João Silvério

I am a researcher and the group leader of the Interactive Skill Learning group at the German Aerospace Center (DLR).

Prior to joining DLR I spent 5 years at IIT in Genova, Italy, where I got my PhD in 2017, and 2.5 years in Switzerland, at the Idiap Research Institute, as a postdoc.

My research focuses primarily on efficient robot skill acquisition via imitation and reinforcement learning. I investigate compact skill representations which leverage prior knowledge in the form of object poses, geometries and uncertainties to achieve data-efficient learning and generalization.

Email / Bio / Google Scholar / YouTube / Github

News

12/8/24 - Excited to announce that our paper "An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks" has won the Best Paper Award in Empirical Resourcefulness in RL at RLC'24!
16/5/24 - Our joint effort led by DeepMind "Open X-Embodiment: Robotic learning datasets and RT-X models" has just won the Best Conference Paper Award at ICRA'24!
15/5/24 - Our work "An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks" has been accepted for publication at the Reinforcement Learning Conference (RLC) 2024!
20/4/24 - New paper "Guiding real-world reinforcement learning for in-contact manipulation tasks with Shared Control Templates" accepted at AuRo!
23/3/24 - Our paper "A probabilistic approach to multi-modal adaptive virtual fixtures" has been accepted at RA-L!
29/1/24 - Two papers accepted at ICRA'24! More details in the list below.
21/9/23 - Happy to share that our work "Probabilistic learning and adaptation of shared control skills for assistive robots" has received the Best Late Breaking Results Poster Award at HFR'23!
8/5/23 - ICRA'23 paper presentations available on Infovaya, see them here and here.
17/1/23 - Two papers accepted at ICRA'23! (see list of publications below)

Publications

	An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks A. Raffin, O. Sigaud, J. Kober, A. Albu-Schaeffer, J. Silvério, F. Stulp Reinforcement Learning Conference (RLC), 2024 Best Paper Award in Empirical Resourcefulness in RL
	Guiding real-world reinforcement learning for in-contact manipulation tasks with Shared Control Templates A. Padalkar, G. Quere, A. Raffin, J. Silvério, F. Stulp Autonomous Robots (AuRo), 2024
	A probabilistic approach to multi-modal adaptive virtual fixtures M. Mühlbauer, T. Hulin, B. Weber, S. Calinon, F. Stulp, A. Albu-Schäffer, J. Silvério IEEE Robotics and Automation Letters (RA-L), 2024
	A probabilistic approach for learning and adapting shared control skills with the human in the loop G. Quere, F. Stulp, D. Filliat, J. Silvério IEEE International Conference on Robotics and Automation (ICRA), 2024
	Open X-Embodiment: Robotic learning datasets and RT-X models Open X-Embodiment Collaboration IEEE International Conference on Robotics and Automation (ICRA), 2024 https://robotics-transformer-x.github.io/ Best Conference Paper Award Best Paper Award in Robot Manipulation Finalist Best Student Paper Award Finalist
	Probabilistic learning and adaptation of shared control skills for assistive robots G. Quere, F. Stulp, D. Filliat, J. Silvério 16th International Workshop on Human-friendly Robotics (HFR), 2023 Best Late-breaking Results Poster Award
	A non-parametric skill representation with soft null space projectors for fast generalization J. Silvério, Y. Huang IEEE International Conference on Robotics and Automation (ICRA), 2023
	Guiding reinforcement learning with shared control templates A. Padalkar, G. Quere, F. Steinmetz, A. Raffin, M. Nieuwenhuisen, J. Silvério, F. Stulp IEEE International Conference on Robotics and Automation (ICRA), 2023
	Mixture of experts on Riemannian manifolds for visual-servoing fixtures M. Mühlbauer, F. Stulp, A. Albu-Schäffer, J. Silvério IROS'22 Workshop "Probabilistic Robotics in the Age of Deep Learning", 2022
	Bilateral teleoperation with object-adaptive mapping X. Gao, J. Silvério, S. Calinon, M. Li, X. Xiao Complex & Intelligent Systems, 2021
	A probabilistic framework for learning geometry-based robot manipulation skills F.J. Abu-Dakka, Y. Huang, J. Silvério, V. Kyrki Robotics and Autonomous Systems (RAS), 2021
	A laser-based dual-arm system for precise control of collaborative robots J. Silvério, G. Clivaz, S. Calinon IEEE International Conference on Robotics and Automation (ICRA), 2021
	Ergodic exploration using tensor train: applications in insertion tasks S. Shetty, J. Silvério, S. Calinon IEEE Transactions on Robotics (T-RO), 2021
	Motion mappings for continuous bilateral teleoperation X. Gao, J. Silvério, E. Pignat, S. Calinon, M. Li, X. Xiao IEEE Robotics and Automation Letters (RA-L), 2021
	Learning from demonstration using products of experts: applications to manipulation and task prioritization E. Pignat, J. Silvério, S. Calinon International Journal of Robotics Research (IJRR), 2021
	Towards orientation learning and adaptation in Cartesian space Y. Huang, F.J. Abu-Dakka, J. Silvério, D.G. Caldwell IEEE Transactions on Robotics (T-RO), 2020
	Fourier movement primitives: an approach for learning rhythmic robot skills from demonstrations T. Kulak, J. Silvério, S. Calinon Robotics: Science and Systems (R:SS), 2020
	Uncertainty-aware imitation learning using kernelized movement primitives J. Silvério, Y. Huang, F.J. Abu-Dakka, L. Rozo, D.G. Caldwell IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
	Kernelized movement primitives Y. Huang, L. Rozo, J. Silvério, D.G. Caldwell International Journal of Robotics Research (IJRR), 2019
	Generalized orientation learning in robot task space Y. Huang, F.J. Abu-Dakka,, J. Silvério, D.G. Caldwell IEEE International Conference on Robotics and Automation (ICRA), 2019
	Non-parametric imitation learning of robot motor skills Y. Huang, L. Rozo, J. Silvério, D.G. Caldwell IEEE International Conference on Robotics and Automation (ICRA), 2019
	Learning Task Priorities from Demonstrations J. Silvério, S. Calinon, L. Rozo, D.G. Caldwell IEEE Transactions on Robotics (T-RO), 2019
	Towards minimal intervention control with competing constraints Y. Huang, J. Silvério, D.G. Caldwell IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
	An uncertainty-aware minimal intervention control strategy learned from demonstrations J. Silvério, Y. Huang, L. Rozo, D.G. Caldwell IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
	Probabilistic learning of torque controllers from kinematic and force constraints J. Silvério, Y. Huang, L. Rozo, S. Calinon, D.G. Caldwell IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
	Hybrid probabilistic trajectory optimization using null-space exploration Y. Huang, J. Silvério, L. Rozo, D.G. Caldwell IEEE International Conference on Robotics and Automation (ICRA), 2018
	Generalized task-parameterized skill learning Y. Huang, J. Silvério, L. Rozo, D.G. Caldwell IEEE International Conference on Robotics and Automation (ICRA), 2018
	Bimanual skill learning with pose and joint space constraints J. Silvério, S. Calinon, L. Rozo, D.G. Caldwell IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2018
	An approach for imitation learning on Riemannian manifolds M. Zeestraten, I. Havoutis, J. Silvério, S. Calinon, D.G. Caldwell IEEE Robotics and Automation Letters, 2017
	Exploiting interaction dynamics for learning collaborative robot behaviors L. Rozo, J. Silvério, S. Calinon, D.G. Caldwell IJCAI'16 Workshop "Interactive Machine Learning", 2016
	Learning controllers for reactive and proactive behaviors in human-robot collaboration L. Rozo, J. Silvério, S. Calinon, D.G. Caldwell Frontiers in Robotics and AI, 2016
	Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems J. Silvério, L. Rozo, S. Calinon, D.G. Caldwell IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015

Forked from https://jonbarron.info/.