Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Xu, Danfei"'
Autor:
Xue, Shangjie, Dill, Jesse, Mathur, Pranay, Dellaert, Frank, Tsiotras, Panagiotis, Xu, Danfei
This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable
Externí odkaz:
http://arxiv.org/abs/2406.06948
Task and Motion Planning (TAMP) integrates high-level task planning and low-level motion planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic tasks. Optimization-based TAMP focuses on hybrid optimization approac
Externí odkaz:
http://arxiv.org/abs/2404.02817
Autor:
Fan, Zhiwen, Cong, Wenyan, Wen, Kairun, Wang, Kevin, Zhang, Jian, Ding, Xinghao, Xu, Danfei, Ivanovic, Boris, Pavone, Marco, Pavlakos, Georgios, Wang, Zhangyang, Wang, Yue
While novel view synthesis (NVS) from a sparse set of images has advanced significantly in 3D computer vision, it relies on precise initial estimation of camera parameters using Structure-from-Motion (SfM). For instance, the recently developed Gaussi
Externí odkaz:
http://arxiv.org/abs/2403.20309
Autor:
Yang, Jiawei, Ivanovic, Boris, Litany, Or, Weng, Xinshuo, Kim, Seung Wook, Li, Boyi, Che, Tong, Xu, Danfei, Fidler, Sanja, Pavone, Marco, Wang, Yue
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootst
Externí odkaz:
http://arxiv.org/abs/2311.02077
Solving complex manipulation tasks in household and factory settings remains challenging due to long-horizon reasoning, fine-grained interactions, and broad object and scene diversity. Learning skills from demonstrations can be an effective strategy,
Externí odkaz:
http://arxiv.org/abs/2311.01530
Offline Imitation Learning (IL) is a powerful paradigm to learn visuomotor skills, especially for high-precision manipulation tasks. However, IL methods are prone to spurious correlation - expressive models may focus on distractors that are irrelevan
Externí odkaz:
http://arxiv.org/abs/2311.01419
We present a learning-based dynamics model for granular material manipulation. Inspired by the Eulerian approach commonly used in fluid dynamics, our method adopts a fully convolutional neural network that operates on a density field-based representa
Externí odkaz:
http://arxiv.org/abs/2311.00802
Imitation learning from human demonstrations can teach robots complex manipulation skills, but is time-consuming and labor intensive. In contrast, Task and Motion Planning (TAMP) systems are automated and excel at solving long-horizon tasks, but they
Externí odkaz:
http://arxiv.org/abs/2310.16014
Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some demonstrations, whi
Externí odkaz:
http://arxiv.org/abs/2310.14196
Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However, such metho
Externí odkaz:
http://arxiv.org/abs/2401.03360