Neuphysics: Editable neural geometry and physics from monocular videos

YL Qiao, A Gao, M Lin - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We present a method for learning 3D geometry and physics parameters of a dynamic scene
from only a monocular RGB video input. To decouple the learning of underlying scene …

Learning quadruped locomotion using differentiable simulation

Y Song, S Kim, D Scaramuzza - arxiv preprint arxiv:2403.14864, 2024 - arxiv.org
This work explores the potential of using differentiable simulation for learning quadruped
locomotion. Differentiable simulation promises fast convergence and stable training by …

Roboninja: Learning an adaptive cutting policy for multi-material objects

Z Xu, Z **an, X Lin, C Chi, Z Huang, C Gan… - arxiv preprint arxiv …, 2023 - arxiv.org
We introduce RoboNinja, a learning-based cutting system for multi-material objects (ie, soft
objects with rigid cores such as avocados or mangos). In contrast to prior works using open …