Gerhard Neumann
143 publications
25 venues
H Index 36
Affiliation
Karlsruhe Institute of Technology, Institute for Anthropomatics and Robotics, GermanyUniversity of Lincoln, Center for Autonomous Systems (L-CAS), UK
TU Darmstadt, Department of Computer Science, Germany
Graz University of Technology, Austria
Links
DBLPGoogle Scholar
ORCID- https://alr.iar.kit.edu/21_65.php
- http://www.ias.informatik.tu-darmstadt.de/Member/GerhardNeumann
- https://openreview.net/profile?id=~Gerhard_Neumann2
- https://www.wikidata.org/entity/Q51574985
- https://d-nb.info/gnd/1186718684
- https://ieeexplore.ieee.org/author/38542033100
- https://id.loc.gov/authorities/names/no2013123154
| Name | Venue | Year | citations |
|---|---|---|---|
Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects.
|
ICLR | 2025 | 8 |
| Point Cloud Segmentation for Autonomous Clip Positioning in Laparoscopic Cholecystectomy on a Phantom.
|
IEEE Robotics and Automation Letters | 2025 | 0 |
| Towards Safe and Efficient Learning in the Wild: Guiding RL With Constrained Uncertainty-Aware Movement Primitives.
|
IEEE Robotics and Automation Letters | 2025 | 1 |
| Underdamped Diffusion Bridges with Applications to Sampling.
|
ICLR | 2025 | 27 |
| End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler.
|
ICLR | 2025 | 6 |
| DIME: Diffusion-Based Maximum Entropy Reinforcement Learning.
|
ICML | 2025 | 0 |
| Efficient Off-Policy Learning for High-Dimensional Action Spaces.
|
ICLR | 2025 | 0 |
| Sequential Controlled Langevin Diffusions.
|
ICLR | 2025 | 0 |
| TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning.
|
ICLR | 2025 | 0 |
| Diffusion for Multi-Embodiment Grasping.
|
IEEE Robotics and Automation Letters | 2025 | 0 |
| Enhancing Exploration With Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation.
|
IEEE Robotics and Automation Letters | 2025 | 0 |
| Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling.
|
ICML | 2024 | 45 |
| Lens Capsule Tearing in Cataract Surgery using Reinforcement Learning.
|
ICRA | 2024 | 0 |
| MaIL: Improving Imitation Learning with Selective State Space Models.
|
CoRL | 2024 | 19 |
| Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning.
|
JMLR | 2024 | 4 |
| MuTT: A Multimodal Trajectory Transformer for Robot Skills.
|
IROS | 2024 | 2 |
| Neural Contractive Dynamical Systems.
|
ICLR | 2024 | 14 |
| Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts.
|
ICML | 2024 | 18 |
| Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning.
|
ICLR | 2024 | 11 |
| PointPatchRL - Masked Reconstruction Improves Reinforcement Learning on Point Clouds.
|
CoRL | 2024 | 4 |
| Variational Distillation of Diffusion Policies into Mixture of Experts.
|
NIPS/NeurIPS | 2024 | 9 |
| Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations.
|
ICLR | 2024 | 46 |
| A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics.
|
NIPS/NeurIPS | 2024 | 1 |
| Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects.
|
IEEE Robotics and Automation Letters | 2024 | 0 |
| Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift.
|
NIPS/NeurIPS | 2023 | 26 |
| SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects.
|
CoRL | 2023 | 8 |
| Adversarial Imitation Learning with Preferences.
|
ICLR | 2023 | 11 |
| Multi Time Scale World Models.
|
NIPS/NeurIPS | 2023 | 6 |
| Curriculum-Based Imitation of Versatile Skills.
|
ICRA | 2023 | 5 |
| SyMFM6D: Symmetry-Aware Multi-Directional Fusion for Multi-View 6D Object Pose Estimation.
|
IEEE Robotics and Automation Letters | 2023 | 11 |
| Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference.
|
ICLR | 2023 | 6 |
| Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills.
|
NIPS/NeurIPS | 2023 | 0 |
| Swarm Reinforcement Learning for Adaptive Mesh Refinement.
|
NIPS/NeurIPS | 2023 | 23 |
| LapGym - An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery.
|
JMLR | 2023 | 42 |
| Grounding Graph Network Simulators using Physical Sensor Observations.
|
ICLR | 2023 | 17 |
| ProDMP: A Unified Perspective on Dynamic and Probabilistic Movement Primitives.
|
IEEE Robotics and Automation Letters | 2023 | 0 |
| Reactive motion generation on learned Riemannian manifolds.
|
IJRR | 2023 | 0 |
| FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion.
|
ECCV | 2022 | 10 |
| Hierarchical Policy Learning for Mechanical Search.
|
ICRA | 2022 | 4 |
| What Matters For Meta-Learning Vision Regression Tasks?
|
CVPR | 2022 | 30 |
| MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network.
|
IROS | 2022 | 18 |
| Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning.
|
ICRA | 2022 | 13 |
| Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors.
|
CoRL | 2022 | 8 |
| Deep Black-Box Reinforcement Learning with Movement Primitives.
|
CoRL | 2022 | 26 |
| Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios.
|
ICLR | 2022 | 8 |
| End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control.
|
RSS | 2022 | 8 |
| Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination.
|
IROS | 2022 | 3 |
| Specializing Versatile Skill Libraries using Local Mixture of Experts.
|
CoRL | 2021 | 41 |
| Learning Riemannian Manifolds for Geodesic Motion Skills.
|
RSS | 2021 | 36 |
| Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty.
|
IROS | 2021 | 13 |
| Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning.
|
IROS | 2021 | 18 |
| Navigate-and-Seek: A Robotics Framework for People Localization in Agricultural Environments.
|
IEEE Robotics and Automation Letters | 2021 | 13 |
| Bayesian Context Aggregation for Neural Processes.
|
ICLR | 2021 | 36 |
| Differentiable Trust Region Layers for Deep Reinforcement Learning.
|
ICLR | 2021 | 23 |
| Expected Information Maximization: Using the I-Projection for Mixture Density Estimation.
|
ICLR | 2020 | 16 |
| Enhancing Grasp Pose Computation in Gripper Workspace Spheres.
|
ICRA | 2020 | 0 |
| Next-Best-Sense: A Multi-Criteria Robotic Exploration Strategy for RFID Tags Discovery.
|
IEEE Robotics and Automation Letters | 2020 | 7 |
| Probabilistic Approach to Physical Object Disentangling.
|
IEEE Robotics and Automation Letters | 2020 | 2 |
| Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning.
|
CoRL | 2020 | 18 |
| Trust-Region Variational Inference with Gaussian Mixture Models.
|
JMLR | 2020 | 0 |
| Learning Replanning Policies With Direct Policy Search.
|
IEEE Robotics and Automation Letters | 2019 | 4 |
| Projections for Approximate Policy Iteration Algorithms.
|
ICML | 2019 | 18 |
| Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces.
|
ICML | 2019 | 0 |
| Learning Kalman Network: A deep monocular visual odometry for on-road driving.
|
Robotics and Autonomous Systems | 2019 | 22 |
| Grasping Unknown Objects Based on Gripper Workspace Spheres.
|
IROS | 2019 | 11 |
| Improving Local Trajectory Optimisation using Probabilistic Movement Primitives.
|
IROS | 2019 | 43 |
| Compatible natural gradient policy search.
|
MLJ | 2019 | 26 |
| The kernel Kalman rule - Efficient nonparametric inference by recursive least-squares and subspace projections.
|
MLJ | 2019 | 0 |
| Deep Reinforcement Learning for Swarm Systems.
|
JMLR | 2019 | 0 |
| Regularizing Reinforcement Learning with State Abstraction.
|
IROS | 2018 | 29 |
| Energy-Efficient Design and Control of a Vibro-Driven Robot.
|
IROS | 2018 | 23 |
| Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences.
|
ICRA | 2018 | 23 |
| Learning Robust Policies for Object Manipulation with Robot Swarms.
|
ICRA | 2018 | 19 |
| Learning Coupled Forward-Inverse Models with Combined Prediction Errors.
|
ICRA | 2018 | 2 |
| Contact Detection and Size Estimation Using a Modular Soft Gripper with Embedded Flex Sensors.
|
IROS | 2018 | 6 |
| Efficient Gradient-Free Variational Inference using Policy Search.
|
ICML | 2018 | 50 |
| Using probabilistic movement primitives in robotics.
|
Autonomous Robots | 2018 | 0 |
| Model-Free Trajectory-based Policy Optimization with Monotonic Improvement.
|
JMLR | 2018 | 0 |
| A Survey of Preference-Based Reinforcement Learning Methods.
|
JMLR | 2017 | 427 |
| Non-parametric Policy Search with Limited Information Loss.
|
JMLR | 2017 | 27 |
| Learning movement primitive libraries through probabilistic segmentation.
|
IJRR | 2017 | 67 |
| Empowered skills.
|
ICRA | 2017 | 4 |
| Hybrid control trajectory optimization under uncertainty.
|
IROS | 2017 | 14 |
| A learning-based shared control architecture for interactive task execution.
|
ICRA | 2017 | 55 |
| Model-based contextual policy search for data-efficient generalization of robot skills.
|
Artificial Intelligence | 2017 | 80 |
| Contextual Covariance Matrix Adaptation Evolutionary Strategies.
|
IJCAI | 2017 | 10 |
| Probabilistic Prioritization of Movement Primitives.
|
IEEE Robotics and Automation Letters | 2017 | 27 |
| State-Regularized Policy Search for Linearized Dynamical Systems.
|
ICAPS | 2017 | 6 |
| Guiding Trajectory Optimization by Demonstrated Distributions.
|
IEEE Robotics and Automation Letters | 2017 | 59 |
| The Kernel Kalman Rule - Efficient Nonparametric Inference with Recursive Least Squares.
|
AAAI | 2017 | 15 |
| Local Bayesian Optimization of Motor Skills.
|
ICML | 2017 | 23 |
| Learning to Assemble Objects with a Robot Swarm.
|
AAMAS | 2017 | 2 |
| Layered direct policy search for learning hierarchical skills.
|
ICRA | 2017 | 23 |
| Policy Search with High-Dimensional Context Variables.
|
AAAI | 2017 | 0 |
| Phase estimation for fast action recognition and trajectory generation in human-robot collaboration.
|
IJRR | 2017 | 0 |
| Probabilistic movement primitives for coordination of multiple human-robot collaborative tasks.
|
Autonomous Robots | 2017 | 0 |
| Movement primitives with multiple phase parameters.
|
ICRA | 2016 | 7 |
| Model-Free Trajectory Optimization for Reinforcement Learning.
|
ICML | 2016 | 51 |
| Catching heuristics are optimal control policies.
|
NIPS/NeurIPS | 2016 | 36 |
| Optimal control and inverse optimal control by distribution matching.
|
IROS | 2016 | 5 |
| Non-parametric contextual stochastic search.
|
IROS | 2016 | 4 |
| Learning soft task priorities for control of redundant robots.
|
ICRA | 2016 | 41 |
| Model-Free Preference-Based Reinforcement Learning.
|
AAAI | 2016 | 110 |
| Demonstration based trajectory optimization for generalizable robot motions.
|
Humanoids | 2016 | 56 |
| Probabilistic inference for determining options in reinforcement learning.
|
MLJ | 2016 | 119 |
| Using probabilistic movement primitives for striking movements.
|
Humanoids | 2016 | 28 |
| Hierarchical Relative Entropy Policy Search.
|
JMLR | 2016 | 0 |
| Probabilistic segmentation applied to an assembly task.
|
Humanoids | 2015 | 47 |
| Learning multiple collaborative tasks with a mixture of Interaction Primitives.
|
ICRA | 2015 | 110 |
| Optimizing robot striking movement primitives with Iterative Learning Control.
|
Humanoids | 2015 | 5 |
| Learning motor skills from partially observed movements executed at different speeds.
|
IROS | 2015 | 25 |
| Model-free Probabilistic Movement Primitives for physical interaction.
|
IROS | 2015 | 24 |
| Learning of Non-Parametric Control Policies with High-Dimensional State Features.
|
AISTATS | 2015 | 36 |
| Learning robot in-hand manipulation with tactile features.
|
Humanoids | 2015 | 179 |
| Towards learning hierarchical skills for multi-phase manipulation tasks.
|
ICRA | 2015 | 135 |
| Regularized covariance estimation for weighted maximum likelihood policy search methods.
|
Humanoids | 2015 | 16 |
| A Probabilistic Framework for Semi-autonomous Robots Based on Interaction Primitives with Phase Estimation.
|
ISRR | 2015 | 14 |
| Extracting low-dimensional control variables for movement primitives.
|
ICRA | 2015 | 47 |
| Policy Evaluation with Temporal Differences: A Survey and Comparison (Extended Abstract).
|
ICAPS | 2015 | 0 |
| Model-Based Relative Entropy Stochastic Search.
|
NIPS/NeurIPS | 2015 | 0 |
| Interaction primitives for human-robot cooperation tasks.
|
ICRA | 2014 | 234 |
| Learning to predict phases of manipulation tasks as hidden states.
|
ICRA | 2014 | 52 |
| Policy Search for Path Integral Control.
|
ECML/PKDD | 2014 | 49 |
| Robust policy updates for stochastic optimal control.
|
Humanoids | 2014 | 11 |
| Learning interaction for collaborative tasks with probabilistic movement primitives.
|
Humanoids | 2014 | 110 |
| Latent space policy search for robotics.
|
IROS | 2014 | 27 |
| Sample-based informationl-theoretic stochastic optimal control.
|
ICRA | 2014 | 32 |
| Dimensionality reduction for probabilistic movement primitives.
|
Humanoids | 2014 | 40 |
| Policy evaluation with temporal differences: a survey and comparison.
|
JMLR | 2014 | 0 |
| A probabilistic approach to robot trajectory generation.
|
Humanoids | 2013 | 25 |
| Probabilistic Movement Primitives.
|
NIPS/NeurIPS | 2013 | 692 |
| Learning sequential motor tasks.
|
ICRA | 2013 | 51 |
| Data-Efficient Generalization of Robot Skills with Contextual Policy Search.
|
AAAI | 2013 | 135 |
| Autonomous reinforcement learning with hierarchical REPS.
|
IJCNN | 2013 | 7 |
| Towards Robot Skill Learning: From Simple Skills to Table Tennis.
|
ECML/PKDD | 2013 | 44 |
| Learning concurrent motor skills in versatile solution spaces.
|
IROS | 2012 | 44 |
| Generalization of human grasping for multi-fingered robot hands.
|
IROS | 2012 | 117 |
| Hierarchical Relative Entropy Policy Search.
|
AISTATS | 2012 | 0 |
| Variational Inference for Policy Search in changing situations.
|
ICML | 2011 | 114 |
| Learning complex motions by sequencing simpler motion templates.
|
ICML | 2009 | 50 |
| Fitted Q-iteration by Advantage Weighted Regression.
|
NIPS/NeurIPS | 2008 | 78 |
| Biologically inspired kinematic synergies provide a new paradigm for balance control of humanoid robots.
|
Humanoids | 2007 | 35 |
| Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs.
|
ECML/PKDD | 2007 | 19 |