Zobrazeno 1 - 10
of 1 173
pro vyhledávání: '"P. Posa"'
Autor:
Yang, William, Posa, Michael
Non-prehensile manipulation enables fast interactions with objects by circumventing the need to grasp and ungrasp as well as handling objects that cannot be grasped through force closure. Current approaches to non-prehensile manipulation focus on sta
Externí odkaz:
http://arxiv.org/abs/2405.08731
Autor:
Schmid, S. W., Pósa, L., Török, T. N., Sánta, B., Pollner, Z., Molnár, G., Horst, Y., Volk, J., Leuthold, J., Halbritter, A., Csontos, M.
Publikováno v:
ACS Nano 2024, 18, 21966-21974
Beyond-Moore computing technologies are expected to provide a sustainable alternative to the von Neumann approach not only due to their down-scaling potential but also via exploiting device-level functional complexity at the lowest possible energy co
Externí odkaz:
http://arxiv.org/abs/2403.13530
Robotic manipulation can greatly benefit from the data efficiency, robustness, and predictability of model-based methods if robots can quickly generate models of novel objects they encounter. This is especially difficult when effects like complex joi
Externí odkaz:
http://arxiv.org/abs/2310.12054
The hybrid nature of multi-contact robotic systems, due to making and breaking contact with the environment, creates significant challenges for high-quality control. Existing model-based methods typically rely on either good prior knowledge of the mu
Externí odkaz:
http://arxiv.org/abs/2310.09893
Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement learning, on
Externí odkaz:
http://arxiv.org/abs/2310.09873
Autor:
Bui, Hien, Posa, Michael
In contact-rich tasks, the hybrid, multi-modal nature of contact dynamics poses great challenges in model representation, planning, and control. Recent efforts have attempted to address these challenges via data-driven methods, learning dynamical mod
Externí odkaz:
http://arxiv.org/abs/2310.09714
Autor:
Acosta, Brian, Posa, Michael
Bipedal robots promise the ability to traverse rough terrain quickly and efficiently, and indeed, humanoid robots can now use strong ankles and careful foot placement to traverse discontinuous terrain. However, more agile underactuated bipeds have sm
Externí odkaz:
http://arxiv.org/abs/2309.07993
This work presents an instance-agnostic learning framework that fuses vision with dynamics to simultaneously learn shape, pose trajectories, and physical properties via the use of geometry as a shared representation. Unlike many contact learning appr
Externí odkaz:
http://arxiv.org/abs/2309.05832
Autor:
Molnár, Dániel, Török, Tímea Nóra, Kövecs, Roland, Pósa, László, Balázs, Péter, Molnár, György, Olalla, Nadia Jimenez, Leuthold, Juerg, Volk, János, Csontos, Miklós, Halbritter, András
Analog tunable memristors are widely utilized as artificial synapses in various neural network applications. However, exploiting the dynamical aspects of their conductance change to implement active neurons is still in its infancy, awaiting the reali
Externí odkaz:
http://arxiv.org/abs/2307.13320
The formation and dissolution of silver nanowires plays a fundamental role in a broad range of resistive switching devices, fundamentally relying on the electrochemical metallization phenomenon. It was shown, however, that resistive switching may als
Externí odkaz:
http://arxiv.org/abs/2306.05736