no code implementations • 15 Mar 2024 • Max Braun, Noémie Jaquier, Leonel Rozo, Tamim Asfour
We introduce Riemannian Flow Matching Policies (RFMP), a novel model for learning and synthesizing robot visuomotor policies.
no code implementations • 17 Jan 2024 • Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Nadia Figueroa, Gerhard Neumann, Leonel Rozo
Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions.
no code implementations • 11 Oct 2023 • Noémie Jaquier, Leonel Rozo, Tamim Asfour
In the realm of robotics, numerous downstream robotics tasks leverage machine learning methods for processing, modeling, or synthesizing data.
no code implementations • 6 Nov 2022 • Jiechao Zhang, Hadi Beik-Mohammadi, Leonel Rozo
This is challenging as the robot state does not evolve on a Euclidean space, and therefore the stability guarantees and vector field encoding need to account for the geometry arising from, for example, the orientation representation.
no code implementations • 4 Oct 2022 • Noémie Jaquier, Leonel Rozo, Miguel González-Duque, Viacheslav Borovitskiy, Tamim Asfour
This may be attributed to the lack of computational models that fill the gap between the discrete hierarchical structure of the taxonomy and the high-dimensional heterogeneous data associated to its categories.
no code implementations • 15 Mar 2022 • Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo
We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills.
1 code implementation • 2 Nov 2021 • Noémie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, Leonel Rozo
Bayesian optimization is a data-efficient technique which can be used for control parameter tuning, parametric policy adaptation, and structure design in robotics.
no code implementations • 28 Oct 2021 • Leonel Rozo, Vedant Dave
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.
no code implementations • 8 Jun 2021 • Hadi Beik-Mohammadi, Søren Hauberg, Georgios Arvanitidis, Gerhard Neumann, Leonel Rozo
For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly.
1 code implementation • NeurIPS 2020 • Noémie Jaquier, Leonel Rozo
Despite the recent success of Bayesian optimization (BO) in a variety of applications where sample efficiency is imperative, its performance may be seriously compromised in settings characterized by high-dimensional parameter spaces.
no code implementations • 24 Aug 2020 • Leonel Rozo, Meng Guo, Andras G. Kupcsik, Marco Todescato, Philipp Schillinger, Markus Giftthaler, Matthias Ochs, Markus Spies, Nicolai Waniek, Patrick Kesper, Mathias Büerger
Furthermore, to accomplish complex manipulation tasks, robots should be able to sequence several skills and adapt them to changing situations.
no code implementations • 11 Oct 2019 • Noémie Jaquier, Leonel Rozo, Sylvain Calinon, Mathias Bürger
Bayesian optimization (BO) recently became popular in robotics to optimize control parameters and parametric policies in direct reinforcement learning due to its data efficiency and gradient-free approach.
no code implementations • 20 Aug 2019 • Leonel Rozo
Flexible manufacturing processes demand robots to easily adapt to changes in the environment and interact with humans.
1 code implementation • 23 May 2019 • Domingo Esteban, Leonel Rozo, Darwin G. Caldwell
Moreover, such composition of individual policies is usually performed sequentially, which is not suitable for tasks that require to perform the subtasks concurrently.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • 5 Mar 2019 • João Silvério, Yanlong Huang, Fares J. Abu-Dakka, Leonel Rozo, Darwin G. Caldwell
This rich set of information is used in combination with optimal controller fusion to learn actions from data, with two main advantages: i) robots become safe when uncertain about their actions and ii) they are able to leverage partial demonstrations, given as elementary sub-tasks, to optimally perform a higher level, more complex task.
no code implementations • 19 Dec 2017 • João Silvério, Yanlong Huang, Leonel Rozo, Sylvain Calinon, Darwin G. Caldwell
When learning skills from demonstrations, one is often required to think in advance about the appropriate task representation (usually in either operational or configuration space).