Autonomous Learning Group University of Tübingen

Publications

Generated from our BibTeX file. Members of the group are shown in bold.

All

2026

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
Pavel Kolev, Marin Vlastelica, Georg Martius
arXiv preprint  ·  2026
arXiv
Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control
Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control
Anselm Paulus, Andreas René Geist, Pierre Schumacher, Vít Musil, Simon Rappenecker, Georg Martius
The Fourteenth International Conference on Learning Representations  ·  2026
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
Loukas Kordos, Leonard T. Franz, Simon Rappenecker, Oliver Hausdoerfer, Angela P. Schoellig, Pavel Kolev, Georg Martius
arXiv preprint  ·  2026
arXiv
Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning
Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning
Nikola Milosevic, Leonard Franz, Daniel Haeufle, Georg Martius, Nico Scherf, Pavel Kolev
arXiv preprint  ·  2026
arXiv

2025

Active Fine-Tuning of Multi-Task Policies
Active Fine-Tuning of Multi-Task Policies
Marco Bagatella, Jonas Hübotter, Georg Martius, Andreas Krause
International Conference on Machine Learning (ICML)  ·  2025
arXiv
Zero-Shot Offline Imitation Learning via Optimal Transport
Zero-Shot Offline Imitation Learning via Optimal Transport
Thomas Rupf, Marco Bagatella, Nico Gürtler, Jonas Frey, Georg Martius
International Conference on Machine Learning (ICML)  ·  2025
arXiv
Adding Internal Audio Sensing to Internal Vision Enables Human-Like In-Hand Fabric Recognition with Soft Robotic Fingertips
Adding Internal Audio Sensing to Internal Vision Enables Human-Like In-Hand Fabric Recognition with Soft Robotic Fingertips
Iris Andrussow, Jans Solano, Benjamin A. Richardson, Georg Martius, Katherine J. Kuchenbecker
Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids)  ·  2025
arXiv
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius
International Conference on Machine Learning (ICML)  ·  2025
arXiv
Temporally Consistent Object-Centric Learning by Contrasting Slots
Temporally Consistent Object-Centric Learning by Contrasting Slots
Anna Manasyan, Maximilian Seitzer, Filip Radovic, Georg Martius, Andrii Zadaianchuk
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  ·  2025
Advancing Out-of-Distribution Detection via Local Neuroplasticity
Advancing Out-of-Distribution Detection via Local Neuroplasticity
A. Canevaro, J. Schmidt, M. S. Marvi, H. Yu, G. Martius, J. Jordan
The Thirteenth International Conference on Learning Representations (ICLR)  ·  2025
arXiv
On the Transfer of Object-Centric Representation Learning
On the Transfer of Object-Centric Representation Learning
A. R. Didolkar, A. Zadaianchuk, A. Goyal, M. C. Mozer, Y. Bengio, G. Martius, M. Seitzer
The Thirteenth International Conference on Learning Representations (ICLR)  ·  2025
Emergence of natural and robust bipedal walking by learning from biologically plausible objectives
Emergence of natural and robust bipedal walking by learning from biologically plausible objectives
Pierre Schumacher, Thomas Geijtenbeek, Vittorio Caggiano, Vikash Kumar, Syn Schmitt, Georg Martius, Daniel F B Haeufle
iScience  ·  2025
arXiv
DOI
Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
Jiaqi Chen, Ji Shi, Cansu Sancaktar, Jonas Frey, Georg Martius
Reinforcement Learning Journal  ·  2025
Epistemically-guided forward-backward exploration
Epistemically-guided forward-backward exploration
Núria Armengol Urpí, Marin Vlastelica, Georg Martius, Stelian Coros
Reinforcement Learning Journal  ·  2025
Long-Horizon Planning with Predictable Skills
Long-Horizon Planning with Predictable Skills
Nico Gürtler, Georg Martius
Reinforcement Learning Journal  ·  2025
Sensing multi-directional forces at superresolution using taxel value isoline theory
Sensing multi-directional forces at superresolution using taxel value isoline theory
Huanbo Sun, Adam Spiers, Hyosang Lee, Jonathan Fiene, Georg Martius
Nature Communications  ·  2025
Forecasting in Offline Reinforcement Learning for Non-stationary Environments
Forecasting in Offline Reinforcement Learning for Non-stationary Environments
Suzan Ece Ada, Georg Martius, Emre Ugur, Erhan Oztop
The Thirty-ninth Annual Conference on Neural Information Processing Systems  ·  2025

2024

Identifying Terrain Physical Parameters from Vision-Towards Physical-Parameter-Aware Locomotion and Navigation
Identifying Terrain Physical Parameters from Vision-Towards Physical-Parameter-Aware Locomotion and Navigation
Jiaqi Chen, Jonas Frey, Ruyi Zhou, Takahiro Miki, Georg Martius, Marco Hutter
IEEE Robotics and Automation Letters  ·  2024
Directed Exploration in Reinforcement Learning from Linear Temporal Logic
Directed Exploration in Reinforcement Learning from Linear Temporal Logic
Marco Bagatella, Andreas Krause, Georg Martius
arXiv preprint  ·  2024
arXiv
Modelling Microbial Communities with Graph Neural Networks
Modelling Microbial Communities with Graph Neural Networks
A. Ruaud, C. Sancaktar, M. Bagatella, C. Ratzke, G. Martius
41st International Conference on Machine Learning (ICML)  ·  2024
Website
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
A. Paulus, G. Martius, V. Musil
41st International Conference on Machine Learning (ICML)  ·  2024
arXiv
Learning with 3D rotations, a hitchhiker s guide to SO 3
Learning with 3D rotations, a hitchhiker's guide to SO(3)
A. R. Geist, J. Frey, M. Zhobro, A. Levina, G. Martius
41st International Conference on Machine Learning (ICML)  ·  2024
arXiv
Causal Action Influence Aware Counterfactual Data Augmentation
Causal Action Influence Aware Counterfactual Data Augmentation
N. A. Urpi, M. Bagatella, M. Vlastelica, G. Martius
41st International Conference on Machine Learning (ICML)  ·  2024
arXiv
Source
Multi-View Causal Representation Learning with Partial Observability
Multi-View Causal Representation Learning with Partial Observability
D. Yao, D. Xu, S. Lachapelle, S. Magliacane, P. Taslakian, G. Martius, J. von Kügelgen, F. Locatello
The Twelfth International Conference on Learning Representations (ICLR)  ·  2024
arXiv
Source
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
Christian Gumbsch, Noor Sajid, Georg Martius, Martin V. Butz
The Twelfth International Conference on Learning Representations  ·  2024
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis, Tim Jakob Schäfer, Georg Martius, Anna Levina
The Twelfth International Conference on Learning Representations  ·  2024
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
A. Spieler, N. Rahaman, G. Martius, B. Schölkopf, A. Levina
The Twelfth International Conference on Learning Representations (ICLR)  ·  2024
arXiv
Source
Offline Diversity Maximization Under Imitation Constraints
Offline Diversity Maximization Under Imitation Constraints
Marin Vlastelica, Jin Cheng, Georg Martius, Pavel Kolev
arXiv preprint  ·  2024
arXiv
Machine learning of a density functional for anisotropic patchy particles
Machine learning of a density functional for anisotropic patchy particles
Alessandro Simon, Jens Weimar, Georg Martius, Martin Oettel
Journal of Chemical Theory and Computation  ·  2024
DOI

2023

Goal-conditioned Offline Planning from Curious Exploration
Goal-conditioned Offline Planning from Curious Exploration
Marco Bagatella, Georg Martius
2023
Regularity as Intrinsic Reward for Free Play
Regularity as Intrinsic Reward for Free Play
Cansu Sancaktar, Justus Piater, Georg Martius
Advances in Neural Information Processing Systems 37  ·  2023
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)  ·  2023
Online Learning under Adversarial Nonlinear Constraints
Online Learning under Adversarial Nonlinear Constraints
Pavel Kolev, Georg Martius, Michael Muehlebach
Advances in Neural Information Processing Systems 36  ·  2023
Minsight: A Fingertip-Sized Vision-Based Tactile Sensor for Robotic Manipulation
Minsight: A Fingertip-Sized Vision-Based Tactile Sensor for Robotic Manipulation
Iris Andrussow, Huanbo Sun, Katherine J. Kuchenbecker, Georg Martius
Advanced Intelligent Systems  ·  2023
Bridging the Gap to Real-World Object-Centric Learning
Bridging the Gap to Real-World Object-Centric Learning
Maximilian Seitzer, Max Horn, Andrii Zadaianchuk, Dominik Zietlow, Tianjun Xiao, …, Tong He, Zheng Zhang, Bernhard Schölkopf, Thomas Brox, Francesco Locatello
Proceedings of the Eleventh International Conference on Learning Representations  ·  2023
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
C. Li, S. Blaes, P. Kolev, M. Vlastelica, J. Frey, G. Martius
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)  ·  2023
arXiv
Source
Website
Video
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
Onno Eberhard, Jakob Hollenstein, Cristina Pinneri, Georg Martius
Proceedings of the Eleventh International Conference on Learning Representations (ICLR)  ·  2023
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
Nico Gürtler, Sebastian Blaes, Pavel Kolev, Felix Widmaier, Manuel Wüthrich, Stefan Bauer, Bernhard Schölkopf, Georg Martius
Proceedings of the Eleventh International Conference on Learning Representations  ·  2023
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Pierre Schumacher, Daniel F.B. Haeufle, Dieter Büchler, Syn Schmitt, Georg Martius
Proceedings of the Eleventh International Conference on Learning Representations (ICLR)  ·  2023
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Subham Sahoo, Anselm Paulus, Marin Vlastelica, Vít Musil, Volodymyr Kuleshov, Georg Martius
Proceedings of the Eleventh International Conference on Learning Representations  ·  2023
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations
C. Li, M. Vlastelica, S. Blaes, J. Frey, F. Grimminger, G. Martius
Proceedings of the 6th Conference on Robot Learning (CoRL)  ·  2023
arXiv
Source
Website
Video
Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius
arXiv preprint  ·  2023
arXiv
Predicting the Force Map of an ERT-Based Tactile Sensor Using Simulation and Deep Networks
Predicting the Force Map of an ERT-Based Tactile Sensor Using Simulation and Deep Networks
Hyosang Lee, Huanbo Sun, Hyunkyu Park, Gokhan Serhat, Bernard Javot, Georg Martius, Katherine J. Kuchenbecker
IEEE Transactions on Automation Science and Engineering  ·  2023
Efficient Learning of High Level Plans from Play
Efficient Learning of High Level Plans from Play
N. Armengol Urpi, M. Bagatella, O. Hilliges, G. Martius, S. Coros
International Conference on Robotics and Automation  ·  2023
arXiv
DOI
Source
Website

2022

Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
P. Reizinger, L. Gresele, J. Brady*, J. von Kügelgen, D. Zietlow, B. Schölkopf, G. Martius, W. Brendel, M. Besserve
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)  ·  2022
arXiv
Source
Video
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
Cansu Sancaktar, Sebastian Blaes, Georg Martius
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)  ·  2022
A Sequential Group VAE for Robot Learning of Haptic Representations
A Sequential Group VAE for Robot Learning of Haptic Representations
Benjamin A. Richardson, Katherine J. Kuchenbecker, Georg Martius
Workshop paper (8 pages) presented at the CoRL Workshop on Aligning Robot Representations with Humans  ·  2022
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
I. Wochner, P. Schumacher, G. Martius, D. Büchler, S. Schmitt, D. Haeufle
Proceedings of the 6th Conference on Robot Learning (CoRL)  ·  2022
A Soft Vision-Based Tactile Sensor for Robotic Fingertip Manipulation
A Soft Vision-Based Tactile Sensor for Robotic Fingertip Manipulation
Iris Andrussow, Huanbo Sun, Katherine J. Kuchenbecker, Georg Martius
Workshop paper (1 page) presented at the IROS Workshop on Large-Scale Robotic Skin: Perception, Interaction and Control  ·  2022
Developing hierarchical anticipations via neural network-based event segmentation
Developing hierarchical anticipations via neural network-based event segmentation
Christian Gumbsch, Maurits Adam, Birgit Elsner, Georg Martius, Martin V Butz
Proceedings of the IEEE International Conference on Development and Learning (ICDL 2022)  ·  2022
arXiv
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
Maximilian Seitzer, Arash Tavakoli, Dimitrije Antic, Georg Martius
International Conference on Learning Representations  ·  2022
A Soft Thumb-Sized Vision-Based Sensor with Accurate All-Round Force Perception
A Soft Thumb-Sized Vision-Based Sensor with Accurate All-Round Force Perception
Huanbo Sun, Katherine J. Kuchenbecker, Georg Martius
Nature Machine Intelligence  ·  2022
DOI
Guiding the Design of Super-resolution Tactile Skins with Taxel Value Isolines Theory
Guiding the Design of Super-resolution Tactile Skins with Taxel Value Isolines Theory
Huanbo Sun, Georg Martius
Science Robotics  ·  2022
DOI
Risk-Averse Zero-Order Trajectory Optimization
Risk-Averse Zero-Order Trajectory Optimization
Marin Vlastelica, Sebastian Blaes, Cristina Pinneri, Georg Martius
Conference on Robot Learning  ·  2022
arXiv
Source
Website
Uncertainty in Equation Learning
Uncertainty in Equation Learning
Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius
Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO)  ·  2022
Intelligent problem-solving as integrated hierarchical reinforcement learning
Intelligent problem-solving as integrated hierarchical reinforcement learning
Manfred Eppe, Christian Gumbsch, Matthias Kerzel, Phuong D. H. Nguyen, Martin V. Butz, Stefan Wermter
Nature Machine Intelligence  ·  2022
DOI

2021

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
Christian Gumbsch, Martin V. Butz, Georg Martius
Advances in Neural Information Processing Systems (NeurIPS 2021)  ·  2021
arXiv
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
Planning from Pixels in Environments with Combinatorially Hard Search Spaces
Marco Bagatella, Mirek Olšák, Michal Rolínek, Georg Martius
Advances in Neural Information Processing Systems (NeurIPS 2021)  ·  2021
arXiv
Hierarchical Reinforcement Learning with Timed Subgoals
Hierarchical Reinforcement Learning with Timed Subgoals
N. Gürtler, D. Büchler, G. Martius
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)  ·  2021
Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Maximilian Seitzer, Bernhard Schölkopf, Georg Martius
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)  ·  2021
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
Self-supervised Reinforcement Learning with Independently Controllable Subgoals
Andrii Zadaianchuk, Georg Martius, Fanny Yang
Conference on Robot Learning  ·  2021
arXiv
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
Marin Vlastelica, Michal Rolinek, Georg Martius
Proceedings of the 2021 International Conference on Machine Learning (ICML)  ·  2021
arXiv
The dynamical regime and its importance for evolvability, task performance and generalization
The dynamical regime and its importance for evolvability, task performance and generalization
Jan Prosi, Sina Khajehabdollahi, Emmanouil Giannakakis, Georg Martius, Anna Levina
The 2021 Conference on Artificial Life  ·  2021
arXiv
DOI
Demystifying Inductive Biases for Beta- VAE Based Architectures
Demystifying Inductive Biases for (Beta-)VAE Based Architectures
Dominik Zietlow, Michal Rolinek, Georg Martius
Proceedings of the 2021 International Conference on Machine Learning (ICML)  ·  2021
arXiv
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Anselm Paulus, Michal Rolínek, Vít Musil, Brandon Amos, Georg Martius
Proceedings of the 38th International Conference on Machine Learning  ·  2021
How to Train Your Differentiable Filter
How to Train Your Differentiable Filter
Alina Kloss, Georg Martius, Jeannette Bohg
Autonomous Robots  ·  2021
DOI
Machine learning time-local generators of open quantum dynamics
Machine learning time-local generators of open quantum dynamics
Paolo P. Mazza, Dominik Zietlow, Federico Carollo, Sabine Andergassen, Georg Martius, Igor Lesanovsky
Phys. Rev. Research  ·  2021
DOI
Jumping over baselines with new methods to predict activation maps from resting-state fMRI
Jumping over baselines with new methods to predict activation maps from resting-state fMRI
Eric Lacosse, Klaus Scheffler, Gabriele Lohmann, Georg Martius
Scientific Reports  ·  2021
DOI
Source
Self-supervised Visual Reinforcement Learning with Object-centric Representations
Self-supervised Visual Reinforcement Learning with Object-centric Representations
Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius
International Conference on Learning Representations  ·  2021
arXiv
Source
Website
Video
Extracting Strong Policies for Robotics Tasks from Zero-order Trajectory Optimizers
Extracting Strong Policies for Robotics Tasks from Zero-order Trajectory Optimizers
Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Georg Martius
International Conference on Learning Representations  ·  2021
A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks
A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks
Christian Landgraf, Bernd Meese, Michael Pabst, Georg Martius, Marco F. Huber
Sensors  ·  2021
DOI
Informed Equation Learning
Informed Equation Learning
Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius
arXiv  ·  2021
arXiv

2020

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Michal Rolinek, Paul Swoboda, Dominik Zietlow, Anselm Paulus, Vit Musil, Georg Martius
Computer Vision – ECCV 2020  ·  2020
arXiv
Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control
Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control
Jia-Jie Zhu, Georg Martius
21rst IFAC World Congress  ·  2020
arXiv
DOI
A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models
A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models
D. Agudelo-España, A. Zadaianchuk, P. Wenk, A. Garg, J. Akpo, …, G. Martius, A. Krause, B. Schölkopf, S. Bauer, M. Wüthrich
IEEE International Conference on Robotics and Automation (ICRA)  ·  2020
PDF
Source
Analytical classical density functionals from an equation learning network
Analytical classical density functionals from an equation learning network
Shang-Chun Lin, Georg Martius, Martin Oettel
The Journal of Chemical Physics  ·  2020
arXiv
DOI
Differentiation of blackbox combinatorial solvers
Differentiation of blackbox combinatorial solvers
Marin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolínek
International Conference on Learning Representations  ·  2020
Optimizing Rank-based Metrics with Blackbox Differentiation
Optimizing Rank-based Metrics with Blackbox Differentiation
Michal Rolınek, Vıt Musil, Anselm Paulus, Marin Vlastelica, Claudio Michaelis, Georg Martius
Conference on Computer Vision and Pattern Recognition  ·  2020
arXiv
DOI
Source
Sample-efficient Cross-Entropy Method for Real-time Planning
Sample-efficient Cross-Entropy Method for Real-time Planning
Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Georg Martius
Conference on Robot Learning (CoRL) 2020  ·  2020

2019

Assessing Aesthetics of Generated Abstract Images Using Correlation Structure
Assessing Aesthetics of Generated Abstract Images Using Correlation Structure
Sina Khajehabdollahi, Georg Martius, Anna Levina
Proceedings 2019 IEEE Symposium Series on Computational Intelligence (SSCI)  ·  2019
arXiv
Variational Autoencoders Pursue PCA Directions by Accident
Variational Autoencoders Pursue PCA Directions (by Accident)
Michal Rolínek, Dominik Zietlow, Georg Martius
Conference on Computer Vision and Pattern Recognition (CVPR'19)  ·  2019
arXiv
Falsification of Hybrid Systems using Symbolic Reachability and Trajectory Splicing
Falsification of Hybrid Systems using Symbolic Reachability and Trajectory Splicing
Sergiy Bogomolov, Goran Frehse, Amit Gurung, Dongxu Li, Georg Martius, Rajarshi Ray
22nd ACM Intl. Conf. on Hybrid Systems: Computation and Control (HSCC 2019)  ·  2019
PDF
DOI
Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives
Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives
Christian Gumbsch, Martin V. Butz, Georg Martius
IEEE Transactions on Cognitive and Developmental Systems  ·  2019
Control What You Can: Intrinsically Motivated Task-Planning Agent
Control What You Can: Intrinsically Motivated Task-Planning Agent
Sebastian Blaes, Marin Vlastelica, Jia-Jie Zhu, Georg Martius
Advances in Neural Information Processing (NeurIPS'19)  ·  2019
Machine Learning for Haptics: Inferring Multi-Contact Stimulation From Sparse Sensor Configuration
Machine Learning for Haptics: Inferring Multi-Contact Stimulation From Sparse Sensor Configuration
Huanbo Sun, Georg Martius
Frontiers in Neurorobotics  ·  2019

2018

Nonlinear decoding of a complex movie from the mammalian retina
Vicente Botella-Soler, Stéphane Deny, Georg Martius, Olivier Marre, Gašper Tkačik
PLOS Computational Biology  ·  2018
Learning equations for extrapolation and control
Learning equations for extrapolation and control
Subham S. Sahoo, Christoph H. Lampert, Georg Martius
Proc. 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden  ·  2018
PDF
Systematic self-exploration of behaviors for robots in a dynamical systems framework
Systematic self-exploration of behaviors for robots in a dynamical systems framework
Cristina Pinneri, Georg Martius
Proc. Artificial Life XI  ·  2018
DOI
Robust and Cheap 3D Haptic Sensation using Deformation Patterns and Machine Learning
Robust and Cheap 3D Haptic Sensation using Deformation Patterns and Machine Learning
Huanbo Sun, Georg Martius
IEEE-RAS International Conference on Humanoid Robots (Humanoids 2018)  ·  2018
Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns
Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns
Huanbo Sun, Georg Martius
Proceedings International Conference on Humanoid Robots (IEEE Humanoids)  ·  2018
L4: Practical loss-based stepsize adaptation for deep learning
L4: Practical loss-based stepsize adaptation for deep learning
Michal Rolínek, Georg Martius
Advances in Neural Information Processing (NeurIPS'18)  ·  2018
Deep Reinforcement Learning for Event-Triggered Control
Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe
2018 IEEE Conference on Decision and Control (CDC)  ·  2018
DOI

2017

Self-Organized Behavior Generation for Musculoskeletal Robots
Ralf Der, Georg Martius
Frontiers in Neurorobotics  ·  2017
arXiv
DOI

2016

Dynamical self-consistency leads to behavioral development and emergent social interactions in robots
Ralf Der, Georg Martius
2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)  ·  2016
PDF
Compliant control for soft robots: emergent behavior of a tendon driven anthropomorphic arm.
Georg Martius, Rafael Hostettler, Alois Knoll, Ralf Der
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  ·  2016
PDF
Extrapolation and learning equations
Extrapolation and learning equations
Georg Martius, Christoph H. Lampert
arXiv preprint  ·  2016
arXiv

2015

Quantifying Emergent Behavior of Autonomous Robots
Georg Martius, Eckehard Olbrich
Entropy  ·  2015
DOI
Novel plasticity rule can explain the development of sensorimotor intelligence
Novel plasticity rule can explain the development of sensorimotor intelligence
Ralf Der, Georg Martius
Proceedings of the National Academy of Sciences  ·  2015
DOI

2014

Self-Exploration of the Stumpy Robot with Predictive Information Maximization
Georg Martius, Luisa Jahn, Helmut Hauser, Verena V. Hafner
Proc. From Animals to Animats, SAB 2014  ·  2014
PDF
Robot Learning by Guided Self-Organization
Georg Martius, Ralf Der, J. Michael Herrmann
Guided Self-Organization: Inception  ·  2014
DOI

2013

Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis
Keyan Zahedi, Georg Martius, Nihat Ay
Frontiers in Psychology  ·  2013
DOI
Information Driven Self-Organization of Complex Robotic Behaviors
Georg Martius, Ralf Der, Nihat Ay
PLoS ONE  ·  2013
DOI
Robustness of guided self-organization against sensorimotor disruptions
Georg Martius
Advances in Complex Systems  ·  2013
PDF
Behavior as broken symmetry in embodied self-organizing robots
Ralf Der, Georg Martius
Advances in Artificial Life, ECAL 2013  ·  2013
PDF

2012

Predictive information in reinforcement learning of embodied agents
Keyan Zahedi, Georg Martius, Nihat Ay
Int. Workshop on Guided Self-Organization 5  ·  2012
Variants of guided self-organization for robot control
Georg Martius, J. Michael Herrmann
Theory in Biosci.  ·  2012
PDF
DOI
The Playful Machine - Theoretical Foundation and Practical Realization of Self-Organizing Robots
The Playful Machine - Theoretical Foundation and Practical Realization of Self-Organizing Robots
Ralf Der, Georg Martius
Springer  ·  2012
PDF

2011

Tipping the Scales: Guidance and Intrinsically Motivated Behavior
Georg Martius, J. M. Herrmann
Advances in Artificial Life, ECAL 2011  ·  2011
PDF

2010

LpzRobots: A free and powerful robot simulator
LpzRobots: A free and powerful robot simulator
Georg Martius, Frank Hesse, Frank Güttler, Ralf Der
<http://robot.informatik.uni-leipzig.de/software>  ·  2010
Taming the Beast: Guided Self-organization of Behavior in Autonomous Robots
Georg Martius, J. Michael Herrmann
From Animals to Animats 11  ·  2010
DOI
Goal-Oriented Control of Self-Organizing Behavior in Autonomous Robots
Georg Martius
Georg-August-Universität Göttingen  ·  2010
Playful Machines: Tutorial
Ralf Der, Georg Martius
<http://robot.informatik.uni-leipzig.de/tutorial?lang=en>  ·  2010

2009

A Sensor-Based Learning Algorithm for the Self-Organization of Robot Behavior
Frank Hesse, Georg Martius, Ralf Der, J. Michael Herrmann
Algorithms  ·  2009

2008

Emergence of Interaction Among Adaptive Agents
Georg Martius, Stefano Nolfi, J. Michael Herrmann
Proc. From Animals to Animats 10 (SAB 2008)  ·  2008
Structure from Behavior in Autonomous Agents
Georg Martius, Katja Fiedler, J. Michael Herrmann
Proc. IEEE Intl. Conf. Intelligent Robots and Systems (IROS 2008)  ·  2008

2007

Guided Self-organisation for Autonomous Robot Development
Georg Martius, J. Michael Herrmann, Ralf Der
Advances in Artificial Life 9th European Conference, ECAL 2007  ·  2007

2006

Let It Roll – Emerging Sensorimotor Coordination in a Spherical Robot
Ralf Der, Georg Martius, Frank Hesse
Proc, Artificial Life X  ·  2006
Rocking Stamper and Jumping Snake from a Dynamical System Approach to Artificial Life
Ralf Der, Frank Hesse, Georg Martius
Adaptive Behavior  ·  2006
PDF
From Motor Babbling to Purposive Actions: Emerging Self-exploration in a Dynamical Systems Approach to Early Robot Development
Ralf Der, Georg Martius
Proc. From Animals to Animats 9, SAB 2006  ·  2006

2005

Learning to Feel the Physics of a Body
Ralf Der, Frank Hesse, Georg Martius
Computational Intelligence for Modelling, Control and Automation, CIMCA 2005  ·  2005