Zobrazeno 1 - 10
of 465
pro vyhledávání: '"YANG, BRIAN"'
Autor:
Villaflor, Adam, Yang, Brian, Su, Huangyuan, Fragkiadaki, Katerina, Dolan, John, Schneider, Jeff
Significant progress has been made in training multimodal trajectory forecasting models for autonomous driving. However, effectively integrating these models with downstream planners and model-based control approaches is still an open problem. Althou
Externí odkaz:
http://arxiv.org/abs/2403.07232
Autor:
Yang, Brian, Su, Huangyuan, Gkanatsios, Nikolaos, Ke, Tsung-Wei, Jain, Ayush, Schneider, Jeff, Fragkiadaki, Katerina
Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward functi
Externí odkaz:
http://arxiv.org/abs/2402.06559
Autor:
Yang, Brian
Within the Schottky problem, the study of special subvarieties of the Torelli locus has long been of great interest. We present a criterion for a dimension $0$ subvariety of the Torelli locus, arising from a $G$-Galois cover of $\mathbb{P}^1$ branche
Externí odkaz:
http://arxiv.org/abs/2304.04557
Autor:
Sun, Charles, Orbik, Jędrzej, Devin, Coline, Yang, Brian, Gupta, Abhishek, Berseth, Glen, Levine, Sergey
We study how robots can autonomously learn skills that require a combination of navigation and grasping. While reinforcement learning in principle provides for automated robotic skill learning, in practice reinforcement learning in the real world is
Externí odkaz:
http://arxiv.org/abs/2107.13545
Autor:
Haeberle, Heather S., DeFrancesco, Christopher J., Yang, Brian W., Victoria, Christian, Wolfe, Scott W.
Publikováno v:
In Journal of Hand Surgery April 2024 49(4):329-336
Autor:
Lambeta, Mike, Chou, Po-Wei, Tian, Stephen, Yang, Brian, Maloon, Benjamin, Most, Victoria Rose, Stroud, Dave, Santos, Raymond, Byagowi, Ahmad, Kammerer, Gregg, Jayaraman, Dinesh, Calandra, Roberto
Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics. One of the contributing factors that limit current robotic manipulation systems is the difficulty of precisely sensing contact force
Externí odkaz:
http://arxiv.org/abs/2005.14679
Existing approaches for visuomotor robotic control typically require characterizing the robot in advance by calibrating the camera or performing system identification. We propose MAVRIC, an approach that works with minimal prior knowledge of the robo
Externí odkaz:
http://arxiv.org/abs/1912.13360
Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic learning would also benefit from benchmarking, and
Externí odkaz:
http://arxiv.org/abs/1905.07447
Autor:
Liao, Thomas, Wang, Grant, Yang, Brian, Lee, Rene, Pister, Kristofer, Levine, Sergey, Calandra, Roberto
Robot design is often a slow and difficult process requiring the iterative construction and testing of prototypes, with the goal of sequentially optimizing the design. For most robots, this process is further complicated by the need, when validating
Externí odkaz:
http://arxiv.org/abs/1905.01334
We report the phenomenon of coherent super decay, where a linear sum of several damped oscillators can collectively decay much faster than the individual ones in the first stage, followed by stagnating ones after more than 90 percent of the energy ha
Externí odkaz:
http://arxiv.org/abs/1811.08621