Publication List with Images
2022 |
|
Xue, Honghu; Hein, Benedikt; Bakr, Mohamed; Schildbach, Georg; Abel, Bengt; Rueckert, Elmar Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics Journal Article In: Applied Sciences (MDPI), Special Issue on Intelligent Robotics, 2022, (Supplement: https://cloud.cps.unileoben.ac.at/index.php/s/Sj68rQewnkf4ppZ). Abstract | Links | BibTeX | Tags: @article{Xue2022, We propose a deep reinforcement learning approach for solving a mapless navigation problem in warehouse scenarios. The automatic guided vehicle is equipped with LiDAR and frontal RGB sensors and learns to reach underneath the target dolly. The challenges reside in the sparseness of positive samples for learning, multi-modal sensor perception with partial observability, the demand for accurate steering maneuvers together with long training cycles. To address these points, we proposed NavACL-Q as an automatic curriculum learning together with distributed soft actor-critic. The performance of the learning algorithm is evaluated exhaustively in a different warehouse environment to check both robustness and generalizability of the learned policy. Results in NVIDIA Isaac Sim demonstrates that our trained agent significantly outperforms the map-based navigation pipeline provided by NVIDIA Isaac Sim in terms of higher agent-goal distances and relative orientations. The ablation studies also confirmed that NavACL-Q greatly facilitates the whole learning process and a pre-trained feature extractor manifestly boosts the training speed. | ![]() |
2021 |
|
Denz, R.; Demirci, R.; Cansev, E.; Bliek, A.; Beckerle, P.; Rueckert, E.; Rottmann, N. A high-accuracy, low-budget Sensor Glove for Trajectory Model Learning Inproceedings In: International Conference on Advanced Robotics , pp. 7, 2021. Links | BibTeX | Tags: Grasping, human motor control, Manipulation, smart sensors @inproceedings{Denz2021, | ![]() |
Rozo*, Leonel; Dave*, Vedant Orientation Probabilistic Movement Primitives on Riemannian Manifolds Conference Conference on Robot Learning, vol. 5, 2021. Abstract | Links | BibTeX | Tags: Manipulation, Probabilistic Movement Primitives, Riemannian Manifolds @conference{Rozo&Dave*2021, Learning complex robot motions necessarily demands to have models that are able to encode and retrieve full-pose trajectories when tasks are defined in operational spaces. Probabilistic movement primitives (ProMPs) stand out as a principled approach that models trajectory distributions learned from demonstrations. ProMPs allow for trajectory modulation and blending to achieve better generalization to novel situations. However, when ProMPs are employed in operational space, their original formulation does not directly apply to full-pose movements including rotational trajectories described by quaternions. This paper proposes a Riemannian formulation of ProMPs that enables encoding and retrieving of quaternion trajectories. Our method builds on Riemannian manifold theory, and exploits multilinear geodesic regression for estimating the ProMPs parameters. This novel approach makes ProMPs a suitable model for learning complex full-pose robot motion patterns. Riemannian ProMPs are tested on toy examples to illustrate their workflow, and on real learning-from-demonstration experiments. | ![]() |
Rottmann, N.; Denz, R.; Bruder, R.; Rueckert, E. Probabilistic Approach for Complete Coverage Path Planning with low-cost Systems Inproceedings In: European Conference on Mobile Robots (ECMR 2021), 2021. Links | BibTeX | Tags: mobile navigation, Probabilistic Inference @inproceedings{Rottmann2021, | ![]() |
Xue, Honghu; Herzog, Rebecca; Berger, Till M.; Bäumer, Tobias; Weissbach, Anne; Rueckert, Elmar Using Probabilistic Movement Primitives in analyzing human motion differences under Transcranial Current Stimulation Journal Article In: Frontiers in Robotics and AI , vol. 8, 2021, ISSN: 2296-9144. Abstract | Links | BibTeX | Tags: Finger Tapping Motion, Human motion analysis, machine learning, Probabilistic Movement Primitives, Transcranial current stimulation @article{Rueckert2021, In medical tasks such as human motion analysis, computer-aided auxiliary systems have become preferred choice for human experts for its high efficiency. However, conventional approaches are typically based on user-defined features such as movement onset times, peak velocities, motion vectors or frequency domain analyses. Such approaches entail careful data post-processing or specific domain knowledge to achieve a meaningful feature extraction. Besides, they are prone to noise and the manual-defined features could hardly be re-used for other analyses. In this paper, we proposed probabilistic movement primitives(ProMPs), a widely-used approach in robot skill learning, to model human motions. The benefit of ProMPs is that the features are directly learned from the data and ProMPs can capture important features describing the trajectory shape, which can easily be extended to other tasks. Distinct from previous research, where classification tasks are mostly investigated, we applied ProMPs together with a variant of Kullback-Leibler (KL) divergence to quantify the effect of different transcranial current stimulation methods on human motions. We presented an initial result with10participants. The results validate ProMPs as a robust and effective feature extractor for human motions. | ![]() |
Tanneberg, Daniel; Ploeger, Kai; Rueckert, Elmar; Peters, Jan SKID RAW: Skill Discovery from Raw Trajectories Journal Article In: IEEE Robotics and Automation Letters (RA-L), pp. 1–8, 2021, ISSN: 2377-3766, (© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.). Links | BibTeX | Tags: Manipulation, movement primitives, Probabilistic Inference @article{Tanneberg2021, | ![]() |
Jamsek, Marko; Kunavar, Tjasa; Bobek, Urban; Rueckert, Elmar; Babic, Jan Predictive exoskeleton control for arm-motion augmentation based on probabilistic movement primitives combined with a flow controller Journal Article In: IEEE Robotics and Automation Letters (RA-L), pp. 1–8, 2021, ISSN: 2377-3766, (© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.). Links | BibTeX | Tags: human motor control, movement primitives @article{Jamsek2021, | ![]() |
Cansev, Mehmet Ege; Xue, Honghu; Rottmann, Nils; Bliek, Adna; Miller, Luke E.; Rueckert, Elmar; Beckerle, Philipp Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience Journal Article In: Advanced Intelligent Systems, pp. 1–28, 2021. Links | BibTeX | Tags: human motor control, intrinsic motivation, movement primitives, Probabilistic Inference, Reinforcement Learning, spiking @article{Cansev2021, | ![]() |
2020 |
|
M Tuluhan ; Oztop Akbulut, Erhan ; Seker 2020. Abstract | Links | BibTeX | Tags: Deep Learning, movement primitives, Transfer Learning @conference{nokey, To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions. | ![]() |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Exploiting Chlorophyll Fluorescense for Building Robust low-Cost Mowing Area Detectors Inproceedings In: IEEE SENSORS , pp. 1–4, 2020. Links | BibTeX | Tags: mobile navigation, smart sensors @inproceedings{Rottmann2020b, | ![]() |
Rottmann, N.; Kunavar, T.; Babič, J.; Peters, J.; Rueckert, E. Learning Hierarchical Acquisition Functions for Bayesian Optimization Inproceedings In: International Conference on Intelligent Robots and Systems (IROS’ 2020), 2020. Links | BibTeX | Tags: Reinforcement Learning @inproceedings{Rottmann2020HiBO, | ![]() |
Rottmann, N.; Bruder, R.; Xue, H.; Schweikard, A.; Rueckert, E. Parameter Optimization for Loop Closure Detection in Closed Environments Inproceedings In: Workshop Paper at the International Conference on Intelligent Robots and Systems (IROS), pp. 1–8, 2020. Links | BibTeX | Tags: mobile navigation, Reinforcement Learning @inproceedings{Rottmann2020c, | ![]() |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. A novel Chlorophyll Fluorescence based approach for Mowing Area Classification Journal Article In: IEEE Sensors Journal, 2020. Links | BibTeX | Tags: mobile navigation, smart sensors @article{Rottmann2020d, | ![]() |
Tanneberg, Daniel; Rueckert, Elmar; Peters, Jan Evolutionary training and abstraction yields algorithmic generalization of neural computers Journal Article In: Nature Machine Intelligence, pp. 1–11, 2020. Links | BibTeX | Tags: neural network, Reinforcement Learning, Transfer Learning @article{Tanneberg2020, | ![]() |
Tolga-Can Çallar, Elmar Rueckert; Böttger, Sven Efficient Body Registration Using Single-View Range Imaging and Generic Shape Templates Inproceedings In: 54th Annual Conference of the German Society for Biomedical Engineering (BMT 2020), 2020. Links | BibTeX | Tags: Medical Robotics @inproceedings{Çallar2020, | ![]() |
Xue, H.; Boettger, S.; Rottmann, N.; Pandya, H.; Bruder, R.; Neumann, G.; Schweikard, A.; Rueckert, E. Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks Inproceedings In: International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI’ 2020), 2020. Links | BibTeX | Tags: Manipulation, Reinforcement Learning @inproceedings{Xue2020, | ![]() |
Cartoni, E.; Mannella, F.; Santucci, V. G.; Triesch, J.; Rueckert, E.; Baldassarre, G. REAL-2019: Robot open-Ended Autonomous Learning competition Journal Article In: Proceedings of Machine Learning Research, vol. 123, pp. 142-152, 2020, (NeurIPS 2019 Competition and Demonstration Track). Links | BibTeX | Tags: Manipulation, Simulation @article{Cartoni2020, | ![]() |
2019 |
|
Stark, Svenja; Peters, Jan; Rueckert, Elmar Experience Reuse with Probabilistic Movement Primitives Inproceedings In: Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2019., 2019. Links | BibTeX | Tags: movement primitives, Reinforcement Learning, Transfer Learning @inproceedings{Stark2019, | ![]() |
Boettger, S.; Callar, T. C.; Schweikard, A.; Rueckert, E. Medical robotics simulation framework for application-specific optimal kinematics Inproceedings In: Current Directions in Biomedical Engineering 2019, pp. 1–5, 2019. Links | BibTeX | Tags: Medical Robotics @inproceedings{Boettger2019, | ![]() |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Loop Closure Detection in Closed Environments Inproceedings In: European Conference on Mobile Robots (ECMR 2019), 2019, ISBN: 978-1-7281-3605-9. Links | BibTeX | Tags: mobile navigation @inproceedings{Rottmann2019b, | ![]() |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Cataglyphis ant navigation strategies solve the global localization problem in robots with binary sensors Inproceedings In: Proceedings of International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS), Prague, Czech Republic , 2019, ( February 22-24, 2019). Links | BibTeX | Tags: constraint optimization, mobile navigation, Simulation @inproceedings{Rottmann2019, | ![]() |
Rueckert, Elmar; Jauer, Philipp; Derksen, Alexander; Schweikard, Achim Dynamic Control Strategies for Cable-Driven Master Slave Robots Inproceedings In: Keck, Tobias (Ed.): Proceedings on Minimally Invasive Surgery, Luebeck, Germany, 2019, (January 24-25, 2019). Links | BibTeX | Tags: Medical Robotics, Reinforcement Learning @inproceedings{Rueckert2019c, | ![]() |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks Journal Article In: Neural Networks – Elsevier, vol. 109, pp. 67-80, 2019, ISBN: 0893-6080, (Impact Factor of 7.197 (2017)). Links | BibTeX | Tags: neural network, Probabilistic Inference, RNN, spiking @article{Tanneberg2019, | ![]() |
2018 |
|
Gondaliya, Kaushikkumar D.; Peters, Jan; Rueckert, Elmar Learning to Categorize Bug Reports with LSTM Networks Inproceedings In: Proceedings of the International Conference on Advances in System Testing and Validation Lifecycle (VALID)., pp. 6, XPS (Xpert Publishing Services), Nice, France, 2018, ISBN: 978-1-61208-671-2, ( October 14-18, 2018). Links | BibTeX | Tags: Natural Language Processing, neural network, RNN @inproceedings{Gondaliya2018, | ![]() |
Sosic, Adrian; Zoubir, Abdelhak M.; Rueckert, Elmar; Peters, Jan; Koeppl, Heinz Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling Journal Article In: Journal of Machine Learning Research (JMLR), vol. 19, no. 69, pp. 1-45, 2018. Links | BibTeX | Tags: movement primitives, Probabilistic Inference, Simulation @article{Sosic2018, | ![]() |
Paraschos, Alexandros; Rueckert, Elmar; Peters, Jan; Neumann, Gerhard Probabilistic Movement Primitives under Unknown System Dynamics Journal Article In: Advanced Robotics (ARJ), vol. 32, no. 6, pp. 297-310, 2018. Links | BibTeX | Tags: inverse dynamics, model learning, movement primitives @article{Paraschos2018, | ![]() |
2017 |
|
Rueckert, Elmar; Nakatenus, Moritz; Tosatto, Samuele; Peters, Jan Learning Inverse Dynamics Models in O(n) time with LSTM networks Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. Links | BibTeX | Tags: inverse dynamics, model learning, RNN @inproceedings{Humanoids2017Rueckert, | ![]() |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Efficient Online Adaptation with Stochastic Recurrent Neural Networks Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. Links | BibTeX | Tags: intrinsic motivation, RNN, spiking @inproceedings{Tanneberg2017a, | ![]() |
Stark, Svenja; Peters, Jan; Rueckert, Elmar A Comparison of Distance Measures for Learning Nonparametric Motor Skill Libraries Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. Links | BibTeX | Tags: intrinsic motivation, movement primitives @inproceedings{Humanoids2017Stark, | ![]() |
Thiem, Simon; Stark, Svenja; Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Simulation of the underactuated Sake Robotics Gripper in V-REP Inproceedings In: Workshop at the International Conference on Humanoid Robots (HUMANOIDS), 2017. Links | BibTeX | Tags: Manipulation, Simulation @inproceedings{Thiem2017b, | ![]() |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals Inproceedings In: Proceedings of the Conference on Robot Learning (CoRL), 2017. Links | BibTeX | Tags: intrinsic motivation, RNN, spiking @inproceedings{Tanneberg2017, | ![]() |
2016 |
|
Tanneberg, Daniel; Paraschos, Alexandros; Peters, Jan; Rueckert, Elmar Deep Spiking Networks for Model-based Planning in Humanoids Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2016. Links | BibTeX | Tags: model learning, RNN, spiking @inproceedings{tanneberg_humanoids16, | ![]() |
Azad, Morteza; Ortenzi, Valerio; Lin, Hsiu-Chin; Rueckert, Elmar; Mistry, Michael Model Estimation and Control of Complaint Contact Normal Force Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2016. Links | BibTeX | Tags: constraint optimization, human motor control, inverse dynamics, model learning @inproceedings{Humanoids2016Azad, | ![]() |
Rueckert, Elmar; Camernik, Jernej; Peters, Jan; Babic, Jan Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control Journal Article In: Nature Publishing Group: Scientific Reports, vol. 6, no. 28455, 2016. Links | BibTeX | Tags: human motor control, muscle synergies, postural control @article{Rueckert2016b, | ![]() |
Rueckert, Elmar; Kappel, David; Tanneberg, Daniel; Pecevski, Dejan; Peters, Jan Recurrent Spiking Networks Solve Planning Tasks Journal Article In: Nature Publishing Group: Scientific Reports, vol. 6, no. 21142, 2016. Links | BibTeX | Tags: RNN, spiking @article{Rueckert2016a, | ![]() |
Kohlschuetter, Jan; Peters, Jan; Rueckert, Elmar Learning Probabilistic Features from EMG Data for Predicting Knee Abnormalities Inproceedings In: Proceedings of the XIV Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON), 2016. Links | BibTeX | Tags: graphical models, muscle synergies @inproceedings{Kohlschuetter2016, | ![]() |
Modugno, Valerio; Neumann, Gerhard; Rueckert, Elmar; Oriolo, Giuseppe; Peters, Jan; Ivaldi, Serena Learning soft task priorities for control of redundant robots Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2016. Links | BibTeX | Tags: constraint optimization, policy search @inproceedings{Modugno_PICRA_2016, | ![]() |
Sharma, David; Tanneberg, Daniel; Grosse-Wentrup, Moritz; Peters, Jan; Rueckert, Elmar Adaptive Training Strategies for BCIs Inproceedings In: Cybathlon Symposium, 2016. Links | BibTeX | Tags: human motor control, Reinforcement Learning @inproceedings{Sharma2016, | ![]() |
Weber, Paul; Rueckert, Elmar; Calandra, Roberto; Peters, Jan; Beckerle, Philipp In: Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2016. Links | BibTeX | Tags: graphical models @inproceedings{ROMANS16_daglove, | ![]() |
2015 |
|
Calandra, Roberto; Ivaldi, Serena; Deisenroth, Marc; Rueckert, Elmar; Peters, Jan Learning Inverse Dynamics Models with Contacts Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2015. Links | BibTeX | Tags: inverse dynamics, model learning, neural network @inproceedings{Calandra2015, | ![]() |
Rueckert, Elmar; Mundo, Jan; Paraschos, Alexandros; Peters, Jan; Neumann, Gerhard Extracting Low-Dimensional Control Variables for Movement Primitives Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2015. Links | BibTeX | Tags: movement primitives, Probabilistic Inference @inproceedings{Rueckert2015, | ![]() |
Paraschos, Alexandros; Rueckert, Elmar; Peters, Jan; Neumann, Gerhard Model-Free Probabilistic Movement Primitives for Physical Interaction Inproceedings In: Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2015. Links | BibTeX | Tags: inverse dynamics, movement primitives @inproceedings{Paraschos2015, | ![]() |
Rueckert, Elmar; Lioutikov, Rudolf; Calandra, Roberto; Schmidt, Marius; Beckerle, Philipp; Peters, Jan Low-cost Sensor Glove with Force Feedback for Learning from Demonstrations using Probabilistic Trajectory Representations Inproceedings In: ICRA 2015 Workshop on Tactile and force sensing for autonomous compliant intelligent robots, 2015. Links | BibTeX | Tags: graphical models @inproceedings{Rueckert2015b, | ![]() |
2014 |
|
Rueckert, Elmar Biologically inspired motor skill learning in robotics through probabilistic inference PhD Thesis Technical University Graz, 2014. Links | BibTeX | Tags: graphical models, locomotion, model learning, morphological compuation, movement primitives, policy search, postural control, Probabilistic Inference, Reinforcement Learning, RNN, SOC, spiking @phdthesis{Rueckert2014a, | ![]() |
Rueckert, Elmar; Mindt, Max; Peters, Jan; Neumann, Gerhard Robust Policy Updates for Stochastic Optimal Control Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2014. Links | BibTeX | Tags: policy search, Probabilistic Inference, SOC @inproceedings{Rueckert2014, | ![]() |
2013 |
|
Rueckert, Elmar; d’Avella, Andrea Learned parametrized dynamic movement primitives with shared synergies for controlling robotic and musculoskeletal systems Journal Article In: Frontiers in Computational Neuroscience, vol. 7, no. 138, 2013. Links | BibTeX | Tags: locomotion, movement primitives, muscle synergies @article{Rueckert2013b, | ![]() |
Rueckert, Elmar; Neumann, Gerhard; Toussaint, Marc; Maass, Wolfgang Learned graphical models for probabilistic planning provide a new class of movement primitives Journal Article In: Frontiers in Computational Neuroscience, vol. 6, no. 97, 2013. Links | BibTeX | Tags: graphical models, movement primitives, Probabilistic Inference @article{Rueckert2013, | ![]() |
Rueckert, Elmar; d’Avella, Andrea Learned Muscle Synergies as Prior in Dynamical Systems for Controlling Bio-mechanical and Robotic Systems Inproceedings In: Abstracts of Neural Control of Movement Conference (NCM), Conference Talk, pp. 27–28, 2013. Links | BibTeX | Tags: muscle synergies, policy search, Reinforcement Learning @inproceedings{Rueckert2013, | ![]() |
2012 |
|
Rueckert, Elmar; Neumann, Gerhard Stochastic Optimal Control Methods for Investigating the Power of Morphological Computation Journal Article In: Artificial Life, vol. 19, no. 1, 2012. Links | BibTeX | Tags: morphological compuation, Probabilistic Inference, SOC @article{Rueckert2012, | ![]() |
2011 |
|
Rueckert, Elmar; Neumann, Gerhard A study of Morphological Computation by using Probabilistic Inference for Motor Planning Inproceedings In: Proceedings of the 2nd International Conference on Morphological Computation (ICMC), pp. 51–53, 2011. Links | BibTeX | Tags: graphical models, morphological compuation, Probabilistic Inference, SOC @inproceedings{Rueckert2011, | ![]() |
2010 |
|
Rueckert, Elmar Simultaneous localisation and mapping for mobile robots with recent sensor technologies Masters Thesis Technical University Graz, 2010. Links | BibTeX | Tags: Probabilistic Inference @mastersthesis{Rueckert2010, | ![]() |
Compact List without Images
Journal Articles |
Xue, Honghu; Hein, Benedikt; Bakr, Mohamed; Schildbach, Georg; Abel, Bengt; Rueckert, Elmar Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics Journal Article In: Applied Sciences (MDPI), Special Issue on Intelligent Robotics, 2022, (Supplement: https://cloud.cps.unileoben.ac.at/index.php/s/Sj68rQewnkf4ppZ). @article{Xue2022, We propose a deep reinforcement learning approach for solving a mapless navigation problem in warehouse scenarios. The automatic guided vehicle is equipped with LiDAR and frontal RGB sensors and learns to reach underneath the target dolly. The challenges reside in the sparseness of positive samples for learning, multi-modal sensor perception with partial observability, the demand for accurate steering maneuvers together with long training cycles. To address these points, we proposed NavACL-Q as an automatic curriculum learning together with distributed soft actor-critic. The performance of the learning algorithm is evaluated exhaustively in a different warehouse environment to check both robustness and generalizability of the learned policy. Results in NVIDIA Isaac Sim demonstrates that our trained agent significantly outperforms the map-based navigation pipeline provided by NVIDIA Isaac Sim in terms of higher agent-goal distances and relative orientations. The ablation studies also confirmed that NavACL-Q greatly facilitates the whole learning process and a pre-trained feature extractor manifestly boosts the training speed. |
Xue, Honghu; Herzog, Rebecca; Berger, Till M.; Bäumer, Tobias; Weissbach, Anne; Rueckert, Elmar Using Probabilistic Movement Primitives in analyzing human motion differences under Transcranial Current Stimulation Journal Article In: Frontiers in Robotics and AI , vol. 8, 2021, ISSN: 2296-9144. @article{Rueckert2021, In medical tasks such as human motion analysis, computer-aided auxiliary systems have become preferred choice for human experts for its high efficiency. However, conventional approaches are typically based on user-defined features such as movement onset times, peak velocities, motion vectors or frequency domain analyses. Such approaches entail careful data post-processing or specific domain knowledge to achieve a meaningful feature extraction. Besides, they are prone to noise and the manual-defined features could hardly be re-used for other analyses. In this paper, we proposed probabilistic movement primitives(ProMPs), a widely-used approach in robot skill learning, to model human motions. The benefit of ProMPs is that the features are directly learned from the data and ProMPs can capture important features describing the trajectory shape, which can easily be extended to other tasks. Distinct from previous research, where classification tasks are mostly investigated, we applied ProMPs together with a variant of Kullback-Leibler (KL) divergence to quantify the effect of different transcranial current stimulation methods on human motions. We presented an initial result with10participants. The results validate ProMPs as a robust and effective feature extractor for human motions. |
Tanneberg, Daniel; Ploeger, Kai; Rueckert, Elmar; Peters, Jan SKID RAW: Skill Discovery from Raw Trajectories Journal Article In: IEEE Robotics and Automation Letters (RA-L), pp. 1–8, 2021, ISSN: 2377-3766, (© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.). @article{Tanneberg2021, |
Jamsek, Marko; Kunavar, Tjasa; Bobek, Urban; Rueckert, Elmar; Babic, Jan Predictive exoskeleton control for arm-motion augmentation based on probabilistic movement primitives combined with a flow controller Journal Article In: IEEE Robotics and Automation Letters (RA-L), pp. 1–8, 2021, ISSN: 2377-3766, (© 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.). @article{Jamsek2021, |
Cansev, Mehmet Ege; Xue, Honghu; Rottmann, Nils; Bliek, Adna; Miller, Luke E.; Rueckert, Elmar; Beckerle, Philipp Interactive Human-Robot Skill Transfer: A Review of Learning Methods and User Experience Journal Article In: Advanced Intelligent Systems, pp. 1–28, 2021. @article{Cansev2021, |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. A novel Chlorophyll Fluorescence based approach for Mowing Area Classification Journal Article In: IEEE Sensors Journal, 2020. @article{Rottmann2020d, |
Tanneberg, Daniel; Rueckert, Elmar; Peters, Jan Evolutionary training and abstraction yields algorithmic generalization of neural computers Journal Article In: Nature Machine Intelligence, pp. 1–11, 2020. @article{Tanneberg2020, |
Cartoni, E.; Mannella, F.; Santucci, V. G.; Triesch, J.; Rueckert, E.; Baldassarre, G. REAL-2019: Robot open-Ended Autonomous Learning competition Journal Article In: Proceedings of Machine Learning Research, vol. 123, pp. 142-152, 2020, (NeurIPS 2019 Competition and Demonstration Track). @article{Cartoni2020, |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks Journal Article In: Neural Networks – Elsevier, vol. 109, pp. 67-80, 2019, ISBN: 0893-6080, (Impact Factor of 7.197 (2017)). @article{Tanneberg2019, |
Sosic, Adrian; Zoubir, Abdelhak M.; Rueckert, Elmar; Peters, Jan; Koeppl, Heinz Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling Journal Article In: Journal of Machine Learning Research (JMLR), vol. 19, no. 69, pp. 1-45, 2018. @article{Sosic2018, |
Paraschos, Alexandros; Rueckert, Elmar; Peters, Jan; Neumann, Gerhard Probabilistic Movement Primitives under Unknown System Dynamics Journal Article In: Advanced Robotics (ARJ), vol. 32, no. 6, pp. 297-310, 2018. @article{Paraschos2018, |
Rueckert, Elmar; Camernik, Jernej; Peters, Jan; Babic, Jan Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control Journal Article In: Nature Publishing Group: Scientific Reports, vol. 6, no. 28455, 2016. @article{Rueckert2016b, |
Rueckert, Elmar; Kappel, David; Tanneberg, Daniel; Pecevski, Dejan; Peters, Jan Recurrent Spiking Networks Solve Planning Tasks Journal Article In: Nature Publishing Group: Scientific Reports, vol. 6, no. 21142, 2016. @article{Rueckert2016a, |
Rueckert, Elmar; d’Avella, Andrea Learned parametrized dynamic movement primitives with shared synergies for controlling robotic and musculoskeletal systems Journal Article In: Frontiers in Computational Neuroscience, vol. 7, no. 138, 2013. @article{Rueckert2013b, |
Rueckert, Elmar; Neumann, Gerhard; Toussaint, Marc; Maass, Wolfgang Learned graphical models for probabilistic planning provide a new class of movement primitives Journal Article In: Frontiers in Computational Neuroscience, vol. 6, no. 97, 2013. @article{Rueckert2013, |
Rueckert, Elmar; Neumann, Gerhard Stochastic Optimal Control Methods for Investigating the Power of Morphological Computation Journal Article In: Artificial Life, vol. 19, no. 1, 2012. @article{Rueckert2012, |
Conferences |
Rozo*, Leonel; Dave*, Vedant Orientation Probabilistic Movement Primitives on Riemannian Manifolds Conference Conference on Robot Learning, vol. 5, 2021. @conference{Rozo&Dave*2021, Learning complex robot motions necessarily demands to have models that are able to encode and retrieve full-pose trajectories when tasks are defined in operational spaces. Probabilistic movement primitives (ProMPs) stand out as a principled approach that models trajectory distributions learned from demonstrations. ProMPs allow for trajectory modulation and blending to achieve better generalization to novel situations. However, when ProMPs are employed in operational space, their original formulation does not directly apply to full-pose movements including rotational trajectories described by quaternions. This paper proposes a Riemannian formulation of ProMPs that enables encoding and retrieving of quaternion trajectories. Our method builds on Riemannian manifold theory, and exploits multilinear geodesic regression for estimating the ProMPs parameters. This novel approach makes ProMPs a suitable model for learning complex full-pose robot motion patterns. Riemannian ProMPs are tested on toy examples to illustrate their workflow, and on real learning-from-demonstration experiments. |
M Tuluhan ; Oztop Akbulut, Erhan ; Seker 2020. @conference{nokey, To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL). In this paper, we propose a novel LfD+RL framework, namely Adaptive Conditional Neural Movement Primitives (ACNMP), that allows efficient policy improvement in novel environments and effective skill transfer between different agents. This is achieved through exploiting the latent representation learned by the underlying Conditional Neural Process (CNP) model, and simultaneous training of the model with supervised learning (SL) for acquiring the demonstrated trajectories and via RL for new trajectory discovery. Through simulation experiments, we show that (i) ACNMP enables the system to extrapolate to situations where pure LfD fails; (ii) Simultaneous training of the system through SL and RL preserves the shape of demonstrations while adapting to novel situations due to the shared representations used by both learners; (iii) ACNMP enables order-of-magnitude sample-efficient RL in extrapolation of reaching tasks compared to the existing approaches; (iv) ACNMPs can be used to implement skill transfer between robots having different morphology, with competitive learning speeds and importantly with less number of assumptions compared to the state-of-the-art approaches. Finally, we show the real-world suitability of ACNMPs through real robot experiments that involve obstacle avoidance, pick and place and pouring actions. |
Inproceedings |
Denz, R.; Demirci, R.; Cansev, E.; Bliek, A.; Beckerle, P.; Rueckert, E.; Rottmann, N. A high-accuracy, low-budget Sensor Glove for Trajectory Model Learning Inproceedings In: International Conference on Advanced Robotics , pp. 7, 2021. @inproceedings{Denz2021, |
Rottmann, N.; Denz, R.; Bruder, R.; Rueckert, E. Probabilistic Approach for Complete Coverage Path Planning with low-cost Systems Inproceedings In: European Conference on Mobile Robots (ECMR 2021), 2021. @inproceedings{Rottmann2021, |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Exploiting Chlorophyll Fluorescense for Building Robust low-Cost Mowing Area Detectors Inproceedings In: IEEE SENSORS , pp. 1–4, 2020. @inproceedings{Rottmann2020b, |
Rottmann, N.; Kunavar, T.; Babič, J.; Peters, J.; Rueckert, E. Learning Hierarchical Acquisition Functions for Bayesian Optimization Inproceedings In: International Conference on Intelligent Robots and Systems (IROS’ 2020), 2020. @inproceedings{Rottmann2020HiBO, |
Rottmann, N.; Bruder, R.; Xue, H.; Schweikard, A.; Rueckert, E. Parameter Optimization for Loop Closure Detection in Closed Environments Inproceedings In: Workshop Paper at the International Conference on Intelligent Robots and Systems (IROS), pp. 1–8, 2020. @inproceedings{Rottmann2020c, |
Tolga-Can Çallar, Elmar Rueckert; Böttger, Sven Efficient Body Registration Using Single-View Range Imaging and Generic Shape Templates Inproceedings In: 54th Annual Conference of the German Society for Biomedical Engineering (BMT 2020), 2020. @inproceedings{Çallar2020, |
Xue, H.; Boettger, S.; Rottmann, N.; Pandya, H.; Bruder, R.; Neumann, G.; Schweikard, A.; Rueckert, E. Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks Inproceedings In: International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI’ 2020), 2020. @inproceedings{Xue2020, |
Stark, Svenja; Peters, Jan; Rueckert, Elmar Experience Reuse with Probabilistic Movement Primitives Inproceedings In: Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2019., 2019. @inproceedings{Stark2019, |
Boettger, S.; Callar, T. C.; Schweikard, A.; Rueckert, E. Medical robotics simulation framework for application-specific optimal kinematics Inproceedings In: Current Directions in Biomedical Engineering 2019, pp. 1–5, 2019. @inproceedings{Boettger2019, |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Loop Closure Detection in Closed Environments Inproceedings In: European Conference on Mobile Robots (ECMR 2019), 2019, ISBN: 978-1-7281-3605-9. @inproceedings{Rottmann2019b, |
Rottmann, N.; Bruder, R.; Schweikard, A.; Rueckert, E. Cataglyphis ant navigation strategies solve the global localization problem in robots with binary sensors Inproceedings In: Proceedings of International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS), Prague, Czech Republic , 2019, ( February 22-24, 2019). @inproceedings{Rottmann2019, |
Rueckert, Elmar; Jauer, Philipp; Derksen, Alexander; Schweikard, Achim Dynamic Control Strategies for Cable-Driven Master Slave Robots Inproceedings In: Keck, Tobias (Ed.): Proceedings on Minimally Invasive Surgery, Luebeck, Germany, 2019, (January 24-25, 2019). @inproceedings{Rueckert2019c, |
Gondaliya, Kaushikkumar D.; Peters, Jan; Rueckert, Elmar Learning to Categorize Bug Reports with LSTM Networks Inproceedings In: Proceedings of the International Conference on Advances in System Testing and Validation Lifecycle (VALID)., pp. 6, XPS (Xpert Publishing Services), Nice, France, 2018, ISBN: 978-1-61208-671-2, ( October 14-18, 2018). @inproceedings{Gondaliya2018, |
Rueckert, Elmar; Nakatenus, Moritz; Tosatto, Samuele; Peters, Jan Learning Inverse Dynamics Models in O(n) time with LSTM networks Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. @inproceedings{Humanoids2017Rueckert, |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Efficient Online Adaptation with Stochastic Recurrent Neural Networks Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. @inproceedings{Tanneberg2017a, |
Stark, Svenja; Peters, Jan; Rueckert, Elmar A Comparison of Distance Measures for Learning Nonparametric Motor Skill Libraries Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2017. @inproceedings{Humanoids2017Stark, |
Thiem, Simon; Stark, Svenja; Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Simulation of the underactuated Sake Robotics Gripper in V-REP Inproceedings In: Workshop at the International Conference on Humanoid Robots (HUMANOIDS), 2017. @inproceedings{Thiem2017b, |
Tanneberg, Daniel; Peters, Jan; Rueckert, Elmar Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals Inproceedings In: Proceedings of the Conference on Robot Learning (CoRL), 2017. @inproceedings{Tanneberg2017, |
Tanneberg, Daniel; Paraschos, Alexandros; Peters, Jan; Rueckert, Elmar Deep Spiking Networks for Model-based Planning in Humanoids Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2016. @inproceedings{tanneberg_humanoids16, |
Azad, Morteza; Ortenzi, Valerio; Lin, Hsiu-Chin; Rueckert, Elmar; Mistry, Michael Model Estimation and Control of Complaint Contact Normal Force Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2016. @inproceedings{Humanoids2016Azad, |
Kohlschuetter, Jan; Peters, Jan; Rueckert, Elmar Learning Probabilistic Features from EMG Data for Predicting Knee Abnormalities Inproceedings In: Proceedings of the XIV Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON), 2016. @inproceedings{Kohlschuetter2016, |
Modugno, Valerio; Neumann, Gerhard; Rueckert, Elmar; Oriolo, Giuseppe; Peters, Jan; Ivaldi, Serena Learning soft task priorities for control of redundant robots Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2016. @inproceedings{Modugno_PICRA_2016, |
Sharma, David; Tanneberg, Daniel; Grosse-Wentrup, Moritz; Peters, Jan; Rueckert, Elmar Adaptive Training Strategies for BCIs Inproceedings In: Cybathlon Symposium, 2016. @inproceedings{Sharma2016, |
Weber, Paul; Rueckert, Elmar; Calandra, Roberto; Peters, Jan; Beckerle, Philipp In: Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2016. @inproceedings{ROMANS16_daglove, |
Calandra, Roberto; Ivaldi, Serena; Deisenroth, Marc; Rueckert, Elmar; Peters, Jan Learning Inverse Dynamics Models with Contacts Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2015. @inproceedings{Calandra2015, |
Rueckert, Elmar; Mundo, Jan; Paraschos, Alexandros; Peters, Jan; Neumann, Gerhard Extracting Low-Dimensional Control Variables for Movement Primitives Inproceedings In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2015. @inproceedings{Rueckert2015, |
Paraschos, Alexandros; Rueckert, Elmar; Peters, Jan; Neumann, Gerhard Model-Free Probabilistic Movement Primitives for Physical Interaction Inproceedings In: Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2015. @inproceedings{Paraschos2015, |
Rueckert, Elmar; Lioutikov, Rudolf; Calandra, Roberto; Schmidt, Marius; Beckerle, Philipp; Peters, Jan Low-cost Sensor Glove with Force Feedback for Learning from Demonstrations using Probabilistic Trajectory Representations Inproceedings In: ICRA 2015 Workshop on Tactile and force sensing for autonomous compliant intelligent robots, 2015. @inproceedings{Rueckert2015b, |
Rueckert, Elmar; Mindt, Max; Peters, Jan; Neumann, Gerhard Robust Policy Updates for Stochastic Optimal Control Inproceedings In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2014. @inproceedings{Rueckert2014, |
Rueckert, Elmar; d’Avella, Andrea Learned Muscle Synergies as Prior in Dynamical Systems for Controlling Bio-mechanical and Robotic Systems Inproceedings In: Abstracts of Neural Control of Movement Conference (NCM), Conference Talk, pp. 27–28, 2013. @inproceedings{Rueckert2013, |
Rueckert, Elmar; Neumann, Gerhard A study of Morphological Computation by using Probabilistic Inference for Motor Planning Inproceedings In: Proceedings of the 2nd International Conference on Morphological Computation (ICMC), pp. 51–53, 2011. @inproceedings{Rueckert2011, |
Masters Theses |
Rueckert, Elmar Simultaneous localisation and mapping for mobile robots with recent sensor technologies Masters Thesis Technical University Graz, 2010. @mastersthesis{Rueckert2010, |
PhD Theses |
Rueckert, Elmar Biologically inspired motor skill learning in robotics through probabilistic inference PhD Thesis Technical University Graz, 2014. @phdthesis{Rueckert2014a, |