Gerhard Neumann
ICML · 2018
Agricultural robotics: the future of robotic agriculture

Agricultural robotics: the future of robotic agriculture

Tom Duckett, Simon Pearson, Simon Blackmore, Bruce Grieve, Wen-Hua Chen, Grzegorz Cielniak, Jason Cleaversmith, Jian Dai, Steve Davis, Charles Fox, others
Preprint · 2018
Contact Detection and Object Size Estimation using a Modular Soft Gripper with Embedded Flex Sensors

Contact Detection and Object Size Estimation using a Modular Soft Gripper with Embedded Flex Sensors

Khaled Elgeneidy, Gerhard Neumann, Simon Pearson, Michael Jackson, Niels Lohse, others
IROS · 2018
Contact Detection and Size Estimation Using a Modular Soft Gripper with Embedded Flex Sensors

Contact Detection and Size Estimation Using a Modular Soft Gripper with Embedded Flex Sensors

Khaled Elgeneidy, Gerhard Neumann, Simon Pearson, Michael Jackson, Niels Lohse
IROS · 2018
Directly printable flexible strain sensors for bending and contact feedback of soft actuators

Directly printable flexible strain sensors for bending and contact feedback of soft actuators

Khaled Elgeneidy, Gerhard Neumann, Michael R Jackson, Niels Lohse
Frontiers in Robotics and AI · 2018
Printable Soft Grippers with Integrated Bend Sensing for Handling of Crops

Printable Soft Grippers with Integrated Bend Sensing for Handling of Crops

Khaled Elgeneidy, Pengcheng Liu, Simon Pearson, Niels Lohse, Gerhard Neumann, others
Towards Autonomous Robotic Systems (TAROS) Conference · 2018
Layered Direct Policy Search for Learning Hierarchical Skills

Layered Direct Policy Search for Learning Hierarchical Skills

Felix End, Riad Akrour, Jan Peters, Gerhard Neumann
ICRA · 2018
Robust learning of object assembly tasks with an invariant representation of robot swarms

Robust learning of object assembly tasks with an invariant representation of robot swarms

Gregor HW Gebhardt, Kevin Daun, Marius Schnaubelt, Gerhard Neumann, others
· 2018
Adaptation and Robust Learning of Probabilistic Movement Primitives

Adaptation and Robust Learning of Probabilistic Movement Primitives

Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf, Jan Peters
Preprint · 2018
Exploiting Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

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

Max Huttenrauch, Adrian Sosic, Gerhard Neumann, others
Springer International Publishing · 2018
Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning

Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann
International Conference on Swarm Intelligence · 2018
Towards Fine Grained Network Flow Prediction

Towards Fine Grained Network Flow Prediction

Patrick Jahnke, Emmanuel Stapf, Jonas Mieseler, Gerhard Neumann, Patrick Eugster
Preprint · 2018
Energy-efficient design and control of a vibro-driven robot

Energy-efficient design and control of a vibro-driven robot

Pengcheng Liu, Gerhard Neumann, Qinbing Fu, Simon Pearson, Hongnian Yu, others
IEEE · 2018
Towards real-time robotic motion planning for grasping in cluttered and uncertain environments

Towards real-time robotic motion planning for grasping in cluttered and uncertain environments

Pengcheng Liu, Khaled Elgeneidy, Simon Pearson, Nazmul Huda, Gerhard Neumann, others
Springer · 2018
An Algorithmic Perspective on Imitation Learning

An Algorithmic Perspective on Imitation Learning

Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J Andrew Bagnell, Pieter Abbeel, Jan Peters, others
Foundations and Trends® in Robotics · 2018
Hierarchical Reinforcement Learning of Multiple Grasping Strategies with Human Instructions

Hierarchical Reinforcement Learning of Multiple Grasping Strategies with Human Instructions

T Osa, J Peters, Gerhard Neumann, others
Advanced Robotics · 2018
Probabilistic movement primitives under unknown system dynamics

Probabilistic movement primitives under unknown system dynamics

Alexandros Paraschos, Elmar Rueckert, Jan Peters, Gerhard Neumann
Advanced Robotics · 2018
Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences

Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences

Robert Pinsler, Riad Akrour, Takayuki Osa, Jan Peters, Gerhard Neumann
ICRA · 2018

2017

Contextual CMA-ES

Contextual CMA-ES

Abbas Abdolmaleki, Bob Price, Nuno Lau, P Reis, Gerhard Neumann
International Joint Conferences on Artificial Intelligence (IJCAI) · 2017
Contextual covariance matrix adaptation evolutionary strategies

Contextual covariance matrix adaptation evolutionary strategies

Abbas Abdolmaleki, Bob Price, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
Proceedings of the 26th International Joint Conference on Artificial Intelligence · 2017
Deriving and improving CMA-ES with Information geometric trust regions

Deriving and improving CMA-ES with Information geometric trust regions

Abbas Abdolmaleki, Bob Price, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
The Genetic and Evolutionary Computation Conference (Gecco) · 2017
Stochastic Search In Changing Situations

Stochastic Search In Changing Situations

Abbas Abdolmaleki, David Simoes, Nuno Lau, Luis Paulo Reis, Bob Price, Gerhard Neumann
· 2017
State-regularized policy search for linearized dynamical systems

State-regularized policy search for linearized dynamical systems

Hany Abdulsamad, Oleg Arenz, Jan Peters, Gerhard Neumann
International Conference on Automated Planning and Scheduling (ICAPS) · 2017
Local Bayesian Optimization of Motor Skills

Local Bayesian Optimization of Motor Skills

Riad Akrour, Dmitry Sorokin, Jan Peters, Gerhard Neumann
ICML · 2017
A Learning-based Shared Control Architecture for Interactive Task Execution

A Learning-based Shared Control Architecture for Interactive Task Execution

Firas Abi-Farraj, Takayuki Osa, Nicoló Pedemonte, Jan Peters, Gerhard Neumann, Paolo Giordano Robuffo
IEEE Int. Conf. on Robotics and Automation, ICRA'17 · 2017
Learning to Assemble Objects with a Robot Swarm

Learning to Assemble Objects with a Robot Swarm

Gregor HW Gebhardt, Kevin Daun, Marius Schnaubelt, Alexander Hendrich, Daniel Kauth, Gerhard Neumann
Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems · 2017
The Kernel Kalman Rule--Efficient Nonparametric Inference with Recursive Least Squares

The Kernel Kalman Rule--Efficient Nonparametric Inference with Recursive Least Squares

Gregor HW Gebhardt, Andras Kupcsik, Gerhard Neumann
AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE · 2017
Non-parametric policy search with limited information loss

Non-parametric policy search with limited information loss

Herke van Hoof, Gerhard Neumann, Jan Peters, others
JMLR · 2017
Guided Deep Reinforcement Learning for Swarm Systems

Guided Deep Reinforcement Learning for Swarm Systems

Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann
Preprint · 2017
Learning Complex Swarm Behaviors by Exploiting Local Communication Protocols with Deep Reinforcement Learning

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

Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann
Preprint · 2017
Learning movement primitive libraries through probabilistic segmentation

Learning movement primitive libraries through probabilistic segmentation

Rudolf Lioutikov, Gerhard Neumann, Guilherme Maeda, Jan Peters
The International Journal of Robotics Research · 2017
Phase estimation for fast action recognition and trajectory generation in human--robot collaboration

Phase estimation for fast action recognition and trajectory generation in human--robot collaboration

Guilherme Maeda, Marco Ewerton, Gerhard Neumann, Rudolf Lioutikov, Jan Peters
The International Journal of Robotics Research · 2017
Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies

Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies

Takayuki Osa, Jan Peters, Gerhard Neumann
Advanced Robotics · 2017
Guiding Trajectory Optimization by Demonstrated Distributions

Guiding Trajectory Optimization by Demonstrated Distributions

Takayuki Osa, Amir M Ghalamzan Esfahani, Rustam Stolkin, Rudolf Lioutikov, Jan Peters, Gerhard Neumann
IEEE Robotics and Automation Letters · 2017
Hybrid control trajectory optimization under uncertainty

Hybrid control trajectory optimization under uncertainty

Joni Pajarinen, Ville Kyrki, Michael Koval, Siddhartha Srinivasa, Jan Peters, Gerhard Neumann
Preprint · 2017
Probabilistic prioritization of movement primitives

Probabilistic prioritization of movement primitives

Alexandros Paraschos, Rudolf Lioutikov, Jan Peters, Gerhard Neumann, others
IEEE Robotics and Automation Letters · 2017
Using probabilistic movement primitives in robotics

Using probabilistic movement primitives in robotics

Alexandros Paraschos, Christian Daniel, Jan Peters, Gerhard Neumann
Autonomous Robots · 2017
A survey of preference-based reinforcement learning methods

A survey of preference-based reinforcement learning methods

Christian Wirth, Riad Akrour, Gerhard Neumann, Johannes Fürnkranz
JMLR · 2017

2016

Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller

Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller

Abbas Abdolmaleki, Nuno Lau, Luis Paulo Reis, Jan Peters, Gerhard Neumann
Journal of Intelligent & Robotic Systems · 2016
Contextual Relative Entropy Policy Search with Covariance Matrix Adaptation

Contextual Relative Entropy Policy Search with Covariance Matrix Adaptation

Abbas Abdolmaleki, David Simões, Nuno Lau, Luís Paulo Reis, Gerhard Neumann
Autonomous Robot Systems and Competitions (ICARSC), 2016 International Conference on · 2016
Contextual Stochastic Search

Contextual Stochastic Search

Abbas Abdolmaleki, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion · 2016
Learning a Humanoid Kick With Controlled Distance

Learning a Humanoid Kick With Controlled Distance

Abbas Abdolmaleki, David Simoes, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
To appear · 2016
Non-Parametric Contextual Stochastic Search

Non-Parametric Contextual Stochastic Search

Abbas Abdolmaleki, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on · 2016
Model-Free Trajectory Optimization for Reinforcement Learning

Model-Free Trajectory Optimization for Reinforcement Learning

Riad Akrour, Gerhard Neumann, Hany Abdulsamad, Abbas Abdolmaleki
ICML · 2016
Monotonically Improving Model-Free Trajectory Optimization

Monotonically Improving Model-Free Trajectory Optimization

Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann
Preprint · 2016
Optimal control and inverse optimal control by distribution matching

Optimal control and inverse optimal control by distribution matching

Oleg Arenz, Hany Abdulsamad, Gerhard Neumann
Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on · 2016
Catching heuristics are optimal control policies

Catching heuristics are optimal control policies

Boris Belousov, Gerhard Neumann, Constantin A Rothkopf, Jan R Peters
NeurIPS · 2016
Hierarchical relative entropy policy search

Hierarchical relative entropy policy search

Christian Daniel, Gerhard Neumann, Oliver Kroemer, Jan Peters
JMLR · 2016
Probabilistic Inference for Determining Options in Reinforcement Learning

Probabilistic Inference for Determining Options in Reinforcement Learning

Christian Daniel, Herke van Hoof, Jan Peters, Gerhard Neumann
Machine Learning Journal · 2016
Using probabilistic movement primitives for striking movements

Using probabilistic movement primitives for striking movements

Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf, Jan Peters
Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on · 2016
Probabilistic movement primitives for coordination of multiple human--robot collaborative tasks

Probabilistic movement primitives for coordination of multiple human--robot collaborative tasks

Guilherme J Maeda, Gerhard Neumann, Marco Ewerton, Rudolf Lioutikov, Oliver Kroemer, Jan Peters
Autonomous Robots · 2016
Learning soft task priorities for control of redundant robots

Learning soft task priorities for control of redundant robots

Valerio Modugno, Gerard Neumann, Elmar Rueckert, Giuseppe Oriolo, Jan Peters, Serena Ivaldi
ICRA · 2016
Demonstration based trajectory optimization for generalizable robot motions

Demonstration based trajectory optimization for generalizable robot motions

Dorothea Koert, Guilherme Maeda, Rudolf Lioutikov, Gerhard Neumann, Jan Peters
Humanoid Robots (Humanoids), 2016 IEEE-RAS 16th International Conference on · 2016
Policy Search with High-Dimensional Context Variables

Policy Search with High-Dimensional Context Variables

Voot Tangkaratt, Herke van Hoof, Simone Parisi, Gerhard Neumann, Jan Peters, Masashi Sugiyama
Preprint · 2016
Model-Free Preference-Based Reinforcement Learning

Model-Free Preference-Based Reinforcement Learning

Christian Wirth, Johannes Fürnkranz, Gerhard Neumann
Thirtieth AAAI Conference on Artificial Intelligence · 2016

2015

Contextual Policy Search for Generalizing a Parameterized Biped Walking Controller

Contextual Policy Search for Generalizing a Parameterized Biped Walking Controller

Abbas Abdolmaleki, Nuno Lau, Luis Paulo Reis, Jan Peters, Gerhard Neumann
Autonomous Robot Systems and Competitions (ICARSC), 2015 IEEE International Conference on · 2015
Model-Based Relative Entropy Stochastic Search

Model-Based Relative Entropy Stochastic Search

Abbas Abdolmaleki, Rudolf Lioutikov, Jan R Peters, Nuno Lau, Luis Pualo Reis, Gerhard Neumann
NeurIPS · 2015
Regularized covariance estimation for weighted maximum likelihood policy search methods

Regularized covariance estimation for weighted maximum likelihood policy search methods

Abbas Abdolmaleki, Nuno Lau, Luis Paulo Reis, Gerhard Neumann
Humanoid Robots (Humanoids), 2015 IEEE-RAS 15th International Conference on · 2015
Learning motor skills from partially observed movements executed at different speeds

Learning motor skills from partially observed movements executed at different speeds

Marco Ewerton, Guilherme Maeda, Jan Peters, Gerhard Neumann
Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on · 2015
Learning Multiple Collaborative Tasks with a Mixture of Interaction Primitives

Learning Multiple Collaborative Tasks with a Mixture of Interaction Primitives

Marco Ewerton, Gerhard Neumann, Rudolf Lioutikov, Heni Ben Amor, Jan Peters, Guilherme Maeda
ICRA · 2015
Learning of Non-Parametric Control Policies with High-Dimensional State Features

Learning of Non-Parametric Control Policies with High-Dimensional State Features

Herke Van Hoof, Jan Peters, Gerhard Neumann
Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics · 2015
Learning robot in-hand manipulation with tactile features

Learning robot in-hand manipulation with tactile features

Herke van Hoof, Tucker Hermans, Gerhard Neumann, Jan Peters
Humanoid Robots (Humanoids), 2015 IEEE-RAS 15th International Conference on · 2015
Optimizing robot striking movement primitives with Iterative Learning Control

Optimizing robot striking movement primitives with Iterative Learning Control

Okan Koc, Guilherme Maeda, Gerhard Neumann, Jan Peters
Humanoid Robots (Humanoids), 2015 IEEE-RAS 15th International Conference on · 2015
Towards learning hierarchical skills for multi-phase manipulation tasks

Towards learning hierarchical skills for multi-phase manipulation tasks

Oliver Kroemer, Christian Daniel, Gerhard Neumann, Herke van Hoof, Jan Peters
Robotics and Automation (ICRA), 2015 IEEE International Conference on · 2015
Probabilistic segmentation applied to an assembly task

Probabilistic segmentation applied to an assembly task

Rudolf Lioutikov, Gerhard Neumann, Guilherme Maeda, Jan Peters
Humanoid Robots (Humanoids), 2015 IEEE-RAS 15th International Conference on · 2015
Lecture Notes: Constraint Optimization

Lecture Notes: Constraint Optimization

Gerhard Neumann
· 2015
Model-free Probabilistic Movement Primitives for physical interaction

Model-free Probabilistic Movement Primitives for physical interaction

Alexandros Paraschos, Elmar Rueckert, Jan Peters, Gerhard Neumann
Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on · 2015
Extracting low-dimensional control variables for movement primitives

Extracting low-dimensional control variables for movement primitives

Elmar Rueckert, Jan Mundo, Alexandros Paraschos, Jan Peters, Gerhard Neumann
Robotics and Automation (ICRA), 2015 IEEE International Conference on · 2015

2014

Omnidirectional Walking with a Compliant Inverted Pendulum Model

Omnidirectional Walking with a Compliant Inverted Pendulum Model

Abbas Abdolmaleki, Nima Shafii, Luis Paulo Reis, Nuno Lau, Jan Peters, Gerhard Neumann
Advances in Artificial Intelligence--IBERAMIA 2014 · 2014
Interaction primitives for human-robot cooperation tasks

Interaction primitives for human-robot cooperation tasks

Heni Ben Amor, Gerhard Neumann, Sanket Kamthe, Oliver Kroemer, Jan Peters
ICRA · 2014
Dimensionality reduction for probabilistic movement primitives

Dimensionality reduction for probabilistic movement primitives

Adrià Colomé, Gerhard Neumann, Jan Peters, Carme Torras
Humanoid Robots (Humanoids), 2014 14th IEEE-RAS International Conference on · 2014
Policy evaluation with temporal differences: A survey and comparison

Policy evaluation with temporal differences: A survey and comparison

Christoph Dann, Gerhard Neumann, Jan Peters
JMLR · 2014
Policy search for path integral control

Policy search for path integral control

Vicenç Gómez, Hilbert J Kappen, Jan Peters, Gerhard Neumann
Machine Learning and Knowledge Discovery in Databases · 2014
Learning to predict phases of manipulation tasks as hidden states

Learning to predict phases of manipulation tasks as hidden states

Oliver Kroemer, Herke Van Hoof, Gerhard Neumann, Jan Peters
ICRA · 2014
Model-based contextual policy search for data-efficient generalization of robot skills

Model-based contextual policy search for data-efficient generalization of robot skills

Andras Kupcsik, Marc Peter Deisenroth, Jan Peters, Ai Poh Loh, Prahlad Vadakkepat, Gerhard Neumann
Artificial Intelligence · 2014
Sample-based informationl-theoretic stochastic optimal control

Sample-based informationl-theoretic stochastic optimal control

Rudolf Lioutikov, Alexandros Paraschos, Jochen Peters, Gerhard Neumann
Robotics and Automation (ICRA), 2014 IEEE International Conference on · 2014
Latent space policy search for robotics

Latent space policy search for robotics

Kevin Sebastian Luck, Gerhard Neumann, Erik Berger, Jochen Peters, Heni Ben Amor
Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on · 2014
Learning interaction for collaborative tasks with probabilistic movement primitives

Learning interaction for collaborative tasks with probabilistic movement primitives

Guilherme Maeda, Marco Ewerton, Rudolf Lioutikov, Heni Ben Amor, Jan Peters, Gerhard Neumann
Humanoid Robots (Humanoids), 2014 14th IEEE-RAS International Conference on · 2014
Generalizing Movements with Information-Theoretic Stochastic Optimal Control

Generalizing Movements with Information-Theoretic Stochastic Optimal Control

Rudolf Lioutikov, Alexandros Paraschos, Jan Peters, Gerhard Neumann
Journal of Aerospace Information Systems · 2014
Learning Modular Policies for Robotics

Learning Modular Policies for Robotics

Gerhard Neumann, Christian Daniel, Alexandros Paraschos, Andras Kupcsik, Jan Peters
Frontiers in Computational Neuroscience · 2014
Robust policy updates for stochastic optimal control

Robust policy updates for stochastic optimal control

Elmar Rueckert, Max Mindt, Jan Peters, Gerhard Neumann
Humanoid Robots (Humanoids), 2014 14th IEEE-RAS International Conference on · 2014

2013

Autonomous reinforcement learning with hierarchical REPS

Autonomous reinforcement learning with hierarchical REPS

Christian Daniel, Gerhard Neumann, Jan Peters
Neural Networks (IJCNN), The 2013 International Joint Conference on · 2013
Learning sequential motor tasks

Learning sequential motor tasks

Christian Daniel, Gerhard Neumann, Oliver Kroemer, Jan Peters
Robotics and Automation (ICRA), 2013 IEEE International Conference on · 2013
A Survey on Policy Search for Robotics.

A Survey on Policy Search for Robotics.

Marc Peter Deisenroth, Gerhard Neumann, Jan Peters
Foundations and Trends in Robotics · 2013
Data-efficient contextual policy search for robot movement skills

Data-efficient contextual policy search for robot movement skills

A Kupcsik, MP Deisenroth, J Peters, G Neumann
Proceedings of the National Conference on Artificial Intelligence (AAAI) · 2013
Data-Efficient Generalization of Robot Skills with Contextual Policy Search.

Data-Efficient Generalization of Robot Skills with Contextual Policy Search.

Andras Gabor Kupcsik, Marc Peter Deisenroth, Jan Peters, Gerhard Neumann
AAAI · 2013
Information-theoretic motor skill learning

Information-theoretic motor skill learning

Gerhard Neumann, Christian Daniel, Andras Kupcsik, Marc Deisenroth, Jan Peters
Proceedings of the AAAI Workshop on Intelligent Robotic Systems · 2013
A probabilistic approach to robot trajectory generation

A probabilistic approach to robot trajectory generation

Alexandros Paraschos, Gerhard Neumann, Jan Peters
Humanoid Robots (Humanoids), 2013 13th IEEE-RAS International Conference on · 2013
Probabilistic movement primitives

Probabilistic movement primitives

Alexandros Paraschos, Christian Daniel, Jan R Peters, Gerhard Neumann
NeurIPS · 2013
Towards Robot Skill Learning: From Simple Skills to Table Tennis

Towards Robot Skill Learning: From Simple Skills to Table Tennis

Jan Peters, Jens Kober, Katharina Mülling, Oliver Krämer, Gerhard Neumann
Machine Learning and Knowledge Discovery in Databases · 2013
Stochastic optimal control methods for investigating the power of morphological computation

Stochastic optimal control methods for investigating the power of morphological computation

Elmar A Rückert, Gerhard Neumann
Artificial life · 2013

2012

Generalization of human grasping for multi-fingered robot hands

Generalization of human grasping for multi-fingered robot hands

Heni Ben Amor, Oliver Kroemer, Ulrich Hillenbrand, Gerhard Neumann, Jan Peters
IROS · 2012
Hierarchical Relative Entropy Policy Search.

Hierarchical Relative Entropy Policy Search.

Christian Daniel, Gerhard Neumann, Jan Peters
AISTATS · 2012
Learning concurrent motor skills in versatile solution spaces

Learning concurrent motor skills in versatile solution spaces

Christian Daniel, Gerhard Neumann, Jan Peters
IROS · 2012
On movement skill learning and movement representations for robotics

On movement skill learning and movement representations for robotics

Gerhard Neumann
na · 2012
Learned graphical models for probabilistic planning provide a new class of movement primitives

Learned graphical models for probabilistic planning provide a new class of movement primitives

Elmar A Rückert, Gerhard Neumann, Marc Toussaint, Wolfgang Maass
Frontiers in computational neuroscience · 2012

2011

Biologically inspired kinematic synergies enable linear balance control of a humanoid robot

Biologically inspired kinematic synergies enable linear balance control of a humanoid robot

Helmut Hauser, Gerhard Neumann, Auke J Ijspeert, Wolfgang Maass
Biological cybernetics · 2011
A study of morphological computation by using probabilistic inference for motor planning

A study of morphological computation by using probabilistic inference for motor planning

Elmar Rückert, Gerhard Neumann
2nd international conference on morphological computation, Venice, Italy · 2011
Variational Inference for Policy Search in Changing Situations

Variational Inference for Policy Search in Changing Situations

Gerhard Neumann
ICML · 2011

2010

Comparative evaluation of approaches in T. 4.1-4.3 and working definition of adaptive module

Comparative evaluation of approaches in T. 4.1-4.3 and working definition of adaptive module

Mostafa Ajallooeian, Sébastien Gay, Auke Ijspeert, Mohammad Khansari-Zadeh, Seungsu Kim, Aude Billard, Elmar Rückert, Gerhard Neumann, Tim Waegeman, Benjamin Schrauwen, others
· 2010

2009

Fitted Q-iteration by advantage weighted regression

Fitted Q-iteration by advantage weighted regression

Gerhard Neumann, Jan R Peters
NeurIPS · 2009
Learning complex motions by sequencing simpler motion templates

Learning complex motions by sequencing simpler motion templates

Gerhard Neumann, Wolfgang Maass, Jan Peters
ICML · 2009

2008

Batch-mode reinforcement learning for continuous state spaces: A survey

Batch-mode reinforcement learning for continuous state spaces: A survey

Gerhard Neumann
ÖGAI Journal · 2008

2007

Biologically inspired kinematic synergies provide a new paradigm for balance control of humanoid robots

Biologically inspired kinematic synergies provide a new paradigm for balance control of humanoid robots

Helmut Hauser, Gerhard Neumann, Auke Jan Ijspeert, Wolfgang Maass
Humanoid Robots, 2007 7th IEEE-RAS International Conference on · 2007
Efficient continuous-time reinforcement learning with adaptive state graphs

Efficient continuous-time reinforcement learning with adaptive state graphs

Gerhard Neumann, Michael Pfeiffer, Wolfgang Maass
Machine Learning: ECML 2007 · 2007

2006

A Reinforcement Learning Toolbox and RL Benchmarks for the Control of Dynamical Systems

A Reinforcement Learning Toolbox and RL Benchmarks for the Control of Dynamical Systems

G Neumann
Dynamical principles for neuroscience and intelligent biomimetic devices · 2006

2005

The reinforcement learning toolbox, reinforcement learning for optimal control tasks

The reinforcement learning toolbox, reinforcement learning for optimal control tasks

Gerhard Neumann
na · 2005

2004

The reinforcement learning toolbox

The reinforcement learning toolbox

Gerhard Neumann, S Neumann
2005)[2005]. http://www. igi. tugraz. at/ril-toolbox · 2004