Zobrazeno 1 - 10
of 159
pro vyhledávání: '"ZHU Xupeng"'
Autor:
Dai Peng, Sun Kai, Yan Xingzhao, Muskens Otto L., de Groot C. H. (Kees), Zhu Xupeng, Hu Yueqiang, Duan Huigao, Huang Ruomeng
Publikováno v:
Nanophotonics, Vol 11, Iss 13, Pp 3057-3069 (2022)
The “one-to-many” problem is a typical challenge that faced by many machine learning aided inverse nanophotonics designs where one target optical response can be achieved by many solutions (designs). Although novel training approaches, such as ta
Externí odkaz:
https://doaj.org/article/ac613e1fdb1a4e19be33a95052799677
Autor:
Qian, Yaoyao, Zhu, Xupeng, Biza, Ondrej, Jiang, Shuo, Zhao, Linfeng, Huang, Haojie, Qi, Yu, Platt, Robert
Robotic grasping in cluttered environments remains a significant challenge due to occlusions and complex object arrangements. We have developed ThinkGrasp, a plug-and-play vision-language grasping system that makes use of GPT-4o's advanced contextual
Externí odkaz:
http://arxiv.org/abs/2407.11298
Autor:
Hu, Boce, Zhu, Xupeng, Wang, Dian, Dong, Zihao, Huang, Haojie, Wang, Chenghao, Walters, Robin, Platt, Robert
While grasp detection is an important part of any robotic manipulation pipeline, reliable and accurate grasp detection in $SE(3)$ remains a research challenge. Many robotics applications in unstructured environments such as the home or warehouse woul
Externí odkaz:
http://arxiv.org/abs/2407.03531
Many complex robotic manipulation tasks can be decomposed as a sequence of pick and place actions. Training a robotic agent to learn this sequence over many different starting conditions typically requires many iterations or demonstrations, especiall
Externí odkaz:
http://arxiv.org/abs/2401.12046
Autor:
Zhao, Linfeng, Howell, Owen, Park, Jung Yeon, Zhu, Xupeng, Walters, Robin, Wong, Lawson L. S.
In robotic tasks, changes in reference frames typically do not influence the underlying physical properties of the system, which has been known as invariance of physical laws.These changes, which preserve distance, encompass isometric transformations
Externí odkaz:
http://arxiv.org/abs/2307.08226
Real-world grasp detection is challenging due to the stochasticity in grasp dynamics and the noise in hardware. Ideally, the system would adapt to the real world by training directly on physical systems. However, this is generally difficult due to th
Externí odkaz:
http://arxiv.org/abs/2306.06489
Autor:
Wang, Dian, Zhu, Xupeng, Park, Jung Yeon, Jia, Mingxi, Su, Guanang, Platt, Robert, Walters, Robin
Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivariant neural network. A missing p
Externí odkaz:
http://arxiv.org/abs/2303.04745
Autor:
Jia, Mingxi, Wang, Dian, Su, Guanang, Klee, David, Zhu, Xupeng, Walters, Robin, Platt, Robert
In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning ta
Externí odkaz:
http://arxiv.org/abs/2211.00194
Given point cloud input, the problem of 6-DoF grasp pose detection is to identify a set of hand poses in SE(3) from which an object can be successfully grasped. This important problem has many practical applications. Here we propose a novel method an
Externí odkaz:
http://arxiv.org/abs/2211.00191
We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path planning p
Externí odkaz:
http://arxiv.org/abs/2206.03674