Zobrazeno 1 - 10
of 703
pro vyhledávání: '"Jaquier, A."'
Autor:
Anne, Timothée, Syrkis, Noah, Elhosni, Meriem, Turati, Florian, Legendre, Franck, Jaquier, Alain, Risi, Sebastian
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. A promising but largely under-explored area is their potential to facilitate human coordination with many agents. Such capabilities would be useful in domains
Externí odkaz:
http://arxiv.org/abs/2412.11761
Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to costly denoisi
Externí odkaz:
http://arxiv.org/abs/2412.10855
Gaussian Process Latent Variable Models (GPLVMs) have proven effective in capturing complex, high-dimensional data through lower-dimensional representations. Recent advances show that using Riemannian manifolds as latent spaces provides more flexibil
Externí odkaz:
http://arxiv.org/abs/2410.20850
By incorporating physical consistency as inductive bias, deep neural networks display increased generalization capabilities and data efficiency in learning nonlinear dynamic models. However, the complexity of these models generally increases with the
Externí odkaz:
http://arxiv.org/abs/2410.18868
Autor:
Mostowsky, Peter, Dutordoir, Vincent, Azangulov, Iskander, Jaquier, Noémie, Hutchinson, Michael John, Ravuri, Aditya, Rozo, Leonel, Terenin, Alexander, Borovitskiy, Viacheslav
Kernels are a fundamental technical primitive in machine learning. In recent years, kernel-based methods such as Gaussian processes are becoming increasingly important in applications where quantifying uncertainty is of key interest. In settings that
Externí odkaz:
http://arxiv.org/abs/2407.08086
We introduce Riemannian Flow Matching Policies (RFMP), a novel model for learning and synthesizing robot visuomotor policies. RFMP leverages the efficient training and inference capabilities of flow matching methods. By design, RFMP inherits the stre
Externí odkaz:
http://arxiv.org/abs/2403.10672
Visual imitation learning has achieved impressive progress in learning unimanual manipulation tasks from a small set of visual observations, thanks to the latest advances in computer vision. However, learning bimanual coordination strategies and comp
Externí odkaz:
http://arxiv.org/abs/2403.03270
Autor:
Daab, Tilman, Jaquier, Noémie, Dreher, Christian, Meixner, Andre, Krebs, Franziska, Asfour, Tamim
Movement primitives (MPs) are compact representations of robot skills that can be learned from demonstrations and combined into complex behaviors. However, merely equipping robots with a fixed set of innate MPs is insufficient to deploy them in dynam
Externí odkaz:
http://arxiv.org/abs/2312.08030
Autor:
Jaquier, Noémie, Welle, Michael C., Gams, Andrej, Yao, Kunpeng, Fichera, Bernardo, Billard, Aude, Ude, Aleš, Asfour, Tamim, Kragic, Danica
Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied agents. The core concept -- reusing prior knowledge to learn in and from novel situations -- is successfully leveraged by humans to handle novel situations
Externí odkaz:
http://arxiv.org/abs/2311.18044
In the realm of robotics, numerous downstream robotics tasks leverage machine learning methods for processing, modeling, or synthesizing data. Often, this data comprises variables that inherently carry geometric constraints, such as the unit-norm con
Externí odkaz:
http://arxiv.org/abs/2310.07902