Zobrazeno 41 - 50
of 1 946
pro vyhledávání: '"Rodriguez, Alberto"'
Autor:
Pérez-Úbeda, María José, Arribas, Pedro, Gimeno García-Andrade, M. Dolores, Garvín, Lucía, Rodríguez, Alberto, Ponz, Virginia, Ballester, Sandra, Fernández, Sergio, Fuentes-Ferrer, Manuel, Ascaso, Ana, Portolés-Pérez, Antonio, Marco, Fernando
Publikováno v:
In Arthroscopy: The Journal of Arthroscopic and Related Surgery February 2024 40(2):305-317
Multi-stage forceful manipulation tasks, such as twisting a nut on a bolt, require reasoning over interlocking constraints over discrete as well as continuous choices. The robot must choose a sequence of discrete actions, or strategy, such as whether
Externí odkaz:
http://arxiv.org/abs/2101.02679
We present the design, implementation, and evaluation of RF-Grasp, a robotic system that can grasp fully-occluded objects in unknown and unstructured environments. Unlike prior systems that are constrained by the line-of-sight perception of vision an
Externí odkaz:
http://arxiv.org/abs/2012.15436
Autor:
Yen-Chen, Lin, Florence, Pete, Barron, Jonathan T., Rodriguez, Alberto, Isola, Phillip, Lin, Tsung-Yi
We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of view synthesis - synthesizing photorealistic novel views of real-worl
Externí odkaz:
http://arxiv.org/abs/2012.05877
In this paper, we present an approach to tactile pose estimation from the first touch for known objects. First, we create an object-agnostic map from real tactile observations to contact shapes. Next, for a new object with known geometry, we learn a
Externí odkaz:
http://arxiv.org/abs/2012.05205
Publikováno v:
In Journal of Energy Storage 1 December 2023 73 Part A
Autor:
Simeonov, Anthony, Du, Yilun, Kim, Beomjoon, Hogan, Francois R., Tenenbaum, Joshua, Agrawal, Pulkit, Rodriguez, Alberto
We present a framework for solving long-horizon planning problems involving manipulation of rigid objects that operates directly from a point-cloud observation, i.e. without prior object models. Our method plans in the space of object subgoals and fr
Externí odkaz:
http://arxiv.org/abs/2011.08177
Autor:
Suresh, Sudharshan, Bauza, Maria, Yu, Kuan-Ting, Mangelson, Joshua G., Rodriguez, Alberto, Kaess, Michael
Tactile perception is central to robot manipulation in unstructured environments. However, it requires contact, and a mature implementation must infer object models while also accounting for the motion induced by the interaction. In this work, we pre
Externí odkaz:
http://arxiv.org/abs/2011.07044
Publikováno v:
Phys. Rev. Lett. 126, 150601 (2021)
We identify the chaotic phase of the Bose-Hubbard Hamiltonian by the energy-resolved correlation between spectral features and structural changes of the associated eigenstates as exposed by their generalized fractal dimensions. The eigenvectors are s
Externí odkaz:
http://arxiv.org/abs/2009.05295
The ability to simulate and predict the outcome of contacts is paramount to the successful execution of many robotic tasks. Simulators are powerful tools for the design of robots and their behaviors, yet the discrepancy between their predictions and
Externí odkaz:
http://arxiv.org/abs/2009.03994